System

Abstract

To provide a system for automatically generating an optimum training plan by accurately evaluating the aroma sensitivity of each patient.SOLUTION: A specific processing part 290 of a data processor 12 in the system evaluates the aroma sensitivity of a patient by using a generation model, designs an individual aroma training session on the basis of the evaluation, collects data during training, selects an aroma on the basis of the data, constructs a prediction model related to a specific aroma, and predicts progress to improvement.SELECTED DRAWING: Figure 2

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] Olfactory impairment caused by COVID-19 infection is a serious problem that reduces the quality of life for many patients. Conventional olfactory training relies on subjective assessment and has limited effectiveness. For this reason, more objective and individualized olfactory training methods are needed. Specifically, it is necessary to develop a system that can accurately evaluate each patient's scent sensitivity and automatically generate an optimal training plan. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a means for assessing a patient's scent sensitivity using a generative model, a means for designing individualized scent training sessions based on the assessment, a means for collecting data during training and selecting scents based on the data, and a means for building a predictive model related to specific scents and predicting progress toward improvement. Specifically, by using AI technology to individualize olfactory training, the system objectively evaluates each patient's olfactory sensitivity and optimizes the training content. Furthermore, the system selects scents to train based on the collected data, monitors progress using a predictive model, and improves the effectiveness of the training. This allows patients to rapidly recover their sense of smell and taste and return to a healthy lifestyle.

[0006] Below are definitions of important terms included in the claims.

[0007] A "generative model" is an algorithm that extracts patterns and features from a given dataset and uses them to generate new data or analytical results.

[0008] "Patient" refers to a person with a particular medical or health problem who is the recipient of treatment or training.

[0009] "Scent sensitivity" refers to the degree of ability to recognize or distinguish a particular scent when smelling it.

[0010] "Evaluation" refers to the process of judging the status or performance of an individual or object based on specific criteria or standards.

[0011] "Training Session" means a time or period during which a series of drills or exercises designed for a specific purpose are performed.

[0012] "Data collection" refers to the process of gathering data through observation or measurement to obtain specific information.

[0013] A "predictive model" refers to an algorithm or calculation method that predicts future states or outcomes based on past data.

[0014] "Session design" refers to the process of planning and structuring the content and sequence of training or activities according to a specific purpose.

[0015] "Progress" refers to the degree to which a particular goal has been achieved or the degree of change or improvement over time.

[0016] "Optimization" refers to adjusting and improving a system or process to best achieve a specific objective. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention relates to a system that uses a generative model to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0039] System Overview

[0040] The system works in the following steps:

[0041] 1. User registration and initial evaluation

[0042] 2. Personalized scent selection

[0043] 3. Progress prediction and training optimization using predictive models

[0044] Specific explanation of the system's operation

[0045] 1. User registration and initial evaluation

[0046] 1. The user downloads and installs the app. They then enter their personal information to create an account. This information is then stored on the server.

[0047] 2. As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability.

[0048] 3. The device sends this evaluation data to the server, which analyzes it using a generative model to evaluate the user's initial olfactory sensitivity.

[0049] 4. Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0050] 2. Personalized scent selection

[0051] 5. The user follows the training plan and smells the designated scents periodically, inputting feedback into the device about the perceived strength and the degree of scent identification.

[0052] 6. The device sends this feedback data to the server, which continuously collects and analyzes this data.

[0053] 7. Based on the above analytical data, the server selects the scent that best suits the user's olfactory sensitivity and reflects it in the next training session.

[0054] 3. Progress prediction and training optimization using predictive models

[0055] 8. The server uses the generative model to predict the user's progress based on the collected feedback data.

[0056] 9. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may optimize the plan by adding a different scent.

[0057] 10. The device will notify the user of the new training plan and continue training according to its contents.

[0058] Specific examples

[0059] Case 1: User A's initial registration and training start

[0060] User A installs the app and performs a scent evaluation test. For example, he smells lemon and rose scents and enters his sensitivity to each scent into his device.

[0061] The server analyzes this data and finds that User A is particularly sensitive to citrus scents.

[0062] The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[0063] Case 2: Progress forecast and training plan updates

[0064] The server analyzes the training feedback entered by user A and predicts that sensitivity is improving.

[0065] The server generates a new training plan, which includes adding a rose scent to further test the sensitivity, etc.

[0066] The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[0067] The above is a specific embodiment of the present invention. This system enables patients with olfactory impairment as a result of COVID-19 to quickly and effectively recover their sense of smell by receiving personalized training.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] Users download and install a dedicated app, enter their personal information, and create an account. This information is stored on the server.

[0071] Step 2:

[0072] The device displays an interface for an initial olfactory evaluation test to the user, who then smells multiple scent samples and fills out a form to evaluate their sensitivity and discrimination ability.

[0073] Step 3:

[0074] The device sends the evaluation data entered by the user to the server, which then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[0075] Step 4:

[0076] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0077] Step 5:

[0078] The device displays an initial training plan to the user, who then follows the plan and periodically smells the designated scent.

[0079] Step 6:

[0080] After each training session, the user inputs feedback into the device about the strength of the scents they perceived and their ability to identify them.

[0081] Step 7:

[0082] The terminal collects the feedback data entered by the user and transmits it to the server.

[0083] Step 8:

[0084] The server continuously collects and analyzes this data, and based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session.

[0085] Step 9:

[0086] The server uses a generative model to predict the user's progress based on the collected feedback data.

[0087] Step 10:

[0088] The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may add a different scent to optimize the training plan.

[0089] Step 11:

[0090] The device notifies the user of the new training plan and continues training according to its contents.

[0091] Step 12:

[0092] The user continues training according to the new training plan, and feedback is again entered into the device and sent to the server.

[0093] Step 13:

[0094] The server continuously analyzes the feedback data and updates and optimizes the training plan as needed.

[0095] Example 1

[0096] 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."

[0097] Conventional olfactory training systems lack the ability to properly evaluate individual users' scent sensitivity and dynamically optimize training plans based on their progress. This means that they are unable to provide effective training tailored to the progression and recovery rate of each user's olfactory disorder. Furthermore, they are unable to collect and analyze real-time feedback data, which makes it difficult to maximize the effectiveness of training.

[0098] 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.

[0099] In this invention, the server includes means for user registration and personal information input, means for collecting sensitivity evaluation data for multiple scent samples as an initial evaluation, means for analyzing the collected initial evaluation data and evaluating the user's initial olfactory sensitivity using a generative model, means for generating an individualized initial training plan based on the analysis results, means for continuously collecting training feedback data and selecting the scent most suitable for the user's olfactory sensitivity using the generative model, and means for predicting progress based on the collected feedback data and optimizing the training plan. This enables individually customized olfactory training and enables effective training tailored to each user's progress. Furthermore, real-time data collection and analysis can maximize the effectiveness of training.

[0100] A "user" is a subject who receives individual olfactory training using this system.

[0101] The "server" is a central control unit that stores and analyzes data sent by users and provides generated training plans to users.

[0102] A "terminal" is a device on which a user installs an app and uses it to input data and provide feedback.

[0103] A "generative model" is an artificial intelligence algorithm that analyzes collected data to assess a user's olfactory sensitivity and generate an optimal training plan.

[0104] "Scent Samples" refers to multiple different scents that a user uses to evaluate and train their sense of smell.

[0105] "Feedback data" refers to data regarding scent strength and discrimination that is input by the user after a training session.

[0106] A "training plan" is a personalized training regimen that uses specific scents based on the user's olfactory sensitivity.

[0107] "Progress" is an indicator that indicates how much the user's olfactory sensitivity has improved through training.

[0108] The "analysis result" is an assessment of the user's olfactory sensitivity resulting from data processed by the generative model.

[0109] "Scent selection" is the process of determining the optimal scent to use in the next training session based on analytical data.

[0110] This invention relates to a system that uses a generative model to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0111] System configuration and technologies used

[0112] This system consists of a user, a server, and a terminal. The server is responsible for storing and analyzing data, running the generative model, and generating and managing training plans. Specifically, it uses generative AI models such as OpenAI's GPT-3. The terminal is a device, such as a smartphone or tablet, through which the user inputs data and provides feedback.

[0113] System Operation

[0114] User registration and initial evaluation

[0115] The user downloads and installs a dedicated app. They then enter their personal information and create an account. As an initial assessment, the user smells multiple scent samples and fills out a form on their device to evaluate their sensitivity and discrimination ability. The device then sends this evaluation data to a server. The server then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity. Based on the analysis results, the server generates a personalized initial training plan and sends it to the device.

[0116] Personalized scent selection

[0117] The user follows a training plan and periodically smells designated scents. They then input feedback into the device about the perceived strength and ability to distinguish the scents. The device then sends this feedback data to the server, which continuously collects and analyzes this data. Based on the analyzed data, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session.

[0118] Predictive models for predicting progress and optimizing training

[0119] The server uses a generative model to predict the user's progress based on the collected feedback data. The server then updates the training plan based on the prediction results. For example, if the user's sensitivity improves, the server may optimize the training by adding a different scent. The device then notifies the user of the new training plan and allows them to continue training according to the plan's contents.

[0120] Specific examples

[0121] Case 1: User A's initial registration and training start

[0122] User A installs the app and creates an account by entering personal information. Next, he or she smells lemon and rose scent samples and enters their sensitivity to each into the device. The device sends the evaluation data to the server, which analyzes it using a generative AI model. The server determines that User A has a low sensitivity to citrus scents and creates an initial training plan using citrus scents. User A follows this plan and begins training by smelling citrus scents every day.

[0123] Case 2: Progress forecast and training plan updates

[0124] The server analyzes the training feedback entered by User A and predicts that sensitivity has improved. The server generates a new training plan. This plan includes adding a rose-like scent to further check sensitivity. The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[0125] The above is a specific embodiment of the present invention. This system enables users with olfactory impairment to quickly and effectively recover their sense of smell by receiving personalized training.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1:

[0128] The user downloads and installs a dedicated app. The input is the download and installation process from the Apple App Store or Google Play Store. The output is the installation of the app on the device. Specifically, the user searches for the app in the device's store and taps the install button.

[0129] Step 2:

[0130] A user creates an account by entering personal information. The input includes personal information such as name, age, and gender, which are entered into the account creation form. The output is that the personal information is saved on the server and the account is created. Specifically, the user enters the required information on the initial setup screen of the app and taps the submit button.

[0131] Step 3:

[0132] As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability. The input is the perceived strength and discrimination of the scent samples, which are entered into the evaluation form. The output is evaluation data generated. In concrete terms, the user smells the provided scent samples and enters their evaluation as a number or comment on the app.

[0133] Step 4:

[0134] The terminal sends initial evaluation data to the server. The input is the evaluation data entered by the user, and the output is received and stored by the server. In concrete terms, the terminal runs a process in the background to transmit the evaluation data over the network.

[0135] Step 5:

[0136] The server uses a generative model to analyze the initial evaluation data and evaluate the user's initial olfactory sensitivity. The input is the evaluation data, and the output is the analysis result. Specifically, the server calls a generative AI model (e.g., GPT-3) and performs data analysis based on the input data.

[0137] Step 6:

[0138] The server generates an individualized initial training plan based on the analysis results and sends it to the device. The input is the analysis results, and the training plan is generated as the output. Specifically, the server creates an optimal training plan using an AI model based on the analysis results and sends this plan to the device.

[0139] Step 7:

[0140] The user follows a training plan and smells designated scents periodically. The training plan is the input, and user feedback data is generated as the output. Specifically, the user follows the app's instructions to smell the designated scents and enters their perceived strength and discrimination into a form.

[0141] Step 8:

[0142] The terminal sends feedback data to the server. The input is the user's feedback data, and the output is the server receiving and storing the data. In concrete terms, the terminal runs a process of sending feedback data over the network in the background.

[0143] Step 9:

[0144] The server analyzes the feedback data, evaluates the user's olfactory sensitivity using a generative model, and selects the optimal scent. The input is the feedback data, and the output is the optimal scent selection result. Specifically, the server calls the generative AI model and performs a reanalysis based on this new data.

[0145] Step 10:

[0146] The server predicts the user's progress and generates a new training plan. The input is the analysis data, and the output is the creation of a new training plan. Specifically, the server analyzes the user's progress data and updates the training plan as necessary.

[0147] Step 11:

[0148] The device notifies the user of the new training plan. The input is the new training plan, and the output is a notification to the user. Specifically, the device notifies the user of the new training plan using a means such as a push notification.

[0149] (Application example 1)

[0150] 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."

[0151] The problem that this invention aims to solve is to provide effective scent training for patients with olfactory impairment after COVID-19 infection. Specifically, it aims to provide a personalized scent training plan for each patient and a method for evaluating and optimizing progress in real time. Another important issue is to incorporate a system with electronic payment functionality, allowing users to easily purchase training fragrances and manage subscriptions.

[0152] 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.

[0153] In this invention, the server includes a means for evaluating a patient's scent sensitivity using a generative model, a means for designing an individual scent training session based on the evaluation, a means for collecting data during training and selecting scents based on the data, and a means for providing electronic payment functionality and managing the purchase and subscription of training fragrances. This maximizes the effect of improving each patient's olfactory disorder, optimizes the progress of the training plan in real time, and allows users to easily purchase the items they need.

[0154] A "generative model" is a model that uses generative AI techniques to generate new data from specific input data.

[0155] "Scent sensitivity assessment" is the process of assessing how sensitive a user is to a particular scent.

[0156] A "training session" is a series of scent training activities designed to improve scent sensitivity.

[0157] An "individual training plan" is a personalized training plan generated based on each user's scent sensitivity.

[0158] "Data collection" is the process of collecting progress and results information entered by users during their workouts.

[0159] "Scent selection" refers to selecting the scent that is best suited to the user based on collected data.

[0160] A "predictive model" is an AI model that uses collected feedback data to predict future outcomes.

[0161] "Electronic Payment Function" means a function that allows users to purchase training materials and manage their subscriptions online.

[0162] A "server" is a computer system that manages the entire system, collects and analyzes data, and provides training plans.

[0163] This invention relates to a system that uses generative models to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. The system consists of a server and a user device (such as a smartphone).

[0164] System Configuration

[0165] This system is centered around a server and implements the following main functions:

[0166] Assessing patients' scent sensitivity using a generative model.

[0167] Design individualized scent training sessions based on the evaluation data.

[0168] Data is collected during training and scents are selected based on the data.

[0169] Build predictive models related to specific scents to forecast progress.

[0170] We provide electronic payment facilities and manage training fragrance purchases and subscriptions.

[0171] Processing procedures and data processing

[0172] The system uses the following major hardware and software components:

[0173] Hardware: Smartphones (e.g., iPhone, Android devices), servers (e.g., AWS, Google Cloud)

[0174] Software: Python, Flask (backend), React Native (frontend), AI libraries for generative models (e.g., TensorFlow, PyTorch)

[0175] User registration and initial evaluation

[0176] The user installs a dedicated application on their smartphone and creates an account by entering their personal information. This information is then stored on the server. As an initial evaluation, the user smells multiple scent samples and enters data evaluating their sensitivity and discrimination ability. The device then sends this evaluation data to the server, which then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[0177] Fragrance selection and training

[0178] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device. The user follows the training plan and smells the designated scents periodically. The user inputs feedback on the strength and discrimination they sensed during the training, which is then sent to the server. The server analyzes the feedback data and selects the scent that is best suited to the next training session based on the user's olfactory sensitivity.

[0179] Progress prediction and training optimization

[0180] Based on the collected feedback data, the server uses a generative model to predict the user's progress and optimizes the training plan accordingly. For example, if the user's sensitivity improves, it may add a different scent. The new training plan is then notified to the device, allowing the user to continue training.

[0181] Electronic payment function

[0182] Purchasing training products and managing subscriptions is done through the app's electronic payment function, allowing users to conveniently purchase the items they need for their training.

[0183] Specific examples

[0184] Case 1: User A's initial registration and training start

[0185] User A installs the app and takes a scent evaluation test. The server analyzes the evaluation data and determines that User A has a low sensitivity to certain scents. The server then creates a training plan using citrus scents and sends it to the device.

[0186] Case 2: Progress forecast and training plan updates

[0187] User A inputs training feedback, and the server analyzes it and determines that sensitivity has improved. A new scent is added to the new training plan, and User A is notified.

[0188] Prompt Sentence Examples

[0189] Below are some example prompts to input to a generative AI model:

[0190] "Generate a personalized olfactory training plan given the user's initial assessment data: {initial_data}."

[0191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0192] Step 1:

[0193] User registration and initial evaluation

[0194] Users download the application and create an account by entering their personal information, such as name, email address, and password. The device sends this data to the server, which stores it in a database.

[0195] Input: User personal information

[0196] Output: Account data is saved on the server

[0197] Specific operation: The user launches the app on their smartphone, enters their personal information into the registration form, and submits it. The server receives the request and stores the information in a database.

[0198] Step 2:

[0199] Initial scent sensitivity assessment

[0200] The user smells multiple scent samples and evaluates their sensitivity and discrimination ability. The device sends the evaluation data entered by the user to the server. The server analyzes this data using a generative model and evaluates the user's initial olfactory sensitivity.

[0201] Input: User-perceived scent evaluation data

[0202] Output: User's initial scent sensitivity evaluation result

[0203] Specific operation: The server inputs the received evaluation data into the generative AI model to obtain analysis results, which are then stored in a database.

[0204] Step 3:

[0205] Designing individual training plans

[0206] The server generates a personalized training plan based on the initial scent sensitivity assessment results, including which scents the user should smell and how often. The server then transmits the generated training plan to the device.

[0207] Input: Initial scent sensitivity evaluation results

[0208] Output: Individual training plan

[0209] Specific operation: The server uses an AI model to create a training plan based on the user's evaluation results and pushes a notification to the device.

[0210] Step 4:

[0211] Conducting scent training and collecting feedback

[0212] The user follows the training plan provided and smells the designated scent periodically. After each training session, the user inputs feedback on the strength and discrimination of the scent they perceived, and the device sends this feedback to the server.

[0213] Input: User feedback data

[0214] Output: Feedback data is saved on the server

[0215] Specific operation: The user trains regularly and enters the results into the app. The device sends the data to the server.

[0216] Step 5:

[0217] Analysis of feedback data and selection of scents

[0218] The server analyzes the collected feedback data to evaluate the user's progress, uses a generative model to select the next scent that best suits the user, and sends a new training plan to the device to reflect the next training session.

[0219] Input: Feedback data

[0220] Output: Updated training plan

[0221] How it works: The server inputs the feedback data into the AI ​​model, selects the optimal scent based on the analysis results, and updates the training plan. The updated plan is then sent to the device.

[0222] Step 6:

[0223] Progress forecast and training plan updates

[0224] The server predicts the user's training progress based on the collected feedback data. A generative model determines how much the user's sense of smell has improved and optimizes the training plan accordingly. The new training plan is then notified to the device.

[0225] Input: Feedback data

[0226] Output: Optimized training plan

[0227] Specific operation: The server updates the predictive model based on the analysis results, generates an optimized training plan, and sends it to the device.

[0228] Step 7:

[0229] Electronic payment function

[0230] Users purchase the training materials and subscriptions they need within the app. The device sends payment information to the server, which processes the payment. Once the purchase is confirmed, it is reflected in the user's account.

[0231] Input: User's payment information

[0232] Output: Payment completion notification and purchase items reflected in your account

[0233] Specific operation: The user makes a purchase through the app, and the device sends the payment information to the server. The server processes the payment and notifies the user of the result.

[0234] 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.

[0235] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0236] System Overview

[0237] The system works in the following steps:

[0238] 1. User registration and initial evaluation

[0239] 2. Personalized scent selection and emotion recognition

[0240] 3. Progress prediction and training optimization using predictive models

[0241] Specific explanation of the system's operation

[0242] 1. User registration and initial evaluation

[0243] 1. The user downloads and installs the app. They then enter their personal information to create an account. This information is then stored on the server.

[0244] 2. As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability.

[0245] 3. The device sends this evaluation data to the server, which analyzes it using a generative model to evaluate the user's initial olfactory sensitivity.

[0246] 4. Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0247] 2. Personalized scent selection and emotion recognition

[0248] 5. The user follows the training plan and smells the designated scents periodically, inputting feedback into the device about the perceived strength and the degree of scent identification.

[0249] 6. The device collects the user's emotional data during training using an emotion engine that also recognizes the user's emotional state.

[0250] 7. Analyze the user's training feedback and emotional data to adjust the training plan. For example, if the user is feeling stressed, a relaxing scent will be selected.

[0251] 8. The device sends this feedback data and emotion data to the server, which continuously collects and analyzes this data.

[0252] 9. Based on the above analytical data, the server selects the scent that best suits the user's olfactory sensitivity and reflects it in the next training session.

[0253] 3. Progress prediction and training optimization using predictive models

[0254] 10. The server uses a generative model to predict the user's progress based on the collected feedback data and emotion data.

[0255] 11. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may optimize the training plan by adding a different scent.

[0256] 12. We can also tailor workout content and timing based on emotional data. For example, we can recommend workouts for times when the user is relaxed.

[0257] 13. The device will notify the user of the new training plan and continue training according to its contents.

[0258] Specific examples

[0259] Case 1: User A's initial registration and training start

[0260] User A installs the app and takes a scent evaluation test and an emotion recognition test. For example, he or she smells lemon and rose and inputs their sensitivity to each scent into the device. At the same time, the emotion engine recognizes User A's emotional state (e.g., relaxed, stressed, etc.).

[0261] The server analyzes this data and determines that User A has a low sensitivity to citrus scents and is in a relaxed state.

[0262] The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[0263] Case 2: Progress forecast and training plan updates

[0264] The server analyzes the training feedback and emotional data entered by user A and predicts that sensitivity is improving and that there are times when the user feels stressed.

[0265] The server generates a new training plan, which includes adding a rose scent and recommending training at times that are relaxing.

[0266] The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[0267] The above is a specific embodiment of the present invention. This system allows patients with olfactory impairment as a result of COVID-19 to receive personalized training, quickly and effectively recovering their sense of smell, and further maximizes the effectiveness of the training by taking into account their emotional state.

[0268] The processing flow will be explained below.

[0269] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0270] Specific explanation of the system's operation

[0271] Step 1:

[0272] The user downloads and installs a dedicated app, enters personal information, and creates an account. This information is stored on the server.

[0273] Step 2:

[0274] The device displays interfaces for an initial olfactory assessment test and an emotion recognition test to the user. In the initial olfactory assessment test, the user smells multiple scent samples and fills out a form to evaluate their sensitivity and discrimination ability. In the emotion recognition test, the emotion engine detects and evaluates the user's emotional state from their face and voice.

[0275] Step 3:

[0276] The device transmits the olfactory evaluation data and emotional data entered by the user to the server, which then analyzes these data using a generative model to evaluate the user's initial olfactory sensitivity and emotional state.

[0277] Step 4:

[0278] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0279] Step 5:

[0280] The device displays an initial training plan to the user, who then follows the plan and periodically smells the designated scent.

[0281] Step 6:

[0282] After each training session, the user inputs feedback into the device about the strength and discrimination of the scents they perceived, and the emotion engine also records the user's emotional state during the training session.

[0283] Step 7:

[0284] The device collects feedback data and emotion data from the user and transmits it to the server.

[0285] Step 8:

[0286] The server continuously collects this data and analyzes it using a generative model. Based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and applies it to the next training session. It also takes into account the collected emotional data and adjusts the content and timing of the training.

[0287] Step 9:

[0288] The server uses a generative model to predict the user's progress based on the collected feedback and emotion data. For example, if the user's sensitivity to a particular scent improves, another scent will be added.

[0289] Step 10:

[0290] The server updates the training plan based on the prediction results and emotion data, for example, by generating a plan that recommends training during times when the user is relaxed.

[0291] Step 11:

[0292] The device notifies the user of the new training plan and continues training according to its contents.

[0293] Step 12:

[0294] The user continues training according to the new training plan, and feedback is again entered into the device, with the emotional state also being recorded by the emotion engine.

[0295] Step 13:

[0296] The server continuously analyzes the feedback data and emotional data, updating and optimizing the training plan as needed. By repeating this process, the user can efficiently recover their sense of smell.

[0297] The above is a specific embodiment of the present invention. This system allows patients with olfactory disorders to receive personalized training to quickly and effectively restore their sense of smell, and further maximizes the effectiveness of the training by taking into account their emotional state.

[0298] Example 2

[0299] 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."

[0300] There is a need for effective and personalized scent training for patients suffering from olfactory impairment after COVID-19 infection. Conventional methods have limited training effectiveness because they do not take into account the patient's emotional state, and there are also challenges in predicting progress and optimizing training plans. The present invention aims to comprehensively solve these challenges.

[0301] The identification processing 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 evaluating the patient's scent sensitivity using a generative model, means for designing an individual scent training session based on the evaluation, means for collecting feedback and emotional data during training and selecting scents based on the data, means for building a predictive model related to specific scents and predicting progress toward improvement, and means for adjusting the training plan based on the emotional data. This enables individualized training according to each patient's olfactory sensitivity and emotional state, maximizing the effectiveness of the training.

[0302] A "generative model" is an algorithm that learns specific patterns or features from data and generates or analyzes new data.

[0303] "Scent sensitivity" refers to the strength and ability of an individual to distinguish a particular scent.

[0304] A "training session" refers to a series of scent sniffing trials conducted under specific instructions.

[0305] "Feedback data" refers to information regarding the strength and discrimination of scents felt by the user during training.

[0306] "Emotional Data" means data regarding the emotional state exhibited by a user during training.

[0307] A "predictive model" is an algorithm that uses past data to predict future developments and outcomes.

[0308] A "training plan" is a plan that shows specific training procedures and schedules designed based on the user's progress and condition.

[0309] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0310] User registration and initial evaluation

[0311] The user downloads and installs a dedicated app. They then enter their personal information and create an account. This information is stored on the server. Then, as an initial assessment, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability. For example, the user might enter their sensitivity to lemon or rose scents as "Strength 3, Discrimination Level 4." The device then sends this evaluation data to the server. The server analyzes this data using a generative AI model to evaluate the user's initial olfactory sensitivity. Based on the analysis results, the server generates a personalized initial training plan and sends it to the device.

[0312] Personalized scent selection and emotion recognition

[0313] The user follows a training plan and periodically smells designated scents. The user then inputs feedback into the device about the perceived strength and scent discrimination. For example, "Rose scent: strength 2, discrimination 3." The device uses an emotion engine that also recognizes the user's emotional state to collect emotional data about the user during training. For example, "relaxed" or "stressed." This feedback and emotional data is sent from the device to a server, which continuously collects and analyzes this data. Based on the analyzed data, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session. For example, if the user is feeling stressed, a scent with a relaxing effect will be selected.

[0314] Predictive models for predicting progress and optimizing training

[0315] The server uses a generative model to predict the user's progress based on the collected feedback data and emotional data. For example, it estimates changes in olfactory sensitivity. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it performs optimization such as adding a new scent. The server also adjusts the training content and timing based on the emotional data. For example, it could recommend training during times when the user is relaxed. The device notifies the user of the new training plan and allows them to continue training according to the plan's contents.

[0316] Specific operation example

[0317] Case 1: User A's initial evaluation and training begins

[0318] User A installs the app and takes a scent evaluation test and an emotion recognition test. For example, he or she smells lemon and rose and inputs his or her sensitivity to each scent into the device. At the same time, the emotion engine recognizes User A's emotional state (e.g., relaxed, stressed, etc.). The server analyzes this data and determines that User A has a low sensitivity to citrus scents and is in a relaxed state. The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[0319] Case 2: Progress prediction and training plan updates

[0320] The server analyzes the training feedback and emotional data entered by User A, and predicts that sensitivity has improved and that there are times when the user feels stressed. The server then generates a new training plan. This plan includes adding a rose-like scent and recommending training at times when relaxation is most effective. The device notifies User A of the new training plan and encourages him or her to carry it out. User A continues training according to this new plan.

[0321] Example prompt sentence:

[0322] "Please smell the designated scent and enter the strength and degree of identification you feel into the terminal."

[0323] "We use an emotion engine to collect data about the emotional state during training."

[0324] The system of the present invention allows patients with olfactory disorders to receive personalized training to quickly and effectively restore their sense of smell, and further maximizes the effectiveness of the training by taking their emotional state into consideration.

[0325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0326] System program processing flow

[0327] User registration and initial evaluation

[0328] Step 1:

[0329] The user downloads and installs a dedicated app. After installation, the user enters personal information such as name, age, and gender to create an account. This information is sent to the server and registered.

[0330] Input: User's personal information (name, age, gender, etc.)

[0331] Output: Account information registered on the server

[0332] Step 2:

[0333] The user performs the scent evaluation test. Following the instructions displayed on the terminal, the user smells multiple scent samples provided and inputs data into the terminal to evaluate their sensitivity and discrimination.

[0334] Input: User's scent sensitivity data (e.g. lemon strength 3, discrimination 4)

[0335] Output: Evaluation data entered on the terminal

[0336] Step 3:

[0337] The device sends the collected evaluation data to a server, which then analyzes the data using a generative AI model to evaluate the user's initial olfactory sensitivity.

[0338] Input: Scent sensitivity data

[0339] Data processing / calculation: Analysis using generative AI models

[0340] Output: Server-generated initial olfactory sensitivity assessment results

[0341] Step 4:

[0342] Based on the initial olfactory sensitivity assessment results, the server generates a personalized initial training plan and sends it to the device. An example plan would be "smell citrus scents for five minutes every day."

[0343] Input: Initial olfactory sensitivity assessment results

[0344] Data processing / calculation: Training plan generation

[0345] Output: A personalized initial training plan

[0346] Personalized scent selection and emotion recognition

[0347] Step 1:

[0348] The user follows a training plan, smelling designated scents periodically, and inputs feedback into the device about the strength and discrimination of the scents.

[0349] Input: Scent based on training plan

[0350] Output: Feedback data (e.g. rose scent, strength 2, discrimination 3)

[0351] Step 2:

[0352] The device uses an emotion engine to collect emotional data from the user during training, for example, recognizing their emotional state (e.g., relaxed, stressed, etc.).

[0353] Input: User's emotional state

[0354] Output: Emotion data (e.g., relaxed)

[0355] Step 3:

[0356] The device sends feedback data and emotion data to a server, which collects and analyzes the data.

[0357] Input: Feedback and emotion data

[0358] Data processing / calculation: Data analysis

[0359] Output: Analysis results

[0360] Step 4:

[0361] Based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and applies it to the next training session. For example, if the user is feeling stressed, it will select a scent that has a relaxing effect.

[0362] Input: Analysis results

[0363] Data processing / calculation: Adjusting training plans

[0364] Output: Tailored training plan

[0365] Predictive models for predicting progress and optimizing training

[0366] Step 1:

[0367] The server uses a generative model to predict the user's progress based on the collected feedback data and emotion data, and estimates changes in olfactory sensitivity.

[0368] Input: Feedback data, emotion data

[0369] Data processing / calculation: Progress forecast

[0370] Output: Progress forecast results

[0371] Step 2:

[0372] The server generates a new training plan based on the prediction results, for example adding a new scent if olfactory sensitivity improves.

[0373] Input: Progress forecast result

[0374] Data processing / calculation: New training plan generation

[0375] Output: New training plan

[0376] Step 3:

[0377] The device notifies the user of the new training plan, and the user continues training according to the plan.

[0378] Enter: New training plan

[0379] Output: User notification, ongoing training begins

[0380] Through the above processing steps, this system provides personalized training to patients who suffer from olfactory impairment as a result of COVID-19, maximizing the effectiveness of the training.

[0381] (Application example 2)

[0382] 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."

[0383] Providing personalized scent training to patients with olfactory impairment after COVID-19 infection is challenging. Conventional methods have not adequately developed optimal training plans tailored to each patient's olfactory sensitivity and emotional state, and have not adequately assessed and adjusted their progress. Furthermore, there has been a lack of methods to provide a relaxing effect in a virtual space that takes into account the patient's emotional state during training and improves the user experience. As a result, the effectiveness of the training has been limited.

[0384] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0385] In this invention, the server includes: means for evaluating a patient's scent sensitivity using a generative model; means for designing an individual scent training session based on the evaluation; means for collecting data during training and selecting scents based on the data; means for building a predictive model related to specific scents and predicting progress toward improvement; means for a user to receive scent training in a virtual space using a terminal; means for recognizing the user's emotional state using an emotion engine and collecting that data; means for adjusting the training content and timing based on the collected emotional data; and means for changing the environment of the virtual space according to the user's evaluation and emotional state. This makes it possible to provide patients with olfactory impairment after COVID-19 infection with personalized scent training and the relaxing effect of the virtual space, maximizing the effectiveness of the training.

[0386] A "generative model" is a system that includes algorithms that analyze data and generate specific patterns or characteristics.

[0387] "Scent sensitivity" is data that indicates an individual's reaction to and ability to discriminate specific scents.

[0388] A "training session" is a series of activities or trials designed to improve olfactory ability.

[0389] "Data collection" is the process of gathering information about the user's olfactory sensitivity and emotional state.

[0390] A "predictive model" is an algorithm that predicts future progress or results based on collected data.

[0391] A "terminal" is a computer device used by a user to receive scent training in a virtual space.

[0392] An "emotion engine" is software that analyzes a user's emotional state and collects that data.

[0393] A "virtual space" is a virtual environment where users can experience training or relaxation.

[0394] "Means for changing the environment" refers to technology that customizes various elements in a virtual space according to the user's evaluation and emotional state.

[0395] The "relaxation effect" is an effect that provides a sensation or experience that puts the user in a relaxed state.

[0396] This invention is a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. The system consists of a server and a terminal (user device). The server uses the generative model to generate a personalized training plan, and the terminal implements the scent training and recognizes and collects the user's emotional state. It can also provide a relaxing environment using a virtual space.

[0397] System Overview

[0398] 1. User Registration and Initial Evaluation:

[0399] Users download a dedicated app and install it on their device. They then enter their personal information to create an account. This information is then stored on the server.

[0400] As an initial evaluation, the user smells multiple scent samples and inputs data assessing their sensitivity and discrimination ability.

[0401] The device transmits this evaluation data to a server, which analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[0402] 2. Personalized scent selection and emotion recognition:

[0403] The user follows a training plan and periodically smells designated scents, while inputting feedback into the device about the scent's strength and discrimination.

[0404] The device uses an emotion engine to collect the user's emotional state during training, and this data is sent to the server along with the feedback data.

[0405] The server continuously collects and analyzes this data, and based on the analysis results, selects the next scent that best suits the user's situation and reflects it in the training plan.

[0406] 3. Predictive models for progress forecasting and training optimization:

[0407] The server uses the collected feedback data and emotion data to build a generative model and predict the user's progress.

[0408] Based on the prediction results, the server updates the training plan and performs optimizations such as adding new scents.

[0409] The content and timing of training is also adjusted based on emotional data.

[0410] 4. Relaxing virtual experience:

[0411] The device uses a virtual space to provide a relaxing environment for users to undergo scent training, which includes visual and auditory elements tailored to specific scents.

[0412] Specific explanation of the system's operation

[0413] Hardware: Devices such as smartphones and tablets

[0414] Software: Server-side application using Flask (Python), emotion engine, virtual space generation tool

[0415] Specific examples

[0416] Case 1: User A's initial registration and training start

[0417] User A installs the app and takes the lemon and rose scent evaluation test and emotion recognition test.

[0418] For example, it may be determined that user A has a low sensitivity to citrus scents and is in a relaxed state.

[0419] An initial training plan using a citrus scent is created, and User A begins training according to this plan.

[0420] Case 2: Progress forecast and training plan updates

[0421] User A's feedback data and emotional data are collected and analyzed to predict that his sensitivity has improved and that there are times when he feels stressed.

[0422] The server generates a new plan that adds a rose-like scent and recommends training during a relaxing time. User A continues training according to the new plan.

[0423] Prompt Sentence Examples

[0424] Based on the user's olfactory sensitivity and emotional data, select the best scent for the next training session. The best time is when the user is less sensitive to citrus scents and is more relaxed. Generate a list of scents to use in the next session.

[0425] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0426] Step 1:

[0427] The user downloads a dedicated app and installs it on their device. They then enter their personal information to create an account. This information is sent from the device to the server and stored on the server.

[0428] Input: User's personal information (name, age, gender, etc.)

[0429] Processing: The terminal sends the user-entered information to the server to create an account.

[0430] Output: User account information stored on the server

[0431] Step 2:

[0432] The user performs an initial evaluation by smelling multiple scent samples and inputting data evaluating their sensitivity and discrimination ability into the terminal, which then transmits this evaluation data to the server.

[0433] Input: User's scent sensitivity evaluation data (scent concentration, discrimination ability, etc.)

[0434] Processing: The device sends the evaluation data to the server, which analyzes these data using the generative model.

[0435] Output: Initial olfactory sensitivity assessment results analyzed by the server

[0436] Step 3:

[0437] Based on the analysis results, the server evaluates the user's initial olfactory sensitivity and generates a personalized training plan, which is then sent to the device.

[0438] Input: Initial olfactory sensitivity assessment results

[0439] Processing: The server uses the generative model to generate a personalized training plan.

[0440] Output: A personalized training plan sent to your device

[0441] Step 4:

[0442] The user periodically smells designated scents according to the training plan, and provides feedback on the scent's strength and discrimination. The device also evaluates the user's emotional state using an emotion engine and transmits the data to the server.

[0443] Input: User training feedback data, emotional state data

[0444] Processing: The device collects feedback data and emotion data and sends them to the server.

[0445] Output: Training feedback data and emotional state data sent to the server

[0446] Step 5:

[0447] The server analyzes the collected data and adjusts the training plan, scheduling training at times that are most relaxing based on emotional data.

[0448] Input: Training feedback data, emotional state data

[0449] Processing: The server analyzes the data and generates a new training plan.

[0450] Output: Updated training plan sent to the user

[0451] Step 6:

[0452] While the user is training in the virtual space, the device provides images and sounds with a relaxing effect. The virtual environment is adjusted according to the user's evaluation and emotional state.

[0453] Input: User rating data, emotional state data

[0454] Processing: The device adjusts the virtual environment and provides relaxing content.

[0455] Output: A customized virtual relaxation environment experienced by the user.

[0456] 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.

[0457] 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.

[0458] 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.

[0459] [Second embodiment]

[0460] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0461] 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.

[0462] 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).

[0463] 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.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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."

[0472] This invention relates to a system that uses a generative model to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0473] System Overview

[0474] The system works in the following steps:

[0475] 1. User registration and initial evaluation

[0476] 2. Personalized scent selection

[0477] 3. Progress prediction and training optimization using predictive models

[0478] Specific explanation of the system's operation

[0479] 1. User registration and initial evaluation

[0480] 1. The user downloads and installs the app. They then enter their personal information to create an account. This information is then stored on the server.

[0481] 2. As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability.

[0482] 3. The device sends this evaluation data to the server, which analyzes it using a generative model to evaluate the user's initial olfactory sensitivity.

[0483] 4. Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0484] 2. Personalized scent selection

[0485] 5. The user follows the training plan and smells the designated scents periodically, inputting feedback into the device about the perceived strength and the degree of scent identification.

[0486] 6. The device sends this feedback data to the server, which continuously collects and analyzes this data.

[0487] 7. Based on the above analytical data, the server selects the scent that best suits the user's olfactory sensitivity and reflects it in the next training session.

[0488] 3. Progress prediction and training optimization using predictive models

[0489] 8. The server uses the generative model to predict the user's progress based on the collected feedback data.

[0490] 9. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may optimize the plan by adding a different scent.

[0491] 10. The device will notify the user of the new training plan and continue training according to its contents.

[0492] Specific examples

[0493] Case 1: User A's initial registration and training start

[0494] User A installs the app and performs a scent evaluation test. For example, he smells lemon and rose scents and enters his sensitivity to each scent into his device.

[0495] The server analyzes this data and finds that User A is particularly sensitive to citrus scents.

[0496] The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[0497] Case 2: Progress forecast and training plan updates

[0498] The server analyzes the training feedback entered by user A and predicts that sensitivity is improving.

[0499] The server generates a new training plan, which includes adding a rose scent to further test the sensitivity, etc.

[0500] The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[0501] The above is a specific embodiment of the present invention. This system enables patients with olfactory impairment as a result of COVID-19 to quickly and effectively recover their sense of smell by receiving personalized training.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] Users download and install a dedicated app, enter their personal information, and create an account. This information is stored on the server.

[0505] Step 2:

[0506] The device displays an interface for an initial olfactory evaluation test to the user, who then smells multiple scent samples and fills out a form to evaluate their sensitivity and discrimination ability.

[0507] Step 3:

[0508] The device sends the evaluation data entered by the user to the server, which then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[0509] Step 4:

[0510] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0511] Step 5:

[0512] The device displays an initial training plan to the user, who then follows the plan and periodically smells the designated scent.

[0513] Step 6:

[0514] After each training session, the user inputs feedback into the device about the strength of the scents they perceived and their ability to identify them.

[0515] Step 7:

[0516] The terminal collects the feedback data entered by the user and transmits it to the server.

[0517] Step 8:

[0518] The server continuously collects and analyzes this data, and based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session.

[0519] Step 9:

[0520] The server uses a generative model to predict the user's progress based on the collected feedback data.

[0521] Step 10:

[0522] The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may add a different scent to optimize the training plan.

[0523] Step 11:

[0524] The device notifies the user of the new training plan and continues training according to its contents.

[0525] Step 12:

[0526] The user continues training according to the new training plan, and feedback is again entered into the device and sent to the server.

[0527] Step 13:

[0528] The server continuously analyzes the feedback data and updates and optimizes the training plan as needed.

[0529] Example 1

[0530] 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."

[0531] Conventional olfactory training systems lack the ability to properly evaluate individual users' scent sensitivity and dynamically optimize training plans based on their progress. This means that they are unable to provide effective training tailored to the progression and recovery rate of each user's olfactory disorder. Furthermore, they are unable to collect and analyze real-time feedback data, which makes it difficult to maximize the effectiveness of training.

[0532] 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.

[0533] In this invention, the server includes means for user registration and personal information input, means for collecting sensitivity evaluation data for multiple scent samples as an initial evaluation, means for analyzing the collected initial evaluation data and evaluating the user's initial olfactory sensitivity using a generative model, means for generating an individualized initial training plan based on the analysis results, means for continuously collecting training feedback data and selecting the scent most suitable for the user's olfactory sensitivity using the generative model, and means for predicting progress based on the collected feedback data and optimizing the training plan. This enables individually customized olfactory training and enables effective training tailored to each user's progress. Furthermore, real-time data collection and analysis can maximize the effectiveness of training.

[0534] A "user" is a subject who receives individual olfactory training using this system.

[0535] The "server" is a central control unit that stores and analyzes data sent by users and provides generated training plans to users.

[0536] A "terminal" is a device on which a user installs an app and uses it to input data and provide feedback.

[0537] A "generative model" is an artificial intelligence algorithm that analyzes collected data to assess a user's olfactory sensitivity and generate an optimal training plan.

[0538] "Scent Samples" refers to multiple different scents that a user uses to evaluate and train their sense of smell.

[0539] "Feedback data" refers to data regarding scent strength and discrimination that is input by the user after a training session.

[0540] A "training plan" is a personalized training regimen that uses specific scents based on the user's olfactory sensitivity.

[0541] "Progress" is an indicator that indicates how much the user's olfactory sensitivity has improved through training.

[0542] The "analysis result" is an assessment of the user's olfactory sensitivity resulting from data processed by the generative model.

[0543] "Scent selection" is the process of determining the optimal scent to use in the next training session based on analytical data.

[0544] This invention relates to a system that uses a generative model to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0545] System configuration and technologies used

[0546] This system consists of a user, a server, and a terminal. The server is responsible for storing and analyzing data, running the generative model, and generating and managing training plans. Specifically, it uses generative AI models such as OpenAI's GPT-3. The terminal is a device, such as a smartphone or tablet, through which the user inputs data and provides feedback.

[0547] System Operation

[0548] User registration and initial evaluation

[0549] The user downloads and installs a dedicated app. They then enter their personal information and create an account. As an initial assessment, the user smells multiple scent samples and fills out a form on their device to evaluate their sensitivity and discrimination ability. The device then sends this evaluation data to a server. The server then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity. Based on the analysis results, the server generates a personalized initial training plan and sends it to the device.

[0550] Personalized scent selection

[0551] The user follows a training plan and periodically smells designated scents. They then input feedback into the device about the perceived strength and ability to distinguish the scents. The device then sends this feedback data to the server, which continuously collects and analyzes this data. Based on the analyzed data, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session.

[0552] Predictive models for predicting progress and optimizing training

[0553] The server uses a generative model to predict the user's progress based on the collected feedback data. The server then updates the training plan based on the prediction results. For example, if the user's sensitivity improves, the server may optimize the training by adding a different scent. The device then notifies the user of the new training plan and allows them to continue training according to the plan's contents.

[0554] Specific examples

[0555] Case 1: User A's initial registration and training start

[0556] User A installs the app and creates an account by entering personal information. Next, he or she smells lemon and rose scent samples and enters their sensitivity to each into the device. The device sends the evaluation data to the server, which analyzes it using a generative AI model. The server determines that User A has a low sensitivity to citrus scents and creates an initial training plan using citrus scents. User A follows this plan and begins training by smelling citrus scents every day.

[0557] Case 2: Progress forecast and training plan updates

[0558] The server analyzes the training feedback entered by User A and predicts that sensitivity has improved. The server generates a new training plan. This plan includes adding a rose-like scent to further check sensitivity. The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[0559] The above is a specific embodiment of the present invention. This system enables users with olfactory impairment to quickly and effectively recover their sense of smell by receiving personalized training.

[0560] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0561] Step 1:

[0562] The user downloads and installs a dedicated app. The input is the download and installation process from the Apple App Store or Google Play Store. The output is the installation of the app on the device. Specifically, the user searches for the app in the device's store and taps the install button.

[0563] Step 2:

[0564] A user creates an account by entering personal information. The input includes personal information such as name, age, and gender, which are entered into the account creation form. The output is that the personal information is saved on the server and the account is created. Specifically, the user enters the required information on the initial setup screen of the app and taps the submit button.

[0565] Step 3:

[0566] As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability. The input is the perceived strength and discrimination of the scent samples, which are entered into the evaluation form. The output is evaluation data generated. In concrete terms, the user smells the provided scent samples and enters their evaluation as a number or comment on the app.

[0567] Step 4:

[0568] The terminal sends initial evaluation data to the server. The input is the evaluation data entered by the user, and the output is received and stored by the server. In concrete terms, the terminal runs a process in the background to transmit the evaluation data over the network.

[0569] Step 5:

[0570] The server uses a generative model to analyze the initial evaluation data and evaluate the user's initial olfactory sensitivity. The input is the evaluation data, and the output is the analysis result. Specifically, the server calls a generative AI model (e.g., GPT-3) and performs data analysis based on the input data.

[0571] Step 6:

[0572] The server generates an individualized initial training plan based on the analysis results and sends it to the device. The input is the analysis results, and the training plan is generated as the output. Specifically, the server creates an optimal training plan using an AI model based on the analysis results and sends this plan to the device.

[0573] Step 7:

[0574] The user follows a training plan and smells designated scents periodically. The training plan is the input, and user feedback data is generated as the output. Specifically, the user follows the app's instructions to smell the designated scents and enters their perceived strength and discrimination into a form.

[0575] Step 8:

[0576] The terminal sends feedback data to the server. The input is the user's feedback data, and the output is the server receiving and storing the data. In concrete terms, the terminal runs a process of sending feedback data over the network in the background.

[0577] Step 9:

[0578] The server analyzes the feedback data, evaluates the user's olfactory sensitivity using a generative model, and selects the optimal scent. The input is the feedback data, and the output is the optimal scent selection result. Specifically, the server calls the generative AI model and performs a reanalysis based on this new data.

[0579] Step 10:

[0580] The server predicts the user's progress and generates a new training plan. The input is the analysis data, and the output is the creation of a new training plan. Specifically, the server analyzes the user's progress data and updates the training plan as necessary.

[0581] Step 11:

[0582] The device notifies the user of the new training plan. The input is the new training plan, and the output is a notification to the user. Specifically, the device notifies the user of the new training plan using a means such as a push notification.

[0583] (Application example 1)

[0584] 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."

[0585] The problem that this invention aims to solve is to provide effective scent training for patients with olfactory impairment after COVID-19 infection. Specifically, it aims to provide a personalized scent training plan for each patient and a method for evaluating and optimizing progress in real time. Another important issue is to incorporate a system with electronic payment functionality, allowing users to easily purchase training fragrances and manage subscriptions.

[0586] 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.

[0587] In this invention, the server includes a means for evaluating a patient's scent sensitivity using a generative model, a means for designing an individual scent training session based on the evaluation, a means for collecting data during training and selecting scents based on the data, and a means for providing electronic payment functionality and managing the purchase and subscription of training fragrances. This maximizes the effect of improving each patient's olfactory disorder, optimizes the progress of the training plan in real time, and allows users to easily purchase the items they need.

[0588] A "generative model" is a model that uses generative AI techniques to generate new data from specific input data.

[0589] "Scent sensitivity assessment" is the process of assessing how sensitive a user is to a particular scent.

[0590] A "training session" is a series of scent training activities designed to improve scent sensitivity.

[0591] An "individual training plan" is a personalized training plan generated based on each user's scent sensitivity.

[0592] "Data collection" is the process of collecting progress and results information entered by users during their workouts.

[0593] "Scent selection" refers to selecting the scent that is best suited to the user based on collected data.

[0594] A "predictive model" is an AI model that uses collected feedback data to predict future outcomes.

[0595] "Electronic Payment Function" means a function that allows users to purchase training materials and manage their subscriptions online.

[0596] A "server" is a computer system that manages the entire system, collects and analyzes data, and provides training plans.

[0597] This invention relates to a system that uses generative models to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. The system consists of a server and a user device (such as a smartphone).

[0598] System Configuration

[0599] This system is centered around a server and implements the following main functions:

[0600] Assessing patients' scent sensitivity using a generative model.

[0601] Design individualized scent training sessions based on the evaluation data.

[0602] Data is collected during training and scents are selected based on the data.

[0603] Build predictive models related to specific scents to forecast progress.

[0604] We provide electronic payment facilities and manage training fragrance purchases and subscriptions.

[0605] Processing procedures and data processing

[0606] The system uses the following major hardware and software components:

[0607] Hardware: Smartphones (e.g., iPhone, Android devices), servers (e.g., AWS, Google Cloud)

[0608] Software: Python, Flask (backend), React Native (frontend), AI libraries for generative models (e.g., TensorFlow, PyTorch)

[0609] User registration and initial evaluation

[0610] The user installs a dedicated application on their smartphone and creates an account by entering their personal information. This information is then stored on the server. As an initial evaluation, the user smells multiple scent samples and enters data evaluating their sensitivity and discrimination ability. The device then sends this evaluation data to the server, which then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[0611] Fragrance selection and training

[0612] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device. The user follows the training plan and smells the designated scents periodically. The user inputs feedback on the strength and discrimination they sensed during the training, which is then sent to the server. The server analyzes the feedback data and selects the scent that is best suited to the next training session based on the user's olfactory sensitivity.

[0613] Progress prediction and training optimization

[0614] Based on the collected feedback data, the server uses a generative model to predict the user's progress and optimizes the training plan accordingly. For example, if the user's sensitivity improves, it may add a different scent. The new training plan is then notified to the device, allowing the user to continue training.

[0615] Electronic payment function

[0616] Purchasing training products and managing subscriptions is done through the app's electronic payment function, allowing users to conveniently purchase the items they need for their training.

[0617] Specific examples

[0618] Case 1: User A's initial registration and training start

[0619] User A installs the app and takes a scent evaluation test. The server analyzes the evaluation data and determines that User A has a low sensitivity to certain scents. The server then creates a training plan using citrus scents and sends it to the device.

[0620] Case 2: Progress forecast and training plan updates

[0621] User A inputs training feedback, and the server analyzes it and determines that sensitivity has improved. A new scent is added to the new training plan, and User A is notified.

[0622] Prompt Sentence Examples

[0623] Below are some example prompts to input to a generative AI model:

[0624] "Generate a personalized olfactory training plan given the user's initial assessment data: {initial_data}."

[0625] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0626] Step 1:

[0627] User registration and initial evaluation

[0628] Users download the application and create an account by entering their personal information, such as name, email address, and password. The device sends this data to the server, which stores it in a database.

[0629] Input: User personal information

[0630] Output: Account data is saved on the server

[0631] Specific operation: The user launches the app on their smartphone, enters their personal information into the registration form, and submits it. The server receives the request and stores the information in a database.

[0632] Step 2:

[0633] Initial scent sensitivity assessment

[0634] The user smells multiple scent samples and evaluates their sensitivity and discrimination ability. The device sends the evaluation data entered by the user to the server. The server analyzes this data using a generative model and evaluates the user's initial olfactory sensitivity.

[0635] Input: User-perceived scent evaluation data

[0636] Output: User's initial scent sensitivity evaluation result

[0637] Specific operation: The server inputs the received evaluation data into the generative AI model to obtain analysis results, which are then stored in a database.

[0638] Step 3:

[0639] Designing individual training plans

[0640] The server generates a personalized training plan based on the initial scent sensitivity assessment results, including which scents the user should smell and how often. The server then transmits the generated training plan to the device.

[0641] Input: Initial scent sensitivity evaluation results

[0642] Output: Individual training plan

[0643] Specific operation: The server uses an AI model to create a training plan based on the user's evaluation results and pushes a notification to the device.

[0644] Step 4:

[0645] Conducting scent training and collecting feedback

[0646] The user follows the training plan provided and smells the designated scent periodically. After each training session, the user inputs feedback on the strength and discrimination of the scent they perceived, and the device sends this feedback to the server.

[0647] Input: User feedback data

[0648] Output: Feedback data is saved on the server

[0649] Specific operation: The user trains regularly and enters the results into the app. The device sends the data to the server.

[0650] Step 5:

[0651] Analysis of feedback data and selection of scents

[0652] The server analyzes the collected feedback data to evaluate the user's progress, uses a generative model to select the next scent that best suits the user, and sends a new training plan to the device to reflect the next training session.

[0653] Input: Feedback data

[0654] Output: Updated training plan

[0655] How it works: The server inputs the feedback data into the AI ​​model, selects the optimal scent based on the analysis results, and updates the training plan. The updated plan is then sent to the device.

[0656] Step 6:

[0657] Progress forecast and training plan updates

[0658] The server predicts the user's training progress based on the collected feedback data. A generative model determines how much the user's sense of smell has improved and optimizes the training plan accordingly. The new training plan is then notified to the device.

[0659] Input: Feedback data

[0660] Output: Optimized training plan

[0661] Specific operation: The server updates the predictive model based on the analysis results, generates an optimized training plan, and sends it to the device.

[0662] Step 7:

[0663] Electronic payment function

[0664] Users purchase the training materials and subscriptions they need within the app. The device sends payment information to the server, which processes the payment. Once the purchase is confirmed, it is reflected in the user's account.

[0665] Input: User's payment information

[0666] Output: Payment completion notification and purchase items reflected in your account

[0667] Specific operation: The user makes a purchase through the app, and the device sends the payment information to the server. The server processes the payment and notifies the user of the result.

[0668] 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.

[0669] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0670] System Overview

[0671] The system works in the following steps:

[0672] 1. User registration and initial evaluation

[0673] 2. Personalized scent selection and emotion recognition

[0674] 3. Progress prediction and training optimization using predictive models

[0675] Specific explanation of the system's operation

[0676] 1. User registration and initial evaluation

[0677] 1. The user downloads and installs the app. They then enter their personal information to create an account. This information is then stored on the server.

[0678] 2. As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability.

[0679] 3. The device sends this evaluation data to the server, which analyzes it using a generative model to evaluate the user's initial olfactory sensitivity.

[0680] 4. Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0681] 2. Personalized scent selection and emotion recognition

[0682] 5. The user follows the training plan and smells the designated scents periodically, inputting feedback into the device about the perceived strength and the degree of scent identification.

[0683] 6. The device collects the user's emotional data during training using an emotion engine that also recognizes the user's emotional state.

[0684] 7. Analyze the user's training feedback and emotional data to adjust the training plan. For example, if the user is feeling stressed, a relaxing scent will be selected.

[0685] 8. The device sends this feedback data and emotion data to the server, which continuously collects and analyzes this data.

[0686] 9. Based on the above analytical data, the server selects the scent that best suits the user's olfactory sensitivity and reflects it in the next training session.

[0687] 3. Progress prediction and training optimization using predictive models

[0688] 10. The server uses a generative model to predict the user's progress based on the collected feedback data and emotion data.

[0689] 11. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may optimize the training plan by adding a different scent.

[0690] 12. We can also tailor workout content and timing based on emotional data. For example, we can recommend workouts for times when the user is relaxed.

[0691] 13. The device will notify the user of the new training plan and continue training according to its contents.

[0692] Specific examples

[0693] Case 1: User A's initial registration and training start

[0694] User A installs the app and takes a scent evaluation test and an emotion recognition test. For example, he or she smells lemon and rose and inputs their sensitivity to each scent into the device. At the same time, the emotion engine recognizes User A's emotional state (e.g., relaxed, stressed, etc.).

[0695] The server analyzes this data and determines that User A has a low sensitivity to citrus scents and is in a relaxed state.

[0696] The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[0697] Case 2: Progress forecast and training plan updates

[0698] The server analyzes the training feedback and emotional data entered by user A and predicts that sensitivity is improving and that there are times when the user feels stressed.

[0699] The server generates a new training plan, which includes adding a rose scent and recommending training at times that are relaxing.

[0700] The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[0701] The above is a specific embodiment of the present invention. This system allows patients with olfactory impairment as a result of COVID-19 to receive personalized training, quickly and effectively recovering their sense of smell, and further maximizes the effectiveness of the training by taking into account their emotional state.

[0702] The processing flow will be explained below.

[0703] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0704] Specific explanation of the system's operation

[0705] Step 1:

[0706] The user downloads and installs a dedicated app, enters personal information, and creates an account. This information is stored on the server.

[0707] Step 2:

[0708] The device displays interfaces for an initial olfactory assessment test and an emotion recognition test to the user. In the initial olfactory assessment test, the user smells multiple scent samples and fills out a form to evaluate their sensitivity and discrimination ability. In the emotion recognition test, the emotion engine detects and evaluates the user's emotional state from their face and voice.

[0709] Step 3:

[0710] The device transmits the olfactory evaluation data and emotional data entered by the user to the server, which then analyzes these data using a generative model to evaluate the user's initial olfactory sensitivity and emotional state.

[0711] Step 4:

[0712] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0713] Step 5:

[0714] The device displays an initial training plan to the user, who then follows the plan and periodically smells the designated scent.

[0715] Step 6:

[0716] After each training session, the user inputs feedback into the device about the strength and discrimination of the scents they perceived, and the emotion engine also records the user's emotional state during the training session.

[0717] Step 7:

[0718] The device collects feedback data and emotion data from the user and transmits it to the server.

[0719] Step 8:

[0720] The server continuously collects this data and analyzes it using a generative model. Based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and applies it to the next training session. It also takes into account the collected emotional data and adjusts the content and timing of the training.

[0721] Step 9:

[0722] The server uses a generative model to predict the user's progress based on the collected feedback and emotion data. For example, if the user's sensitivity to a particular scent improves, another scent will be added.

[0723] Step 10:

[0724] The server updates the training plan based on the prediction results and emotion data, for example, by generating a plan that recommends training during times when the user is relaxed.

[0725] Step 11:

[0726] The device notifies the user of the new training plan and continues training according to its contents.

[0727] Step 12:

[0728] The user continues training according to the new training plan, and feedback is again entered into the device, with the emotional state also being recorded by the emotion engine.

[0729] Step 13:

[0730] The server continuously analyzes the feedback data and emotional data, updating and optimizing the training plan as needed. By repeating this process, the user can efficiently recover their sense of smell.

[0731] The above is a specific embodiment of the present invention. This system allows patients with olfactory disorders to receive personalized training to quickly and effectively restore their sense of smell, and further maximizes the effectiveness of the training by taking into account their emotional state.

[0732] Example 2

[0733] 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."

[0734] There is a need for effective and personalized scent training for patients suffering from olfactory impairment after COVID-19 infection. Conventional methods have limited training effectiveness because they do not take into account the patient's emotional state, and there are also challenges in predicting progress and optimizing training plans. The present invention aims to comprehensively solve these challenges.

[0735] The identification processing 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 evaluating the patient's scent sensitivity using a generative model, means for designing an individual scent training session based on the evaluation, means for collecting feedback and emotional data during training and selecting scents based on the data, means for building a predictive model related to specific scents and predicting progress toward improvement, and means for adjusting the training plan based on the emotional data. This enables individualized training according to each patient's olfactory sensitivity and emotional state, maximizing the effectiveness of the training.

[0736] A "generative model" is an algorithm that learns specific patterns or features from data and generates or analyzes new data.

[0737] "Scent sensitivity" refers to the strength and ability of an individual to distinguish a particular scent.

[0738] A "training session" refers to a series of scent sniffing trials conducted under specific instructions.

[0739] "Feedback data" refers to information regarding the strength and discrimination of scents felt by the user during training.

[0740] "Emotional Data" means data regarding the emotional state exhibited by a user during training.

[0741] A "predictive model" is an algorithm that uses past data to predict future developments and outcomes.

[0742] A "training plan" is a plan that shows specific training procedures and schedules designed based on the user's progress and condition.

[0743] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0744] User registration and initial evaluation

[0745] The user downloads and installs a dedicated app. They then enter their personal information and create an account. This information is stored on the server. Then, as an initial assessment, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability. For example, the user might enter their sensitivity to lemon or rose scents as "Strength 3, Discrimination Level 4." The device then sends this evaluation data to the server. The server analyzes this data using a generative AI model to evaluate the user's initial olfactory sensitivity. Based on the analysis results, the server generates a personalized initial training plan and sends it to the device.

[0746] Personalized scent selection and emotion recognition

[0747] The user follows a training plan and periodically smells designated scents. The user then inputs feedback into the device about the perceived strength and scent discrimination. For example, "Rose scent: strength 2, discrimination 3." The device uses an emotion engine that also recognizes the user's emotional state to collect emotional data about the user during training. For example, "relaxed" or "stressed." This feedback and emotional data is sent from the device to a server, which continuously collects and analyzes this data. Based on the analyzed data, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session. For example, if the user is feeling stressed, a scent with a relaxing effect will be selected.

[0748] Predictive models for predicting progress and optimizing training

[0749] The server uses a generative model to predict the user's progress based on the collected feedback data and emotional data. For example, it estimates changes in olfactory sensitivity. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it performs optimization such as adding a new scent. The server also adjusts the training content and timing based on the emotional data. For example, it could recommend training during times when the user is relaxed. The device notifies the user of the new training plan and allows them to continue training according to the plan's contents.

[0750] Specific operation example

[0751] Case 1: User A's initial evaluation and training begins

[0752] User A installs the app and takes a scent evaluation test and an emotion recognition test. For example, he or she smells lemon and rose and inputs his or her sensitivity to each scent into the device. At the same time, the emotion engine recognizes User A's emotional state (e.g., relaxed, stressed, etc.). The server analyzes this data and determines that User A has a low sensitivity to citrus scents and is in a relaxed state. The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[0753] Case 2: Progress prediction and training plan updates

[0754] The server analyzes the training feedback and emotional data entered by User A, and predicts that sensitivity has improved and that there are times when the user feels stressed. The server then generates a new training plan. This plan includes adding a rose-like scent and recommending training at times when relaxation is most effective. The device notifies User A of the new training plan and encourages him or her to carry it out. User A continues training according to this new plan.

[0755] Example prompt sentence:

[0756] "Please smell the designated scent and enter the strength and degree of identification you feel into the terminal."

[0757] "We use an emotion engine to collect data about the emotional state during training."

[0758] The system of the present invention allows patients with olfactory disorders to receive personalized training to quickly and effectively restore their sense of smell, and further maximizes the effectiveness of the training by taking their emotional state into consideration.

[0759] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0760] System program processing flow

[0761] User registration and initial evaluation

[0762] Step 1:

[0763] The user downloads and installs a dedicated app. After installation, the user enters personal information such as name, age, and gender to create an account. This information is sent to the server and registered.

[0764] Input: User's personal information (name, age, gender, etc.)

[0765] Output: Account information registered on the server

[0766] Step 2:

[0767] The user performs the scent evaluation test. Following the instructions displayed on the terminal, the user smells multiple scent samples provided and inputs data into the terminal to evaluate their sensitivity and discrimination.

[0768] Input: User's scent sensitivity data (e.g. lemon strength 3, discrimination 4)

[0769] Output: Evaluation data entered on the terminal

[0770] Step 3:

[0771] The device sends the collected evaluation data to a server, which then analyzes the data using a generative AI model to evaluate the user's initial olfactory sensitivity.

[0772] Input: Scent sensitivity data

[0773] Data processing / calculation: Analysis using generative AI models

[0774] Output: Server-generated initial olfactory sensitivity assessment results

[0775] Step 4:

[0776] Based on the initial olfactory sensitivity assessment results, the server generates a personalized initial training plan and sends it to the device. An example plan would be "smell citrus scents for five minutes every day."

[0777] Input: Initial olfactory sensitivity assessment results

[0778] Data processing / calculation: Training plan generation

[0779] Output: A personalized initial training plan

[0780] Personalized scent selection and emotion recognition

[0781] Step 1:

[0782] The user follows a training plan, smelling designated scents periodically, and inputs feedback into the device about the strength and discrimination of the scents.

[0783] Input: Scent based on training plan

[0784] Output: Feedback data (e.g. rose scent, strength 2, discrimination 3)

[0785] Step 2:

[0786] The device uses an emotion engine to collect emotional data from the user during training, for example, recognizing their emotional state (e.g., relaxed, stressed, etc.).

[0787] Input: User's emotional state

[0788] Output: Emotion data (e.g., relaxed)

[0789] Step 3:

[0790] The device sends feedback data and emotion data to a server, which collects and analyzes the data.

[0791] Input: Feedback and emotion data

[0792] Data processing / calculation: Data analysis

[0793] Output: Analysis results

[0794] Step 4:

[0795] Based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and applies it to the next training session. For example, if the user is feeling stressed, it will select a scent that has a relaxing effect.

[0796] Input: Analysis results

[0797] Data processing / calculation: Adjusting training plans

[0798] Output: Tailored training plan

[0799] Predictive models for predicting progress and optimizing training

[0800] Step 1:

[0801] The server uses a generative model to predict the user's progress based on the collected feedback data and emotion data, and estimates changes in olfactory sensitivity.

[0802] Input: Feedback data, emotion data

[0803] Data processing / calculation: Progress forecast

[0804] Output: Progress forecast results

[0805] Step 2:

[0806] The server generates a new training plan based on the prediction results, for example adding a new scent if olfactory sensitivity improves.

[0807] Input: Progress forecast result

[0808] Data processing / calculation: New training plan generation

[0809] Output: New training plan

[0810] Step 3:

[0811] The device notifies the user of the new training plan, and the user continues training according to the plan.

[0812] Enter: New training plan

[0813] Output: User notification, ongoing training begins

[0814] Through the above processing steps, this system provides personalized training to patients who suffer from olfactory impairment as a result of COVID-19, maximizing the effectiveness of the training.

[0815] (Application example 2)

[0816] 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."

[0817] Providing personalized scent training to patients with olfactory impairment after COVID-19 infection is challenging. Conventional methods have not adequately developed optimal training plans tailored to each patient's olfactory sensitivity and emotional state, and have not adequately assessed and adjusted their progress. Furthermore, there has been a lack of methods to provide a relaxing effect in a virtual space that takes into account the patient's emotional state during training and improves the user experience. As a result, the effectiveness of the training has been limited.

[0818] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0819] In this invention, the server includes: means for evaluating a patient's scent sensitivity using a generative model; means for designing an individual scent training session based on the evaluation; means for collecting data during training and selecting scents based on the data; means for building a predictive model related to specific scents and predicting progress toward improvement; means for a user to receive scent training in a virtual space using a terminal; means for recognizing the user's emotional state using an emotion engine and collecting that data; means for adjusting the training content and timing based on the collected emotional data; and means for changing the environment of the virtual space according to the user's evaluation and emotional state. This makes it possible to provide patients with olfactory impairment after COVID-19 infection with personalized scent training and the relaxing effect of the virtual space, maximizing the effectiveness of the training.

[0820] A "generative model" is a system that includes algorithms that analyze data and generate specific patterns or characteristics.

[0821] "Scent sensitivity" is data that indicates an individual's reaction to and ability to discriminate specific scents.

[0822] A "training session" is a series of activities or trials designed to improve olfactory ability.

[0823] "Data collection" is the process of gathering information about the user's olfactory sensitivity and emotional state.

[0824] A "predictive model" is an algorithm that predicts future progress or results based on collected data.

[0825] A "terminal" is a computer device used by a user to receive scent training in a virtual space.

[0826] An "emotion engine" is software that analyzes a user's emotional state and collects that data.

[0827] A "virtual space" is a virtual environment where users can experience training or relaxation.

[0828] "Means for changing the environment" refers to technology that customizes various elements in a virtual space according to the user's evaluation and emotional state.

[0829] The "relaxation effect" is an effect that provides a sensation or experience that puts the user in a relaxed state.

[0830] This invention is a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. The system consists of a server and a terminal (user device). The server uses the generative model to generate a personalized training plan, and the terminal implements the scent training and recognizes and collects the user's emotional state. It can also provide a relaxing environment using a virtual space.

[0831] System Overview

[0832] 1. User Registration and Initial Evaluation:

[0833] Users download a dedicated app and install it on their device. They then enter their personal information to create an account. This information is then stored on the server.

[0834] As an initial evaluation, the user smells multiple scent samples and inputs data assessing their sensitivity and discrimination ability.

[0835] The device transmits this evaluation data to a server, which analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[0836] 2. Personalized scent selection and emotion recognition:

[0837] The user follows a training plan and periodically smells designated scents, while inputting feedback into the device about the scent's strength and discrimination.

[0838] The device uses an emotion engine to collect the user's emotional state during training, and this data is sent to the server along with the feedback data.

[0839] The server continuously collects and analyzes this data, and based on the analysis results, selects the next scent that best suits the user's situation and reflects it in the training plan.

[0840] 3. Predictive models for progress forecasting and training optimization:

[0841] The server uses the collected feedback data and emotion data to build a generative model and predict the user's progress.

[0842] Based on the prediction results, the server updates the training plan and performs optimizations such as adding new scents.

[0843] The content and timing of training is also adjusted based on emotional data.

[0844] 4. Relaxing virtual experience:

[0845] The device uses a virtual space to provide a relaxing environment for users to undergo scent training, which includes visual and auditory elements tailored to specific scents.

[0846] Specific explanation of the system's operation

[0847] Hardware: Devices such as smartphones and tablets

[0848] Software: Server-side application using Flask (Python), emotion engine, virtual space generation tool

[0849] Specific examples

[0850] Case 1: User A's initial registration and training start

[0851] User A installs the app and takes the lemon and rose scent evaluation test and emotion recognition test.

[0852] For example, it may be determined that user A has a low sensitivity to citrus scents and is in a relaxed state.

[0853] An initial training plan using a citrus scent is created, and User A begins training according to this plan.

[0854] Case 2: Progress forecast and training plan updates

[0855] User A's feedback data and emotional data are collected and analyzed to predict that his sensitivity has improved and that there are times when he feels stressed.

[0856] The server generates a new plan that adds a rose-like scent and recommends training during a relaxing time. User A continues training according to the new plan.

[0857] Prompt Sentence Examples

[0858] Based on the user's olfactory sensitivity and emotional data, select the best scent for the next training session. The best time is when the user is less sensitive to citrus scents and is more relaxed. Generate a list of scents to use in the next session.

[0859] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0860] Step 1:

[0861] The user downloads a dedicated app and installs it on their device. They then enter their personal information to create an account. This information is sent from the device to the server and stored on the server.

[0862] Input: User's personal information (name, age, gender, etc.)

[0863] Processing: The terminal sends the user-entered information to the server to create an account.

[0864] Output: User account information stored on the server

[0865] Step 2:

[0866] The user performs an initial evaluation by smelling multiple scent samples and inputting data evaluating their sensitivity and discrimination ability into the terminal, which then transmits this evaluation data to the server.

[0867] Input: User's scent sensitivity evaluation data (scent concentration, discrimination ability, etc.)

[0868] Processing: The device sends the evaluation data to the server, which analyzes these data using the generative model.

[0869] Output: Initial olfactory sensitivity assessment results analyzed by the server

[0870] Step 3:

[0871] Based on the analysis results, the server evaluates the user's initial olfactory sensitivity and generates a personalized training plan, which is then sent to the device.

[0872] Input: Initial olfactory sensitivity assessment results

[0873] Processing: The server uses the generative model to generate a personalized training plan.

[0874] Output: A personalized training plan sent to your device

[0875] Step 4:

[0876] The user periodically smells designated scents according to the training plan, and provides feedback on the scent's strength and discrimination. The device also evaluates the user's emotional state using an emotion engine and transmits the data to the server.

[0877] Input: User training feedback data, emotional state data

[0878] Processing: The device collects feedback data and emotion data and sends them to the server.

[0879] Output: Training feedback data and emotional state data sent to the server

[0880] Step 5:

[0881] The server analyzes the collected data and adjusts the training plan, scheduling training at times that are most relaxing based on emotional data.

[0882] Input: Training feedback data, emotional state data

[0883] Processing: The server analyzes the data and generates a new training plan.

[0884] Output: Updated training plan sent to the user

[0885] Step 6:

[0886] While the user is training in the virtual space, the device provides images and sounds with a relaxing effect. The virtual environment is adjusted according to the user's evaluation and emotional state.

[0887] Input: User rating data, emotional state data

[0888] Processing: The device adjusts the virtual environment and provides relaxing content.

[0889] Output: A customized virtual relaxation environment experienced by the user.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] [Third embodiment]

[0894] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0895] 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.

[0896] 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).

[0897] 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.

[0898] 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.

[0899] 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).

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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."

[0906] This invention relates to a system that uses a generative model to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0907] System Overview

[0908] The system works in the following steps:

[0909] 1. User registration and initial evaluation

[0910] 2. Personalized scent selection

[0911] 3. Progress prediction and training optimization using predictive models

[0912] Specific explanation of the system's operation

[0913] 1. User registration and initial evaluation

[0914] 1. The user downloads and installs the app. They then enter their personal information to create an account. This information is then stored on the server.

[0915] 2. As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability.

[0916] 3. The device sends this evaluation data to the server, which analyzes it using a generative model to evaluate the user's initial olfactory sensitivity.

[0917] 4. Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0918] 2. Personalized scent selection

[0919] 5. The user follows the training plan and smells the designated scents periodically, inputting feedback into the device about the perceived strength and the degree of scent identification.

[0920] 6. The device sends this feedback data to the server, which continuously collects and analyzes this data.

[0921] 7. Based on the above analytical data, the server selects the scent that best suits the user's olfactory sensitivity and reflects it in the next training session.

[0922] 3. Progress prediction and training optimization using predictive models

[0923] 8. The server uses the generative model to predict the user's progress based on the collected feedback data.

[0924] 9. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may optimize the plan by adding a different scent.

[0925] 10. The device will notify the user of the new training plan and continue training according to its contents.

[0926] Specific examples

[0927] Case 1: User A's initial registration and training start

[0928] User A installs the app and performs a scent evaluation test. For example, he smells lemon and rose scents and enters his sensitivity to each scent into his device.

[0929] The server analyzes this data and finds that User A is particularly sensitive to citrus scents.

[0930] The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[0931] Case 2: Progress forecast and training plan updates

[0932] The server analyzes the training feedback entered by user A and predicts that sensitivity is improving.

[0933] The server generates a new training plan, which includes adding a rose scent to further test the sensitivity, etc.

[0934] The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[0935] The above is a specific embodiment of the present invention. This system enables patients with olfactory impairment as a result of COVID-19 to quickly and effectively recover their sense of smell by receiving personalized training.

[0936] The processing flow will be explained below.

[0937] Step 1:

[0938] Users download and install a dedicated app, enter their personal information, and create an account. This information is stored on the server.

[0939] Step 2:

[0940] The device displays an interface for an initial olfactory evaluation test to the user, who then smells multiple scent samples and fills out a form to evaluate their sensitivity and discrimination ability.

[0941] Step 3:

[0942] The device sends the evaluation data entered by the user to the server, which then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[0943] Step 4:

[0944] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[0945] Step 5:

[0946] The device displays an initial training plan to the user, who then follows the plan and periodically smells the designated scent.

[0947] Step 6:

[0948] After each training session, the user inputs feedback into the device about the strength of the scents they perceived and their ability to identify them.

[0949] Step 7:

[0950] The terminal collects the feedback data entered by the user and transmits it to the server.

[0951] Step 8:

[0952] The server continuously collects and analyzes this data, and based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session.

[0953] Step 9:

[0954] The server uses a generative model to predict the user's progress based on the collected feedback data.

[0955] Step 10:

[0956] The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may add a different scent to optimize the training plan.

[0957] Step 11:

[0958] The device notifies the user of the new training plan and continues training according to its contents.

[0959] Step 12:

[0960] The user continues training according to the new training plan, and feedback is again entered into the device and sent to the server.

[0961] Step 13:

[0962] The server continuously analyzes the feedback data and updates and optimizes the training plan as needed.

[0963] Example 1

[0964] 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."

[0965] Conventional olfactory training systems lack the ability to properly evaluate individual users' scent sensitivity and dynamically optimize training plans based on their progress. This means that they are unable to provide effective training tailored to the progression and recovery rate of each user's olfactory disorder. Furthermore, they are unable to collect and analyze real-time feedback data, which makes it difficult to maximize the effectiveness of training.

[0966] 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.

[0967] In this invention, the server includes means for user registration and personal information input, means for collecting sensitivity evaluation data for multiple scent samples as an initial evaluation, means for analyzing the collected initial evaluation data and evaluating the user's initial olfactory sensitivity using a generative model, means for generating an individualized initial training plan based on the analysis results, means for continuously collecting training feedback data and selecting the scent most suitable for the user's olfactory sensitivity using the generative model, and means for predicting progress based on the collected feedback data and optimizing the training plan. This enables individually customized olfactory training and enables effective training tailored to each user's progress. Furthermore, real-time data collection and analysis can maximize the effectiveness of training.

[0968] A "user" is a subject who receives individual olfactory training using this system.

[0969] The "server" is a central control unit that stores and analyzes data sent by users and provides generated training plans to users.

[0970] A "terminal" is a device on which a user installs an app and uses it to input data and provide feedback.

[0971] A "generative model" is an artificial intelligence algorithm that analyzes collected data to assess a user's olfactory sensitivity and generate an optimal training plan.

[0972] "Scent Samples" refers to multiple different scents that a user uses to evaluate and train their sense of smell.

[0973] "Feedback data" refers to data regarding scent strength and discrimination that is input by the user after a training session.

[0974] A "training plan" is a personalized training regimen that uses specific scents based on the user's olfactory sensitivity.

[0975] "Progress" is an indicator that indicates how much the user's olfactory sensitivity has improved through training.

[0976] The "analysis result" is an assessment of the user's olfactory sensitivity resulting from data processed by the generative model.

[0977] "Scent selection" is the process of determining the optimal scent to use in the next training session based on analytical data.

[0978] This invention relates to a system that uses a generative model to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[0979] System configuration and technologies used

[0980] This system consists of a user, a server, and a terminal. The server is responsible for storing and analyzing data, running the generative model, and generating and managing training plans. Specifically, it uses generative AI models such as OpenAI's GPT-3. The terminal is a device, such as a smartphone or tablet, through which the user inputs data and provides feedback.

[0981] System Operation

[0982] User registration and initial evaluation

[0983] The user downloads and installs a dedicated app. They then enter their personal information and create an account. As an initial assessment, the user smells multiple scent samples and fills out a form on their device to evaluate their sensitivity and discrimination ability. The device then sends this evaluation data to a server. The server then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity. Based on the analysis results, the server generates a personalized initial training plan and sends it to the device.

[0984] Personalized scent selection

[0985] The user follows a training plan and periodically smells designated scents. They then input feedback into the device about the perceived strength and ability to distinguish the scents. The device then sends this feedback data to the server, which continuously collects and analyzes this data. Based on the analyzed data, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session.

[0986] Predictive models for predicting progress and optimizing training

[0987] The server uses a generative model to predict the user's progress based on the collected feedback data. The server then updates the training plan based on the prediction results. For example, if the user's sensitivity improves, the server may optimize the training by adding a different scent. The device then notifies the user of the new training plan and allows them to continue training according to the plan's contents.

[0988] Specific examples

[0989] Case 1: User A's initial registration and training start

[0990] User A installs the app and creates an account by entering personal information. Next, he or she smells lemon and rose scent samples and enters their sensitivity to each into the device. The device sends the evaluation data to the server, which analyzes it using a generative AI model. The server determines that User A has a low sensitivity to citrus scents and creates an initial training plan using citrus scents. User A follows this plan and begins training by smelling citrus scents every day.

[0991] Case 2: Progress forecast and training plan updates

[0992] The server analyzes the training feedback entered by User A and predicts that sensitivity has improved. The server generates a new training plan. This plan includes adding a rose-like scent to further check sensitivity. The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[0993] The above is a specific embodiment of the present invention. This system enables users with olfactory impairment to quickly and effectively recover their sense of smell by receiving personalized training.

[0994] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0995] Step 1:

[0996] The user downloads and installs a dedicated app. The input is the download and installation process from the Apple App Store or Google Play Store. The output is the installation of the app on the device. Specifically, the user searches for the app in the device's store and taps the install button.

[0997] Step 2:

[0998] A user creates an account by entering personal information. The input includes personal information such as name, age, and gender, which are entered into the account creation form. The output is that the personal information is saved on the server and the account is created. Specifically, the user enters the required information on the initial setup screen of the app and taps the submit button.

[0999] Step 3:

[1000] As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability. The input is the perceived strength and discrimination of the scent samples, which are entered into the evaluation form. The output is evaluation data generated. In concrete terms, the user smells the provided scent samples and enters their evaluation as a number or comment on the app.

[1001] Step 4:

[1002] The terminal sends initial evaluation data to the server. The input is the evaluation data entered by the user, and the output is received and stored by the server. In concrete terms, the terminal runs a process in the background to transmit the evaluation data over the network.

[1003] Step 5:

[1004] The server uses a generative model to analyze the initial evaluation data and evaluate the user's initial olfactory sensitivity. The input is the evaluation data, and the output is the analysis result. Specifically, the server calls a generative AI model (e.g., GPT-3) and performs data analysis based on the input data.

[1005] Step 6:

[1006] The server generates an individualized initial training plan based on the analysis results and sends it to the device. The input is the analysis results, and the training plan is generated as the output. Specifically, the server creates an optimal training plan using an AI model based on the analysis results and sends this plan to the device.

[1007] Step 7:

[1008] The user follows a training plan and smells designated scents periodically. The training plan is the input, and user feedback data is generated as the output. Specifically, the user follows the app's instructions to smell the designated scents and enters their perceived strength and discrimination into a form.

[1009] Step 8:

[1010] The terminal sends feedback data to the server. The input is the user's feedback data, and the output is the server receiving and storing the data. In concrete terms, the terminal runs a process of sending feedback data over the network in the background.

[1011] Step 9:

[1012] The server analyzes the feedback data, evaluates the user's olfactory sensitivity using a generative model, and selects the optimal scent. The input is the feedback data, and the output is the optimal scent selection result. Specifically, the server calls the generative AI model and performs a reanalysis based on this new data.

[1013] Step 10:

[1014] The server predicts the user's progress and generates a new training plan. The input is the analysis data, and the output is the creation of a new training plan. Specifically, the server analyzes the user's progress data and updates the training plan as necessary.

[1015] Step 11:

[1016] The device notifies the user of the new training plan. The input is the new training plan, and the output is a notification to the user. Specifically, the device notifies the user of the new training plan using a means such as a push notification.

[1017] (Application example 1)

[1018] 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."

[1019] The problem that this invention aims to solve is to provide effective scent training for patients with olfactory impairment after COVID-19 infection. Specifically, it aims to provide a personalized scent training plan for each patient and a method for evaluating and optimizing progress in real time. Another important issue is to incorporate a system with electronic payment functionality, allowing users to easily purchase training fragrances and manage subscriptions.

[1020] 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.

[1021] In this invention, the server includes a means for evaluating a patient's scent sensitivity using a generative model, a means for designing an individual scent training session based on the evaluation, a means for collecting data during training and selecting scents based on the data, and a means for providing electronic payment functionality and managing the purchase and subscription of training fragrances. This maximizes the effect of improving each patient's olfactory disorder, optimizes the progress of the training plan in real time, and allows users to easily purchase the items they need.

[1022] A "generative model" is a model that uses generative AI techniques to generate new data from specific input data.

[1023] "Scent sensitivity assessment" is the process of assessing how sensitive a user is to a particular scent.

[1024] A "training session" is a series of scent training activities designed to improve scent sensitivity.

[1025] An "individual training plan" is a personalized training plan generated based on each user's scent sensitivity.

[1026] "Data collection" is the process of collecting progress and results information entered by users during their workouts.

[1027] "Scent selection" refers to selecting the scent that is best suited to the user based on collected data.

[1028] A "predictive model" is an AI model that uses collected feedback data to predict future outcomes.

[1029] "Electronic Payment Function" means a function that allows users to purchase training materials and manage their subscriptions online.

[1030] A "server" is a computer system that manages the entire system, collects and analyzes data, and provides training plans.

[1031] This invention relates to a system that uses generative models to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. The system consists of a server and a user device (such as a smartphone).

[1032] System Configuration

[1033] This system is centered around a server and implements the following main functions:

[1034] Assessing patients' scent sensitivity using a generative model.

[1035] Design individualized scent training sessions based on the evaluation data.

[1036] Data is collected during training and scents are selected based on the data.

[1037] Build predictive models related to specific scents to forecast progress.

[1038] We provide electronic payment facilities and manage training fragrance purchases and subscriptions.

[1039] Processing procedures and data processing

[1040] The system uses the following major hardware and software components:

[1041] Hardware: Smartphones (e.g., iPhone, Android devices), servers (e.g., AWS, Google Cloud)

[1042] Software: Python, Flask (backend), React Native (frontend), AI libraries for generative models (e.g., TensorFlow, PyTorch)

[1043] User registration and initial evaluation

[1044] The user installs a dedicated application on their smartphone and creates an account by entering their personal information. This information is then stored on the server. As an initial evaluation, the user smells multiple scent samples and enters data evaluating their sensitivity and discrimination ability. The device then sends this evaluation data to the server, which then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[1045] Fragrance selection and training

[1046] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device. The user follows the training plan and smells the designated scents periodically. The user inputs feedback on the strength and discrimination they sensed during the training, which is then sent to the server. The server analyzes the feedback data and selects the scent that is best suited to the next training session based on the user's olfactory sensitivity.

[1047] Progress prediction and training optimization

[1048] Based on the collected feedback data, the server uses a generative model to predict the user's progress and optimizes the training plan accordingly. For example, if the user's sensitivity improves, it may add a different scent. The new training plan is then notified to the device, allowing the user to continue training.

[1049] Electronic payment function

[1050] Purchasing training products and managing subscriptions is done through the app's electronic payment function, allowing users to conveniently purchase the items they need for their training.

[1051] Specific examples

[1052] Case 1: User A's initial registration and training start

[1053] User A installs the app and takes a scent evaluation test. The server analyzes the evaluation data and determines that User A has a low sensitivity to certain scents. The server then creates a training plan using citrus scents and sends it to the device.

[1054] Case 2: Progress forecast and training plan updates

[1055] User A inputs training feedback, and the server analyzes it and determines that sensitivity has improved. A new scent is added to the new training plan, and User A is notified.

[1056] Prompt Sentence Examples

[1057] Below are some example prompts to input to a generative AI model:

[1058] "Generate a personalized olfactory training plan given the user's initial assessment data: {initial_data}."

[1059] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1060] Step 1:

[1061] User registration and initial evaluation

[1062] Users download the application and create an account by entering their personal information, such as name, email address, and password. The device sends this data to the server, which stores it in a database.

[1063] Input: User personal information

[1064] Output: Account data is saved on the server

[1065] Specific operation: The user launches the app on their smartphone, enters their personal information into the registration form, and submits it. The server receives the request and stores the information in a database.

[1066] Step 2:

[1067] Initial scent sensitivity assessment

[1068] The user smells multiple scent samples and evaluates their sensitivity and discrimination ability. The device sends the evaluation data entered by the user to the server. The server analyzes this data using a generative model and evaluates the user's initial olfactory sensitivity.

[1069] Input: User-perceived scent evaluation data

[1070] Output: User's initial scent sensitivity evaluation result

[1071] Specific operation: The server inputs the received evaluation data into the generative AI model to obtain analysis results, which are then stored in a database.

[1072] Step 3:

[1073] Designing individual training plans

[1074] The server generates a personalized training plan based on the initial scent sensitivity assessment results, including which scents the user should smell and how often. The server then transmits the generated training plan to the device.

[1075] Input: Initial scent sensitivity evaluation results

[1076] Output: Individual training plan

[1077] Specific operation: The server uses an AI model to create a training plan based on the user's evaluation results and pushes a notification to the device.

[1078] Step 4:

[1079] Conducting scent training and collecting feedback

[1080] The user follows the training plan provided and smells the designated scent periodically. After each training session, the user inputs feedback on the strength and discrimination of the scent they perceived, and the device sends this feedback to the server.

[1081] Input: User feedback data

[1082] Output: Feedback data is saved on the server

[1083] Specific operation: The user trains regularly and enters the results into the app. The device sends the data to the server.

[1084] Step 5:

[1085] Analysis of feedback data and selection of scents

[1086] The server analyzes the collected feedback data to evaluate the user's progress, uses a generative model to select the next scent that best suits the user, and sends a new training plan to the device to reflect the next training session.

[1087] Input: Feedback data

[1088] Output: Updated training plan

[1089] How it works: The server inputs the feedback data into the AI ​​model, selects the optimal scent based on the analysis results, and updates the training plan. The updated plan is then sent to the device.

[1090] Step 6:

[1091] Progress forecast and training plan updates

[1092] The server predicts the user's training progress based on the collected feedback data. A generative model determines how much the user's sense of smell has improved and optimizes the training plan accordingly. The new training plan is then notified to the device.

[1093] Input: Feedback data

[1094] Output: Optimized training plan

[1095] Specific operation: The server updates the predictive model based on the analysis results, generates an optimized training plan, and sends it to the device.

[1096] Step 7:

[1097] Electronic payment function

[1098] Users purchase the training materials and subscriptions they need within the app. The device sends payment information to the server, which processes the payment. Once the purchase is confirmed, it is reflected in the user's account.

[1099] Input: User's payment information

[1100] Output: Payment completion notification and purchase items reflected in your account

[1101] Specific operation: The user makes a purchase through the app, and the device sends the payment information to the server. The server processes the payment and notifies the user of the result.

[1102] 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.

[1103] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[1104] System Overview

[1105] The system works in the following steps:

[1106] 1. User registration and initial evaluation

[1107] 2. Personalized scent selection and emotion recognition

[1108] 3. Progress prediction and training optimization using predictive models

[1109] Specific explanation of the system's operation

[1110] 1. User registration and initial evaluation

[1111] 1. The user downloads and installs the app. They then enter their personal information to create an account. This information is then stored on the server.

[1112] 2. As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability.

[1113] 3. The device sends this evaluation data to the server, which analyzes it using a generative model to evaluate the user's initial olfactory sensitivity.

[1114] 4. Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[1115] 2. Personalized scent selection and emotion recognition

[1116] 5. The user follows the training plan and smells the designated scents periodically, inputting feedback into the device about the perceived strength and the degree of scent identification.

[1117] 6. The device collects the user's emotional data during training using an emotion engine that also recognizes the user's emotional state.

[1118] 7. Analyze the user's training feedback and emotional data to adjust the training plan. For example, if the user is feeling stressed, a relaxing scent will be selected.

[1119] 8. The device sends this feedback data and emotion data to the server, which continuously collects and analyzes this data.

[1120] 9. Based on the above analytical data, the server selects the scent that best suits the user's olfactory sensitivity and reflects it in the next training session.

[1121] 3. Progress prediction and training optimization using predictive models

[1122] 10. The server uses a generative model to predict the user's progress based on the collected feedback data and emotion data.

[1123] 11. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may optimize the training plan by adding a different scent.

[1124] 12. We can also tailor workout content and timing based on emotional data. For example, we can recommend workouts for times when the user is relaxed.

[1125] 13. The device will notify the user of the new training plan and continue training according to its contents.

[1126] Specific examples

[1127] Case 1: User A's initial registration and training start

[1128] User A installs the app and takes a scent evaluation test and an emotion recognition test. For example, he or she smells lemon and rose and inputs their sensitivity to each scent into the device. At the same time, the emotion engine recognizes User A's emotional state (e.g., relaxed, stressed, etc.).

[1129] The server analyzes this data and determines that User A has a low sensitivity to citrus scents and is in a relaxed state.

[1130] The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[1131] Case 2: Progress forecast and training plan updates

[1132] The server analyzes the training feedback and emotional data entered by user A and predicts that sensitivity is improving and that there are times when the user feels stressed.

[1133] The server generates a new training plan, which includes adding a rose scent and recommending training at times that are relaxing.

[1134] The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[1135] The above is a specific embodiment of the present invention. This system allows patients with olfactory impairment as a result of COVID-19 to receive personalized training, quickly and effectively recovering their sense of smell, and further maximizes the effectiveness of the training by taking into account their emotional state.

[1136] The processing flow will be explained below.

[1137] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[1138] Specific explanation of the system's operation

[1139] Step 1:

[1140] The user downloads and installs a dedicated app, enters personal information, and creates an account. This information is stored on the server.

[1141] Step 2:

[1142] The device displays interfaces for an initial olfactory assessment test and an emotion recognition test to the user. In the initial olfactory assessment test, the user smells multiple scent samples and fills out a form to evaluate their sensitivity and discrimination ability. In the emotion recognition test, the emotion engine detects and evaluates the user's emotional state from their face and voice.

[1143] Step 3:

[1144] The device transmits the olfactory evaluation data and emotional data entered by the user to the server, which then analyzes these data using a generative model to evaluate the user's initial olfactory sensitivity and emotional state.

[1145] Step 4:

[1146] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[1147] Step 5:

[1148] The device displays an initial training plan to the user, who then follows the plan and periodically smells the designated scent.

[1149] Step 6:

[1150] After each training session, the user inputs feedback into the device about the strength and discrimination of the scents they perceived, and the emotion engine also records the user's emotional state during the training session.

[1151] Step 7:

[1152] The device collects feedback data and emotion data from the user and transmits it to the server.

[1153] Step 8:

[1154] The server continuously collects this data and analyzes it using a generative model. Based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and applies it to the next training session. It also takes into account the collected emotional data and adjusts the content and timing of the training.

[1155] Step 9:

[1156] The server uses a generative model to predict the user's progress based on the collected feedback and emotion data. For example, if the user's sensitivity to a particular scent improves, another scent will be added.

[1157] Step 10:

[1158] The server updates the training plan based on the prediction results and emotion data, for example, by generating a plan that recommends training during times when the user is relaxed.

[1159] Step 11:

[1160] The device notifies the user of the new training plan and continues training according to its contents.

[1161] Step 12:

[1162] The user continues training according to the new training plan, and feedback is again entered into the device, with the emotional state also being recorded by the emotion engine.

[1163] Step 13:

[1164] The server continuously analyzes the feedback data and emotional data, updating and optimizing the training plan as needed. By repeating this process, the user can efficiently recover their sense of smell.

[1165] The above is a specific embodiment of the present invention. This system allows patients with olfactory disorders to receive personalized training to quickly and effectively restore their sense of smell, and further maximizes the effectiveness of the training by taking into account their emotional state.

[1166] Example 2

[1167] 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."

[1168] There is a need for effective and personalized scent training for patients suffering from olfactory impairment after COVID-19 infection. Conventional methods have limited training effectiveness because they do not take into account the patient's emotional state, and there are also challenges in predicting progress and optimizing training plans. The present invention aims to comprehensively solve these challenges.

[1169] The identification processing 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 evaluating the patient's scent sensitivity using a generative model, means for designing an individual scent training session based on the evaluation, means for collecting feedback and emotional data during training and selecting scents based on the data, means for building a predictive model related to specific scents and predicting progress toward improvement, and means for adjusting the training plan based on the emotional data. This enables individualized training according to each patient's olfactory sensitivity and emotional state, maximizing the effectiveness of the training.

[1170] A "generative model" is an algorithm that learns specific patterns or features from data and generates or analyzes new data.

[1171] "Scent sensitivity" refers to the strength and ability of an individual to distinguish a particular scent.

[1172] A "training session" refers to a series of scent sniffing trials conducted under specific instructions.

[1173] "Feedback data" refers to information regarding the strength and discrimination of scents felt by the user during training.

[1174] "Emotional Data" means data regarding the emotional state exhibited by a user during training.

[1175] A "predictive model" is an algorithm that uses past data to predict future developments and outcomes.

[1176] A "training plan" is a plan that shows specific training procedures and schedules designed based on the user's progress and condition.

[1177] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[1178] User registration and initial evaluation

[1179] The user downloads and installs a dedicated app. They then enter their personal information and create an account. This information is stored on the server. Then, as an initial assessment, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability. For example, the user might enter their sensitivity to lemon or rose scents as "Strength 3, Discrimination Level 4." The device then sends this evaluation data to the server. The server analyzes this data using a generative AI model to evaluate the user's initial olfactory sensitivity. Based on the analysis results, the server generates a personalized initial training plan and sends it to the device.

[1180] Personalized scent selection and emotion recognition

[1181] The user follows a training plan and periodically smells designated scents. The user then inputs feedback into the device about the perceived strength and scent discrimination. For example, "Rose scent: strength 2, discrimination 3." The device uses an emotion engine that also recognizes the user's emotional state to collect emotional data about the user during training. For example, "relaxed" or "stressed." This feedback and emotional data is sent from the device to a server, which continuously collects and analyzes this data. Based on the analyzed data, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session. For example, if the user is feeling stressed, a scent with a relaxing effect will be selected.

[1182] Predictive models for predicting progress and optimizing training

[1183] The server uses a generative model to predict the user's progress based on the collected feedback data and emotional data. For example, it estimates changes in olfactory sensitivity. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it performs optimization such as adding a new scent. The server also adjusts the training content and timing based on the emotional data. For example, it could recommend training during times when the user is relaxed. The device notifies the user of the new training plan and allows them to continue training according to the plan's contents.

[1184] Specific operation example

[1185] Case 1: User A's initial evaluation and training begins

[1186] User A installs the app and takes a scent evaluation test and an emotion recognition test. For example, he or she smells lemon and rose and inputs his or her sensitivity to each scent into the device. At the same time, the emotion engine recognizes User A's emotional state (e.g., relaxed, stressed, etc.). The server analyzes this data and determines that User A has a low sensitivity to citrus scents and is in a relaxed state. The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[1187] Case 2: Progress prediction and training plan updates

[1188] The server analyzes the training feedback and emotional data entered by User A, and predicts that sensitivity has improved and that there are times when the user feels stressed. The server then generates a new training plan. This plan includes adding a rose-like scent and recommending training at times when relaxation is most effective. The device notifies User A of the new training plan and encourages him or her to carry it out. User A continues training according to this new plan.

[1189] Example prompt sentence:

[1190] "Please smell the designated scent and enter the strength and degree of identification you feel into the terminal."

[1191] "We use an emotion engine to collect data about the emotional state during training."

[1192] The system of the present invention allows patients with olfactory disorders to receive personalized training to quickly and effectively restore their sense of smell, and further maximizes the effectiveness of the training by taking their emotional state into consideration.

[1193] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1194] System program processing flow

[1195] User registration and initial evaluation

[1196] Step 1:

[1197] The user downloads and installs a dedicated app. After installation, the user enters personal information such as name, age, and gender to create an account. This information is sent to the server and registered.

[1198] Input: User's personal information (name, age, gender, etc.)

[1199] Output: Account information registered on the server

[1200] Step 2:

[1201] The user performs the scent evaluation test. Following the instructions displayed on the terminal, the user smells multiple scent samples provided and inputs data into the terminal to evaluate their sensitivity and discrimination.

[1202] Input: User's scent sensitivity data (e.g. lemon strength 3, discrimination 4)

[1203] Output: Evaluation data entered on the terminal

[1204] Step 3:

[1205] The device sends the collected evaluation data to a server, which then analyzes the data using a generative AI model to evaluate the user's initial olfactory sensitivity.

[1206] Input: Scent sensitivity data

[1207] Data processing / calculation: Analysis using generative AI models

[1208] Output: Server-generated initial olfactory sensitivity assessment results

[1209] Step 4:

[1210] Based on the initial olfactory sensitivity assessment results, the server generates a personalized initial training plan and sends it to the device. An example plan would be "smell citrus scents for five minutes every day."

[1211] Input: Initial olfactory sensitivity assessment results

[1212] Data processing / calculation: Training plan generation

[1213] Output: A personalized initial training plan

[1214] Personalized scent selection and emotion recognition

[1215] Step 1:

[1216] The user follows a training plan, smelling designated scents periodically, and inputs feedback into the device about the strength and discrimination of the scents.

[1217] Input: Scent based on training plan

[1218] Output: Feedback data (e.g. rose scent, strength 2, discrimination 3)

[1219] Step 2:

[1220] The device uses an emotion engine to collect emotional data from the user during training, for example, recognizing their emotional state (e.g., relaxed, stressed, etc.).

[1221] Input: User's emotional state

[1222] Output: Emotion data (e.g., relaxed)

[1223] Step 3:

[1224] The device sends feedback data and emotion data to a server, which collects and analyzes the data.

[1225] Input: Feedback and emotion data

[1226] Data processing / calculation: Data analysis

[1227] Output: Analysis results

[1228] Step 4:

[1229] Based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and applies it to the next training session. For example, if the user is feeling stressed, it will select a scent that has a relaxing effect.

[1230] Input: Analysis results

[1231] Data processing / calculation: Adjusting training plans

[1232] Output: Tailored training plan

[1233] Predictive models for predicting progress and optimizing training

[1234] Step 1:

[1235] The server uses a generative model to predict the user's progress based on the collected feedback data and emotion data, and estimates changes in olfactory sensitivity.

[1236] Input: Feedback data, emotion data

[1237] Data processing / calculation: Progress forecast

[1238] Output: Progress forecast results

[1239] Step 2:

[1240] The server generates a new training plan based on the prediction results, for example adding a new scent if olfactory sensitivity improves.

[1241] Input: Progress forecast result

[1242] Data processing / calculation: New training plan generation

[1243] Output: New training plan

[1244] Step 3:

[1245] The device notifies the user of the new training plan, and the user continues training according to the plan.

[1246] Enter: New training plan

[1247] Output: User notification, ongoing training begins

[1248] Through the above processing steps, this system provides personalized training to patients who suffer from olfactory impairment as a result of COVID-19, maximizing the effectiveness of the training.

[1249] (Application example 2)

[1250] 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."

[1251] Providing personalized scent training to patients with olfactory impairment after COVID-19 infection is challenging. Conventional methods have not adequately developed optimal training plans tailored to each patient's olfactory sensitivity and emotional state, and have not adequately assessed and adjusted their progress. Furthermore, there has been a lack of methods to provide a relaxing effect in a virtual space that takes into account the patient's emotional state during training and improves the user experience. As a result, the effectiveness of the training has been limited.

[1252] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1253] In this invention, the server includes: means for evaluating a patient's scent sensitivity using a generative model; means for designing an individual scent training session based on the evaluation; means for collecting data during training and selecting scents based on the data; means for building a predictive model related to specific scents and predicting progress toward improvement; means for a user to receive scent training in a virtual space using a terminal; means for recognizing the user's emotional state using an emotion engine and collecting that data; means for adjusting the training content and timing based on the collected emotional data; and means for changing the environment of the virtual space according to the user's evaluation and emotional state. This makes it possible to provide patients with olfactory impairment after COVID-19 infection with personalized scent training and the relaxing effect of the virtual space, maximizing the effectiveness of the training.

[1254] A "generative model" is a system that includes algorithms that analyze data and generate specific patterns or characteristics.

[1255] "Scent sensitivity" is data that indicates an individual's reaction to and ability to discriminate specific scents.

[1256] A "training session" is a series of activities or trials designed to improve olfactory ability.

[1257] "Data collection" is the process of gathering information about the user's olfactory sensitivity and emotional state.

[1258] A "predictive model" is an algorithm that predicts future progress or results based on collected data.

[1259] A "terminal" is a computer device used by a user to receive scent training in a virtual space.

[1260] An "emotion engine" is software that analyzes a user's emotional state and collects that data.

[1261] A "virtual space" is a virtual environment where users can experience training or relaxation.

[1262] "Means for changing the environment" refers to technology that customizes various elements in a virtual space according to the user's evaluation and emotional state.

[1263] The "relaxation effect" is an effect that provides a sensation or experience that puts the user in a relaxed state.

[1264] This invention is a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. The system consists of a server and a terminal (user device). The server uses the generative model to generate a personalized training plan, and the terminal implements the scent training and recognizes and collects the user's emotional state. It can also provide a relaxing environment using a virtual space.

[1265] System Overview

[1266] 1. User Registration and Initial Evaluation:

[1267] Users download a dedicated app and install it on their device. They then enter their personal information to create an account. This information is then stored on the server.

[1268] As an initial evaluation, the user smells multiple scent samples and inputs data assessing their sensitivity and discrimination ability.

[1269] The device transmits this evaluation data to a server, which analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[1270] 2. Personalized scent selection and emotion recognition:

[1271] The user follows a training plan and periodically smells designated scents, while inputting feedback into the device about the scent's strength and discrimination.

[1272] The device uses an emotion engine to collect the user's emotional state during training, and this data is sent to the server along with the feedback data.

[1273] The server continuously collects and analyzes this data, and based on the analysis results, selects the next scent that best suits the user's situation and reflects it in the training plan.

[1274] 3. Predictive models for progress forecasting and training optimization:

[1275] The server uses the collected feedback data and emotion data to build a generative model and predict the user's progress.

[1276] Based on the prediction results, the server updates the training plan and performs optimizations such as adding new scents.

[1277] The content and timing of training is also adjusted based on emotional data.

[1278] 4. Relaxing virtual experience:

[1279] The device uses a virtual space to provide a relaxing environment for users to undergo scent training, which includes visual and auditory elements tailored to specific scents.

[1280] Specific explanation of the system's operation

[1281] Hardware: Devices such as smartphones and tablets

[1282] Software: Server-side application using Flask (Python), emotion engine, virtual space generation tool

[1283] Specific examples

[1284] Case 1: User A's initial registration and training start

[1285] User A installs the app and takes the lemon and rose scent evaluation test and emotion recognition test.

[1286] For example, it may be determined that user A has a low sensitivity to citrus scents and is in a relaxed state.

[1287] An initial training plan using a citrus scent is created, and User A begins training according to this plan.

[1288] Case 2: Progress forecast and training plan updates

[1289] User A's feedback data and emotional data are collected and analyzed to predict that his sensitivity has improved and that there are times when he feels stressed.

[1290] The server generates a new plan that adds a rose-like scent and recommends training during a relaxing time. User A continues training according to the new plan.

[1291] Prompt Sentence Examples

[1292] Based on the user's olfactory sensitivity and emotional data, select the best scent for the next training session. The best time is when the user is less sensitive to citrus scents and is more relaxed. Generate a list of scents to use in the next session.

[1293] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1294] Step 1:

[1295] The user downloads a dedicated app and installs it on their device. They then enter their personal information to create an account. This information is sent from the device to the server and stored on the server.

[1296] Input: User's personal information (name, age, gender, etc.)

[1297] Processing: The terminal sends the user-entered information to the server to create an account.

[1298] Output: User account information stored on the server

[1299] Step 2:

[1300] The user performs an initial evaluation by smelling multiple scent samples and inputting data evaluating their sensitivity and discrimination ability into the terminal, which then transmits this evaluation data to the server.

[1301] Input: User's scent sensitivity evaluation data (scent concentration, discrimination ability, etc.)

[1302] Processing: The device sends the evaluation data to the server, which analyzes these data using the generative model.

[1303] Output: Initial olfactory sensitivity assessment results analyzed by the server

[1304] Step 3:

[1305] Based on the analysis results, the server evaluates the user's initial olfactory sensitivity and generates a personalized training plan, which is then sent to the device.

[1306] Input: Initial olfactory sensitivity assessment results

[1307] Processing: The server uses the generative model to generate a personalized training plan.

[1308] Output: A personalized training plan sent to your device

[1309] Step 4:

[1310] The user periodically smells designated scents according to the training plan, and provides feedback on the scent's strength and discrimination. The device also evaluates the user's emotional state using an emotion engine and transmits the data to the server.

[1311] Input: User training feedback data, emotional state data

[1312] Processing: The device collects feedback data and emotion data and sends them to the server.

[1313] Output: Training feedback data and emotional state data sent to the server

[1314] Step 5:

[1315] The server analyzes the collected data and adjusts the training plan, scheduling training at times that are most relaxing based on emotional data.

[1316] Input: Training feedback data, emotional state data

[1317] Processing: The server analyzes the data and generates a new training plan.

[1318] Output: Updated training plan sent to the user

[1319] Step 6:

[1320] While the user is training in the virtual space, the device provides images and sounds with a relaxing effect. The virtual environment is adjusted according to the user's evaluation and emotional state.

[1321] Input: User rating data, emotional state data

[1322] Processing: The device adjusts the virtual environment and provides relaxing content.

[1323] Output: A customized virtual relaxation environment experienced by the user.

[1324] 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.

[1325] 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.

[1326] 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.

[1327] [Fourth embodiment]

[1328] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1329] 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.

[1330] 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).

[1331] 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.

[1332] 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.

[1333] 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).

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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."

[1341] This invention relates to a system that uses a generative model to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[1342] System Overview

[1343] The system works in the following steps:

[1344] 1. User registration and initial evaluation

[1345] 2. Personalized scent selection

[1346] 3. Progress prediction and training optimization using predictive models

[1347] Specific explanation of the system's operation

[1348] 1. User registration and initial evaluation

[1349] 1. The user downloads and installs the app. They then enter their personal information to create an account. This information is then stored on the server.

[1350] 2. As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability.

[1351] 3. The device sends this evaluation data to the server, which analyzes it using a generative model to evaluate the user's initial olfactory sensitivity.

[1352] 4. Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[1353] 2. Personalized scent selection

[1354] 5. The user follows the training plan and smells the designated scents periodically, inputting feedback into the device about the perceived strength and the degree of scent identification.

[1355] 6. The device sends this feedback data to the server, which continuously collects and analyzes this data.

[1356] 7. Based on the above analytical data, the server selects the scent that best suits the user's olfactory sensitivity and reflects it in the next training session.

[1357] 3. Progress prediction and training optimization using predictive models

[1358] 8. The server uses the generative model to predict the user's progress based on the collected feedback data.

[1359] 9. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may optimize the plan by adding a different scent.

[1360] 10. The device will notify the user of the new training plan and continue training according to its contents.

[1361] Specific examples

[1362] Case 1: User A's initial registration and training start

[1363] User A installs the app and performs a scent evaluation test. For example, he smells lemon and rose scents and enters his sensitivity to each scent into his device.

[1364] The server analyzes this data and finds that User A is particularly sensitive to citrus scents.

[1365] The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[1366] Case 2: Progress forecast and training plan updates

[1367] The server analyzes the training feedback entered by user A and predicts that sensitivity is improving.

[1368] The server generates a new training plan, which includes adding a rose scent to further test the sensitivity, etc.

[1369] The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[1370] The above is a specific embodiment of the present invention. This system enables patients with olfactory impairment as a result of COVID-19 to quickly and effectively recover their sense of smell by receiving personalized training.

[1371] The processing flow will be explained below.

[1372] Step 1:

[1373] Users download and install a dedicated app, enter their personal information, and create an account. This information is stored on the server.

[1374] Step 2:

[1375] The device displays an interface for an initial olfactory evaluation test to the user, who then smells multiple scent samples and fills out a form to evaluate their sensitivity and discrimination ability.

[1376] Step 3:

[1377] The device sends the evaluation data entered by the user to the server, which then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[1378] Step 4:

[1379] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[1380] Step 5:

[1381] The device displays an initial training plan to the user, who then follows the plan and periodically smells the designated scent.

[1382] Step 6:

[1383] After each training session, the user inputs feedback into the device about the strength of the scents they perceived and their ability to identify them.

[1384] Step 7:

[1385] The terminal collects the feedback data entered by the user and transmits it to the server.

[1386] Step 8:

[1387] The server continuously collects and analyzes this data, and based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session.

[1388] Step 9:

[1389] The server uses a generative model to predict the user's progress based on the collected feedback data.

[1390] Step 10:

[1391] The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may add a different scent to optimize the training plan.

[1392] Step 11:

[1393] The device notifies the user of the new training plan and continues training according to its contents.

[1394] Step 12:

[1395] The user continues training according to the new training plan, and feedback is again entered into the device and sent to the server.

[1396] Step 13:

[1397] The server continuously analyzes the feedback data and updates and optimizes the training plan as needed.

[1398] Example 1

[1399] 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."

[1400] Conventional olfactory training systems lack the ability to properly evaluate individual users' scent sensitivity and dynamically optimize training plans based on their progress. This means that they are unable to provide effective training tailored to the progression and recovery rate of each user's olfactory disorder. Furthermore, they are unable to collect and analyze real-time feedback data, which makes it difficult to maximize the effectiveness of training.

[1401] 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.

[1402] In this invention, the server includes means for user registration and personal information input, means for collecting sensitivity evaluation data for multiple scent samples as an initial evaluation, means for analyzing the collected initial evaluation data and evaluating the user's initial olfactory sensitivity using a generative model, means for generating an individualized initial training plan based on the analysis results, means for continuously collecting training feedback data and selecting the scent most suitable for the user's olfactory sensitivity using the generative model, and means for predicting progress based on the collected feedback data and optimizing the training plan. This enables individually customized olfactory training and enables effective training tailored to each user's progress. Furthermore, real-time data collection and analysis can maximize the effectiveness of training.

[1403] A "user" is a subject who receives individual olfactory training using this system.

[1404] The "server" is a central control unit that stores and analyzes data sent by users and provides generated training plans to users.

[1405] A "terminal" is a device on which a user installs an app and uses it to input data and provide feedback.

[1406] A "generative model" is an artificial intelligence algorithm that analyzes collected data to assess a user's olfactory sensitivity and generate an optimal training plan.

[1407] "Scent Samples" refers to multiple different scents that a user uses to evaluate and train their sense of smell.

[1408] "Feedback data" refers to data regarding scent strength and discrimination that is input by the user after a training session.

[1409] A "training plan" is a personalized training regimen that uses specific scents based on the user's olfactory sensitivity.

[1410] "Progress" is an indicator that indicates how much the user's olfactory sensitivity has improved through training.

[1411] The "analysis result" is an assessment of the user's olfactory sensitivity resulting from data processed by the generative model.

[1412] "Scent selection" is the process of determining the optimal scent to use in the next training session based on analytical data.

[1413] This invention relates to a system that uses a generative model to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[1414] System configuration and technologies used

[1415] This system consists of a user, a server, and a terminal. The server is responsible for storing and analyzing data, running the generative model, and generating and managing training plans. Specifically, it uses generative AI models such as OpenAI's GPT-3. The terminal is a device, such as a smartphone or tablet, through which the user inputs data and provides feedback.

[1416] System Operation

[1417] User registration and initial evaluation

[1418] The user downloads and installs a dedicated app. They then enter their personal information and create an account. As an initial assessment, the user smells multiple scent samples and fills out a form on their device to evaluate their sensitivity and discrimination ability. The device then sends this evaluation data to a server. The server then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity. Based on the analysis results, the server generates a personalized initial training plan and sends it to the device.

[1419] Personalized scent selection

[1420] The user follows a training plan and periodically smells designated scents. They then input feedback into the device about the perceived strength and ability to distinguish the scents. The device then sends this feedback data to the server, which continuously collects and analyzes this data. Based on the analyzed data, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session.

[1421] Predictive models for predicting progress and optimizing training

[1422] The server uses a generative model to predict the user's progress based on the collected feedback data. The server then updates the training plan based on the prediction results. For example, if the user's sensitivity improves, the server may optimize the training by adding a different scent. The device then notifies the user of the new training plan and allows them to continue training according to the plan's contents.

[1423] Specific examples

[1424] Case 1: User A's initial registration and training start

[1425] User A installs the app and creates an account by entering personal information. Next, he or she smells lemon and rose scent samples and enters their sensitivity to each into the device. The device sends the evaluation data to the server, which analyzes it using a generative AI model. The server determines that User A has a low sensitivity to citrus scents and creates an initial training plan using citrus scents. User A follows this plan and begins training by smelling citrus scents every day.

[1426] Case 2: Progress forecast and training plan updates

[1427] The server analyzes the training feedback entered by User A and predicts that sensitivity has improved. The server generates a new training plan. This plan includes adding a rose-like scent to further check sensitivity. The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[1428] The above is a specific embodiment of the present invention. This system enables users with olfactory impairment to quickly and effectively recover their sense of smell by receiving personalized training.

[1429] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1430] Step 1:

[1431] The user downloads and installs a dedicated app. The input is the download and installation process from the Apple App Store or Google Play Store. The output is the installation of the app on the device. Specifically, the user searches for the app in the device's store and taps the install button.

[1432] Step 2:

[1433] A user creates an account by entering personal information. The input includes personal information such as name, age, and gender, which are entered into the account creation form. The output is that the personal information is saved on the server and the account is created. Specifically, the user enters the required information on the initial setup screen of the app and taps the submit button.

[1434] Step 3:

[1435] As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability. The input is the perceived strength and discrimination of the scent samples, which are entered into the evaluation form. The output is evaluation data generated. In concrete terms, the user smells the provided scent samples and enters their evaluation as a number or comment on the app.

[1436] Step 4:

[1437] The terminal sends initial evaluation data to the server. The input is the evaluation data entered by the user, and the output is received and stored by the server. In concrete terms, the terminal runs a process in the background to transmit the evaluation data over the network.

[1438] Step 5:

[1439] The server uses a generative model to analyze the initial evaluation data and evaluate the user's initial olfactory sensitivity. The input is the evaluation data, and the output is the analysis result. Specifically, the server calls a generative AI model (e.g., GPT-3) and performs data analysis based on the input data.

[1440] Step 6:

[1441] The server generates an individualized initial training plan based on the analysis results and sends it to the device. The input is the analysis results, and the training plan is generated as the output. Specifically, the server creates an optimal training plan using an AI model based on the analysis results and sends this plan to the device.

[1442] Step 7:

[1443] The user follows a training plan and smells designated scents periodically. The training plan is the input, and user feedback data is generated as the output. Specifically, the user follows the app's instructions to smell the designated scents and enters their perceived strength and discrimination into a form.

[1444] Step 8:

[1445] The terminal sends feedback data to the server. The input is the user's feedback data, and the output is the server receiving and storing the data. In concrete terms, the terminal runs a process of sending feedback data over the network in the background.

[1446] Step 9:

[1447] The server analyzes the feedback data, evaluates the user's olfactory sensitivity using a generative model, and selects the optimal scent. The input is the feedback data, and the output is the optimal scent selection result. Specifically, the server calls the generative AI model and performs a reanalysis based on this new data.

[1448] Step 10:

[1449] The server predicts the user's progress and generates a new training plan. The input is the analysis data, and the output is the creation of a new training plan. Specifically, the server analyzes the user's progress data and updates the training plan as necessary.

[1450] Step 11:

[1451] The device notifies the user of the new training plan. The input is the new training plan, and the output is a notification to the user. Specifically, the device notifies the user of the new training plan using a means such as a push notification.

[1452] (Application example 1)

[1453] 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."

[1454] The problem that this invention aims to solve is to provide effective scent training for patients with olfactory impairment after COVID-19 infection. Specifically, it aims to provide a personalized scent training plan for each patient and a method for evaluating and optimizing progress in real time. Another important issue is to incorporate a system with electronic payment functionality, allowing users to easily purchase training fragrances and manage subscriptions.

[1455] 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.

[1456] In this invention, the server includes a means for evaluating a patient's scent sensitivity using a generative model, a means for designing an individual scent training session based on the evaluation, a means for collecting data during training and selecting scents based on the data, and a means for providing electronic payment functionality and managing the purchase and subscription of training fragrances. This maximizes the effect of improving each patient's olfactory disorder, optimizes the progress of the training plan in real time, and allows users to easily purchase the items they need.

[1457] A "generative model" is a model that uses generative AI techniques to generate new data from specific input data.

[1458] "Scent sensitivity assessment" is the process of assessing how sensitive a user is to a particular scent.

[1459] A "training session" is a series of scent training activities designed to improve scent sensitivity.

[1460] An "individual training plan" is a personalized training plan generated based on each user's scent sensitivity.

[1461] "Data collection" is the process of collecting progress and results information entered by users during their workouts.

[1462] "Scent selection" refers to selecting the scent that is best suited to the user based on collected data.

[1463] A "predictive model" is an AI model that uses collected feedback data to predict future outcomes.

[1464] "Electronic Payment Function" means a function that allows users to purchase training materials and manage their subscriptions online.

[1465] A "server" is a computer system that manages the entire system, collects and analyzes data, and provides training plans.

[1466] This invention relates to a system that uses generative models to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. The system consists of a server and a user device (such as a smartphone).

[1467] System Configuration

[1468] This system is centered around a server and implements the following main functions:

[1469] Assessing patients' scent sensitivity using a generative model.

[1470] Design individualized scent training sessions based on the evaluation data.

[1471] Data is collected during training and scents are selected based on the data.

[1472] Build predictive models related to specific scents to forecast progress.

[1473] We provide electronic payment facilities and manage training fragrance purchases and subscriptions.

[1474] Processing procedures and data processing

[1475] The system uses the following major hardware and software components:

[1476] Hardware: Smartphones (e.g., iPhone, Android devices), servers (e.g., AWS, Google Cloud)

[1477] Software: Python, Flask (backend), React Native (frontend), AI libraries for generative models (e.g., TensorFlow, PyTorch)

[1478] User registration and initial evaluation

[1479] The user installs a dedicated application on their smartphone and creates an account by entering their personal information. This information is then stored on the server. As an initial evaluation, the user smells multiple scent samples and enters data evaluating their sensitivity and discrimination ability. The device then sends this evaluation data to the server, which then analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[1480] Fragrance selection and training

[1481] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device. The user follows the training plan and smells the designated scents periodically. The user inputs feedback on the strength and discrimination they sensed during the training, which is then sent to the server. The server analyzes the feedback data and selects the scent that is best suited to the next training session based on the user's olfactory sensitivity.

[1482] Progress prediction and training optimization

[1483] Based on the collected feedback data, the server uses a generative model to predict the user's progress and optimizes the training plan accordingly. For example, if the user's sensitivity improves, it may add a different scent. The new training plan is then notified to the device, allowing the user to continue training.

[1484] Electronic payment function

[1485] Purchasing training products and managing subscriptions is done through the app's electronic payment function, allowing users to conveniently purchase the items they need for their training.

[1486] Specific examples

[1487] Case 1: User A's initial registration and training start

[1488] User A installs the app and takes a scent evaluation test. The server analyzes the evaluation data and determines that User A has a low sensitivity to certain scents. The server then creates a training plan using citrus scents and sends it to the device.

[1489] Case 2: Progress forecast and training plan updates

[1490] User A inputs training feedback, and the server analyzes it and determines that sensitivity has improved. A new scent is added to the new training plan, and User A is notified.

[1491] Prompt Sentence Examples

[1492] Below are some example prompts to input to a generative AI model:

[1493] "Generate a personalized olfactory training plan given the user's initial assessment data: {initial_data}."

[1494] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1495] Step 1:

[1496] User registration and initial evaluation

[1497] Users download the application and create an account by entering their personal information, such as name, email address, and password. The device sends this data to the server, which stores it in a database.

[1498] Input: User personal information

[1499] Output: Account data is saved on the server

[1500] Specific operation: The user launches the app on their smartphone, enters their personal information into the registration form, and submits it. The server receives the request and stores the information in a database.

[1501] Step 2:

[1502] Initial scent sensitivity assessment

[1503] The user smells multiple scent samples and evaluates their sensitivity and discrimination ability. The device sends the evaluation data entered by the user to the server. The server analyzes this data using a generative model and evaluates the user's initial olfactory sensitivity.

[1504] Input: User-perceived scent evaluation data

[1505] Output: User's initial scent sensitivity evaluation result

[1506] Specific operation: The server inputs the received evaluation data into the generative AI model to obtain analysis results, which are then stored in a database.

[1507] Step 3:

[1508] Designing individual training plans

[1509] The server generates a personalized training plan based on the initial scent sensitivity assessment results, including which scents the user should smell and how often. The server then transmits the generated training plan to the device.

[1510] Input: Initial scent sensitivity evaluation results

[1511] Output: Individual training plan

[1512] Specific operation: The server uses an AI model to create a training plan based on the user's evaluation results and pushes a notification to the device.

[1513] Step 4:

[1514] Conducting scent training and collecting feedback

[1515] The user follows the training plan provided and smells the designated scent periodically. After each training session, the user inputs feedback on the strength and discrimination of the scent they perceived, and the device sends this feedback to the server.

[1516] Input: User feedback data

[1517] Output: Feedback data is saved on the server

[1518] Specific operation: The user trains regularly and enters the results into the app. The device sends the data to the server.

[1519] Step 5:

[1520] Analysis of feedback data and selection of scents

[1521] The server analyzes the collected feedback data to evaluate the user's progress, uses a generative model to select the next scent that best suits the user, and sends a new training plan to the device to reflect the next training session.

[1522] Input: Feedback data

[1523] Output: Updated training plan

[1524] How it works: The server inputs the feedback data into the AI ​​model, selects the optimal scent based on the analysis results, and updates the training plan. The updated plan is then sent to the device.

[1525] Step 6:

[1526] Progress forecast and training plan updates

[1527] The server predicts the user's training progress based on the collected feedback data. A generative model determines how much the user's sense of smell has improved and optimizes the training plan accordingly. The new training plan is then notified to the device.

[1528] Input: Feedback data

[1529] Output: Optimized training plan

[1530] Specific operation: The server updates the predictive model based on the analysis results, generates an optimized training plan, and sends it to the device.

[1531] Step 7:

[1532] Electronic payment function

[1533] Users purchase the training materials and subscriptions they need within the app. The device sends payment information to the server, which processes the payment. Once the purchase is confirmed, it is reflected in the user's account.

[1534] Input: User's payment information

[1535] Output: Payment completion notification and purchase items reflected in your account

[1536] Specific operation: The user makes a purchase through the app, and the device sends the payment information to the server. The server processes the payment and notifies the user of the result.

[1537] 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.

[1538] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[1539] System Overview

[1540] The system works in the following steps:

[1541] 1. User registration and initial evaluation

[1542] 2. Personalized scent selection and emotion recognition

[1543] 3. Progress prediction and training optimization using predictive models

[1544] Specific explanation of the system's operation

[1545] 1. User registration and initial evaluation

[1546] 1. The user downloads and installs the app. They then enter their personal information to create an account. This information is then stored on the server.

[1547] 2. As an initial evaluation, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability.

[1548] 3. The device sends this evaluation data to the server, which analyzes it using a generative model to evaluate the user's initial olfactory sensitivity.

[1549] 4. Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[1550] 2. Personalized scent selection and emotion recognition

[1551] 5. The user follows the training plan and smells the designated scents periodically, inputting feedback into the device about the perceived strength and the degree of scent identification.

[1552] 6. The device collects the user's emotional data during training using an emotion engine that also recognizes the user's emotional state.

[1553] 7. Analyze the user's training feedback and emotional data to adjust the training plan. For example, if the user is feeling stressed, a relaxing scent will be selected.

[1554] 8. The device sends this feedback data and emotion data to the server, which continuously collects and analyzes this data.

[1555] 9. Based on the above analytical data, the server selects the scent that best suits the user's olfactory sensitivity and reflects it in the next training session.

[1556] 3. Progress prediction and training optimization using predictive models

[1557] 10. The server uses a generative model to predict the user's progress based on the collected feedback data and emotion data.

[1558] 11. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it may optimize the training plan by adding a different scent.

[1559] 12. We can also tailor workout content and timing based on emotional data. For example, we can recommend workouts for times when the user is relaxed.

[1560] 13. The device will notify the user of the new training plan and continue training according to its contents.

[1561] Specific examples

[1562] Case 1: User A's initial registration and training start

[1563] User A installs the app and takes a scent evaluation test and an emotion recognition test. For example, he or she smells lemon and rose and inputs their sensitivity to each scent into the device. At the same time, the emotion engine recognizes User A's emotional state (e.g., relaxed, stressed, etc.).

[1564] The server analyzes this data and determines that User A has a low sensitivity to citrus scents and is in a relaxed state.

[1565] The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[1566] Case 2: Progress forecast and training plan updates

[1567] The server analyzes the training feedback and emotional data entered by user A and predicts that sensitivity is improving and that there are times when the user feels stressed.

[1568] The server generates a new training plan, which includes adding a rose scent and recommending training at times that are relaxing.

[1569] The device notifies User A of the new training plan and encourages him to carry it out. User A continues training according to this new plan.

[1570] The above is a specific embodiment of the present invention. This system allows patients with olfactory impairment as a result of COVID-19 to receive personalized training, quickly and effectively recovering their sense of smell, and further maximizes the effectiveness of the training by taking into account their emotional state.

[1571] The processing flow will be explained below.

[1572] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[1573] Specific explanation of the system's operation

[1574] Step 1:

[1575] The user downloads and installs a dedicated app, enters personal information, and creates an account. This information is stored on the server.

[1576] Step 2:

[1577] The device displays interfaces for an initial olfactory assessment test and an emotion recognition test to the user. In the initial olfactory assessment test, the user smells multiple scent samples and fills out a form to evaluate their sensitivity and discrimination ability. In the emotion recognition test, the emotion engine detects and evaluates the user's emotional state from their face and voice.

[1578] Step 3:

[1579] The device transmits the olfactory evaluation data and emotional data entered by the user to the server, which then analyzes these data using a generative model to evaluate the user's initial olfactory sensitivity and emotional state.

[1580] Step 4:

[1581] Based on the analysis results, the server generates an individualized initial training plan and sends it to the device.

[1582] Step 5:

[1583] The device displays an initial training plan to the user, who then follows the plan and periodically smells the designated scent.

[1584] Step 6:

[1585] After each training session, the user inputs feedback into the device about the strength and discrimination of the scents they perceived, and the emotion engine also records the user's emotional state during the training session.

[1586] Step 7:

[1587] The device collects feedback data and emotion data from the user and transmits it to the server.

[1588] Step 8:

[1589] The server continuously collects this data and analyzes it using a generative model. Based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and applies it to the next training session. It also takes into account the collected emotional data and adjusts the content and timing of the training.

[1590] Step 9:

[1591] The server uses a generative model to predict the user's progress based on the collected feedback and emotion data. For example, if the user's sensitivity to a particular scent improves, another scent will be added.

[1592] Step 10:

[1593] The server updates the training plan based on the prediction results and emotion data, for example, by generating a plan that recommends training during times when the user is relaxed.

[1594] Step 11:

[1595] The device notifies the user of the new training plan and continues training according to its contents.

[1596] Step 12:

[1597] The user continues training according to the new training plan, and feedback is again entered into the device, with the emotional state also being recorded by the emotion engine.

[1598] Step 13:

[1599] The server continuously analyzes the feedback data and emotional data, updating and optimizing the training plan as needed. By repeating this process, the user can efficiently recover their sense of smell.

[1600] The above is a specific embodiment of the present invention. This system allows patients with olfactory disorders to receive personalized training to quickly and effectively restore their sense of smell, and further maximizes the effectiveness of the training by taking into account their emotional state.

[1601] Example 2

[1602] 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."

[1603] There is a need for effective and personalized scent training for patients suffering from olfactory impairment after COVID-19 infection. Conventional methods have limited training effectiveness because they do not take into account the patient's emotional state, and there are also challenges in predicting progress and optimizing training plans. The present invention aims to comprehensively solve these challenges.

[1604] The identification processing 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 evaluating the patient's scent sensitivity using a generative model, means for designing an individual scent training session based on the evaluation, means for collecting feedback and emotional data during training and selecting scents based on the data, means for building a predictive model related to specific scents and predicting progress toward improvement, and means for adjusting the training plan based on the emotional data. This enables individualized training according to each patient's olfactory sensitivity and emotional state, maximizing the effectiveness of the training.

[1605] A "generative model" is an algorithm that learns specific patterns or features from data and generates or analyzes new data.

[1606] "Scent sensitivity" refers to the strength and ability of an individual to distinguish a particular scent.

[1607] A "training session" refers to a series of scent sniffing trials conducted under specific instructions.

[1608] "Feedback data" refers to information regarding the strength and discrimination of scents felt by the user during training.

[1609] "Emotional Data" means data regarding the emotional state exhibited by a user during training.

[1610] A "predictive model" is an algorithm that uses past data to predict future developments and outcomes.

[1611] A "training plan" is a plan that shows specific training procedures and schedules designed based on the user's progress and condition.

[1612] This invention relates to a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory disorders after COVID-19 infection. This system consists of a server and a terminal (user device) and operates as follows.

[1613] User registration and initial evaluation

[1614] The user downloads and installs a dedicated app. They then enter their personal information and create an account. This information is stored on the server. Then, as an initial assessment, the user smells multiple scent samples and fills out a form on the device to evaluate their sensitivity and discrimination ability. For example, the user might enter their sensitivity to lemon or rose scents as "Strength 3, Discrimination Level 4." The device then sends this evaluation data to the server. The server analyzes this data using a generative AI model to evaluate the user's initial olfactory sensitivity. Based on the analysis results, the server generates a personalized initial training plan and sends it to the device.

[1615] Personalized scent selection and emotion recognition

[1616] The user follows a training plan and periodically smells designated scents. The user then inputs feedback into the device about the perceived strength and scent discrimination. For example, "Rose scent: strength 2, discrimination 3." The device uses an emotion engine that also recognizes the user's emotional state to collect emotional data about the user during training. For example, "relaxed" or "stressed." This feedback and emotional data is sent from the device to a server, which continuously collects and analyzes this data. Based on the analyzed data, the server selects the scent that best suits the user's olfactory sensitivity and incorporates it into the next training session. For example, if the user is feeling stressed, a scent with a relaxing effect will be selected.

[1617] Predictive models for predicting progress and optimizing training

[1618] The server uses a generative model to predict the user's progress based on the collected feedback data and emotional data. For example, it estimates changes in olfactory sensitivity. The server updates the training plan based on the prediction results. For example, if the user's sensitivity improves, it performs optimization such as adding a new scent. The server also adjusts the training content and timing based on the emotional data. For example, it could recommend training during times when the user is relaxed. The device notifies the user of the new training plan and allows them to continue training according to the plan's contents.

[1619] Specific operation example

[1620] Case 1: User A's initial evaluation and training begins

[1621] User A installs the app and takes a scent evaluation test and an emotion recognition test. For example, he or she smells lemon and rose and inputs his or her sensitivity to each scent into the device. At the same time, the emotion engine recognizes User A's emotional state (e.g., relaxed, stressed, etc.). The server analyzes this data and determines that User A has a low sensitivity to citrus scents and is in a relaxed state. The server creates an initial training plan using citrus scents and sends it to the device. User A follows this plan and begins training by smelling citrus scents every day.

[1622] Case 2: Progress prediction and training plan updates

[1623] The server analyzes the training feedback and emotional data entered by User A, and predicts that sensitivity has improved and that there are times when the user feels stressed. The server then generates a new training plan. This plan includes adding a rose-like scent and recommending training at times when relaxation is most effective. The device notifies User A of the new training plan and encourages him or her to carry it out. User A continues training according to this new plan.

[1624] Example prompt sentence:

[1625] "Please smell the designated scent and enter the strength and degree of identification you feel into the terminal."

[1626] "We use an emotion engine to collect data about the emotional state during training."

[1627] The system of the present invention allows patients with olfactory disorders to receive personalized training to quickly and effectively restore their sense of smell, and further maximizes the effectiveness of the training by taking their emotional state into consideration.

[1628] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1629] System program processing flow

[1630] User registration and initial evaluation

[1631] Step 1:

[1632] The user downloads and installs a dedicated app. After installation, the user enters personal information such as name, age, and gender to create an account. This information is sent to the server and registered.

[1633] Input: User's personal information (name, age, gender, etc.)

[1634] Output: Account information registered on the server

[1635] Step 2:

[1636] The user performs the scent evaluation test. Following the instructions displayed on the terminal, the user smells multiple scent samples provided and inputs data into the terminal to evaluate their sensitivity and discrimination.

[1637] Input: User's scent sensitivity data (e.g. lemon strength 3, discrimination 4)

[1638] Output: Evaluation data entered on the terminal

[1639] Step 3:

[1640] The device sends the collected evaluation data to a server, which then analyzes the data using a generative AI model to evaluate the user's initial olfactory sensitivity.

[1641] Input: Scent sensitivity data

[1642] Data processing / calculation: Analysis using generative AI models

[1643] Output: Server-generated initial olfactory sensitivity assessment results

[1644] Step 4:

[1645] Based on the initial olfactory sensitivity assessment results, the server generates a personalized initial training plan and sends it to the device. An example plan would be "smell citrus scents for five minutes every day."

[1646] Input: Initial olfactory sensitivity assessment results

[1647] Data processing / calculation: Training plan generation

[1648] Output: A personalized initial training plan

[1649] Personalized scent selection and emotion recognition

[1650] Step 1:

[1651] The user follows a training plan, smelling designated scents periodically, and inputs feedback into the device about the strength and discrimination of the scents.

[1652] Input: Scent based on training plan

[1653] Output: Feedback data (e.g. rose scent, strength 2, discrimination 3)

[1654] Step 2:

[1655] The device uses an emotion engine to collect emotional data from the user during training, for example, recognizing their emotional state (e.g., relaxed, stressed, etc.).

[1656] Input: User's emotional state

[1657] Output: Emotion data (e.g., relaxed)

[1658] Step 3:

[1659] The device sends feedback data and emotion data to a server, which collects and analyzes the data.

[1660] Input: Feedback and emotion data

[1661] Data processing / calculation: Data analysis

[1662] Output: Analysis results

[1663] Step 4:

[1664] Based on the analysis results, the server selects the scent that best suits the user's olfactory sensitivity and applies it to the next training session. For example, if the user is feeling stressed, it will select a scent that has a relaxing effect.

[1665] Input: Analysis results

[1666] Data processing / calculation: Adjusting training plans

[1667] Output: Tailored training plan

[1668] Predictive models for predicting progress and optimizing training

[1669] Step 1:

[1670] The server uses a generative model to predict the user's progress based on the collected feedback data and emotion data, and estimates changes in olfactory sensitivity.

[1671] Input: Feedback data, emotion data

[1672] Data processing / calculation: Progress forecast

[1673] Output: Progress forecast results

[1674] Step 2:

[1675] The server generates a new training plan based on the prediction results, for example adding a new scent if olfactory sensitivity improves.

[1676] Input: Progress forecast result

[1677] Data processing / calculation: New training plan generation

[1678] Output: New training plan

[1679] Step 3:

[1680] The device notifies the user of the new training plan, and the user continues training according to the plan.

[1681] Enter: New training plan

[1682] Output: User notification, ongoing training begins

[1683] Through the above processing steps, this system provides personalized training to patients who suffer from olfactory impairment as a result of COVID-19, maximizing the effectiveness of the training.

[1684] (Application example 2)

[1685] 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."

[1686] Providing personalized scent training to patients with olfactory impairment after COVID-19 infection is challenging. Conventional methods have not adequately developed optimal training plans tailored to each patient's olfactory sensitivity and emotional state, and have not adequately assessed and adjusted their progress. Furthermore, there has been a lack of methods to provide a relaxing effect in a virtual space that takes into account the patient's emotional state during training and improves the user experience. As a result, the effectiveness of the training has been limited.

[1687] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1688] In this invention, the server includes: means for evaluating a patient's scent sensitivity using a generative model; means for designing an individual scent training session based on the evaluation; means for collecting data during training and selecting scents based on the data; means for building a predictive model related to specific scents and predicting progress toward improvement; means for a user to receive scent training in a virtual space using a terminal; means for recognizing the user's emotional state using an emotion engine and collecting that data; means for adjusting the training content and timing based on the collected emotional data; and means for changing the environment of the virtual space according to the user's evaluation and emotional state. This makes it possible to provide patients with olfactory impairment after COVID-19 infection with personalized scent training and the relaxing effect of the virtual space, maximizing the effectiveness of the training.

[1689] A "generative model" is a system that includes algorithms that analyze data and generate specific patterns or characteristics.

[1690] "Scent sensitivity" is data that indicates an individual's reaction to and ability to discriminate specific scents.

[1691] A "training session" is a series of activities or trials designed to improve olfactory ability.

[1692] "Data collection" is the process of gathering information about the user's olfactory sensitivity and emotional state.

[1693] A "predictive model" is an algorithm that predicts future progress or results based on collected data.

[1694] A "terminal" is a computer device used by a user to receive scent training in a virtual space.

[1695] An "emotion engine" is software that analyzes a user's emotional state and collects that data.

[1696] A "virtual space" is a virtual environment where users can experience training or relaxation.

[1697] "Means for changing the environment" refers to technology that customizes various elements in a virtual space according to the user's evaluation and emotional state.

[1698] The "relaxation effect" is an effect that provides a sensation or experience that puts the user in a relaxed state.

[1699] This invention is a system that uses a generative model and an emotion engine to provide personalized scent training to patients with olfactory impairment after COVID-19 infection. The system consists of a server and a terminal (user device). The server uses the generative model to generate a personalized training plan, and the terminal implements the scent training and recognizes and collects the user's emotional state. It can also provide a relaxing environment using a virtual space.

[1700] System Overview

[1701] 1. User Registration and Initial Evaluation:

[1702] Users download a dedicated app and install it on their device. They then enter their personal information to create an account. This information is then stored on the server.

[1703] As an initial evaluation, the user smells multiple scent samples and inputs data assessing their sensitivity and discrimination ability.

[1704] The device transmits this evaluation data to a server, which analyzes the data using a generative model to evaluate the user's initial olfactory sensitivity.

[1705] 2. Personalized scent selection and emotion recognition:

[1706] The user follows a training plan and periodically smells designated scents, while inputting feedback into the device about the scent's strength and discrimination.

[1707] The device uses an emotion engine to collect the user's emotional state during training, and this data is sent to the server along with the feedback data.

[1708] The server continuously collects and analyzes this data, and based on the analysis results, selects the next scent that best suits the user's situation and reflects it in the training plan.

[1709] 3. Predictive models for progress forecasting and training optimization:

[1710] The server uses the collected feedback data and emotion data to build a generative model and predict the user's progress.

[1711] Based on the prediction results, the server updates the training plan and performs optimizations such as adding new scents.

[1712] The content and timing of training is also adjusted based on emotional data.

[1713] 4. Relaxing virtual experience:

[1714] The device uses a virtual space to provide a relaxing environment for users to undergo scent training, which includes visual and auditory elements tailored to specific scents.

[1715] Specific explanation of the system's operation

[1716] Hardware: Devices such as smartphones and tablets

[1717] Software: Server-side application using Flask (Python), emotion engine, virtual space generation tool

[1718] Specific examples

[1719] Case 1: User A's initial registration and training start

[1720] User A installs the app and takes the lemon and rose scent evaluation test and emotion recognition test.

[1721] For example, it may be determined that user A has a low sensitivity to citrus scents and is in a relaxed state.

[1722] An initial training plan using a citrus scent is created, and User A begins training according to this plan.

[1723] Case 2: Progress forecast and training plan updates

[1724] User A's feedback data and emotional data are collected and analyzed to predict that his sensitivity has improved and that there are times when he feels stressed.

[1725] The server generates a new plan that adds a rose-like scent and recommends training during a relaxing time. User A continues training according to the new plan.

[1726] Prompt Sentence Examples

[1727] Based on the user's olfactory sensitivity and emotional data, select the best scent for the next training session. The best time is when the user is less sensitive to citrus scents and is more relaxed. Generate a list of scents to use in the next session.

[1728] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1729] Step 1:

[1730] The user downloads a dedicated app and installs it on their device. They then enter their personal information to create an account. This information is sent from the device to the server and stored on the server.

[1731] Input: User's personal information (name, age, gender, etc.)

[1732] Processing: The terminal sends the user-entered information to the server to create an account.

[1733] Output: User account information stored on the server

[1734] Step 2:

[1735] The user performs an initial evaluation by smelling multiple scent samples and inputting data evaluating their sensitivity and discrimination ability into the terminal, which then transmits this evaluation data to the server.

[1736] Input: User's scent sensitivity evaluation data (scent concentration, discrimination ability, etc.)

[1737] Processing: The device sends the evaluation data to the server, which analyzes these data using the generative model.

[1738] Output: Initial olfactory sensitivity assessment results analyzed by the server

[1739] Step 3:

[1740] Based on the analysis results, the server evaluates the user's initial olfactory sensitivity and generates a personalized training plan, which is then sent to the device.

[1741] Input: Initial olfactory sensitivity assessment results

[1742] Processing: The server uses the generative model to generate a personalized training plan.

[1743] Output: A personalized training plan sent to your device

[1744] Step 4:

[1745] The user periodically smells designated scents according to the training plan, and provides feedback on the scent's strength and discrimination. The device also evaluates the user's emotional state using an emotion engine and transmits the data to the server.

[1746] Input: User training feedback data, emotional state data

[1747] Processing: The device collects feedback data and emotion data and sends them to the server.

[1748] Output: Training feedback data and emotional state data sent to the server

[1749] Step 5:

[1750] The server analyzes the collected data and adjusts the training plan, scheduling training at times that are most relaxing based on emotional data.

[1751] Input: Training feedback data, emotional state data

[1752] Processing: The server analyzes the data and generates a new training plan.

[1753] Output: Updated training plan sent to the user

[1754] Step 6:

[1755] While the user is training in the virtual space, the device provides images and sounds with a relaxing effect. The virtual environment is adjusted according to the user's evaluation and emotional state.

[1756] Input: User rating data, emotional state data

[1757] Processing: The device adjusts the virtual environment and provides relaxing content.

[1758] Output: A customized virtual relaxation environment experienced by the user.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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.

[1765] 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).

[1766] 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.

[1767] 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."

[1768] 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.

[1769] 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).

[1770] 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.

[1771] 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.

[1772] 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.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] 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.

[1779] 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.

[1780] The following is further disclosed regarding the above embodiment.

[1781] (Claim 1)

[1782] a means for assessing a patient's scent sensitivity using a generative model;

[1783] means for designing a personalized scent training session based on said evaluation;

[1784] a means for collecting data during training and selecting a scent based on said data;

[1785] A means to build a predictive model related to a specific scent and predict progress towards improvement;

[1786] A system including:

[1787] (Claim 2)

[1788] Using AI, we will be able to assess each patient's scent sensitivity and olfactory changes in real time.

[1789] means for selecting individual scent training targets based on the evaluation results and data collection;

[1790] A means for predicting training progress based on the selected scent and optimizing training effects;

[1791] 10. The system of claim 1, comprising:

[1792] (Claim 3)

[1793] means for providing an interface for conducting an initial scent sensitivity assessment;

[1794] means for analyzing the scent sensitivity data collected through the interface;

[1795] A means for providing individual training plans based on the analysis results;

[1796] 10. The system of claim 1, comprising:

[1797] "Example 1"

[1798] (Claim 1)

[1799] A means for user registration and personal information input;

[1800] A means for collecting sensitivity evaluation data for a plurality of scent samples as an initial evaluation;

[1801] a means for analyzing the collected initial evaluation data and evaluating the user's initial olfactory sensitivity using a generative model;

[1802] means for generating an initial personalized training plan based on the analysis results;

[1803] A means for continuously collecting training feedback data and using a generative model to select scents that best suit the user's olfactory sensitivity; and

[1804] A means to predict progress and optimize training plans based on collected feedback data;

[1805] A system including:

[1806] (Claim 2)

[1807] Using AI, we will evaluate each user's scent sensitivity and changes in their sense of smell in real time.

[1808] means for selecting individual scent training targets based on the evaluation results and data collection;

[1809] A means for predicting training progress based on the selected scent and optimizing training effects;

[1810] 10. The system of claim 1, comprising:

[1811] (Claim 3)

[1812] means for providing an interface for conducting an initial scent sensitivity assessment;

[1813] means for analyzing the scent sensitivity data collected through the interface;

[1814] A means for providing individual training plans based on the analysis results;

[1815] 10. The system of claim 1, comprising:

[1816] "Application Example 1"

[1817] (Claim 1)

[1818] a means for assessing a patient's scent sensitivity using a generative model;

[1819] means for designing a personalized scent training session based on said evaluation;

[1820] a means for collecting data during training and selecting a scent based on said data;

[1821] A means to build a predictive model related to a specific scent and predict progress towards improvement;

[1822] Providing electronic payment facilities and a means to manage training fragrance purchases and subscriptions;

[1823] A system including:

[1824] (Claim 2)

[1825] Using AI, we will be able to assess each patient's scent sensitivity and olfactory changes in real time.

[1826] means for selecting individual scent training targets based on the evaluation results and data collection;

[1827] A means for predicting training progress based on the selected scent and optimizing training effects;

[1828] The acquired feedback data is analyzed using a generative AI model to dynamically update the optimal training plan.

[1829] 10. The system of claim 1, comprising:

[1830] (Claim 3)

[1831] means for providing an interface for conducting an initial scent sensitivity assessment;

[1832] means for analyzing the scent sensitivity data collected through the interface;

[1833] A means for providing individual training plans based on the analysis results;

[1834] A way to predict your training plan progress and provide timely and relevant feedback and advice;

[1835] 10. The system of claim 1, comprising:

[1836] "Example 2: Combining Emotion Engines"

[1837] (Claim 1)

[1838] a means for assessing a patient's scent sensitivity using a generative model;

[1839] means for designing a personalized scent training session based on said evaluation;

[1840] means for collecting feedback and emotional data during training and selecting scents based on said data;

[1841] A means to build a predictive model related to a specific scent and predict progress towards improvement;

[1842] A way to adjust your training plan based on your emotional data;

[1843] A system including:

[1844] (Claim 2)

[1845] Using AI, we will be able to assess each patient's scent sensitivity and olfactory changes in real time.

[1846] means for selecting individual scent training targets based on the evaluation results and data collection;

[1847] a means for predicting training progress based on the selected scent and emotion data and optimizing training effects;

[1848] 10. The system of claim 1, comprising:

[1849] (Claim 3)

[1850] means for providing an interface for conducting an initial scent sensitivity assessment;

[1851] means for analyzing the scent sensitivity data and emotion data collected through the interface;

[1852] A means of providing personalized training plans based on the analysis results and recommending training based on emotional data;

[1853] 10. The system of claim 1, comprising:

[1854] "Application example 2 when combining emotion engines"

[1855] (Claim 1)

[1856] a means for assessing a patient's scent sensitivity using a generative model;

[1857] means for designing a personalized scent training session based on said evaluation;

[1858] a means for collecting data during training and selecting a scent based on said data;

[1859] A means to build a predictive model related to a specific scent and predict progress towards improvement;

[1860] A means for a user to receive scent training in a virtual space using a terminal;

[1861] means for recognizing and collecting data on a user's emotional state using an emotion engine;

[1862] A means to adjust training content and timing based on collected emotional data;

[1863] A means for changing the environment of the virtual space according to the user's evaluation and emotional state;

[1864] A system including:

[1865] (Claim 2)

[1866] Using AI, we will be able to assess each patient's scent sensitivity and olfactory changes in real time.

[1867] means for selecting individual scent training targets based on the evaluation results and data collection;

[1868] A means for predicting training progress based on the selected scent and optimizing training effects;

[1869] A means to provide a relaxing effect through a scent experience in a virtual space,

[1870] 10. The system of claim 1, comprising:

[1871] (Claim 3)

[1872] means for providing an interface for conducting an initial scent sensitivity assessment;

[1873] means for analyzing the scent sensitivity data collected through the interface;

[1874] A means for providing individual training plans based on the analysis results;

[1875] A means including an interface for providing a scent experience in a virtual space;

[1876] 10. The system of claim 1, comprising: [Explanation of symbols]

[1877] 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 assessing a patient's scent sensitivity using a generative model; means for designing a personalized scent training session based on said evaluation; a means for collecting data during training and selecting a scent based on said data; A means to build a predictive model related to a specific scent and predict progress towards improvement; A system including:

2. Using AI, we will be able to assess each patient's scent sensitivity and olfactory changes in real time. means for selecting individual scent training targets based on the evaluation results and data collection; A means for predicting training progress based on the selected scent and optimizing training effects; The system of claim 1 , comprising:

3. means for providing an interface for conducting an initial scent sensitivity assessment; means for analyzing the scent sensitivity data collected through the interface; A means for providing individual training plans based on the analysis results; The system of claim 1 , comprising:

Images