System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving information on a physical condition, a mood, and a favorite smell from a user; means for transmitting the information received from the user to a server; means for analyzing the user information received by the server and determining an optimum aroma blend for a state of the user; means for notifying the user of aroma blend information determined by the server; and means for receiving feedback after use of aroma from the user and transmitting the feedback to the server.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Aromatherapy is said to be effective for relaxation and health promotion, but selecting the optimal aroma requires specialized knowledge, and it is difficult to choose an aroma that suits an individual's condition and preferences. Furthermore, because physical condition and mood are affected by seasonal fluctuations and individual usage history, it is difficult to find consistent patterns. For this reason, there is a need for a system that can easily suggest aromas that are suitable for each individual user and maximize their effects. [Means for solving the problem]

[0005] The present invention provides a means for receiving information about a user's physical condition, mood, and preferred scents and transmitting it to a server. The server also has a means for analyzing the received user information and determining the optimal aroma blend for the user's condition. The server also provides a means for notifying the user of the determined aroma blend information. The system also includes a means for receiving feedback from the user after using the aroma and transmitting it to the server. The system has a means for improving future aroma blend suggestions based on the feedback. The system also includes a means for correcting aroma blend suggestions by referring to seasonal fluctuations and the user's past usage history, and a means for the server to learn from the feedback data using a machine learning model and improve the accuracy of future suggestions.

[0006] "User information" is data entered by the user regarding physical condition, mood, and favorite smells.

[0007] A "terminal" is a device through which a user inputs information and communicates with a server.

[0008] The "server" is a computer system that analyzes user information, determines the optimal aroma blend, and notifies the user.

[0009] "Aroma blending" is a method of combining multiple aroma oils to achieve a specific effect.

[0010] "Feedback" is information regarding the effects and satisfaction felt by the user after using the aroma.

[0011] A "machine learning model" is an algorithm that the server uses to improve the accuracy of its analysis and suggestions based on feedback data.

[0012] The "notification means" is a method for notifying the user of the aroma blend information determined by the server, and is carried out via the terminal.

[0013] "Analysis" refers to information processing to determine the optimal aroma blend based on the user information received by the server.

[0014] "Proposal accuracy" refers to the degree to which an aroma blend can be proposed that is appropriate for the user's needs.

[0015] "Seasonal variation" refers to the tendency for a user's physical condition and mood to change over time. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The aromatherapist AI system of this invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, proposal notification, and feedback processing.

[0038] User: Information entry process

[0039] First, the user launches the dedicated application and logs in. Then, on the application screen, the user inputs their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent (e.g., lavender, mint, etc.). This information is collected through the application. This input information is extremely important for determining the aroma blend.

[0040] Terminal: Information transmission process

[0041] The information entered by the user about their physical condition, mood, and preferred scents is stored in temporary storage on the device. The device then generates an API request to send this data to the server, which then sends it. The transmitted data is encrypted to protect privacy.

[0042] Server: Data analysis process

[0043] The server analyzes the received user information. Using a machine learning model, the server determines the optimal aroma combination for the user's current condition. This analysis takes into account not only the user's current physical condition, mood, and preferred scents, but also past feedback data and seasonal patterns. For example, if lavender and bergamot are deemed suitable for a user who needs stress relief, this combination will be suggested.

[0044] Server: Proposal generation process

[0045] The server generates a proposal for the optimal aroma blend for the user based on the analysis results. This proposal includes details such as the specific aroma oil type, amount to use, blending method, and usage method. The proposal is sent to the device as an API response.

[0046] Terminal: Proposal Notification Process

[0047] The device receives the API response from the server and notifies the user of the proposed aroma blend. The user can then check the proposed aroma blend on the application screen. The notification uses a visual interface to make it easy for the user to understand.

[0048] User: Feedback input process

[0049] Users try out the proposed aroma blends and enter their feedback through the application about their experience and satisfaction, including perceived effects, satisfaction, and possible improvements.

[0050] Terminal: Feedback sending process

[0051] The feedback data sent by the user is temporarily stored on the device, and an API request is generated to send it to the server. The device then sends the generated API request to the server.

[0052] Server: Feedback processing process

[0053] The server analyzes the received feedback data and inputs it into a machine learning model. The machine learning model is retrained based on this feedback data, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0054] Specific examples

[0055] User A uses the application to input that he is "stressed," and further states that he "wants to relax," selecting "lavender" and "mint" as his favorite scents. The device sends this information to the server, which then takes into account past feedback and seasonal fluctuation patterns and suggests the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback, rating it as "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of suggestions from next time onwards.

[0056] In this way, this system utilizes artificial intelligence and machine learning to accurately suggest the optimal aroma blend for the user's condition, thereby maximizing the effects of aromatherapy.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The user launches the application and logs in. The user enters information about their physical condition, mood, desired effect (e.g., relaxation, concentration), and preferred scent (e.g., lavender, mint).

[0060] Step 2:

[0061] The device temporarily stores the information entered by the user in storage.

[0062] Step 3:

[0063] The device generates an API request to send the saved user information to the server.

[0064] Step 4:

[0065] The device sends the generated API request to the server.

[0066] Step 5:

[0067] The server receives the API request sent from the device.

[0068] Step 6:

[0069] The server parses the contents of the request body and extracts the user data.

[0070] Step 7:

[0071] The server stores the extracted user data in a database.

[0072] Step 8:

[0073] The server inputs the stored user data into a machine learning model for analysis.

[0074] Step 9:

[0075] The machine learning model calculates the optimal aroma combination based on information such as "physical condition," "mood," "desired effect," and "preferred smell."

[0076] Step 10:

[0077] The server takes into account past feedback data and seasonal fluctuations to adjust the aroma blend.

[0078] Step 11:

[0079] The server will create the optimal aroma combination (e.g., 3 drops lavender, 2 drops mint, 2 drops bergamot).

[0080] Step 12:

[0081] The server creates a message to suggest the generated aroma blend to the user.

[0082] Step 13:

[0083] The server generates an API response to send this message to the device.

[0084] Step 14:

[0085] The device receives the API response from the server.

[0086] Step 15:

[0087] The terminal analyzes the received proposal message and displays it to the user.

[0088] Step 16:

[0089] The user checks the proposed aroma blend on the application screen.

[0090] Step 17:

[0091] The user tries out the suggested aroma and enters feedback on its effectiveness and satisfaction.

[0092] Step 18:

[0093] The device temporarily stores the feedback entered by the user in storage.

[0094] Step 19:

[0095] The device generates an API request to send the saved feedback data to the server.

[0096] Step 20:

[0097] The device sends the generated API request to the server.

[0098] Step 21:

[0099] The server receives the feedback data sent from the terminal.

[0100] Step 22:

[0101] The server analyzes the feedback data and adds it to the dataset of the machine learning model.

[0102] Step 23:

[0103] The server retrains the machine learning model to improve the accuracy of future suggestions.

[0104] Example 1

[0105] 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."

[0106] Conventional aromatherapy systems lack the functionality to suggest optimal aroma blends based on the user's physical condition and mood. In particular, it is difficult to make personalized suggestions that take into account each user's past usage history and feedback, and external factors such as seasonal variations tend to be ignored. Furthermore, systems often lack a mechanism for incorporating user feedback into future suggestions. This poses a challenge, preventing users from maximizing the benefits of aromatherapy.

[0107] 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.

[0108] In this invention, the server includes means for receiving information about the user's physical condition, mood, and preferred scents from the user, means for temporarily storing the received information and generating an API request to send to the server, means for the server to analyze the received user information and determine an aroma blend optimal for the user's condition using a machine learning model, means for the server to send the determined aroma blend information to the terminal as an API response and for the terminal to notify the user, means for receiving feedback from the user after using the aromas and generating an API request to send to the server, means for retraining the machine learning model based on the received feedback to improve subsequent aroma blend suggestions, means for correcting the aroma blend suggestions by referring to seasonal fluctuations and the user's past usage history, and means for the server to learn from the feedback data using the machine learning model and improve the accuracy of subsequent suggestions. This enables highly accurate and personalized suggestions of aroma blends optimal for the user's condition, maximizing the effects of aromatherapy.

[0109] "Physical condition" refers to the physical condition and health status of the user.

[0110] "Mood" refers to the user's emotional or mental state.

[0111] "Favorite scent" refers to the type of scent that the user particularly likes.

[0112] "Means for receiving information" refers to the method for obtaining data entered by the user from the application.

[0113] "Temporary storage" refers to the process of temporarily storing input information in a storage device.

[0114] "Means for generating API requests" refers to the method for creating the request format required to send data to the server.

[0115] "Server" means hardware or software for processing, analyzing, and storing data over a network.

[0116] "Machine learning model" refers to an algorithmic model used for data analysis and prediction.

[0117] "API response" refers to the response data sent from the server to the terminal.

[0118] "Means of notification" refers to the method by which the terminal presents information to the user.

[0119] "Feedback" refers to the impressions and evaluations provided by users after using an aroma.

[0120] "Retraining" refers to the process of retraining a machine learning model using new data received.

[0121] "Seasonal variation" refers to the pattern of the external environment that changes with the seasons.

[0122] "Usage history" refers to records of aroma compounds used by the user in the past and their effects.

[0123] "Corrective measures" refer to methods for fine-tuning proposals based on existing data and conditions.

[0124] "Suggestion accuracy" refers to the degree to which the optimum formulation for the user's condition can be accurately suggested.

[0125] "Terminal" refers to a device that allows a user to input or receive information.

[0126] The aromatherapist AI system of this invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, proposal notification, and feedback processing.

[0127] Hardware and software used

[0128] The implementation of this system uses the following hardware and software:

[0129] User devices: devices such as smartphones, tablets, and PCs

[0130] Application: A dedicated application that runs on the user's device

[0131] Server: Cloud or on-premise server

[0132] Database: A database system for storing user information and feedback data.

[0133] Machine learning models: Machine learning algorithms for analyzing and predicting aroma formulations

[0134] Natural language explanation of the process

[0135] User: Enter information

[0136] The user launches the application and logs in. After logging in, they input their physical condition, mood, desired effect (e.g., relaxation, concentration, refreshment), and favorite scent (e.g., lavender, mint). This input is done through the application's user interface.

[0137] Terminal: Sending information

[0138] The device stores the information entered by the user in temporary storage and generates an API request to send to the server, which is sent encrypted using HTTP.

[0139] Server: Data analysis

[0140] The server stores the received user information in a database. The stored data is then input into a machine learning model to determine the optimal aroma blend for the user's condition. This analysis also takes into account past usage history, seasonal patterns, and feedback data.

[0141] Server: Proposal Generation

[0142] The server generates the optimal aroma blend based on the analysis results. This proposal includes the specific type of aroma oil, the amount to be used, the blending method, and even the method of use. The generated proposal is sent to the device as an API response.

[0143] Device: Proposal Notification

[0144] The device uses the API response received from the server to notify the user of the proposed content. The notification is done using a visual interface and is displayed in a user-friendly format.

[0145] User:Feedback

[0146] Users try out the proposed aroma blends and enter feedback on their results and satisfaction, including perceived effects, satisfaction, and areas for improvement.

[0147] Terminal and Server: Feedback Processing

[0148] The device temporarily stores the feedback data, generates an API request to send it to the server, and sends it to the server. The server analyzes the received feedback data and inputs it into a machine learning model for retraining. This improves the accuracy of aroma blend suggestions from the next time onwards.

[0149] Specific examples

[0150] For example, User A uses the application to input "stress," states that he or she "wants to relax," and selects "lavender" and "mint" as his or her favorite scents. The device sends this information to the server, which then considers past feedback data and seasonal fluctuation patterns to suggest the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback that it was "very relaxing." This feedback is used in the next analysis, further improving the accuracy of the suggestions.

[0151] Examples of prompt statements

[0152] Enter the following prompt into the generative AI model:

[0153] "The user says they are stressed and want to relax. Their favorite aromas are lavender and mint. Please suggest the best aroma combination."

[0154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0155] Step 1: Enter your user information

[0156] The user launches the dedicated application and logs in. After logging in, they enter their physical condition, mood, favorite scent, and desired effect on the application screen. For example, they might enter "I'm stressed," "I want to relax," or "I like lavender and mint." This input is done through the application's user interface (UI) and is saved in the device's temporary storage.

[0157] Step 2: Send data

[0158] The device temporarily stores the information entered by the user, then generates an API request to send it to the server. This API request includes encrypted user data. The generated API request is sent to the server via the Internet.

[0159] Step 3: Receiving and storing data on the server

[0160] The server receives API requests sent from the device and stores user information in a database. Specifically, it analyzes the data received as an HTTP request and stores it in the appropriate table in the database based on the specifications. This stored data includes the user's physical condition, mood, preferred scent, and desired effect.

[0161] Step 4: Data analysis

[0162] The server inputs the saved user information into a machine learning model and begins analysis. This machine learning model also references past usage history, seasonal fluctuation patterns, feedback data, etc. to determine the optimal aroma blend. For example, a suggestion such as "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" may be generated. The model performs data calculations based on the input data and outputs a suggestion for the optimal aroma blend.

[0163] Step 5: Proposal generation and submission

[0164] The server generates specific aroma blend suggestions for the user based on the analysis results obtained from the machine learning model. These suggestions include the type, amount, blending method, and usage of aroma oils to be used. The generated suggestions are sent to the device as an API response.

[0165] Step 6: Proposal Notification

[0166] The device notifies the user of the proposed aroma blend based on the API response received from the server. The result is displayed on the application screen in a visually easy-to-understand interface. The user can check the notification and try out the proposed aroma blend.

[0167] Step 7: Enter your feedback

[0168] Users try out the proposed aroma blends and enter feedback through the application about their effects and satisfaction, such as "It was very relaxing" or "I wish there was a bit more mint."

[0169] Step 8: Send your feedback

[0170] The device temporarily stores the feedback data received from the user and generates an API request to send to the server, which is also encrypted before being sent to the server.

[0171] Step 9: Feedback processing and model retraining

[0172] The server analyzes the received feedback data and stores it in a database. This feedback data is then input into the machine learning model for retraining. This allows the machine learning model to improve the accuracy of its aroma blending suggestions from the next time onwards.

[0173] Through these steps, the aromatherapist AI system can propose the aroma combination that is best suited to the user's condition and continuously improve the accuracy of its proposals based on feedback.

[0174] (Application example 1)

[0175] 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."

[0176] Conventional aromatherapy systems often fail to effectively suggest aroma blends based on the user's physical condition, mood, and preferred scents, making it difficult to provide individually optimized services. They also lack a means to effectively utilize user feedback to improve the accuracy of their next suggestions. Furthermore, suggestions are limited to simple notifications, which lacks user convenience and immediacy.

[0177] 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.

[0178] In this invention, the server includes means for receiving information on the user's physical condition, mood, and preferred scent from the user, means for transmitting the information received from the user to the server, means for the server to analyze the user information received and determine an aroma blend optimal for the user's condition, means for notifying the smart device of the aroma blend information determined by the server, means for receiving feedback from the user after using the aroma via the smart device and transmitting the feedback to the server, and means for improving subsequent aroma blend suggestions based on the received feedback. This not only makes it possible to suggest an aroma blend optimal for the user's condition, but also makes it possible to continuously improve the service based on the feedback and enhance the user experience.

[0179] "User information" is information collected from the user about their physical condition, mood, and favorite smell.

[0180] The "server" is a central processing unit that analyzes user information, determines the aroma blend that best suits the user's condition, and notifies the smart device of the results.

[0181] A "smart device" is an electronic device that can input user information, receive aroma blend information, and receive and send feedback, and includes smartphones and smart glasses.

[0182] An "aroma blend" is a combination of aroma oils optimized according to the user's physical condition, mood, and preferred scent.

[0183] "Feedback" refers to information about the evaluation, impressions, and satisfaction level submitted by a user after trying out the proposed aroma blend.

[0184] "Data analysis" is an information processing method for determining the optimal aroma blend using user information and feedback received by the server.

[0185] A "machine learning model" is an algorithm that learns from feedback data and improves the accuracy of aroma blend suggestions from the next time onwards.

[0186] The aromatherapist AI system of this invention utilizes smart devices to suggest optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, suggestion notification, and feedback processing.

[0187] User operations

[0188] First, the user puts on a smart device (such as a smartphone or smart glasses), launches a dedicated application, and logs in. On the application screen, the user enters their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and preferred scent (e.g., lavender, mint, etc.). This information is crucial for determining the aroma blend.

[0189] Data transmission

[0190] The information entered by the user regarding their physical condition, mood, and preferred scent is stored in temporary storage on the smart device, after which the smart device generates an API request to send this data to the server, encrypts it, and sends it to the server.

[0191] Data analysis

[0192] The server uses a machine learning model called a generative AI model to analyze the received user information. Data analysis takes into account not only the user's current condition, but also past feedback data and seasonal patterns, and determines the optimal aroma combination based on this. For example, a combination of lavender and bergamot may be recommended, as it is determined to be effective in relieving stress based on past data.

[0193] proposal notification

[0194] The determined aroma blend information is sent to the smart device as an API response. The smart device receives this information and notifies the user visually or audibly. The user can then check the proposed aroma blend on the application screen and view details such as the specific type of aroma oil, the amount to be used, the blending method, and how to use it.

[0195] Feedback Processing

[0196] The user tries out the proposed aroma blend and enters feedback on its effectiveness and satisfaction via their smart device. This feedback includes perceived effectiveness, satisfaction, and areas for improvement. The feedback data is temporarily stored on the smart device and then sent back to the server.

[0197] Continuous improvement

[0198] The server analyzes the received feedback data and inputs it into the generative AI model. This retrains the machine learning model, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0199] Specific examples

[0200] For example, if a user inputs that they are "stressed" and desires to "relax," selecting "lavender" and "mint" as their favorite scents, this user information is sent to the server. The server uses a generative AI model to consider past feedback and seasonal fluctuation patterns, and suggests "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" as the optimal aroma blend. The user tries this and provides feedback that they found it "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of future suggestions.

[0201] Prompt Sentence Examples

[0202] "User feedback: 'Very relaxing'. Please use this feedback to re-learn the optimal aroma combination to improve the accuracy of our suggestions next time."

[0203] In this way, the system of the present invention can accurately suggest personalized aroma blends based on the user's physical condition and mood, improving the user experience.

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1: Enter user information

[0206] The user launches a dedicated application using a smart device (e.g., a smartphone or smart glasses) and logs in. On the application screen, the user enters their current physical condition (e.g., stressed), mood (e.g., wanting to relax), desired effect, and favorite scent (e.g., lavender, mint). This information is used in the next processing step.

[0207] Input: physical condition, mood, favorite smell

[0208] Output: User information data

[0209] Step 2: Send data

[0210] The device temporarily stores the information entered by the user in storage, then generates an API request to send the stored user information data to the server, encrypts the data, and sends it to the server.

[0211] Input: User information data

[0212] Output: API request to the server

[0213] Step 3: Data analysis

[0214] The server analyzes the received user information data using a generative AI model, which takes into account the user's current condition, past feedback data, and seasonal patterns to determine the optimal aroma blend.

[0215] Input: User information data, past feedback data, seasonal fluctuation patterns

[0216] Output: Optimal aroma blend data

[0217] Step 4: Proposal Notification

[0218] The server sends the determined optimal aroma blend data to the terminal as an API response, and the terminal notifies the user of the received aroma blend data via the smart device's display or voice notification.

[0219] Input: Optimal aroma blend data

[0220] Output: Aroma blending suggestions notified to the user

[0221] Step 5: Enter your feedback

[0222] The user tries out the proposed aroma blend and enters feedback on its effectiveness and satisfaction. This feedback data is then temporarily stored on the smart device.

[0223] Input: Impressions after use, satisfaction level

[0224] Output: User feedback data

[0225] Step 6: Send your feedback

[0226] The terminal generates an API request for transmitting the feedback data collected from the user to the server, and transmits the request to the server.

[0227] Input: User feedback data

[0228] Output: API request to the server

[0229] Step 7: Feedback analysis and model retraining

[0230] The server analyzes the received feedback data and reflects it in the generative AI model. This re-learning improves the accuracy of aroma blend suggestions from the next time onwards.

[0231] Input: User feedback data

[0232] Output: Updated machine learning model

[0233] Through these steps, the aromatherapist AI system of the present invention can provide optimal aroma blends that meet the individual needs of users and can continuously improve them based on feedback.

[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] The aromatherapist AI system of the present invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. Furthermore, by combining it with an emotion engine, the system also recognizes the user's emotional state and proposes aroma blends based on that. This system consists of multiple processes: user input, emotion recognition data acquisition, data transmission, data analysis, proposal notification, and feedback processing.

[0236] User: Information entry process

[0237] First, the user launches the dedicated application and logs in. Then, on the application screen, the user inputs their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent (e.g., lavender, mint, etc.). The input information is crucial for determining the aroma composition.

[0238] User: Emotion recognition process

[0239] While the user is inputting, the device's built-in camera and microphone collect the user's voice and facial expression data. The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise, etc.). The emotional state data is sent to the server along with information on the user's physical condition and mood.

[0240] Terminal: Information transmission process

[0241] The information entered by the user regarding their physical condition, mood, and preferred scent, as well as the emotional state data recognized by the emotion engine, are stored in temporary storage on the device. The device then generates an API request to send this data to the server, which then sends it to the server. The transmitted data is encrypted to ensure privacy.

[0242] Server: Data analysis process

[0243] The server analyzes the received user information and uses a machine learning model to determine the optimal aroma blend for the user's current state. This analysis takes into account data such as physical condition, mood, and preferred scents, as well as emotional state data recognized by the emotion engine. For example, if the server recognizes that the user is feeling stressed, it will suggest aroma oils with a relaxing effect (e.g., lavender or bergamot).

[0244] Server: Proposal generation process

[0245] The server generates a proposal for the optimal aroma blend for the user based on the analysis results. This proposal includes details such as the specific aroma oil type, amount to use, blending method, and usage method. The proposal is sent to the device as an API response.

[0246] Terminal: Proposal Notification Process

[0247] The device receives the API response from the server and notifies the user of the proposed aroma blend. The user can then check the proposed aroma blend on the application screen. The notification uses a visual interface to make it easy for the user to understand.

[0248] User: Feedback input process

[0249] Users try out the proposed aroma blends and enter their feedback through the application about their experience and satisfaction, including perceived effects, satisfaction, and possible improvements.

[0250] Terminal: Feedback sending process

[0251] The feedback data sent by the user is temporarily stored on the device, and an API request is generated to send it to the server. The device then sends the generated API request to the server.

[0252] Server: Feedback processing process

[0253] The server analyzes the received feedback data and inputs it into a machine learning model. The machine learning model is retrained based on this feedback data, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0254] Specific examples

[0255] User A uses the application to input that he is "stressed," and further states that he "wants to relax," selecting "lavender" and "mint" as his favorite scents. The device collects this information along with the user's facial expressions and voice data, and uses an emotion engine to recognize "irritation." The device then sends this data set to the server. Taking into account past feedback and seasonal fluctuation patterns, the server suggests the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback, rating it as "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of future suggestions.

[0256] By combining this with an emotion engine, it will be possible to propose sophisticated aroma blends that take into account even the subtlest emotional changes of the user, which is expected to maximize the effects of aromatherapy.

[0257] The processing flow will be explained below.

[0258] Step 1:

[0259] The user launches the application and logs in. The user enters information about their physical condition, mood, desired effect (e.g., relaxation, concentration), and preferred scent (e.g., lavender, mint).

[0260] Step 2:

[0261] The device's built-in camera and microphone collect the user's voice and facial expression data.

[0262] Step 3:

[0263] The device transmits the collected voice and facial expression data to the emotion engine in real time.

[0264] Step 4:

[0265] The emotion engine analyzes the user's voice tone, facial expression changes, and language patterns to recognize the user's emotional state (e.g., joy, sadness, anger, surprise).

[0266] Step 5:

[0267] The device temporarily stores information entered by the user regarding physical condition, mood, and preferred scent, as well as emotional state data recognized by the emotion engine.

[0268] Step 6:

[0269] The device generates an API request to send the stored user information and emotional state data to the server.

[0270] Step 7:

[0271] The device sends the generated API request to the server.

[0272] Step 8:

[0273] The server receives the API request sent from the device.

[0274] Step 9:

[0275] The server parses the contents of the request body and extracts user data and emotional state data.

[0276] Step 10:

[0277] The server stores the extracted user data and emotional state data in a database.

[0278] Step 11:

[0279] The server inputs the stored user data and emotional state data into a machine learning model for analysis.

[0280] Step 12:

[0281] The machine learning model calculates the optimal aroma combination based on information such as "physical condition," "mood," "desired effect," "preferred smell," and "emotional state."

[0282] Step 13:

[0283] The server takes into account past feedback data and seasonal fluctuations to adjust the aroma blend.

[0284] Step 14:

[0285] The server will create the optimal aroma combination (e.g., 3 drops lavender, 2 drops mint, 2 drops bergamot).

[0286] Step 15:

[0287] The server creates a message to suggest the generated aroma blend to the user.

[0288] Step 16:

[0289] The server generates an API response to send this message to the device.

[0290] Step 17:

[0291] The device receives the API response from the server.

[0292] Step 18:

[0293] The terminal analyzes the received proposal message and notifies the user.

[0294] Step 19:

[0295] The user checks the proposed aroma blend on the application screen.

[0296] Step 20:

[0297] The user tries out the suggested aroma and enters feedback on its effectiveness and satisfaction.

[0298] Step 21:

[0299] The device temporarily stores the feedback entered by the user in storage.

[0300] Step 22:

[0301] The device generates an API request to send the saved feedback data to the server.

[0302] Step 23:

[0303] The device sends the generated API request to the server.

[0304] Step 24:

[0305] The server receives the feedback data sent from the terminal.

[0306] Step 25:

[0307] The server analyzes the feedback data and adds it to the dataset of the machine learning model.

[0308] Step 26:

[0309] The server retrains the machine learning model to improve the accuracy of future suggestions.

[0310] Example 2

[0311] 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."

[0312] Conventional aromatherapy systems only suggest aroma blends based on the user's physical condition and mood, but do not take into account the user's emotional state. This makes it difficult to suggest personalized aroma blends that respond to subtle changes in the user's emotions. Furthermore, the accuracy of suggestions based on feedback has not been sufficiently improved.

[0313] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0314] In this invention, the server includes means for receiving information about the user's physical condition, mood, and preferred scent from the user, means for collecting the user's voice and facial expression data using a camera and microphone while the user is inputting the information, means for analyzing the collected emotional state data, means for transmitting the information received from the user and the emotional state data to the server, means for the server to analyze the received user information and emotional state data and determine an aroma blend optimal for the user's condition, means for notifying the user of the aroma blend information determined by the server, means for receiving feedback from the user after using the aromas and transmitting it to the server, means for improving subsequent aroma blend suggestions based on the received feedback, means for recognizing the user's emotional changes using an emotion engine and reflecting them in aroma blend suggestions, and means for learning the user's feedback using a machine learning model to improve the accuracy of subsequent suggestions. This enables advanced personalization that takes into account not only the user's physical condition and mood but also their emotional state, thereby maximizing the effects of aromatherapy.

[0315] "Physical condition" refers to the user's physical health condition and current physical condition.

[0316] "Mood" refers to the user's psychological and emotional state, or how they feel at a given moment.

[0317] "Favorite scent" refers to the aroma or type of scent that the user particularly likes.

[0318] "Camera" refers to a video input device for capturing the user's facial expression.

[0319] "Microphone" refers to an audio input device for capturing a user's voice.

[0320] "Voice data" refers to audio information obtained from a user's voice and speaking style.

[0321] "Facial expression data" refers to visual information obtained from the user's facial expressions.

[0322] An "emotion engine" refers to software or hardware that analyzes collected voice and facial expression data and recognizes the user's emotional state.

[0323] "Emotional state" refers to the emotions the user is feeling at that time, such as joy, sadness, anger, surprise, etc.

[0324] "Analysis" refers to the act of processing received and collected data to derive a specific conclusion or result.

[0325] "Server" refers to a central processing unit that receives and analyzes data sent by users.

[0326] "Aroma blend" refers to the types and proportions of aromatic oils blended to bring out a specific effect.

[0327] "Notification" refers to the act of sending information to inform users of the proposed content and analysis results.

[0328] "Feedback" refers to the act of a user providing the results and impressions of a proposed aroma blend after trying it out.

[0329] A "machine learning model" refers to an algorithm or system that learns from data and improves the accuracy of future suggestions and predictions.

[0330] "Personalization" refers to the act of customizing offers and services to suit the individual preferences and circumstances of each user.

[0331] "Encryption" refers to the technology of converting data so that it cannot be read by third parties.

[0332] The aromatherapist AI system of the present invention is a system that proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. Furthermore, it utilizes an emotion engine to take the user's emotional state into consideration. Specific embodiments are described below.

[0333] Users use a device such as a smartphone or tablet to launch a dedicated application and log in. After logging in, users enter their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and preferred scent on the application screen. This input information is important for determining the aroma blend.

[0334] While the user is typing, the device's built-in camera and microphone collect the user's voice and facial expression data. This data is analyzed in real time by an emotion engine to recognize the user's emotional state. Examples of emotion engines include Microsoft Azure Cognitive Services and IBM Watson.

[0335] The collected data on physical condition, mood, preferred odor, and emotional state is stored in temporary storage on the device, after which the device generates an API request to send this data to the server, where it is encrypted and sent.

[0336] The server analyzes the data received from the device and uses a machine learning model to determine the optimal aroma combination for the user's current state. This analysis process takes into account the user's physical condition, mood, preferred scents, and emotional state data. Examples of machine learning models include TensorFlow and PyTorch.

[0337] The server then uses the analysis results to propose the optimal aroma blend for the user. This proposal includes the specific type of aroma oil, the amount to use, the blending method, and how to use it. The proposal is sent to the device as an API response.

[0338] The device receives the API response from the server and notifies the user of the proposed content. The notification is sent via the application screen and displayed in a visually easy-to-understand format.

[0339] Users try out the proposed aroma blends and enter their feedback through the application about their perceived effects and satisfaction, as well as areas for improvement.

[0340] The device temporarily stores the feedback data and generates an API request to send it to the server, where it is encrypted and sent.

[0341] The server analyzes the received feedback data and inputs it into a machine learning model, which then retrains the model based on the feedback data, improving the accuracy of future suggestions.

[0342] As a concrete example, user A uses an application, inputs that he is "stressed," and selects his favorite scents as "lavender" and "mint," saying that he "wants to relax." When the device collects this information, it also analyzes the user's facial expressions and voice data using an emotion engine to recognize "irritation." The server considers past feedback and seasonal fluctuation patterns and suggests "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" as the optimal aroma blend. User A tries this blend and sends feedback that it was "very relaxing." This feedback is reflected in future suggestions.

[0343] Example prompts to input to the generative AI model:

[0344] "Suggest the best aroma combination based on your current physical condition, mood, preferred smell, and emotional state. Example: Use lavender, bergamot, and mint."

[0345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0346] Step 1:

[0347] The user launches a dedicated application and logs in. After logging in, they enter their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent into the input form displayed on the application screen. This generates data on physical condition, mood, desired effect, and favorite scent. Examples of input data include "Physical condition: tired," "Mood: stressed," "Desired effect: relaxation," and "Favorite scent: lavender, mint."

[0348] Step 2:

[0349] While the user is entering information, the device's built-in camera and microphone collect the user's voice and facial expression data. The collected voice and facial expression data is sent to an emotion engine, which recognizes the user's emotional state as "happiness," "sadness," "irritation," etc. Specifically, the camera captures the user's facial expressions while the user is entering information, and the microphone records the voice. This data is analyzed in real time by the emotion engine, and "irritation" is output as emotional state data.

[0350] Step 3:

[0351] The device temporarily stores data entered by the user regarding their physical condition, mood, and favorite scent, as well as the emotional state data recognized by the emotion engine. It then generates an API request to send this data to the server. Specifically, it generates a data packet containing "Physical condition: tired," "Mood: stressed," "Favorite scent: lavender, mint," and "Emotional state: irritated," encrypts it, and sends it to the server.

[0352] Step 4:

[0353] The server receives the data sent from the device. The received data is stored in a database and input into a machine learning model for analysis. Specific examples of data processing include integrating data on physical condition, mood, preferred scent, and emotional state and converting it into a format suitable for analysis.

[0354] Step 5:

[0355] The server uses machine learning models to determine the optimal aroma blend for the user's current state. Based on the analysis results, a specific aroma blend, such as "3 drops lavender, 2 drops mint, and 2 drops bergamot," is determined. This output is best suited to the user's physical condition, mood, and emotional state.

[0356] Step 6:

[0357] The server sends the determined aroma blend information to the terminal as an API response. The response includes details such as the specific aroma oil type, amount to be used, blending method, and usage instructions. For example, it suggests mixing "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" and using it once every night.

[0358] Step 7:

[0359] The device receives the API response from the server and notifies the user of its contents. The notification is displayed visually on the application screen and is designed to be easy for the user to understand. For example, the application screen displays an icon of an aroma oil bottle along with detailed instructions on how to use it.

[0360] Step 8:

[0361] The user tries out the proposed aroma blend and enters feedback through the application about its effectiveness and satisfaction. The feedback includes perceived effectiveness, satisfaction, and areas for improvement. Specifically, the user enters the comment, "It was very relaxing."

[0362] Step 9:

[0363] The device temporarily stores the feedback data entered by the user and generates an API request to send to the server. The generated request is encrypted and sent to the server. For example, the request may contain feedback data such as "very relaxing" or "no improvement needed."

[0364] Step 10:

[0365] The server analyzes the received feedback data and inputs it into a machine learning model. This allows the model to be retrained based on the feedback data, improving the accuracy of future aroma blend suggestions. Specifically, feedback such as "I felt very relaxed" will be reflected in the next suggestion, enabling more personalized suggestions.

[0366] (Application example 2)

[0367] 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."

[0368] In modern self-driving vehicles, there is a lack of relaxation methods that correspond to the physical condition and mood of the driver and passengers during long driving sessions, which causes stress and fatigue to accumulate.In addition, there is no system that can recognize the emotional state of each user in real time and respond appropriately, which makes it difficult to provide personalized relaxation effects.

[0369] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice and facial expression data via a camera and microphone to recognize the user's emotional state, means for transmitting information and emotional data received from the user to the server, and means for analyzing the user information and emotional state data received by the server and determining the optimal aroma blend for the user's condition. This makes it possible to provide optimal aromatherapy based on the user's real-time physical condition and emotional state, thereby reducing stress and fatigue in an autonomous vehicle.

[0370] The "means for receiving information about the user's physical condition, mood, and favorite smell" is a device or application that provides an interface through which the user can input information about their physical condition, mood, and favorite smell.

[0371] "Means for collecting voice and facial expression data via a camera or microphone to recognize the emotional state of a user" refers to a device that acquires data using a camera or microphone to detect the emotional state of a user from their voice or facial expression.

[0372] The "means for transmitting information and emotional data received from the user to the server" refers to a device or application with a communication function for transferring the user's input information and collected emotional data to the server.

[0373] The "means for analyzing the user information and emotional state data received by the server and determining the optimal aroma blend for the user's state" refers to a server equipped with an algorithm or machine learning model that analyzes the received information and emotional data and determines the optimal aroma type and blend based on that.

[0374] The "means for notifying the user of the aroma blend information determined by the server" refers to a device or application that has a display function or notification function for informing the user of the results of the aroma blend.

[0375] "Means for receiving feedback from users after using an aroma and transmitting it to a server" refers to a device or application with an interface and communication functions that allows users to input their impressions and effects after using an aroma and transmit that data to a server.

[0376] The "means for improving subsequent aroma blend suggestions based on received feedback" is a server that analyzes user feedback and retrains the machine learning model to improve the accuracy of subsequent aroma blend suggestions.

[0377] The "means for correcting aroma blend suggestions by referring to seasonal fluctuations and the user's past usage history" refers to a server equipped with an algorithm that adjusts aroma blend suggestions by taking into account seasonal fluctuations in demand for fragrances and the user's past feedback data.

[0378] "Means for the server to learn feedback data using a machine learning model and improve the accuracy of future suggestions" refers to a mechanism that uses a machine learning model to learn feedback data from users and improves the accuracy of future aroma suggestions based on the results.

[0379] The aromatherapist system of this invention is realized by an application that operates in conjunction with a smartphone or head-mounted display installed in an autonomous vehicle. This system collects and analyzes the user's physical condition, mood, preferred scents, and emotional state in real time, and based on that data, sprays the optimal aroma inside the vehicle.

[0380] Hardware and software used

[0381] Smartphones and head-mounted displays: Interface for application operation and user input.

[0382] Camera and microphone: Devices for collecting voice and facial expression data.

[0383] Server: Back-end infrastructure for analyzing data and making aroma formulation decisions.

[0384] Specific features

[0385] 1. User Input and Emotion Recognition:

[0386] Users can input their physical condition, mood, and preferred scent using a smartphone or head-mounted display, and the system collects voice and facial expression data in real time through a camera and microphone, and identifies the user's emotional state through an emotion recognition engine.

[0387] 2. Data transmission:

[0388] The information entered by the user and the collected emotional data are temporarily stored on the device and then sent to the server as an API request. The data is encrypted and transmitted in a privacy-protected manner.

[0389] 3. Data analysis and aroma formulation determination:

[0390] The server analyzes the received user information and emotional state data and determines the optimal aroma blend based on that information, using machine learning models that take into account the user's past usage history and seasonal variations.

[0391] 4. Proposal Notice and Aroma Dispersal:

[0392] The aroma blend information determined by the server is then written back to the terminal and notified to the user. The user can confirm the proposed aroma blend and issue a command to spray it inside the car.

[0393] 5. Gathering Feedback and Improving:

[0394] Users try out aroma blends and provide feedback through a dedicated interface, which is then sent to a server to retrain the machine learning model to improve future aroma blend suggestions.

[0395] Specific prompt examples

[0396] Prompt Sentence Examples

[0397] "User's physical condition: tired, mood: stressed, favorite smells: lemon, peppermint. Suggest the best aroma combination based on emotional state: irritated."

[0398] As described above, this system reduces stress and fatigue in the car, providing a comfortable driving experience.

[0399] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0400] Step 1:

[0401] The user inputs their physical condition, mood, and preferred scent using a smartphone or head-mounted display, which then inputs information about the user's condition into the application. The input data is temporarily stored in the device's memory for the next processing step.

[0402] Step 2:

[0403] The user's voice and facial expression data are collected through a camera and microphone. The camera and microphone capture the user's face and voice in real time, and the acquired data is input into an emotion recognition engine. The emotion recognition engine analyzes this data and identifies the user's emotional state (e.g., joy, sadness, irritation, etc.). This analyzed data is also stored in the device's memory.

[0404] Step 3:

[0405] The device temporarily stores the information and emotional data input by the user in storage. Based on this data, it generates an API request and sends it to the server in an encrypted form. This API request includes data on the user's physical condition, mood, preferred scent, and emotional state.

[0406] Step 4:

[0407] The server analyzes the received user information and emotional state data. A machine learning model is used to determine the optimal aroma blend based on the user's current state. The machine learning model is based on a pre-trained dataset and takes into account past usage history and seasonal fluctuations.

[0408] Step 5:

[0409] The server generates aroma blend information based on the analysis results. This information includes details such as the specific aroma oil type, amount to be used, blending method, and usage method. The generated aroma blend information is sent to the device as an API response.

[0410] Step 6:

[0411] The device receives the API response from the server and notifies the user of the suggested aroma blend. The notification is made through a visual interface, allowing the user to confirm the recommended aroma blend. After confirming, the user can spray the aroma into the car through the aroma diffuser.

[0412] Step 7:

[0413] After using the aroma, users enter feedback about its effects and satisfaction through the application. This feedback data is temporarily stored on the device again, and an API request is generated to send it to the server. The feedback data sent to the server through the API request will be used to improve the accuracy of future suggestions.

[0414] Step 8:

[0415] The server analyzes the received feedback data and inputs it into a machine learning model. This analysis retrains the machine learning model, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Second embodiment]

[0420] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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."

[0432] The aromatherapist AI system of this invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, proposal notification, and feedback processing.

[0433] User: Information entry process

[0434] First, the user launches the dedicated application and logs in. Then, on the application screen, the user inputs their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent (e.g., lavender, mint, etc.). This information is collected through the application. This input information is extremely important for determining the aroma blend.

[0435] Terminal: Information transmission process

[0436] The information entered by the user about their physical condition, mood, and preferred scents is stored in temporary storage on the device. The device then generates an API request to send this data to the server, which then sends it. The transmitted data is encrypted to protect privacy.

[0437] Server: Data analysis process

[0438] The server analyzes the received user information. Using a machine learning model, the server determines the optimal aroma combination for the user's current condition. This analysis takes into account not only the user's current physical condition, mood, and preferred scents, but also past feedback data and seasonal patterns. For example, if lavender and bergamot are deemed suitable for a user who needs stress relief, this combination will be suggested.

[0439] Server: Proposal generation process

[0440] The server generates a proposal for the optimal aroma blend for the user based on the analysis results. This proposal includes details such as the specific aroma oil type, amount to use, blending method, and usage method. The proposal is sent to the device as an API response.

[0441] Terminal: Proposal Notification Process

[0442] The device receives the API response from the server and notifies the user of the proposed aroma blend. The user can then check the proposed aroma blend on the application screen. The notification uses a visual interface to make it easy for the user to understand.

[0443] User: Feedback input process

[0444] Users try out the proposed aroma blends and enter their feedback through the application about their experience and satisfaction, including perceived effects, satisfaction, and possible improvements.

[0445] Terminal: Feedback sending process

[0446] The feedback data sent by the user is temporarily stored on the device, and an API request is generated to send it to the server. The device then sends the generated API request to the server.

[0447] Server: Feedback processing process

[0448] The server analyzes the received feedback data and inputs it into a machine learning model. The machine learning model is retrained based on this feedback data, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0449] Specific examples

[0450] User A uses the application to input that he is "stressed," and further states that he "wants to relax," selecting "lavender" and "mint" as his favorite scents. The device sends this information to the server, which then takes into account past feedback and seasonal fluctuation patterns and suggests the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback, rating it as "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of suggestions from next time onwards.

[0451] In this way, this system utilizes artificial intelligence and machine learning to accurately suggest the optimal aroma blend for the user's condition, thereby maximizing the effects of aromatherapy.

[0452] The processing flow will be explained below.

[0453] Step 1:

[0454] The user launches the application and logs in. The user enters information about their physical condition, mood, desired effect (e.g., relaxation, concentration), and preferred scent (e.g., lavender, mint).

[0455] Step 2:

[0456] The device temporarily stores the information entered by the user in storage.

[0457] Step 3:

[0458] The device generates an API request to send the saved user information to the server.

[0459] Step 4:

[0460] The device sends the generated API request to the server.

[0461] Step 5:

[0462] The server receives the API request sent from the device.

[0463] Step 6:

[0464] The server parses the contents of the request body and extracts the user data.

[0465] Step 7:

[0466] The server stores the extracted user data in a database.

[0467] Step 8:

[0468] The server inputs the stored user data into a machine learning model for analysis.

[0469] Step 9:

[0470] The machine learning model calculates the optimal aroma combination based on information such as "physical condition," "mood," "desired effect," and "preferred smell."

[0471] Step 10:

[0472] The server takes into account past feedback data and seasonal fluctuations to adjust the aroma blend.

[0473] Step 11:

[0474] The server will create the optimal aroma combination (e.g., 3 drops lavender, 2 drops mint, 2 drops bergamot).

[0475] Step 12:

[0476] The server creates a message to suggest the generated aroma blend to the user.

[0477] Step 13:

[0478] The server generates an API response to send this message to the device.

[0479] Step 14:

[0480] The device receives the API response from the server.

[0481] Step 15:

[0482] The terminal analyzes the received proposal message and displays it to the user.

[0483] Step 16:

[0484] The user checks the proposed aroma blend on the application screen.

[0485] Step 17:

[0486] The user tries out the suggested aroma and enters feedback on its effectiveness and satisfaction.

[0487] Step 18:

[0488] The device temporarily stores the feedback entered by the user in storage.

[0489] Step 19:

[0490] The device generates an API request to send the saved feedback data to the server.

[0491] Step 20:

[0492] The device sends the generated API request to the server.

[0493] Step 21:

[0494] The server receives the feedback data sent from the terminal.

[0495] Step 22:

[0496] The server analyzes the feedback data and adds it to the dataset of the machine learning model.

[0497] Step 23:

[0498] The server retrains the machine learning model to improve the accuracy of future suggestions.

[0499] Example 1

[0500] 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."

[0501] Conventional aromatherapy systems lack the functionality to suggest optimal aroma blends based on the user's physical condition and mood. In particular, it is difficult to make personalized suggestions that take into account each user's past usage history and feedback, and external factors such as seasonal variations tend to be ignored. Furthermore, systems often lack a mechanism for incorporating user feedback into future suggestions. This poses a challenge, preventing users from maximizing the benefits of aromatherapy.

[0502] 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.

[0503] In this invention, the server includes means for receiving information about the user's physical condition, mood, and preferred scents from the user, means for temporarily storing the received information and generating an API request to send to the server, means for the server to analyze the received user information and determine an aroma blend optimal for the user's condition using a machine learning model, means for the server to send the determined aroma blend information to the terminal as an API response and for the terminal to notify the user, means for receiving feedback from the user after using the aromas and generating an API request to send to the server, means for retraining the machine learning model based on the received feedback to improve subsequent aroma blend suggestions, means for correcting the aroma blend suggestions by referring to seasonal fluctuations and the user's past usage history, and means for the server to learn from the feedback data using the machine learning model and improve the accuracy of subsequent suggestions. This enables highly accurate and personalized suggestions of aroma blends optimal for the user's condition, maximizing the effects of aromatherapy.

[0504] "Physical condition" refers to the physical condition and health status of the user.

[0505] "Mood" refers to the user's emotional or mental state.

[0506] "Favorite scent" refers to the type of scent that the user particularly likes.

[0507] "Means for receiving information" refers to the method for obtaining data entered by the user from the application.

[0508] "Temporary storage" refers to the process of temporarily storing input information in a storage device.

[0509] "Means for generating API requests" refers to the method for creating the request format required to send data to the server.

[0510] "Server" means hardware or software for processing, analyzing, and storing data over a network.

[0511] "Machine learning model" refers to an algorithmic model used for data analysis and prediction.

[0512] "API response" refers to the response data sent from the server to the terminal.

[0513] "Means of notification" refers to the method by which the terminal presents information to the user.

[0514] "Feedback" refers to the impressions and evaluations provided by users after using an aroma.

[0515] "Retraining" refers to the process of retraining a machine learning model using new data received.

[0516] "Seasonal variation" refers to the pattern of the external environment that changes with the seasons.

[0517] "Usage history" refers to records of aroma compounds used by the user in the past and their effects.

[0518] "Corrective measures" refer to methods for fine-tuning proposals based on existing data and conditions.

[0519] "Suggestion accuracy" refers to the degree to which the optimum formulation for the user's condition can be accurately suggested.

[0520] "Terminal" refers to a device that allows a user to input or receive information.

[0521] The aromatherapist AI system of this invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, proposal notification, and feedback processing.

[0522] Hardware and software used

[0523] The implementation of this system uses the following hardware and software:

[0524] User devices: devices such as smartphones, tablets, and PCs

[0525] Application: A dedicated application that runs on the user's device

[0526] Server: Cloud or on-premise server

[0527] Database: A database system for storing user information and feedback data.

[0528] Machine learning models: Machine learning algorithms for analyzing and predicting aroma formulations

[0529] Natural language explanation of the process

[0530] User: Enter information

[0531] The user launches the application and logs in. After logging in, they input their physical condition, mood, desired effect (e.g., relaxation, concentration, refreshment), and favorite scent (e.g., lavender, mint). This input is done through the application's user interface.

[0532] Terminal: Sending information

[0533] The device stores the information entered by the user in temporary storage and generates an API request to send to the server, which is sent encrypted using HTTP.

[0534] Server: Data analysis

[0535] The server stores the received user information in a database. The stored data is then input into a machine learning model to determine the optimal aroma blend for the user's condition. This analysis also takes into account past usage history, seasonal patterns, and feedback data.

[0536] Server: Proposal Generation

[0537] The server generates the optimal aroma blend based on the analysis results. This proposal includes the specific type of aroma oil, the amount to be used, the blending method, and even the method of use. The generated proposal is sent to the device as an API response.

[0538] Device: Proposal Notification

[0539] The device uses the API response received from the server to notify the user of the proposed content. The notification is done using a visual interface and is displayed in a user-friendly format.

[0540] User:Feedback

[0541] Users try out the proposed aroma blends and enter feedback on their results and satisfaction, including perceived effects, satisfaction, and areas for improvement.

[0542] Terminal and Server: Feedback Processing

[0543] The device temporarily stores the feedback data, generates an API request to send it to the server, and sends it to the server. The server analyzes the received feedback data and inputs it into a machine learning model for retraining. This improves the accuracy of aroma blend suggestions from the next time onwards.

[0544] Specific examples

[0545] For example, User A uses the application to input "stress," states that he or she "wants to relax," and selects "lavender" and "mint" as his or her favorite scents. The device sends this information to the server, which then considers past feedback data and seasonal fluctuation patterns to suggest the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback that it was "very relaxing." This feedback is used in the next analysis, further improving the accuracy of the suggestions.

[0546] Examples of prompt statements

[0547] Enter the following prompt into the generative AI model:

[0548] "The user says they are stressed and want to relax. Their favorite aromas are lavender and mint. Please suggest the best aroma combination."

[0549] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0550] Step 1: Enter your user information

[0551] The user launches the dedicated application and logs in. After logging in, they enter their physical condition, mood, favorite scent, and desired effect on the application screen. For example, they might enter "I'm stressed," "I want to relax," or "I like lavender and mint." This input is done through the application's user interface (UI) and is saved in the device's temporary storage.

[0552] Step 2: Send data

[0553] The device temporarily stores the information entered by the user, then generates an API request to send it to the server. This API request includes encrypted user data. The generated API request is sent to the server via the Internet.

[0554] Step 3: Receiving and storing data on the server

[0555] The server receives API requests sent from the device and stores user information in a database. Specifically, it analyzes the data received as an HTTP request and stores it in the appropriate table in the database based on the specifications. This stored data includes the user's physical condition, mood, preferred scent, and desired effect.

[0556] Step 4: Data analysis

[0557] The server inputs the saved user information into a machine learning model and begins analysis. This machine learning model also references past usage history, seasonal fluctuation patterns, feedback data, etc. to determine the optimal aroma blend. For example, a suggestion such as "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" may be generated. The model performs data calculations based on the input data and outputs a suggestion for the optimal aroma blend.

[0558] Step 5: Proposal generation and submission

[0559] The server generates specific aroma blend suggestions for the user based on the analysis results obtained from the machine learning model. These suggestions include the type, amount, blending method, and usage of aroma oils to be used. The generated suggestions are sent to the device as an API response.

[0560] Step 6: Proposal Notification

[0561] The device notifies the user of the proposed aroma blend based on the API response received from the server. The result is displayed on the application screen in a visually easy-to-understand interface. The user can check the notification and try out the proposed aroma blend.

[0562] Step 7: Enter your feedback

[0563] Users try out the proposed aroma blends and enter feedback through the application about their effects and satisfaction, such as "It was very relaxing" or "I wish there was a bit more mint."

[0564] Step 8: Send your feedback

[0565] The device temporarily stores the feedback data received from the user and generates an API request to send to the server, which is also encrypted before being sent to the server.

[0566] Step 9: Feedback processing and model retraining

[0567] The server analyzes the received feedback data and stores it in a database. This feedback data is then input into the machine learning model for retraining. This allows the machine learning model to improve the accuracy of its aroma blending suggestions from the next time onwards.

[0568] Through these steps, the aromatherapist AI system can propose the aroma combination that is best suited to the user's condition and continuously improve the accuracy of its proposals based on feedback.

[0569] (Application example 1)

[0570] 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."

[0571] Conventional aromatherapy systems often fail to effectively suggest aroma blends based on the user's physical condition, mood, and preferred scents, making it difficult to provide individually optimized services. They also lack a means to effectively utilize user feedback to improve the accuracy of their next suggestions. Furthermore, suggestions are limited to simple notifications, which lacks user convenience and immediacy.

[0572] 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.

[0573] In this invention, the server includes means for receiving information on the user's physical condition, mood, and preferred scent from the user, means for transmitting the information received from the user to the server, means for the server to analyze the user information received and determine an aroma blend optimal for the user's condition, means for notifying the smart device of the aroma blend information determined by the server, means for receiving feedback from the user after using the aroma via the smart device and transmitting the feedback to the server, and means for improving subsequent aroma blend suggestions based on the received feedback. This not only makes it possible to suggest an aroma blend optimal for the user's condition, but also makes it possible to continuously improve the service based on the feedback and enhance the user experience.

[0574] "User information" is information collected from the user about their physical condition, mood, and favorite smell.

[0575] The "server" is a central processing unit that analyzes user information, determines the aroma blend that best suits the user's condition, and notifies the smart device of the results.

[0576] A "smart device" is an electronic device that can input user information, receive aroma blend information, and receive and send feedback, and includes smartphones and smart glasses.

[0577] An "aroma blend" is a combination of aroma oils optimized according to the user's physical condition, mood, and preferred scent.

[0578] "Feedback" refers to information about the evaluation, impressions, and satisfaction level submitted by a user after trying out the proposed aroma blend.

[0579] "Data analysis" is an information processing method for determining the optimal aroma blend using user information and feedback received by the server.

[0580] A "machine learning model" is an algorithm that learns from feedback data and improves the accuracy of aroma blend suggestions from the next time onwards.

[0581] The aromatherapist AI system of this invention utilizes smart devices to suggest optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, suggestion notification, and feedback processing.

[0582] User operations

[0583] First, the user puts on a smart device (such as a smartphone or smart glasses), launches a dedicated application, and logs in. On the application screen, the user enters their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and preferred scent (e.g., lavender, mint, etc.). This information is crucial for determining the aroma blend.

[0584] Data transmission

[0585] The information entered by the user regarding their physical condition, mood, and preferred scent is stored in temporary storage on the smart device, after which the smart device generates an API request to send this data to the server, encrypts it, and sends it to the server.

[0586] Data analysis

[0587] The server uses a machine learning model called a generative AI model to analyze the received user information. Data analysis takes into account not only the user's current condition, but also past feedback data and seasonal patterns, and determines the optimal aroma combination based on this. For example, a combination of lavender and bergamot may be recommended, as it is determined to be effective in relieving stress based on past data.

[0588] proposal notification

[0589] The determined aroma blend information is sent to the smart device as an API response. The smart device receives this information and notifies the user visually or audibly. The user can then check the proposed aroma blend on the application screen and view details such as the specific type of aroma oil, the amount to be used, the blending method, and how to use it.

[0590] Feedback Processing

[0591] The user tries out the proposed aroma blend and enters feedback on its effectiveness and satisfaction via their smart device. This feedback includes perceived effectiveness, satisfaction, and areas for improvement. The feedback data is temporarily stored on the smart device and then sent back to the server.

[0592] Continuous improvement

[0593] The server analyzes the received feedback data and inputs it into the generative AI model. This retrains the machine learning model, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0594] Specific examples

[0595] For example, if a user inputs that they are "stressed" and desires to "relax," selecting "lavender" and "mint" as their favorite scents, this user information is sent to the server. The server uses a generative AI model to consider past feedback and seasonal fluctuation patterns, and suggests "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" as the optimal aroma blend. The user tries this and provides feedback that they found it "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of future suggestions.

[0596] Prompt Sentence Examples

[0597] "User feedback: 'Very relaxing'. Please use this feedback to re-learn the optimal aroma combination to improve the accuracy of our suggestions next time."

[0598] In this way, the system of the present invention can accurately suggest personalized aroma blends based on the user's physical condition and mood, improving the user experience.

[0599] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0600] Step 1: Enter user information

[0601] The user launches a dedicated application using a smart device (e.g., a smartphone or smart glasses) and logs in. On the application screen, the user enters their current physical condition (e.g., stressed), mood (e.g., wanting to relax), desired effect, and favorite scent (e.g., lavender, mint). This information is used in the next processing step.

[0602] Input: physical condition, mood, favorite smell

[0603] Output: User information data

[0604] Step 2: Send data

[0605] The device temporarily stores the information entered by the user in storage, then generates an API request to send the stored user information data to the server, encrypts the data, and sends it to the server.

[0606] Input: User information data

[0607] Output: API request to the server

[0608] Step 3: Data analysis

[0609] The server analyzes the received user information data using a generative AI model, which takes into account the user's current condition, past feedback data, and seasonal patterns to determine the optimal aroma blend.

[0610] Input: User information data, past feedback data, seasonal fluctuation patterns

[0611] Output: Optimal aroma blend data

[0612] Step 4: Proposal Notification

[0613] The server sends the determined optimal aroma blend data to the terminal as an API response, and the terminal notifies the user of the received aroma blend data via the smart device's display or voice notification.

[0614] Input: Optimal aroma blend data

[0615] Output: Aroma blending suggestions notified to the user

[0616] Step 5: Enter your feedback

[0617] The user tries out the proposed aroma blend and enters feedback on its effectiveness and satisfaction. This feedback data is then temporarily stored on the smart device.

[0618] Input: Impressions after use, satisfaction level

[0619] Output: User feedback data

[0620] Step 6: Send your feedback

[0621] The terminal generates an API request for transmitting the feedback data collected from the user to the server, and transmits the request to the server.

[0622] Input: User feedback data

[0623] Output: API request to the server

[0624] Step 7: Feedback analysis and model retraining

[0625] The server analyzes the received feedback data and reflects it in the generative AI model. This re-learning improves the accuracy of aroma blend suggestions from the next time onwards.

[0626] Input: User feedback data

[0627] Output: Updated machine learning model

[0628] Through these steps, the aromatherapist AI system of the present invention can provide optimal aroma blends that meet the individual needs of users and can continuously improve them based on feedback.

[0629] 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.

[0630] The aromatherapist AI system of the present invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. Furthermore, by combining it with an emotion engine, the system also recognizes the user's emotional state and proposes aroma blends based on that. This system consists of multiple processes: user input, emotion recognition data acquisition, data transmission, data analysis, proposal notification, and feedback processing.

[0631] User: Information entry process

[0632] First, the user launches the dedicated application and logs in. Then, on the application screen, the user inputs their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent (e.g., lavender, mint, etc.). The input information is crucial for determining the aroma composition.

[0633] User: Emotion recognition process

[0634] While the user is inputting, the device's built-in camera and microphone collect the user's voice and facial expression data. The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise, etc.). The emotional state data is sent to the server along with information on the user's physical condition and mood.

[0635] Terminal: Information transmission process

[0636] The information entered by the user regarding their physical condition, mood, and preferred scent, as well as the emotional state data recognized by the emotion engine, are stored in temporary storage on the device. The device then generates an API request to send this data to the server, which then sends it to the server. The transmitted data is encrypted to ensure privacy.

[0637] Server: Data analysis process

[0638] The server analyzes the received user information and uses a machine learning model to determine the optimal aroma blend for the user's current state. This analysis takes into account data such as physical condition, mood, and preferred scents, as well as emotional state data recognized by the emotion engine. For example, if the server recognizes that the user is feeling stressed, it will suggest aroma oils with a relaxing effect (e.g., lavender or bergamot).

[0639] Server: Proposal generation process

[0640] The server generates a proposal for the optimal aroma blend for the user based on the analysis results. This proposal includes details such as the specific aroma oil type, amount to use, blending method, and usage method. The proposal is sent to the device as an API response.

[0641] Terminal: Proposal Notification Process

[0642] The device receives the API response from the server and notifies the user of the proposed aroma blend. The user can then check the proposed aroma blend on the application screen. The notification uses a visual interface to make it easy for the user to understand.

[0643] User: Feedback input process

[0644] Users try out the proposed aroma blends and enter their feedback through the application about their experience and satisfaction, including perceived effects, satisfaction, and possible improvements.

[0645] Terminal: Feedback sending process

[0646] The feedback data sent by the user is temporarily stored on the device, and an API request is generated to send it to the server. The device then sends the generated API request to the server.

[0647] Server: Feedback processing process

[0648] The server analyzes the received feedback data and inputs it into a machine learning model. The machine learning model is retrained based on this feedback data, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0649] Specific examples

[0650] User A uses the application to input that he is "stressed," and further states that he "wants to relax," selecting "lavender" and "mint" as his favorite scents. The device collects this information along with the user's facial expressions and voice data, and uses an emotion engine to recognize "irritation." The device then sends this data set to the server. Taking into account past feedback and seasonal fluctuation patterns, the server suggests the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback, rating it as "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of future suggestions.

[0651] By combining this with an emotion engine, it will be possible to propose sophisticated aroma blends that take into account even the subtlest emotional changes of the user, which is expected to maximize the effects of aromatherapy.

[0652] The processing flow will be explained below.

[0653] Step 1:

[0654] The user launches the application and logs in. The user enters information about their physical condition, mood, desired effect (e.g., relaxation, concentration), and preferred scent (e.g., lavender, mint).

[0655] Step 2:

[0656] The device's built-in camera and microphone collect the user's voice and facial expression data.

[0657] Step 3:

[0658] The device transmits the collected voice and facial expression data to the emotion engine in real time.

[0659] Step 4:

[0660] The emotion engine analyzes the user's voice tone, facial expression changes, and language patterns to recognize the user's emotional state (e.g., joy, sadness, anger, surprise).

[0661] Step 5:

[0662] The device temporarily stores information entered by the user regarding physical condition, mood, and preferred scent, as well as emotional state data recognized by the emotion engine.

[0663] Step 6:

[0664] The device generates an API request to send the stored user information and emotional state data to the server.

[0665] Step 7:

[0666] The device sends the generated API request to the server.

[0667] Step 8:

[0668] The server receives the API request sent from the device.

[0669] Step 9:

[0670] The server parses the contents of the request body and extracts user data and emotional state data.

[0671] Step 10:

[0672] The server stores the extracted user data and emotional state data in a database.

[0673] Step 11:

[0674] The server inputs the stored user data and emotional state data into a machine learning model for analysis.

[0675] Step 12:

[0676] The machine learning model calculates the optimal aroma combination based on information such as "physical condition," "mood," "desired effect," "preferred smell," and "emotional state."

[0677] Step 13:

[0678] The server takes into account past feedback data and seasonal fluctuations to adjust the aroma blend.

[0679] Step 14:

[0680] The server will create the optimal aroma combination (e.g., 3 drops lavender, 2 drops mint, 2 drops bergamot).

[0681] Step 15:

[0682] The server creates a message to suggest the generated aroma blend to the user.

[0683] Step 16:

[0684] The server generates an API response to send this message to the device.

[0685] Step 17:

[0686] The device receives the API response from the server.

[0687] Step 18:

[0688] The terminal analyzes the received proposal message and notifies the user.

[0689] Step 19:

[0690] The user checks the proposed aroma blend on the application screen.

[0691] Step 20:

[0692] The user tries out the suggested aroma and enters feedback on its effectiveness and satisfaction.

[0693] Step 21:

[0694] The device temporarily stores the feedback entered by the user in storage.

[0695] Step 22:

[0696] The device generates an API request to send the saved feedback data to the server.

[0697] Step 23:

[0698] The device sends the generated API request to the server.

[0699] Step 24:

[0700] The server receives the feedback data sent from the terminal.

[0701] Step 25:

[0702] The server analyzes the feedback data and adds it to the dataset of the machine learning model.

[0703] Step 26:

[0704] The server retrains the machine learning model to improve the accuracy of future suggestions.

[0705] Example 2

[0706] 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."

[0707] Conventional aromatherapy systems only suggest aroma blends based on the user's physical condition and mood, but do not take into account the user's emotional state. This makes it difficult to suggest personalized aroma blends that respond to subtle changes in the user's emotions. Furthermore, the accuracy of suggestions based on feedback has not been sufficiently improved.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0709] In this invention, the server includes means for receiving information about the user's physical condition, mood, and preferred scent from the user, means for collecting the user's voice and facial expression data using a camera and microphone while the user is inputting the information, means for analyzing the collected emotional state data, means for transmitting the information received from the user and the emotional state data to the server, means for the server to analyze the received user information and emotional state data and determine an aroma blend optimal for the user's condition, means for notifying the user of the aroma blend information determined by the server, means for receiving feedback from the user after using the aromas and transmitting it to the server, means for improving subsequent aroma blend suggestions based on the received feedback, means for recognizing the user's emotional changes using an emotion engine and reflecting them in aroma blend suggestions, and means for learning the user's feedback using a machine learning model to improve the accuracy of subsequent suggestions. This enables advanced personalization that takes into account not only the user's physical condition and mood but also their emotional state, thereby maximizing the effects of aromatherapy.

[0710] "Physical condition" refers to the user's physical health condition and current physical condition.

[0711] "Mood" refers to the user's psychological and emotional state, or how they feel at a given moment.

[0712] "Favorite scent" refers to the aroma or type of scent that the user particularly likes.

[0713] "Camera" refers to a video input device for capturing the user's facial expression.

[0714] "Microphone" refers to an audio input device for capturing a user's voice.

[0715] "Voice data" refers to audio information obtained from a user's voice and speaking style.

[0716] "Facial expression data" refers to visual information obtained from the user's facial expressions.

[0717] An "emotion engine" refers to software or hardware that analyzes collected voice and facial expression data and recognizes the user's emotional state.

[0718] "Emotional state" refers to the emotions the user is feeling at that time, such as joy, sadness, anger, surprise, etc.

[0719] "Analysis" refers to the act of processing received and collected data to derive a specific conclusion or result.

[0720] "Server" refers to a central processing unit that receives and analyzes data sent by users.

[0721] "Aroma blend" refers to the types and proportions of aromatic oils blended to bring out a specific effect.

[0722] "Notification" refers to the act of sending information to inform users of the proposed content and analysis results.

[0723] "Feedback" refers to the act of a user providing the results and impressions of a proposed aroma blend after trying it out.

[0724] A "machine learning model" refers to an algorithm or system that learns from data and improves the accuracy of future suggestions and predictions.

[0725] "Personalization" refers to the act of customizing offers and services to suit the individual preferences and circumstances of each user.

[0726] "Encryption" refers to the technology of converting data so that it cannot be read by third parties.

[0727] The aromatherapist AI system of the present invention is a system that proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. Furthermore, it utilizes an emotion engine to take the user's emotional state into consideration. Specific embodiments are described below.

[0728] Users use a device such as a smartphone or tablet to launch a dedicated application and log in. After logging in, users enter their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and preferred scent on the application screen. This input information is important for determining the aroma blend.

[0729] While the user is typing, the device's built-in camera and microphone collect the user's voice and facial expression data. This data is analyzed in real time by an emotion engine to recognize the user's emotional state. Examples of emotion engines include Microsoft Azure Cognitive Services and IBM Watson.

[0730] The collected data on physical condition, mood, preferred odor, and emotional state is stored in temporary storage on the device, after which the device generates an API request to send this data to the server, where it is encrypted and sent.

[0731] The server analyzes the data received from the device and uses a machine learning model to determine the optimal aroma combination for the user's current state. This analysis process takes into account the user's physical condition, mood, preferred scents, and emotional state data. Examples of machine learning models include TensorFlow and PyTorch.

[0732] The server then uses the analysis results to propose the optimal aroma blend for the user. This proposal includes the specific type of aroma oil, the amount to use, the blending method, and how to use it. The proposal is sent to the device as an API response.

[0733] The device receives the API response from the server and notifies the user of the proposed content. The notification is sent via the application screen and displayed in a visually easy-to-understand format.

[0734] Users try out the proposed aroma blends and enter their feedback through the application about their perceived effects and satisfaction, as well as areas for improvement.

[0735] The device temporarily stores the feedback data and generates an API request to send it to the server, where it is encrypted and sent.

[0736] The server analyzes the received feedback data and inputs it into a machine learning model, which then retrains the model based on the feedback data, improving the accuracy of future suggestions.

[0737] As a concrete example, user A uses an application, inputs that he is "stressed," and selects his favorite scents as "lavender" and "mint," saying that he "wants to relax." When the device collects this information, it also analyzes the user's facial expressions and voice data using an emotion engine to recognize "irritation." The server considers past feedback and seasonal fluctuation patterns and suggests "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" as the optimal aroma blend. User A tries this blend and sends feedback that it was "very relaxing." This feedback is reflected in future suggestions.

[0738] Example prompts to input to the generative AI model:

[0739] "Suggest the best aroma combination based on your current physical condition, mood, preferred smell, and emotional state. Example: Use lavender, bergamot, and mint."

[0740] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0741] Step 1:

[0742] The user launches a dedicated application and logs in. After logging in, they enter their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent into the input form displayed on the application screen. This generates data on physical condition, mood, desired effect, and favorite scent. Examples of input data include "Physical condition: tired," "Mood: stressed," "Desired effect: relaxation," and "Favorite scent: lavender, mint."

[0743] Step 2:

[0744] While the user is entering information, the device's built-in camera and microphone collect the user's voice and facial expression data. The collected voice and facial expression data is sent to an emotion engine, which recognizes the user's emotional state as "happiness," "sadness," "irritation," etc. Specifically, the camera captures the user's facial expressions while the user is entering information, and the microphone records the voice. This data is analyzed in real time by the emotion engine, and "irritation" is output as emotional state data.

[0745] Step 3:

[0746] The device temporarily stores data entered by the user regarding their physical condition, mood, and favorite scent, as well as the emotional state data recognized by the emotion engine. It then generates an API request to send this data to the server. Specifically, it generates a data packet containing "Physical condition: tired," "Mood: stressed," "Favorite scent: lavender, mint," and "Emotional state: irritated," encrypts it, and sends it to the server.

[0747] Step 4:

[0748] The server receives the data sent from the device. The received data is stored in a database and input into a machine learning model for analysis. Specific examples of data processing include integrating data on physical condition, mood, preferred scent, and emotional state and converting it into a format suitable for analysis.

[0749] Step 5:

[0750] The server uses machine learning models to determine the optimal aroma blend for the user's current state. Based on the analysis results, a specific aroma blend, such as "3 drops lavender, 2 drops mint, and 2 drops bergamot," is determined. This output is best suited to the user's physical condition, mood, and emotional state.

[0751] Step 6:

[0752] The server sends the determined aroma blend information to the terminal as an API response. The response includes details such as the specific aroma oil type, amount to be used, blending method, and usage instructions. For example, it suggests mixing "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" and using it once every night.

[0753] Step 7:

[0754] The device receives the API response from the server and notifies the user of its contents. The notification is displayed visually on the application screen and is designed to be easy for the user to understand. For example, the application screen displays an icon of an aroma oil bottle along with detailed instructions on how to use it.

[0755] Step 8:

[0756] The user tries out the proposed aroma blend and enters feedback through the application about its effectiveness and satisfaction. The feedback includes perceived effectiveness, satisfaction, and areas for improvement. Specifically, the user enters the comment, "It was very relaxing."

[0757] Step 9:

[0758] The device temporarily stores the feedback data entered by the user and generates an API request to send to the server. The generated request is encrypted and sent to the server. For example, the request may contain feedback data such as "very relaxing" or "no improvement needed."

[0759] Step 10:

[0760] The server analyzes the received feedback data and inputs it into a machine learning model. This allows the model to be retrained based on the feedback data, improving the accuracy of future aroma blend suggestions. Specifically, feedback such as "I felt very relaxed" will be reflected in the next suggestion, enabling more personalized suggestions.

[0761] (Application example 2)

[0762] 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."

[0763] In modern self-driving vehicles, there is a lack of relaxation methods that correspond to the physical condition and mood of the driver and passengers during long driving sessions, which causes stress and fatigue to accumulate.In addition, there is no system that can recognize the emotional state of each user in real time and respond appropriately, which makes it difficult to provide personalized relaxation effects.

[0764] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice and facial expression data via a camera and microphone to recognize the user's emotional state, means for transmitting information and emotional data received from the user to the server, and means for analyzing the user information and emotional state data received by the server and determining the optimal aroma blend for the user's condition. This makes it possible to provide optimal aromatherapy based on the user's real-time physical condition and emotional state, thereby reducing stress and fatigue in an autonomous vehicle.

[0765] The "means for receiving information about the user's physical condition, mood, and favorite smell" is a device or application that provides an interface through which the user can input information about their physical condition, mood, and favorite smell.

[0766] "Means for collecting voice and facial expression data via a camera or microphone to recognize the emotional state of a user" refers to a device that acquires data using a camera or microphone to detect the emotional state of a user from their voice or facial expression.

[0767] The "means for transmitting information and emotional data received from the user to the server" refers to a device or application with a communication function for transferring the user's input information and collected emotional data to the server.

[0768] The "means for analyzing the user information and emotional state data received by the server and determining the optimal aroma blend for the user's state" refers to a server equipped with an algorithm or machine learning model that analyzes the received information and emotional data and determines the optimal aroma type and blend based on that.

[0769] The "means for notifying the user of the aroma blend information determined by the server" refers to a device or application that has a display function or notification function for informing the user of the results of the aroma blend.

[0770] "Means for receiving feedback from users after using an aroma and transmitting it to a server" refers to a device or application with an interface and communication functions that allows users to input their impressions and effects after using an aroma and transmit that data to a server.

[0771] The "means for improving subsequent aroma blend suggestions based on received feedback" is a server that analyzes user feedback and retrains the machine learning model to improve the accuracy of subsequent aroma blend suggestions.

[0772] The "means for correcting aroma blend suggestions by referring to seasonal fluctuations and the user's past usage history" refers to a server equipped with an algorithm that adjusts aroma blend suggestions by taking into account seasonal fluctuations in demand for fragrances and the user's past feedback data.

[0773] "Means for the server to learn feedback data using a machine learning model and improve the accuracy of future suggestions" refers to a mechanism that uses a machine learning model to learn feedback data from users and improves the accuracy of future aroma suggestions based on the results.

[0774] The aromatherapist system of this invention is realized by an application that operates in conjunction with a smartphone or head-mounted display installed in an autonomous vehicle. This system collects and analyzes the user's physical condition, mood, preferred scents, and emotional state in real time, and based on that data, sprays the optimal aroma inside the vehicle.

[0775] Hardware and software used

[0776] Smartphones and head-mounted displays: Interface for application operation and user input.

[0777] Camera and microphone: Devices for collecting voice and facial expression data.

[0778] Server: Back-end infrastructure for analyzing data and making aroma formulation decisions.

[0779] Specific features

[0780] 1. User Input and Emotion Recognition:

[0781] Users can input their physical condition, mood, and preferred scent using a smartphone or head-mounted display, and the system collects voice and facial expression data in real time through a camera and microphone, and identifies the user's emotional state through an emotion recognition engine.

[0782] 2. Data transmission:

[0783] The information entered by the user and the collected emotional data are temporarily stored on the device and then sent to the server as an API request. The data is encrypted and transmitted in a privacy-protected manner.

[0784] 3. Data analysis and aroma formulation determination:

[0785] The server analyzes the received user information and emotional state data and determines the optimal aroma blend based on that information, using machine learning models that take into account the user's past usage history and seasonal variations.

[0786] 4. Proposal Notice and Aroma Dispersal:

[0787] The aroma blend information determined by the server is then written back to the terminal and notified to the user. The user can confirm the proposed aroma blend and issue a command to spray it inside the car.

[0788] 5. Gathering Feedback and Improving:

[0789] Users try out aroma blends and provide feedback through a dedicated interface, which is then sent to a server to retrain the machine learning model to improve future aroma blend suggestions.

[0790] Specific prompt examples

[0791] Prompt Sentence Examples

[0792] "User's physical condition: tired, mood: stressed, favorite smells: lemon, peppermint. Suggest the best aroma combination based on emotional state: irritated."

[0793] As described above, this system reduces stress and fatigue in the car, providing a comfortable driving experience.

[0794] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0795] Step 1:

[0796] The user inputs their physical condition, mood, and preferred scent using a smartphone or head-mounted display, which then inputs information about the user's condition into the application. The input data is temporarily stored in the device's memory for the next processing step.

[0797] Step 2:

[0798] The user's voice and facial expression data are collected through a camera and microphone. The camera and microphone capture the user's face and voice in real time, and the acquired data is input into an emotion recognition engine. The emotion recognition engine analyzes this data and identifies the user's emotional state (e.g., joy, sadness, irritation, etc.). This analyzed data is also stored in the device's memory.

[0799] Step 3:

[0800] The device temporarily stores the information and emotional data input by the user in storage. Based on this data, it generates an API request and sends it to the server in an encrypted form. This API request includes data on the user's physical condition, mood, preferred scent, and emotional state.

[0801] Step 4:

[0802] The server analyzes the received user information and emotional state data. A machine learning model is used to determine the optimal aroma blend based on the user's current state. The machine learning model is based on a pre-trained dataset and takes into account past usage history and seasonal fluctuations.

[0803] Step 5:

[0804] The server generates aroma blend information based on the analysis results. This information includes details such as the specific aroma oil type, amount to be used, blending method, and usage method. The generated aroma blend information is sent to the device as an API response.

[0805] Step 6:

[0806] The device receives the API response from the server and notifies the user of the suggested aroma blend. The notification is made through a visual interface, allowing the user to confirm the recommended aroma blend. After confirming, the user can spray the aroma into the car through the aroma diffuser.

[0807] Step 7:

[0808] After using the aroma, users enter feedback about its effects and satisfaction through the application. This feedback data is temporarily stored on the device again, and an API request is generated to send it to the server. The feedback data sent to the server through the API request will be used to improve the accuracy of future suggestions.

[0809] Step 8:

[0810] The server analyzes the received feedback data and inputs it into a machine learning model. This analysis retrains the machine learning model, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] [Third embodiment]

[0815] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0816] 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.

[0817] 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).

[0818] 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.

[0819] 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.

[0820] 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).

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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."

[0827] The aromatherapist AI system of this invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, proposal notification, and feedback processing.

[0828] User: Information entry process

[0829] First, the user launches the dedicated application and logs in. Then, on the application screen, the user inputs their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent (e.g., lavender, mint, etc.). This information is collected through the application. This input information is extremely important for determining the aroma blend.

[0830] Terminal: Information transmission process

[0831] The information entered by the user about their physical condition, mood, and preferred scents is stored in temporary storage on the device. The device then generates an API request to send this data to the server, which then sends it. The transmitted data is encrypted to protect privacy.

[0832] Server: Data analysis process

[0833] The server analyzes the received user information. Using a machine learning model, the server determines the optimal aroma combination for the user's current condition. This analysis takes into account not only the user's current physical condition, mood, and preferred scents, but also past feedback data and seasonal patterns. For example, if lavender and bergamot are deemed suitable for a user who needs stress relief, this combination will be suggested.

[0834] Server: Proposal generation process

[0835] The server generates a proposal for the optimal aroma blend for the user based on the analysis results. This proposal includes details such as the specific aroma oil type, amount to use, blending method, and usage method. The proposal is sent to the device as an API response.

[0836] Terminal: Proposal Notification Process

[0837] The device receives the API response from the server and notifies the user of the proposed aroma blend. The user can then check the proposed aroma blend on the application screen. The notification uses a visual interface to make it easy for the user to understand.

[0838] User: Feedback input process

[0839] Users try out the proposed aroma blends and enter their feedback through the application about their experience and satisfaction, including perceived effects, satisfaction, and possible improvements.

[0840] Terminal: Feedback sending process

[0841] The feedback data sent by the user is temporarily stored on the device, and an API request is generated to send it to the server. The device then sends the generated API request to the server.

[0842] Server: Feedback processing process

[0843] The server analyzes the received feedback data and inputs it into a machine learning model. The machine learning model is retrained based on this feedback data, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0844] Specific examples

[0845] User A uses the application to input that he is "stressed," and further states that he "wants to relax," selecting "lavender" and "mint" as his favorite scents. The device sends this information to the server, which then takes into account past feedback and seasonal fluctuation patterns and suggests the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback, rating it as "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of suggestions from next time onwards.

[0846] In this way, this system utilizes artificial intelligence and machine learning to accurately suggest the optimal aroma blend for the user's condition, thereby maximizing the effects of aromatherapy.

[0847] The processing flow will be explained below.

[0848] Step 1:

[0849] The user launches the application and logs in. The user enters information about their physical condition, mood, desired effect (e.g., relaxation, concentration), and preferred scent (e.g., lavender, mint).

[0850] Step 2:

[0851] The device temporarily stores the information entered by the user in storage.

[0852] Step 3:

[0853] The device generates an API request to send the saved user information to the server.

[0854] Step 4:

[0855] The device sends the generated API request to the server.

[0856] Step 5:

[0857] The server receives the API request sent from the device.

[0858] Step 6:

[0859] The server parses the contents of the request body and extracts the user data.

[0860] Step 7:

[0861] The server stores the extracted user data in a database.

[0862] Step 8:

[0863] The server inputs the stored user data into a machine learning model for analysis.

[0864] Step 9:

[0865] The machine learning model calculates the optimal aroma combination based on information such as "physical condition," "mood," "desired effect," and "preferred smell."

[0866] Step 10:

[0867] The server takes into account past feedback data and seasonal fluctuations to adjust the aroma blend.

[0868] Step 11:

[0869] The server will create the optimal aroma combination (e.g., 3 drops lavender, 2 drops mint, 2 drops bergamot).

[0870] Step 12:

[0871] The server creates a message to suggest the generated aroma blend to the user.

[0872] Step 13:

[0873] The server generates an API response to send this message to the device.

[0874] Step 14:

[0875] The device receives the API response from the server.

[0876] Step 15:

[0877] The terminal analyzes the received proposal message and displays it to the user.

[0878] Step 16:

[0879] The user checks the proposed aroma blend on the application screen.

[0880] Step 17:

[0881] The user tries out the suggested aroma and enters feedback on its effectiveness and satisfaction.

[0882] Step 18:

[0883] The device temporarily stores the feedback entered by the user in storage.

[0884] Step 19:

[0885] The device generates an API request to send the saved feedback data to the server.

[0886] Step 20:

[0887] The device sends the generated API request to the server.

[0888] Step 21:

[0889] The server receives the feedback data sent from the terminal.

[0890] Step 22:

[0891] The server analyzes the feedback data and adds it to the dataset of the machine learning model.

[0892] Step 23:

[0893] The server retrains the machine learning model to improve the accuracy of future suggestions.

[0894] Example 1

[0895] 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."

[0896] Conventional aromatherapy systems lack the functionality to suggest optimal aroma blends based on the user's physical condition and mood. In particular, it is difficult to make personalized suggestions that take into account each user's past usage history and feedback, and external factors such as seasonal variations tend to be ignored. Furthermore, systems often lack a mechanism for incorporating user feedback into future suggestions. This poses a challenge, preventing users from maximizing the benefits of aromatherapy.

[0897] 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.

[0898] In this invention, the server includes means for receiving information about the user's physical condition, mood, and preferred scents from the user, means for temporarily storing the received information and generating an API request to send to the server, means for the server to analyze the received user information and determine an aroma blend optimal for the user's condition using a machine learning model, means for the server to send the determined aroma blend information to the terminal as an API response and for the terminal to notify the user, means for receiving feedback from the user after using the aromas and generating an API request to send to the server, means for retraining the machine learning model based on the received feedback to improve subsequent aroma blend suggestions, means for correcting the aroma blend suggestions by referring to seasonal fluctuations and the user's past usage history, and means for the server to learn from the feedback data using the machine learning model and improve the accuracy of subsequent suggestions. This enables highly accurate and personalized suggestions of aroma blends optimal for the user's condition, maximizing the effects of aromatherapy.

[0899] "Physical condition" refers to the physical condition and health status of the user.

[0900] "Mood" refers to the user's emotional or mental state.

[0901] "Favorite scent" refers to the type of scent that the user particularly likes.

[0902] "Means for receiving information" refers to the method for obtaining data entered by the user from the application.

[0903] "Temporary storage" refers to the process of temporarily storing input information in a storage device.

[0904] "Means for generating API requests" refers to the method for creating the request format required to send data to the server.

[0905] "Server" means hardware or software for processing, analyzing, and storing data over a network.

[0906] "Machine learning model" refers to an algorithmic model used for data analysis and prediction.

[0907] "API response" refers to the response data sent from the server to the terminal.

[0908] "Means of notification" refers to the method by which the terminal presents information to the user.

[0909] "Feedback" refers to the impressions and evaluations provided by users after using an aroma.

[0910] "Retraining" refers to the process of retraining a machine learning model using new data received.

[0911] "Seasonal variation" refers to the pattern of the external environment that changes with the seasons.

[0912] "Usage history" refers to records of aroma compounds used by the user in the past and their effects.

[0913] "Corrective measures" refer to methods for fine-tuning proposals based on existing data and conditions.

[0914] "Suggestion accuracy" refers to the degree to which the optimum formulation for the user's condition can be accurately suggested.

[0915] "Terminal" refers to a device that allows a user to input or receive information.

[0916] The aromatherapist AI system of this invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, proposal notification, and feedback processing.

[0917] Hardware and software used

[0918] The implementation of this system uses the following hardware and software:

[0919] User devices: devices such as smartphones, tablets, and PCs

[0920] Application: A dedicated application that runs on the user's device

[0921] Server: Cloud or on-premise server

[0922] Database: A database system for storing user information and feedback data.

[0923] Machine learning models: Machine learning algorithms for analyzing and predicting aroma formulations

[0924] Natural language explanation of the process

[0925] User: Enter information

[0926] The user launches the application and logs in. After logging in, they input their physical condition, mood, desired effect (e.g., relaxation, concentration, refreshment), and favorite scent (e.g., lavender, mint). This input is done through the application's user interface.

[0927] Terminal: Sending information

[0928] The device stores the information entered by the user in temporary storage and generates an API request to send to the server, which is sent encrypted using HTTP.

[0929] Server: Data analysis

[0930] The server stores the received user information in a database. The stored data is then input into a machine learning model to determine the optimal aroma blend for the user's condition. This analysis also takes into account past usage history, seasonal patterns, and feedback data.

[0931] Server: Proposal Generation

[0932] The server generates the optimal aroma blend based on the analysis results. This proposal includes the specific type of aroma oil, the amount to be used, the blending method, and even the method of use. The generated proposal is sent to the device as an API response.

[0933] Device: Proposal Notification

[0934] The device uses the API response received from the server to notify the user of the proposed content. The notification is done using a visual interface and is displayed in a user-friendly format.

[0935] User:Feedback

[0936] Users try out the proposed aroma blends and enter feedback on their results and satisfaction, including perceived effects, satisfaction, and areas for improvement.

[0937] Terminal and Server: Feedback Processing

[0938] The device temporarily stores the feedback data, generates an API request to send it to the server, and sends it to the server. The server analyzes the received feedback data and inputs it into a machine learning model for retraining. This improves the accuracy of aroma blend suggestions from the next time onwards.

[0939] Specific examples

[0940] For example, User A uses the application to input "stress," states that he or she "wants to relax," and selects "lavender" and "mint" as his or her favorite scents. The device sends this information to the server, which then considers past feedback data and seasonal fluctuation patterns to suggest the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback that it was "very relaxing." This feedback is used in the next analysis, further improving the accuracy of the suggestions.

[0941] Examples of prompt statements

[0942] Enter the following prompt into the generative AI model:

[0943] "The user says they are stressed and want to relax. Their favorite aromas are lavender and mint. Please suggest the best aroma combination."

[0944] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0945] Step 1: Enter your user information

[0946] The user launches the dedicated application and logs in. After logging in, they enter their physical condition, mood, favorite scent, and desired effect on the application screen. For example, they might enter "I'm stressed," "I want to relax," or "I like lavender and mint." This input is done through the application's user interface (UI) and is saved in the device's temporary storage.

[0947] Step 2: Send data

[0948] The device temporarily stores the information entered by the user, then generates an API request to send it to the server. This API request includes encrypted user data. The generated API request is sent to the server via the Internet.

[0949] Step 3: Receiving and storing data on the server

[0950] The server receives API requests sent from the device and stores user information in a database. Specifically, it analyzes the data received as an HTTP request and stores it in the appropriate table in the database based on the specifications. This stored data includes the user's physical condition, mood, preferred scent, and desired effect.

[0951] Step 4: Data analysis

[0952] The server inputs the saved user information into a machine learning model and begins analysis. This machine learning model also references past usage history, seasonal fluctuation patterns, feedback data, etc. to determine the optimal aroma blend. For example, a suggestion such as "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" may be generated. The model performs data calculations based on the input data and outputs a suggestion for the optimal aroma blend.

[0953] Step 5: Proposal generation and submission

[0954] The server generates specific aroma blend suggestions for the user based on the analysis results obtained from the machine learning model. These suggestions include the type, amount, blending method, and usage of aroma oils to be used. The generated suggestions are sent to the device as an API response.

[0955] Step 6: Proposal Notification

[0956] The device notifies the user of the proposed aroma blend based on the API response received from the server. The result is displayed on the application screen in a visually easy-to-understand interface. The user can check the notification and try out the proposed aroma blend.

[0957] Step 7: Enter your feedback

[0958] Users try out the proposed aroma blends and enter feedback through the application about their effects and satisfaction, such as "It was very relaxing" or "I wish there was a bit more mint."

[0959] Step 8: Send your feedback

[0960] The device temporarily stores the feedback data received from the user and generates an API request to send to the server, which is also encrypted before being sent to the server.

[0961] Step 9: Feedback processing and model retraining

[0962] The server analyzes the received feedback data and stores it in a database. This feedback data is then input into the machine learning model for retraining. This allows the machine learning model to improve the accuracy of its aroma blending suggestions from the next time onwards.

[0963] Through these steps, the aromatherapist AI system can propose the aroma combination that is best suited to the user's condition and continuously improve the accuracy of its proposals based on feedback.

[0964] (Application example 1)

[0965] 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."

[0966] Conventional aromatherapy systems often fail to effectively suggest aroma blends based on the user's physical condition, mood, and preferred scents, making it difficult to provide individually optimized services. They also lack a means to effectively utilize user feedback to improve the accuracy of their next suggestions. Furthermore, suggestions are limited to simple notifications, which lacks user convenience and immediacy.

[0967] 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.

[0968] In this invention, the server includes means for receiving information on the user's physical condition, mood, and preferred scent from the user, means for transmitting the information received from the user to the server, means for the server to analyze the user information received and determine an aroma blend optimal for the user's condition, means for notifying the smart device of the aroma blend information determined by the server, means for receiving feedback from the user after using the aroma via the smart device and transmitting the feedback to the server, and means for improving subsequent aroma blend suggestions based on the received feedback. This not only makes it possible to suggest an aroma blend optimal for the user's condition, but also makes it possible to continuously improve the service based on the feedback and enhance the user experience.

[0969] "User information" is information collected from the user about their physical condition, mood, and favorite smell.

[0970] The "server" is a central processing unit that analyzes user information, determines the aroma blend that best suits the user's condition, and notifies the smart device of the results.

[0971] A "smart device" is an electronic device that can input user information, receive aroma blend information, and receive and send feedback, and includes smartphones and smart glasses.

[0972] An "aroma blend" is a combination of aroma oils optimized according to the user's physical condition, mood, and preferred scent.

[0973] "Feedback" refers to information about the evaluation, impressions, and satisfaction level submitted by a user after trying out the proposed aroma blend.

[0974] "Data analysis" is an information processing method for determining the optimal aroma blend using user information and feedback received by the server.

[0975] A "machine learning model" is an algorithm that learns from feedback data and improves the accuracy of aroma blend suggestions from the next time onwards.

[0976] The aromatherapist AI system of this invention utilizes smart devices to suggest optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, suggestion notification, and feedback processing.

[0977] User operations

[0978] First, the user puts on a smart device (such as a smartphone or smart glasses), launches a dedicated application, and logs in. On the application screen, the user enters their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and preferred scent (e.g., lavender, mint, etc.). This information is crucial for determining the aroma blend.

[0979] Data transmission

[0980] The information entered by the user regarding their physical condition, mood, and preferred scent is stored in temporary storage on the smart device, after which the smart device generates an API request to send this data to the server, encrypts it, and sends it to the server.

[0981] Data analysis

[0982] The server uses a machine learning model called a generative AI model to analyze the received user information. Data analysis takes into account not only the user's current condition, but also past feedback data and seasonal patterns, and determines the optimal aroma combination based on this. For example, a combination of lavender and bergamot may be recommended, as it is determined to be effective in relieving stress based on past data.

[0983] proposal notification

[0984] The determined aroma blend information is sent to the smart device as an API response. The smart device receives this information and notifies the user visually or audibly. The user can then check the proposed aroma blend on the application screen and view details such as the specific type of aroma oil, the amount to be used, the blending method, and how to use it.

[0985] Feedback Processing

[0986] The user tries out the proposed aroma blend and enters feedback on its effectiveness and satisfaction via their smart device. This feedback includes perceived effectiveness, satisfaction, and areas for improvement. The feedback data is temporarily stored on the smart device and then sent back to the server.

[0987] Continuous improvement

[0988] The server analyzes the received feedback data and inputs it into the generative AI model. This retrains the machine learning model, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[0989] Specific examples

[0990] For example, if a user inputs that they are "stressed" and desires to "relax," selecting "lavender" and "mint" as their favorite scents, this user information is sent to the server. The server uses a generative AI model to consider past feedback and seasonal fluctuation patterns, and suggests "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" as the optimal aroma blend. The user tries this and provides feedback that they found it "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of future suggestions.

[0991] Prompt Sentence Examples

[0992] "User feedback: 'Very relaxing'. Please use this feedback to re-learn the optimal aroma combination to improve the accuracy of our suggestions next time."

[0993] In this way, the system of the present invention can accurately suggest personalized aroma blends based on the user's physical condition and mood, improving the user experience.

[0994] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0995] Step 1: Enter user information

[0996] The user launches a dedicated application using a smart device (e.g., a smartphone or smart glasses) and logs in. On the application screen, the user enters their current physical condition (e.g., stressed), mood (e.g., wanting to relax), desired effect, and favorite scent (e.g., lavender, mint). This information is used in the next processing step.

[0997] Input: physical condition, mood, favorite smell

[0998] Output: User information data

[0999] Step 2: Send data

[1000] The device temporarily stores the information entered by the user in storage, then generates an API request to send the stored user information data to the server, encrypts the data, and sends it to the server.

[1001] Input: User information data

[1002] Output: API request to the server

[1003] Step 3: Data analysis

[1004] The server analyzes the received user information data using a generative AI model, which takes into account the user's current condition, past feedback data, and seasonal patterns to determine the optimal aroma blend.

[1005] Input: User information data, past feedback data, seasonal fluctuation patterns

[1006] Output: Optimal aroma blend data

[1007] Step 4: Proposal Notification

[1008] The server sends the determined optimal aroma blend data to the terminal as an API response, and the terminal notifies the user of the received aroma blend data via the smart device's display or voice notification.

[1009] Input: Optimal aroma blend data

[1010] Output: Aroma blending suggestions notified to the user

[1011] Step 5: Enter your feedback

[1012] The user tries out the proposed aroma blend and enters feedback on its effectiveness and satisfaction. This feedback data is then temporarily stored on the smart device.

[1013] Input: Impressions after use, satisfaction level

[1014] Output: User feedback data

[1015] Step 6: Send your feedback

[1016] The terminal generates an API request for transmitting the feedback data collected from the user to the server, and transmits the request to the server.

[1017] Input: User feedback data

[1018] Output: API request to the server

[1019] Step 7: Feedback analysis and model retraining

[1020] The server analyzes the received feedback data and reflects it in the generative AI model. This re-learning improves the accuracy of aroma blend suggestions from the next time onwards.

[1021] Input: User feedback data

[1022] Output: Updated machine learning model

[1023] Through these steps, the aromatherapist AI system of the present invention can provide optimal aroma blends that meet the individual needs of users and can continuously improve them based on feedback.

[1024] 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.

[1025] The aromatherapist AI system of the present invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. Furthermore, by combining it with an emotion engine, the system also recognizes the user's emotional state and proposes aroma blends based on that. This system consists of multiple processes: user input, emotion recognition data acquisition, data transmission, data analysis, proposal notification, and feedback processing.

[1026] User: Information entry process

[1027] First, the user launches the dedicated application and logs in. Then, on the application screen, the user inputs their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent (e.g., lavender, mint, etc.). The input information is crucial for determining the aroma composition.

[1028] User: Emotion recognition process

[1029] While the user is inputting, the device's built-in camera and microphone collect the user's voice and facial expression data. The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise, etc.). The emotional state data is sent to the server along with information on the user's physical condition and mood.

[1030] Terminal: Information transmission process

[1031] The information entered by the user regarding their physical condition, mood, and preferred scent, as well as the emotional state data recognized by the emotion engine, are stored in temporary storage on the device. The device then generates an API request to send this data to the server, which then sends it to the server. The transmitted data is encrypted to ensure privacy.

[1032] Server: Data analysis process

[1033] The server analyzes the received user information and uses a machine learning model to determine the optimal aroma blend for the user's current state. This analysis takes into account data such as physical condition, mood, and preferred scents, as well as emotional state data recognized by the emotion engine. For example, if the server recognizes that the user is feeling stressed, it will suggest aroma oils with a relaxing effect (e.g., lavender or bergamot).

[1034] Server: Proposal generation process

[1035] The server generates a proposal for the optimal aroma blend for the user based on the analysis results. This proposal includes details such as the specific aroma oil type, amount to use, blending method, and usage method. The proposal is sent to the device as an API response.

[1036] Terminal: Proposal Notification Process

[1037] The device receives the API response from the server and notifies the user of the proposed aroma blend. The user can then check the proposed aroma blend on the application screen. The notification uses a visual interface to make it easy for the user to understand.

[1038] User: Feedback input process

[1039] Users try out the proposed aroma blends and enter their feedback through the application about their experience and satisfaction, including perceived effects, satisfaction, and possible improvements.

[1040] Terminal: Feedback sending process

[1041] The feedback data sent by the user is temporarily stored on the device, and an API request is generated to send it to the server. The device then sends the generated API request to the server.

[1042] Server: Feedback processing process

[1043] The server analyzes the received feedback data and inputs it into a machine learning model. The machine learning model is retrained based on this feedback data, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[1044] Specific examples

[1045] User A uses the application to input that he is "stressed," and further states that he "wants to relax," selecting "lavender" and "mint" as his favorite scents. The device collects this information along with the user's facial expressions and voice data, and uses an emotion engine to recognize "irritation." The device then sends this data set to the server. Taking into account past feedback and seasonal fluctuation patterns, the server suggests the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback, rating it as "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of future suggestions.

[1046] By combining this with an emotion engine, it will be possible to propose sophisticated aroma blends that take into account even the subtlest emotional changes of the user, which is expected to maximize the effects of aromatherapy.

[1047] The processing flow will be explained below.

[1048] Step 1:

[1049] The user launches the application and logs in. The user enters information about their physical condition, mood, desired effect (e.g., relaxation, concentration), and preferred scent (e.g., lavender, mint).

[1050] Step 2:

[1051] The device's built-in camera and microphone collect the user's voice and facial expression data.

[1052] Step 3:

[1053] The device transmits the collected voice and facial expression data to the emotion engine in real time.

[1054] Step 4:

[1055] The emotion engine analyzes the user's voice tone, facial expression changes, and language patterns to recognize the user's emotional state (e.g., joy, sadness, anger, surprise).

[1056] Step 5:

[1057] The device temporarily stores information entered by the user regarding physical condition, mood, and preferred scent, as well as emotional state data recognized by the emotion engine.

[1058] Step 6:

[1059] The device generates an API request to send the stored user information and emotional state data to the server.

[1060] Step 7:

[1061] The device sends the generated API request to the server.

[1062] Step 8:

[1063] The server receives the API request sent from the device.

[1064] Step 9:

[1065] The server parses the contents of the request body and extracts user data and emotional state data.

[1066] Step 10:

[1067] The server stores the extracted user data and emotional state data in a database.

[1068] Step 11:

[1069] The server inputs the stored user data and emotional state data into a machine learning model for analysis.

[1070] Step 12:

[1071] The machine learning model calculates the optimal aroma combination based on information such as "physical condition," "mood," "desired effect," "preferred smell," and "emotional state."

[1072] Step 13:

[1073] The server takes into account past feedback data and seasonal fluctuations to adjust the aroma blend.

[1074] Step 14:

[1075] The server will create the optimal aroma combination (e.g., 3 drops lavender, 2 drops mint, 2 drops bergamot).

[1076] Step 15:

[1077] The server creates a message to suggest the generated aroma blend to the user.

[1078] Step 16:

[1079] The server generates an API response to send this message to the device.

[1080] Step 17:

[1081] The device receives the API response from the server.

[1082] Step 18:

[1083] The terminal analyzes the received proposal message and notifies the user.

[1084] Step 19:

[1085] The user checks the proposed aroma blend on the application screen.

[1086] Step 20:

[1087] The user tries out the suggested aroma and enters feedback on its effectiveness and satisfaction.

[1088] Step 21:

[1089] The device temporarily stores the feedback entered by the user in storage.

[1090] Step 22:

[1091] The device generates an API request to send the saved feedback data to the server.

[1092] Step 23:

[1093] The device sends the generated API request to the server.

[1094] Step 24:

[1095] The server receives the feedback data sent from the terminal.

[1096] Step 25:

[1097] The server analyzes the feedback data and adds it to the dataset of the machine learning model.

[1098] Step 26:

[1099] The server retrains the machine learning model to improve the accuracy of future suggestions.

[1100] Example 2

[1101] 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."

[1102] Conventional aromatherapy systems only suggest aroma blends based on the user's physical condition and mood, but do not take into account the user's emotional state. This makes it difficult to suggest personalized aroma blends that respond to subtle changes in the user's emotions. Furthermore, the accuracy of suggestions based on feedback has not been sufficiently improved.

[1103] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1104] In this invention, the server includes means for receiving information about the user's physical condition, mood, and preferred scent from the user, means for collecting the user's voice and facial expression data using a camera and microphone while the user is inputting the information, means for analyzing the collected emotional state data, means for transmitting the information received from the user and the emotional state data to the server, means for the server to analyze the received user information and emotional state data and determine an aroma blend optimal for the user's condition, means for notifying the user of the aroma blend information determined by the server, means for receiving feedback from the user after using the aromas and transmitting it to the server, means for improving subsequent aroma blend suggestions based on the received feedback, means for recognizing the user's emotional changes using an emotion engine and reflecting them in aroma blend suggestions, and means for learning the user's feedback using a machine learning model to improve the accuracy of subsequent suggestions. This enables advanced personalization that takes into account not only the user's physical condition and mood but also their emotional state, thereby maximizing the effects of aromatherapy.

[1105] "Physical condition" refers to the user's physical health condition and current physical condition.

[1106] "Mood" refers to the user's psychological and emotional state, or how they feel at a given moment.

[1107] "Favorite scent" refers to the aroma or type of scent that the user particularly likes.

[1108] "Camera" refers to a video input device for capturing the user's facial expression.

[1109] "Microphone" refers to an audio input device for capturing a user's voice.

[1110] "Voice data" refers to audio information obtained from a user's voice and speaking style.

[1111] "Facial expression data" refers to visual information obtained from the user's facial expressions.

[1112] An "emotion engine" refers to software or hardware that analyzes collected voice and facial expression data and recognizes the user's emotional state.

[1113] "Emotional state" refers to the emotions the user is feeling at that time, such as joy, sadness, anger, surprise, etc.

[1114] "Analysis" refers to the act of processing received and collected data to derive a specific conclusion or result.

[1115] "Server" refers to a central processing unit that receives and analyzes data sent by users.

[1116] "Aroma blend" refers to the types and proportions of aromatic oils blended to bring out a specific effect.

[1117] "Notification" refers to the act of sending information to inform users of the proposed content and analysis results.

[1118] "Feedback" refers to the act of a user providing the results and impressions of a proposed aroma blend after trying it out.

[1119] A "machine learning model" refers to an algorithm or system that learns from data and improves the accuracy of future suggestions and predictions.

[1120] "Personalization" refers to the act of customizing offers and services to suit the individual preferences and circumstances of each user.

[1121] "Encryption" refers to the technology of converting data so that it cannot be read by third parties.

[1122] The aromatherapist AI system of the present invention is a system that proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. Furthermore, it utilizes an emotion engine to take the user's emotional state into consideration. Specific embodiments are described below.

[1123] Users use a device such as a smartphone or tablet to launch a dedicated application and log in. After logging in, users enter their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and preferred scent on the application screen. This input information is important for determining the aroma blend.

[1124] While the user is typing, the device's built-in camera and microphone collect the user's voice and facial expression data. This data is analyzed in real time by an emotion engine to recognize the user's emotional state. Examples of emotion engines include Microsoft Azure Cognitive Services and IBM Watson.

[1125] The collected data on physical condition, mood, preferred odor, and emotional state is stored in temporary storage on the device, after which the device generates an API request to send this data to the server, where it is encrypted and sent.

[1126] The server analyzes the data received from the device and uses a machine learning model to determine the optimal aroma combination for the user's current state. This analysis process takes into account the user's physical condition, mood, preferred scents, and emotional state data. Examples of machine learning models include TensorFlow and PyTorch.

[1127] The server then uses the analysis results to propose the optimal aroma blend for the user. This proposal includes the specific type of aroma oil, the amount to use, the blending method, and how to use it. The proposal is sent to the device as an API response.

[1128] The device receives the API response from the server and notifies the user of the proposed content. The notification is sent via the application screen and displayed in a visually easy-to-understand format.

[1129] Users try out the proposed aroma blends and enter their feedback through the application about their perceived effects and satisfaction, as well as areas for improvement.

[1130] The device temporarily stores the feedback data and generates an API request to send it to the server, where it is encrypted and sent.

[1131] The server analyzes the received feedback data and inputs it into a machine learning model, which then retrains the model based on the feedback data, improving the accuracy of future suggestions.

[1132] As a concrete example, user A uses an application, inputs that he is "stressed," and selects his favorite scents as "lavender" and "mint," saying that he "wants to relax." When the device collects this information, it also analyzes the user's facial expressions and voice data using an emotion engine to recognize "irritation." The server considers past feedback and seasonal fluctuation patterns and suggests "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" as the optimal aroma blend. User A tries this blend and sends feedback that it was "very relaxing." This feedback is reflected in future suggestions.

[1133] Example prompts to input to the generative AI model:

[1134] "Suggest the best aroma combination based on your current physical condition, mood, preferred smell, and emotional state. Example: Use lavender, bergamot, and mint."

[1135] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1136] Step 1:

[1137] The user launches a dedicated application and logs in. After logging in, they enter their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent into the input form displayed on the application screen. This generates data on physical condition, mood, desired effect, and favorite scent. Examples of input data include "Physical condition: tired," "Mood: stressed," "Desired effect: relaxation," and "Favorite scent: lavender, mint."

[1138] Step 2:

[1139] While the user is entering information, the device's built-in camera and microphone collect the user's voice and facial expression data. The collected voice and facial expression data is sent to an emotion engine, which recognizes the user's emotional state as "happiness," "sadness," "irritation," etc. Specifically, the camera captures the user's facial expressions while the user is entering information, and the microphone records the voice. This data is analyzed in real time by the emotion engine, and "irritation" is output as emotional state data.

[1140] Step 3:

[1141] The device temporarily stores data entered by the user regarding their physical condition, mood, and favorite scent, as well as the emotional state data recognized by the emotion engine. It then generates an API request to send this data to the server. Specifically, it generates a data packet containing "Physical condition: tired," "Mood: stressed," "Favorite scent: lavender, mint," and "Emotional state: irritated," encrypts it, and sends it to the server.

[1142] Step 4:

[1143] The server receives the data sent from the device. The received data is stored in a database and input into a machine learning model for analysis. Specific examples of data processing include integrating data on physical condition, mood, preferred scent, and emotional state and converting it into a format suitable for analysis.

[1144] Step 5:

[1145] The server uses machine learning models to determine the optimal aroma blend for the user's current state. Based on the analysis results, a specific aroma blend, such as "3 drops lavender, 2 drops mint, and 2 drops bergamot," is determined. This output is best suited to the user's physical condition, mood, and emotional state.

[1146] Step 6:

[1147] The server sends the determined aroma blend information to the terminal as an API response. The response includes details such as the specific aroma oil type, amount to be used, blending method, and usage instructions. For example, it suggests mixing "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" and using it once every night.

[1148] Step 7:

[1149] The device receives the API response from the server and notifies the user of its contents. The notification is displayed visually on the application screen and is designed to be easy for the user to understand. For example, the application screen displays an icon of an aroma oil bottle along with detailed instructions on how to use it.

[1150] Step 8:

[1151] The user tries out the proposed aroma blend and enters feedback through the application about its effectiveness and satisfaction. The feedback includes perceived effectiveness, satisfaction, and areas for improvement. Specifically, the user enters the comment, "It was very relaxing."

[1152] Step 9:

[1153] The device temporarily stores the feedback data entered by the user and generates an API request to send to the server. The generated request is encrypted and sent to the server. For example, the request may contain feedback data such as "very relaxing" or "no improvement needed."

[1154] Step 10:

[1155] The server analyzes the received feedback data and inputs it into a machine learning model. This allows the model to be retrained based on the feedback data, improving the accuracy of future aroma blend suggestions. Specifically, feedback such as "I felt very relaxed" will be reflected in the next suggestion, enabling more personalized suggestions.

[1156] (Application example 2)

[1157] 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."

[1158] In modern self-driving vehicles, there is a lack of relaxation methods that correspond to the physical condition and mood of the driver and passengers during long driving sessions, which causes stress and fatigue to accumulate.In addition, there is no system that can recognize the emotional state of each user in real time and respond appropriately, which makes it difficult to provide personalized relaxation effects.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice and facial expression data via a camera and microphone to recognize the user's emotional state, means for transmitting information and emotional data received from the user to the server, and means for analyzing the user information and emotional state data received by the server and determining the optimal aroma blend for the user's condition. This makes it possible to provide optimal aromatherapy based on the user's real-time physical condition and emotional state, thereby reducing stress and fatigue in an autonomous vehicle.

[1160] The "means for receiving information about the user's physical condition, mood, and favorite smell" is a device or application that provides an interface through which the user can input information about their physical condition, mood, and favorite smell.

[1161] "Means for collecting voice and facial expression data via a camera or microphone to recognize the emotional state of a user" refers to a device that acquires data using a camera or microphone to detect the emotional state of a user from their voice or facial expression.

[1162] The "means for transmitting information and emotional data received from the user to the server" refers to a device or application with a communication function for transferring the user's input information and collected emotional data to the server.

[1163] The "means for analyzing the user information and emotional state data received by the server and determining the optimal aroma blend for the user's state" refers to a server equipped with an algorithm or machine learning model that analyzes the received information and emotional data and determines the optimal aroma type and blend based on that.

[1164] The "means for notifying the user of the aroma blend information determined by the server" refers to a device or application that has a display function or notification function for informing the user of the results of the aroma blend.

[1165] "Means for receiving feedback from users after using an aroma and transmitting it to a server" refers to a device or application with an interface and communication functions that allows users to input their impressions and effects after using an aroma and transmit that data to a server.

[1166] The "means for improving subsequent aroma blend suggestions based on received feedback" is a server that analyzes user feedback and retrains the machine learning model to improve the accuracy of subsequent aroma blend suggestions.

[1167] The "means for correcting aroma blend suggestions by referring to seasonal fluctuations and the user's past usage history" refers to a server equipped with an algorithm that adjusts aroma blend suggestions by taking into account seasonal fluctuations in demand for fragrances and the user's past feedback data.

[1168] "Means for the server to learn feedback data using a machine learning model and improve the accuracy of future suggestions" refers to a mechanism that uses a machine learning model to learn feedback data from users and improves the accuracy of future aroma suggestions based on the results.

[1169] The aromatherapist system of this invention is realized by an application that operates in conjunction with a smartphone or head-mounted display installed in an autonomous vehicle. This system collects and analyzes the user's physical condition, mood, preferred scents, and emotional state in real time, and based on that data, sprays the optimal aroma inside the vehicle.

[1170] Hardware and software used

[1171] Smartphones and head-mounted displays: Interface for application operation and user input.

[1172] Camera and microphone: Devices for collecting voice and facial expression data.

[1173] Server: Back-end infrastructure for analyzing data and making aroma formulation decisions.

[1174] Specific features

[1175] 1. User Input and Emotion Recognition:

[1176] Users can input their physical condition, mood, and preferred scent using a smartphone or head-mounted display, and the system collects voice and facial expression data in real time through a camera and microphone, and identifies the user's emotional state through an emotion recognition engine.

[1177] 2. Data transmission:

[1178] The information entered by the user and the collected emotional data are temporarily stored on the device and then sent to the server as an API request. The data is encrypted and transmitted in a privacy-protected manner.

[1179] 3. Data analysis and aroma formulation determination:

[1180] The server analyzes the received user information and emotional state data and determines the optimal aroma blend based on that information, using machine learning models that take into account the user's past usage history and seasonal variations.

[1181] 4. Proposal Notice and Aroma Dispersal:

[1182] The aroma blend information determined by the server is then written back to the terminal and notified to the user. The user can confirm the proposed aroma blend and issue a command to spray it inside the car.

[1183] 5. Gathering Feedback and Improving:

[1184] Users try out aroma blends and provide feedback through a dedicated interface, which is then sent to a server to retrain the machine learning model to improve future aroma blend suggestions.

[1185] Specific prompt examples

[1186] Prompt Sentence Examples

[1187] "User's physical condition: tired, mood: stressed, favorite smells: lemon, peppermint. Suggest the best aroma combination based on emotional state: irritated."

[1188] As described above, this system reduces stress and fatigue in the car, providing a comfortable driving experience.

[1189] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1190] Step 1:

[1191] The user inputs their physical condition, mood, and preferred scent using a smartphone or head-mounted display, which then inputs information about the user's condition into the application. The input data is temporarily stored in the device's memory for the next processing step.

[1192] Step 2:

[1193] The user's voice and facial expression data are collected through a camera and microphone. The camera and microphone capture the user's face and voice in real time, and the acquired data is input into an emotion recognition engine. The emotion recognition engine analyzes this data and identifies the user's emotional state (e.g., joy, sadness, irritation, etc.). This analyzed data is also stored in the device's memory.

[1194] Step 3:

[1195] The device temporarily stores the information and emotional data input by the user in storage. Based on this data, it generates an API request and sends it to the server in an encrypted form. This API request includes data on the user's physical condition, mood, preferred scent, and emotional state.

[1196] Step 4:

[1197] The server analyzes the received user information and emotional state data. A machine learning model is used to determine the optimal aroma blend based on the user's current state. The machine learning model is based on a pre-trained dataset and takes into account past usage history and seasonal fluctuations.

[1198] Step 5:

[1199] The server generates aroma blend information based on the analysis results. This information includes details such as the specific aroma oil type, amount to be used, blending method, and usage method. The generated aroma blend information is sent to the device as an API response.

[1200] Step 6:

[1201] The device receives the API response from the server and notifies the user of the suggested aroma blend. The notification is made through a visual interface, allowing the user to confirm the recommended aroma blend. After confirming, the user can spray the aroma into the car through the aroma diffuser.

[1202] Step 7:

[1203] After using the aroma, users enter feedback about its effects and satisfaction through the application. This feedback data is temporarily stored on the device again, and an API request is generated to send it to the server. The feedback data sent to the server through the API request will be used to improve the accuracy of future suggestions.

[1204] Step 8:

[1205] The server analyzes the received feedback data and inputs it into a machine learning model. This analysis retrains the machine learning model, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[1206] 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.

[1207] 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.

[1208] 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.

[1209] [Fourth embodiment]

[1210] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1211] 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.

[1212] 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).

[1213] 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.

[1214] 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.

[1215] 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).

[1216] 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.

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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."

[1223] The aromatherapist AI system of this invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, proposal notification, and feedback processing.

[1224] User: Information entry process

[1225] First, the user launches the dedicated application and logs in. Then, on the application screen, the user inputs their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent (e.g., lavender, mint, etc.). This information is collected through the application. This input information is extremely important for determining the aroma blend.

[1226] Terminal: Information transmission process

[1227] The information entered by the user about their physical condition, mood, and preferred scents is stored in temporary storage on the device. The device then generates an API request to send this data to the server, which then sends it. The transmitted data is encrypted to protect privacy.

[1228] Server: Data analysis process

[1229] The server analyzes the received user information. Using a machine learning model, the server determines the optimal aroma combination for the user's current condition. This analysis takes into account not only the user's current physical condition, mood, and preferred scents, but also past feedback data and seasonal patterns. For example, if lavender and bergamot are deemed suitable for a user who needs stress relief, this combination will be suggested.

[1230] Server: Proposal generation process

[1231] The server generates a proposal for the optimal aroma blend for the user based on the analysis results. This proposal includes details such as the specific aroma oil type, amount to use, blending method, and usage method. The proposal is sent to the device as an API response.

[1232] Terminal: Proposal Notification Process

[1233] The device receives the API response from the server and notifies the user of the proposed aroma blend. The user can then check the proposed aroma blend on the application screen. The notification uses a visual interface to make it easy for the user to understand.

[1234] User: Feedback input process

[1235] Users try out the proposed aroma blends and enter their feedback through the application about their experience and satisfaction, including perceived effects, satisfaction, and possible improvements.

[1236] Terminal: Feedback sending process

[1237] The feedback data sent by the user is temporarily stored on the device, and an API request is generated to send it to the server. The device then sends the generated API request to the server.

[1238] Server: Feedback processing process

[1239] The server analyzes the received feedback data and inputs it into a machine learning model. The machine learning model is retrained based on this feedback data, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[1240] Specific examples

[1241] User A uses the application to input that he is "stressed," and further states that he "wants to relax," selecting "lavender" and "mint" as his favorite scents. The device sends this information to the server, which then takes into account past feedback and seasonal fluctuation patterns and suggests the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback, rating it as "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of suggestions from next time onwards.

[1242] In this way, this system utilizes artificial intelligence and machine learning to accurately suggest the optimal aroma blend for the user's condition, thereby maximizing the effects of aromatherapy.

[1243] The processing flow will be explained below.

[1244] Step 1:

[1245] The user launches the application and logs in. The user enters information about their physical condition, mood, desired effect (e.g., relaxation, concentration), and preferred scent (e.g., lavender, mint).

[1246] Step 2:

[1247] The device temporarily stores the information entered by the user in storage.

[1248] Step 3:

[1249] The device generates an API request to send the saved user information to the server.

[1250] Step 4:

[1251] The device sends the generated API request to the server.

[1252] Step 5:

[1253] The server receives the API request sent from the device.

[1254] Step 6:

[1255] The server parses the contents of the request body and extracts the user data.

[1256] Step 7:

[1257] The server stores the extracted user data in a database.

[1258] Step 8:

[1259] The server inputs the stored user data into a machine learning model for analysis.

[1260] Step 9:

[1261] The machine learning model calculates the optimal aroma combination based on information such as "physical condition," "mood," "desired effect," and "preferred smell."

[1262] Step 10:

[1263] The server takes into account past feedback data and seasonal fluctuations to adjust the aroma blend.

[1264] Step 11:

[1265] The server will create the optimal aroma combination (e.g., 3 drops lavender, 2 drops mint, 2 drops bergamot).

[1266] Step 12:

[1267] The server creates a message to suggest the generated aroma blend to the user.

[1268] Step 13:

[1269] The server generates an API response to send this message to the device.

[1270] Step 14:

[1271] The device receives the API response from the server.

[1272] Step 15:

[1273] The terminal analyzes the received proposal message and displays it to the user.

[1274] Step 16:

[1275] The user checks the proposed aroma blend on the application screen.

[1276] Step 17:

[1277] The user tries out the suggested aroma and enters feedback on its effectiveness and satisfaction.

[1278] Step 18:

[1279] The device temporarily stores the feedback entered by the user in storage.

[1280] Step 19:

[1281] The device generates an API request to send the saved feedback data to the server.

[1282] Step 20:

[1283] The device sends the generated API request to the server.

[1284] Step 21:

[1285] The server receives the feedback data sent from the terminal.

[1286] Step 22:

[1287] The server analyzes the feedback data and adds it to the dataset of the machine learning model.

[1288] Step 23:

[1289] The server retrains the machine learning model to improve the accuracy of future suggestions.

[1290] Example 1

[1291] 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."

[1292] Conventional aromatherapy systems lack the functionality to suggest optimal aroma blends based on the user's physical condition and mood. In particular, it is difficult to make personalized suggestions that take into account each user's past usage history and feedback, and external factors such as seasonal variations tend to be ignored. Furthermore, systems often lack a mechanism for incorporating user feedback into future suggestions. This poses a challenge, preventing users from maximizing the benefits of aromatherapy.

[1293] 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.

[1294] In this invention, the server includes means for receiving information about the user's physical condition, mood, and preferred scents from the user, means for temporarily storing the received information and generating an API request to send to the server, means for the server to analyze the received user information and determine an aroma blend optimal for the user's condition using a machine learning model, means for the server to send the determined aroma blend information to the terminal as an API response and for the terminal to notify the user, means for receiving feedback from the user after using the aromas and generating an API request to send to the server, means for retraining the machine learning model based on the received feedback to improve subsequent aroma blend suggestions, means for correcting the aroma blend suggestions by referring to seasonal fluctuations and the user's past usage history, and means for the server to learn from the feedback data using the machine learning model and improve the accuracy of subsequent suggestions. This enables highly accurate and personalized suggestions of aroma blends optimal for the user's condition, maximizing the effects of aromatherapy.

[1295] "Physical condition" refers to the physical condition and health status of the user.

[1296] "Mood" refers to the user's emotional or mental state.

[1297] "Favorite scent" refers to the type of scent that the user particularly likes.

[1298] "Means for receiving information" refers to the method for obtaining data entered by the user from the application.

[1299] "Temporary storage" refers to the process of temporarily storing input information in a storage device.

[1300] "Means for generating API requests" refers to the method for creating the request format required to send data to the server.

[1301] "Server" means hardware or software for processing, analyzing, and storing data over a network.

[1302] "Machine learning model" refers to an algorithmic model used for data analysis and prediction.

[1303] "API response" refers to the response data sent from the server to the terminal.

[1304] "Means of notification" refers to the method by which the terminal presents information to the user.

[1305] "Feedback" refers to the impressions and evaluations provided by users after using an aroma.

[1306] "Retraining" refers to the process of retraining a machine learning model using new data received.

[1307] "Seasonal variation" refers to the pattern of the external environment that changes with the seasons.

[1308] "Usage history" refers to records of aroma compounds used by the user in the past and their effects.

[1309] "Corrective measures" refer to methods for fine-tuning proposals based on existing data and conditions.

[1310] "Suggestion accuracy" refers to the degree to which the optimum formulation for the user's condition can be accurately suggested.

[1311] "Terminal" refers to a device that allows a user to input or receive information.

[1312] The aromatherapist AI system of this invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, proposal notification, and feedback processing.

[1313] Hardware and software used

[1314] The implementation of this system uses the following hardware and software:

[1315] User devices: devices such as smartphones, tablets, and PCs

[1316] Application: A dedicated application that runs on the user's device

[1317] Server: Cloud or on-premise server

[1318] Database: A database system for storing user information and feedback data.

[1319] Machine learning models: Machine learning algorithms for analyzing and predicting aroma formulations

[1320] Natural language explanation of the process

[1321] User: Enter information

[1322] The user launches the application and logs in. After logging in, they input their physical condition, mood, desired effect (e.g., relaxation, concentration, refreshment), and favorite scent (e.g., lavender, mint). This input is done through the application's user interface.

[1323] Terminal: Sending information

[1324] The device stores the information entered by the user in temporary storage and generates an API request to send to the server, which is sent encrypted using HTTP.

[1325] Server: Data analysis

[1326] The server stores the received user information in a database. The stored data is then input into a machine learning model to determine the optimal aroma blend for the user's condition. This analysis also takes into account past usage history, seasonal patterns, and feedback data.

[1327] Server: Proposal Generation

[1328] The server generates the optimal aroma blend based on the analysis results. This proposal includes the specific type of aroma oil, the amount to be used, the blending method, and even the method of use. The generated proposal is sent to the device as an API response.

[1329] Device: Proposal Notification

[1330] The device uses the API response received from the server to notify the user of the proposed content. The notification is done using a visual interface and is displayed in a user-friendly format.

[1331] User:Feedback

[1332] Users try out the proposed aroma blends and enter feedback on their results and satisfaction, including perceived effects, satisfaction, and areas for improvement.

[1333] Terminal and Server: Feedback Processing

[1334] The device temporarily stores the feedback data, generates an API request to send it to the server, and sends it to the server. The server analyzes the received feedback data and inputs it into a machine learning model for retraining. This improves the accuracy of aroma blend suggestions from the next time onwards.

[1335] Specific examples

[1336] For example, User A uses the application to input "stress," states that he or she "wants to relax," and selects "lavender" and "mint" as his or her favorite scents. The device sends this information to the server, which then considers past feedback data and seasonal fluctuation patterns to suggest the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback that it was "very relaxing." This feedback is used in the next analysis, further improving the accuracy of the suggestions.

[1337] Examples of prompt statements

[1338] Enter the following prompt into the generative AI model:

[1339] "The user says they are stressed and want to relax. Their favorite aromas are lavender and mint. Please suggest the best aroma combination."

[1340] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1341] Step 1: Enter your user information

[1342] The user launches the dedicated application and logs in. After logging in, they enter their physical condition, mood, favorite scent, and desired effect on the application screen. For example, they might enter "I'm stressed," "I want to relax," or "I like lavender and mint." This input is done through the application's user interface (UI) and is saved in the device's temporary storage.

[1343] Step 2: Send data

[1344] The device temporarily stores the information entered by the user, then generates an API request to send it to the server. This API request includes encrypted user data. The generated API request is sent to the server via the Internet.

[1345] Step 3: Receiving and storing data on the server

[1346] The server receives API requests sent from the device and stores user information in a database. Specifically, it analyzes the data received as an HTTP request and stores it in the appropriate table in the database based on the specifications. This stored data includes the user's physical condition, mood, preferred scent, and desired effect.

[1347] Step 4: Data analysis

[1348] The server inputs the saved user information into a machine learning model and begins analysis. This machine learning model also references past usage history, seasonal fluctuation patterns, feedback data, etc. to determine the optimal aroma blend. For example, a suggestion such as "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" may be generated. The model performs data calculations based on the input data and outputs a suggestion for the optimal aroma blend.

[1349] Step 5: Proposal generation and submission

[1350] The server generates specific aroma blend suggestions for the user based on the analysis results obtained from the machine learning model. These suggestions include the type, amount, blending method, and usage of aroma oils to be used. The generated suggestions are sent to the device as an API response.

[1351] Step 6: Proposal Notification

[1352] The device notifies the user of the proposed aroma blend based on the API response received from the server. The result is displayed on the application screen in a visually easy-to-understand interface. The user can check the notification and try out the proposed aroma blend.

[1353] Step 7: Enter your feedback

[1354] Users try out the proposed aroma blends and enter feedback through the application about their effects and satisfaction, such as "It was very relaxing" or "I wish there was a bit more mint."

[1355] Step 8: Send your feedback

[1356] The device temporarily stores the feedback data received from the user and generates an API request to send to the server, which is also encrypted before being sent to the server.

[1357] Step 9: Feedback processing and model retraining

[1358] The server analyzes the received feedback data and stores it in a database. This feedback data is then input into the machine learning model for retraining. This allows the machine learning model to improve the accuracy of its aroma blending suggestions from the next time onwards.

[1359] Through these steps, the aromatherapist AI system can propose the aroma combination that is best suited to the user's condition and continuously improve the accuracy of its proposals based on feedback.

[1360] (Application example 1)

[1361] 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."

[1362] Conventional aromatherapy systems often fail to effectively suggest aroma blends based on the user's physical condition, mood, and preferred scents, making it difficult to provide individually optimized services. They also lack a means to effectively utilize user feedback to improve the accuracy of their next suggestions. Furthermore, suggestions are limited to simple notifications, which lacks user convenience and immediacy.

[1363] 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.

[1364] In this invention, the server includes means for receiving information on the user's physical condition, mood, and preferred scent from the user, means for transmitting the information received from the user to the server, means for the server to analyze the user information received and determine an aroma blend optimal for the user's condition, means for notifying the smart device of the aroma blend information determined by the server, means for receiving feedback from the user after using the aroma via the smart device and transmitting the feedback to the server, and means for improving subsequent aroma blend suggestions based on the received feedback. This not only makes it possible to suggest an aroma blend optimal for the user's condition, but also makes it possible to continuously improve the service based on the feedback and enhance the user experience.

[1365] "User information" is information collected from the user about their physical condition, mood, and favorite smell.

[1366] The "server" is a central processing unit that analyzes user information, determines the aroma blend that best suits the user's condition, and notifies the smart device of the results.

[1367] A "smart device" is an electronic device that can input user information, receive aroma blend information, and receive and send feedback, and includes smartphones and smart glasses.

[1368] An "aroma blend" is a combination of aroma oils optimized according to the user's physical condition, mood, and preferred scent.

[1369] "Feedback" refers to information about the evaluation, impressions, and satisfaction level submitted by a user after trying out the proposed aroma blend.

[1370] "Data analysis" is an information processing method for determining the optimal aroma blend using user information and feedback received by the server.

[1371] A "machine learning model" is an algorithm that learns from feedback data and improves the accuracy of aroma blend suggestions from the next time onwards.

[1372] The aromatherapist AI system of this invention utilizes smart devices to suggest optimal aroma blends based on the user's physical condition, mood, and preferred scents. This system consists of multiple processes: user input, data transmission, data analysis, suggestion notification, and feedback processing.

[1373] User operations

[1374] First, the user puts on a smart device (such as a smartphone or smart glasses), launches a dedicated application, and logs in. On the application screen, the user enters their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and preferred scent (e.g., lavender, mint, etc.). This information is crucial for determining the aroma blend.

[1375] Data transmission

[1376] The information entered by the user regarding their physical condition, mood, and preferred scent is stored in temporary storage on the smart device, after which the smart device generates an API request to send this data to the server, encrypts it, and sends it to the server.

[1377] Data analysis

[1378] The server uses a machine learning model called a generative AI model to analyze the received user information. Data analysis takes into account not only the user's current condition, but also past feedback data and seasonal patterns, and determines the optimal aroma combination based on this. For example, a combination of lavender and bergamot may be recommended, as it is determined to be effective in relieving stress based on past data.

[1379] proposal notification

[1380] The determined aroma blend information is sent to the smart device as an API response. The smart device receives this information and notifies the user visually or audibly. The user can then check the proposed aroma blend on the application screen and view details such as the specific type of aroma oil, the amount to be used, the blending method, and how to use it.

[1381] Feedback Processing

[1382] The user tries out the proposed aroma blend and enters feedback on its effectiveness and satisfaction via their smart device. This feedback includes perceived effectiveness, satisfaction, and areas for improvement. The feedback data is temporarily stored on the smart device and then sent back to the server.

[1383] Continuous improvement

[1384] The server analyzes the received feedback data and inputs it into the generative AI model. This retrains the machine learning model, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[1385] Specific examples

[1386] For example, if a user inputs that they are "stressed" and desires to "relax," selecting "lavender" and "mint" as their favorite scents, this user information is sent to the server. The server uses a generative AI model to consider past feedback and seasonal fluctuation patterns, and suggests "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" as the optimal aroma blend. The user tries this and provides feedback that they found it "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of future suggestions.

[1387] Prompt Sentence Examples

[1388] "User feedback: 'Very relaxing'. Please use this feedback to re-learn the optimal aroma combination to improve the accuracy of our suggestions next time."

[1389] In this way, the system of the present invention can accurately suggest personalized aroma blends based on the user's physical condition and mood, improving the user experience.

[1390] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1391] Step 1: Enter user information

[1392] The user launches a dedicated application using a smart device (e.g., a smartphone or smart glasses) and logs in. On the application screen, the user enters their current physical condition (e.g., stressed), mood (e.g., wanting to relax), desired effect, and favorite scent (e.g., lavender, mint). This information is used in the next processing step.

[1393] Input: physical condition, mood, favorite smell

[1394] Output: User information data

[1395] Step 2: Send data

[1396] The device temporarily stores the information entered by the user in storage, then generates an API request to send the stored user information data to the server, encrypts the data, and sends it to the server.

[1397] Input: User information data

[1398] Output: API request to the server

[1399] Step 3: Data analysis

[1400] The server analyzes the received user information data using a generative AI model, which takes into account the user's current condition, past feedback data, and seasonal patterns to determine the optimal aroma blend.

[1401] Input: User information data, past feedback data, seasonal fluctuation patterns

[1402] Output: Optimal aroma blend data

[1403] Step 4: Proposal Notification

[1404] The server sends the determined optimal aroma blend data to the terminal as an API response, and the terminal notifies the user of the received aroma blend data via the smart device's display or voice notification.

[1405] Input: Optimal aroma blend data

[1406] Output: Aroma blending suggestions notified to the user

[1407] Step 5: Enter your feedback

[1408] The user tries out the proposed aroma blend and enters feedback on its effectiveness and satisfaction. This feedback data is then temporarily stored on the smart device.

[1409] Input: Impressions after use, satisfaction level

[1410] Output: User feedback data

[1411] Step 6: Send your feedback

[1412] The terminal generates an API request for transmitting the feedback data collected from the user to the server, and transmits the request to the server.

[1413] Input: User feedback data

[1414] Output: API request to the server

[1415] Step 7: Feedback analysis and model retraining

[1416] The server analyzes the received feedback data and reflects it in the generative AI model. This re-learning improves the accuracy of aroma blend suggestions from the next time onwards.

[1417] Input: User feedback data

[1418] Output: Updated machine learning model

[1419] Through these steps, the aromatherapist AI system of the present invention can provide optimal aroma blends that meet the individual needs of users and can continuously improve them based on feedback.

[1420] 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.

[1421] The aromatherapist AI system of the present invention proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. Furthermore, by combining it with an emotion engine, the system also recognizes the user's emotional state and proposes aroma blends based on that. This system consists of multiple processes: user input, emotion recognition data acquisition, data transmission, data analysis, proposal notification, and feedback processing.

[1422] User: Information entry process

[1423] First, the user launches the dedicated application and logs in. Then, on the application screen, the user inputs their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent (e.g., lavender, mint, etc.). The input information is crucial for determining the aroma composition.

[1424] User: Emotion recognition process

[1425] While the user is inputting, the device's built-in camera and microphone collect the user's voice and facial expression data. The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise, etc.). The emotional state data is sent to the server along with information on the user's physical condition and mood.

[1426] Terminal: Information transmission process

[1427] The information entered by the user regarding their physical condition, mood, and preferred scent, as well as the emotional state data recognized by the emotion engine, are stored in temporary storage on the device. The device then generates an API request to send this data to the server, which then sends it to the server. The transmitted data is encrypted to ensure privacy.

[1428] Server: Data analysis process

[1429] The server analyzes the received user information and uses a machine learning model to determine the optimal aroma blend for the user's current state. This analysis takes into account data such as physical condition, mood, and preferred scents, as well as emotional state data recognized by the emotion engine. For example, if the server recognizes that the user is feeling stressed, it will suggest aroma oils with a relaxing effect (e.g., lavender or bergamot).

[1430] Server: Proposal generation process

[1431] The server generates a proposal for the optimal aroma blend for the user based on the analysis results. This proposal includes details such as the specific aroma oil type, amount to use, blending method, and usage method. The proposal is sent to the device as an API response.

[1432] Terminal: Proposal Notification Process

[1433] The device receives the API response from the server and notifies the user of the proposed aroma blend. The user can then check the proposed aroma blend on the application screen. The notification uses a visual interface to make it easy for the user to understand.

[1434] User: Feedback input process

[1435] Users try out the proposed aroma blends and enter their feedback through the application about their experience and satisfaction, including perceived effects, satisfaction, and possible improvements.

[1436] Terminal: Feedback sending process

[1437] The feedback data sent by the user is temporarily stored on the device, and an API request is generated to send it to the server. The device then sends the generated API request to the server.

[1438] Server: Feedback processing process

[1439] The server analyzes the received feedback data and inputs it into a machine learning model. The machine learning model is retrained based on this feedback data, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[1440] Specific examples

[1441] User A uses the application to input that he is "stressed," and further states that he "wants to relax," selecting "lavender" and "mint" as his favorite scents. The device collects this information along with the user's facial expressions and voice data, and uses an emotion engine to recognize "irritation." The device then sends this data set to the server. Taking into account past feedback and seasonal fluctuation patterns, the server suggests the optimal aroma blend of "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot." User A tries the proposed blend and sends feedback, rating it as "very relaxing." This feedback is analyzed by the server and used to improve the accuracy of future suggestions.

[1442] By combining this with an emotion engine, it will be possible to propose sophisticated aroma blends that take into account even the subtlest emotional changes of the user, which is expected to maximize the effects of aromatherapy.

[1443] The processing flow will be explained below.

[1444] Step 1:

[1445] The user launches the application and logs in. The user enters information about their physical condition, mood, desired effect (e.g., relaxation, concentration), and preferred scent (e.g., lavender, mint).

[1446] Step 2:

[1447] The device's built-in camera and microphone collect the user's voice and facial expression data.

[1448] Step 3:

[1449] The device transmits the collected voice and facial expression data to the emotion engine in real time.

[1450] Step 4:

[1451] The emotion engine analyzes the user's voice tone, facial expression changes, and language patterns to recognize the user's emotional state (e.g., joy, sadness, anger, surprise).

[1452] Step 5:

[1453] The device temporarily stores information entered by the user regarding physical condition, mood, and preferred scent, as well as emotional state data recognized by the emotion engine.

[1454] Step 6:

[1455] The device generates an API request to send the stored user information and emotional state data to the server.

[1456] Step 7:

[1457] The device sends the generated API request to the server.

[1458] Step 8:

[1459] The server receives the API request sent from the device.

[1460] Step 9:

[1461] The server parses the contents of the request body and extracts user data and emotional state data.

[1462] Step 10:

[1463] The server stores the extracted user data and emotional state data in a database.

[1464] Step 11:

[1465] The server inputs the stored user data and emotional state data into a machine learning model for analysis.

[1466] Step 12:

[1467] The machine learning model calculates the optimal aroma combination based on information such as "physical condition," "mood," "desired effect," "preferred smell," and "emotional state."

[1468] Step 13:

[1469] The server takes into account past feedback data and seasonal fluctuations to adjust the aroma blend.

[1470] Step 14:

[1471] The server will create the optimal aroma combination (e.g., 3 drops lavender, 2 drops mint, 2 drops bergamot).

[1472] Step 15:

[1473] The server creates a message to suggest the generated aroma blend to the user.

[1474] Step 16:

[1475] The server generates an API response to send this message to the device.

[1476] Step 17:

[1477] The device receives the API response from the server.

[1478] Step 18:

[1479] The terminal analyzes the received proposal message and notifies the user.

[1480] Step 19:

[1481] The user checks the proposed aroma blend on the application screen.

[1482] Step 20:

[1483] The user tries out the suggested aroma and enters feedback on its effectiveness and satisfaction.

[1484] Step 21:

[1485] The device temporarily stores the feedback entered by the user in storage.

[1486] Step 22:

[1487] The device generates an API request to send the saved feedback data to the server.

[1488] Step 23:

[1489] The device sends the generated API request to the server.

[1490] Step 24:

[1491] The server receives the feedback data sent from the terminal.

[1492] Step 25:

[1493] The server analyzes the feedback data and adds it to the dataset of the machine learning model.

[1494] Step 26:

[1495] The server retrains the machine learning model to improve the accuracy of future suggestions.

[1496] Example 2

[1497] 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."

[1498] Conventional aromatherapy systems only suggest aroma blends based on the user's physical condition and mood, but do not take into account the user's emotional state. This makes it difficult to suggest personalized aroma blends that respond to subtle changes in the user's emotions. Furthermore, the accuracy of suggestions based on feedback has not been sufficiently improved.

[1499] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1500] In this invention, the server includes means for receiving information about the user's physical condition, mood, and preferred scent from the user, means for collecting the user's voice and facial expression data using a camera and microphone while the user is inputting the information, means for analyzing the collected emotional state data, means for transmitting the information received from the user and the emotional state data to the server, means for the server to analyze the received user information and emotional state data and determine an aroma blend optimal for the user's condition, means for notifying the user of the aroma blend information determined by the server, means for receiving feedback from the user after using the aromas and transmitting it to the server, means for improving subsequent aroma blend suggestions based on the received feedback, means for recognizing the user's emotional changes using an emotion engine and reflecting them in aroma blend suggestions, and means for learning the user's feedback using a machine learning model to improve the accuracy of subsequent suggestions. This enables advanced personalization that takes into account not only the user's physical condition and mood but also their emotional state, thereby maximizing the effects of aromatherapy.

[1501] "Physical condition" refers to the user's physical health condition and current physical condition.

[1502] "Mood" refers to the user's psychological and emotional state, or how they feel at a given moment.

[1503] "Favorite scent" refers to the aroma or type of scent that the user particularly likes.

[1504] "Camera" refers to a video input device for capturing the user's facial expression.

[1505] "Microphone" refers to an audio input device for capturing a user's voice.

[1506] "Voice data" refers to audio information obtained from a user's voice and speaking style.

[1507] "Facial expression data" refers to visual information obtained from the user's facial expressions.

[1508] An "emotion engine" refers to software or hardware that analyzes collected voice and facial expression data and recognizes the user's emotional state.

[1509] "Emotional state" refers to the emotions the user is feeling at that time, such as joy, sadness, anger, surprise, etc.

[1510] "Analysis" refers to the act of processing received and collected data to derive a specific conclusion or result.

[1511] "Server" refers to a central processing unit that receives and analyzes data sent by users.

[1512] "Aroma blend" refers to the types and proportions of aromatic oils blended to bring out a specific effect.

[1513] "Notification" refers to the act of sending information to inform users of the proposed content and analysis results.

[1514] "Feedback" refers to the act of a user providing the results and impressions of a proposed aroma blend after trying it out.

[1515] A "machine learning model" refers to an algorithm or system that learns from data and improves the accuracy of future suggestions and predictions.

[1516] "Personalization" refers to the act of customizing offers and services to suit the individual preferences and circumstances of each user.

[1517] "Encryption" refers to the technology of converting data so that it cannot be read by third parties.

[1518] The aromatherapist AI system of the present invention is a system that proposes optimal aroma blends based on the user's physical condition, mood, and preferred scents. Furthermore, it utilizes an emotion engine to take the user's emotional state into consideration. Specific embodiments are described below.

[1519] Users use a device such as a smartphone or tablet to launch a dedicated application and log in. After logging in, users enter their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and preferred scent on the application screen. This input information is important for determining the aroma blend.

[1520] While the user is typing, the device's built-in camera and microphone collect the user's voice and facial expression data. This data is analyzed in real time by an emotion engine to recognize the user's emotional state. Examples of emotion engines include Microsoft Azure Cognitive Services and IBM Watson.

[1521] The collected data on physical condition, mood, preferred odor, and emotional state is stored in temporary storage on the device, after which the device generates an API request to send this data to the server, where it is encrypted and sent.

[1522] The server analyzes the data received from the device and uses a machine learning model to determine the optimal aroma combination for the user's current state. This analysis process takes into account the user's physical condition, mood, preferred scents, and emotional state data. Examples of machine learning models include TensorFlow and PyTorch.

[1523] The server then uses the analysis results to propose the optimal aroma blend for the user. This proposal includes the specific type of aroma oil, the amount to use, the blending method, and how to use it. The proposal is sent to the device as an API response.

[1524] The device receives the API response from the server and notifies the user of the proposed content. The notification is sent via the application screen and displayed in a visually easy-to-understand format.

[1525] Users try out the proposed aroma blends and enter their feedback through the application about their perceived effects and satisfaction, as well as areas for improvement.

[1526] The device temporarily stores the feedback data and generates an API request to send it to the server, where it is encrypted and sent.

[1527] The server analyzes the received feedback data and inputs it into a machine learning model, which then retrains the model based on the feedback data, improving the accuracy of future suggestions.

[1528] As a concrete example, user A uses an application, inputs that he is "stressed," and selects his favorite scents as "lavender" and "mint," saying that he "wants to relax." When the device collects this information, it also analyzes the user's facial expressions and voice data using an emotion engine to recognize "irritation." The server considers past feedback and seasonal fluctuation patterns and suggests "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" as the optimal aroma blend. User A tries this blend and sends feedback that it was "very relaxing." This feedback is reflected in future suggestions.

[1529] Example prompts to input to the generative AI model:

[1530] "Suggest the best aroma combination based on your current physical condition, mood, preferred smell, and emotional state. Example: Use lavender, bergamot, and mint."

[1531] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1532] Step 1:

[1533] The user launches a dedicated application and logs in. After logging in, they enter their current physical condition, mood, desired effect (relaxation, concentration, refreshment, etc.), and favorite scent into the input form displayed on the application screen. This generates data on physical condition, mood, desired effect, and favorite scent. Examples of input data include "Physical condition: tired," "Mood: stressed," "Desired effect: relaxation," and "Favorite scent: lavender, mint."

[1534] Step 2:

[1535] While the user is entering information, the device's built-in camera and microphone collect the user's voice and facial expression data. The collected voice and facial expression data is sent to an emotion engine, which recognizes the user's emotional state as "happiness," "sadness," "irritation," etc. Specifically, the camera captures the user's facial expressions while the user is entering information, and the microphone records the voice. This data is analyzed in real time by the emotion engine, and "irritation" is output as emotional state data.

[1536] Step 3:

[1537] The device temporarily stores data entered by the user regarding their physical condition, mood, and favorite scent, as well as the emotional state data recognized by the emotion engine. It then generates an API request to send this data to the server. Specifically, it generates a data packet containing "Physical condition: tired," "Mood: stressed," "Favorite scent: lavender, mint," and "Emotional state: irritated," encrypts it, and sends it to the server.

[1538] Step 4:

[1539] The server receives the data sent from the device. The received data is stored in a database and input into a machine learning model for analysis. Specific examples of data processing include integrating data on physical condition, mood, preferred scent, and emotional state and converting it into a format suitable for analysis.

[1540] Step 5:

[1541] The server uses machine learning models to determine the optimal aroma blend for the user's current state. Based on the analysis results, a specific aroma blend, such as "3 drops lavender, 2 drops mint, and 2 drops bergamot," is determined. This output is best suited to the user's physical condition, mood, and emotional state.

[1542] Step 6:

[1543] The server sends the determined aroma blend information to the terminal as an API response. The response includes details such as the specific aroma oil type, amount to be used, blending method, and usage instructions. For example, it suggests mixing "3 drops of lavender, 2 drops of mint, and 2 drops of bergamot" and using it once every night.

[1544] Step 7:

[1545] The device receives the API response from the server and notifies the user of its contents. The notification is displayed visually on the application screen and is designed to be easy for the user to understand. For example, the application screen displays an icon of an aroma oil bottle along with detailed instructions on how to use it.

[1546] Step 8:

[1547] The user tries out the proposed aroma blend and enters feedback through the application about its effectiveness and satisfaction. The feedback includes perceived effectiveness, satisfaction, and areas for improvement. Specifically, the user enters the comment, "It was very relaxing."

[1548] Step 9:

[1549] The device temporarily stores the feedback data entered by the user and generates an API request to send to the server. The generated request is encrypted and sent to the server. For example, the request may contain feedback data such as "very relaxing" or "no improvement needed."

[1550] Step 10:

[1551] The server analyzes the received feedback data and inputs it into a machine learning model. This allows the model to be retrained based on the feedback data, improving the accuracy of future aroma blend suggestions. Specifically, feedback such as "I felt very relaxed" will be reflected in the next suggestion, enabling more personalized suggestions.

[1552] (Application example 2)

[1553] 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."

[1554] In modern self-driving vehicles, there is a lack of relaxation methods that correspond to the physical condition and mood of the driver and passengers during long driving sessions, which causes stress and fatigue to accumulate.In addition, there is no system that can recognize the emotional state of each user in real time and respond appropriately, which makes it difficult to provide personalized relaxation effects.

[1555] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting voice and facial expression data via a camera and microphone to recognize the user's emotional state, means for transmitting information and emotional data received from the user to the server, and means for analyzing the user information and emotional state data received by the server and determining the optimal aroma blend for the user's condition. This makes it possible to provide optimal aromatherapy based on the user's real-time physical condition and emotional state, thereby reducing stress and fatigue in an autonomous vehicle.

[1556] The "means for receiving information about the user's physical condition, mood, and favorite smell" is a device or application that provides an interface through which the user can input information about their physical condition, mood, and favorite smell.

[1557] "Means for collecting voice and facial expression data via a camera or microphone to recognize the emotional state of a user" refers to a device that acquires data using a camera or microphone to detect the emotional state of a user from their voice or facial expression.

[1558] The "means for transmitting information and emotional data received from the user to the server" refers to a device or application with a communication function for transferring the user's input information and collected emotional data to the server.

[1559] The "means for analyzing the user information and emotional state data received by the server and determining the optimal aroma blend for the user's state" refers to a server equipped with an algorithm or machine learning model that analyzes the received information and emotional data and determines the optimal aroma type and blend based on that.

[1560] The "means for notifying the user of the aroma blend information determined by the server" refers to a device or application that has a display function or notification function for informing the user of the results of the aroma blend.

[1561] "Means for receiving feedback from users after using an aroma and transmitting it to a server" refers to a device or application with an interface and communication functions that allows users to input their impressions and effects after using an aroma and transmit that data to a server.

[1562] The "means for improving subsequent aroma blend suggestions based on received feedback" is a server that analyzes user feedback and retrains the machine learning model to improve the accuracy of subsequent aroma blend suggestions.

[1563] The "means for correcting aroma blend suggestions by referring to seasonal fluctuations and the user's past usage history" refers to a server equipped with an algorithm that adjusts aroma blend suggestions by taking into account seasonal fluctuations in demand for fragrances and the user's past feedback data.

[1564] "Means for the server to learn feedback data using a machine learning model and improve the accuracy of future suggestions" refers to a mechanism that uses a machine learning model to learn feedback data from users and improves the accuracy of future aroma suggestions based on the results.

[1565] The aromatherapist system of this invention is realized by an application that operates in conjunction with a smartphone or head-mounted display installed in an autonomous vehicle. This system collects and analyzes the user's physical condition, mood, preferred scents, and emotional state in real time, and based on that data, sprays the optimal aroma inside the vehicle.

[1566] Hardware and software used

[1567] Smartphones and head-mounted displays: Interface for application operation and user input.

[1568] Camera and microphone: Devices for collecting voice and facial expression data.

[1569] Server: Back-end infrastructure for analyzing data and making aroma formulation decisions.

[1570] Specific features

[1571] 1. User Input and Emotion Recognition:

[1572] Users can input their physical condition, mood, and preferred scent using a smartphone or head-mounted display, and the system collects voice and facial expression data in real time through a camera and microphone, and identifies the user's emotional state through an emotion recognition engine.

[1573] 2. Data transmission:

[1574] The information entered by the user and the collected emotional data are temporarily stored on the device and then sent to the server as an API request. The data is encrypted and transmitted in a privacy-protected manner.

[1575] 3. Data analysis and aroma formulation determination:

[1576] The server analyzes the received user information and emotional state data and determines the optimal aroma blend based on that information, using machine learning models that take into account the user's past usage history and seasonal variations.

[1577] 4. Proposal Notice and Aroma Dispersal:

[1578] The aroma blend information determined by the server is then written back to the terminal and notified to the user. The user can confirm the proposed aroma blend and issue a command to spray it inside the car.

[1579] 5. Gathering Feedback and Improving:

[1580] Users try out aroma blends and provide feedback through a dedicated interface, which is then sent to a server to retrain the machine learning model to improve future aroma blend suggestions.

[1581] Specific prompt examples

[1582] Prompt Sentence Examples

[1583] "User's physical condition: tired, mood: stressed, favorite smells: lemon, peppermint. Suggest the best aroma combination based on emotional state: irritated."

[1584] As described above, this system reduces stress and fatigue in the car, providing a comfortable driving experience.

[1585] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1586] Step 1:

[1587] The user inputs their physical condition, mood, and preferred scent using a smartphone or head-mounted display, which then inputs information about the user's condition into the application. The input data is temporarily stored in the device's memory for the next processing step.

[1588] Step 2:

[1589] The user's voice and facial expression data are collected through a camera and microphone. The camera and microphone capture the user's face and voice in real time, and the acquired data is input into an emotion recognition engine. The emotion recognition engine analyzes this data and identifies the user's emotional state (e.g., joy, sadness, irritation, etc.). This analyzed data is also stored in the device's memory.

[1590] Step 3:

[1591] The device temporarily stores the information and emotional data input by the user in storage. Based on this data, it generates an API request and sends it to the server in an encrypted form. This API request includes data on the user's physical condition, mood, preferred scent, and emotional state.

[1592] Step 4:

[1593] The server analyzes the received user information and emotional state data. A machine learning model is used to determine the optimal aroma blend based on the user's current state. The machine learning model is based on a pre-trained dataset and takes into account past usage history and seasonal fluctuations.

[1594] Step 5:

[1595] The server generates aroma blend information based on the analysis results. This information includes details such as the specific aroma oil type, amount to be used, blending method, and usage method. The generated aroma blend information is sent to the device as an API response.

[1596] Step 6:

[1597] The device receives the API response from the server and notifies the user of the suggested aroma blend. The notification is made through a visual interface, allowing the user to confirm the recommended aroma blend. After confirming, the user can spray the aroma into the car through the aroma diffuser.

[1598] Step 7:

[1599] After using the aroma, users enter feedback about its effects and satisfaction through the application. This feedback data is temporarily stored on the device again, and an API request is generated to send it to the server. The feedback data sent to the server through the API request will be used to improve the accuracy of future suggestions.

[1600] Step 8:

[1601] The server analyzes the received feedback data and inputs it into a machine learning model. This analysis retrains the machine learning model, improving the accuracy of future aroma blend suggestions. This enables more personalized suggestions for each user.

[1602] 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.

[1603] 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.

[1604] 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.

[1605] 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.

[1606] 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.

[1607] 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.

[1608] 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).

[1609] 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.

[1610] 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."

[1611] 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.

[1612] 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).

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] The following is further disclosed regarding the above embodiment.

[1624] (Claim 1)

[1625] A means for receiving information regarding physical condition, mood, and preferred smell from a user;

[1626] means for transmitting information received from a user to a server;

[1627] A means for analyzing the user information received by the server and determining an aroma blend that is optimal for the user's condition;

[1628] a means for notifying a user of the aroma blend information determined by the server;

[1629] A means for receiving feedback from the user after using the aroma and transmitting the feedback to the server;

[1630] The system includes a means for improving subsequent aroma blend suggestions based on the received feedback.

[1631] (Claim 2)

[1632] The system according to claim 1, further comprising means for correcting the aroma blend proposal by referring to seasonal variations and the user's past usage history.

[1633] (Claim 3)

[1634] The system according to claim 1, further comprising means for learning the feedback data using a machine learning model, and for the server to improve the accuracy of suggestions from the next time onwards.

[1635] "Example 1"

[1636] (Claim 1)

[1637] A means for receiving information regarding physical condition, mood, and preferred smell from a user;

[1638] A means for temporarily storing the received information and generating an API request to send to a server;

[1639] A means for analyzing the user information received by the server and determining the aroma composition that is best suited to the user's condition using a machine learning model;

[1640] A means for the server to send the determined aroma blend information to the terminal as an API response, and for the terminal to notify the user;

[1641] A means for receiving feedback from a user after using the aroma and generating an API request to send to a server;

[1642] The system includes means for retraining the machine learning model based on the received feedback to improve subsequent aroma blend suggestions.

[1643] (Claim 2)

[1644] The system according to claim 1, further comprising means for correcting the aroma blend proposal by referring to seasonal variations and the user's past usage history.

[1645] (Claim 3)

[1646] The system according to claim 1, further comprising means for learning the feedback data using a machine learning model, and for the server to improve the accuracy of suggestions from the next time onwards.

[1647] "Application Example 1"

[1648] (Claim 1)

[1649] A means for receiving information regarding physical condition, mood, and preferred smell from a user;

[1650] means for transmitting information received from a user to a server;

[1651] A means for analyzing the user information received by the server and determining an aroma blend that is optimal for the user's condition;

[1652] A means for notifying the smart device of the aroma blend information determined by the server;

[1653] A means for receiving feedback from a user after using the aroma via a smart device and transmitting the feedback to a server;

[1654] The system includes a means for improving subsequent aroma blend suggestions based on the received feedback.

[1655] (Claim 2)

[1656] The system according to claim 1, further comprising means for correcting the aroma blend proposal by referring to seasonal variations and the user's past usage history.

[1657] (Claim 3)

[1658] The system according to claim 1, further comprising means for learning the feedback data using a machine learning model, and for the server to improve the accuracy of suggestions from the next time onwards.

[1659] "Example 2: Combining Emotion Engines"

[1660] (Claim 1)

[1661] A means for receiving information regarding physical condition, mood, and preferred smell from a user;

[1662] means for collecting voice and facial expression data of the user using a camera and / or microphone while the user is entering information;

[1663] means for analyzing the collected emotional state data;

[1664] means for transmitting the information and emotional state data received from the user to a server;

[1665] A means for analyzing the user information and emotional state data received by the server and determining an aroma blend that is optimal for the user's state;

[1666] a means for notifying a user of the aroma blend information determined by the server;

[1667] A means for receiving feedback from the user after using the aroma and transmitting the feedback to the server;

[1668] a means of improving future aroma blend proposals based on the feedback received; and

[1669] A means for recognizing changes in the user's emotions using an emotion engine and reflecting these changes in aroma blending suggestions;

[1670] A system that uses a machine learning model to learn from user feedback and improve the accuracy of future suggestions.

[1671] (Claim 2)

[1672] The system according to claim 1, further comprising means for correcting the aroma blend proposal by referring to seasonal variations and the user's past usage history.

[1673] (Claim 3)

[1674] The system according to claim 1, further comprising means for learning the feedback data using a machine learning model, and for the server to improve the accuracy of suggestions from the next time onwards.

[1675] "Application example 2 when combining emotion engines"

[1676] (Claim 1)

[1677] A means for receiving information regarding physical condition, mood, and preferred smell from a user;

[1678] means for collecting voice and facial expression data via a camera and / or microphone to recognize the user's emotional state;

[1679] means for transmitting the information and emotion data received from the user to a server;

[1680] A means for analyzing the user information and emotional state data received by the server and determining an aroma blend that is optimal for the user's state;

[1681] a means for notifying a user of the aroma blend information determined by the server;

[1682] A means for receiving feedback from the user after using the aroma and transmitting the feedback to the server;

[1683] The system includes a means for improving subsequent aroma blend suggestions based on the received feedback.

[1684] (Claim 2)

[1685] The system according to claim 1, further comprising means for correcting the aroma blend proposal by referring to seasonal variations and the user's past usage history.

[1686] (Claim 3)

[1687] The system according to claim 1, further comprising means for learning the feedback data using a machine learning model, and for the server to improve the accuracy of suggestions from the next time onwards. [Explanation of symbols]

[1688] 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 receiving information regarding physical condition, mood, and preferred smell from a user; means for transmitting information received from a user to a server; A means for analyzing the user information received by the server and determining an aroma blend that is optimal for the user's condition; a means for notifying a user of the aroma blend information determined by the server; A means for receiving feedback from the user after using the aroma and transmitting the feedback to the server; The system includes a means for improving subsequent aroma blend suggestions based on the received feedback.

2. 2. The system according to claim 1, further comprising means for correcting the aroma blend proposal by referring to seasonal variations and the user's past usage history.

3. The system according to claim 1 , further comprising means for learning the feedback data using a machine learning model, and for the server to improve the accuracy of proposals from the next time onwards.

Images