System

Abstract

A system is provided.SOLUTION: A system including means for collecting olfactory data and storing it as chemical composition data in a database, means for training a machine learning model on the basis of the olfactory data, means for generating and transmitting a request for generating a specific scent in response to an action of a user, means for generating scent data using a scent generation model in response to the request and transmitting the scent data to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, and means for collecting feedback from the user and reflecting the feedback in improvement of the system or the model.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] Among the five senses, the sense of smell has been particularly slow to undergo digital transformation (DX), and current technology has made it difficult to provide users with a realistic olfactory experience. For example, while the reproduction of sight and hearing has been achieved with high accuracy in the gaming industry and the metaverse, reproduction of smell has not yet become widespread, preventing users from fully satisfying their sense of immersion and realism. Furthermore, the lack of technology to generate and deliver scents in real time in response to user actions has delayed the creation of new user experiences. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. Specifically, the system includes a means for collecting olfactory data and storing it in a database as chemical composition data. It also includes a means for training a machine learning model based on the collected olfactory data. It further includes a means for generating and sending a request to generate a specific scent in response to a user's action. It also includes a means for generating scent data using a scent generation model in response to the request and sending it to a corresponding terminal. The terminal includes a means for using the received scent data to generate an actual scent using a scent diffuser. It also includes a means for collecting feedback from users and reflecting it in improving the system and model, thereby providing a more realistic and immersive olfactory experience.

[0006] "Olfactory data" refers to information about chemical composition and molecular structure collected to digitally represent the sense of smell.

[0007] "Chemical composition data" refers to data that indicates the components of a fragrance and their proportions, and includes information necessary to identify and reproduce the fragrance.

[0008] A "database" is a structured information system that organizes and stores collected olfactory data and chemical composition data, and makes them searchable and accessible as needed.

[0009] A "machine learning model" is an algorithm based on mathematical and computational laws that uses large amounts of data to learn patterns and generate and recognize olfactory data.

[0010] "User actions" are operations or movements performed by users in digital environments such as games or metaverse spaces, and are what trigger the system to generate a scent.

[0011] A "request" is request information sent from a terminal to a server, and includes instructions for generating a specific fragrance.

[0012] An "aroma generation model" is a type of machine learning model, a method or process that generates a specific aroma based on input olfactory data.

[0013] A "terminal" is a device or equipment that is directly operated by a user and has the function of receiving scent data and actually generating the scent.

[0014] An "aroma diffuser" is a device that emits a specific scent based on digital data, and is hardware that provides users with an olfactory experience.

[0015] "Feedback" refers to evaluations and opinions provided by users, and is information that is useful for improving systems and models.

[0016] A "system" is a combination of the above means and elements and software and hardware for performing a series of operations. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] An embodiment of the olfactory digitization system of the present invention will be specifically described below.

[0039] This system consists of a device for collecting and digitizing olfactory data, a device for training a machine learning model based on the collected data, a device for generating and transmitting scent data in response to user actions, and a device for reproducing the scent data as an actual scent.

[0040] Data collection and training phase

[0041] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[0042] User Actions and Request Generation

[0043] When a user performs a specific action in a game or in the metaverse, the device detects it and collects the corresponding event information. For example, when a user enters a virtual cafe, the device generates a request saying "I need the smell of coffee" and sends it to the server. The server receives this request and generates the appropriate scent data.

[0044] Scent generation and transmission

[0045] The server operates the scent generation model based on the received request and generates specific scent data. The generated scent data is converted into an appropriate format and sent to the device. The device generates an actual scent using a scent diffuser based on the received scent data. The scent diffuser mixes specific compounds based on the scent data and releases the scent.

[0046] User Experience and Feedback

[0047] By smelling the generated scent, the user can experience a more realistic and immersive experience. The user's evaluation and feedback of the experience are sent to the server via the device. This feedback is used to improve the accuracy of the scent generation model and the overall system.

[0048] Specific examples

[0049] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device, which will then use a scent diffuser to recreate these scents, enhancing the user's sense of realism in the game.

[0050] As another example, if a user enters a virtual cafe in the metaverse, the server will generate the aroma of coffee or freshly baked bread and send it to the device, which will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more realistic.

[0051] This system provides new value to users by realizing a real-time olfactory experience in digital space, and solves the problem through the means described in the claims.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The server uses an olfactory sensor to collect data on various scents, which is then stored in a database as chemical composition data.

[0055] Step 2:

[0056] The server preprocesses the stored chemical composition data, removing impurities and noise and streamlining the dataset to obtain high-quality data.

[0057] Step 3:

[0058] The server trains a machine learning model on the pre-processed data, using machine learning algorithms to learn patterns from the data and build a model capable of generating specific scents.

[0059] Step 4:

[0060] When a user performs a specific action in a game or in the Metaverse space, the device detects this action through sensors and interfaces, for example, when the user enters a virtual cafe.

[0061] Step 5:

[0062] The device generates a scent request based on the detected user action, for example, "I need the scent of coffee," and sends this request to the server.

[0063] Step 6:

[0064] The server runs the scent generation model based on the received request, generates the necessary scent data, converts it into an appropriate format, and sends it back to the device.

[0065] Step 7:

[0066] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[0067] Step 8:

[0068] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[0069] Step 9:

[0070] Users smell the scent emitted from the scent diffuser, making the digital experience feel realistic and immersive.

[0071] Step 10:

[0072] Users rate their experience based on the aromas they experience, for example, feeling that the coffee aroma was realistic.

[0073] Step 11:

[0074] The device collects user ratings and feedback and sends it to the server, which uses the feedback to improve the system.

[0075] Step 12:

[0076] The server analyzes user feedback and improves the scent generation model and the entire system, for example, by improving the accuracy of the scent generation algorithm.

[0077] The above is a detailed explanation of the processing steps of the Smell Tech system.

[0078] Example 1

[0079] 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."

[0080] Previous olfactory experiences in virtual spaces and games were limited, making it difficult for users to achieve a deeper sense of immersion through their sense of smell. Furthermore, the accuracy of scent generation and reproduction was low, and there was a lack of effective ways to utilize user feedback to improve the system. Furthermore, the entire process from data collection to reproduction was inefficient. This limited the quality of the user experience and made it difficult to provide new olfactory experiences.

[0081] 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.

[0082] In this invention, the server includes a means for collecting olfactory data and storing it in a database as chemical composition data, a means for training a machine learning model based on the olfactory data, and a cloud storage means for storing comprehensive scent data, thereby enabling highly accurate reproduction of scents and improving user experience.

[0083] The terminal also includes a means for detecting specific events and sending them to the server in a request format, a means for receiving scent data at the terminal and generating an actual scent using the scent diffuser, and a communication means for linking the terminal and the scent diffuser, thereby enabling scent generation in real time in response to user actions.

[0084] Furthermore, the system includes a means for collecting user feedback and reflecting it in improvements to the system and model, allowing for continuous system improvement based on the collected feedback, thereby providing a more advanced olfactory experience.

[0085] "Olfactory data" refers to data obtained by an olfactory sensor about the molecular components and chemical composition associated with a particular scent.

[0086] "Chemical composition data" is a part of olfactory data, and is information that includes the molecules that make up a particular scent and their proportions.

[0087] A "database" is a storage system that systematically stores olfactory data and chemical composition data, allowing for efficient access and searching.

[0088] A "machine learning model" is an algorithm that learns patterns from large amounts of data and automatically performs specific tasks.

[0089] "Cloud storage" is a service that stores data on the Internet and is a means of efficiently storing large amounts of data.

[0090] A "terminal" is a device that a user operates via an interface, and is a device that generates requests and reproduces scents.

[0091] A "request" is a request that includes event information corresponding to a user action, and is information that is sent to a server.

[0092] An "aroma generation model" is a machine learning model trained to generate aromas based on specific chemical composition data.

[0093] "Communication means" refers to a network connection means for linking the terminal and the server, or the terminal and the scent diffuser.

[0094] An "aroma diffuser" is a device that physically reproduces a specific scent based on scent data.

[0095] "Feedback" refers to user-provided information about experience ratings and areas for improvement, and is data used to improve the system.

[0096] A "server" is a computer system that centrally collects, stores, analyzes, processes, and distributes olfactory data.

[0097] A "user action" is an event that occurs on the interface when a user performs a specific action or operation.

[0098] MODE FOR CARRYING OUT THE INVENTION

[0099] System Overview

[0100] The present invention consists of a device that collects and digitizes olfactory data, a device that trains a machine learning model based on the collected data, a device that generates and transmits scent data in response to user actions, and a device that reproduces the scent data as an actual scent.

[0101] Data Collection and Machine Learning

[0102] The server collects various scent samples using an olfactory sensor (e.g., an electronic nose) and obtains their chemical composition data. This data is stored in a database. The server uses machine learning libraries such as TensorFlow and PyTorch to train a scent generation model based on the collected data. Comprehensive scent data is stored in cloud storage (e.g., AWS S3 or Google Cloud Storage).

[0103] User action detection and request generation

[0104] When a user performs a specific action in the game or metaverse space, the device detects this through sensors and interfaces and collects corresponding event information. The device generates a request that says "the user has entered the virtual cafe" and sends it to the server. The request is sent to the server in JSON or XML format.

[0105] Generation and transmission of scent data

[0106] The server analyzes requests received from the device and generates scent data corresponding to specific events using a trained machine learning model. The generated scent data is sent to the device in JSON or XML format.

[0107] Fragrance reproduction and user experience

[0108] The device analyzes the received scent data and sends it to the scent diffuser, which then mixes specific compounds based on the scent data to create a realistic scent that the user can smell, providing a more realistic and immersive experience.

[0109] Gathering feedback and improving the system

[0110] The user's impressions and evaluations of the experience are sent to the server via the device, and this feedback is stored in a database and used to improve the scent generation model and optimize the entire system.

[0111] Specific examples

[0112] For example, if a user steps into an ancient temple in an adventure game, the device detects this action and requests "ancient temple scent data" from the server. The server generates scent data of damp stone and old books and sends it to the device. The device then controls a scent diffuser to reproduce these scents. By smelling these scents, the user can further enhance the sense of realism within the game.

[0113] When a user enters a virtual cafe in the metaverse, the server generates aroma data for coffee and freshly baked bread and sends it to the device, which then uses a scent diffuser to recreate the aroma, making the user's experience in the virtual space feel more realistic.

[0114] Prompt Sentence Examples

[0115] "Generate the aroma of coffee as you enter a virtual cafe."

[0116] "Recreate the scent of damp stone for a scene in an adventure game where you enter an ancient temple."

[0117] "Create a sea salt scent that wafts through the air when users are on a virtual beach."

[0118] This system provides a real-time olfactory experience, bringing new value to users.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1:

[0121] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. Specifically, the electronic nose sensor captures the molecular components of the scent and records them as digital data. The server then stores this data in a database as chemical composition data.

[0122] Input: Scent sample

[0123] Data processing: Digitalization of chemical components through sensing

[0124] Output: Chemical composition data

[0125] Step 2:

[0126] The server uses a machine learning algorithm based on the collected data to train a scent generation model. The server uses machine learning libraries such as TensorFlow and PyTorch, and uses the chemical composition data and meta-information about the scent (such as name, category, and intensity) as training data. The scent generation model is saved in cloud storage.

[0127] Input: Chemical composition data, meta information

[0128] Data Computation: Training with Machine Learning Algorithms

[0129] Output: Scent generation model

[0130] Step 3:

[0131] When a user performs a specific action in the game or in the metaverse space, the device detects this through sensors and interfaces and collects event information. The device generates event information such as "the user has entered a virtual cafe" and sends it to the server in the form of a request.

[0132] Input: User action

[0133] Data processing: action detection and event information generation

[0134] Output: Event-based request

[0135] Step 4:

[0136] The server receives the request sent from the device and analyzes the content. The server generates scent data corresponding to the event using the trained scent generation model. For example, the server generates coffee scent data for the event of entering a "virtual cafe." The scent data is then sent to the device.

[0137] Input: Event-based request

[0138] Data computation: Generation of scent data using scent generation models

[0139] Output: Scent data

[0140] Step 5:

[0141] The device analyzes the scent data received from the server and sends it to the scent diffuser, which then mixes specific compounds based on the scent data to create the actual scent.The device controls the scent diffuser using Bluetooth or Wi-Fi.

[0142] Input: Scent data

[0143] Data processing: Data analysis and transmission to the diffuser

[0144] Output: The actual scent generated

[0145] Step 6:

[0146] The user smells the generated scent and provides feedback on their experience. The device collects the user's feedback data and sends it to the server, which stores it in a database and uses it to improve the scent generation model and optimize the entire system.

[0147] Input: User feedback

[0148] Data Processing: Collecting and Sending Feedback

[0149] Output: Improved model and system optimization

[0150] (Application example 1)

[0151] 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."

[0152] Conventional content distribution services have focused on providing immersive experiences through video and audio, but incorporating the sense of smell has made it difficult to provide users with a more realistic and immersive experience. Furthermore, the development of systems that generate scents in real time and dynamically change them in response to user actions has also remained immature. To address this issue, a system that digitizes the sense of smell and enriches users' content viewing experiences is needed.

[0153] 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.

[0154] In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for generating and transmitting a request to generate a specific scent in response to a user's actions, means for generating scent data using the scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, means for collecting user feedback and reflecting it in improving the system and model, and means for generating and providing a scent tailored to a specific scene in real time while the user is viewing content. This provides a realistic scent experience in response to the user's actions, enabling a more immersive content viewing experience.

[0155] "Olfaction data" is digitalized information about scents that a user perceives through their sense of smell.

[0156] "Chemical composition data" refers to data on the composition of molecules and compounds used to reproduce a scent.

[0157] A "database" is an information management system that efficiently stores information such as olfactory data and chemical composition data, and enables searching and retrieval.

[0158] A "machine learning model" is a collection of algorithms that learn patterns from large amounts of data and generate and predict scents.

[0159] A "request" is a request sent to the server to generate a specific scent based on a user action.

[0160] A "terminal" is a device that is directly operated by the user to generate requests, receive scent data, and control the scent diffuser.

[0161] The "fragrance generation model" is a method for generating specific fragrances as digital data using a machine learning model.

[0162] "Scent data" is digital information for reproducing a specific scent generated by the scent generation model.

[0163] A "fragrance diffuser" is a device that physically generates and releases an actual scent based on scent data.

[0164] A "user action" is an operation or movement that a user performs through a terminal, which triggers the generation of a request.

[0165] "Feedback" refers to the user's evaluations and opinions about the scent they have experienced, and is information used to improve the system and the accuracy of the model.

[0166] "Content viewing" refers to the act of a user viewing video, audio, or other media content.

[0167] MODE FOR CARRYING OUT THE INVENTION

[0168] System Overview

[0169] This system consists of a series of processes that collect olfactory data, digitize it, generate scents using machine learning models, and provide the scents in real time during the user's content viewing experience. Specifically, a server, terminal, and scent diffuser work together.

[0170] Data collection and training phase

[0171] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. This data is stored in a database and used to train a machine learning model. Based on the collected data, the server trains a scent generation model using a machine learning algorithm (e.g., RandomForestRegressor using Scikit-learn), thereby improving its ability to reproduce specific scents.

[0172] User Actions and Request Generation

[0173] When a user is watching content on a smartphone or head-mounted display and a specific action (e.g., a scene change in a movie) occurs, the device detects this. The device's application generates a request for the scent of wet earth and sends it to the server. The server receives this request and generates the corresponding scent data.

[0174] Scent generation and transmission

[0175] The server operates the scent generation model based on the received request and generates specific scent data. The generated scent data is then converted into an appropriate format and sent to the terminal. The terminal then generates and releases an actual scent using a scent diffuser based on the received scent data. The scent diffuser then mixes specific compounds based on the scent data and releases the scent.

[0176] Feedback and System Improvement

[0177] By smelling the generated scent, the user can experience a more realistic and immersive experience. The user's evaluation and feedback of the experience are sent to the server via the device. This feedback is used to improve the accuracy of the scent generation model and the overall system.

[0178] Specific examples

[0179] For example, if a user is using the "Olfactory Cinema Experience App" to watch a movie and the scene switches to a rainy scene, the system will generate data on the scent of "wet earth" and send it to the device. The device's scent diffuser will then release the scent in real time based on this data, providing the user with a more immersive viewing experience.

[0180] Example prompts for generative AI models

[0181] Prompt: Create a scent that matches a scene from this movie. Scene: "Jungle at night", Desired scent: "The scent of damp vegetation"

[0182] This allows users to enjoy the content both visually and olfactory.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Step 1:

[0185] The server collects olfactory data. It uses an olfactory sensor to obtain various scent samples as olfactory data, and stores the chemical composition data in a database. The input is the scent sample from the olfactory sensor, and the output is stored in the database as chemical composition data.

[0186] Step 2:

[0187] The server trains a machine learning model based on the collected chemical composition data. Specifically, it uses Scikit-learn to train a RandomForestRegressor model to improve its ability to reproduce specific scents. The input is the chemical composition data stored in the database, and the output is the trained machine learning model.

[0188] Step 3:

[0189] When a user performs a specific action (e.g., scene change) while watching content on a device, the device detects this. The device detects the user's behavior through sensors and interfaces and collects event information. The input is the user's action, and the output is event information.

[0190] Step 4:

[0191] The device generates a request to generate a specific scent based on the collected event information and sends it to the server. For example, if a user watches a rainy scene in a movie, the device generates a request saying, "I need the scent of wet earth." The input is the event information, and the output is a scent generation request.

[0192] Step 5:

[0193] The server runs the scent generation model based on the received request. It uses the trained machine learning model to generate specific scent data and sends it to the device. The input is the scent generation request, and the output is the scent data.

[0194] Step 6:

[0195] The device generates the actual scent using a scent diffuser based on the scent data received from the server. The diffuser mixes the specified chemical ingredients and releases the scent. The input is scent data, and the output is a physical scent.

[0196] Step 7:

[0197] By smelling the generated scent, the user experiences the realism of watching content. The user then inputs their evaluation and feedback about the experience into the device, which then sends this to the server. The input is the user's feedback, and the output is the feedback data.

[0198] Step 8:

[0199] The server collects feedback data from users and reflects it in improving the system and machine learning model. The input is the feedback data, and the output is an improved system or model.

[0200] 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.

[0201] A system combining the olfactory digitization system and emotion engine of the present invention will be described below in detail with reference to an embodiment thereof.

[0202] This system consists of a device for collecting and digitizing olfactory data, a device for recognizing user emotions using an emotion engine, a device for training a machine learning model based on the collected data, a device for generating and transmitting scent data in response to user actions and emotions, and a device for reproducing the scent data as an actual scent.

[0203] Data collection and training phase

[0204] The server uses an olfactory sensor to collect data on various scents and obtain their chemical composition. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[0205] User actions, emotion recognition and request generation

[0206] When a user performs a specific action in a game or in the Metaverse space, the device detects this and collects corresponding event information. For example, a user entering a virtual cafe can be detected.

[0207] The device then activates an emotion engine that analyzes the user's facial, voice, and movement data to recognize their emotions, for example, whether they are feeling happy or anxious.

[0208] The device generates a scent request based on the detected user actions and the recognized emotions. For example, it generates a request such as "The user has entered a virtual cafe and is enjoying themselves, so I need the relaxing aroma of coffee." The request is then sent to the server.

[0209] Scent generation and transmission

[0210] The server runs the scent generation model based on the received request to generate specific scent data, which is then converted into an appropriate format and sent back to the device.

[0211] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[0212] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[0213] User Experience and Feedback

[0214] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. Furthermore, the scent is generated according to the user's emotional state, providing a scent experience appropriate to the user's emotional state.

[0215] Users rate their experience based on the aromas they experience, for example, feeling that the aroma of coffee was "realistic and relaxing."

[0216] The device collects user ratings and feedback and sends it to the server, which uses the feedback to improve the system.

[0217] Specific examples

[0218] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device, which will then use a scent diffuser to recreate these scents, enhancing the user's sense of realism in the game.

[0219] As another example, if a user enters a virtual cafe in the metaverse, and the emotion engine recognizes that the user is enjoying themselves based on their facial expressions and actions, the server will generate the relaxing aroma of coffee or freshly baked bread and send it to the device. The device will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more realistic.

[0220] This system provides new value to users by realizing a real-time olfactory experience in digital space, and solves the problem through the means described in the claims.

[0221] The processing flow will be explained below.

[0222] Step 1:

[0223] The server uses an olfactory sensor to collect data on various scents, which is then stored in a database as chemical composition data.

[0224] Step 2:

[0225] The server preprocesses the stored chemical composition data, removing impurities and noise and streamlining the dataset to obtain high-quality data.

[0226] Step 3:

[0227] The server trains a machine learning model on the pre-processed data, using machine learning algorithms to learn patterns from the data and build a model capable of generating specific scents.

[0228] Step 4:

[0229] A user performs a specific action in the game or metaverse space, such as reaching a specific location in the game or using a specific item.

[0230] Step 5:

[0231] The device detects user actions through sensors and interfaces, such as when a user enters a virtual cafe.

[0232] Step 6:

[0233] The device runs an emotion engine that analyzes the user's facial, voice, and movement data to recognize emotions, for example, whether the user is feeling happy or anxious.

[0234] Step 7:

[0235] The device generates a scent request based on the detected user actions and the recognized emotions, for example, "The user has entered a virtual cafe and is enjoying themselves, so the relaxing aroma of coffee is needed."

[0236] Step 8:

[0237] The terminal transmits the generated scent request to the server.

[0238] Step 9:

[0239] The server runs the scent generation model based on the received request, generates the necessary scent data, converts it into an appropriate format, and sends it back to the device.

[0240] Step 10:

[0241] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[0242] Step 11:

[0243] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[0244] Step 12:

[0245] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. Furthermore, the scent is generated according to the user's emotional state, providing a scent experience appropriate to the user's emotional state.

[0246] Step 13:

[0247] Users rate their experience based on the aromas they experience, for example, feeling that the aroma of coffee was "realistic and relaxing."

[0248] Step 14:

[0249] The device collects user ratings and feedback and sends it to the server.

[0250] Step 15:

[0251] The server analyzes user feedback and improves the scent generation model and the entire system, for example, by improving the accuracy of the scent generation algorithm.

[0252] The above is a detailed step-by-step explanation of the processing flow of the Smell Tech system.

[0253] Example 2

[0254] 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."

[0255] In modern digital experiences and virtual spaces, there is a demand for comprehensive experiences that include not only sight and sound, but also smell. However, existing technologies lack the ability to digitalize the sense of smell or generate scents that respond to the user's emotions, making it difficult to achieve an immersive or realistic experience. In addition, there are limited methods for effectively collecting user feedback and incorporating it into systems and machine learning models.

[0256] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for detecting a user's actions and analyzing the actions and the user's emotions, means for generating and transmitting a request to generate a specific scent based on the analysis results, means for generating scent data using a scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, and means for collecting user feedback and reflecting it in improving the system and model. This makes it possible to generate and reproduce scents in real time according to the user's actions and emotions, realize an olfactory experience in a digital space, and utilize user feedback to continuously improve the system.

[0257] "Olfactory data" is data that quantifies and digitizes information about scents and odors, and includes information about chemical composition and ingredients.

[0258] "Chemical composition data" is data that indicates the types and proportions of chemical components contained in a specific fragrance or substance.

[0259] The "database" is an information recording system for storing and managing collected olfactory data and chemical composition data.

[0260] A "machine learning model" is an algorithm that learns patterns based on collected data and makes predictions and classifications for new inputs.

[0261] "User actions" refer to operations or movements that a user makes within a digital or virtual environment.

[0262] "Emotion analysis" is the process of determining a user's emotional state from data such as facial expressions, voice, and movements.

[0263] A "scent request" is a request to instruct the system to generate a particular scent.

[0264] A "scent generation model" is a machine learning model trained to generate a specific scent as digital data.

[0265] "Scent data" refers to data that includes specific chemical components and their blending ratios for reproducing the created scent.

[0266] A "terminal" is an electronic device or device that allows a user to access a digital space or virtual environment.

[0267] An "aroma diffuser" is a device that generates and releases actual scents based on scent data.

[0268] "Feedback" is information that provides the system with the user's evaluation and opinions regarding the scent they experienced.

[0269] "System improvement" refers to improving the performance and functionality of a system based on collected feedback.

[0270] This invention is a system that combines an olfactory digitization system and an emotion engine, allowing users to experience not only sight and hearing but also smell in digital or virtual environments. The present invention provides a system that comprehensively executes a series of processes from collecting olfactory data to generating scents and recognizing the user's emotions.

[0271] First, the server uses an olfactory sensor to collect data on various scents and obtain their chemical composition data. The specific hardware used includes various types of sensors. For example, olfactory sensors include gas sensors and electrochemical sensors that accurately measure chemical composition. This data is collected using a Python script and stored in a database (e.g., MySQL or PostgreSQL).

[0272] The server then trains a machine learning model based on the collected olfactory data. Specifically, it uses Python's scikit-learn and TensorFlow libraries to build and train a model based on the collected chemical composition data. For example, it uses a random forest algorithm or a neural network to learn specific scent generation patterns.

[0273] When a user performs a specific action in a digital space (e.g., a game or the Metaverse), the device (PC, smartphone, VR device, etc.) detects the action. Here, a script in a game engine based on Unity or Unreal Engine runs to monitor and detect the user's location and actions. For example, if a user is detected entering a virtual cafe, this information is registered as an event.

[0274] The device then uses an emotion engine to analyze the user's facial, voice, and movement data to recognize their emotions. Specifically, it uses the camera to analyze facial expressions using the OpenCV library and sends the data to the Microsoft Azure Face API to obtain the analysis results. At the same time, it collects voice data through the microphone and performs voice analysis using Google Cloud Speech-to-Text. This allows it to recognize the user's emotional state, such as whether they are happy or anxious.

[0275] The device generates a scent request based on the results of the above sentiment analysis and the user's actions. For example, a request such as "The user has entered a virtual cafe and is enjoying themselves, so they need a relaxing coffee aroma" is generated in JSON format and sent to the server. An example of a prompt sentence is:

[0276] A request is sent to the server saying, "The emotion engine has recognized that the user has entered a cafe in a virtual space and is enjoying themselves. Please generate scent data that has a relaxing effect."

[0277] The server then runs a scent generation model based on the received request to generate specific scent data. For example, it uses TensorFlow to generate the scent data and sends it back to the device in JSON or binary format. This scent data is formatted to include specific chemical component information.

[0278] The device receives the scent data sent from the server and sends it to the scent diffuser. The scent diffuser then mixes specific compounds based on the scent data to create the actual scent. Specific devices that can be connected via Bluetooth or Wi-Fi are used. For example, by using a smart device made by Scentee, the appropriate mixture of chemical components is created to recreate the relaxing aroma of coffee.

[0279] Users experience the scent emitted from the scent diffuser, making their digital experience more realistic and immersive. They also provide feedback on their scent experience through an application on their device. For example, a user might write a review such as, "The relaxing coffee aroma was very realistic." This feedback is temporarily stored on the device and later sent to a server. The server analyzes this feedback and uses it to improve the system and machine learning models.

[0280] As described above, the present invention provides a system that realizes a real-time olfactory experience in a digital space and enables the generation of scents according to the user's actions and emotions. Furthermore, by utilizing user feedback and continuously improving the system, it is possible to provide a higher quality olfactory experience.

[0281] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0282] Step 1:

[0283] The server collects scent data using an olfactory sensor. The olfactory sensor (e.g., a gas sensor or electrochemical sensor) is used to obtain chemical composition data of specific scents in real time. The obtained data is converted into CSV format using a Python script and sent to the server. The inputs are scent samples and sensor measurement results. The output is chemical composition data as a CSV file.

[0284] Step 2:

[0285] The server stores the collected chemical composition data in a database, using MySQL or PostgreSQL. The stored data is organized for later use in model training. The CSV file obtained in step 1 is used as input, and the data stored in the database is generated as output.

[0286] Step 3:

[0287] The server trains a machine learning model based on the stored chemical composition data. It uses Python's scikit-learn and TensorFlow libraries to build a scent generation model. Specifically, it uses a random forest algorithm and neural networks to train a model capable of reproducing a specific scent. The input is chemical composition data obtained from the database, and the output is a trained machine learning model.

[0288] Step 4:

[0289] When a user performs a specific action in the digital space, the device detects that action. Using scripts in game engines such as Unity or Unreal Engine, the device monitors the user's location and movements. For example, a user entering a virtual cafe is detected. The input is information about the user's action, and the output is event information generated for the specific action performed by the user.

[0290] Step 5:

[0291] The device collects the user's facial expression, voice, and movement data to recognize emotions. The specific technology used is to analyze facial expressions using a camera and the OpenCV library, and send the data to the Microsoft Azure Face API to obtain the analysis results. Voice data is analyzed using a microphone with Google Cloud Speech-to-Text. The input is the user's facial expression data, voice data, and movement data, and the output is the user's emotional state.

[0292] Step 6:

[0293] The device generates a scent request based on the user's actions and the results of emotion recognition. The scent request includes the specific action performed by the user and instructions for the scent based on the recognized emotion. The input is the event information of the user's actions and the results of emotion recognition. The output is a request to generate a specific scent in JSON format, which is sent to the server.

[0294] Step 7:

[0295] The server generates scent data based on the received scent request using a scent generation model. It runs a TensorFlow model to generate the specified scent chemical components. The input is the scent request and the machine learning model, and the output is the generated scent data in JSON format.

[0296] Step 8:

[0297] The server sends the generated scent data to the terminal. The scent data is transmitted to the terminal via the network and received by the terminal. The input is the generated scent data, and the output includes the scent data sent to the terminal.

[0298] Step 9:

[0299] The device generates an actual scent using a scent diffuser based on the received scent data. The device transmits the data to the scent diffuser, which mixes specific compounds based on the data and releases the scent. The input is the received scent data, and the output is a physically reproduced scent.

[0300] Step 10:

[0301] The user experiences the released scent and provides feedback. They input their evaluation and opinions about the scent experience through an application on their device. The input is the user's feedback, and the output is the collected feedback information.

[0302] Step 11:

[0303] The device stores the user's feedback and later transmits it to the server. The feedback is reflected in the system's improvements and is used to generate future scents. The input is the user's feedback information, and the output includes the feedback transmitted to the server.

[0304] Through these steps, this system provides a real-time olfactory experience in the digital space and can generate and reproduce scents according to the user's emotions.

[0305] (Application example 2)

[0306] 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."

[0307] Conventional virtual reality (VR) experiences and metaverse spaces rely solely on sight and hearing, limiting the user's sense of immersion and the realism of the experience. Furthermore, they are unable to provide personalized content based on the user's emotions and behavior, resulting in a uniform user experience and making it difficult to provide an optimal experience tailored to each user's condition. The present invention aims to solve these problems by providing an olfactory digitization system that provides a more realistic and personalized VR experience.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0309] In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for generating and transmitting a request to generate a specific scent in response to a user's actions and emotions, means for generating scent data using the scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, and means for collecting feedback from users and reflecting it in improving the system and model. This allows for the generation of specific scents in response to the user's actions and emotions, making the experience in the VR space more immersive and realistic.

[0310] "Olfactory data" is information about a particular scent expressed as chemical composition data.

[0311] "Chemical composition data" is olfactory data that has been quantified and expressed in a form that can be stored in a database.

[0312] The "database" is a system for systematically storing and managing collected olfactory data and other related information.

[0313] A "machine learning model" is an algorithm trained to generate specific scents based on collected olfactory data.

[0314] "User actions" refer to specific actions or operations performed by the user within the VR space.

[0315] "Emotion" refers to the psychological state that can be recognized from the user's facial expressions, voice, and behavior.

[0316] A "scent generation model" is an algorithm trained to generate specific scent data.

[0317] A "terminal" is a device that receives olfactory data and controls the scent diffuser.

[0318] An "aroma diffuser" is a device that mixes specific compounds based on aroma data and releases aromas.

[0319] "Feedback" refers to the user's evaluation or opinion based on the scent they experienced, their overall experience, etc.

[0320] The following describes a specific embodiment of a system that combines the olfactory digitization system and emotion engine of the present invention, thereby realizing an immersive and personalized virtual reality (VR) experience for users.

[0321] Data collection and training phase

[0322] The server uses an olfactory sensor to collect data on various scents and obtain their chemical composition. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[0323] User actions, emotion recognition and request generation

[0324] When a user performs a specific action in a game or in the metaverse space, the device detects this and collects corresponding event information. For example, the device detects that the user is entering a virtual cafe. The device then activates its emotion engine and analyzes the user's facial, voice, and movement data to recognize their emotions. For example, it identifies whether the user is enjoying themselves or feeling anxious. The device generates a scent request based on the detected user action and the recognized emotion. For example, it generates a request such as "The user has entered a virtual cafe and is enjoying themselves, so I need the relaxing aroma of coffee," and sends this request to the server.

[0325] Scent generation and transmission

[0326] The server runs a scent generation model based on the received request to generate specific scent data. The generated scent data is converted into an appropriate format and sent back to the device. The device receives the scent data sent from the server. This scent data is used by a scent diffuser built into the device. The device runs the scent diffuser based on the received scent data. The scent diffuser appropriately mixes specific compounds based on the data to generate the actual scent.

[0327] User Experience and Feedback

[0328] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. In addition, scents are generated according to emotions, providing an appropriate scent experience for the user's emotional state. The user evaluates the experience based on the scent generated. For example, the user may feel that the "relaxing coffee aroma was realistic." The device collects user evaluations and feedback and sends it to the server. This feedback is used to improve the system.

[0329] Specific examples

[0330] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device. The device will then use a scent diffuser to recreate these scents, further enhancing the user's sense of realism in the game. As another example, if a user enters a virtual cafe in the metaverse, and the emotion engine recognizes that the user is enjoying themselves based on their facial expressions and actions, the server will generate the relaxing scent of coffee and freshly baked bread and send it to the device. The device will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more real.

[0331] Prompt Sentence Examples

[0332] A user enters a virtual cafe in a VR space, and the emotion engine recognizes this as "fun" based on data collected by the camera and microphone. Please generate a scent request for this action.

[0333] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0334] Step 1:

[0335] The device tracks the user's actions within the VR environment. Specifically, it collects user movement data through the interface and sensors, processes that data, and detects specific actions. For example, when a user enters a virtual cafe, their movements are tracked and event information is collected. Sensor and camera data is used as input, and a list of detected actions is output.

[0336] Step 2:

[0337] The device activates an emotion engine and analyzes the user's facial and voice data, thereby recognizing the user's emotions. Specifically, data is acquired in real time from the camera and microphone installed in the HMD, and the data is analyzed using an emotion recognition algorithm. Facial and voice data are used as input, and the output is a tag of the recognized emotion.

[0338] Step 3:

[0339] The device generates a scent request based on the detected user actions and the recognized emotions. For example, a request may be generated such as, "The user has entered a virtual cafe and is enjoying themselves, so I need a relaxing coffee aroma." This process uses tags representing the user's actions and emotions as input, and outputs a scent request.

[0340] Step 4:

[0341] The device sends the generated scent request to the server. Specifically, it sends the scent request to the server via the Internet and waits for a reply from the server. The scent request is used as input, and the output is the transmission to the server.

[0342] Step 5:

[0343] The server activates the scent generation model based on the received scent request and generates specific scent data. Specifically, it uses a machine learning model on the server to generate a scent corresponding to the request. The scent request is used as input, and the generated scent data is the output.

[0344] Step 6:

[0345] The server returns the generated scent data to the terminal. Specifically, it converts the scent data into an appropriate format and sends it to the terminal. The generated scent data is used as input, and the output is sent to the terminal.

[0346] Step 7:

[0347] The device operates the scent diffuser based on the received scent data. Specifically, it sends the scent data to the scent diffuser, which then mixes specific compounds and releases the scent. The received scent data is used as input, and the output is the actual scent that is generated.

[0348] Step 8:

[0349] The user experiences the scent emitted from the scent diffuser, making the digital experience realistic and immersive. The input is the scent emitted from the diffuser, and the output is the user's experience.

[0350] Step 9:

[0351] The user provides feedback based on the aroma they experienced. For example, they input feedback such as "The relaxing aroma of coffee was realistic." The input is the user's feedback, and the output is the collected ratings and opinions.

[0352] Step 10:

[0353] The device sends the feedback collected from the user to the server. This feedback can be used to improve the system and model in the future. Specifically, the feedback data is sent to the server via the Internet. The user's feedback is used as input, and the output is sent to the server.

[0354] 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.

[0355] 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.

[0356] 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.

[0357] [Second embodiment]

[0358] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0359] 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.

[0360] 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).

[0361] 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.

[0362] 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.

[0363] 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).

[0364] 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.

[0365] 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.

[0366] 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.

[0367] 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.

[0368] 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.

[0369] 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."

[0370] An embodiment of the olfactory digitization system of the present invention will be specifically described below.

[0371] This system consists of a device for collecting and digitizing olfactory data, a device for training a machine learning model based on the collected data, a device for generating and transmitting scent data in response to user actions, and a device for reproducing the scent data as an actual scent.

[0372] Data collection and training phase

[0373] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[0374] User Actions and Request Generation

[0375] When a user performs a specific action in a game or in the metaverse, the device detects it and collects the corresponding event information. For example, when a user enters a virtual cafe, the device generates a request saying "I need the smell of coffee" and sends it to the server. The server receives this request and generates the appropriate scent data.

[0376] Scent generation and transmission

[0377] The server operates the scent generation model based on the received request and generates specific scent data. The generated scent data is converted into an appropriate format and sent to the device. The device generates an actual scent using a scent diffuser based on the received scent data. The scent diffuser mixes specific compounds based on the scent data and releases the scent.

[0378] User Experience and Feedback

[0379] By smelling the generated scent, the user can experience a more realistic and immersive experience. The user's evaluation and feedback of the experience are sent to the server via the device. This feedback is used to improve the accuracy of the scent generation model and the overall system.

[0380] Specific examples

[0381] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device, which will then use a scent diffuser to recreate these scents, enhancing the user's sense of realism in the game.

[0382] As another example, if a user enters a virtual cafe in the metaverse, the server will generate the aroma of coffee or freshly baked bread and send it to the device, which will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more realistic.

[0383] This system provides new value to users by realizing a real-time olfactory experience in digital space, and solves the problem through the means described in the claims.

[0384] The processing flow will be explained below.

[0385] Step 1:

[0386] The server uses an olfactory sensor to collect data on various scents, which is then stored in a database as chemical composition data.

[0387] Step 2:

[0388] The server preprocesses the stored chemical composition data, removing impurities and noise and streamlining the dataset to obtain high-quality data.

[0389] Step 3:

[0390] The server trains a machine learning model on the pre-processed data, using machine learning algorithms to learn patterns from the data and build a model capable of generating specific scents.

[0391] Step 4:

[0392] When a user performs a specific action in a game or in the Metaverse space, the device detects this action through sensors and interfaces, for example, when the user enters a virtual cafe.

[0393] Step 5:

[0394] The device generates a scent request based on the detected user action, for example, "I need the scent of coffee," and sends this request to the server.

[0395] Step 6:

[0396] The server runs the scent generation model based on the received request, generates the necessary scent data, converts it into an appropriate format, and sends it back to the device.

[0397] Step 7:

[0398] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[0399] Step 8:

[0400] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[0401] Step 9:

[0402] Users smell the scent emitted from the scent diffuser, making the digital experience feel realistic and immersive.

[0403] Step 10:

[0404] Users rate their experience based on the aromas they experience, for example, feeling that the coffee aroma was realistic.

[0405] Step 11:

[0406] The device collects user ratings and feedback and sends it to the server, which uses the feedback to improve the system.

[0407] Step 12:

[0408] The server analyzes user feedback and improves the scent generation model and the entire system, for example, by improving the accuracy of the scent generation algorithm.

[0409] The above is a detailed explanation of the processing steps of the Smell Tech system.

[0410] Example 1

[0411] 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."

[0412] Previous olfactory experiences in virtual spaces and games were limited, making it difficult for users to achieve a deeper sense of immersion through their sense of smell. Furthermore, the accuracy of scent generation and reproduction was low, and there was a lack of effective ways to utilize user feedback to improve the system. Furthermore, the entire process from data collection to reproduction was inefficient. This limited the quality of the user experience and made it difficult to provide new olfactory experiences.

[0413] 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.

[0414] In this invention, the server includes a means for collecting olfactory data and storing it in a database as chemical composition data, a means for training a machine learning model based on the olfactory data, and a cloud storage means for storing comprehensive scent data, thereby enabling highly accurate reproduction of scents and improving user experience.

[0415] The terminal also includes a means for detecting specific events and sending them to the server in a request format, a means for receiving scent data at the terminal and generating an actual scent using the scent diffuser, and a communication means for linking the terminal and the scent diffuser, thereby enabling scent generation in real time in response to user actions.

[0416] Furthermore, the system includes a means for collecting user feedback and reflecting it in improvements to the system and model, allowing for continuous system improvement based on the collected feedback, thereby providing a more advanced olfactory experience.

[0417] "Olfactory data" refers to data obtained by an olfactory sensor about the molecular components and chemical composition associated with a particular scent.

[0418] "Chemical composition data" is a part of olfactory data, and is information that includes the molecules that make up a particular scent and their proportions.

[0419] A "database" is a storage system that systematically stores olfactory data and chemical composition data, allowing for efficient access and searching.

[0420] A "machine learning model" is an algorithm that learns patterns from large amounts of data and automatically performs specific tasks.

[0421] "Cloud storage" is a service that stores data on the Internet and is a means of efficiently storing large amounts of data.

[0422] A "terminal" is a device that a user operates via an interface, and is a device that generates requests and reproduces scents.

[0423] A "request" is a request that includes event information corresponding to a user action, and is information that is sent to a server.

[0424] An "aroma generation model" is a machine learning model trained to generate aromas based on specific chemical composition data.

[0425] "Communication means" refers to a network connection means for linking the terminal and the server, or the terminal and the scent diffuser.

[0426] An "aroma diffuser" is a device that physically reproduces a specific scent based on scent data.

[0427] "Feedback" refers to user-provided information about experience ratings and areas for improvement, and is data used to improve the system.

[0428] A "server" is a computer system that centrally collects, stores, analyzes, processes, and distributes olfactory data.

[0429] A "user action" is an event that occurs on the interface when a user performs a specific action or operation.

[0430] MODE FOR CARRYING OUT THE INVENTION

[0431] System Overview

[0432] The present invention consists of a device that collects and digitizes olfactory data, a device that trains a machine learning model based on the collected data, a device that generates and transmits scent data in response to user actions, and a device that reproduces the scent data as an actual scent.

[0433] Data Collection and Machine Learning

[0434] The server collects various scent samples using an olfactory sensor (e.g., an electronic nose) and obtains their chemical composition data. This data is stored in a database. The server uses machine learning libraries such as TensorFlow and PyTorch to train a scent generation model based on the collected data. Comprehensive scent data is stored in cloud storage (e.g., AWS S3 or Google Cloud Storage).

[0435] User action detection and request generation

[0436] When a user performs a specific action in the game or metaverse space, the device detects this through sensors and interfaces and collects corresponding event information. The device generates a request that says "the user has entered the virtual cafe" and sends it to the server. The request is sent to the server in JSON or XML format.

[0437] Generation and transmission of scent data

[0438] The server analyzes requests received from the device and generates scent data corresponding to specific events using a trained machine learning model. The generated scent data is sent to the device in JSON or XML format.

[0439] Fragrance reproduction and user experience

[0440] The device analyzes the received scent data and sends it to the scent diffuser, which then mixes specific compounds based on the scent data to create a realistic scent that the user can smell, providing a more realistic and immersive experience.

[0441] Gathering feedback and improving the system

[0442] The user's impressions and evaluations of the experience are sent to the server via the device, and this feedback is stored in a database and used to improve the scent generation model and optimize the entire system.

[0443] Specific examples

[0444] For example, if a user steps into an ancient temple in an adventure game, the device detects this action and requests "ancient temple scent data" from the server. The server generates scent data of damp stone and old books and sends it to the device. The device then controls a scent diffuser to reproduce these scents. By smelling these scents, the user can further enhance the sense of realism within the game.

[0445] When a user enters a virtual cafe in the metaverse, the server generates aroma data for coffee and freshly baked bread and sends it to the device, which then uses a scent diffuser to recreate the aroma, making the user's experience in the virtual space feel more realistic.

[0446] Prompt Sentence Examples

[0447] "Generate the aroma of coffee as you enter a virtual cafe."

[0448] "Recreate the scent of damp stone for a scene in an adventure game where you enter an ancient temple."

[0449] "Create a sea salt scent that wafts through the air when users are on a virtual beach."

[0450] This system provides a real-time olfactory experience, bringing new value to users.

[0451] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0452] Step 1:

[0453] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. Specifically, the electronic nose sensor captures the molecular components of the scent and records them as digital data. The server then stores this data in a database as chemical composition data.

[0454] Input: Scent sample

[0455] Data processing: Digitalization of chemical components through sensing

[0456] Output: Chemical composition data

[0457] Step 2:

[0458] The server uses a machine learning algorithm based on the collected data to train a scent generation model. The server uses machine learning libraries such as TensorFlow and PyTorch, and uses the chemical composition data and meta-information about the scent (such as name, category, and intensity) as training data. The scent generation model is saved in cloud storage.

[0459] Input: Chemical composition data, meta information

[0460] Data Computation: Training with Machine Learning Algorithms

[0461] Output: Scent generation model

[0462] Step 3:

[0463] When a user performs a specific action in the game or in the metaverse space, the device detects this through sensors and interfaces and collects event information. The device generates event information such as "the user has entered a virtual cafe" and sends it to the server in the form of a request.

[0464] Input: User action

[0465] Data processing: action detection and event information generation

[0466] Output: Event-based request

[0467] Step 4:

[0468] The server receives the request sent from the device and analyzes the content. The server generates scent data corresponding to the event using the trained scent generation model. For example, the server generates coffee scent data for the event of entering a "virtual cafe." The scent data is then sent to the device.

[0469] Input: Event-based request

[0470] Data computation: Generation of scent data using scent generation models

[0471] Output: Scent data

[0472] Step 5:

[0473] The device analyzes the scent data received from the server and sends it to the scent diffuser, which then mixes specific compounds based on the scent data to create the actual scent.The device controls the scent diffuser using Bluetooth or Wi-Fi.

[0474] Input: Scent data

[0475] Data processing: Data analysis and transmission to the diffuser

[0476] Output: The actual scent generated

[0477] Step 6:

[0478] The user smells the generated scent and provides feedback on their experience. The device collects the user's feedback data and sends it to the server, which stores it in a database and uses it to improve the scent generation model and optimize the entire system.

[0479] Input: User feedback

[0480] Data Processing: Collecting and Sending Feedback

[0481] Output: Improved model and system optimization

[0482] (Application example 1)

[0483] 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."

[0484] Conventional content distribution services have focused on providing immersive experiences through video and audio, but incorporating the sense of smell has made it difficult to provide users with a more realistic and immersive experience. Furthermore, the development of systems that generate scents in real time and dynamically change them in response to user actions has also remained immature. To address this issue, a system that digitizes the sense of smell and enriches users' content viewing experiences is needed.

[0485] 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.

[0486] In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for generating and transmitting a request to generate a specific scent in response to a user's actions, means for generating scent data using the scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, means for collecting user feedback and reflecting it in improving the system and model, and means for generating and providing a scent tailored to a specific scene in real time while the user is viewing content. This provides a realistic scent experience in response to the user's actions, enabling a more immersive content viewing experience.

[0487] "Olfaction data" is digitalized information about scents that a user perceives through their sense of smell.

[0488] "Chemical composition data" refers to data on the composition of molecules and compounds used to reproduce a scent.

[0489] A "database" is an information management system that efficiently stores information such as olfactory data and chemical composition data, and enables searching and retrieval.

[0490] A "machine learning model" is a collection of algorithms that learn patterns from large amounts of data and generate and predict scents.

[0491] A "request" is a request sent to the server to generate a specific scent based on a user action.

[0492] A "terminal" is a device that is directly operated by the user to generate requests, receive scent data, and control the scent diffuser.

[0493] The "fragrance generation model" is a method for generating specific fragrances as digital data using a machine learning model.

[0494] "Scent data" is digital information for reproducing a specific scent generated by the scent generation model.

[0495] A "fragrance diffuser" is a device that physically generates and releases an actual scent based on scent data.

[0496] A "user action" is an operation or movement that a user performs through a terminal, which triggers the generation of a request.

[0497] "Feedback" refers to the user's evaluations and opinions about the scent they have experienced, and is information used to improve the system and the accuracy of the model.

[0498] "Content viewing" refers to the act of a user viewing video, audio, or other media content.

[0499] MODE FOR CARRYING OUT THE INVENTION

[0500] System Overview

[0501] This system consists of a series of processes that collect olfactory data, digitize it, generate scents using machine learning models, and provide the scents in real time during the user's content viewing experience. Specifically, a server, terminal, and scent diffuser work together.

[0502] Data collection and training phase

[0503] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. This data is stored in a database and used to train a machine learning model. Based on the collected data, the server trains a scent generation model using a machine learning algorithm (e.g., RandomForestRegressor using Scikit-learn), thereby improving its ability to reproduce specific scents.

[0504] User Actions and Request Generation

[0505] When a user is watching content on a smartphone or head-mounted display and a specific action (e.g., a scene change in a movie) occurs, the device detects this. The device's application generates a request for the scent of wet earth and sends it to the server. The server receives this request and generates the corresponding scent data.

[0506] Scent generation and transmission

[0507] The server operates the scent generation model based on the received request and generates specific scent data. The generated scent data is then converted into an appropriate format and sent to the terminal. The terminal then generates and releases an actual scent using a scent diffuser based on the received scent data. The scent diffuser then mixes specific compounds based on the scent data and releases the scent.

[0508] Feedback and System Improvement

[0509] By smelling the generated scent, the user can experience a more realistic and immersive experience. The user's evaluation and feedback of the experience are sent to the server via the device. This feedback is used to improve the accuracy of the scent generation model and the overall system.

[0510] Specific examples

[0511] For example, if a user is using the "Olfactory Cinema Experience App" to watch a movie and the scene switches to a rainy scene, the system will generate data on the scent of "wet earth" and send it to the device. The device's scent diffuser will then release the scent in real time based on this data, providing the user with a more immersive viewing experience.

[0512] Example prompts for generative AI models

[0513] Prompt: Create a scent that matches a scene from this movie. Scene: "Jungle at night", Desired scent: "The scent of damp vegetation"

[0514] This allows users to enjoy the content both visually and olfactory.

[0515] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0516] Step 1:

[0517] The server collects olfactory data. It uses an olfactory sensor to obtain various scent samples as olfactory data, and stores the chemical composition data in a database. The input is the scent sample from the olfactory sensor, and the output is stored in the database as chemical composition data.

[0518] Step 2:

[0519] The server trains a machine learning model based on the collected chemical composition data. Specifically, it uses Scikit-learn to train a RandomForestRegressor model to improve its ability to reproduce specific scents. The input is the chemical composition data stored in the database, and the output is the trained machine learning model.

[0520] Step 3:

[0521] When a user performs a specific action (e.g., scene change) while watching content on a device, the device detects this. The device detects the user's behavior through sensors and interfaces and collects event information. The input is the user's action, and the output is event information.

[0522] Step 4:

[0523] The device generates a request to generate a specific scent based on the collected event information and sends it to the server. For example, if a user watches a rainy scene in a movie, the device generates a request saying, "I need the scent of wet earth." The input is the event information, and the output is a scent generation request.

[0524] Step 5:

[0525] The server runs the scent generation model based on the received request. It uses the trained machine learning model to generate specific scent data and sends it to the device. The input is the scent generation request, and the output is the scent data.

[0526] Step 6:

[0527] The device generates the actual scent using a scent diffuser based on the scent data received from the server. The diffuser mixes the specified chemical ingredients and releases the scent. The input is scent data, and the output is a physical scent.

[0528] Step 7:

[0529] By smelling the generated scent, the user experiences the realism of watching content. The user then inputs their evaluation and feedback about the experience into the device, which then sends this to the server. The input is the user's feedback, and the output is the feedback data.

[0530] Step 8:

[0531] The server collects feedback data from users and reflects it in improving the system and machine learning model. The input is the feedback data, and the output is an improved system or model.

[0532] 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.

[0533] A system combining the olfactory digitization system and emotion engine of the present invention will be described below in detail with reference to an embodiment thereof.

[0534] This system consists of a device for collecting and digitizing olfactory data, a device for recognizing user emotions using an emotion engine, a device for training a machine learning model based on the collected data, a device for generating and transmitting scent data in response to user actions and emotions, and a device for reproducing the scent data as an actual scent.

[0535] Data collection and training phase

[0536] The server uses an olfactory sensor to collect data on various scents and obtain their chemical composition. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[0537] User actions, emotion recognition and request generation

[0538] When a user performs a specific action in a game or in the Metaverse space, the device detects this and collects corresponding event information. For example, a user entering a virtual cafe can be detected.

[0539] The device then activates an emotion engine that analyzes the user's facial, voice, and movement data to recognize their emotions, for example, whether they are feeling happy or anxious.

[0540] The device generates a scent request based on the detected user actions and the recognized emotions. For example, it generates a request such as "The user has entered a virtual cafe and is enjoying themselves, so I need the relaxing aroma of coffee." The request is then sent to the server.

[0541] Scent generation and transmission

[0542] The server runs the scent generation model based on the received request to generate specific scent data, which is then converted into an appropriate format and sent back to the device.

[0543] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[0544] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[0545] User Experience and Feedback

[0546] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. Furthermore, the scent is generated according to the user's emotional state, providing a scent experience appropriate to the user's emotional state.

[0547] Users rate their experience based on the aromas they experience, for example, feeling that the aroma of coffee was "realistic and relaxing."

[0548] The device collects user ratings and feedback and sends it to the server, which uses the feedback to improve the system.

[0549] Specific examples

[0550] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device, which will then use a scent diffuser to recreate these scents, enhancing the user's sense of realism in the game.

[0551] As another example, if a user enters a virtual cafe in the metaverse, and the emotion engine recognizes that the user is enjoying themselves based on their facial expressions and actions, the server will generate the relaxing aroma of coffee or freshly baked bread and send it to the device. The device will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more realistic.

[0552] This system provides new value to users by realizing a real-time olfactory experience in digital space, and solves the problem through the means described in the claims.

[0553] The processing flow will be explained below.

[0554] Step 1:

[0555] The server uses an olfactory sensor to collect data on various scents, which is then stored in a database as chemical composition data.

[0556] Step 2:

[0557] The server preprocesses the stored chemical composition data, removing impurities and noise and streamlining the dataset to obtain high-quality data.

[0558] Step 3:

[0559] The server trains a machine learning model on the pre-processed data, using machine learning algorithms to learn patterns from the data and build a model capable of generating specific scents.

[0560] Step 4:

[0561] A user performs a specific action in the game or metaverse space, such as reaching a specific location in the game or using a specific item.

[0562] Step 5:

[0563] The device detects user actions through sensors and interfaces, such as when a user enters a virtual cafe.

[0564] Step 6:

[0565] The device runs an emotion engine that analyzes the user's facial, voice, and movement data to recognize emotions, for example, whether the user is feeling happy or anxious.

[0566] Step 7:

[0567] The device generates a scent request based on the detected user actions and the recognized emotions, for example, "The user has entered a virtual cafe and is enjoying themselves, so the relaxing aroma of coffee is needed."

[0568] Step 8:

[0569] The terminal transmits the generated scent request to the server.

[0570] Step 9:

[0571] The server runs the scent generation model based on the received request, generates the necessary scent data, converts it into an appropriate format, and sends it back to the device.

[0572] Step 10:

[0573] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[0574] Step 11:

[0575] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[0576] Step 12:

[0577] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. Furthermore, the scent is generated according to the user's emotional state, providing a scent experience appropriate to the user's emotional state.

[0578] Step 13:

[0579] Users rate their experience based on the aromas they experience, for example, feeling that the aroma of coffee was "realistic and relaxing."

[0580] Step 14:

[0581] The device collects user ratings and feedback and sends it to the server.

[0582] Step 15:

[0583] The server analyzes user feedback and improves the scent generation model and the entire system, for example, by improving the accuracy of the scent generation algorithm.

[0584] The above is a detailed step-by-step explanation of the processing flow of the Smell Tech system.

[0585] Example 2

[0586] 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."

[0587] In modern digital experiences and virtual spaces, there is a demand for comprehensive experiences that include not only sight and sound, but also smell. However, existing technologies lack the ability to digitalize the sense of smell or generate scents that respond to the user's emotions, making it difficult to achieve an immersive or realistic experience. In addition, there are limited methods for effectively collecting user feedback and incorporating it into systems and machine learning models.

[0588] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for detecting a user's actions and analyzing the actions and the user's emotions, means for generating and transmitting a request to generate a specific scent based on the analysis results, means for generating scent data using a scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, and means for collecting user feedback and reflecting it in improving the system and model. This makes it possible to generate and reproduce scents in real time according to the user's actions and emotions, realize an olfactory experience in a digital space, and utilize user feedback to continuously improve the system.

[0589] "Olfactory data" is data that quantifies and digitizes information about scents and odors, and includes information about chemical composition and ingredients.

[0590] "Chemical composition data" is data that indicates the types and proportions of chemical components contained in a specific fragrance or substance.

[0591] The "database" is an information recording system for storing and managing collected olfactory data and chemical composition data.

[0592] A "machine learning model" is an algorithm that learns patterns based on collected data and makes predictions and classifications for new inputs.

[0593] "User actions" refer to operations or movements that a user makes within a digital or virtual environment.

[0594] "Emotion analysis" is the process of determining a user's emotional state from data such as facial expressions, voice, and movements.

[0595] A "scent request" is a request to instruct the system to generate a particular scent.

[0596] A "scent generation model" is a machine learning model trained to generate a specific scent as digital data.

[0597] "Scent data" refers to data that includes specific chemical components and their blending ratios for reproducing the created scent.

[0598] A "terminal" is an electronic device or device that allows a user to access a digital space or virtual environment.

[0599] An "aroma diffuser" is a device that generates and releases actual scents based on scent data.

[0600] "Feedback" is information that provides the system with the user's evaluation and opinions regarding the scent they experienced.

[0601] "System improvement" refers to improving the performance and functionality of a system based on collected feedback.

[0602] This invention is a system that combines an olfactory digitization system and an emotion engine, allowing users to experience not only sight and hearing but also smell in digital or virtual environments. The present invention provides a system that comprehensively executes a series of processes from collecting olfactory data to generating scents and recognizing the user's emotions.

[0603] First, the server uses an olfactory sensor to collect data on various scents and obtain their chemical composition data. The specific hardware used includes various types of sensors. For example, olfactory sensors include gas sensors and electrochemical sensors that accurately measure chemical composition. This data is collected using a Python script and stored in a database (e.g., MySQL or PostgreSQL).

[0604] The server then trains a machine learning model based on the collected olfactory data. Specifically, it uses Python's scikit-learn and TensorFlow libraries to build and train a model based on the collected chemical composition data. For example, it uses a random forest algorithm or a neural network to learn specific scent generation patterns.

[0605] When a user performs a specific action in a digital space (e.g., a game or the Metaverse), the device (PC, smartphone, VR device, etc.) detects the action. Here, a script in a game engine based on Unity or Unreal Engine runs to monitor and detect the user's location and actions. For example, if a user is detected entering a virtual cafe, this information is registered as an event.

[0606] The device then uses an emotion engine to analyze the user's facial, voice, and movement data to recognize their emotions. Specifically, it uses the camera to analyze facial expressions using the OpenCV library and sends the data to the Microsoft Azure Face API to obtain the analysis results. At the same time, it collects voice data through the microphone and performs voice analysis using Google Cloud Speech-to-Text. This allows it to recognize the user's emotional state, such as whether they are happy or anxious.

[0607] The device generates a scent request based on the results of the above sentiment analysis and the user's actions. For example, a request such as "The user has entered a virtual cafe and is enjoying themselves, so they need a relaxing coffee aroma" is generated in JSON format and sent to the server. An example of a prompt sentence is:

[0608] A request is sent to the server saying, "The emotion engine has recognized that the user has entered a cafe in a virtual space and is enjoying themselves. Please generate scent data that has a relaxing effect."

[0609] The server then runs a scent generation model based on the received request to generate specific scent data. For example, it uses TensorFlow to generate the scent data and sends it back to the device in JSON or binary format. This scent data is formatted to include specific chemical component information.

[0610] The device receives the scent data sent from the server and sends it to the scent diffuser. The scent diffuser then mixes specific compounds based on the scent data to create the actual scent. Specific devices that can be connected via Bluetooth or Wi-Fi are used. For example, by using a smart device made by Scentee, the appropriate mixture of chemical components is created to recreate the relaxing aroma of coffee.

[0611] Users experience the scent emitted from the scent diffuser, making their digital experience more realistic and immersive. They also provide feedback on their scent experience through an application on their device. For example, a user might write a review such as, "The relaxing coffee aroma was very realistic." This feedback is temporarily stored on the device and later sent to a server. The server analyzes this feedback and uses it to improve the system and machine learning models.

[0612] As described above, the present invention provides a system that realizes a real-time olfactory experience in a digital space and enables the generation of scents according to the user's actions and emotions. Furthermore, by utilizing user feedback and continuously improving the system, it is possible to provide a higher quality olfactory experience.

[0613] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0614] Step 1:

[0615] The server collects scent data using an olfactory sensor. The olfactory sensor (e.g., a gas sensor or electrochemical sensor) is used to obtain chemical composition data of specific scents in real time. The obtained data is converted into CSV format using a Python script and sent to the server. The inputs are scent samples and sensor measurement results. The output is chemical composition data as a CSV file.

[0616] Step 2:

[0617] The server stores the collected chemical composition data in a database, using MySQL or PostgreSQL. The stored data is organized for later use in model training. The CSV file obtained in step 1 is used as input, and the data stored in the database is generated as output.

[0618] Step 3:

[0619] The server trains a machine learning model based on the stored chemical composition data. It uses Python's scikit-learn and TensorFlow libraries to build a scent generation model. Specifically, it uses a random forest algorithm and neural networks to train a model capable of reproducing a specific scent. The input is chemical composition data obtained from the database, and the output is a trained machine learning model.

[0620] Step 4:

[0621] When a user performs a specific action in the digital space, the device detects that action. Using scripts in game engines such as Unity or Unreal Engine, the device monitors the user's location and movements. For example, a user entering a virtual cafe is detected. The input is information about the user's action, and the output is event information generated for the specific action performed by the user.

[0622] Step 5:

[0623] The device collects the user's facial expression, voice, and movement data to recognize emotions. The specific technology used is to analyze facial expressions using a camera and the OpenCV library, and send the data to the Microsoft Azure Face API to obtain the analysis results. Voice data is analyzed using a microphone with Google Cloud Speech-to-Text. The input is the user's facial expression data, voice data, and movement data, and the output is the user's emotional state.

[0624] Step 6:

[0625] The device generates a scent request based on the user's actions and the results of emotion recognition. The scent request includes the specific action performed by the user and instructions for the scent based on the recognized emotion. The input is the event information of the user's actions and the results of emotion recognition. The output is a request to generate a specific scent in JSON format, which is sent to the server.

[0626] Step 7:

[0627] The server generates scent data based on the received scent request using a scent generation model. It runs a TensorFlow model to generate the specified scent chemical components. The input is the scent request and the machine learning model, and the output is the generated scent data in JSON format.

[0628] Step 8:

[0629] The server sends the generated scent data to the terminal. The scent data is transmitted to the terminal via the network and received by the terminal. The input is the generated scent data, and the output includes the scent data sent to the terminal.

[0630] Step 9:

[0631] The device generates an actual scent using a scent diffuser based on the received scent data. The device transmits the data to the scent diffuser, which mixes specific compounds based on the data and releases the scent. The input is the received scent data, and the output is a physically reproduced scent.

[0632] Step 10:

[0633] The user experiences the released scent and provides feedback. They input their evaluation and opinions about the scent experience through an application on their device. The input is the user's feedback, and the output is the collected feedback information.

[0634] Step 11:

[0635] The device stores the user's feedback and later transmits it to the server. The feedback is reflected in the system's improvements and is used to generate future scents. The input is the user's feedback information, and the output includes the feedback transmitted to the server.

[0636] Through these steps, this system provides a real-time olfactory experience in the digital space and can generate and reproduce scents according to the user's emotions.

[0637] (Application example 2)

[0638] 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."

[0639] Conventional virtual reality (VR) experiences and metaverse spaces rely solely on sight and hearing, limiting the user's sense of immersion and the realism of the experience. Furthermore, they are unable to provide personalized content based on the user's emotions and behavior, resulting in a uniform user experience and making it difficult to provide an optimal experience tailored to each user's condition. The present invention aims to solve these problems by providing an olfactory digitization system that provides a more realistic and personalized VR experience.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0641] In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for generating and transmitting a request to generate a specific scent in response to a user's actions and emotions, means for generating scent data using the scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, and means for collecting feedback from users and reflecting it in improving the system and model. This allows for the generation of specific scents in response to the user's actions and emotions, making the experience in the VR space more immersive and realistic.

[0642] "Olfactory data" is information about a particular scent expressed as chemical composition data.

[0643] "Chemical composition data" is olfactory data that has been quantified and expressed in a form that can be stored in a database.

[0644] The "database" is a system for systematically storing and managing collected olfactory data and other related information.

[0645] A "machine learning model" is an algorithm trained to generate specific scents based on collected olfactory data.

[0646] "User actions" refer to specific actions or operations performed by the user within the VR space.

[0647] "Emotion" refers to the psychological state that can be recognized from the user's facial expressions, voice, and behavior.

[0648] A "scent generation model" is an algorithm trained to generate specific scent data.

[0649] A "terminal" is a device that receives olfactory data and controls the scent diffuser.

[0650] An "aroma diffuser" is a device that mixes specific compounds based on aroma data and releases aromas.

[0651] "Feedback" refers to the user's evaluation or opinion based on the scent they experienced, their overall experience, etc.

[0652] The following describes a specific embodiment of a system that combines the olfactory digitization system and emotion engine of the present invention, thereby realizing an immersive and personalized virtual reality (VR) experience for users.

[0653] Data collection and training phase

[0654] The server uses an olfactory sensor to collect data on various scents and obtain their chemical composition. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[0655] User actions, emotion recognition and request generation

[0656] When a user performs a specific action in a game or in the metaverse space, the device detects this and collects corresponding event information. For example, the device detects that the user is entering a virtual cafe. The device then activates its emotion engine and analyzes the user's facial, voice, and movement data to recognize their emotions. For example, it identifies whether the user is enjoying themselves or feeling anxious. The device generates a scent request based on the detected user action and the recognized emotion. For example, it generates a request such as "The user has entered a virtual cafe and is enjoying themselves, so I need the relaxing aroma of coffee," and sends this request to the server.

[0657] Scent generation and transmission

[0658] The server runs a scent generation model based on the received request to generate specific scent data. The generated scent data is converted into an appropriate format and sent back to the device. The device receives the scent data sent from the server. This scent data is used by a scent diffuser built into the device. The device runs the scent diffuser based on the received scent data. The scent diffuser appropriately mixes specific compounds based on the data to generate the actual scent.

[0659] User Experience and Feedback

[0660] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. In addition, scents are generated according to emotions, providing an appropriate scent experience for the user's emotional state. The user evaluates the experience based on the scent generated. For example, the user may feel that the "relaxing coffee aroma was realistic." The device collects user evaluations and feedback and sends it to the server. This feedback is used to improve the system.

[0661] Specific examples

[0662] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device. The device will then use a scent diffuser to recreate these scents, further enhancing the user's sense of realism in the game. As another example, if a user enters a virtual cafe in the metaverse, and the emotion engine recognizes that the user is enjoying themselves based on their facial expressions and actions, the server will generate the relaxing scent of coffee and freshly baked bread and send it to the device. The device will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more real.

[0663] Prompt Sentence Examples

[0664] A user enters a virtual cafe in a VR space, and the emotion engine recognizes this as "fun" based on data collected by the camera and microphone. Please generate a scent request for this action.

[0665] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0666] Step 1:

[0667] The device tracks the user's actions within the VR environment. Specifically, it collects user movement data through the interface and sensors, processes that data, and detects specific actions. For example, when a user enters a virtual cafe, their movements are tracked and event information is collected. Sensor and camera data is used as input, and a list of detected actions is output.

[0668] Step 2:

[0669] The device activates an emotion engine and analyzes the user's facial and voice data, thereby recognizing the user's emotions. Specifically, data is acquired in real time from the camera and microphone installed in the HMD, and the data is analyzed using an emotion recognition algorithm. Facial and voice data are used as input, and the output is a tag of the recognized emotion.

[0670] Step 3:

[0671] The device generates a scent request based on the detected user actions and the recognized emotions. For example, a request may be generated such as, "The user has entered a virtual cafe and is enjoying themselves, so I need a relaxing coffee aroma." This process uses tags representing the user's actions and emotions as input, and outputs a scent request.

[0672] Step 4:

[0673] The device sends the generated scent request to the server. Specifically, it sends the scent request to the server via the Internet and waits for a reply from the server. The scent request is used as input, and the output is the transmission to the server.

[0674] Step 5:

[0675] The server activates the scent generation model based on the received scent request and generates specific scent data. Specifically, it uses a machine learning model on the server to generate a scent corresponding to the request. The scent request is used as input, and the generated scent data is the output.

[0676] Step 6:

[0677] The server returns the generated scent data to the terminal. Specifically, it converts the scent data into an appropriate format and sends it to the terminal. The generated scent data is used as input, and the output is sent to the terminal.

[0678] Step 7:

[0679] The device operates the scent diffuser based on the received scent data. Specifically, it sends the scent data to the scent diffuser, which then mixes specific compounds and releases the scent. The received scent data is used as input, and the output is the actual scent that is generated.

[0680] Step 8:

[0681] The user experiences the scent emitted from the scent diffuser, making the digital experience realistic and immersive. The input is the scent emitted from the diffuser, and the output is the user's experience.

[0682] Step 9:

[0683] The user provides feedback based on the aroma they experienced. For example, they input feedback such as "The relaxing aroma of coffee was realistic." The input is the user's feedback, and the output is the collected ratings and opinions.

[0684] Step 10:

[0685] The device sends the feedback collected from the user to the server. This feedback can be used to improve the system and model in the future. Specifically, the feedback data is sent to the server via the Internet. The user's feedback is used as input, and the output is sent to the server.

[0686] 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.

[0687] 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.

[0688] 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.

[0689] [Third embodiment]

[0690] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0691] 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.

[0692] 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).

[0693] 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.

[0694] 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.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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.

[0699] 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.

[0700] 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.

[0701] 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."

[0702] An embodiment of the olfactory digitization system of the present invention will be specifically described below.

[0703] This system consists of a device for collecting and digitizing olfactory data, a device for training a machine learning model based on the collected data, a device for generating and transmitting scent data in response to user actions, and a device for reproducing the scent data as an actual scent.

[0704] Data collection and training phase

[0705] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[0706] User Actions and Request Generation

[0707] When a user performs a specific action in a game or in the metaverse, the device detects it and collects the corresponding event information. For example, when a user enters a virtual cafe, the device generates a request saying "I need the smell of coffee" and sends it to the server. The server receives this request and generates the appropriate scent data.

[0708] Scent generation and transmission

[0709] The server operates the scent generation model based on the received request and generates specific scent data. The generated scent data is converted into an appropriate format and sent to the device. The device generates an actual scent using a scent diffuser based on the received scent data. The scent diffuser mixes specific compounds based on the scent data and releases the scent.

[0710] User Experience and Feedback

[0711] By smelling the generated scent, the user can experience a more realistic and immersive experience. The user's evaluation and feedback of the experience are sent to the server via the device. This feedback is used to improve the accuracy of the scent generation model and the overall system.

[0712] Specific examples

[0713] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device, which will then use a scent diffuser to recreate these scents, enhancing the user's sense of realism in the game.

[0714] As another example, if a user enters a virtual cafe in the metaverse, the server will generate the aroma of coffee or freshly baked bread and send it to the device, which will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more realistic.

[0715] This system provides new value to users by realizing a real-time olfactory experience in digital space, and solves the problem through the means described in the claims.

[0716] The processing flow will be explained below.

[0717] Step 1:

[0718] The server uses an olfactory sensor to collect data on various scents, which is then stored in a database as chemical composition data.

[0719] Step 2:

[0720] The server preprocesses the stored chemical composition data, removing impurities and noise and streamlining the dataset to obtain high-quality data.

[0721] Step 3:

[0722] The server trains a machine learning model on the pre-processed data, using machine learning algorithms to learn patterns from the data and build a model capable of generating specific scents.

[0723] Step 4:

[0724] When a user performs a specific action in a game or in the Metaverse space, the device detects this action through sensors and interfaces, for example, when the user enters a virtual cafe.

[0725] Step 5:

[0726] The device generates a scent request based on the detected user action, for example, "I need the scent of coffee," and sends this request to the server.

[0727] Step 6:

[0728] The server runs the scent generation model based on the received request, generates the necessary scent data, converts it into an appropriate format, and sends it back to the device.

[0729] Step 7:

[0730] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[0731] Step 8:

[0732] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[0733] Step 9:

[0734] Users smell the scent emitted from the scent diffuser, making the digital experience feel realistic and immersive.

[0735] Step 10:

[0736] Users rate their experience based on the aromas they experience, for example, feeling that the coffee aroma was realistic.

[0737] Step 11:

[0738] The device collects user ratings and feedback and sends it to the server, which uses the feedback to improve the system.

[0739] Step 12:

[0740] The server analyzes user feedback and improves the scent generation model and the entire system, for example, by improving the accuracy of the scent generation algorithm.

[0741] The above is a detailed explanation of the processing steps of the Smell Tech system.

[0742] Example 1

[0743] 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."

[0744] Previous olfactory experiences in virtual spaces and games were limited, making it difficult for users to achieve a deeper sense of immersion through their sense of smell. Furthermore, the accuracy of scent generation and reproduction was low, and there was a lack of effective ways to utilize user feedback to improve the system. Furthermore, the entire process from data collection to reproduction was inefficient. This limited the quality of the user experience and made it difficult to provide new olfactory experiences.

[0745] 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.

[0746] In this invention, the server includes a means for collecting olfactory data and storing it in a database as chemical composition data, a means for training a machine learning model based on the olfactory data, and a cloud storage means for storing comprehensive scent data, thereby enabling highly accurate reproduction of scents and improving user experience.

[0747] The terminal also includes a means for detecting specific events and sending them to the server in a request format, a means for receiving scent data at the terminal and generating an actual scent using the scent diffuser, and a communication means for linking the terminal and the scent diffuser, thereby enabling scent generation in real time in response to user actions.

[0748] Furthermore, the system includes a means for collecting user feedback and reflecting it in improvements to the system and model, allowing for continuous system improvement based on the collected feedback, thereby providing a more advanced olfactory experience.

[0749] "Olfactory data" refers to data obtained by an olfactory sensor about the molecular components and chemical composition associated with a particular scent.

[0750] "Chemical composition data" is a part of olfactory data, and is information that includes the molecules that make up a particular scent and their proportions.

[0751] A "database" is a storage system that systematically stores olfactory data and chemical composition data, allowing for efficient access and searching.

[0752] A "machine learning model" is an algorithm that learns patterns from large amounts of data and automatically performs specific tasks.

[0753] "Cloud storage" is a service that stores data on the Internet and is a means of efficiently storing large amounts of data.

[0754] A "terminal" is a device that a user operates via an interface, and is a device that generates requests and reproduces scents.

[0755] A "request" is a request that includes event information corresponding to a user action, and is information that is sent to a server.

[0756] An "aroma generation model" is a machine learning model trained to generate aromas based on specific chemical composition data.

[0757] "Communication means" refers to a network connection means for linking the terminal and the server, or the terminal and the scent diffuser.

[0758] An "aroma diffuser" is a device that physically reproduces a specific scent based on scent data.

[0759] "Feedback" refers to user-provided information about experience ratings and areas for improvement, and is data used to improve the system.

[0760] A "server" is a computer system that centrally collects, stores, analyzes, processes, and distributes olfactory data.

[0761] A "user action" is an event that occurs on the interface when a user performs a specific action or operation.

[0762] MODE FOR CARRYING OUT THE INVENTION

[0763] System Overview

[0764] The present invention consists of a device that collects and digitizes olfactory data, a device that trains a machine learning model based on the collected data, a device that generates and transmits scent data in response to user actions, and a device that reproduces the scent data as an actual scent.

[0765] Data Collection and Machine Learning

[0766] The server collects various scent samples using an olfactory sensor (e.g., an electronic nose) and obtains their chemical composition data. This data is stored in a database. The server uses machine learning libraries such as TensorFlow and PyTorch to train a scent generation model based on the collected data. Comprehensive scent data is stored in cloud storage (e.g., AWS S3 or Google Cloud Storage).

[0767] User action detection and request generation

[0768] When a user performs a specific action in the game or metaverse space, the device detects this through sensors and interfaces and collects corresponding event information. The device generates a request that says "the user has entered the virtual cafe" and sends it to the server. The request is sent to the server in JSON or XML format.

[0769] Generation and transmission of scent data

[0770] The server analyzes requests received from the device and generates scent data corresponding to specific events using a trained machine learning model. The generated scent data is sent to the device in JSON or XML format.

[0771] Fragrance reproduction and user experience

[0772] The device analyzes the received scent data and sends it to the scent diffuser, which then mixes specific compounds based on the scent data to create a realistic scent that the user can smell, providing a more realistic and immersive experience.

[0773] Gathering feedback and improving the system

[0774] The user's impressions and evaluations of the experience are sent to the server via the device, and this feedback is stored in a database and used to improve the scent generation model and optimize the entire system.

[0775] Specific examples

[0776] For example, if a user steps into an ancient temple in an adventure game, the device detects this action and requests "ancient temple scent data" from the server. The server generates scent data of damp stone and old books and sends it to the device. The device then controls a scent diffuser to reproduce these scents. By smelling these scents, the user can further enhance the sense of realism within the game.

[0777] When a user enters a virtual cafe in the metaverse, the server generates aroma data for coffee and freshly baked bread and sends it to the device, which then uses a scent diffuser to recreate the aroma, making the user's experience in the virtual space feel more realistic.

[0778] Prompt Sentence Examples

[0779] "Generate the aroma of coffee as you enter a virtual cafe."

[0780] "Recreate the scent of damp stone for a scene in an adventure game where you enter an ancient temple."

[0781] "Create a sea salt scent that wafts through the air when users are on a virtual beach."

[0782] This system provides a real-time olfactory experience, bringing new value to users.

[0783] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0784] Step 1:

[0785] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. Specifically, the electronic nose sensor captures the molecular components of the scent and records them as digital data. The server then stores this data in a database as chemical composition data.

[0786] Input: Scent sample

[0787] Data processing: Digitalization of chemical components through sensing

[0788] Output: Chemical composition data

[0789] Step 2:

[0790] The server uses a machine learning algorithm based on the collected data to train a scent generation model. The server uses machine learning libraries such as TensorFlow and PyTorch, and uses the chemical composition data and meta-information about the scent (such as name, category, and intensity) as training data. The scent generation model is saved in cloud storage.

[0791] Input: Chemical composition data, meta information

[0792] Data Computation: Training with Machine Learning Algorithms

[0793] Output: Scent generation model

[0794] Step 3:

[0795] When a user performs a specific action in the game or in the metaverse space, the device detects this through sensors and interfaces and collects event information. The device generates event information such as "the user has entered a virtual cafe" and sends it to the server in the form of a request.

[0796] Input: User action

[0797] Data processing: action detection and event information generation

[0798] Output: Event-based request

[0799] Step 4:

[0800] The server receives the request sent from the device and analyzes the content. The server generates scent data corresponding to the event using the trained scent generation model. For example, the server generates coffee scent data for the event of entering a "virtual cafe." The scent data is then sent to the device.

[0801] Input: Event-based request

[0802] Data computation: Generation of scent data using scent generation models

[0803] Output: Scent data

[0804] Step 5:

[0805] The device analyzes the scent data received from the server and sends it to the scent diffuser, which then mixes specific compounds based on the scent data to create the actual scent.The device controls the scent diffuser using Bluetooth or Wi-Fi.

[0806] Input: Scent data

[0807] Data processing: Data analysis and transmission to the diffuser

[0808] Output: The actual scent generated

[0809] Step 6:

[0810] The user smells the generated scent and provides feedback on their experience. The device collects the user's feedback data and sends it to the server, which stores it in a database and uses it to improve the scent generation model and optimize the entire system.

[0811] Input: User feedback

[0812] Data Processing: Collecting and Sending Feedback

[0813] Output: Improved model and system optimization

[0814] (Application example 1)

[0815] 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."

[0816] Conventional content distribution services have focused on providing immersive experiences through video and audio, but incorporating the sense of smell has made it difficult to provide users with a more realistic and immersive experience. Furthermore, the development of systems that generate scents in real time and dynamically change them in response to user actions has also remained immature. To address this issue, a system that digitizes the sense of smell and enriches users' content viewing experiences is needed.

[0817] 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.

[0818] In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for generating and transmitting a request to generate a specific scent in response to a user's actions, means for generating scent data using the scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, means for collecting user feedback and reflecting it in improving the system and model, and means for generating and providing a scent tailored to a specific scene in real time while the user is viewing content. This provides a realistic scent experience in response to the user's actions, enabling a more immersive content viewing experience.

[0819] "Olfaction data" is digitalized information about scents that a user perceives through their sense of smell.

[0820] "Chemical composition data" refers to data on the composition of molecules and compounds used to reproduce a scent.

[0821] A "database" is an information management system that efficiently stores information such as olfactory data and chemical composition data, and enables searching and retrieval.

[0822] A "machine learning model" is a collection of algorithms that learn patterns from large amounts of data and generate and predict scents.

[0823] A "request" is a request sent to the server to generate a specific scent based on a user action.

[0824] A "terminal" is a device that is directly operated by the user to generate requests, receive scent data, and control the scent diffuser.

[0825] The "fragrance generation model" is a method for generating specific fragrances as digital data using a machine learning model.

[0826] "Scent data" is digital information for reproducing a specific scent generated by the scent generation model.

[0827] A "fragrance diffuser" is a device that physically generates and releases an actual scent based on scent data.

[0828] A "user action" is an operation or movement that a user performs through a terminal, which triggers the generation of a request.

[0829] "Feedback" refers to the user's evaluations and opinions about the scent they have experienced, and is information used to improve the system and the accuracy of the model.

[0830] "Content viewing" refers to the act of a user viewing video, audio, or other media content.

[0831] MODE FOR CARRYING OUT THE INVENTION

[0832] System Overview

[0833] This system consists of a series of processes that collect olfactory data, digitize it, generate scents using machine learning models, and provide the scents in real time during the user's content viewing experience. Specifically, a server, terminal, and scent diffuser work together.

[0834] Data collection and training phase

[0835] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. This data is stored in a database and used to train a machine learning model. Based on the collected data, the server trains a scent generation model using a machine learning algorithm (e.g., RandomForestRegressor using Scikit-learn), thereby improving its ability to reproduce specific scents.

[0836] User Actions and Request Generation

[0837] When a user is watching content on a smartphone or head-mounted display and a specific action (e.g., a scene change in a movie) occurs, the device detects this. The device's application generates a request for the scent of wet earth and sends it to the server. The server receives this request and generates the corresponding scent data.

[0838] Scent generation and transmission

[0839] The server operates the scent generation model based on the received request and generates specific scent data. The generated scent data is then converted into an appropriate format and sent to the terminal. The terminal then generates and releases an actual scent using a scent diffuser based on the received scent data. The scent diffuser then mixes specific compounds based on the scent data and releases the scent.

[0840] Feedback and System Improvement

[0841] By smelling the generated scent, the user can experience a more realistic and immersive experience. The user's evaluation and feedback of the experience are sent to the server via the device. This feedback is used to improve the accuracy of the scent generation model and the overall system.

[0842] Specific examples

[0843] For example, if a user is using the "Olfactory Cinema Experience App" to watch a movie and the scene switches to a rainy scene, the system will generate data on the scent of "wet earth" and send it to the device. The device's scent diffuser will then release the scent in real time based on this data, providing the user with a more immersive viewing experience.

[0844] Example prompts for generative AI models

[0845] Prompt: Create a scent that matches a scene from this movie. Scene: "Jungle at night", Desired scent: "The scent of damp vegetation"

[0846] This allows users to enjoy the content both visually and olfactory.

[0847] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0848] Step 1:

[0849] The server collects olfactory data. It uses an olfactory sensor to obtain various scent samples as olfactory data, and stores the chemical composition data in a database. The input is the scent sample from the olfactory sensor, and the output is stored in the database as chemical composition data.

[0850] Step 2:

[0851] The server trains a machine learning model based on the collected chemical composition data. Specifically, it uses Scikit-learn to train a RandomForestRegressor model to improve its ability to reproduce specific scents. The input is the chemical composition data stored in the database, and the output is the trained machine learning model.

[0852] Step 3:

[0853] When a user performs a specific action (e.g., scene change) while watching content on a device, the device detects this. The device detects the user's behavior through sensors and interfaces and collects event information. The input is the user's action, and the output is event information.

[0854] Step 4:

[0855] The device generates a request to generate a specific scent based on the collected event information and sends it to the server. For example, if a user watches a rainy scene in a movie, the device generates a request saying, "I need the scent of wet earth." The input is the event information, and the output is a scent generation request.

[0856] Step 5:

[0857] The server runs the scent generation model based on the received request. It uses the trained machine learning model to generate specific scent data and sends it to the device. The input is the scent generation request, and the output is the scent data.

[0858] Step 6:

[0859] The device generates the actual scent using a scent diffuser based on the scent data received from the server. The diffuser mixes the specified chemical ingredients and releases the scent. The input is scent data, and the output is a physical scent.

[0860] Step 7:

[0861] By smelling the generated scent, the user experiences the realism of watching content. The user then inputs their evaluation and feedback about the experience into the device, which then sends this to the server. The input is the user's feedback, and the output is the feedback data.

[0862] Step 8:

[0863] The server collects feedback data from users and reflects it in improving the system and machine learning model. The input is the feedback data, and the output is an improved system or model.

[0864] 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.

[0865] A system combining the olfactory digitization system and emotion engine of the present invention will be described below in detail with reference to an embodiment thereof.

[0866] This system consists of a device for collecting and digitizing olfactory data, a device for recognizing user emotions using an emotion engine, a device for training a machine learning model based on the collected data, a device for generating and transmitting scent data in response to user actions and emotions, and a device for reproducing the scent data as an actual scent.

[0867] Data collection and training phase

[0868] The server uses an olfactory sensor to collect data on various scents and obtain their chemical composition. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[0869] User actions, emotion recognition and request generation

[0870] When a user performs a specific action in a game or in the Metaverse space, the device detects this and collects corresponding event information. For example, a user entering a virtual cafe can be detected.

[0871] The device then activates an emotion engine that analyzes the user's facial, voice, and movement data to recognize their emotions, for example, whether they are feeling happy or anxious.

[0872] The device generates a scent request based on the detected user actions and the recognized emotions. For example, it generates a request such as "The user has entered a virtual cafe and is enjoying themselves, so I need the relaxing aroma of coffee." The request is then sent to the server.

[0873] Scent generation and transmission

[0874] The server runs the scent generation model based on the received request to generate specific scent data, which is then converted into an appropriate format and sent back to the device.

[0875] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[0876] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[0877] User Experience and Feedback

[0878] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. Furthermore, the scent is generated according to the user's emotional state, providing a scent experience appropriate to the user's emotional state.

[0879] Users rate their experience based on the aromas they experience, for example, feeling that the aroma of coffee was "realistic and relaxing."

[0880] The device collects user ratings and feedback and sends it to the server, which uses the feedback to improve the system.

[0881] Specific examples

[0882] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device, which will then use a scent diffuser to recreate these scents, enhancing the user's sense of realism in the game.

[0883] As another example, if a user enters a virtual cafe in the metaverse, and the emotion engine recognizes that the user is enjoying themselves based on their facial expressions and actions, the server will generate the relaxing aroma of coffee or freshly baked bread and send it to the device. The device will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more realistic.

[0884] This system provides new value to users by realizing a real-time olfactory experience in digital space, and solves the problem through the means described in the claims.

[0885] The processing flow will be explained below.

[0886] Step 1:

[0887] The server uses an olfactory sensor to collect data on various scents, which is then stored in a database as chemical composition data.

[0888] Step 2:

[0889] The server preprocesses the stored chemical composition data, removing impurities and noise and streamlining the dataset to obtain high-quality data.

[0890] Step 3:

[0891] The server trains a machine learning model on the pre-processed data, using machine learning algorithms to learn patterns from the data and build a model capable of generating specific scents.

[0892] Step 4:

[0893] A user performs a specific action in the game or metaverse space, such as reaching a specific location in the game or using a specific item.

[0894] Step 5:

[0895] The device detects user actions through sensors and interfaces, such as when a user enters a virtual cafe.

[0896] Step 6:

[0897] The device runs an emotion engine that analyzes the user's facial, voice, and movement data to recognize emotions, for example, whether the user is feeling happy or anxious.

[0898] Step 7:

[0899] The device generates a scent request based on the detected user actions and the recognized emotions, for example, "The user has entered a virtual cafe and is enjoying themselves, so the relaxing aroma of coffee is needed."

[0900] Step 8:

[0901] The terminal transmits the generated scent request to the server.

[0902] Step 9:

[0903] The server runs the scent generation model based on the received request, generates the necessary scent data, converts it into an appropriate format, and sends it back to the device.

[0904] Step 10:

[0905] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[0906] Step 11:

[0907] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[0908] Step 12:

[0909] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. Furthermore, the scent is generated according to the user's emotional state, providing a scent experience appropriate to the user's emotional state.

[0910] Step 13:

[0911] Users rate their experience based on the aromas they experience, for example, feeling that the aroma of coffee was "realistic and relaxing."

[0912] Step 14:

[0913] The device collects user ratings and feedback and sends it to the server.

[0914] Step 15:

[0915] The server analyzes user feedback and improves the scent generation model and the entire system, for example, by improving the accuracy of the scent generation algorithm.

[0916] The above is a detailed step-by-step explanation of the processing flow of the Smell Tech system.

[0917] Example 2

[0918] 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."

[0919] In modern digital experiences and virtual spaces, there is a demand for comprehensive experiences that include not only sight and sound, but also smell. However, existing technologies lack the ability to digitalize the sense of smell or generate scents that respond to the user's emotions, making it difficult to achieve an immersive or realistic experience. In addition, there are limited methods for effectively collecting user feedback and incorporating it into systems and machine learning models.

[0920] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for detecting a user's actions and analyzing the actions and the user's emotions, means for generating and transmitting a request to generate a specific scent based on the analysis results, means for generating scent data using a scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, and means for collecting user feedback and reflecting it in improving the system and model. This makes it possible to generate and reproduce scents in real time according to the user's actions and emotions, realize an olfactory experience in a digital space, and utilize user feedback to continuously improve the system.

[0921] "Olfactory data" is data that quantifies and digitizes information about scents and odors, and includes information about chemical composition and ingredients.

[0922] "Chemical composition data" is data that indicates the types and proportions of chemical components contained in a specific fragrance or substance.

[0923] The "database" is an information recording system for storing and managing collected olfactory data and chemical composition data.

[0924] A "machine learning model" is an algorithm that learns patterns based on collected data and makes predictions and classifications for new inputs.

[0925] "User actions" refer to operations or movements that a user makes within a digital or virtual environment.

[0926] "Emotion analysis" is the process of determining a user's emotional state from data such as facial expressions, voice, and movements.

[0927] A "scent request" is a request to instruct the system to generate a particular scent.

[0928] A "scent generation model" is a machine learning model trained to generate a specific scent as digital data.

[0929] "Scent data" refers to data that includes specific chemical components and their blending ratios for reproducing the created scent.

[0930] A "terminal" is an electronic device or device that allows a user to access a digital space or virtual environment.

[0931] An "aroma diffuser" is a device that generates and releases actual scents based on scent data.

[0932] "Feedback" is information that provides the system with the user's evaluation and opinions regarding the scent they experienced.

[0933] "System improvement" refers to improving the performance and functionality of a system based on collected feedback.

[0934] This invention is a system that combines an olfactory digitization system and an emotion engine, allowing users to experience not only sight and hearing but also smell in digital or virtual environments. The present invention provides a system that comprehensively executes a series of processes from collecting olfactory data to generating scents and recognizing the user's emotions.

[0935] First, the server uses an olfactory sensor to collect data on various scents and obtain their chemical composition data. The specific hardware used includes various types of sensors. For example, olfactory sensors include gas sensors and electrochemical sensors that accurately measure chemical composition. This data is collected using a Python script and stored in a database (e.g., MySQL or PostgreSQL).

[0936] The server then trains a machine learning model based on the collected olfactory data. Specifically, it uses Python's scikit-learn and TensorFlow libraries to build and train a model based on the collected chemical composition data. For example, it uses a random forest algorithm or a neural network to learn specific scent generation patterns.

[0937] When a user performs a specific action in a digital space (e.g., a game or the Metaverse), the device (PC, smartphone, VR device, etc.) detects the action. Here, a script in a game engine based on Unity or Unreal Engine runs to monitor and detect the user's location and actions. For example, if a user is detected entering a virtual cafe, this information is registered as an event.

[0938] The device then uses an emotion engine to analyze the user's facial, voice, and movement data to recognize their emotions. Specifically, it uses the camera to analyze facial expressions using the OpenCV library and sends the data to the Microsoft Azure Face API to obtain the analysis results. At the same time, it collects voice data through the microphone and performs voice analysis using Google Cloud Speech-to-Text. This allows it to recognize the user's emotional state, such as whether they are happy or anxious.

[0939] The device generates a scent request based on the results of the above sentiment analysis and the user's actions. For example, a request such as "The user has entered a virtual cafe and is enjoying themselves, so they need a relaxing coffee aroma" is generated in JSON format and sent to the server. An example of a prompt sentence is:

[0940] A request is sent to the server saying, "The emotion engine has recognized that the user has entered a cafe in a virtual space and is enjoying themselves. Please generate scent data that has a relaxing effect."

[0941] The server then runs a scent generation model based on the received request to generate specific scent data. For example, it uses TensorFlow to generate the scent data and sends it back to the device in JSON or binary format. This scent data is formatted to include specific chemical component information.

[0942] The device receives the scent data sent from the server and sends it to the scent diffuser. The scent diffuser then mixes specific compounds based on the scent data to create the actual scent. Specific devices that can be connected via Bluetooth or Wi-Fi are used. For example, by using a smart device made by Scentee, the appropriate mixture of chemical components is created to recreate the relaxing aroma of coffee.

[0943] Users experience the scent emitted from the scent diffuser, making their digital experience more realistic and immersive. They also provide feedback on their scent experience through an application on their device. For example, a user might write a review such as, "The relaxing coffee aroma was very realistic." This feedback is temporarily stored on the device and later sent to a server. The server analyzes this feedback and uses it to improve the system and machine learning models.

[0944] As described above, the present invention provides a system that realizes a real-time olfactory experience in a digital space and enables the generation of scents according to the user's actions and emotions. Furthermore, by utilizing user feedback and continuously improving the system, it is possible to provide a higher quality olfactory experience.

[0945] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0946] Step 1:

[0947] The server collects scent data using an olfactory sensor. The olfactory sensor (e.g., a gas sensor or electrochemical sensor) is used to obtain chemical composition data of specific scents in real time. The obtained data is converted into CSV format using a Python script and sent to the server. The inputs are scent samples and sensor measurement results. The output is chemical composition data as a CSV file.

[0948] Step 2:

[0949] The server stores the collected chemical composition data in a database, using MySQL or PostgreSQL. The stored data is organized for later use in model training. The CSV file obtained in step 1 is used as input, and the data stored in the database is generated as output.

[0950] Step 3:

[0951] The server trains a machine learning model based on the stored chemical composition data. It uses Python's scikit-learn and TensorFlow libraries to build a scent generation model. Specifically, it uses a random forest algorithm and neural networks to train a model capable of reproducing a specific scent. The input is chemical composition data obtained from the database, and the output is a trained machine learning model.

[0952] Step 4:

[0953] When a user performs a specific action in the digital space, the device detects that action. Using scripts in game engines such as Unity or Unreal Engine, the device monitors the user's location and movements. For example, a user entering a virtual cafe is detected. The input is information about the user's action, and the output is event information generated for the specific action performed by the user.

[0954] Step 5:

[0955] The device collects the user's facial expression, voice, and movement data to recognize emotions. The specific technology used is to analyze facial expressions using a camera and the OpenCV library, and send the data to the Microsoft Azure Face API to obtain the analysis results. Voice data is analyzed using a microphone with Google Cloud Speech-to-Text. The input is the user's facial expression data, voice data, and movement data, and the output is the user's emotional state.

[0956] Step 6:

[0957] The device generates a scent request based on the user's actions and the results of emotion recognition. The scent request includes the specific action performed by the user and instructions for the scent based on the recognized emotion. The input is the event information of the user's actions and the results of emotion recognition. The output is a request to generate a specific scent in JSON format, which is sent to the server.

[0958] Step 7:

[0959] The server generates scent data based on the received scent request using a scent generation model. It runs a TensorFlow model to generate the specified scent chemical components. The input is the scent request and the machine learning model, and the output is the generated scent data in JSON format.

[0960] Step 8:

[0961] The server sends the generated scent data to the terminal. The scent data is transmitted to the terminal via the network and received by the terminal. The input is the generated scent data, and the output includes the scent data sent to the terminal.

[0962] Step 9:

[0963] The device generates an actual scent using a scent diffuser based on the received scent data. The device transmits the data to the scent diffuser, which mixes specific compounds based on the data and releases the scent. The input is the received scent data, and the output is a physically reproduced scent.

[0964] Step 10:

[0965] The user experiences the released scent and provides feedback. They input their evaluation and opinions about the scent experience through an application on their device. The input is the user's feedback, and the output is the collected feedback information.

[0966] Step 11:

[0967] The device stores the user's feedback and later transmits it to the server. The feedback is reflected in the system's improvements and is used to generate future scents. The input is the user's feedback information, and the output includes the feedback transmitted to the server.

[0968] Through these steps, this system provides a real-time olfactory experience in the digital space and can generate and reproduce scents according to the user's emotions.

[0969] (Application example 2)

[0970] 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."

[0971] Conventional virtual reality (VR) experiences and metaverse spaces rely solely on sight and hearing, limiting the user's sense of immersion and the realism of the experience. Furthermore, they are unable to provide personalized content based on the user's emotions and behavior, resulting in a uniform user experience and making it difficult to provide an optimal experience tailored to each user's condition. The present invention aims to solve these problems by providing an olfactory digitization system that provides a more realistic and personalized VR experience.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0973] In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for generating and transmitting a request to generate a specific scent in response to a user's actions and emotions, means for generating scent data using the scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, and means for collecting feedback from users and reflecting it in improving the system and model. This allows for the generation of specific scents in response to the user's actions and emotions, making the experience in the VR space more immersive and realistic.

[0974] "Olfactory data" is information about a particular scent expressed as chemical composition data.

[0975] "Chemical composition data" is olfactory data that has been quantified and expressed in a form that can be stored in a database.

[0976] The "database" is a system for systematically storing and managing collected olfactory data and other related information.

[0977] A "machine learning model" is an algorithm trained to generate specific scents based on collected olfactory data.

[0978] "User actions" refer to specific actions or operations performed by the user within the VR space.

[0979] "Emotion" refers to the psychological state that can be recognized from the user's facial expressions, voice, and behavior.

[0980] A "scent generation model" is an algorithm trained to generate specific scent data.

[0981] A "terminal" is a device that receives olfactory data and controls the scent diffuser.

[0982] An "aroma diffuser" is a device that mixes specific compounds based on aroma data and releases aromas.

[0983] "Feedback" refers to the user's evaluation or opinion based on the scent they experienced, their overall experience, etc.

[0984] The following describes a specific embodiment of a system that combines the olfactory digitization system and emotion engine of the present invention, thereby realizing an immersive and personalized virtual reality (VR) experience for users.

[0985] Data collection and training phase

[0986] The server uses an olfactory sensor to collect data on various scents and obtain their chemical composition. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[0987] User actions, emotion recognition and request generation

[0988] When a user performs a specific action in a game or in the metaverse space, the device detects this and collects corresponding event information. For example, the device detects that the user is entering a virtual cafe. The device then activates its emotion engine and analyzes the user's facial, voice, and movement data to recognize their emotions. For example, it identifies whether the user is enjoying themselves or feeling anxious. The device generates a scent request based on the detected user action and the recognized emotion. For example, it generates a request such as "The user has entered a virtual cafe and is enjoying themselves, so I need the relaxing aroma of coffee," and sends this request to the server.

[0989] Scent generation and transmission

[0990] The server runs a scent generation model based on the received request to generate specific scent data. The generated scent data is converted into an appropriate format and sent back to the device. The device receives the scent data sent from the server. This scent data is used by a scent diffuser built into the device. The device runs the scent diffuser based on the received scent data. The scent diffuser appropriately mixes specific compounds based on the data to generate the actual scent.

[0991] User Experience and Feedback

[0992] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. In addition, scents are generated according to emotions, providing an appropriate scent experience for the user's emotional state. The user evaluates the experience based on the scent generated. For example, the user may feel that the "relaxing coffee aroma was realistic." The device collects user evaluations and feedback and sends it to the server. This feedback is used to improve the system.

[0993] Specific examples

[0994] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device. The device will then use a scent diffuser to recreate these scents, further enhancing the user's sense of realism in the game. As another example, if a user enters a virtual cafe in the metaverse, and the emotion engine recognizes that the user is enjoying themselves based on their facial expressions and actions, the server will generate the relaxing scent of coffee and freshly baked bread and send it to the device. The device will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more real.

[0995] Prompt Sentence Examples

[0996] A user enters a virtual cafe in a VR space, and the emotion engine recognizes this as "fun" based on data collected by the camera and microphone. Please generate a scent request for this action.

[0997] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0998] Step 1:

[0999] The device tracks the user's actions within the VR environment. Specifically, it collects user movement data through the interface and sensors, processes that data, and detects specific actions. For example, when a user enters a virtual cafe, their movements are tracked and event information is collected. Sensor and camera data is used as input, and a list of detected actions is output.

[1000] Step 2:

[1001] The device activates an emotion engine and analyzes the user's facial and voice data, thereby recognizing the user's emotions. Specifically, data is acquired in real time from the camera and microphone installed in the HMD, and the data is analyzed using an emotion recognition algorithm. Facial and voice data are used as input, and the output is a tag of the recognized emotion.

[1002] Step 3:

[1003] The device generates a scent request based on the detected user actions and the recognized emotions. For example, a request may be generated such as, "The user has entered a virtual cafe and is enjoying themselves, so I need a relaxing coffee aroma." This process uses tags representing the user's actions and emotions as input, and outputs a scent request.

[1004] Step 4:

[1005] The device sends the generated scent request to the server. Specifically, it sends the scent request to the server via the Internet and waits for a reply from the server. The scent request is used as input, and the output is the transmission to the server.

[1006] Step 5:

[1007] The server activates the scent generation model based on the received scent request and generates specific scent data. Specifically, it uses a machine learning model on the server to generate a scent corresponding to the request. The scent request is used as input, and the generated scent data is the output.

[1008] Step 6:

[1009] The server returns the generated scent data to the terminal. Specifically, it converts the scent data into an appropriate format and sends it to the terminal. The generated scent data is used as input, and the output is sent to the terminal.

[1010] Step 7:

[1011] The device operates the scent diffuser based on the received scent data. Specifically, it sends the scent data to the scent diffuser, which then mixes specific compounds and releases the scent. The received scent data is used as input, and the output is the actual scent that is generated.

[1012] Step 8:

[1013] The user experiences the scent emitted from the scent diffuser, making the digital experience realistic and immersive. The input is the scent emitted from the diffuser, and the output is the user's experience.

[1014] Step 9:

[1015] The user provides feedback based on the aroma they experienced. For example, they input feedback such as "The relaxing aroma of coffee was realistic." The input is the user's feedback, and the output is the collected ratings and opinions.

[1016] Step 10:

[1017] The device sends the feedback collected from the user to the server. This feedback can be used to improve the system and model in the future. Specifically, the feedback data is sent to the server via the Internet. The user's feedback is used as input, and the output is sent to the server.

[1018] 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.

[1019] 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.

[1020] 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.

[1021] [Fourth embodiment]

[1022] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1023] 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.

[1024] 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).

[1025] 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.

[1026] 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.

[1027] 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).

[1028] 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.

[1029] 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.

[1030] 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.

[1031] 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.

[1032] 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.

[1033] 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.

[1034] 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."

[1035] An embodiment of the olfactory digitization system of the present invention will be specifically described below.

[1036] This system consists of a device for collecting and digitizing olfactory data, a device for training a machine learning model based on the collected data, a device for generating and transmitting scent data in response to user actions, and a device for reproducing the scent data as an actual scent.

[1037] Data collection and training phase

[1038] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[1039] User Actions and Request Generation

[1040] When a user performs a specific action in a game or in the metaverse, the device detects it and collects the corresponding event information. For example, when a user enters a virtual cafe, the device generates a request saying "I need the smell of coffee" and sends it to the server. The server receives this request and generates the appropriate scent data.

[1041] Scent generation and transmission

[1042] The server operates the scent generation model based on the received request and generates specific scent data. The generated scent data is converted into an appropriate format and sent to the device. The device generates an actual scent using a scent diffuser based on the received scent data. The scent diffuser mixes specific compounds based on the scent data and releases the scent.

[1043] User Experience and Feedback

[1044] By smelling the generated scent, the user can experience a more realistic and immersive experience. The user's evaluation and feedback of the experience are sent to the server via the device. This feedback is used to improve the accuracy of the scent generation model and the overall system.

[1045] Specific examples

[1046] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device, which will then use a scent diffuser to recreate these scents, enhancing the user's sense of realism in the game.

[1047] As another example, if a user enters a virtual cafe in the metaverse, the server will generate the aroma of coffee or freshly baked bread and send it to the device, which will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more realistic.

[1048] This system provides new value to users by realizing a real-time olfactory experience in digital space, and solves the problem through the means described in the claims.

[1049] The processing flow will be explained below.

[1050] Step 1:

[1051] The server uses an olfactory sensor to collect data on various scents, which is then stored in a database as chemical composition data.

[1052] Step 2:

[1053] The server preprocesses the stored chemical composition data, removing impurities and noise and streamlining the dataset to obtain high-quality data.

[1054] Step 3:

[1055] The server trains a machine learning model on the pre-processed data, using machine learning algorithms to learn patterns from the data and build a model capable of generating specific scents.

[1056] Step 4:

[1057] When a user performs a specific action in a game or in the Metaverse space, the device detects this action through sensors and interfaces, for example, when the user enters a virtual cafe.

[1058] Step 5:

[1059] The device generates a scent request based on the detected user action, for example, "I need the scent of coffee," and sends this request to the server.

[1060] Step 6:

[1061] The server runs the scent generation model based on the received request, generates the necessary scent data, converts it into an appropriate format, and sends it back to the device.

[1062] Step 7:

[1063] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[1064] Step 8:

[1065] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[1066] Step 9:

[1067] Users smell the scent emitted from the scent diffuser, making the digital experience feel realistic and immersive.

[1068] Step 10:

[1069] Users rate their experience based on the aromas they experience, for example, feeling that the coffee aroma was realistic.

[1070] Step 11:

[1071] The device collects user ratings and feedback and sends it to the server, which uses the feedback to improve the system.

[1072] Step 12:

[1073] The server analyzes user feedback and improves the scent generation model and the entire system, for example, by improving the accuracy of the scent generation algorithm.

[1074] The above is a detailed explanation of the processing steps of the Smell Tech system.

[1075] Example 1

[1076] 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."

[1077] Previous olfactory experiences in virtual spaces and games were limited, making it difficult for users to achieve a deeper sense of immersion through their sense of smell. Furthermore, the accuracy of scent generation and reproduction was low, and there was a lack of effective ways to utilize user feedback to improve the system. Furthermore, the entire process from data collection to reproduction was inefficient. This limited the quality of the user experience and made it difficult to provide new olfactory experiences.

[1078] 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.

[1079] In this invention, the server includes a means for collecting olfactory data and storing it in a database as chemical composition data, a means for training a machine learning model based on the olfactory data, and a cloud storage means for storing comprehensive scent data, thereby enabling highly accurate reproduction of scents and improving user experience.

[1080] The terminal also includes a means for detecting specific events and sending them to the server in a request format, a means for receiving scent data at the terminal and generating an actual scent using the scent diffuser, and a communication means for linking the terminal and the scent diffuser, thereby enabling scent generation in real time in response to user actions.

[1081] Furthermore, the system includes a means for collecting user feedback and reflecting it in improvements to the system and model, allowing for continuous system improvement based on the collected feedback, thereby providing a more advanced olfactory experience.

[1082] "Olfactory data" refers to data obtained by an olfactory sensor about the molecular components and chemical composition associated with a particular scent.

[1083] "Chemical composition data" is a part of olfactory data, and is information that includes the molecules that make up a particular scent and their proportions.

[1084] A "database" is a storage system that systematically stores olfactory data and chemical composition data, allowing for efficient access and searching.

[1085] A "machine learning model" is an algorithm that learns patterns from large amounts of data and automatically performs specific tasks.

[1086] "Cloud storage" is a service that stores data on the Internet and is a means of efficiently storing large amounts of data.

[1087] A "terminal" is a device that a user operates via an interface, and is a device that generates requests and reproduces scents.

[1088] A "request" is a request that includes event information corresponding to a user action, and is information that is sent to a server.

[1089] An "aroma generation model" is a machine learning model trained to generate aromas based on specific chemical composition data.

[1090] "Communication means" refers to a network connection means for linking the terminal and the server, or the terminal and the scent diffuser.

[1091] An "aroma diffuser" is a device that physically reproduces a specific scent based on scent data.

[1092] "Feedback" refers to user-provided information about experience ratings and areas for improvement, and is data used to improve the system.

[1093] A "server" is a computer system that centrally collects, stores, analyzes, processes, and distributes olfactory data.

[1094] A "user action" is an event that occurs on the interface when a user performs a specific action or operation.

[1095] MODE FOR CARRYING OUT THE INVENTION

[1096] System Overview

[1097] The present invention consists of a device that collects and digitizes olfactory data, a device that trains a machine learning model based on the collected data, a device that generates and transmits scent data in response to user actions, and a device that reproduces the scent data as an actual scent.

[1098] Data Collection and Machine Learning

[1099] The server collects various scent samples using an olfactory sensor (e.g., an electronic nose) and obtains their chemical composition data. This data is stored in a database. The server uses machine learning libraries such as TensorFlow and PyTorch to train a scent generation model based on the collected data. Comprehensive scent data is stored in cloud storage (e.g., AWS S3 or Google Cloud Storage).

[1100] User action detection and request generation

[1101] When a user performs a specific action in the game or metaverse space, the device detects this through sensors and interfaces and collects corresponding event information. The device generates a request that says "the user has entered the virtual cafe" and sends it to the server. The request is sent to the server in JSON or XML format.

[1102] Generation and transmission of scent data

[1103] The server analyzes requests received from the device and generates scent data corresponding to specific events using a trained machine learning model. The generated scent data is sent to the device in JSON or XML format.

[1104] Fragrance reproduction and user experience

[1105] The device analyzes the received scent data and sends it to the scent diffuser, which then mixes specific compounds based on the scent data to create a realistic scent that the user can smell, providing a more realistic and immersive experience.

[1106] Gathering feedback and improving the system

[1107] The user's impressions and evaluations of the experience are sent to the server via the device, and this feedback is stored in a database and used to improve the scent generation model and optimize the entire system.

[1108] Specific examples

[1109] For example, if a user steps into an ancient temple in an adventure game, the device detects this action and requests "ancient temple scent data" from the server. The server generates scent data of damp stone and old books and sends it to the device. The device then controls a scent diffuser to reproduce these scents. By smelling these scents, the user can further enhance the sense of realism within the game.

[1110] When a user enters a virtual cafe in the metaverse, the server generates aroma data for coffee and freshly baked bread and sends it to the device, which then uses a scent diffuser to recreate the aroma, making the user's experience in the virtual space feel more realistic.

[1111] Prompt Sentence Examples

[1112] "Generate the aroma of coffee as you enter a virtual cafe."

[1113] "Recreate the scent of damp stone for a scene in an adventure game where you enter an ancient temple."

[1114] "Create a sea salt scent that wafts through the air when users are on a virtual beach."

[1115] This system provides a real-time olfactory experience, bringing new value to users.

[1116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1117] Step 1:

[1118] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. Specifically, the electronic nose sensor captures the molecular components of the scent and records them as digital data. The server then stores this data in a database as chemical composition data.

[1119] Input: Scent sample

[1120] Data processing: Digitalization of chemical components through sensing

[1121] Output: Chemical composition data

[1122] Step 2:

[1123] The server uses a machine learning algorithm based on the collected data to train a scent generation model. The server uses machine learning libraries such as TensorFlow and PyTorch, and uses the chemical composition data and meta-information about the scent (such as name, category, and intensity) as training data. The scent generation model is saved in cloud storage.

[1124] Input: Chemical composition data, meta information

[1125] Data Computation: Training with Machine Learning Algorithms

[1126] Output: Scent generation model

[1127] Step 3:

[1128] When a user performs a specific action in the game or in the metaverse space, the device detects this through sensors and interfaces and collects event information. The device generates event information such as "the user has entered a virtual cafe" and sends it to the server in the form of a request.

[1129] Input: User action

[1130] Data processing: action detection and event information generation

[1131] Output: Event-based request

[1132] Step 4:

[1133] The server receives the request sent from the device and analyzes the content. The server generates scent data corresponding to the event using the trained scent generation model. For example, the server generates coffee scent data for the event of entering a "virtual cafe." The scent data is then sent to the device.

[1134] Input: Event-based request

[1135] Data computation: Generation of scent data using scent generation models

[1136] Output: Scent data

[1137] Step 5:

[1138] The device analyzes the scent data received from the server and sends it to the scent diffuser, which then mixes specific compounds based on the scent data to create the actual scent.The device controls the scent diffuser using Bluetooth or Wi-Fi.

[1139] Input: Scent data

[1140] Data processing: Data analysis and transmission to the diffuser

[1141] Output: The actual scent generated

[1142] Step 6:

[1143] The user smells the generated scent and provides feedback on their experience. The device collects the user's feedback data and sends it to the server, which stores it in a database and uses it to improve the scent generation model and optimize the entire system.

[1144] Input: User feedback

[1145] Data Processing: Collecting and Sending Feedback

[1146] Output: Improved model and system optimization

[1147] (Application example 1)

[1148] 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."

[1149] Conventional content distribution services have focused on providing immersive experiences through video and audio, but incorporating the sense of smell has made it difficult to provide users with a more realistic and immersive experience. Furthermore, the development of systems that generate scents in real time and dynamically change them in response to user actions has also remained immature. To address this issue, a system that digitizes the sense of smell and enriches users' content viewing experiences is needed.

[1150] 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.

[1151] In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for generating and transmitting a request to generate a specific scent in response to a user's actions, means for generating scent data using the scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, means for collecting user feedback and reflecting it in improving the system and model, and means for generating and providing a scent tailored to a specific scene in real time while the user is viewing content. This provides a realistic scent experience in response to the user's actions, enabling a more immersive content viewing experience.

[1152] "Olfaction data" is digitalized information about scents that a user perceives through their sense of smell.

[1153] "Chemical composition data" refers to data on the composition of molecules and compounds used to reproduce a scent.

[1154] A "database" is an information management system that efficiently stores information such as olfactory data and chemical composition data, and enables searching and retrieval.

[1155] A "machine learning model" is a collection of algorithms that learn patterns from large amounts of data and generate and predict scents.

[1156] A "request" is a request sent to the server to generate a specific scent based on a user action.

[1157] A "terminal" is a device that is directly operated by the user to generate requests, receive scent data, and control the scent diffuser.

[1158] The "fragrance generation model" is a method for generating specific fragrances as digital data using a machine learning model.

[1159] "Scent data" is digital information for reproducing a specific scent generated by the scent generation model.

[1160] A "fragrance diffuser" is a device that physically generates and releases an actual scent based on scent data.

[1161] A "user action" is an operation or movement that a user performs through a terminal, which triggers the generation of a request.

[1162] "Feedback" refers to the user's evaluations and opinions about the scent they have experienced, and is information used to improve the system and the accuracy of the model.

[1163] "Content viewing" refers to the act of a user viewing video, audio, or other media content.

[1164] MODE FOR CARRYING OUT THE INVENTION

[1165] System Overview

[1166] This system consists of a series of processes that collect olfactory data, digitize it, generate scents using machine learning models, and provide the scents in real time during the user's content viewing experience. Specifically, a server, terminal, and scent diffuser work together.

[1167] Data collection and training phase

[1168] The server uses an olfactory sensor to collect various scent samples and obtain their chemical composition data. This data is stored in a database and used to train a machine learning model. Based on the collected data, the server trains a scent generation model using a machine learning algorithm (e.g., RandomForestRegressor using Scikit-learn), thereby improving its ability to reproduce specific scents.

[1169] User Actions and Request Generation

[1170] When a user is watching content on a smartphone or head-mounted display and a specific action (e.g., a scene change in a movie) occurs, the device detects this. The device's application generates a request for the scent of wet earth and sends it to the server. The server receives this request and generates the corresponding scent data.

[1171] Scent generation and transmission

[1172] The server operates the scent generation model based on the received request and generates specific scent data. The generated scent data is then converted into an appropriate format and sent to the terminal. The terminal then generates and releases an actual scent using a scent diffuser based on the received scent data. The scent diffuser then mixes specific compounds based on the scent data and releases the scent.

[1173] Feedback and System Improvement

[1174] By smelling the generated scent, the user can experience a more realistic and immersive experience. The user's evaluation and feedback of the experience are sent to the server via the device. This feedback is used to improve the accuracy of the scent generation model and the overall system.

[1175] Specific examples

[1176] For example, if a user is using the "Olfactory Cinema Experience App" to watch a movie and the scene switches to a rainy scene, the system will generate data on the scent of "wet earth" and send it to the device. The device's scent diffuser will then release the scent in real time based on this data, providing the user with a more immersive viewing experience.

[1177] Example prompts for generative AI models

[1178] Prompt: Create a scent that matches a scene from this movie. Scene: "Jungle at night", Desired scent: "The scent of damp vegetation"

[1179] This allows users to enjoy the content both visually and olfactory.

[1180] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1181] Step 1:

[1182] The server collects olfactory data. It uses an olfactory sensor to obtain various scent samples as olfactory data, and stores the chemical composition data in a database. The input is the scent sample from the olfactory sensor, and the output is stored in the database as chemical composition data.

[1183] Step 2:

[1184] The server trains a machine learning model based on the collected chemical composition data. Specifically, it uses Scikit-learn to train a RandomForestRegressor model to improve its ability to reproduce specific scents. The input is the chemical composition data stored in the database, and the output is the trained machine learning model.

[1185] Step 3:

[1186] When a user performs a specific action (e.g., scene change) while watching content on a device, the device detects this. The device detects the user's behavior through sensors and interfaces and collects event information. The input is the user's action, and the output is event information.

[1187] Step 4:

[1188] The device generates a request to generate a specific scent based on the collected event information and sends it to the server. For example, if a user watches a rainy scene in a movie, the device generates a request saying, "I need the scent of wet earth." The input is the event information, and the output is a scent generation request.

[1189] Step 5:

[1190] The server runs the scent generation model based on the received request. It uses the trained machine learning model to generate specific scent data and sends it to the device. The input is the scent generation request, and the output is the scent data.

[1191] Step 6:

[1192] The device generates the actual scent using a scent diffuser based on the scent data received from the server. The diffuser mixes the specified chemical ingredients and releases the scent. The input is scent data, and the output is a physical scent.

[1193] Step 7:

[1194] By smelling the generated scent, the user experiences the realism of watching content. The user then inputs their evaluation and feedback about the experience into the device, which then sends this to the server. The input is the user's feedback, and the output is the feedback data.

[1195] Step 8:

[1196] The server collects feedback data from users and reflects it in improving the system and machine learning model. The input is the feedback data, and the output is an improved system or model.

[1197] 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.

[1198] A system combining the olfactory digitization system and emotion engine of the present invention will be described below in detail with reference to an embodiment thereof.

[1199] This system consists of a device for collecting and digitizing olfactory data, a device for recognizing user emotions using an emotion engine, a device for training a machine learning model based on the collected data, a device for generating and transmitting scent data in response to user actions and emotions, and a device for reproducing the scent data as an actual scent.

[1200] Data collection and training phase

[1201] The server uses an olfactory sensor to collect data on various scents and obtain their chemical composition. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[1202] User actions, emotion recognition and request generation

[1203] When a user performs a specific action in a game or in the Metaverse space, the device detects this and collects corresponding event information. For example, a user entering a virtual cafe can be detected.

[1204] The device then activates an emotion engine that analyzes the user's facial, voice, and movement data to recognize their emotions, for example, whether they are feeling happy or anxious.

[1205] The device generates a scent request based on the detected user actions and the recognized emotions. For example, it generates a request such as "The user has entered a virtual cafe and is enjoying themselves, so I need the relaxing aroma of coffee." The request is then sent to the server.

[1206] Scent generation and transmission

[1207] The server runs the scent generation model based on the received request to generate specific scent data, which is then converted into an appropriate format and sent back to the device.

[1208] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[1209] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[1210] User Experience and Feedback

[1211] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. Furthermore, the scent is generated according to the user's emotional state, providing a scent experience appropriate to the user's emotional state.

[1212] Users rate their experience based on the aromas they experience, for example, feeling that the aroma of coffee was "realistic and relaxing."

[1213] The device collects user ratings and feedback and sends it to the server, which uses the feedback to improve the system.

[1214] Specific examples

[1215] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device, which will then use a scent diffuser to recreate these scents, enhancing the user's sense of realism in the game.

[1216] As another example, if a user enters a virtual cafe in the metaverse, and the emotion engine recognizes that the user is enjoying themselves based on their facial expressions and actions, the server will generate the relaxing aroma of coffee or freshly baked bread and send it to the device. The device will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more realistic.

[1217] This system provides new value to users by realizing a real-time olfactory experience in digital space, and solves the problem through the means described in the claims.

[1218] The processing flow will be explained below.

[1219] Step 1:

[1220] The server uses an olfactory sensor to collect data on various scents, which is then stored in a database as chemical composition data.

[1221] Step 2:

[1222] The server preprocesses the stored chemical composition data, removing impurities and noise and streamlining the dataset to obtain high-quality data.

[1223] Step 3:

[1224] The server trains a machine learning model on the pre-processed data, using machine learning algorithms to learn patterns from the data and build a model capable of generating specific scents.

[1225] Step 4:

[1226] A user performs a specific action in the game or metaverse space, such as reaching a specific location in the game or using a specific item.

[1227] Step 5:

[1228] The device detects user actions through sensors and interfaces, such as when a user enters a virtual cafe.

[1229] Step 6:

[1230] The device runs an emotion engine that analyzes the user's facial, voice, and movement data to recognize emotions, for example, whether the user is feeling happy or anxious.

[1231] Step 7:

[1232] The device generates a scent request based on the detected user actions and the recognized emotions, for example, "The user has entered a virtual cafe and is enjoying themselves, so the relaxing aroma of coffee is needed."

[1233] Step 8:

[1234] The terminal transmits the generated scent request to the server.

[1235] Step 9:

[1236] The server runs the scent generation model based on the received request, generates the necessary scent data, converts it into an appropriate format, and sends it back to the device.

[1237] Step 10:

[1238] The device receives the scent data sent from the server, and the scent data is used by the scent diffuser built into the device.

[1239] Step 11:

[1240] The device operates the scent diffuser based on the received scent data, which then mixes specific compounds appropriately to create the actual scent.

[1241] Step 12:

[1242] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. Furthermore, the scent is generated according to the user's emotional state, providing a scent experience appropriate to the user's emotional state.

[1243] Step 13:

[1244] Users rate their experience based on the aromas they experience, for example, feeling that the aroma of coffee was "realistic and relaxing."

[1245] Step 14:

[1246] The device collects user ratings and feedback and sends it to the server.

[1247] Step 15:

[1248] The server analyzes user feedback and improves the scent generation model and the entire system, for example, by improving the accuracy of the scent generation algorithm.

[1249] The above is a detailed step-by-step explanation of the processing flow of the Smell Tech system.

[1250] Example 2

[1251] 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."

[1252] In modern digital experiences and virtual spaces, there is a demand for comprehensive experiences that include not only sight and sound, but also smell. However, existing technologies lack the ability to digitalize the sense of smell or generate scents that respond to the user's emotions, making it difficult to achieve an immersive or realistic experience. In addition, there are limited methods for effectively collecting user feedback and incorporating it into systems and machine learning models.

[1253] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for detecting a user's actions and analyzing the actions and the user's emotions, means for generating and transmitting a request to generate a specific scent based on the analysis results, means for generating scent data using a scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, and means for collecting user feedback and reflecting it in improving the system and model. This makes it possible to generate and reproduce scents in real time according to the user's actions and emotions, realize an olfactory experience in a digital space, and utilize user feedback to continuously improve the system.

[1254] "Olfactory data" is data that quantifies and digitizes information about scents and odors, and includes information about chemical composition and ingredients.

[1255] "Chemical composition data" is data that indicates the types and proportions of chemical components contained in a specific fragrance or substance.

[1256] The "database" is an information recording system for storing and managing collected olfactory data and chemical composition data.

[1257] A "machine learning model" is an algorithm that learns patterns based on collected data and makes predictions and classifications for new inputs.

[1258] "User actions" refer to operations or movements that a user makes within a digital or virtual environment.

[1259] "Emotion analysis" is the process of determining a user's emotional state from data such as facial expressions, voice, and movements.

[1260] A "scent request" is a request to instruct the system to generate a particular scent.

[1261] A "scent generation model" is a machine learning model trained to generate a specific scent as digital data.

[1262] "Scent data" refers to data that includes specific chemical components and their blending ratios for reproducing the created scent.

[1263] A "terminal" is an electronic device or device that allows a user to access a digital space or virtual environment.

[1264] An "aroma diffuser" is a device that generates and releases actual scents based on scent data.

[1265] "Feedback" is information that provides the system with the user's evaluation and opinions regarding the scent they experienced.

[1266] "System improvement" refers to improving the performance and functionality of a system based on collected feedback.

[1267] This invention is a system that combines an olfactory digitization system and an emotion engine, allowing users to experience not only sight and hearing but also smell in digital or virtual environments. The present invention provides a system that comprehensively executes a series of processes from collecting olfactory data to generating scents and recognizing the user's emotions.

[1268] First, the server uses an olfactory sensor to collect data on various scents and obtain their chemical composition data. The specific hardware used includes various types of sensors. For example, olfactory sensors include gas sensors and electrochemical sensors that accurately measure chemical composition. This data is collected using a Python script and stored in a database (e.g., MySQL or PostgreSQL).

[1269] The server then trains a machine learning model based on the collected olfactory data. Specifically, it uses Python's scikit-learn and TensorFlow libraries to build and train a model based on the collected chemical composition data. For example, it uses a random forest algorithm or a neural network to learn specific scent generation patterns.

[1270] When a user performs a specific action in a digital space (e.g., a game or the Metaverse), the device (PC, smartphone, VR device, etc.) detects the action. Here, a script in a game engine based on Unity or Unreal Engine runs to monitor and detect the user's location and actions. For example, if a user is detected entering a virtual cafe, this information is registered as an event.

[1271] The device then uses an emotion engine to analyze the user's facial, voice, and movement data to recognize their emotions. Specifically, it uses the camera to analyze facial expressions using the OpenCV library and sends the data to the Microsoft Azure Face API to obtain the analysis results. At the same time, it collects voice data through the microphone and performs voice analysis using Google Cloud Speech-to-Text. This allows it to recognize the user's emotional state, such as whether they are happy or anxious.

[1272] The device generates a scent request based on the results of the above sentiment analysis and the user's actions. For example, a request such as "The user has entered a virtual cafe and is enjoying themselves, so they need a relaxing coffee aroma" is generated in JSON format and sent to the server. An example of a prompt sentence is:

[1273] A request is sent to the server saying, "The emotion engine has recognized that the user has entered a cafe in a virtual space and is enjoying themselves. Please generate scent data that has a relaxing effect."

[1274] The server then runs a scent generation model based on the received request to generate specific scent data. For example, it uses TensorFlow to generate the scent data and sends it back to the device in JSON or binary format. This scent data is formatted to include specific chemical component information.

[1275] The device receives the scent data sent from the server and sends it to the scent diffuser. The scent diffuser then mixes specific compounds based on the scent data to create the actual scent. Specific devices that can be connected via Bluetooth or Wi-Fi are used. For example, by using a smart device made by Scentee, the appropriate mixture of chemical components is created to recreate the relaxing aroma of coffee.

[1276] Users experience the scent emitted from the scent diffuser, making their digital experience more realistic and immersive. They also provide feedback on their scent experience through an application on their device. For example, a user might write a review such as, "The relaxing coffee aroma was very realistic." This feedback is temporarily stored on the device and later sent to a server. The server analyzes this feedback and uses it to improve the system and machine learning models.

[1277] As described above, the present invention provides a system that realizes a real-time olfactory experience in a digital space and enables the generation of scents according to the user's actions and emotions. Furthermore, by utilizing user feedback and continuously improving the system, it is possible to provide a higher quality olfactory experience.

[1278] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1279] Step 1:

[1280] The server collects scent data using an olfactory sensor. The olfactory sensor (e.g., a gas sensor or electrochemical sensor) is used to obtain chemical composition data of specific scents in real time. The obtained data is converted into CSV format using a Python script and sent to the server. The inputs are scent samples and sensor measurement results. The output is chemical composition data as a CSV file.

[1281] Step 2:

[1282] The server stores the collected chemical composition data in a database, using MySQL or PostgreSQL. The stored data is organized for later use in model training. The CSV file obtained in step 1 is used as input, and the data stored in the database is generated as output.

[1283] Step 3:

[1284] The server trains a machine learning model based on the stored chemical composition data. It uses Python's scikit-learn and TensorFlow libraries to build a scent generation model. Specifically, it uses a random forest algorithm and neural networks to train a model capable of reproducing a specific scent. The input is chemical composition data obtained from the database, and the output is a trained machine learning model.

[1285] Step 4:

[1286] When a user performs a specific action in the digital space, the device detects that action. Using scripts in game engines such as Unity or Unreal Engine, the device monitors the user's location and movements. For example, a user entering a virtual cafe is detected. The input is information about the user's action, and the output is event information generated for the specific action performed by the user.

[1287] Step 5:

[1288] The device collects the user's facial expression, voice, and movement data to recognize emotions. The specific technology used is to analyze facial expressions using a camera and the OpenCV library, and send the data to the Microsoft Azure Face API to obtain the analysis results. Voice data is analyzed using a microphone with Google Cloud Speech-to-Text. The input is the user's facial expression data, voice data, and movement data, and the output is the user's emotional state.

[1289] Step 6:

[1290] The device generates a scent request based on the user's actions and the results of emotion recognition. The scent request includes the specific action performed by the user and instructions for the scent based on the recognized emotion. The input is the event information of the user's actions and the results of emotion recognition. The output is a request to generate a specific scent in JSON format, which is sent to the server.

[1291] Step 7:

[1292] The server generates scent data based on the received scent request using a scent generation model. It runs a TensorFlow model to generate the specified scent chemical components. The input is the scent request and the machine learning model, and the output is the generated scent data in JSON format.

[1293] Step 8:

[1294] The server sends the generated scent data to the terminal. The scent data is transmitted to the terminal via the network and received by the terminal. The input is the generated scent data, and the output includes the scent data sent to the terminal.

[1295] Step 9:

[1296] The device generates an actual scent using a scent diffuser based on the received scent data. The device transmits the data to the scent diffuser, which mixes specific compounds based on the data and releases the scent. The input is the received scent data, and the output is a physically reproduced scent.

[1297] Step 10:

[1298] The user experiences the released scent and provides feedback. They input their evaluation and opinions about the scent experience through an application on their device. The input is the user's feedback, and the output is the collected feedback information.

[1299] Step 11:

[1300] The device stores the user's feedback and later transmits it to the server. The feedback is reflected in the system's improvements and is used to generate future scents. The input is the user's feedback information, and the output includes the feedback transmitted to the server.

[1301] Through these steps, this system provides a real-time olfactory experience in the digital space and can generate and reproduce scents according to the user's emotions.

[1302] (Application example 2)

[1303] 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."

[1304] Conventional virtual reality (VR) experiences and metaverse spaces rely solely on sight and hearing, limiting the user's sense of immersion and the realism of the experience. Furthermore, they are unable to provide personalized content based on the user's emotions and behavior, resulting in a uniform user experience and making it difficult to provide an optimal experience tailored to each user's condition. The present invention aims to solve these problems by providing an olfactory digitization system that provides a more realistic and personalized VR experience.

[1305] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1306] In this invention, the server includes means for collecting olfactory data and storing it in a database as chemical composition data, means for training a machine learning model based on the olfactory data, means for generating and transmitting a request to generate a specific scent in response to a user's actions and emotions, means for generating scent data using the scent generation model in response to the request and transmitting it to a corresponding terminal, means for receiving the scent data at the terminal and generating an actual scent using a scent diffuser, and means for collecting feedback from users and reflecting it in improving the system and model. This allows for the generation of specific scents in response to the user's actions and emotions, making the experience in the VR space more immersive and realistic.

[1307] "Olfactory data" is information about a particular scent expressed as chemical composition data.

[1308] "Chemical composition data" is olfactory data that has been quantified and expressed in a form that can be stored in a database.

[1309] The "database" is a system for systematically storing and managing collected olfactory data and other related information.

[1310] A "machine learning model" is an algorithm trained to generate specific scents based on collected olfactory data.

[1311] "User actions" refer to specific actions or operations performed by the user within the VR space.

[1312] "Emotion" refers to the psychological state that can be recognized from the user's facial expressions, voice, and behavior.

[1313] A "scent generation model" is an algorithm trained to generate specific scent data.

[1314] A "terminal" is a device that receives olfactory data and controls the scent diffuser.

[1315] An "aroma diffuser" is a device that mixes specific compounds based on aroma data and releases aromas.

[1316] "Feedback" refers to the user's evaluation or opinion based on the scent they experienced, their overall experience, etc.

[1317] The following describes a specific embodiment of a system that combines the olfactory digitization system and emotion engine of the present invention, thereby realizing an immersive and personalized virtual reality (VR) experience for users.

[1318] Data collection and training phase

[1319] The server uses an olfactory sensor to collect data on various scents and obtain their chemical composition. This data is stored in a database and used to train a machine learning model. The server then uses a machine learning algorithm to train a scent generation model based on the collected data. It learns patterns from the dataset and improves its ability to reproduce specific scents.

[1320] User actions, emotion recognition and request generation

[1321] When a user performs a specific action in a game or in the metaverse space, the device detects this and collects corresponding event information. For example, the device detects that the user is entering a virtual cafe. The device then activates its emotion engine and analyzes the user's facial, voice, and movement data to recognize their emotions. For example, it identifies whether the user is enjoying themselves or feeling anxious. The device generates a scent request based on the detected user action and the recognized emotion. For example, it generates a request such as "The user has entered a virtual cafe and is enjoying themselves, so I need the relaxing aroma of coffee," and sends this request to the server.

[1322] Scent generation and transmission

[1323] The server runs a scent generation model based on the received request to generate specific scent data. The generated scent data is converted into an appropriate format and sent back to the device. The device receives the scent data sent from the server. This scent data is used by a scent diffuser built into the device. The device runs the scent diffuser based on the received scent data. The scent diffuser appropriately mixes specific compounds based on the data to generate the actual scent.

[1324] User Experience and Feedback

[1325] The user smells the scent emitted from the scent diffuser, making the experience in the digital space more realistic and immersive. In addition, scents are generated according to emotions, providing an appropriate scent experience for the user's emotional state. The user evaluates the experience based on the scent generated. For example, the user may feel that the "relaxing coffee aroma was realistic." The device collects user evaluations and feedback and sends it to the server. This feedback is used to improve the system.

[1326] Specific examples

[1327] For example, if a user is playing an adventure game and steps into an ancient temple, the server will generate scent data of damp stone and old books and send it to the device. The device will then use a scent diffuser to recreate these scents, further enhancing the user's sense of realism in the game. As another example, if a user enters a virtual cafe in the metaverse, and the emotion engine recognizes that the user is enjoying themselves based on their facial expressions and actions, the server will generate the relaxing scent of coffee and freshly baked bread and send it to the device. The device will then use a scent diffuser to recreate these scents, making the user's experience in the virtual space feel more real.

[1328] Prompt Sentence Examples

[1329] A user enters a virtual cafe in a VR space, and the emotion engine recognizes this as "fun" based on data collected by the camera and microphone. Please generate a scent request for this action.

[1330] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1331] Step 1:

[1332] The device tracks the user's actions within the VR environment. Specifically, it collects user movement data through the interface and sensors, processes that data, and detects specific actions. For example, when a user enters a virtual cafe, their movements are tracked and event information is collected. Sensor and camera data is used as input, and a list of detected actions is output.

[1333] Step 2:

[1334] The device activates an emotion engine and analyzes the user's facial and voice data, thereby recognizing the user's emotions. Specifically, data is acquired in real time from the camera and microphone installed in the HMD, and the data is analyzed using an emotion recognition algorithm. Facial and voice data are used as input, and the output is a tag of the recognized emotion.

[1335] Step 3:

[1336] The device generates a scent request based on the detected user actions and the recognized emotions. For example, a request may be generated such as, "The user has entered a virtual cafe and is enjoying themselves, so I need a relaxing coffee aroma." This process uses tags representing the user's actions and emotions as input, and outputs a scent request.

[1337] Step 4:

[1338] The device sends the generated scent request to the server. Specifically, it sends the scent request to the server via the Internet and waits for a reply from the server. The scent request is used as input, and the output is the transmission to the server.

[1339] Step 5:

[1340] The server activates the scent generation model based on the received scent request and generates specific scent data. Specifically, it uses a machine learning model on the server to generate a scent corresponding to the request. The scent request is used as input, and the generated scent data is the output.

[1341] Step 6:

[1342] The server returns the generated scent data to the terminal. Specifically, it converts the scent data into an appropriate format and sends it to the terminal. The generated scent data is used as input, and the output is sent to the terminal.

[1343] Step 7:

[1344] The device operates the scent diffuser based on the received scent data. Specifically, it sends the scent data to the scent diffuser, which then mixes specific compounds and releases the scent. The received scent data is used as input, and the output is the actual scent that is generated.

[1345] Step 8:

[1346] The user experiences the scent emitted from the scent diffuser, making the digital experience realistic and immersive. The input is the scent emitted from the diffuser, and the output is the user's experience.

[1347] Step 9:

[1348] The user provides feedback based on the aroma they experienced. For example, they input feedback such as "The relaxing aroma of coffee was realistic." The input is the user's feedback, and the output is the collected ratings and opinions.

[1349] Step 10:

[1350] The device sends the feedback collected from the user to the server. This feedback can be used to improve the system and model in the future. Specifically, the feedback data is sent to the server via the Internet. The user's feedback is used as input, and the output is sent to the server.

[1351] 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.

[1352] 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.

[1353] 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.

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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).

[1358] 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.

[1359] 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."

[1360] 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.

[1361] 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).

[1362] 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.

[1363] 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.

[1364] 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.

[1365] 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.

[1366] 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.

[1367] 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.

[1368] 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.

[1369] 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.

[1370] 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.

[1371] 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.

[1372] The following is further disclosed regarding the above embodiment.

[1373] (Claim 1)

[1374] a means for collecting olfactory data and storing it in a database as chemical composition data;

[1375] a means of training a machine learning model based on olfactory data; and

[1376] means for generating and transmitting a request to generate a specific scent in response to a user's action;

[1377] a means for generating scent data using the scent generation model in response to a request and transmitting the generated scent data to a corresponding terminal;

[1378] A means for receiving scent data at a terminal and generating an actual scent using a scent diffuser;

[1379] A means of collecting user feedback and incorporating it into improvements to the system and models;

[1380] A system including:

[1381] (Claim 2)

[1382] 2. The system according to claim 1, wherein the terminal includes means for detecting user actions through a sensor or an interface and collecting event information.

[1383] (Claim 3)

[1384] 10. The system of claim 1, wherein the scent diffuser includes means for mixing specific compounds and releasing the scent based on the scent data.

[1385] "Example 1"

[1386] (Claim 1)

[1387] a means for collecting olfactory data and storing it in a database as chemical composition data;

[1388] a means of training a machine learning model based on olfactory data; and

[1389] means for generating and transmitting a request to generate a specific scent in response to a user's action;

[1390] a means for generating scent data using the scent generation model in response to a request and transmitting the generated scent data to a corresponding terminal;

[1391] A means for receiving scent data at a terminal and generating an actual scent using a scent diffuser;

[1392] A means of collecting user feedback and incorporating it into improvements to the system and models;

[1393] a cloud storage means for storing comprehensive scent data;

[1394] a server means for training a scent generation model using a machine learning library;

[1395] a terminal means for detecting a specific event and transmitting the event to a server in a request format;

[1396] A communication means for linking the terminal and the scent diffuser;

[1397] A system including:

[1398] (Claim 2)

[1399] 2. The system according to claim 1, wherein the terminal includes means for detecting user actions through a sensor or an interface and collecting event information.

[1400] (Claim 3)

[1401] 10. The system of claim 1, wherein the scent diffuser includes means for mixing specific compounds and releasing the scent based on the scent data.

[1402] "Application Example 1"

[1403] (Claim 1)

[1404] a means for collecting olfactory data and storing it in a database as chemical composition data;

[1405] a means of training a machine learning model based on olfactory data; and

[1406] means for generating and transmitting a request to generate a specific scent in response to a user's action;

[1407] a means for generating scent data using the scent generation model in response to a request and transmitting the generated scent data to a corresponding terminal;

[1408] A means for receiving scent data at a terminal and generating an actual scent using a scent diffuser;

[1409] A means of collecting user feedback and incorporating it into improvements to the system and models;

[1410] A means for generating and providing a scent tailored to a specific scene in real time while a user is viewing content;

[1411] A system including:

[1412] (Claim 2)

[1413] 2. The system according to claim 1, wherein the terminal includes means for detecting user actions through a sensor or an interface and collecting event information.

[1414] (Claim 3)

[1415] 10. The system of claim 1, wherein the scent diffuser includes means for mixing specific compounds and releasing the scent based on the scent data.

[1416] "Example 2: Combining Emotion Engines"

[1417] (Claim 1)

[1418] a means for collecting olfactory data and storing it in a database as chemical composition data;

[1419] a means of training a machine learning model based on olfactory data; and

[1420] means for detecting a user's action and analyzing the action and the user's emotion;

[1421] means for generating and transmitting a request to generate a specific scent based on the analysis results;

[1422] a means for generating scent data using the scent generation model in response to a request and transmitting the generated scent data to a corresponding terminal;

[1423] A means for receiving scent data at a terminal and generating an actual scent using a scent diffuser;

[1424] A means of collecting user feedback and incorporating it into improvements to the system and models;

[1425] A system including:

[1426] (Claim 2)

[1427] 2. The system according to claim 1, wherein the terminal includes means for detecting user behavior through sensors and interfaces, collecting event information, and recognizing emotions by analyzing facial expression, voice, and movement data.

[1428] (Claim 3)

[1429] 10. The system of claim 1, wherein the scent diffuser includes means for mixing specific compounds and releasing the scent based on the scent data.

[1430] "Application example 2 when combining emotion engines"

[1431] (Claim 1)

[1432] a means for collecting olfactory data and storing it in a database as chemical composition data;

[1433] a means of training a machine learning model based on olfactory data; and

[1434] means for generating and transmitting requests to generate specific scents in response to user actions and emotions;

[1435] a means for generating scent data using the scent generation model in response to a request and transmitting the generated scent data to a corresponding terminal;

[1436] A means for receiving scent data at a terminal and generating an actual scent using a scent diffuser;

[1437] A means of collecting user feedback and incorporating it into improvements to the system and models;

[1438] A system including:

[1439] (Claim 2)

[1440] 10. The system of claim 1, wherein the terminal includes means for detecting user behavior and emotions through sensors and interfaces and collecting event information.

[1441] (Claim 3)

[1442] 10. The system of claim 1, wherein the scent diffuser includes means for mixing specific compounds and releasing the scent based on the scent data. [Explanation of symbols]

[1443] 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 collecting olfactory data and storing it in a database as chemical composition data; a means of training a machine learning model based on olfactory data; and means for generating and transmitting a request to generate a specific scent in response to a user's action; a means for generating scent data using the scent generation model in response to a request and transmitting the generated scent data to a corresponding terminal; A means for receiving scent data at a terminal and generating an actual scent using a scent diffuser; A means of collecting user feedback and incorporating it into improvements to the system and models; A system including:

2. The system according to claim 1, wherein the terminal includes means for detecting user actions through a sensor or an interface and collecting event information.

3. 10. The system of claim 1, wherein the scent diffuser includes means for mixing specific compounds and emitting a scent based on the scent data.

Images