system

Abstract

Provide a system. A sensor means for acquiring odor data; terminal means for preprocessing odor data from said sensor means; a server means for receiving the preprocessed odor data transmitted from the terminal means; means for extracting features from the received data; an artificial intelligence means for predicting the expression of a specific scent from the extracted feature quantity; means for transmitting the predicted scent representation to a terminal means; a means for displaying the transmitted scent description to a user in the terminal means; A system including:

Description

[Technical Field]

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

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

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

[0004] Scents are abstract, and the way they are expressed varies from person to person. For example, even if we say something like a citrus scent, its intensity and subtle nuances are difficult to verbalize, making it difficult to establish a unified standard. Furthermore, when dealing with scents as data, previous technology lacked a system that could automatically and accurately extract scent features and predict the expression of a specific scent. As a result, information about scents could not be shared, making it difficult to design and evaluate scents for specific uses. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. First, a sensor means is provided for acquiring odor data. Then, a terminal means is provided for preprocessing the odor data obtained from the sensor means, and a server means is provided for receiving the preprocessed odor data transmitted from the terminal means. Next, the server means has a means for extracting features from the received data, and is equipped with an artificial intelligence means for predicting a specific odor expression from the extracted features. Finally, a means is provided for transmitting the predicted odor expression to the terminal means, and the terminal means includes a means for displaying the transmitted odor expression to the user. This makes it possible to quantitatively evaluate odors and provide the user with a verbalized odor analysis result. Furthermore, by configuring the artificial intelligence means to predict the odor expression from the features using a neural network, more accurate predictions are possible.

[0006] "Odor data" is digital data that represents the chemical information of an odor detected by an odor sensor.

[0007] The "sensor means" is a device for detecting odors and acquiring the information as digital data.

[0008] The "terminal means" is a computer system or device for preprocessing data obtained from the odor sensor and transmitting the data to the server.

[0009] "Preprocessing" is the process of improving the quality of the odor data obtained from the sensor by performing noise removal, scaling, etc.

[0010] The "server means" is a system equipped with a central processing unit for receiving odor data transmitted from the terminal means and executing specific processing.

[0011] "Features" are specific attributes or indicators extracted from odor data, which quantitatively express the characteristics of a scent.

[0012] "Artificial intelligence means" refers to the artificial intelligence algorithms or models used to predict a particular scent expression from the features.

[0013] A "neural network" is a type of machine learning model that mimics the neural circuits of the human brain and is used for complex pattern recognition and data analysis.

[0014] "Prediction result" is data obtained when the artificial intelligence means predicts the description of a particular scent.

[0015] A "communications protocol" is a system that defines the rules and procedures for securely sending and receiving data.

[0016] The "display means" refers to an interface or device on a terminal for visually presenting the prediction results to the user. [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 illustrating 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] The present invention relates to a system for quantifying odor data and verbalizing a specific odor based on the quantified data. Specific embodiments of this system will be described below.

[0039] Program Overview

[0040] This system consists of an odor sensor, a terminal, a server, and an artificial intelligence model. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, preprocesses it, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the expression of the scent from the features. Finally, the prediction result is sent to the terminal and displayed to the user.

[0041] Specific operation of the system

[0042] Acquisition and transmission of odor data (terminal)

[0043] The device activates the odor sensor and acquires odor data in a specific environment. This data is converted into a digital format and preprocessed. Preprocessing includes noise reduction and scaling. The preprocessed data is then sent to a server using a secure communication protocol (e.g., HTTPS).

[0044] Data reception and preprocessing (server)

[0045] The server receives the data sent from the device. The received data requires further preprocessing, such as filtering and normalization. The processed data is then used for feature extraction.

[0046] Feature extraction and scent prediction (server)

[0047] The server has a means of extracting features from the preprocessed data. Specifically, it calculates features based on the concentration of specific chemical components and pattern recognition. These features are converted into vector format and input into an artificial intelligence model. The artificial intelligence model uses a neural network in particular, and predicts the aroma expression (e.g., citrus, floral, etc.) from the input features.

[0048] Sending and displaying prediction results (terminal)

[0049] The server then sends the predicted scent description to the device, which then displays the result to the user. The result may be presented in the form of, for example, "This scent is citrus-like and slightly sweet and sour."

[0050] Specific examples

[0051] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server, which performs further preprocessing and feature extraction. The extracted features are then input into an artificial intelligence model, which generates a prediction result: "citrus-like, slightly sweet and sour." This result is sent to the device and displayed to the user.

[0052] This system enables quantitative evaluation of scents and provides users with verbalized scent analysis results, facilitating the design and evaluation of scents for specific applications.

[0053] The processing flow will be explained below.

[0054] Step 1: Acquire scents (device)

[0055] The device activates the odor sensor, detects odors emanating from the object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components.

[0056] Step 2: Preprocessing the data (terminal)

[0057] The device preprocesses the acquired odor data, specifically removing noise from the data and scaling or filtering as necessary. The preprocessed data is then converted into a format suitable for analysis.

[0058] Step 3: Sending data (terminal)

[0059] The preprocessed odor data is transmitted to a server using a secure communication protocol (e.g., HTTPS), ensuring data integrity and security.

[0060] Step 4: Receiving Data (Server)

[0061] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step.

[0062] Step 5: Data Preprocessing (Server)

[0063] The server performs further pre-processing on the received data, including normalizing, filtering, and further noise reduction, to improve the data quality and make it suitable for analysis.

[0064] Step 6: Feature extraction (server)

[0065] The server extracts features from the pre-processed data, which can be based on the concentration of specific chemical components or pattern recognition, and represent attributes or indicators required for subsequent analysis.

[0066] Step 7: Scent prediction (server)

[0067] The server inputs the extracted features into an AI model. This AI model is built using a neural network and predicts the expression of a specific scent from the features. The prediction results are verbalized and stored on the server.

[0068] Step 8: Sending prediction results (server)

[0069] The server sends the prediction results to the device, which then provides the user with a representation of the predicted scent.

[0070] Step 9: View the results (terminal)

[0071] The device receives the prediction results sent from the server and displays them to the user. The results are presented in a format that is easy for the user to understand, such as "This scent is citrus-like and slightly sweet and sour."

[0072] Step 10: Check the results (user)

[0073] The user checks the prediction results displayed on the device, evaluates whether the results match their own intuition, and can provide feedback on the results if necessary.

[0074] Example 1

[0075] 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."

[0076] Conventional systems that analyze odor data and verbalize scents have had issues with data accuracy and security. It is also difficult to accurately extract and verbalize the characteristics of odors, making it difficult to provide users with useful information. Furthermore, processing speed and prediction accuracy are often insufficient, making them impractical.

[0077] 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.

[0078] In this invention, the server includes means for additionally preprocessing the received data, filtering and normalizing it, means for extracting features from the additionally preprocessed data, and means for converting the extracted features into vector format, thereby enabling highly accurate and efficient data analysis and scent prediction.

[0079] "Odor data" is digital data that represents information about odors in a particular environment, obtained by a sensor means.

[0080] The "sensor means" is a device for acquiring odor data, which senses odors from any environment and converts them into digital data.

[0081] The "terminal means" is a device that receives odor data obtained from the sensor means and performs preprocessing, and also has the function of transmitting the processed data to the server means.

[0082] "Preprocessing" refers to the process of removing noise and scaling odor data acquired from the sensor means to make it easier to analyze.

[0083] The "server means" is a device that receives preprocessed odor data sent from the terminal means, and performs additional preprocessing, feature extraction, and prediction using artificial intelligence means.

[0084] "Additional pre-processing" refers to the filtering and normalization processes that the server means performs on the data it receives, in order to improve the consistency and accuracy of the data.

[0085] "Features" are information that indicates the concentration and pattern of specific chemical components, extracted from odor data that has undergone preprocessing and additional preprocessing.

[0086] The "vector format" is a format for expressing feature quantities as numerical data, and is a data format used for inputting data to artificial intelligence means.

[0087] "Artificial intelligence means" refers to software or hardware that predicts the expression of a scent from features, primarily using techniques such as neural networks.

[0088] A "scent description" is a specific description of a scent based on scent data predicted by artificial intelligence means, and is information provided in a format that is understandable to the user.

[0089] A "secure communication protocol" is a communication protocol used to ensure confidentiality and integrity of information when sending and receiving data, and examples include HTTPS.

[0090] The present invention relates to a system for quantifying odor data and verbalizing a specific odor based on the quantified data. Specific embodiments of this system will be described below.

[0091] System Overview

[0092] This system consists of an odor sensor, a terminal, a server, and an artificial intelligence model. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, performs additional preprocessing, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the scent expression from the features. Finally, the prediction result is sent to the terminal and displayed to the user.

[0093] Acquisition and preprocessing of odor data (terminal)

[0094] The user uses an odor sensor connected to a device. For example, when the user holds an orange peel close to the sensor, the sensor captures odor data in the environment and converts it into digital data. This data is then pre-processed on the device, with noise reduction and scaling. The pre-processed data is then sent to a server using a secure communication protocol such as HTTPS.

[0095] Data reception and additional preprocessing (server)

[0096] The server receives the preprocessed odor data sent from the device, which undergoes additional preprocessing such as filtering and normalization to improve consistency and accuracy, preparing the data for feature extraction.

[0097] Feature extraction and scent prediction (server)

[0098] The server extracts features from the pre-processed data. For example, it analyzes the concentration and patterns of specific chemical components and converts them into vector format. This feature vector is input into an artificial intelligence model using a neural network, which predicts the scent expression (e.g., citrus or floral) from the odor data.

[0099] Sending and displaying prediction results (terminal)

[0100] The server sends the predicted scent description to the device, which then receives the result and displays it to the user. For example, the result might be something like, "This scent is citrusy and slightly sweet and sour."

[0101] Specific examples

[0102] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server using a secure communication protocol. The server then performs further preprocessing on the received data and extracts features. The extracted features are then input into an artificial intelligence model, which generates a prediction result: "citrus-like, slightly sweet and sour." This result is sent to the device and displayed to the user.

[0103] Prompt Sentence Examples

[0104] An example of a prompt to be input to the generative AI model is as follows:

[0105] 1. "Describe the smell of orange peel."

[0106] 2. "Predict the scent description from this smell data."

[0107] 3. "Please describe in words the scent detected by the odor sensor."

[0108] This system enables quantitative evaluation of scents and can quickly provide users with verbalized scent analysis results, facilitating the design and evaluation of scents for specific applications.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1: Acquiring odor data (device)

[0111] When a user brings an orange peel close to the sensor, an odor sensor connected to the device captures odor data in the environment. The sensor detects this odor as an analog signal and converts it into digital data. Specifically, the sensor measures the concentration of chemical components and converts that data into binary code. At this stage, the input is the odor components emanating from the orange peel, and the output is odor data in digital format.

[0112] Step 2: Data preprocessing (terminal)

[0113] The device performs preprocessing on the acquired digital odor data. Specifically, it applies a noise reduction filter to the data and scales it to improve the quality of the data. Noise reduction is the process of removing random noise, and scaling is the process of confining the data within a certain range. The input at this stage is the digital odor data sent from the sensor, and the output after processing is the preprocessed odor data.

[0114] Step 3: Send data (terminal)

[0115] The preprocessed odor data is sent to the server using a secure communication protocol (e.g., HTTPS). At this time, the terminal encrypts the data using AES to ensure data confidentiality. Specifically, the terminal generates a data packet and sends it to the server using the HTTPS protocol. At this stage, the input is the preprocessed odor data, and the output is securely transmitted data.

[0116] Step 4: Receiving data (server)

[0117] The server receives preprocessed smell data sent from the device. The server verifies the received data and checks for unauthorized access or data corruption. Specific operations include the server decoding the received packets and verifying the integrity of the data. The input at this stage is the secure transmission data, and the output is the verified smell data.

[0118] Step 5: Preprocessing for adding data (server)

[0119] The server performs additional preprocessing on the received data. Specifically, it filters and normalizes the data to improve the consistency and accuracy of the data. Filtering is the operation of removing unnecessary data, and normalization is the operation of converting the data to a unified scale. The input at this stage is the verified odor data, and the output is the odor data that has undergone additional preprocessing.

[0120] Step 6: Feature extraction (server)

[0121] The server extracts features from the additionally preprocessed data. Specifically, it analyzes the concentrations and patterns of specific chemical components in the data and converts them into vector format. These features are important data to input into the subsequent artificial intelligence model. The input at this stage is the additionally preprocessed odor data, and the output is a feature vector.

[0122] Step 7: Scent prediction (server)

[0123] The server inputs the feature vector into an artificial intelligence model (e.g., a neural network) to predict the aroma expression. Specifically, the server uses the neural network to generate an aroma expression, such as "citrus, slightly sweet and sour," from the features. The input at this stage is the feature vector, and the output is the predicted aroma expression.

[0124] Step 8: Send prediction results (server)

[0125] The server sends the predicted scent representation to the device, which then displays a specific scent representation on the device to the user. Specific operations include the server formatting the prediction results in JSON and sending them to the device again using a secure protocol. The input at this stage is the predicted scent representation, and the output is securely transmitted data.

[0126] Step 9: Display the results (terminal)

[0127] The device displays the received prediction results to the user. For example, the screen might display "This scent is citrus-like and slightly sweet and sour." Specific operations include the device analyzing the received data and displaying the results on the user interface. The input at this stage is the transmitted prediction data, and the output is a representation of the scent displayed to the user.

[0128] (Application example 1)

[0129] 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."

[0130] Conventional odor data analysis systems were able to quantify acquired odor data and verbalize specific odors based on that data, but they lacked the functionality to recommend related product information when providing the analysis results to users. As a result, users considering purchasing a specific product faced the challenge of not being provided with sufficient information based on the analysis results alone. Specifically, even if a scent was detected in a fragrance section, the system was unable to effectively support users' purchasing behavior because it did not provide product information related to that scent or recommendations for similar products.

[0131] 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.

[0132] In this invention, the server includes a sensor means for acquiring odor data, a terminal means for preprocessing the odor data from the sensor means, a server means for receiving the preprocessed odor data transmitted from the terminal means, a means for extracting features from the received data, an artificial intelligence means for predicting a description of a specific odor from the extracted features, a means for transmitting the predicted odor description to the terminal means, a means for displaying the transmitted odor description to the user on the terminal means, and a recommendation means for recommending related product information based on the odor description displayed to the user. This allows the user to receive not only the analysis results but also product information related to the odor and recommendations of similar products, thereby supporting purchasing behavior.

[0133] "Odor data" is quantitative information about a specific scent obtained by an odor sensor.

[0134] "Sensor means" refers to a device or mechanism for acquiring odor data.

[0135] The "terminal means" is an electronic device that preprocesses the odor data acquired from the odor sensor and communicates with other devices or systems as necessary.

[0136] The "server means" is a central processing unit that receives and processes data sent from the terminal, and further performs feature extraction and predictions using artificial intelligence.

[0137] "Features" are numerical and parametric information extracted from odor data that is necessary to specifically express a scent.

[0138] "Artificial intelligence means" refers to a system or device that uses machine learning algorithms such as neural networks to predict the expression of a scent from features.

[0139] "Description of scent" refers to verbalized information about a specific scent, such as "citrus-like, slightly sweet and sour."

[0140] A "recommendation means" is a system or algorithm that recommends related product information or similar products based on the analyzed scent expression.

[0141] The present invention relates to a system for quantifying odor data, verbalizing a specific scent based on the quantified data, and recommending related product information to a user. Specific embodiments of the present invention will be described below.

[0142] System Overview

[0143] The system comprises a sensor means, a terminal means, a server means, an artificial intelligence means, and a recommendation means.

[0144] 1. Sensor means

[0145] The sensor means is a device for acquiring odor data, and may be, for example, a gas sensor or an electronic nose. This sensor detects the scent in a specific environment and acquires it as digital data.

[0146] 2. Terminal means

[0147] The terminal means preprocesses the odor data obtained from the sensor means and transmits it to the server means. The preprocessing includes noise removal and data scaling. The terminal means transmits the preprocessed odor data to the server means using a secure communication protocol (e.g., HTTPS).

[0148] 3. Server Means

[0149] The server receives the preprocessed odor data sent from the terminal, performs further preprocessing and extracts features, and then inputs the features into the artificial intelligence to predict the expression of the scent.

[0150] 4. Artificial Intelligence Means

[0151] The artificial intelligence means is a model that predicts the expression of a scent from feature quantities, particularly using a neural network. A pre-trained neural network is used to generate a scent expression, such as "citrus-like, slightly sweet and sour." The prediction result is sent to the terminal means via the server means.

[0152] 5. Recommendation method

[0153] The recommendation system is a system that recommends related product information and similar products based on the scent description displayed to the user. The analysis results are linked to a product database to recommend the most suitable products to the user.

[0154] Specific examples of operation procedures

[0155] A specific example of the operation procedure is shown below: A user picks up a specific perfume bottle at a fragrance counter, starts the application, and holds the scent over the sensor. The sensor means acquires scent data and transmits the data to the terminal means.

[0156] The terminal means preprocesses the data and then transmits it to the server means using secure communication. The server means receives the data, performs further preprocessing, and extracts features. The features are then input into the artificial intelligence means to predict the expression of the scent.

[0157] The prediction result is sent to the terminal means and displayed to the user. Finally, the recommendation means recommends related product information based on the analysis result.

[0158] Example prompts for generative AI models

[0159] "I would like to develop an application for analyzing odor data. Please write a program in Python that uses a neural network to predict odors based on data obtained from an odor sensor. The program must include processes for preprocessing the odor data, extracting features, making predictions using an AI model, and displaying the results in a format that is easy for humans to understand."

[0160] In this way, the system of the present invention provides users with scent analysis and related product information, helping them to have a more comfortable purchasing experience.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1: Acquiring odor data

[0163] A user activates an odor sensor using a terminal. The sensor means acquires the surrounding odor as data. At this time, the sensor means receives the odor in the environment as input, and outputs the odor data in digital format. Specifically, for example, an electronic nose uses multiple gas sensors to detect the chemical components of the odor and outputs their concentration information as digital data.

[0164] Step 2: Preprocessing the odor data

[0165] The terminal receives the digital data acquired from the odor sensor and performs preprocessing. The input here is the odor data acquired from the sensor means, and the output is the preprocessed data. The terminal means converts the data into a format that is easy to analyze later by removing noise and normalizing the data. Specific examples include noise removal by filtering and data normalization by scaling.

[0166] Step 3: Sending data

[0167] The preprocessed odor data is sent from the device to the server using a secure communication protocol (e.g., HTTPS). The input is the preprocessed data, and the output is the data sent to the server. Specifically, the device encrypts the data using HTTPS and transfers it securely to the server.

[0168] Step 4: Receiving data and further preprocessing

[0169] The server receives the data sent from the device and performs further preprocessing. The input is the data sent from the device, and the output is the preprocessed data. The server filters and normalizes the data, preparing it for feature extraction.

[0170] Step 5: Feature extraction

[0171] The server extracts features from the preprocessed data. The input here is further preprocessed data, and the output is features. Specifically, the server extracts important parameters using chemical component concentrations and pattern recognition algorithms, and converts them into vector format as features.

[0172] Step 6: Predict the scent

[0173] The server inputs the extracted features into an artificial intelligence means (neural network) to predict the scent expression. The input is the features and the output is the scent expression. The pre-trained neural network generates a scent expression such as "citrus, slightly sweet and sour" from the input features.

[0174] Step 7: Submit and view prediction results

[0175] The server sends the predicted scent expression to the terminal. The input is the predicted scent expression, and the output is the data sent to the terminal. The terminal receives this data and displays it to the user. Specifically, the terminal uses a user interface to display the analysis results in the form of "This scent is citrus-like and slightly sweet and sour."

[0176] Step 8: Recommend product information

[0177] The device recommends related product information based on the displayed scent description. The input is the displayed scent description, and the output is recommended product information. Specifically, the analysis results are compared with a product database, and appropriate product information (e.g., related perfumes and air fresheners) is presented to the user.

[0178] 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.

[0179] The present invention combines an emotion engine with a system that quantifies odor data and verbalizes specific odors based on that data. The emotion engine can recognize the user's emotions and adjust the expression of the odor based on those emotions. Specific embodiments of this system are described below.

[0180] Program Overview

[0181] This system consists of an odor sensor, a terminal, a server, an artificial intelligence model, and an emotion engine. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, preprocesses it, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the expression of the scent from the features. The emotion engine recognizes the user's emotion and adjusts the expression of the scent based on that emotion. Finally, the adjusted prediction result is sent to the terminal and displayed to the user.

[0182] Specific operation of the system

[0183] Acquisition and transmission of odor data (terminal)

[0184] The device activates the odor sensor, detects odors emanating from the target object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components. The acquired odor data is preprocessed and sent to the server using a secure communication protocol (e.g., HTTPS).

[0185] Data reception and preprocessing (server)

[0186] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step. The server then performs further pre-processing on the received data, such as normalization, filtering, and further noise reduction.

[0187] Feature extraction and scent prediction (server)

[0188] The server extracts features from the preprocessed data. These features are based on the concentration of specific chemical components or pattern recognition, and represent the attributes and indicators required for subsequent analysis. The extracted features are input into an artificial intelligence model, which uses a neural network to predict the expression of the scent from the input features.

[0189] Emotion recognition and scent adjustment (terminal)

[0190] The device activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expression data or voice data to recognize the emotion. For example, it determines whether the user is relaxed or nervous. Based on the emotion recognized by the emotion engine, the server adjusts the predicted scent expression accordingly.

[0191] Sending and displaying prediction results (terminal)

[0192] The adjusted prediction results are sent to the device, which receives the scent description sent from the server and displays it to the user. The displayed results are presented in a user-friendly format, such as "This scent is citrus-like and slightly sweet and sour."

[0193] Specific examples

[0194] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server, which performs further preprocessing and feature extraction. The extracted features are then input into an artificial intelligence model, which generates a prediction result of "citrus, slightly sweet and sour." If the emotion engine recognizes the user's emotion as "relaxed," the server adjusts the prediction result to something like "citrus with a relaxing effect." This result is sent to the device and displayed to the user.

[0195] This system enables quantitative evaluation of scents and provides users with verbalized scent analysis results. Furthermore, by adjusting the scent expression based on the user's emotions, more appropriate scent evaluation and design becomes possible.

[0196] The processing flow will be explained below.

[0197] Step 1: Acquire scents (device)

[0198] The device activates the odor sensor, detects odors emanating from the object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components.

[0199] Step 2: Preprocessing the data (terminal)

[0200] The device preprocesses the acquired odor data, specifically removing noise from the data and scaling or filtering as necessary. The preprocessed data is then converted into a format suitable for analysis.

[0201] Step 3: Sending data (terminal)

[0202] The preprocessed odor data is transmitted to a server using a secure communication protocol (e.g., HTTPS), ensuring data integrity and security.

[0203] Step 4: Receiving Data (Server)

[0204] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step.

[0205] Step 5: Data Preprocessing (Server)

[0206] The server performs further pre-processing on the received data, including normalizing, filtering, and further noise reduction, to improve the data quality and make it suitable for analysis.

[0207] Step 6: Feature extraction (server)

[0208] The server extracts features from the pre-processed data, which can be based on the concentration of specific chemical components or pattern recognition, and represent attributes or indicators required for subsequent analysis.

[0209] Step 7: Scent prediction (server)

[0210] The server inputs the extracted features into an AI model. This AI model is built using a neural network and predicts the expression of a specific scent from the features. The prediction results are verbalized and stored on the server.

[0211] Step 8: Emotion Recognition (Device)

[0212] The device activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expression data or voice data to recognize the user's emotions. For example, it determines whether the user is relaxed or nervous.

[0213] Step 9: Adjusting the scent (server)

[0214] The server adjusts the predicted scent expression based on the user's emotion recognized by the emotion engine. For example, if the user is relaxed, it adds the attribute "has a relaxing effect" to the scent expression.

[0215] Step 10: Sending prediction results (server)

[0216] The server then sends the adjusted prediction results to the device, allowing the device to provide a representation of the predicted scent to the user.

[0217] Step 11: Viewing the Results (Terminal)

[0218] The device receives the prediction results sent from the server and displays them to the user. The results are presented in a format that is easy for the user to understand, such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[0219] Step 12: Check the results (user)

[0220] The user checks the prediction results displayed on the device, evaluates whether the results match their own intuition, and can provide feedback on the results if necessary.

[0221] Example 2

[0222] 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."

[0223] Conventional odor data evaluation and analysis have been subjective, making quantitative evaluation difficult. Furthermore, the inability to appropriately evaluate and adjust the expression of odors based on the user's emotions limits the user experience. Therefore, there is a growing need for a system that can quantify odor data and recognize the user's emotions to appropriately express odors.

[0224] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes server means for receiving data, analysis means for preprocessing the data and extracting features, artificial intelligence means for predicting the expression of a specific scent from the features, and emotion recognition means for adjusting the expression of the scent predicted by the artificial intelligence means. This makes it possible to quantify the scent data and appropriately evaluate and adjust the expression of the scent based on the user's emotions.

[0225] A "sensor means" is a device for acquiring odor data.

[0226] The "processing device means" is a device for pre-processing odor data and transmitting it to a server as needed.

[0227] "Server means" refers to devices and systems for receiving, storing and analyzing pre-processed odor data.

[0228] The "analysis means" refers to a device or software that has the function of extracting features from the received odor data.

[0229] "Artificial intelligence means" refers to machine learning models and related technologies for predicting the expression of a specific scent from extracted features.

[0230] "Emotion recognition means" refers to a device or software that has the function of analyzing the user's facial expression data or voice data to recognize their emotions and adjust the expression of the scent.

[0231] A "secure communication protocol" is a communication method for securely transmitting odor data to a server.

[0232] "Features" are information that represent the concentration and pattern of specific chemical components extracted from odor data.

[0233] An "aroma description" is a description or adjective of a particular aroma that is generated based on the extracted features.

[0234] "Means for displaying to the user" refers to a mechanism for visually presenting the processed data and the adjusted scent expression to the user.

[0235] MODE FOR CARRYING OUT THE INVENTION

[0236] This invention is a system that quantifies odor data and verbalizes specific scents based on that data. Furthermore, by combining it with an emotion engine, it is possible to adjust the expression of the scent based on the user's emotions. This system is composed of the following elements:

[0237] Acquiring odor data (device)

[0238] The device uses an odor sensor to detect the odor of the target object and acquires it as digital data. The sensor quantifies the concentration and pattern of chemical components and passes the data to the device as digital data. It is desirable to use a high-precision chemical sensor for this process.

[0239] Preprocessing of odor data (terminal)

[0240] The device is equipped with software for preprocessing the acquired data, including noise removal and data correction, to improve the accuracy and reliability of the data. The preprocessed data is then sent to the server using a secure communication protocol.

[0241] Receiving and storing data (server)

[0242] The server receives the pre-processed data sent from the terminal and stores it in a database, which contains all the information necessary for subsequent analysis. The stored data is then sent to the analysis means for further pre-processing.

[0243] Data preprocessing and feature extraction (server)

[0244] The server performs preprocessing on the stored data, such as normalization, filtering, and noise removal. After preprocessing, feature values ​​are extracted by the analysis means. Feature values ​​are numerical indicators that indicate the concentration and pattern of chemical components.

[0245] Scent prediction (server)

[0246] The extracted features are input into an artificial intelligence means, which uses a neural network to predict a specific aroma expression from the features. For example, an abstract aroma expression such as "citrus, slightly sweet and sour" can be obtained.

[0247] Emotion recognition and expression regulation (terminal)

[0248] When a user approaches the device, the emotion engine is activated. The emotion engine analyzes the user's facial expression and voice data to recognize their emotion. Based on the analysis results, the server adjusts the predicted scent expression. For example, if the user is relaxed, the expression will be modified to something like "citrus with a relaxing effect."

[0249] Sending and displaying adjustment results (terminal)

[0250] The adjusted results are sent from the server to the device using a secure communication protocol. The device receives them and displays them to the user. The display format is a specific description such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[0251] Specific examples

[0252] For example, when a user brings an orange peel close to a scent sensor, the system operates as follows: The device activates the scent sensor, acquires data, and performs preprocessing. The preprocessed data is sent to the server using the HTTPS protocol. The server saves the received data, performs further preprocessing, and extracts features. A neural network is used to predict the scent, such as "citrus, slightly sweet and sour." At the same time, if the emotion engine recognizes the user's emotion as "relaxed," the predicted result is adjusted to "citrus with a relaxing effect." This result is sent to the device and displayed to the user.

[0253] Example prompts for generative AI models

[0254] The following prompts can be used to have the generative AI model generate explanatory text:

[0255] Please explain the specific program processing flow of a system that combines an odor sensor and an emotion engine. Please break down the processing steps and provide a detailed description of each.

[0256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0257] Processing Steps

[0258] Step 1: Acquiring odor data (device)

[0259] The device activates the odor sensor and captures the odor emanating from the object as digital data. The input is the object's odor, which is converted into digital data as output. This data contains numerical values ​​that indicate the concentration and pattern of specific chemical components. For example, when a user brings an orange peel close to the sensor, chemical component concentration data is obtained.

[0260] Step 2: Preprocessing the odor data (terminal)

[0261] The device performs preprocessing on the acquired digital data. The acquired digital data is the input, and the preprocessed data is the output. Preprocessing includes noise removal, data correction, normalization, etc. Specifically, operations are performed to filter out noise in the data and normalize the signal from the sensor.

[0262] Step 3: Sending odor data (device)

[0263] The terminal sends the preprocessed data to the server. The preprocessed data is the input, and the output is the data sent via a secure communication protocol (e.g., HTTPS). The data is encrypted before being sent, ensuring security.

[0264] Step 4: Receiving and storing data (server)

[0265] The server receives the pre-processed data sent from the terminal. The sent data is the input and is saved in the database as the output. The received data is stored in the server's database for later analysis.

[0266] Step 5: Data Preprocessing (Server)

[0267] The server performs further pre-processing on the received and stored data. It takes the stored data as input and the re-processed data as output. Pre-processing here includes noise filtering, normalization, and additional data correction. This processing further improves the accuracy and consistency of the data.

[0268] Step 6: Feature extraction (server)

[0269] The server extracts features from the preprocessed data. The preprocessed data is input, and features are obtained as output. Features are numerical indicators such as the concentration or pattern of chemical components. Specifically, data analysis algorithms are used to recognize the characteristics of chemical components, and that information is extracted as features.

[0270] Step 7: Scent prediction (server)

[0271] The server inputs the extracted features into an artificial intelligence model to predict the expression of the scent. The features are input, and the predicted scent expression is obtained as output. A neural network is used as the artificial intelligence model. For example, the model predicts a scent expression such as "citrus, slightly sweet and sour" from the input features.

[0272] Step 8: Emotion Recognition (Device)

[0273] The device activates an emotion engine and collects facial expression and voice data to recognize the user's emotions. The input is the user's facial expression and voice data, and the output is recognized emotion data. The emotion engine collects data using a camera and microphone and analyzes it to determine whether the user is relaxed or tense.

[0274] Step 9: Adjusting scent expression (server)

[0275] The server adjusts the predicted scent expression appropriately based on the recognized emotion data. The input is the predicted scent expression and emotion data, and the output is the adjusted scent expression. For example, if the user is recognized as relaxed, the scent expression is adjusted to "citrus with a relaxing effect."

[0276] Step 10: Sending the adjustment results (server)

[0277] The server sends the adjusted scent representation to the device. The input is the adjusted scent representation, and the output is data sent via a secure communication protocol. This data is also encrypted before transmission, so the information remains secure.

[0278] Step 11: Viewing the adjustment results (device)

[0279] The device displays the adjustment results received from the server to the user. The received data is input, and the output is the information displayed to the user. The display format is a specific description of the scent, such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[0280] (Application example 2)

[0281] 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."

[0282] Conventional odor analysis systems can quantitatively acquire and analyze odor data, but they cannot adjust the analysis results based on the user's emotions. This poses a problem in that users are unable to receive optimal suggestions based on their emotions when selecting a scent. Another issue with conventional systems is that they can only represent odors in a fixed way, which lacks flexibility.

[0283] 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.

[0284] In this invention, the server includes means for receiving odor data, means for extracting features from the received data, means for predicting an aroma expression from the features using artificial intelligence means, means for recognizing a user's emotion, means for adjusting the aroma expression based on the recognized emotion, and means for transmitting the predicted and adjusted aroma expression to the terminal, thereby making it possible to provide an aroma expression that is appropriately adjusted based on the user's emotion.

[0285] "Odor data" refers to the digital representation of the concentration and pattern of specific chemical components acquired by an odor sensor.

[0286] "Sensor means" refers to a technological means for acquiring odor data, including devices that sense specific chemical components.

[0287] The term "terminal means" refers to an electronic device for preprocessing acquired odor data and transmitting the data to the server means.

[0288] "Preprocessed odor data" refers to raw data obtained from a sensor means that has been appropriately filtered and denoised.

[0289] The "server means" is a central processing unit that stores the odor data received from the terminal means, extracts features, and performs analysis using artificial intelligence means.

[0290] "Features" are information that serves as important attributes or indicators of the analysis target, extracted from preprocessed odor data.

[0291] "Artificial intelligence means" refers to a technical means that uses machine learning models such as neural networks to predict the expression of a specific fragrance from features.

[0292] "Emotion recognition means" refers to a technical means for analyzing a user's facial expression data and voice data and estimating the user's emotions.

[0293] The "means for adjusting the expression of a scent" refers to a technical means for appropriately correcting and adjusting the predicted expression of a scent based on the user's emotions recognized by the emotion recognition means.

[0294] "Scent expression" refers to the characteristics and impressions of a scent that are verbalized based on scent data acquired by a scent sensor.

[0295] The present invention combines an emotion engine with a system that quantifies odor data and verbalizes specific scents. An embodiment of this system will be described in detail below.

[0296] System Configuration

[0297] The system consists of an odor sensor, a terminal, a server, an artificial intelligence model, and an emotion engine.

[0298] Hardware and Software

[0299] Odor sensor: A device that detects specific chemical components and is used to obtain odor data.

[0300] Terminal: A device such as a smartphone or smart glasses that preprocesses the odor data and transmits it to the server. The terminal also has a camera and microphone for emotion recognition.

[0301] Server: Located on the cloud, it receives odor data sent from the device and extracts features from the preprocessed data.

[0302] Artificial intelligence model: A technology that uses neural networks to predict the expression of a scent from features.

[0303] Emotion engine: A technology that analyzes the user's facial expressions and voice to recognize emotions.

[0304] Program processing overview

[0305] 1. Acquisition and preprocessing of odor data

[0306] The device acquires odor data from the target object using an odor sensor. The acquired data is preprocessed on the device to remove noise and perform filtering. The preprocessed data is then sent to the server using a secure communication protocol (e.g., HTTPS).

[0307] 2. Data reception and feature extraction

[0308] The server receives the preprocessed data sent from the device. The received data is stored in a database and then goes on to the next processing step. The server extracts features from this data and inputs them into an artificial intelligence model.

[0309] 3. Fragrance Expression Prediction

[0310] Using an artificial intelligence model (neural network), a specific aroma expression is predicted from the features. For example, a predicted result such as "citrus, slightly sweet and sour" is generated.

[0311] 4. Emotional recognition and scent regulation

[0312] The emotion engine runs on the device and analyzes the user's facial expression data (e.g., using the camera in smart glasses) and voice data to recognize emotions. Based on the recognized emotion, the server adjusts the prediction result and generates a more appropriate scent description. For example, it adjusts the description to "citrus with a relaxing effect."

[0313] 5. Sending and displaying the expression results

[0314] The final adjusted scent representation is sent from the server to the device, which receives the result and displays it to the user.

[0315] Usage example

[0316] For example, let's consider a specific example where a user tries out perfume in a physical store. When the user brings a perfume bottle close to an odor sensor, the sensor captures odor data. The captured data is preprocessed on the device and sent to the server. The server extracts features from the data and predicts the scent expression using an artificial intelligence model. The emotion engine then recognizes the user's relaxed facial expression and adjusts the expression to "citrus with a relaxing effect." This is then sent to the device and displayed to the user, allowing them to choose a scent that suits their condition.

[0317] Prompt Sentence Examples

[0318] "When a user chooses a perfume in a physical store, acquire scent data using an odor sensor, and adjust the scent representation predicted by an AI model using smart glasses based on emotion recognition data to generate an application that suggests the appropriate scent."

[0319] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0320] Step 1:

[0321] The device acquires odor data using an odor sensor. The sensor detects odors emanating from an object and sends the data in digital format to the device. The input is the odor of the object, and the output is digital odor data. Specifically, the odor sensor activates and detects the odor components of the surrounding air and the object.

[0322] Step 2:

[0323] The device preprocesses the acquired odor data, removing noise and filtering to improve data accuracy. The input is raw data obtained from the odor sensor, and the output is preprocessed data. Specifically, the device's preprocessing algorithm normalizes the data and removes unnecessary noise.

[0324] Step 3:

[0325] The device sends the preprocessed odor data to the server. The data is transferred securely using a secure communication protocol (e.g., HTTPS). The input is the preprocessed data, and the output is a notification to the server that transmission has been completed. Specifically, the device establishes an Internet connection and uploads the data to the server.

[0326] Step 4:

[0327] The server receives odor data sent from the device and stores it in a database. The input is the preprocessed data sent from the device, and the output is a notification that the data has been stored in the database. Specifically, the server converts the received data into a specific format and stores it in the database.

[0328] Step 5:

[0329] The server extracts features from the data stored in the database. These features contain the information necessary for analysis. The input is preprocessed data, and the output is the extracted features. Specifically, the server uses machine learning algorithms to extract important attributes and patterns.

[0330] Step 6:

[0331] The server inputs the extracted features into an artificial intelligence model (neural network) to predict the expression of the scent. The input is the features, and the output is the predicted expression of the scent. Specifically, the AI ​​model on the server analyzes the data and verbalizes the scent.

[0332] Step 7:

[0333] The device recognizes the user's emotions using emotion recognition means. It uses a camera and microphone to collect emotion data from the user's facial expressions and voice. The input is the user's facial expression data and voice data, and the output is the recognized emotion. Specifically, the device performs emotion analysis in real time to identify the emotion.

[0334] Step 8:

[0335] The server adjusts the predicted scent expression based on the recognized emotion. The input is the predicted scent expression and the recognized emotion, and the output is the adjusted scent expression. Specifically, the server uses the emotion engine to modify the scent expression.

[0336] Step 9:

[0337] The server sends the adjusted scent representation to the terminal. The input is the adjusted scent representation, and the output is a notification of completion of transmission to the terminal. Specifically, the server packs the data into packets and sends them to the terminal via the network.

[0338] Step 10:

[0339] The device receives the scent description sent from the server and displays it to the user. The input is the adjusted scent description, and the output is a description of the displayed scent. Specifically, the device displays the scent information in text format on the display.

[0340] 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.

[0341] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0342] 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.

[0343] [Second embodiment]

[0344] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0345] 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.

[0346] 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).

[0347] 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.

[0348] 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.

[0349] 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).

[0350] 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.

[0351] 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.

[0352] 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.

[0353] 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.

[0354] 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.

[0355] 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."

[0356] The present invention relates to a system for quantifying odor data and verbalizing a specific odor based on the quantified data. Specific embodiments of this system will be described below.

[0357] Program Overview

[0358] This system consists of an odor sensor, a terminal, a server, and an artificial intelligence model. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, preprocesses it, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the expression of the scent from the features. Finally, the prediction result is sent to the terminal and displayed to the user.

[0359] Specific operation of the system

[0360] Acquisition and transmission of odor data (terminal)

[0361] The device activates the odor sensor and acquires odor data in a specific environment. This data is converted into a digital format and preprocessed. Preprocessing includes noise reduction and scaling. The preprocessed data is then sent to a server using a secure communication protocol (e.g., HTTPS).

[0362] Data reception and preprocessing (server)

[0363] The server receives the data sent from the device. The received data requires further preprocessing, such as filtering and normalization. The processed data is then used for feature extraction.

[0364] Feature extraction and scent prediction (server)

[0365] The server has a means of extracting features from the preprocessed data. Specifically, it calculates features based on the concentration of specific chemical components and pattern recognition. These features are converted into vector format and input into an artificial intelligence model. The artificial intelligence model uses a neural network in particular, and predicts the aroma expression (e.g., citrus, floral, etc.) from the input features.

[0366] Sending and displaying prediction results (terminal)

[0367] The server then sends the predicted scent description to the device, which then displays the result to the user. The result may be presented in the form of, for example, "This scent is citrus-like and slightly sweet and sour."

[0368] Specific examples

[0369] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server, which performs further preprocessing and feature extraction. The extracted features are then input into an artificial intelligence model, which generates a prediction result: "citrus-like, slightly sweet and sour." This result is sent to the device and displayed to the user.

[0370] This system enables quantitative evaluation of scents and provides users with verbalized scent analysis results, facilitating the design and evaluation of scents for specific applications.

[0371] The processing flow will be explained below.

[0372] Step 1: Acquire scents (device)

[0373] The device activates the odor sensor, detects odors emanating from the object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components.

[0374] Step 2: Preprocessing the data (terminal)

[0375] The device preprocesses the acquired odor data, specifically removing noise from the data and scaling or filtering as necessary. The preprocessed data is then converted into a format suitable for analysis.

[0376] Step 3: Sending data (terminal)

[0377] The preprocessed odor data is transmitted to a server using a secure communication protocol (e.g., HTTPS), ensuring data integrity and security.

[0378] Step 4: Receiving Data (Server)

[0379] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step.

[0380] Step 5: Data Preprocessing (Server)

[0381] The server performs further pre-processing on the received data, including normalizing, filtering, and further noise reduction, to improve the data quality and make it suitable for analysis.

[0382] Step 6: Feature extraction (server)

[0383] The server extracts features from the pre-processed data, which can be based on the concentration of specific chemical components or pattern recognition, and represent attributes or indicators required for subsequent analysis.

[0384] Step 7: Scent prediction (server)

[0385] The server inputs the extracted features into an AI model. This AI model is built using a neural network and predicts the expression of a specific scent from the features. The prediction results are verbalized and stored on the server.

[0386] Step 8: Sending prediction results (server)

[0387] The server sends the prediction results to the device, which then provides the user with a representation of the predicted scent.

[0388] Step 9: View the results (terminal)

[0389] The device receives the prediction results sent from the server and displays them to the user. The results are presented in a format that is easy for the user to understand, such as "This scent is citrus-like and slightly sweet and sour."

[0390] Step 10: Check the results (user)

[0391] The user checks the prediction results displayed on the device, evaluates whether the results match their own intuition, and can provide feedback on the results if necessary.

[0392] Example 1

[0393] 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."

[0394] Conventional systems that analyze odor data and verbalize scents have had issues with data accuracy and security. It is also difficult to accurately extract and verbalize the characteristics of odors, making it difficult to provide users with useful information. Furthermore, processing speed and prediction accuracy are often insufficient, making them impractical.

[0395] 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.

[0396] In this invention, the server includes means for additionally preprocessing the received data, filtering and normalizing it, means for extracting features from the additionally preprocessed data, and means for converting the extracted features into vector format, thereby enabling highly accurate and efficient data analysis and scent prediction.

[0397] "Odor data" is digital data that represents information about odors in a particular environment, obtained by a sensor means.

[0398] The "sensor means" is a device for acquiring odor data, which senses odors from any environment and converts them into digital data.

[0399] The "terminal means" is a device that receives odor data obtained from the sensor means and performs preprocessing, and also has the function of transmitting the processed data to the server means.

[0400] "Preprocessing" refers to the process of removing noise and scaling odor data acquired from the sensor means to make it easier to analyze.

[0401] The "server means" is a device that receives preprocessed odor data sent from the terminal means, and performs additional preprocessing, feature extraction, and prediction using artificial intelligence means.

[0402] "Additional pre-processing" refers to the filtering and normalization processes that the server means performs on the data it receives, in order to improve the consistency and accuracy of the data.

[0403] "Features" are information that indicates the concentration and pattern of specific chemical components, extracted from odor data that has undergone preprocessing and additional preprocessing.

[0404] The "vector format" is a format for expressing feature quantities as numerical data, and is a data format used for inputting data to artificial intelligence means.

[0405] "Artificial intelligence means" refers to software or hardware that predicts the expression of a scent from features, primarily using techniques such as neural networks.

[0406] A "scent description" is a specific description of a scent based on scent data predicted by artificial intelligence means, and is information provided in a format that is understandable to the user.

[0407] A "secure communication protocol" is a communication protocol used to ensure confidentiality and integrity of information when sending and receiving data, and examples include HTTPS.

[0408] The present invention relates to a system for quantifying odor data and verbalizing a specific odor based on the quantified data. Specific embodiments of this system will be described below.

[0409] System Overview

[0410] This system consists of an odor sensor, a terminal, a server, and an artificial intelligence model. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, performs additional preprocessing, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the scent expression from the features. Finally, the prediction result is sent to the terminal and displayed to the user.

[0411] Acquisition and preprocessing of odor data (terminal)

[0412] The user uses an odor sensor connected to a device. For example, when the user holds an orange peel close to the sensor, the sensor captures odor data in the environment and converts it into digital data. This data is then pre-processed on the device, with noise reduction and scaling. The pre-processed data is then sent to a server using a secure communication protocol such as HTTPS.

[0413] Data reception and additional preprocessing (server)

[0414] The server receives the preprocessed odor data sent from the device, which undergoes additional preprocessing such as filtering and normalization to improve consistency and accuracy, preparing the data for feature extraction.

[0415] Feature extraction and scent prediction (server)

[0416] The server extracts features from the pre-processed data. For example, it analyzes the concentration and patterns of specific chemical components and converts them into vector format. This feature vector is input into an artificial intelligence model using a neural network, which predicts the scent expression (e.g., citrus or floral) from the odor data.

[0417] Sending and displaying prediction results (terminal)

[0418] The server sends the predicted scent description to the device, which then receives the result and displays it to the user. For example, the result might be something like, "This scent is citrusy and slightly sweet and sour."

[0419] Specific examples

[0420] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server using a secure communication protocol. The server then performs further preprocessing on the received data and extracts features. The extracted features are then input into an artificial intelligence model, which generates a prediction result: "citrus-like, slightly sweet and sour." This result is sent to the device and displayed to the user.

[0421] Prompt Sentence Examples

[0422] An example of a prompt to be input to the generative AI model is as follows:

[0423] 1. "Describe the smell of orange peel."

[0424] 2. "Predict the scent description from this smell data."

[0425] 3. "Please describe in words the scent detected by the odor sensor."

[0426] This system enables quantitative evaluation of scents and can quickly provide users with verbalized scent analysis results, facilitating the design and evaluation of scents for specific applications.

[0427] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0428] Step 1: Acquiring odor data (device)

[0429] When a user brings an orange peel close to the sensor, an odor sensor connected to the device captures odor data in the environment. The sensor detects this odor as an analog signal and converts it into digital data. Specifically, the sensor measures the concentration of chemical components and converts that data into binary code. At this stage, the input is the odor components emanating from the orange peel, and the output is odor data in digital format.

[0430] Step 2: Data preprocessing (terminal)

[0431] The device performs preprocessing on the acquired digital odor data. Specifically, it applies a noise reduction filter to the data and scales it to improve the quality of the data. Noise reduction is the process of removing random noise, and scaling is the process of confining the data within a certain range. The input at this stage is the digital odor data sent from the sensor, and the output after processing is the preprocessed odor data.

[0432] Step 3: Send data (terminal)

[0433] The preprocessed odor data is sent to the server using a secure communication protocol (e.g., HTTPS). At this time, the terminal encrypts the data using AES to ensure data confidentiality. Specifically, the terminal generates a data packet and sends it to the server using the HTTPS protocol. At this stage, the input is the preprocessed odor data, and the output is securely transmitted data.

[0434] Step 4: Receiving data (server)

[0435] The server receives preprocessed smell data sent from the device. The server verifies the received data and checks for unauthorized access or data corruption. Specific operations include the server decoding the received packets and verifying the integrity of the data. The input at this stage is the secure transmission data, and the output is the verified smell data.

[0436] Step 5: Preprocessing for adding data (server)

[0437] The server performs additional preprocessing on the received data. Specifically, it filters and normalizes the data to improve the consistency and accuracy of the data. Filtering is the operation of removing unnecessary data, and normalization is the operation of converting the data to a unified scale. The input at this stage is the verified odor data, and the output is the odor data that has undergone additional preprocessing.

[0438] Step 6: Feature extraction (server)

[0439] The server extracts features from the additionally preprocessed data. Specifically, it analyzes the concentrations and patterns of specific chemical components in the data and converts them into vector format. These features are important data to input into the subsequent artificial intelligence model. The input at this stage is the additionally preprocessed odor data, and the output is a feature vector.

[0440] Step 7: Scent prediction (server)

[0441] The server inputs the feature vector into an artificial intelligence model (e.g., a neural network) to predict the aroma expression. Specifically, the server uses the neural network to generate an aroma expression, such as "citrus, slightly sweet and sour," from the features. The input at this stage is the feature vector, and the output is the predicted aroma expression.

[0442] Step 8: Send prediction results (server)

[0443] The server sends the predicted scent representation to the device, which then displays a specific scent representation on the device to the user. Specific operations include the server formatting the prediction results in JSON and sending them to the device again using a secure protocol. The input at this stage is the predicted scent representation, and the output is securely transmitted data.

[0444] Step 9: Display the results (terminal)

[0445] The device displays the received prediction results to the user. For example, the screen might display "This scent is citrus-like and slightly sweet and sour." Specific operations include the device analyzing the received data and displaying the results on the user interface. The input at this stage is the transmitted prediction data, and the output is a representation of the scent displayed to the user.

[0446] (Application example 1)

[0447] 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."

[0448] Conventional odor data analysis systems were able to quantify acquired odor data and verbalize specific odors based on that data, but they lacked the functionality to recommend related product information when providing the analysis results to users. As a result, users considering purchasing a specific product faced the challenge of not being provided with sufficient information based on the analysis results alone. Specifically, even if a scent was detected in a fragrance section, the system was unable to effectively support users' purchasing behavior because it did not provide product information related to that scent or recommendations for similar products.

[0449] 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.

[0450] In this invention, the server includes a sensor means for acquiring odor data, a terminal means for preprocessing the odor data from the sensor means, a server means for receiving the preprocessed odor data transmitted from the terminal means, a means for extracting features from the received data, an artificial intelligence means for predicting a description of a specific odor from the extracted features, a means for transmitting the predicted odor description to the terminal means, a means for displaying the transmitted odor description to the user on the terminal means, and a recommendation means for recommending related product information based on the odor description displayed to the user. This allows the user to receive not only the analysis results but also product information related to the odor and recommendations of similar products, thereby supporting purchasing behavior.

[0451] "Odor data" is quantitative information about a specific scent obtained by an odor sensor.

[0452] "Sensor means" refers to a device or mechanism for acquiring odor data.

[0453] The "terminal means" is an electronic device that preprocesses the odor data acquired from the odor sensor and communicates with other devices or systems as necessary.

[0454] The "server means" is a central processing unit that receives and processes data sent from the terminal, and further performs feature extraction and predictions using artificial intelligence.

[0455] "Features" are numerical and parametric information extracted from odor data that is necessary to specifically express a scent.

[0456] "Artificial intelligence means" refers to a system or device that uses machine learning algorithms such as neural networks to predict the expression of a scent from features.

[0457] "Description of scent" refers to verbalized information about a specific scent, such as "citrus-like, slightly sweet and sour."

[0458] A "recommendation means" is a system or algorithm that recommends related product information or similar products based on the analyzed scent expression.

[0459] The present invention relates to a system for quantifying odor data, verbalizing a specific scent based on the quantified data, and recommending related product information to a user. Specific embodiments of the present invention will be described below.

[0460] System Overview

[0461] The system comprises a sensor means, a terminal means, a server means, an artificial intelligence means, and a recommendation means.

[0462] 1. Sensor means

[0463] The sensor means is a device for acquiring odor data, and may be, for example, a gas sensor or an electronic nose. This sensor detects the scent in a specific environment and acquires it as digital data.

[0464] 2. Terminal means

[0465] The terminal means preprocesses the odor data obtained from the sensor means and transmits it to the server means. The preprocessing includes noise removal and data scaling. The terminal means transmits the preprocessed odor data to the server means using a secure communication protocol (e.g., HTTPS).

[0466] 3. Server Means

[0467] The server receives the preprocessed odor data sent from the terminal, performs further preprocessing and extracts features, and then inputs the features into the artificial intelligence to predict the expression of the scent.

[0468] 4. Artificial Intelligence Means

[0469] The artificial intelligence means is a model that predicts the expression of a scent from feature quantities, particularly using a neural network. A pre-trained neural network is used to generate a scent expression, such as "citrus-like, slightly sweet and sour." The prediction result is sent to the terminal means via the server means.

[0470] 5. Recommendation method

[0471] The recommendation system is a system that recommends related product information and similar products based on the scent description displayed to the user. The analysis results are linked to a product database to recommend the most suitable products to the user.

[0472] Specific examples of operation procedures

[0473] A specific example of the operation procedure is shown below: A user picks up a specific perfume bottle at a fragrance counter, starts the application, and holds the scent over the sensor. The sensor means acquires scent data and transmits the data to the terminal means.

[0474] The terminal means preprocesses the data and then transmits it to the server means using secure communication. The server means receives the data, performs further preprocessing, and extracts features. The features are then input into the artificial intelligence means to predict the expression of the scent.

[0475] The prediction result is sent to the terminal means and displayed to the user. Finally, the recommendation means recommends related product information based on the analysis result.

[0476] Example prompts for generative AI models

[0477] "I would like to develop an application for analyzing odor data. Please write a program in Python that uses a neural network to predict odors based on data obtained from an odor sensor. The program must include processes for preprocessing the odor data, extracting features, making predictions using an AI model, and displaying the results in a format that is easy for humans to understand."

[0478] In this way, the system of the present invention provides users with scent analysis and related product information, helping them to have a more comfortable purchasing experience.

[0479] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0480] Step 1: Acquiring odor data

[0481] A user activates an odor sensor using a terminal. The sensor means acquires the surrounding odor as data. At this time, the sensor means receives the odor in the environment as input, and outputs the odor data in digital format. Specifically, for example, an electronic nose uses multiple gas sensors to detect the chemical components of the odor and outputs their concentration information as digital data.

[0482] Step 2: Preprocessing the odor data

[0483] The terminal receives the digital data acquired from the odor sensor and performs preprocessing. The input here is the odor data acquired from the sensor means, and the output is the preprocessed data. The terminal means converts the data into a format that is easy to analyze later by removing noise and normalizing the data. Specific examples include noise removal by filtering and data normalization by scaling.

[0484] Step 3: Sending data

[0485] The preprocessed odor data is sent from the device to the server using a secure communication protocol (e.g., HTTPS). The input is the preprocessed data, and the output is the data sent to the server. Specifically, the device encrypts the data using HTTPS and transfers it securely to the server.

[0486] Step 4: Receiving data and further preprocessing

[0487] The server receives the data sent from the device and performs further preprocessing. The input is the data sent from the device, and the output is the preprocessed data. The server filters and normalizes the data, preparing it for feature extraction.

[0488] Step 5: Feature extraction

[0489] The server extracts features from the preprocessed data. The input here is further preprocessed data, and the output is features. Specifically, the server extracts important parameters using chemical component concentrations and pattern recognition algorithms, and converts them into vector format as features.

[0490] Step 6: Predict the scent

[0491] The server inputs the extracted features into an artificial intelligence means (neural network) to predict the scent expression. The input is the features and the output is the scent expression. The pre-trained neural network generates a scent expression such as "citrus, slightly sweet and sour" from the input features.

[0492] Step 7: Submit and view prediction results

[0493] The server sends the predicted scent expression to the terminal. The input is the predicted scent expression, and the output is the data sent to the terminal. The terminal receives this data and displays it to the user. Specifically, the terminal uses a user interface to display the analysis results in the form of "This scent is citrus-like and slightly sweet and sour."

[0494] Step 8: Recommend product information

[0495] The device recommends related product information based on the displayed scent description. The input is the displayed scent description, and the output is recommended product information. Specifically, the analysis results are compared with a product database, and appropriate product information (e.g., related perfumes and air fresheners) is presented to the user.

[0496] 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.

[0497] The present invention combines an emotion engine with a system that quantifies odor data and verbalizes specific odors based on that data. The emotion engine can recognize the user's emotions and adjust the expression of the odor based on those emotions. Specific embodiments of this system are described below.

[0498] Program Overview

[0499] This system consists of an odor sensor, a terminal, a server, an artificial intelligence model, and an emotion engine. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, preprocesses it, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the expression of the scent from the features. The emotion engine recognizes the user's emotion and adjusts the expression of the scent based on that emotion. Finally, the adjusted prediction result is sent to the terminal and displayed to the user.

[0500] Specific operation of the system

[0501] Acquisition and transmission of odor data (terminal)

[0502] The device activates the odor sensor, detects odors emanating from the target object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components. The acquired odor data is preprocessed and sent to the server using a secure communication protocol (e.g., HTTPS).

[0503] Data reception and preprocessing (server)

[0504] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step. The server then performs further pre-processing on the received data, such as normalization, filtering, and further noise reduction.

[0505] Feature extraction and scent prediction (server)

[0506] The server extracts features from the preprocessed data. These features are based on the concentration of specific chemical components or pattern recognition, and represent the attributes and indicators required for subsequent analysis. The extracted features are input into an artificial intelligence model, which uses a neural network to predict the expression of the scent from the input features.

[0507] Emotion recognition and scent adjustment (terminal)

[0508] The device activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expression data or voice data to recognize the emotion. For example, it determines whether the user is relaxed or nervous. Based on the emotion recognized by the emotion engine, the server adjusts the predicted scent expression accordingly.

[0509] Sending and displaying prediction results (terminal)

[0510] The adjusted prediction results are sent to the device, which receives the scent description sent from the server and displays it to the user. The displayed results are presented in a user-friendly format, such as "This scent is citrus-like and slightly sweet and sour."

[0511] Specific examples

[0512] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server, which performs further preprocessing and feature extraction. The extracted features are then input into an artificial intelligence model, which generates a prediction result of "citrus, slightly sweet and sour." If the emotion engine recognizes the user's emotion as "relaxed," the server adjusts the prediction result to something like "citrus with a relaxing effect." This result is sent to the device and displayed to the user.

[0513] This system enables quantitative evaluation of scents and provides users with verbalized scent analysis results. Furthermore, by adjusting the scent expression based on the user's emotions, more appropriate scent evaluation and design becomes possible.

[0514] The processing flow will be explained below.

[0515] Step 1: Acquire scents (device)

[0516] The device activates the odor sensor, detects odors emanating from the object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components.

[0517] Step 2: Preprocessing the data (terminal)

[0518] The device preprocesses the acquired odor data, specifically removing noise from the data and scaling or filtering as necessary. The preprocessed data is then converted into a format suitable for analysis.

[0519] Step 3: Sending data (terminal)

[0520] The preprocessed odor data is transmitted to a server using a secure communication protocol (e.g., HTTPS), ensuring data integrity and security.

[0521] Step 4: Receiving Data (Server)

[0522] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step.

[0523] Step 5: Data Preprocessing (Server)

[0524] The server performs further pre-processing on the received data, including normalizing, filtering, and further noise reduction, to improve the data quality and make it suitable for analysis.

[0525] Step 6: Feature extraction (server)

[0526] The server extracts features from the pre-processed data, which can be based on the concentration of specific chemical components or pattern recognition, and represent attributes or indicators required for subsequent analysis.

[0527] Step 7: Scent prediction (server)

[0528] The server inputs the extracted features into an AI model. This AI model is built using a neural network and predicts the expression of a specific scent from the features. The prediction results are verbalized and stored on the server.

[0529] Step 8: Emotion Recognition (Device)

[0530] The device activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expression data or voice data to recognize the user's emotions. For example, it determines whether the user is relaxed or nervous.

[0531] Step 9: Adjusting the scent (server)

[0532] The server adjusts the predicted scent expression based on the user's emotion recognized by the emotion engine. For example, if the user is relaxed, it adds the attribute "has a relaxing effect" to the scent expression.

[0533] Step 10: Sending prediction results (server)

[0534] The server then sends the adjusted prediction results to the device, allowing the device to provide a representation of the predicted scent to the user.

[0535] Step 11: Viewing the Results (Terminal)

[0536] The device receives the prediction results sent from the server and displays them to the user. The results are presented in a format that is easy for the user to understand, such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[0537] Step 12: Check the results (user)

[0538] The user checks the prediction results displayed on the device, evaluates whether the results match their own intuition, and can provide feedback on the results if necessary.

[0539] Example 2

[0540] 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."

[0541] Conventional odor data evaluation and analysis have been subjective, making quantitative evaluation difficult. Furthermore, the inability to appropriately evaluate and adjust the expression of odors based on the user's emotions limits the user experience. Therefore, there is a growing need for a system that can quantify odor data and recognize the user's emotions to appropriately express odors.

[0542] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes server means for receiving data, analysis means for preprocessing the data and extracting features, artificial intelligence means for predicting the expression of a specific scent from the features, and emotion recognition means for adjusting the expression of the scent predicted by the artificial intelligence means. This makes it possible to quantify the scent data and appropriately evaluate and adjust the expression of the scent based on the user's emotions.

[0543] A "sensor means" is a device for acquiring odor data.

[0544] The "processing device means" is a device for pre-processing odor data and transmitting it to a server as needed.

[0545] "Server means" refers to devices and systems for receiving, storing and analyzing pre-processed odor data.

[0546] The "analysis means" refers to a device or software that has the function of extracting features from the received odor data.

[0547] "Artificial intelligence means" refers to machine learning models and related technologies for predicting the expression of a specific scent from extracted features.

[0548] "Emotion recognition means" refers to a device or software that has the function of analyzing the user's facial expression data or voice data to recognize their emotions and adjust the expression of the scent.

[0549] A "secure communication protocol" is a communication method for securely transmitting odor data to a server.

[0550] "Features" are information that represent the concentration and pattern of specific chemical components extracted from odor data.

[0551] An "aroma description" is a description or adjective of a particular aroma that is generated based on the extracted features.

[0552] "Means for displaying to the user" refers to a mechanism for visually presenting the processed data and the adjusted scent expression to the user.

[0553] MODE FOR CARRYING OUT THE INVENTION

[0554] This invention is a system that quantifies odor data and verbalizes specific scents based on that data. Furthermore, by combining it with an emotion engine, it is possible to adjust the expression of the scent based on the user's emotions. This system is composed of the following elements:

[0555] Acquiring odor data (device)

[0556] The device uses an odor sensor to detect the odor of the target object and acquires it as digital data. The sensor quantifies the concentration and pattern of chemical components and passes the data to the device as digital data. It is desirable to use a high-precision chemical sensor for this process.

[0557] Preprocessing of odor data (terminal)

[0558] The device is equipped with software for preprocessing the acquired data, including noise removal and data correction, to improve the accuracy and reliability of the data. The preprocessed data is then sent to the server using a secure communication protocol.

[0559] Receiving and storing data (server)

[0560] The server receives the pre-processed data sent from the terminal and stores it in a database, which contains all the information necessary for subsequent analysis. The stored data is then sent to the analysis means for further pre-processing.

[0561] Data preprocessing and feature extraction (server)

[0562] The server performs preprocessing on the stored data, such as normalization, filtering, and noise removal. After preprocessing, feature values ​​are extracted by the analysis means. Feature values ​​are numerical indicators that indicate the concentration and pattern of chemical components.

[0563] Scent prediction (server)

[0564] The extracted features are input into an artificial intelligence means, which uses a neural network to predict a specific aroma expression from the features. For example, an abstract aroma expression such as "citrus, slightly sweet and sour" can be obtained.

[0565] Emotion recognition and expression regulation (terminal)

[0566] When a user approaches the device, the emotion engine is activated. The emotion engine analyzes the user's facial expression and voice data to recognize their emotion. Based on the analysis results, the server adjusts the predicted scent expression. For example, if the user is relaxed, the expression will be modified to something like "citrus with a relaxing effect."

[0567] Sending and displaying adjustment results (terminal)

[0568] The adjusted results are sent from the server to the device using a secure communication protocol. The device receives them and displays them to the user. The display format is a specific description such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[0569] Specific examples

[0570] For example, when a user brings an orange peel close to a scent sensor, the system operates as follows: The device activates the scent sensor, acquires data, and performs preprocessing. The preprocessed data is sent to the server using the HTTPS protocol. The server saves the received data, performs further preprocessing, and extracts features. A neural network is used to predict the scent, such as "citrus, slightly sweet and sour." At the same time, if the emotion engine recognizes the user's emotion as "relaxed," the predicted result is adjusted to "citrus with a relaxing effect." This result is sent to the device and displayed to the user.

[0571] Example prompts for generative AI models

[0572] The following prompts can be used to have the generative AI model generate explanatory text:

[0573] Please explain the specific program processing flow of a system that combines an odor sensor and an emotion engine. Please break down the processing steps and provide a detailed description of each.

[0574] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0575] Processing Steps

[0576] Step 1: Acquiring odor data (device)

[0577] The device activates the odor sensor and captures the odor emanating from the object as digital data. The input is the object's odor, which is converted into digital data as output. This data contains numerical values ​​that indicate the concentration and pattern of specific chemical components. For example, when a user brings an orange peel close to the sensor, chemical component concentration data is obtained.

[0578] Step 2: Preprocessing the odor data (terminal)

[0579] The device performs preprocessing on the acquired digital data. The acquired digital data is the input, and the preprocessed data is the output. Preprocessing includes noise removal, data correction, normalization, etc. Specifically, operations are performed to filter out noise in the data and normalize the signal from the sensor.

[0580] Step 3: Sending odor data (device)

[0581] The terminal sends the preprocessed data to the server. The preprocessed data is the input, and the output is the data sent via a secure communication protocol (e.g., HTTPS). The data is encrypted before being sent, ensuring security.

[0582] Step 4: Receiving and storing data (server)

[0583] The server receives the pre-processed data sent from the terminal. The sent data is the input and is saved in the database as the output. The received data is stored in the server's database for later analysis.

[0584] Step 5: Data Preprocessing (Server)

[0585] The server performs further pre-processing on the received and stored data. It takes the stored data as input and the re-processed data as output. Pre-processing here includes noise filtering, normalization, and additional data correction. This processing further improves the accuracy and consistency of the data.

[0586] Step 6: Feature extraction (server)

[0587] The server extracts features from the preprocessed data. The preprocessed data is input, and features are obtained as output. Features are numerical indicators such as the concentration or pattern of chemical components. Specifically, data analysis algorithms are used to recognize the characteristics of chemical components, and that information is extracted as features.

[0588] Step 7: Scent prediction (server)

[0589] The server inputs the extracted features into an artificial intelligence model to predict the expression of the scent. The features are input, and the predicted scent expression is obtained as output. A neural network is used as the artificial intelligence model. For example, the model predicts a scent expression such as "citrus, slightly sweet and sour" from the input features.

[0590] Step 8: Emotion Recognition (Device)

[0591] The device activates an emotion engine and collects facial expression and voice data to recognize the user's emotions. The input is the user's facial expression and voice data, and the output is recognized emotion data. The emotion engine collects data using a camera and microphone and analyzes it to determine whether the user is relaxed or tense.

[0592] Step 9: Adjusting scent expression (server)

[0593] The server adjusts the predicted scent expression appropriately based on the recognized emotion data. The input is the predicted scent expression and emotion data, and the output is the adjusted scent expression. For example, if the user is recognized as relaxed, the scent expression is adjusted to "citrus with a relaxing effect."

[0594] Step 10: Sending the adjustment results (server)

[0595] The server sends the adjusted scent representation to the device. The input is the adjusted scent representation, and the output is data sent via a secure communication protocol. This data is also encrypted before transmission, so the information remains secure.

[0596] Step 11: Viewing the adjustment results (device)

[0597] The device displays the adjustment results received from the server to the user. The received data is input, and the output is the information displayed to the user. The display format is a specific description of the scent, such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[0598] (Application example 2)

[0599] 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."

[0600] Conventional odor analysis systems can quantitatively acquire and analyze odor data, but they cannot adjust the analysis results based on the user's emotions. This poses a problem in that users are unable to receive optimal suggestions based on their emotions when selecting a scent. Another issue with conventional systems is that they can only represent odors in a fixed way, which lacks flexibility.

[0601] 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.

[0602] In this invention, the server includes means for receiving odor data, means for extracting features from the received data, means for predicting an aroma expression from the features using artificial intelligence means, means for recognizing a user's emotion, means for adjusting the aroma expression based on the recognized emotion, and means for transmitting the predicted and adjusted aroma expression to the terminal, thereby making it possible to provide an aroma expression that is appropriately adjusted based on the user's emotion.

[0603] "Odor data" refers to the digital representation of the concentration and pattern of specific chemical components acquired by an odor sensor.

[0604] "Sensor means" refers to a technological means for acquiring odor data, including devices that sense specific chemical components.

[0605] The term "terminal means" refers to an electronic device for preprocessing acquired odor data and transmitting the data to the server means.

[0606] "Preprocessed odor data" refers to raw data obtained from a sensor means that has been appropriately filtered and denoised.

[0607] The "server means" is a central processing unit that stores the odor data received from the terminal means, extracts features, and performs analysis using artificial intelligence means.

[0608] "Features" are information that serves as important attributes or indicators of the analysis target, extracted from preprocessed odor data.

[0609] "Artificial intelligence means" refers to a technical means that uses machine learning models such as neural networks to predict the expression of a specific fragrance from features.

[0610] "Emotion recognition means" refers to a technical means for analyzing a user's facial expression data and voice data and estimating the user's emotions.

[0611] The "means for adjusting the expression of a scent" refers to a technical means for appropriately correcting and adjusting the predicted expression of a scent based on the user's emotions recognized by the emotion recognition means.

[0612] "Scent expression" refers to the characteristics and impressions of a scent that are verbalized based on scent data acquired by a scent sensor.

[0613] The present invention combines an emotion engine with a system that quantifies odor data and verbalizes specific scents. An embodiment of this system will be described in detail below.

[0614] System Configuration

[0615] The system consists of an odor sensor, a terminal, a server, an artificial intelligence model, and an emotion engine.

[0616] Hardware and Software

[0617] Odor sensor: A device that detects specific chemical components and is used to obtain odor data.

[0618] Terminal: A device such as a smartphone or smart glasses that preprocesses the odor data and transmits it to the server. The terminal also has a camera and microphone for emotion recognition.

[0619] Server: Located on the cloud, it receives odor data sent from the device and extracts features from the preprocessed data.

[0620] Artificial intelligence model: A technology that uses neural networks to predict the expression of a scent from features.

[0621] Emotion engine: A technology that analyzes the user's facial expressions and voice to recognize emotions.

[0622] Program processing overview

[0623] 1. Acquisition and preprocessing of odor data

[0624] The device acquires odor data from the target object using an odor sensor. The acquired data is preprocessed on the device to remove noise and perform filtering. The preprocessed data is then sent to the server using a secure communication protocol (e.g., HTTPS).

[0625] 2. Data reception and feature extraction

[0626] The server receives the preprocessed data sent from the device. The received data is stored in a database and then goes on to the next processing step. The server extracts features from this data and inputs them into an artificial intelligence model.

[0627] 3. Fragrance Expression Prediction

[0628] Using an artificial intelligence model (neural network), a specific aroma expression is predicted from the features. For example, a predicted result such as "citrus, slightly sweet and sour" is generated.

[0629] 4. Emotional recognition and scent regulation

[0630] The emotion engine runs on the device and analyzes the user's facial expression data (e.g., using the camera in smart glasses) and voice data to recognize emotions. Based on the recognized emotion, the server adjusts the prediction result and generates a more appropriate scent description. For example, it adjusts the description to "citrus with a relaxing effect."

[0631] 5. Sending and displaying the expression results

[0632] The final adjusted scent representation is sent from the server to the device, which receives the result and displays it to the user.

[0633] Usage example

[0634] For example, let's consider a specific example where a user tries out perfume in a physical store. When the user brings a perfume bottle close to an odor sensor, the sensor captures odor data. The captured data is preprocessed on the device and sent to the server. The server extracts features from the data and predicts the scent expression using an artificial intelligence model. The emotion engine then recognizes the user's relaxed facial expression and adjusts the expression to "citrus with a relaxing effect." This is then sent to the device and displayed to the user, allowing them to choose a scent that suits their condition.

[0635] Prompt Sentence Examples

[0636] "When a user chooses a perfume in a physical store, acquire scent data using an odor sensor, and adjust the scent representation predicted by an AI model using smart glasses based on emotion recognition data to generate an application that suggests the appropriate scent."

[0637] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0638] Step 1:

[0639] The device acquires odor data using an odor sensor. The sensor detects odors emanating from an object and sends the data in digital format to the device. The input is the odor of the object, and the output is digital odor data. Specifically, the odor sensor activates and detects the odor components of the surrounding air and the object.

[0640] Step 2:

[0641] The device preprocesses the acquired odor data, removing noise and filtering to improve data accuracy. The input is raw data obtained from the odor sensor, and the output is preprocessed data. Specifically, the device's preprocessing algorithm normalizes the data and removes unnecessary noise.

[0642] Step 3:

[0643] The device sends the preprocessed odor data to the server. The data is transferred securely using a secure communication protocol (e.g., HTTPS). The input is the preprocessed data, and the output is a notification to the server that transmission has been completed. Specifically, the device establishes an Internet connection and uploads the data to the server.

[0644] Step 4:

[0645] The server receives odor data sent from the device and stores it in a database. The input is the preprocessed data sent from the device, and the output is a notification that the data has been stored in the database. Specifically, the server converts the received data into a specific format and stores it in the database.

[0646] Step 5:

[0647] The server extracts features from the data stored in the database. These features contain the information necessary for analysis. The input is preprocessed data, and the output is the extracted features. Specifically, the server uses machine learning algorithms to extract important attributes and patterns.

[0648] Step 6:

[0649] The server inputs the extracted features into an artificial intelligence model (neural network) to predict the expression of the scent. The input is the features, and the output is the predicted expression of the scent. Specifically, the AI ​​model on the server analyzes the data and verbalizes the scent.

[0650] Step 7:

[0651] The device recognizes the user's emotions using emotion recognition means. It uses a camera and microphone to collect emotion data from the user's facial expressions and voice. The input is the user's facial expression data and voice data, and the output is the recognized emotion. Specifically, the device performs emotion analysis in real time to identify the emotion.

[0652] Step 8:

[0653] The server adjusts the predicted scent expression based on the recognized emotion. The input is the predicted scent expression and the recognized emotion, and the output is the adjusted scent expression. Specifically, the server uses the emotion engine to modify the scent expression.

[0654] Step 9:

[0655] The server sends the adjusted scent representation to the terminal. The input is the adjusted scent representation, and the output is a notification of completion of transmission to the terminal. Specifically, the server packs the data into packets and sends them to the terminal via the network.

[0656] Step 10:

[0657] The device receives the scent description sent from the server and displays it to the user. The input is the adjusted scent description, and the output is a description of the displayed scent. Specifically, the device displays the scent information in text format on the display.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] [Third embodiment]

[0662] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0663] 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.

[0664] 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).

[0665] 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.

[0666] 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.

[0667] 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).

[0668] 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.

[0669] 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.

[0670] 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.

[0671] 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.

[0672] 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.

[0673] 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."

[0674] The present invention relates to a system for quantifying odor data and verbalizing a specific odor based on the quantified data. Specific embodiments of this system will be described below.

[0675] Program Overview

[0676] This system consists of an odor sensor, a terminal, a server, and an artificial intelligence model. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, preprocesses it, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the expression of the scent from the features. Finally, the prediction result is sent to the terminal and displayed to the user.

[0677] Specific operation of the system

[0678] Acquisition and transmission of odor data (terminal)

[0679] The device activates the odor sensor and acquires odor data in a specific environment. This data is converted into a digital format and preprocessed. Preprocessing includes noise reduction and scaling. The preprocessed data is then sent to a server using a secure communication protocol (e.g., HTTPS).

[0680] Data reception and preprocessing (server)

[0681] The server receives the data sent from the device. The received data requires further preprocessing, such as filtering and normalization. The processed data is then used for feature extraction.

[0682] Feature extraction and scent prediction (server)

[0683] The server has a means of extracting features from the preprocessed data. Specifically, it calculates features based on the concentration of specific chemical components and pattern recognition. These features are converted into vector format and input into an artificial intelligence model. The artificial intelligence model uses a neural network in particular, and predicts the aroma expression (e.g., citrus, floral, etc.) from the input features.

[0684] Sending and displaying prediction results (terminal)

[0685] The server then sends the predicted scent description to the device, which then displays the result to the user. The result may be presented in the form of, for example, "This scent is citrus-like and slightly sweet and sour."

[0686] Specific examples

[0687] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server, which performs further preprocessing and feature extraction. The extracted features are then input into an artificial intelligence model, which generates a prediction result: "citrus-like, slightly sweet and sour." This result is sent to the device and displayed to the user.

[0688] This system enables quantitative evaluation of scents and provides users with verbalized scent analysis results, facilitating the design and evaluation of scents for specific applications.

[0689] The processing flow will be explained below.

[0690] Step 1: Acquire scents (device)

[0691] The device activates the odor sensor, detects odors emanating from the object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components.

[0692] Step 2: Preprocessing the data (terminal)

[0693] The device preprocesses the acquired odor data, specifically removing noise from the data and scaling or filtering as necessary. The preprocessed data is then converted into a format suitable for analysis.

[0694] Step 3: Sending data (terminal)

[0695] The preprocessed odor data is transmitted to a server using a secure communication protocol (e.g., HTTPS), ensuring data integrity and security.

[0696] Step 4: Receiving Data (Server)

[0697] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step.

[0698] Step 5: Data Preprocessing (Server)

[0699] The server performs further pre-processing on the received data, including normalizing, filtering, and further noise reduction, to improve the data quality and make it suitable for analysis.

[0700] Step 6: Feature extraction (server)

[0701] The server extracts features from the pre-processed data, which can be the concentrations of specific chemical components or pattern recognition, and represent attributes or indicators required for subsequent analysis.

[0702] Step 7: Scent prediction (server)

[0703] The server inputs the extracted features into an AI model. This AI model is built using a neural network and predicts the expression of a specific scent from the features. The prediction results are verbalized and stored on the server.

[0704] Step 8: Sending prediction results (server)

[0705] The server sends the prediction results to the device, which then provides the user with a representation of the predicted scent.

[0706] Step 9: View the results (terminal)

[0707] The device receives the prediction results sent from the server and displays them to the user. The results are presented in a format that is easy for the user to understand, such as "This scent is citrus-like and slightly sweet and sour."

[0708] Step 10: Check the results (user)

[0709] The user checks the prediction results displayed on the device, evaluates whether the results match their own intuition, and can provide feedback on the results if necessary.

[0710] Example 1

[0711] 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."

[0712] Conventional systems that analyze odor data and verbalize scents have had issues with data accuracy and security. It is also difficult to accurately extract and verbalize the characteristics of odors, making it difficult to provide users with useful information. Furthermore, processing speed and prediction accuracy are often insufficient, making them impractical.

[0713] 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.

[0714] In this invention, the server includes means for additionally preprocessing the received data, filtering and normalizing it, means for extracting features from the additionally preprocessed data, and means for converting the extracted features into vector format, thereby enabling highly accurate and efficient data analysis and scent prediction.

[0715] "Odor data" is digital data that represents information about odors in a particular environment, obtained by a sensor means.

[0716] The "sensor means" is a device for acquiring odor data, which senses odors from any environment and converts them into digital data.

[0717] The "terminal means" is a device that receives odor data obtained from the sensor means and performs preprocessing, and also has the function of transmitting the processed data to the server means.

[0718] "Preprocessing" refers to the process of removing noise and scaling odor data acquired from the sensor means to make it easier to analyze.

[0719] The "server means" is a device that receives preprocessed odor data sent from the terminal means, and performs additional preprocessing, feature extraction, and prediction using artificial intelligence means.

[0720] "Additional pre-processing" refers to the filtering and normalization processes that the server means performs on the data it receives, in order to improve the consistency and accuracy of the data.

[0721] "Features" are information that indicates the concentration and pattern of specific chemical components, extracted from odor data that has undergone preprocessing and additional preprocessing.

[0722] The "vector format" is a format for expressing feature quantities as numerical data, and is a data format used for inputting data to artificial intelligence means.

[0723] "Artificial intelligence means" refers to software or hardware that predicts the expression of a scent from features, primarily using techniques such as neural networks.

[0724] A "scent description" is a specific description of a scent based on scent data predicted by artificial intelligence means, and is information provided in a format that is understandable to the user.

[0725] A "secure communication protocol" is a communication protocol used to ensure confidentiality and integrity of information when sending and receiving data, and examples include HTTPS.

[0726] The present invention relates to a system for quantifying odor data and verbalizing a specific odor based on the quantified data. Specific embodiments of this system will be described below.

[0727] System Overview

[0728] This system consists of an odor sensor, a terminal, a server, and an artificial intelligence model. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, performs additional preprocessing, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the scent expression from the features. Finally, the prediction result is sent to the terminal and displayed to the user.

[0729] Acquisition and preprocessing of odor data (terminal)

[0730] The user uses an odor sensor connected to a device. For example, when the user holds an orange peel close to the sensor, the sensor captures odor data in the environment and converts it into digital data. This data is then pre-processed on the device, with noise reduction and scaling. The pre-processed data is then sent to a server using a secure communication protocol such as HTTPS.

[0731] Data reception and additional preprocessing (server)

[0732] The server receives the preprocessed odor data sent from the device, which undergoes additional preprocessing such as filtering and normalization to improve consistency and accuracy, preparing the data for feature extraction.

[0733] Feature extraction and scent prediction (server)

[0734] The server extracts features from the pre-processed data. For example, it analyzes the concentration and patterns of specific chemical components and converts them into vector format. This feature vector is input into an artificial intelligence model using a neural network, which predicts the scent expression (e.g., citrus or floral) from the odor data.

[0735] Sending and displaying prediction results (terminal)

[0736] The server sends the predicted scent description to the device, which then receives the result and displays it to the user. For example, the result might be something like, "This scent is citrusy and slightly sweet and sour."

[0737] Specific examples

[0738] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server using a secure communication protocol. The server then performs further preprocessing on the received data and extracts features. The extracted features are then input into an artificial intelligence model, which generates a prediction result: "citrus-like, slightly sweet and sour." This result is sent to the device and displayed to the user.

[0739] Prompt Sentence Examples

[0740] An example of a prompt to be input to the generative AI model is as follows:

[0741] 1. "Describe the smell of orange peel."

[0742] 2. "Predict the scent description from this smell data."

[0743] 3. "Please describe in words the scent detected by the odor sensor."

[0744] This system enables quantitative evaluation of scents and can quickly provide users with verbalized scent analysis results, facilitating the design and evaluation of scents for specific applications.

[0745] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0746] Step 1: Acquiring odor data (device)

[0747] When a user brings an orange peel close to the sensor, an odor sensor connected to the device captures odor data in the environment. The sensor detects this odor as an analog signal and converts it into digital data. Specifically, the sensor measures the concentration of chemical components and converts that data into binary code. At this stage, the input is the odor components emanating from the orange peel, and the output is odor data in digital format.

[0748] Step 2: Data preprocessing (terminal)

[0749] The device performs preprocessing on the acquired digital odor data. Specifically, it applies a noise reduction filter to the data and scales it to improve the quality of the data. Noise reduction is the process of removing random noise, and scaling is the process of confining the data within a certain range. The input at this stage is the digital odor data sent from the sensor, and the output after processing is the preprocessed odor data.

[0750] Step 3: Send data (terminal)

[0751] The preprocessed odor data is sent to the server using a secure communication protocol (e.g., HTTPS). At this time, the terminal encrypts the data using AES to ensure data confidentiality. Specifically, the terminal generates a data packet and sends it to the server using the HTTPS protocol. At this stage, the input is the preprocessed odor data, and the output is securely transmitted data.

[0752] Step 4: Receiving data (server)

[0753] The server receives preprocessed smell data sent from the device. The server verifies the received data and checks for unauthorized access or data corruption. Specific operations include the server decoding the received packets and verifying the integrity of the data. The input at this stage is the secure transmission data, and the output is the verified smell data.

[0754] Step 5: Preprocessing for adding data (server)

[0755] The server performs additional preprocessing on the received data. Specifically, it filters and normalizes the data to improve the consistency and accuracy of the data. Filtering is the operation of removing unnecessary data, and normalization is the operation of converting the data to a unified scale. The input at this stage is the verified odor data, and the output is the odor data that has undergone additional preprocessing.

[0756] Step 6: Feature extraction (server)

[0757] The server extracts features from the additionally preprocessed data. Specifically, it analyzes the concentrations and patterns of specific chemical components in the data and converts them into vector format. These features are important data to input into the subsequent artificial intelligence model. The input at this stage is the additionally preprocessed odor data, and the output is a feature vector.

[0758] Step 7: Scent prediction (server)

[0759] The server inputs the feature vector into an artificial intelligence model (e.g., a neural network) to predict the aroma expression. Specifically, the server uses the neural network to generate an aroma expression, such as "citrus, slightly sweet and sour," from the features. The input at this stage is the feature vector, and the output is the predicted aroma expression.

[0760] Step 8: Send prediction results (server)

[0761] The server sends the predicted scent representation to the device, which then displays a specific scent representation on the device to the user. Specific operations include the server formatting the prediction results in JSON and sending them to the device again using a secure protocol. The input at this stage is the predicted scent representation, and the output is securely transmitted data.

[0762] Step 9: Display the results (terminal)

[0763] The device displays the received prediction results to the user. For example, the screen might display "This scent is citrus-like and slightly sweet and sour." Specific operations include the device analyzing the received data and displaying the results on the user interface. The input at this stage is the transmitted prediction data, and the output is a representation of the scent displayed to the user.

[0764] (Application example 1)

[0765] 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."

[0766] Conventional odor data analysis systems were able to quantify acquired odor data and verbalize specific odors based on that data, but they lacked the functionality to recommend related product information when providing the analysis results to users. As a result, users considering purchasing a specific product faced the challenge of not being provided with sufficient information based on the analysis results alone. Specifically, even if a scent was detected in a fragrance section, the system was unable to effectively support users' purchasing behavior because it did not provide product information related to that scent or recommendations for similar products.

[0767] 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.

[0768] In this invention, the server includes a sensor means for acquiring odor data, a terminal means for preprocessing the odor data from the sensor means, a server means for receiving the preprocessed odor data transmitted from the terminal means, a means for extracting features from the received data, an artificial intelligence means for predicting a description of a specific odor from the extracted features, a means for transmitting the predicted odor description to the terminal means, a means for displaying the transmitted odor description to the user on the terminal means, and a recommendation means for recommending related product information based on the odor description displayed to the user. This allows the user to receive not only the analysis results but also product information related to the odor and recommendations of similar products, thereby supporting purchasing behavior.

[0769] "Odor data" is quantitative information about a specific scent obtained by an odor sensor.

[0770] "Sensor means" refers to a device or mechanism for acquiring odor data.

[0771] The "terminal means" is an electronic device that preprocesses the odor data acquired from the odor sensor and communicates with other devices or systems as necessary.

[0772] The "server means" is a central processing unit that receives and processes data sent from the terminal, and further performs feature extraction and predictions using artificial intelligence.

[0773] "Features" are numerical and parametric information extracted from odor data that is necessary to specifically express a scent.

[0774] "Artificial intelligence means" refers to a system or device that uses machine learning algorithms such as neural networks to predict the expression of a scent from features.

[0775] "Description of scent" refers to verbalized information about a specific scent, such as "citrus-like, slightly sweet and sour."

[0776] A "recommendation means" is a system or algorithm that recommends related product information or similar products based on the analyzed scent expression.

[0777] The present invention relates to a system for quantifying odor data, verbalizing a specific scent based on the quantified data, and recommending related product information to a user. Specific embodiments of the present invention will be described below.

[0778] System Overview

[0779] The system comprises a sensor means, a terminal means, a server means, an artificial intelligence means, and a recommendation means.

[0780] 1. Sensor means

[0781] The sensor means is a device for acquiring odor data, and may be, for example, a gas sensor or an electronic nose. This sensor detects the scent in a specific environment and acquires it as digital data.

[0782] 2. Terminal means

[0783] The terminal means preprocesses the odor data obtained from the sensor means and transmits it to the server means. The preprocessing includes noise removal and data scaling. The terminal means transmits the preprocessed odor data to the server means using a secure communication protocol (e.g., HTTPS).

[0784] 3. Server Means

[0785] The server receives the preprocessed odor data sent from the terminal, performs further preprocessing and extracts features, and then inputs the features into the artificial intelligence to predict the expression of the scent.

[0786] 4. Artificial Intelligence Means

[0787] The artificial intelligence means is a model that predicts the expression of a scent from feature quantities, particularly using a neural network. A pre-trained neural network is used to generate a scent expression, such as "citrus-like, slightly sweet and sour." The prediction result is sent to the terminal means via the server means.

[0788] 5. Recommendation method

[0789] The recommendation system is a system that recommends related product information and similar products based on the scent description displayed to the user. The analysis results are linked to a product database to recommend the most suitable products to the user.

[0790] Specific examples of operation procedures

[0791] A specific example of the operation procedure is shown below: A user picks up a specific perfume bottle at a fragrance counter, starts the application, and holds the scent over the sensor. The sensor means acquires scent data and transmits the data to the terminal means.

[0792] The terminal means preprocesses the data and then transmits it to the server means using secure communication. The server means receives the data, performs further preprocessing, and extracts features. The features are then input into the artificial intelligence means to predict the expression of the scent.

[0793] The prediction result is sent to the terminal means and displayed to the user. Finally, the recommendation means recommends related product information based on the analysis result.

[0794] Example prompts for generative AI models

[0795] "I would like to develop an application for analyzing odor data. Please write a program in Python that uses a neural network to predict odors based on data obtained from an odor sensor. The program must include processes for preprocessing the odor data, extracting features, making predictions using an AI model, and displaying the results in a format that is easy for humans to understand."

[0796] In this way, the system of the present invention provides users with scent analysis and related product information, helping them to have a more comfortable purchasing experience.

[0797] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0798] Step 1: Acquiring odor data

[0799] A user activates an odor sensor using a terminal. The sensor means acquires the surrounding odor as data. At this time, the sensor means receives the odor in the environment as input, and outputs the odor data in digital format. Specifically, for example, an electronic nose uses multiple gas sensors to detect the chemical components of the odor and outputs their concentration information as digital data.

[0800] Step 2: Preprocessing the odor data

[0801] The terminal receives the digital data acquired from the odor sensor and performs preprocessing. The input here is the odor data acquired from the sensor means, and the output is the preprocessed data. The terminal means converts the data into a format that is easy to analyze later by removing noise and normalizing the data. Specific examples include noise removal by filtering and data normalization by scaling.

[0802] Step 3: Sending data

[0803] The preprocessed odor data is sent from the device to the server using a secure communication protocol (e.g., HTTPS). The input is the preprocessed data, and the output is the data sent to the server. Specifically, the device encrypts the data using HTTPS and transfers it securely to the server.

[0804] Step 4: Receiving data and further preprocessing

[0805] The server receives the data sent from the device and performs further preprocessing. The input is the data sent from the device, and the output is the preprocessed data. The server filters and normalizes the data, preparing it for feature extraction.

[0806] Step 5: Feature extraction

[0807] The server extracts features from the preprocessed data. The input here is further preprocessed data, and the output is features. Specifically, the server extracts important parameters using chemical component concentrations and pattern recognition algorithms, and converts them into vector format as features.

[0808] Step 6: Predict the scent

[0809] The server inputs the extracted features into an artificial intelligence means (neural network) to predict the scent expression. The input is the features and the output is the scent expression. The pre-trained neural network generates a scent expression such as "citrus, slightly sweet and sour" from the input features.

[0810] Step 7: Submit and view prediction results

[0811] The server sends the predicted scent expression to the terminal. The input is the predicted scent expression, and the output is the data sent to the terminal. The terminal receives this data and displays it to the user. Specifically, the terminal uses a user interface to display the analysis results in the form of "This scent is citrus-like and slightly sweet and sour."

[0812] Step 8: Recommend product information

[0813] The device recommends related product information based on the displayed scent description. The input is the displayed scent description, and the output is recommended product information. Specifically, the analysis results are compared with a product database, and appropriate product information (e.g., related perfumes and air fresheners) is presented to the user.

[0814] 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.

[0815] The present invention combines an emotion engine with a system that quantifies odor data and verbalizes specific odors based on that data. The emotion engine can recognize the user's emotions and adjust the expression of the odor based on those emotions. Specific embodiments of this system are described below.

[0816] Program Overview

[0817] This system consists of an odor sensor, a terminal, a server, an artificial intelligence model, and an emotion engine. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, preprocesses it, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the expression of the scent from the features. The emotion engine recognizes the user's emotion and adjusts the expression of the scent based on that emotion. Finally, the adjusted prediction result is sent to the terminal and displayed to the user.

[0818] Specific operation of the system

[0819] Acquisition and transmission of odor data (terminal)

[0820] The device activates the odor sensor, detects odors emanating from the target object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components. The acquired odor data is preprocessed and sent to the server using a secure communication protocol (e.g., HTTPS).

[0821] Data reception and preprocessing (server)

[0822] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step. The server then performs further pre-processing on the received data, such as normalization, filtering, and further noise reduction.

[0823] Feature extraction and scent prediction (server)

[0824] The server extracts features from the preprocessed data. These features are based on the concentration of specific chemical components or pattern recognition, and represent the attributes and indicators required for subsequent analysis. The extracted features are input into an artificial intelligence model, which uses a neural network to predict the expression of the scent from the input features.

[0825] Emotion recognition and scent adjustment (terminal)

[0826] The device activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expression data or voice data to recognize the emotion. For example, it determines whether the user is relaxed or nervous. Based on the emotion recognized by the emotion engine, the server adjusts the predicted scent expression accordingly.

[0827] Sending and displaying prediction results (terminal)

[0828] The adjusted prediction results are sent to the device, which receives the scent description sent from the server and displays it to the user. The displayed results are presented in a user-friendly format, such as "This scent is citrus-like and slightly sweet and sour."

[0829] Specific examples

[0830] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server, which performs further preprocessing and feature extraction. The extracted features are then input into an artificial intelligence model, which generates a prediction result of "citrus, slightly sweet and sour." If the emotion engine recognizes the user's emotion as "relaxed," the server adjusts the prediction result to something like "citrus with a relaxing effect." This result is sent to the device and displayed to the user.

[0831] This system enables quantitative evaluation of scents and provides users with verbalized scent analysis results. Furthermore, by adjusting the scent expression based on the user's emotions, more appropriate scent evaluation and design becomes possible.

[0832] The processing flow will be explained below.

[0833] Step 1: Acquire scents (device)

[0834] The device activates the odor sensor, detects odors emanating from the object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components.

[0835] Step 2: Preprocessing the data (terminal)

[0836] The device preprocesses the acquired odor data, specifically removing noise from the data and scaling or filtering as necessary. The preprocessed data is then converted into a format suitable for analysis.

[0837] Step 3: Sending data (terminal)

[0838] The preprocessed odor data is transmitted to a server using a secure communication protocol (e.g., HTTPS), ensuring data integrity and security.

[0839] Step 4: Receiving Data (Server)

[0840] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step.

[0841] Step 5: Data Preprocessing (Server)

[0842] The server performs further pre-processing on the received data, including normalizing, filtering, and further noise reduction, to improve the data quality and make it suitable for analysis.

[0843] Step 6: Feature extraction (server)

[0844] The server extracts features from the pre-processed data, which can be based on the concentration of specific chemical components or pattern recognition, and represent attributes or indicators required for subsequent analysis.

[0845] Step 7: Scent prediction (server)

[0846] The server inputs the extracted features into an AI model. This AI model is built using a neural network and predicts the expression of a specific scent from the features. The prediction results are verbalized and stored on the server.

[0847] Step 8: Emotion Recognition (Device)

[0848] The device activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expression data or voice data to recognize the user's emotions. For example, it determines whether the user is relaxed or nervous.

[0849] Step 9: Adjusting the scent (server)

[0850] The server adjusts the predicted scent expression based on the user's emotion recognized by the emotion engine. For example, if the user is relaxed, it adds the attribute "has a relaxing effect" to the scent expression.

[0851] Step 10: Sending prediction results (server)

[0852] The server then sends the adjusted prediction results to the device, allowing the device to provide a representation of the predicted scent to the user.

[0853] Step 11: Viewing the Results (Terminal)

[0854] The device receives the prediction results sent from the server and displays them to the user. The results are presented in a format that is easy for the user to understand, such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[0855] Step 12: Check the results (user)

[0856] The user checks the prediction results displayed on the device, evaluates whether the results match their own intuition, and can provide feedback on the results if necessary.

[0857] Example 2

[0858] 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."

[0859] Conventional odor data evaluation and analysis have been subjective, making quantitative evaluation difficult. Furthermore, the inability to appropriately evaluate and adjust the expression of odors based on the user's emotions limits the user experience. Therefore, there is a growing need for a system that can quantify odor data and recognize the user's emotions to appropriately express odors.

[0860] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes server means for receiving data, analysis means for preprocessing the data and extracting features, artificial intelligence means for predicting the expression of a specific scent from the features, and emotion recognition means for adjusting the expression of the scent predicted by the artificial intelligence means. This makes it possible to quantify the scent data and appropriately evaluate and adjust the expression of the scent based on the user's emotions.

[0861] A "sensor means" is a device for acquiring odor data.

[0862] The "processing device means" is a device for pre-processing odor data and transmitting it to a server as needed.

[0863] "Server means" refers to devices and systems for receiving, storing and analyzing pre-processed odor data.

[0864] The "analysis means" refers to a device or software that has the function of extracting features from the received odor data.

[0865] "Artificial intelligence means" refers to machine learning models and related technologies for predicting the expression of a specific scent from extracted features.

[0866] "Emotion recognition means" refers to a device or software that has the function of analyzing the user's facial expression data or voice data to recognize their emotions and adjust the expression of the scent.

[0867] A "secure communication protocol" is a communication method for securely transmitting odor data to a server.

[0868] "Features" are information that represent the concentration and pattern of specific chemical components extracted from odor data.

[0869] An "aroma description" is a description or adjective of a particular aroma that is generated based on the extracted features.

[0870] "Means for displaying to the user" refers to a mechanism for visually presenting the processed data and the adjusted scent expression to the user.

[0871] MODE FOR CARRYING OUT THE INVENTION

[0872] This invention is a system that quantifies odor data and verbalizes specific scents based on that data. Furthermore, by combining it with an emotion engine, it is possible to adjust the expression of the scent based on the user's emotions. This system is composed of the following elements:

[0873] Acquiring odor data (device)

[0874] The device uses an odor sensor to detect the odor of the target object and acquires it as digital data. The sensor quantifies the concentration and pattern of chemical components and passes the data to the device as digital data. It is desirable to use a high-precision chemical sensor for this process.

[0875] Preprocessing of odor data (terminal)

[0876] The device is equipped with software for preprocessing the acquired data, including noise removal and data correction, to improve the accuracy and reliability of the data. The preprocessed data is then sent to the server using a secure communication protocol.

[0877] Receiving and storing data (server)

[0878] The server receives the pre-processed data sent from the terminal and stores it in a database, which contains all the information necessary for subsequent analysis. The stored data is then sent to the analysis means for further pre-processing.

[0879] Data preprocessing and feature extraction (server)

[0880] The server performs preprocessing on the stored data, such as normalization, filtering, and noise removal. After preprocessing, feature values ​​are extracted by the analysis means. Feature values ​​are numerical indicators that indicate the concentration and pattern of chemical components.

[0881] Scent prediction (server)

[0882] The extracted features are input into an artificial intelligence means, which uses a neural network to predict a specific aroma expression from the features. For example, an abstract aroma expression such as "citrus, slightly sweet and sour" can be obtained.

[0883] Emotion recognition and expression regulation (terminal)

[0884] When a user approaches the device, the emotion engine is activated. The emotion engine analyzes the user's facial expression and voice data to recognize their emotion. Based on the analysis results, the server adjusts the predicted scent expression. For example, if the user is relaxed, the expression will be modified to something like "citrus with a relaxing effect."

[0885] Sending and displaying adjustment results (terminal)

[0886] The adjusted results are sent from the server to the device using a secure communication protocol. The device receives them and displays them to the user. The display format is a specific description such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[0887] Specific examples

[0888] For example, when a user brings an orange peel close to a scent sensor, the system operates as follows: The device activates the scent sensor, acquires data, and performs preprocessing. The preprocessed data is sent to the server using the HTTPS protocol. The server saves the received data, performs further preprocessing, and extracts features. A neural network is used to predict the scent, such as "citrus, slightly sweet and sour." At the same time, if the emotion engine recognizes the user's emotion as "relaxed," the predicted result is adjusted to "citrus with a relaxing effect." This result is sent to the device and displayed to the user.

[0889] Example prompts for generative AI models

[0890] The following prompts can be used to have the generative AI model generate explanatory text:

[0891] Please explain the specific program processing flow of a system that combines an odor sensor and an emotion engine. Please break down the processing steps and provide a detailed description of each.

[0892] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0893] Processing Steps

[0894] Step 1: Acquiring odor data (device)

[0895] The device activates the odor sensor and captures the odor emanating from the object as digital data. The input is the object's odor, which is converted into digital data as output. This data contains numerical values ​​that indicate the concentration and pattern of specific chemical components. For example, when a user brings an orange peel close to the sensor, chemical component concentration data is obtained.

[0896] Step 2: Preprocessing the odor data (terminal)

[0897] The device performs preprocessing on the acquired digital data. The acquired digital data is the input, and the preprocessed data is the output. Preprocessing includes noise removal, data correction, normalization, etc. Specifically, operations are performed to filter out noise in the data and normalize the signal from the sensor.

[0898] Step 3: Sending odor data (device)

[0899] The terminal sends the preprocessed data to the server. The preprocessed data is the input, and the output is the data sent via a secure communication protocol (e.g., HTTPS). The data is encrypted before being sent, ensuring security.

[0900] Step 4: Receiving and storing data (server)

[0901] The server receives the pre-processed data sent from the terminal. The sent data is the input and is saved in the database as the output. The received data is stored in the server's database for later analysis.

[0902] Step 5: Data Preprocessing (Server)

[0903] The server performs further pre-processing on the received and stored data. It takes the stored data as input and the re-processed data as output. Pre-processing here includes noise filtering, normalization, and additional data correction. This processing further improves the accuracy and consistency of the data.

[0904] Step 6: Feature extraction (server)

[0905] The server extracts features from the preprocessed data. The preprocessed data is input, and features are obtained as output. Features are numerical indicators such as the concentration or pattern of chemical components. Specifically, data analysis algorithms are used to recognize the characteristics of chemical components, and that information is extracted as features.

[0906] Step 7: Scent prediction (server)

[0907] The server inputs the extracted features into an artificial intelligence model to predict the expression of the scent. The features are input, and the predicted scent expression is obtained as output. A neural network is used as the artificial intelligence model. For example, the model predicts a scent expression such as "citrus, slightly sweet and sour" from the input features.

[0908] Step 8: Emotion Recognition (Device)

[0909] The device activates an emotion engine and collects facial expression and voice data to recognize the user's emotions. The input is the user's facial expression and voice data, and the output is recognized emotion data. The emotion engine collects data using a camera and microphone and analyzes it to determine whether the user is relaxed or tense.

[0910] Step 9: Adjusting scent expression (server)

[0911] The server adjusts the predicted scent expression appropriately based on the recognized emotion data. The input is the predicted scent expression and emotion data, and the output is the adjusted scent expression. For example, if the user is recognized as relaxed, the scent expression is adjusted to "citrus with a relaxing effect."

[0912] Step 10: Sending the adjustment results (server)

[0913] The server sends the adjusted scent representation to the device. The input is the adjusted scent representation, and the output is data sent via a secure communication protocol. This data is also encrypted before transmission, so the information remains secure.

[0914] Step 11: Viewing the adjustment results (device)

[0915] The device displays the adjustment results received from the server to the user. The received data is input, and the output is the information displayed to the user. The display format is a specific description of the scent, such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[0916] (Application example 2)

[0917] 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."

[0918] Conventional odor analysis systems can quantitatively acquire and analyze odor data, but they cannot adjust the analysis results based on the user's emotions. This poses a problem in that users are unable to receive optimal suggestions based on their emotions when selecting a scent. Another issue with conventional systems is that they can only represent odors in a fixed way, which lacks flexibility.

[0919] 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.

[0920] In this invention, the server includes means for receiving odor data, means for extracting features from the received data, means for predicting an aroma expression from the features using artificial intelligence means, means for recognizing a user's emotion, means for adjusting the aroma expression based on the recognized emotion, and means for transmitting the predicted and adjusted aroma expression to the terminal, thereby making it possible to provide an aroma expression that is appropriately adjusted based on the user's emotion.

[0921] "Odor data" refers to the digital representation of the concentration and pattern of specific chemical components acquired by an odor sensor.

[0922] "Sensor means" refers to a technological means for acquiring odor data, including devices that sense specific chemical components.

[0923] The term "terminal means" refers to an electronic device for preprocessing acquired odor data and transmitting the data to the server means.

[0924] "Preprocessed odor data" refers to raw data obtained from a sensor means that has been appropriately filtered and denoised.

[0925] The "server means" is a central processing unit that stores the odor data received from the terminal means, extracts features, and performs analysis using artificial intelligence means.

[0926] "Features" are information that serves as important attributes or indicators of the analysis target, extracted from preprocessed odor data.

[0927] "Artificial intelligence means" refers to a technical means that uses machine learning models such as neural networks to predict the expression of a specific fragrance from features.

[0928] "Emotion recognition means" refers to a technical means for analyzing a user's facial expression data and voice data and estimating the user's emotions.

[0929] The "means for adjusting the expression of a scent" refers to a technical means for appropriately correcting and adjusting the predicted expression of a scent based on the user's emotions recognized by the emotion recognition means.

[0930] "Scent expression" refers to the characteristics and impressions of a scent that are verbalized based on scent data acquired by a scent sensor.

[0931] The present invention combines an emotion engine with a system that quantifies odor data and verbalizes specific scents. An embodiment of this system will be described in detail below.

[0932] System Configuration

[0933] The system consists of an odor sensor, a terminal, a server, an artificial intelligence model, and an emotion engine.

[0934] Hardware and Software

[0935] Odor sensor: A device that detects specific chemical components and is used to obtain odor data.

[0936] Terminal: A device such as a smartphone or smart glasses that preprocesses the odor data and transmits it to the server. The terminal also has a camera and microphone for emotion recognition.

[0937] Server: Located on the cloud, it receives odor data sent from the device and extracts features from the preprocessed data.

[0938] Artificial intelligence model: A technology that uses neural networks to predict the expression of a scent from features.

[0939] Emotion engine: A technology that analyzes the user's facial expressions and voice to recognize emotions.

[0940] Program processing overview

[0941] 1. Acquisition and preprocessing of odor data

[0942] The device acquires odor data from the target object using an odor sensor. The acquired data is preprocessed on the device to remove noise and perform filtering. The preprocessed data is then sent to the server using a secure communication protocol (e.g., HTTPS).

[0943] 2. Data reception and feature extraction

[0944] The server receives the preprocessed data sent from the device. The received data is stored in a database and then goes on to the next processing step. The server extracts features from this data and inputs them into an artificial intelligence model.

[0945] 3. Fragrance Expression Prediction

[0946] Using an artificial intelligence model (neural network), a specific aroma expression is predicted from the features. For example, a predicted result such as "citrus, slightly sweet and sour" is generated.

[0947] 4. Emotional recognition and scent regulation

[0948] The emotion engine runs on the device and analyzes the user's facial expression data (e.g., using the camera in smart glasses) and voice data to recognize emotions. Based on the recognized emotion, the server adjusts the prediction result and generates a more appropriate scent description. For example, it adjusts the description to "citrus with a relaxing effect."

[0949] 5. Sending and displaying the expression results

[0950] The final adjusted scent representation is sent from the server to the device, which receives the result and displays it to the user.

[0951] Usage example

[0952] For example, let's consider a specific example where a user tries out perfume in a physical store. When the user brings a perfume bottle close to an odor sensor, the sensor captures odor data. The captured data is preprocessed on the device and sent to the server. The server extracts features from the data and predicts the scent expression using an artificial intelligence model. The emotion engine then recognizes the user's relaxed facial expression and adjusts the expression to "citrus with a relaxing effect." This is then sent to the device and displayed to the user, allowing them to choose a scent that suits their condition.

[0953] Prompt Sentence Examples

[0954] "When a user chooses a perfume in a physical store, acquire scent data using an odor sensor, and adjust the scent representation predicted by an AI model using smart glasses based on emotion recognition data to generate an application that suggests the appropriate scent."

[0955] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0956] Step 1:

[0957] The device acquires odor data using an odor sensor. The sensor detects odors emanating from an object and sends the data in digital format to the device. The input is the odor of the object, and the output is digital odor data. Specifically, the odor sensor activates and detects the odor components of the surrounding air and the object.

[0958] Step 2:

[0959] The device preprocesses the acquired odor data, removing noise and filtering to improve data accuracy. The input is raw data obtained from the odor sensor, and the output is preprocessed data. Specifically, the device's preprocessing algorithm normalizes the data and removes unnecessary noise.

[0960] Step 3:

[0961] The device sends the preprocessed odor data to the server. The data is transferred securely using a secure communication protocol (e.g., HTTPS). The input is the preprocessed data, and the output is a notification to the server that transmission has been completed. Specifically, the device establishes an Internet connection and uploads the data to the server.

[0962] Step 4:

[0963] The server receives odor data sent from the device and stores it in a database. The input is the preprocessed data sent from the device, and the output is a notification that the data has been stored in the database. Specifically, the server converts the received data into a specific format and stores it in the database.

[0964] Step 5:

[0965] The server extracts features from the data stored in the database. These features contain the information necessary for analysis. The input is preprocessed data, and the output is the extracted features. Specifically, the server uses machine learning algorithms to extract important attributes and patterns.

[0966] Step 6:

[0967] The server inputs the extracted features into an artificial intelligence model (neural network) to predict the expression of the scent. The input is the features, and the output is the predicted expression of the scent. Specifically, the AI ​​model on the server analyzes the data and verbalizes the scent.

[0968] Step 7:

[0969] The device recognizes the user's emotions using emotion recognition means. It uses a camera and microphone to collect emotion data from the user's facial expressions and voice. The input is the user's facial expression data and voice data, and the output is the recognized emotion. Specifically, the device performs emotion analysis in real time to identify the emotion.

[0970] Step 8:

[0971] The server adjusts the predicted scent expression based on the recognized emotion. The input is the predicted scent expression and the recognized emotion, and the output is the adjusted scent expression. Specifically, the server uses the emotion engine to modify the scent expression.

[0972] Step 9:

[0973] The server sends the adjusted scent representation to the terminal. The input is the adjusted scent representation, and the output is a notification of completion of transmission to the terminal. Specifically, the server packs the data into packets and sends them to the terminal via the network.

[0974] Step 10:

[0975] The device receives the scent description sent from the server and displays it to the user. The input is the adjusted scent description, and the output is a description of the displayed scent. Specifically, the device displays the scent information in text format on the display.

[0976] 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.

[0977] 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.

[0978] 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.

[0979] [Fourth embodiment]

[0980] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0981] 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.

[0982] 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).

[0983] 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.

[0984] 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.

[0985] 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).

[0986] 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.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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.

[0991] 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.

[0992] 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."

[0993] The present invention relates to a system for quantifying odor data and verbalizing a specific odor based on the quantified data. Specific embodiments of this system will be described below.

[0994] Program Overview

[0995] This system consists of an odor sensor, a terminal, a server, and an artificial intelligence model. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, preprocesses it, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the expression of the scent from the features. Finally, the prediction result is sent to the terminal and displayed to the user.

[0996] Specific operation of the system

[0997] Acquisition and transmission of odor data (terminal)

[0998] The device activates the odor sensor and acquires odor data in a specific environment. This data is converted into a digital format and preprocessed. Preprocessing includes noise reduction and scaling. The preprocessed data is then sent to a server using a secure communication protocol (e.g., HTTPS).

[0999] Data reception and preprocessing (server)

[1000] The server receives the data sent from the device. The received data requires further preprocessing, such as filtering and normalization. The processed data is then used for feature extraction.

[1001] Feature extraction and scent prediction (server)

[1002] The server has a means of extracting features from the preprocessed data. Specifically, it calculates features based on the concentration of specific chemical components and pattern recognition. These features are converted into vector format and input into an artificial intelligence model. The artificial intelligence model uses a neural network in particular, and predicts the aroma expression (e.g., citrus, floral, etc.) from the input features.

[1003] Sending and displaying prediction results (terminal)

[1004] The server then sends the predicted scent description to the device, which then displays the result to the user. The result may be presented in the form of, for example, "This scent is citrus-like and slightly sweet and sour."

[1005] Specific examples

[1006] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server, which performs further preprocessing and feature extraction. The extracted features are then input into an artificial intelligence model, which generates a prediction result: "citrus-like, slightly sweet and sour." This result is sent to the device and displayed to the user.

[1007] This system enables quantitative evaluation of scents and provides users with verbalized scent analysis results, facilitating the design and evaluation of scents for specific applications.

[1008] The processing flow will be explained below.

[1009] Step 1: Acquire scents (device)

[1010] The device activates the odor sensor, detects odors emanating from the object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components.

[1011] Step 2: Preprocessing the data (terminal)

[1012] The device preprocesses the acquired odor data, specifically removing noise from the data and scaling or filtering as necessary. The preprocessed data is then converted into a format suitable for analysis.

[1013] Step 3: Sending data (terminal)

[1014] The preprocessed odor data is transmitted to a server using a secure communication protocol (e.g., HTTPS), ensuring data integrity and security.

[1015] Step 4: Receiving Data (Server)

[1016] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step.

[1017] Step 5: Data Preprocessing (Server)

[1018] The server performs further pre-processing on the received data, including normalizing, filtering, and further noise reduction, to improve the data quality and make it suitable for analysis.

[1019] Step 6: Feature extraction (server)

[1020] The server extracts features from the pre-processed data, which can be based on the concentration of specific chemical components or pattern recognition, and represent attributes or indicators required for subsequent analysis.

[1021] Step 7: Scent prediction (server)

[1022] The server inputs the extracted features into an AI model. This AI model is built using a neural network and predicts the expression of a specific scent from the features. The prediction results are verbalized and stored on the server.

[1023] Step 8: Sending prediction results (server)

[1024] The server sends the prediction results to the device, which then provides the user with a representation of the predicted scent.

[1025] Step 9: View the results (terminal)

[1026] The device receives the prediction results sent from the server and displays them to the user. The results are presented in a format that is easy for the user to understand, such as "This scent is citrus-like and slightly sweet and sour."

[1027] Step 10: Check the results (user)

[1028] The user checks the prediction results displayed on the device, evaluates whether the results match their own intuition, and can provide feedback on the results if necessary.

[1029] Example 1

[1030] 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."

[1031] Conventional systems that analyze odor data and verbalize scents have had issues with data accuracy and security. It is also difficult to accurately extract and verbalize the characteristics of odors, making it difficult to provide users with useful information. Furthermore, processing speed and prediction accuracy are often insufficient, making them impractical.

[1032] 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.

[1033] In this invention, the server includes means for additionally preprocessing the received data, filtering and normalizing it, means for extracting features from the additionally preprocessed data, and means for converting the extracted features into vector format, thereby enabling highly accurate and efficient data analysis and scent prediction.

[1034] "Odor data" is digital data that represents information about odors in a particular environment, obtained by a sensor means.

[1035] The "sensor means" is a device for acquiring odor data, which senses odors from any environment and converts them into digital data.

[1036] The "terminal means" is a device that receives odor data obtained from the sensor means and performs preprocessing, and also has the function of transmitting the processed data to the server means.

[1037] "Preprocessing" refers to the process of removing noise and scaling odor data acquired from the sensor means to make it easier to analyze.

[1038] The "server means" is a device that receives preprocessed odor data sent from the terminal means, and performs additional preprocessing, feature extraction, and prediction using artificial intelligence means.

[1039] "Additional pre-processing" refers to the filtering and normalization processes that the server means performs on the data it receives, in order to improve the consistency and accuracy of the data.

[1040] "Features" are information that indicates the concentration and pattern of specific chemical components, extracted from odor data that has undergone preprocessing and additional preprocessing.

[1041] The "vector format" is a format for expressing feature quantities as numerical data, and is a data format used for inputting data to artificial intelligence means.

[1042] "Artificial intelligence means" refers to software or hardware that predicts the expression of a scent from features, primarily using techniques such as neural networks.

[1043] A "scent description" is a specific description of a scent based on scent data predicted by artificial intelligence means, and is information provided in a format that is understandable to the user.

[1044] A "secure communication protocol" is a communication protocol used to ensure confidentiality and integrity of information when sending and receiving data, and examples include HTTPS.

[1045] The present invention relates to a system for quantifying odor data and verbalizing a specific odor based on the quantified data. Specific embodiments of this system will be described below.

[1046] System Overview

[1047] This system consists of an odor sensor, a terminal, a server, and an artificial intelligence model. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, performs additional preprocessing, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the scent expression from the features. Finally, the prediction result is sent to the terminal and displayed to the user.

[1048] Acquisition and preprocessing of odor data (terminal)

[1049] The user uses an odor sensor connected to a device. For example, when the user holds an orange peel close to the sensor, the sensor captures odor data in the environment and converts it into digital data. This data is then pre-processed on the device, with noise reduction and scaling. The pre-processed data is then sent to a server using a secure communication protocol such as HTTPS.

[1050] Data reception and additional preprocessing (server)

[1051] The server receives the preprocessed odor data sent from the device, which undergoes additional preprocessing such as filtering and normalization to improve consistency and accuracy, preparing the data for feature extraction.

[1052] Feature extraction and scent prediction (server)

[1053] The server extracts features from the pre-processed data. For example, it analyzes the concentration and patterns of specific chemical components and converts them into vector format. This feature vector is input into an artificial intelligence model using a neural network, which predicts the scent expression (e.g., citrus or floral) from the odor data.

[1054] Sending and displaying prediction results (terminal)

[1055] The server sends the predicted scent description to the device, which then receives the result and displays it to the user. For example, the result might be something like, "This scent is citrusy and slightly sweet and sour."

[1056] Specific examples

[1057] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server using a secure communication protocol. The server then performs further preprocessing on the received data and extracts features. The extracted features are then input into an artificial intelligence model, which generates a prediction result: "citrus-like, slightly sweet and sour." This result is sent to the device and displayed to the user.

[1058] Prompt Sentence Examples

[1059] An example of a prompt to be input to the generative AI model is as follows:

[1060] 1. "Describe the smell of orange peel."

[1061] 2. "Predict the scent description from this smell data."

[1062] 3. "Please describe in words the scent detected by the odor sensor."

[1063] This system enables quantitative evaluation of scents and can quickly provide users with verbalized scent analysis results, facilitating the design and evaluation of scents for specific applications.

[1064] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1065] Step 1: Acquiring odor data (device)

[1066] When a user brings an orange peel close to the sensor, an odor sensor connected to the device captures odor data in the environment. The sensor detects this odor as an analog signal and converts it into digital data. Specifically, the sensor measures the concentration of chemical components and converts that data into binary code. At this stage, the input is the odor components emanating from the orange peel, and the output is odor data in digital format.

[1067] Step 2: Data preprocessing (terminal)

[1068] The device performs preprocessing on the acquired digital odor data. Specifically, it applies a noise reduction filter to the data and scales it to improve the quality of the data. Noise reduction is the process of removing random noise, and scaling is the process of confining the data within a certain range. The input at this stage is the digital odor data sent from the sensor, and the output after processing is the preprocessed odor data.

[1069] Step 3: Send data (terminal)

[1070] The preprocessed odor data is sent to the server using a secure communication protocol (e.g., HTTPS). At this time, the terminal encrypts the data using AES to ensure data confidentiality. Specifically, the terminal generates a data packet and sends it to the server using the HTTPS protocol. At this stage, the input is the preprocessed odor data, and the output is securely transmitted data.

[1071] Step 4: Receiving data (server)

[1072] The server receives preprocessed smell data sent from the device. The server verifies the received data and checks for unauthorized access or data corruption. Specific operations include the server decoding the received packets and verifying the integrity of the data. The input at this stage is the secure transmission data, and the output is the verified smell data.

[1073] Step 5: Preprocessing for adding data (server)

[1074] The server performs additional preprocessing on the received data. Specifically, it filters and normalizes the data to improve the consistency and accuracy of the data. Filtering is the operation of removing unnecessary data, and normalization is the operation of converting the data to a unified scale. The input at this stage is the verified odor data, and the output is the odor data that has undergone additional preprocessing.

[1075] Step 6: Feature extraction (server)

[1076] The server extracts features from the additionally preprocessed data. Specifically, it analyzes the concentrations and patterns of specific chemical components in the data and converts them into vector format. These features are important data to input into the subsequent artificial intelligence model. The input at this stage is the additionally preprocessed odor data, and the output is a feature vector.

[1077] Step 7: Scent prediction (server)

[1078] The server inputs the feature vector into an artificial intelligence model (e.g., a neural network) to predict the aroma expression. Specifically, the server uses the neural network to generate an aroma expression, such as "citrus, slightly sweet and sour," from the features. The input at this stage is the feature vector, and the output is the predicted aroma expression.

[1079] Step 8: Send prediction results (server)

[1080] The server sends the predicted scent representation to the device, which then displays a specific scent representation on the device to the user. Specific operations include the server formatting the prediction results in JSON and sending them to the device again using a secure protocol. The input at this stage is the predicted scent representation, and the output is securely transmitted data.

[1081] Step 9: Display the results (terminal)

[1082] The device displays the received prediction results to the user. For example, the screen might display "This scent is citrus-like and slightly sweet and sour." Specific operations include the device analyzing the received data and displaying the results on the user interface. The input at this stage is the transmitted prediction data, and the output is a representation of the scent displayed to the user.

[1083] (Application example 1)

[1084] 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."

[1085] Conventional odor data analysis systems were able to quantify acquired odor data and verbalize specific odors based on that data, but they lacked the functionality to recommend related product information when providing the analysis results to users. As a result, users considering purchasing a specific product faced the challenge of not being provided with sufficient information based on the analysis results alone. Specifically, even if a scent was detected in a fragrance section, the system was unable to effectively support users' purchasing behavior because it did not provide product information related to that scent or recommendations for similar products.

[1086] 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.

[1087] In this invention, the server includes a sensor means for acquiring odor data, a terminal means for preprocessing the odor data from the sensor means, a server means for receiving the preprocessed odor data transmitted from the terminal means, a means for extracting features from the received data, an artificial intelligence means for predicting a description of a specific odor from the extracted features, a means for transmitting the predicted odor description to the terminal means, a means for displaying the transmitted odor description to the user on the terminal means, and a recommendation means for recommending related product information based on the odor description displayed to the user. This allows the user to receive not only the analysis results but also product information related to the odor and recommendations of similar products, thereby supporting purchasing behavior.

[1088] "Odor data" is quantitative information about a specific scent obtained by an odor sensor.

[1089] "Sensor means" refers to a device or mechanism for acquiring odor data.

[1090] The "terminal means" is an electronic device that preprocesses the odor data acquired from the odor sensor and communicates with other devices or systems as necessary.

[1091] The "server means" is a central processing unit that receives and processes data sent from the terminal, and further performs feature extraction and predictions using artificial intelligence.

[1092] "Features" are numerical and parametric information extracted from odor data that is necessary to specifically express a scent.

[1093] "Artificial intelligence means" refers to a system or device that uses machine learning algorithms such as neural networks to predict the expression of a scent from features.

[1094] "Description of scent" refers to verbalized information about a specific scent, such as "citrus-like, slightly sweet and sour."

[1095] A "recommendation means" is a system or algorithm that recommends related product information or similar products based on the analyzed scent expression.

[1096] The present invention relates to a system for quantifying odor data, verbalizing a specific scent based on the quantified data, and recommending related product information to a user. Specific embodiments of the present invention will be described below.

[1097] System Overview

[1098] The system comprises a sensor means, a terminal means, a server means, an artificial intelligence means, and a recommendation means.

[1099] 1. Sensor means

[1100] The sensor means is a device for acquiring odor data, and may be, for example, a gas sensor or an electronic nose. This sensor detects the scent in a specific environment and acquires it as digital data.

[1101] 2. Terminal means

[1102] The terminal means preprocesses the odor data obtained from the sensor means and transmits it to the server means. The preprocessing includes noise removal and data scaling. The terminal means transmits the preprocessed odor data to the server means using a secure communication protocol (e.g., HTTPS).

[1103] 3. Server Means

[1104] The server receives the preprocessed odor data sent from the terminal, performs further preprocessing and extracts features, and then inputs the features into the artificial intelligence to predict the expression of the scent.

[1105] 4. Artificial Intelligence Means

[1106] The artificial intelligence means is a model that predicts the expression of a scent from feature quantities, particularly using a neural network. A pre-trained neural network is used to generate a scent expression, such as "citrus-like, slightly sweet and sour." The prediction result is sent to the terminal means via the server means.

[1107] 5. Recommendation method

[1108] The recommendation system is a system that recommends related product information and similar products based on the scent description displayed to the user. The analysis results are linked to a product database to recommend the most suitable products to the user.

[1109] Specific examples of operation procedures

[1110] A specific example of the operation procedure is shown below: A user picks up a specific perfume bottle at a fragrance counter, starts the application, and holds the scent over the sensor. The sensor means acquires scent data and transmits the data to the terminal means.

[1111] The terminal means preprocesses the data and then transmits it to the server means using secure communication. The server means receives the data, performs further preprocessing, and extracts features. The features are then input into the artificial intelligence means to predict the expression of the scent.

[1112] The prediction result is sent to the terminal means and displayed to the user. Finally, the recommendation means recommends related product information based on the analysis result.

[1113] Example prompts for generative AI models

[1114] "I would like to develop an application for analyzing odor data. Please write a program in Python that uses a neural network to predict odors based on data obtained from an odor sensor. The program must include processes for preprocessing the odor data, extracting features, making predictions using an AI model, and displaying the results in a format that is easy for humans to understand."

[1115] In this way, the system of the present invention provides users with scent analysis and related product information, helping them to have a more comfortable purchasing experience.

[1116] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1117] Step 1: Acquiring odor data

[1118] A user activates an odor sensor using a terminal. The sensor means acquires the surrounding odor as data. At this time, the sensor means receives the odor in the environment as input, and outputs the odor data in digital format. Specifically, for example, an electronic nose uses multiple gas sensors to detect the chemical components of the odor and outputs their concentration information as digital data.

[1119] Step 2: Preprocessing the odor data

[1120] The terminal receives the digital data acquired from the odor sensor and performs preprocessing. The input here is the odor data acquired from the sensor means, and the output is the preprocessed data. The terminal means converts the data into a format that is easy to analyze later by removing noise and normalizing the data. Specific examples include noise removal by filtering and data normalization by scaling.

[1121] Step 3: Sending data

[1122] The preprocessed odor data is sent from the device to the server using a secure communication protocol (e.g., HTTPS). The input is the preprocessed data, and the output is the data sent to the server. Specifically, the device encrypts the data using HTTPS and transfers it securely to the server.

[1123] Step 4: Receiving data and further preprocessing

[1124] The server receives the data sent from the device and performs further preprocessing. The input is the data sent from the device, and the output is the preprocessed data. The server filters and normalizes the data, preparing it for feature extraction.

[1125] Step 5: Feature extraction

[1126] The server extracts features from the preprocessed data. The input here is further preprocessed data, and the output is features. Specifically, the server extracts important parameters using chemical component concentrations and pattern recognition algorithms, and converts them into vector format as features.

[1127] Step 6: Predict the scent

[1128] The server inputs the extracted features into an artificial intelligence means (neural network) to predict the scent expression. The input is the features and the output is the scent expression. The pre-trained neural network generates a scent expression such as "citrus, slightly sweet and sour" from the input features.

[1129] Step 7: Submit and view prediction results

[1130] The server sends the predicted scent expression to the terminal. The input is the predicted scent expression, and the output is the data sent to the terminal. The terminal receives this data and displays it to the user. Specifically, the terminal uses a user interface to display the analysis results in the form of "This scent is citrus-like and slightly sweet and sour."

[1131] Step 8: Recommend product information

[1132] The device recommends related product information based on the displayed scent description. The input is the displayed scent description, and the output is recommended product information. Specifically, the analysis results are compared with a product database, and appropriate product information (e.g., related perfumes and air fresheners) is presented to the user.

[1133] 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.

[1134] The present invention combines an emotion engine with a system that quantifies odor data and verbalizes specific odors based on that data. The emotion engine can recognize the user's emotions and adjust the expression of the odor based on those emotions. Specific embodiments of this system are described below.

[1135] Program Overview

[1136] This system consists of an odor sensor, a terminal, a server, an artificial intelligence model, and an emotion engine. The odor sensor acquires odor data, which is preprocessed by the terminal and sent to the server. The server receives the data, preprocesses it, and extracts features from it. Next, an artificial intelligence model (e.g., a neural network) is used to predict the expression of the scent from the features. The emotion engine recognizes the user's emotion and adjusts the expression of the scent based on that emotion. Finally, the adjusted prediction result is sent to the terminal and displayed to the user.

[1137] Specific operation of the system

[1138] Acquisition and transmission of odor data (terminal)

[1139] The device activates the odor sensor, detects odors emanating from the target object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components. The acquired odor data is preprocessed and sent to the server using a secure communication protocol (e.g., HTTPS).

[1140] Data reception and preprocessing (server)

[1141] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step. The server then performs further pre-processing on the received data, such as normalization, filtering, and further noise reduction.

[1142] Feature extraction and scent prediction (server)

[1143] The server extracts features from the preprocessed data. These features are based on the concentration of specific chemical components or pattern recognition, and represent the attributes and indicators required for subsequent analysis. The extracted features are input into an artificial intelligence model, which uses a neural network to predict the expression of the scent from the input features.

[1144] Emotion recognition and scent adjustment (terminal)

[1145] The device activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expression data or voice data to recognize the emotion. For example, it determines whether the user is relaxed or nervous. Based on the emotion recognized by the emotion engine, the server adjusts the predicted scent expression accordingly.

[1146] Sending and displaying prediction results (terminal)

[1147] The adjusted prediction results are sent to the device, which receives the scent description sent from the server and displays it to the user. The displayed results are presented in a user-friendly format, such as "This scent is citrus-like and slightly sweet and sour."

[1148] Specific examples

[1149] For example, suppose a user holds an orange peel close to an odor sensor. The device activates the odor sensor, acquires the data, and performs preprocessing. The preprocessed data is sent to the server, which performs further preprocessing and feature extraction. The extracted features are then input into an artificial intelligence model, which generates a prediction result of "citrus, slightly sweet and sour." If the emotion engine recognizes the user's emotion as "relaxed," the server adjusts the prediction result to something like "citrus with a relaxing effect." This result is sent to the device and displayed to the user.

[1150] This system enables quantitative evaluation of scents and provides users with verbalized scent analysis results. Furthermore, by adjusting the scent expression based on the user's emotions, more appropriate scent evaluation and design becomes possible.

[1151] The processing flow will be explained below.

[1152] Step 1: Acquire scents (device)

[1153] The device activates the odor sensor, detects odors emanating from the object, and captures them as digital data. This data is acquired as sensor output, and includes numerical values ​​that represent the concentration and pattern of specific chemical components.

[1154] Step 2: Preprocessing the data (terminal)

[1155] The device preprocesses the acquired odor data, specifically removing noise from the data and scaling or filtering as necessary. The preprocessed data is then converted into a format suitable for analysis.

[1156] Step 3: Sending data (terminal)

[1157] The preprocessed odor data is transmitted to a server using a secure communication protocol (e.g., HTTPS), ensuring data integrity and security.

[1158] Step 4: Receiving Data (Server)

[1159] The server receives the data sent from the device, stores it in a database, and prepares it for the next processing step.

[1160] Step 5: Data Preprocessing (Server)

[1161] The server performs further pre-processing on the received data, including normalizing, filtering, and further noise reduction, to improve the data quality and make it suitable for analysis.

[1162] Step 6: Feature extraction (server)

[1163] The server extracts features from the pre-processed data, which can be based on the concentration of specific chemical components or pattern recognition, and represent attributes or indicators required for subsequent analysis.

[1164] Step 7: Scent prediction (server)

[1165] The server inputs the extracted features into an AI model. This AI model is built using a neural network and predicts the expression of a specific scent from the features. The prediction results are verbalized and stored on the server.

[1166] Step 8: Emotion Recognition (Device)

[1167] The device activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expression data or voice data to recognize the user's emotions. For example, it determines whether the user is relaxed or nervous.

[1168] Step 9: Adjusting the scent (server)

[1169] The server adjusts the predicted scent expression based on the user's emotion recognized by the emotion engine. For example, if the user is relaxed, it adds the attribute "has a relaxing effect" to the scent expression.

[1170] Step 10: Sending prediction results (server)

[1171] The server then sends the adjusted prediction results to the device, allowing the device to provide a representation of the predicted scent to the user.

[1172] Step 11: Viewing the Results (Terminal)

[1173] The device receives the prediction results sent from the server and displays them to the user. The results are presented in a format that is easy for the user to understand, such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[1174] Step 12: Check the results (user)

[1175] The user checks the prediction results displayed on the device, evaluates whether the results match their own intuition, and can provide feedback on the results if necessary.

[1176] Example 2

[1177] 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."

[1178] Conventional odor data evaluation and analysis have been subjective, making quantitative evaluation difficult. Furthermore, the inability to appropriately evaluate and adjust the expression of odors based on the user's emotions limits the user experience. Therefore, there is a growing need for a system that can quantify odor data and recognize the user's emotions to appropriately express odors.

[1179] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes server means for receiving data, analysis means for preprocessing the data and extracting features, artificial intelligence means for predicting the expression of a specific scent from the features, and emotion recognition means for adjusting the expression of the scent predicted by the artificial intelligence means. This makes it possible to quantify the scent data and appropriately evaluate and adjust the expression of the scent based on the user's emotions.

[1180] A "sensor means" is a device for acquiring odor data.

[1181] The "processing device means" is a device for pre-processing odor data and transmitting it to a server as needed.

[1182] "Server means" refers to devices and systems for receiving, storing and analyzing pre-processed odor data.

[1183] The "analysis means" refers to a device or software that has the function of extracting features from the received odor data.

[1184] "Artificial intelligence means" refers to machine learning models and related technologies for predicting the expression of a specific scent from extracted features.

[1185] "Emotion recognition means" refers to a device or software that has the function of analyzing the user's facial expression data or voice data to recognize their emotions and adjust the expression of the scent.

[1186] A "secure communication protocol" is a communication method for securely transmitting odor data to a server.

[1187] "Features" are information that represent the concentration and pattern of specific chemical components extracted from odor data.

[1188] An "aroma description" is a description or adjective of a particular aroma that is generated based on the extracted features.

[1189] "Means for displaying to the user" refers to a mechanism for visually presenting the processed data and the adjusted scent expression to the user.

[1190] MODE FOR CARRYING OUT THE INVENTION

[1191] This invention is a system that quantifies odor data and verbalizes specific scents based on that data. Furthermore, by combining it with an emotion engine, it is possible to adjust the expression of the scent based on the user's emotions. This system is composed of the following elements:

[1192] Acquiring odor data (device)

[1193] The device uses an odor sensor to detect the odor of the target object and acquires it as digital data. The sensor quantifies the concentration and pattern of chemical components and passes the data to the device as digital data. It is desirable to use a high-precision chemical sensor for this process.

[1194] Preprocessing of odor data (terminal)

[1195] The device is equipped with software for preprocessing the acquired data, including noise removal and data correction, to improve the accuracy and reliability of the data. The preprocessed data is then sent to the server using a secure communication protocol.

[1196] Receiving and storing data (server)

[1197] The server receives the pre-processed data sent from the terminal and stores it in a database, which contains all the information necessary for subsequent analysis. The stored data is then sent to the analysis means for further pre-processing.

[1198] Data preprocessing and feature extraction (server)

[1199] The server performs preprocessing on the stored data, such as normalization, filtering, and noise removal. After preprocessing, feature values ​​are extracted by the analysis means. Feature values ​​are numerical indicators that indicate the concentration and pattern of chemical components.

[1200] Scent prediction (server)

[1201] The extracted features are input into an artificial intelligence means, which uses a neural network to predict a specific aroma expression from the features. For example, an abstract aroma expression such as "citrus, slightly sweet and sour" can be obtained.

[1202] Emotion recognition and expression regulation (terminal)

[1203] When a user approaches the device, the emotion engine is activated. The emotion engine analyzes the user's facial expression and voice data to recognize their emotion. Based on the analysis results, the server adjusts the predicted scent expression. For example, if the user is relaxed, the expression will be modified to something like "citrus with a relaxing effect."

[1204] Sending and displaying adjustment results (terminal)

[1205] The adjusted results are sent from the server to the device using a secure communication protocol. The device receives them and displays them to the user. The display format is a specific description such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[1206] Specific examples

[1207] For example, when a user brings an orange peel close to a scent sensor, the system operates as follows: The device activates the scent sensor, acquires data, and performs preprocessing. The preprocessed data is sent to the server using the HTTPS protocol. The server saves the received data, performs further preprocessing, and extracts features. A neural network is used to predict the scent, such as "citrus, slightly sweet and sour." At the same time, if the emotion engine recognizes the user's emotion as "relaxed," the predicted result is adjusted to "citrus with a relaxing effect." This result is sent to the device and displayed to the user.

[1208] Example prompts for generative AI models

[1209] The following prompts can be used to have the generative AI model generate explanatory text:

[1210] Please explain the specific program processing flow of a system that combines an odor sensor and an emotion engine. Please break down the processing steps and provide a detailed description of each.

[1211] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1212] Processing Steps

[1213] Step 1: Acquiring odor data (device)

[1214] The device activates the odor sensor and captures the odor emanating from the object as digital data. The input is the object's odor, which is converted into digital data as output. This data contains numerical values ​​that indicate the concentration and pattern of specific chemical components. For example, when a user brings an orange peel close to the sensor, chemical component concentration data is obtained.

[1215] Step 2: Preprocessing the odor data (terminal)

[1216] The device performs preprocessing on the acquired digital data. The acquired digital data is the input, and the preprocessed data is the output. Preprocessing includes noise removal, data correction, normalization, etc. Specifically, operations are performed to filter out noise in the data and normalize the signal from the sensor.

[1217] Step 3: Sending odor data (device)

[1218] The terminal sends the preprocessed data to the server. The preprocessed data is the input, and the output is the data sent via a secure communication protocol (e.g., HTTPS). The data is encrypted before being sent, ensuring security.

[1219] Step 4: Receiving and storing data (server)

[1220] The server receives the pre-processed data sent from the terminal. The sent data is the input and is saved in the database as the output. The received data is stored in the server's database for later analysis.

[1221] Step 5: Data Preprocessing (Server)

[1222] The server performs further pre-processing on the received and stored data. It takes the stored data as input and the re-processed data as output. Pre-processing here includes noise filtering, normalization, and additional data correction. This processing further improves the accuracy and consistency of the data.

[1223] Step 6: Feature extraction (server)

[1224] The server extracts features from the preprocessed data. The preprocessed data is input, and features are obtained as output. Features are numerical indicators such as the concentration or pattern of chemical components. Specifically, data analysis algorithms are used to recognize the characteristics of chemical components, and that information is extracted as features.

[1225] Step 7: Scent prediction (server)

[1226] The server inputs the extracted features into an artificial intelligence model to predict the expression of the scent. The features are input, and the predicted scent expression is obtained as output. A neural network is used as the artificial intelligence model. For example, the model predicts a scent expression such as "citrus, slightly sweet and sour" from the input features.

[1227] Step 8: Emotion Recognition (Device)

[1228] The device activates an emotion engine and collects facial expression and voice data to recognize the user's emotions. The input is the user's facial expression and voice data, and the output is recognized emotion data. The emotion engine collects data using a camera and microphone and analyzes it to determine whether the user is relaxed or tense.

[1229] Step 9: Adjusting scent expression (server)

[1230] The server adjusts the predicted scent expression appropriately based on the recognized emotion data. The input is the predicted scent expression and emotion data, and the output is the adjusted scent expression. For example, if the user is recognized as relaxed, the scent expression is adjusted to "citrus with a relaxing effect."

[1231] Step 10: Sending the adjustment results (server)

[1232] The server sends the adjusted scent representation to the device. The input is the adjusted scent representation, and the output is data sent via a secure communication protocol. This data is also encrypted before transmission, so the information remains secure.

[1233] Step 11: Viewing the adjustment results (device)

[1234] The device displays the adjustment results received from the server to the user. The received data is input, and the output is the information displayed to the user. The display format is a specific description of the scent, such as "This scent has a relaxing citrus scent with a slightly sweet and sour taste."

[1235] (Application example 2)

[1236] 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."

[1237] Conventional odor analysis systems can quantitatively acquire and analyze odor data, but they cannot adjust the analysis results based on the user's emotions. This poses a problem in that users are unable to receive optimal suggestions based on their emotions when selecting a scent. Another issue with conventional systems is that they can only represent odors in a fixed way, which lacks flexibility.

[1238] 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.

[1239] In this invention, the server includes means for receiving odor data, means for extracting features from the received data, means for predicting an aroma expression from the features using artificial intelligence means, means for recognizing a user's emotion, means for adjusting the aroma expression based on the recognized emotion, and means for transmitting the predicted and adjusted aroma expression to the terminal, thereby making it possible to provide an aroma expression that is appropriately adjusted based on the user's emotion.

[1240] "Odor data" refers to the digital representation of the concentration and pattern of specific chemical components acquired by an odor sensor.

[1241] "Sensor means" refers to a technological means for acquiring odor data, including devices that sense specific chemical components.

[1242] The term "terminal means" refers to an electronic device for preprocessing acquired odor data and transmitting the data to the server means.

[1243] "Preprocessed odor data" refers to raw data obtained from a sensor means that has been appropriately filtered and denoised.

[1244] The "server means" is a central processing unit that stores the odor data received from the terminal means, extracts features, and performs analysis using artificial intelligence means.

[1245] "Features" are information that serves as important attributes or indicators of the analysis target, extracted from preprocessed odor data.

[1246] "Artificial intelligence means" refers to a technical means that uses machine learning models such as neural networks to predict the expression of a specific fragrance from features.

[1247] "Emotion recognition means" refers to a technical means for analyzing a user's facial expression data and voice data and estimating the user's emotions.

[1248] The "means for adjusting the expression of a scent" refers to a technical means for appropriately correcting and adjusting the predicted expression of a scent based on the user's emotions recognized by the emotion recognition means.

[1249] "Scent expression" refers to the characteristics and impressions of a scent that are verbalized based on scent data acquired by a scent sensor.

[1250] The present invention combines an emotion engine with a system that quantifies odor data and verbalizes specific scents. An embodiment of this system will be described in detail below.

[1251] System Configuration

[1252] The system consists of an odor sensor, a terminal, a server, an artificial intelligence model, and an emotion engine.

[1253] Hardware and Software

[1254] Odor sensor: A device that detects specific chemical components and is used to obtain odor data.

[1255] Terminal: A device such as a smartphone or smart glasses that preprocesses the odor data and transmits it to the server. The terminal also has a camera and microphone for emotion recognition.

[1256] Server: Located on the cloud, it receives odor data sent from the device and extracts features from the preprocessed data.

[1257] Artificial intelligence model: A technology that uses neural networks to predict the expression of a scent from features.

[1258] Emotion engine: A technology that analyzes the user's facial expressions and voice to recognize emotions.

[1259] Program processing overview

[1260] 1. Acquisition and preprocessing of odor data

[1261] The device acquires odor data from the target object using an odor sensor. The acquired data is preprocessed on the device to remove noise and perform filtering. The preprocessed data is then sent to the server using a secure communication protocol (e.g., HTTPS).

[1262] 2. Data reception and feature extraction

[1263] The server receives the preprocessed data sent from the device. The received data is stored in a database and then goes on to the next processing step. The server extracts features from this data and inputs them into an artificial intelligence model.

[1264] 3. Fragrance Expression Prediction

[1265] Using an artificial intelligence model (neural network), a specific aroma expression is predicted from the features. For example, a predicted result such as "citrus, slightly sweet and sour" is generated.

[1266] 4. Emotional recognition and scent regulation

[1267] The emotion engine runs on the device and analyzes the user's facial expression data (e.g., using the camera in smart glasses) and voice data to recognize emotions. Based on the recognized emotion, the server adjusts the prediction result and generates a more appropriate scent description. For example, it adjusts the description to "citrus with a relaxing effect."

[1268] 5. Sending and displaying the expression results

[1269] The final adjusted scent representation is sent from the server to the device, which receives the result and displays it to the user.

[1270] Usage example

[1271] For example, let's consider a specific example where a user tries out perfume in a physical store. When the user brings a perfume bottle close to an odor sensor, the sensor captures odor data. The captured data is preprocessed on the device and sent to the server. The server extracts features from the data and predicts the scent expression using an artificial intelligence model. The emotion engine then recognizes the user's relaxed facial expression and adjusts the expression to "citrus with a relaxing effect." This is then sent to the device and displayed to the user, allowing them to choose a scent that suits their condition.

[1272] Prompt Sentence Examples

[1273] "When a user chooses a perfume in a physical store, acquire scent data using an odor sensor, and adjust the scent representation predicted by an AI model using smart glasses based on emotion recognition data to generate an application that suggests the appropriate scent."

[1274] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1275] Step 1:

[1276] The device acquires odor data using an odor sensor. The sensor detects odors emanating from an object and sends the data in digital format to the device. The input is the odor of the object, and the output is digital odor data. Specifically, the odor sensor activates and detects the odor components of the surrounding air and the object.

[1277] Step 2:

[1278] The device preprocesses the acquired odor data, removing noise and filtering to improve data accuracy. The input is raw data obtained from the odor sensor, and the output is preprocessed data. Specifically, the device's preprocessing algorithm normalizes the data and removes unnecessary noise.

[1279] Step 3:

[1280] The device sends the preprocessed odor data to the server. The data is transferred securely using a secure communication protocol (e.g., HTTPS). The input is the preprocessed data, and the output is a notification to the server that transmission has been completed. Specifically, the device establishes an Internet connection and uploads the data to the server.

[1281] Step 4:

[1282] The server receives odor data sent from the device and stores it in a database. The input is the preprocessed data sent from the device, and the output is a notification that the data has been stored in the database. Specifically, the server converts the received data into a specific format and stores it in the database.

[1283] Step 5:

[1284] The server extracts features from the data stored in the database. These features contain the information necessary for analysis. The input is preprocessed data, and the output is the extracted features. Specifically, the server uses machine learning algorithms to extract important attributes and patterns.

[1285] Step 6:

[1286] The server inputs the extracted features into an artificial intelligence model (neural network) to predict the expression of the scent. The input is the features, and the output is the predicted expression of the scent. Specifically, the AI ​​model on the server analyzes the data and verbalizes the scent.

[1287] Step 7:

[1288] The device recognizes the user's emotions using emotion recognition means. It uses a camera and microphone to collect emotion data from the user's facial expressions and voice. The input is the user's facial expression data and voice data, and the output is the recognized emotion. Specifically, the device performs emotion analysis in real time to identify the emotion.

[1289] Step 8:

[1290] The server adjusts the predicted scent expression based on the recognized emotion. The input is the predicted scent expression and the recognized emotion, and the output is the adjusted scent expression. Specifically, the server uses the emotion engine to modify the scent expression.

[1291] Step 9:

[1292] The server sends the adjusted scent representation to the terminal. The input is the adjusted scent representation, and the output is a notification of completion of transmission to the terminal. Specifically, the server packs the data into packets and sends them to the terminal via the network.

[1293] Step 10:

[1294] The device receives the scent description sent from the server and displays it to the user. The input is the adjusted scent description, and the output is a description of the displayed scent. Specifically, the device displays the scent information in text format on the display.

[1295] 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.

[1296] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1297] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1298] 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.

[1299] 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.

[1300] 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.

[1301] 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).

[1302] 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.

[1303] 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."

[1304] 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.

[1305] 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).

[1306] 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.

[1307] 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.

[1308] 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.

[1309] 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.

[1310] 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.

[1311] 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.

[1312] 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.

[1313] 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.

[1314] 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.

[1315] 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.

[1316] The following is further disclosed regarding the above embodiment.

[1317] (Claim 1)

[1318] sensor means for acquiring odor data;

[1319] terminal means for preprocessing odor data from said sensor means;

[1320] a server means for receiving the preprocessed odor data transmitted from the terminal means;

[1321] means for extracting features from the received data;

[1322] an artificial intelligence means for predicting the expression of a specific scent from the extracted feature quantity;

[1323] means for transmitting the predicted scent representation to a terminal means;

[1324] a means for displaying the transmitted scent description to a user in the terminal means;

[1325] A system including:

[1326] (Claim 2)

[1327] 2. The system according to claim 1, wherein the artificial intelligence means predicts the expression of a scent from features using a neural network.

[1328] (Claim 3)

[1329] 2. The system according to claim 1, wherein the terminal means transmits the odor data obtained from the sensor means to the server means using a secure communication protocol.

[1330] "Example 1"

[1331] (Claim 1)

[1332] sensor means for acquiring odor data;

[1333] terminal means for preprocessing odor data from said sensor means;

[1334] a server means for receiving the preprocessed odor data transmitted from the terminal means;

[1335] means for additionally pre-processing, filtering and normalizing the received data;

[1336] means for extracting features from the additionally preprocessed data;

[1337] means for converting the extracted feature quantity into a vector format;

[1338] an artificial intelligence means that receives the feature quantity in vector format as an input;

[1339] means for the artificial intelligence means to predict a particular scent expression;

[1340] means for transmitting the predicted scent representation to a terminal means;

[1341] a means for displaying the transmitted scent description to a user in the terminal means;

[1342] A system including:

[1343] (Claim 2)

[1344] 2. The system according to claim 1, wherein the artificial intelligence means predicts the expression of a scent from features using a neural network.

[1345] (Claim 3)

[1346] 2. The system according to claim 1, wherein the terminal means transmits the odor data obtained from the sensor means to the server means using a secure communication protocol.

[1347] "Application Example 1"

[1348] (Claim 1)

[1349] sensor means for acquiring odor data;

[1350] terminal means for preprocessing odor data from said sensor means;

[1351] a server means for receiving the preprocessed odor data transmitted from the terminal means;

[1352] means for extracting features from the received data;

[1353] an artificial intelligence means for predicting the expression of a specific scent from the extracted feature quantity;

[1354] means for transmitting the predicted scent representation to a terminal means;

[1355] a means for displaying the transmitted scent description to a user in the terminal means;

[1356] a recommendation means for recommending related product information based on the scent description displayed to the user;

[1357] A system including:

[1358] (Claim 2)

[1359] 2. The system according to claim 1, wherein the artificial intelligence means predicts the expression of a scent from features using a neural network.

[1360] (Claim 3)

[1361] 2. The system according to claim 1, wherein the terminal means transmits the odor data obtained from the sensor means to the server means using a secure communication protocol.

[1362] "Example 2: Combining Emotion Engines"

[1363] (Claim 1)

[1364] sensor means for acquiring odor data;

[1365] processor means for preprocessing odor data from said sensor means;

[1366] a server means for receiving the preprocessed odor data transmitted from the processing device means;

[1367] analysis means for extracting features from the received data;

[1368] an artificial intelligence means for predicting the expression of a specific scent from the extracted feature quantity;

[1369] an emotion recognition means for adjusting the expression of the scent predicted by said artificial intelligence means;

[1370] means for transmitting said adjusted scent representation to said processing device means;

[1371] means for displaying the transmitted scent description to a user in said processing device means;

[1372] A system including:

[1373] (Claim 2)

[1374] 2. The system according to claim 1, wherein the artificial intelligence means predicts the expression of a scent from features using a neural network.

[1375] (Claim 3)

[1376] 10. The system of claim 1, wherein said processing device means transmits odor data obtained from said sensor means to said server means using a secure communication protocol.

[1377] (Claim 4)

[1378] 2. The system according to claim 1, wherein the emotion recognition means recognizes emotions by analyzing facial expression data or voice data of the user.

[1379] (Claim 5)

[1380] 2. The system according to claim 1, wherein the expression of the scent predicted by the artificial intelligence means is adjusted based on the user's emotion recognized by the emotion recognition means.

[1381] "Application example 2 when combining emotion engines"

[1382] (Claim 1)

[1383] sensor means for acquiring odor data;

[1384] terminal means for preprocessing odor data from said sensor means;

[1385] a server means for receiving the preprocessed odor data transmitted from the terminal means;

[1386] means for extracting features from the received data;

[1387] an artificial intelligence means for predicting the expression of a specific scent from the extracted feature quantity;

[1388] emotion recognition means for recognizing an emotion of a user;

[1389] means for adjusting the expression of the scent based on the emotion recognized by the emotion recognition means;

[1390] means for transmitting the predicted and adjusted scent representation to a terminal means;

[1391] a means for displaying the transmitted scent description to a user in the terminal means;

[1392] A system including:

[1393] (Claim 2)

[1394] 2. The system according to claim 1, wherein the artificial intelligence means predicts the expression of a scent from features using a neural network.

[1395] (Claim 3)

[1396] 2. The system according to claim 1, wherein the terminal means transmits the odor data obtained from the sensor means to the server means using a secure communication protocol. [Explanation of symbols]

[1397] 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. sensor means for acquiring odor data; terminal means for preprocessing odor data from said sensor means; a server means for receiving the preprocessed odor data transmitted from the terminal means; means for extracting features from the received data; an artificial intelligence means for predicting the expression of a specific scent from the extracted feature quantity; means for transmitting the predicted scent representation to a terminal means; a means for displaying the transmitted scent description to a user in the terminal means; A system including:

2. 2. The system according to claim 1, wherein the artificial intelligence means predicts the expression of a scent from the feature quantities using a neural network.

3. The system according to claim 1, wherein the terminal means transmits the odor data obtained from the sensor means to the server means using a secure communication protocol.

Images