System

Abstract

To provide a system for highly accurately and quickly determining the authenticity of a high-grade article by using a smartphone.SOLUTION: A system for determining authenticity of a luxury product, the system comprising: a photographing unit for a user to photograph the luxury product; a communication unit that transmits image data photographed by the photographing unit to a server; a preprocessing unit on the server side that receives the image data and performs preprocessing; a feature extraction unit that extracts a feature from the preprocessed image data; and a determination unit that determines authenticity of the luxury product based on the feature extracted by the feature extraction unit. A result display means for saving or sharing.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the luxury goods market, distinguishing between counterfeits and genuine goods is extremely difficult and requires specialized knowledge and experience. Furthermore, determining authenticity often takes time and money, creating a demand for fast and reliable authentication. In particular, there is a strong need for objective evaluation of quality and condition in the secondhand goods market. To address these challenges, the present invention aims to provide technology for quickly and accurately determining the authenticity of luxury goods using a smartphone. [Means for solving the problem]

[0005] The present invention is a system for determining the authenticity of luxury goods, and includes the following means.

[0006] The system includes a photographing means for a user to photograph luxury goods, a communication means for transmitting image data photographed by the photographing means to a server, a server-side preprocessing means for receiving and preprocessing the image data, a feature extraction means for extracting features from the preprocessed image data, a determination means for determining the authenticity of the luxury goods based on the features extracted by the feature extraction means, a result transmission means for generating a determination result and a detailed report and transmitting them to the user's terminal, and a result display means for displaying the result on the user's terminal and saving or sharing it.

[0007] This allows users to easily verify the authenticity of luxury goods using their smartphones, improving trust in the luxury goods market and providing peace of mind to consumers.

[0008] "Photographing means" refers to the device or its functions that a user uses to photograph a luxury item.

[0009] "Communication means" refers to an Internet connection or its functions for transmitting captured image data to a server.

[0010] The "preprocessing means" is a function for appropriately processing image data received on the server side before analysis.

[0011] "Feature extraction means" refers to algorithms and functions for extracting important features from pre-processed image data.

[0012] The "determination means" refers to an AI model or its functions for determining the authenticity of luxury goods based on the features extracted by the feature extraction means.

[0013] The "result transmission means" is a function for generating a detailed report of the judgment results and transmitting them to the user's terminal.

[0014] The "result display means" is a function for displaying the judgment results on the user's terminal and saving or sharing the report. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0037] This invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The user uses their smartphone to take a picture of the luxury goods and send it to a server. The server analyzes the received image data and uses AI technology to determine the authenticity. The results are returned to the user and displayed on the smartphone.

[0038] System configuration

[0039] The system is broadly composed of the following components:

[0040] 1. Shooting method (device)

[0041] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button.

[0042] 2. Communication method (terminal → server)

[0043] The captured image data is sent to a server via an Internet connection. Specifically, the image data is uploaded to the server as an HTTP request.

[0044] 3. Preprocessing means (server)

[0045] The server preprocesses the received image data, which includes normalizing, resizing, and removing noise from the image.

[0046] 4. Feature extraction method (server)

[0047] The server extracts features from the pre-processed image data using advanced image recognition algorithms such as convolutional neural networks (CNNs).

[0048] 5. Determination means (server)

[0049] Based on the feature vectors obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[0050] 6. Result transmission method (server → terminal)

[0051] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone via the Internet.

[0052] 7. Result display means (terminal)

[0053] The user's smartphone uses an app that displays the received judgment results, which are rated as "genuine" or "fake," and a detailed report can also be viewed.

[0054] Program processing

[0055] The system process proceeds as follows, with an example:

[0056] Example: Authentication of luxury brand bags

[0057] 1. User - Launches the camera app on the smartphone and takes a photo of a luxury brand bag. For example, the user takes a photo of the entire bag and a detailed image of the logo.

[0058] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[0059] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[0060] 4. Server - Extract features from the preprocessed image data. Using a convolutional neural network (CNN), features such as the position of the logo, the stitching of the bag, and the texture of the material are extracted.

[0061] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[0062] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone, including the evaluation result and reliability of each feature.

[0063] 7. Device - The received judgment result is displayed. The user can confirm the judgment result of "genuine" or "fake" through the app. For example, the report will show an evaluation such as "The logo position is accurate and matches the genuine article."

[0064] As described above, by using the system of the present invention, users can easily determine the authenticity of luxury goods, providing reliability and peace of mind in the luxury goods market.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] User - Launches the camera app on the smartphone and takes a picture of a luxury item (e.g., a bag). By pressing the capture button on the camera app, high-resolution image data is acquired.

[0068] Step 2:

[0069] Device - The captured image data is temporarily stored in the device's memory, and a preview of the stored image is displayed, prompting the user for confirmation.

[0070] Step 3:

[0071] Terminal - Prepares communication to send the confirmed image data to the server. Specifically, it compresses the image data appropriately and sends it to the server endpoint in the form of an HTTP request.

[0072] Step 4:

[0073] Server - Temporarily stores the received image data. The server prepares this data for passing to the analysis module.

[0074] Step 5:

[0075] Server - Initiates pre-processing of the image data, which includes denoising the image, color normalizing it, and resizing it to a size suitable for analysis.

[0076] Step 6:

[0077] Server - Extracts features from the pre-processed image data. Convolutional neural networks (CNNs) are used to detect specific features in the image (e.g., logo location, stitching patterns, material textures, etc.).

[0078] Step 7:

[0079] Server - Using the results of feature extraction, the AI ​​model determines the authenticity of the image. The AI ​​model has been trained with a large amount of data in advance, and calculates the probability that the image is genuine or fake based on the extracted features.

[0080] Step 8:

[0081] Server - Generates the assessment results and a detailed report detailing the assessment result and confidence level for each feature.

[0082] Step 9:

[0083] Server - Sends the generated verdicts and reports to the user's device, usually as an HTTP response, and notifies the user in real time.

[0084] Step 10:

[0085] Terminal - Analyzes the received judgment results and displays them on the user interface. Users can check the results and view detailed reports via a smartphone app.

[0086] Step 11:

[0087] Users can review the results and optionally save or share them with others, allowing them to quickly make the right decisions about the authenticity of luxury items.

[0088] Example 1

[0089] 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."

[0090] Counterfeits are rampant in the luxury goods market, and users are seeking a means to easily determine the authenticity of luxury goods. Conventional methods require advanced expertise and special equipment, making them difficult for average users to use. In addition, expert appraisals are time-consuming and expensive, and do not meet modern needs for immediacy. Therefore, there is a need for a system that can quickly and accurately determine the authenticity of luxury goods.

[0091] 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.

[0092] In this invention, the server includes a preprocessing means that receives image data and performs preprocessing such as noise removal, normalization, and resizing, a feature extraction means that extracts features from the preprocessed image data using a convolutional neural network, and a determination means that determines the authenticity of luxury goods using an AI model based on the feature vectors extracted by the feature extraction means. This enables users to easily verify the authenticity of luxury goods in real time.

[0093] "Photographing means" refers to a device or system that a user uses to capture images of luxury items, and includes a smartphone camera or dedicated photographic equipment.

[0094] The "communication means" refers to a mechanism or protocol for transmitting image data captured by the image capturing means to a server, and includes an internet connection, an HTTP request, and the like.

[0095] The "preprocessing means" is a function that performs processes such as noise removal, normalization, and resizing on the image data received by the server, and converts the image data into a format suitable for analysis.

[0096] The "feature extraction means" is a function for extracting useful features from preprocessed image data, and mainly uses algorithms such as convolutional neural networks (CNNs).

[0097] The "determination means" refers to a system or algorithm for determining the authenticity of luxury goods based on the feature vector obtained by the feature extraction means, and an AI model is mainly used.

[0098] The "result transmission means" is a function that allows the server to generate the authenticity determination result and a detailed report and transmit them to the user's terminal.

[0099] The "result display means" is a function that displays the authenticity determination results and detailed reports on the user's terminal, and provides information in a format that is easy for the user to understand.

[0100] An "AI model" is a mathematical model that uses machine learning and deep learning techniques to learn features from large amounts of data and perform highly accurate authenticity determinations.

[0101] A "convolutional neural network (CNN)" is a type of deep learning algorithm specialized in image recognition and feature extraction, which clarifies features by analyzing pixel data extracted from an input image across multiple layers.

[0102] This invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's device (e.g., a smartphone). The user takes a picture of the luxury goods using the device's camera and sends the image to a server. The server then preprocesses the received image data and uses AI technology to determine its authenticity. The results are returned to the user and displayed on the device.

[0103] Hardware and software used

[0104] 1. Device (smartphone)

[0105] Hardware: Smartphone (e.g. iPhone (registered trademark), ANDROID (registered trademark))

[0106] Software: Camera app (e.g. iOS camera app, Google Camera)

[0107] 2. Means of communication

[0108] Network: Internet connection (e.g. Wi-Fi, LTE)

[0109] Communication library: HTTP communication library (e.g., OkHttp, Retrofit)

[0110] 3. Server

[0111] Hardware: Cloud servers (e.g., AWS (registered trademark) EC2 instances, Google Cloud Platform GPU instances)

[0112] software:

[0113] Preprocessing library: Image processing library (e.g. OpenCV, Pillow)

[0114] AI / Deep Learning Framework: Deep Learning Framework (e.g., TENSORFLOW (registered trademark), PyTorch)

[0115] System action

[0116] The system works as follows:

[0117] 1. User operation: The user launches the camera app on their smartphone and takes a picture of a luxury item, for example, taking a full picture of the bag and a detailed shot of the logo.

[0118] Example: A user takes a photo of the logo of a luxury brand bag with their smartphone.

[0119] 2. Image transmission from the device to the server: The device compresses the captured image data and sends it to the server as an HTTP request.

[0120] Example: An Android smartphone takes a picture, compresses it into JPEG format, and sends it to a server using an HTTP POST request.

[0121] 3. Preprocessing on the server: The server performs preprocessing on the received image data, such as noise removal, normalization, and resizing.

[0122] Example: A Python script on a server preprocesses image data using the Pillow library.

[0123] 4. Feature extraction on the server: Features are extracted from the preprocessed image data using a convolutional neural network (CNN).

[0124] Example: Using TensorFlow, a CNN model extracts features from the logo on a bag.

[0125] 5. Authentication on the server: Based on the feature vectors, the AI ​​model determines the authenticity of luxury goods, for example, by checking the placement of logos and stitching patterns.

[0126] Example: A PyTorch-based ResNet model analyzes logo placement and stitching patterns to determine authenticity.

[0127] 6. Sending results from the server to the device: The judgment results and a detailed report are generated and sent to the user's device as an HTTP response.

[0128] Example: As a result of the judgment, a report is generated stating that "The logo position matches precisely and the stitching matches that of the genuine product, so it has been judged to be genuine," and this is sent to the terminal in JSON format.

[0129] 7. Displaying results on the terminal: Displaying the received judgment results and providing a detailed report to the user.

[0130] Example: The dedicated verification app displays the results, stating that "the logo position is accurate and matches the genuine article."

[0131] Examples and prompts

[0132] Example: Authentication of luxury brand bags

[0133] The user launches the smartphone's camera app and takes a photo of the bag's overall appearance and the logo. The smartphone then compresses the image data and sends it as an HTTP request to the server. The server preprocesses the received image data and uses CNN to extract features such as the logo and stitching. Based on these features, the AI ​​model determines whether the bag is authentic or not, and generates and returns the results and a detailed report to the user. Finally, the smartphone displays the results, allowing the user to view the "genuine" or "fake" rating and detailed report.

[0134] Prompt Sentence Examples

[0135] "To determine the authenticity of a luxury brand bag, you take a photo of the entire bag and the logo with your smartphone and send the image to our server. The server preprocesses the image, extracts features using CNN, and then uses an AI model to make a determination. You can then check the determination results and a detailed report on your smartphone."

[0136] The present invention enables users to easily and quickly verify the authenticity of luxury goods, providing reliability and peace of mind in the luxury goods market.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1:

[0139] User-generated photos

[0140] A user starts the camera app on their smartphone and takes a picture of a luxury item. For example, the user takes a picture of the entire luxury brand bag and the logo. The input at this stage is the start of the camera and the selection of the subject, and the output is the captured image data.

[0141] Step 2:

[0142] Sending images from the device to the server

[0143] The device compresses the captured image data and sends it as an HTTP request to a server via the Internet. The input is the captured image data, and the output is the compressed image data and its HTTP request. Specifically, the device compresses the image into JPEG format and sends it using an HTTP POST request.

[0144] Step 3:

[0145] Preprocessing on the server

[0146] The server reads the received image data and performs preprocessing such as noise removal, normalization, and resizing. The input of this step is compressed image data, and the output is preprocessed image data. Specifically, a Python script on the server uses the Pillow library to resize the image appropriately and remove noise.

[0147] Step 4:

[0148] Feature extraction on the server

[0149] The server extracts features from the preprocessed image data using a convolutional neural network (CNN). The input of this step is the preprocessed image data, and the output is a feature vector. For example, using TensorFlow, a CNN model extracts features such as the logo and stitching of a bag.

[0150] Step 5:

[0151] Authentication on the server

[0152] The server uses an AI model to determine the authenticity of luxury goods based on the extracted feature vectors. The input for this step is the feature vector, and the output is the authenticity determination result. Specifically, a PyTorch-based ResNet model analyzes the position of the logo and the stitching pattern to determine authenticity.

[0153] Step 6:

[0154] Sending results from the server to the device

[0155] The server generates the judgment result and a detailed report and sends them to the user's device as an HTTP response. The input to this step is the authenticity judgment result, and the output is a detailed report and its HTTP response. Specifically, the judgment result is converted to JSON format and sent.

[0156] Step 7:

[0157] Displaying results on your device

[0158] The device displays the received judgment result and provides it to the user. The input of this step is the detailed report received from the server, and the output is the judgment result displayed to the user. Specifically, the dedicated verification app displays the judgment result and a detailed report, informing the user that "the logo position is accurate and matches the genuine article."

[0159] (Application example 1)

[0160] 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."

[0161] Conventional systems for determining the authenticity of luxury goods are primarily designed for online use, and have the problem of difficulty in quickly and accurately determining authenticity in physical stores. In particular, there is a need to be able to instantly determine the authenticity of luxury goods when they are being explained to customers in physical stores, and to provide customers with highly reliable information. In addition, from the perspective of the devices used, there is a need to improve the work efficiency of store clerks by utilizing smart glasses and head-mounted displays.

[0162] 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.

[0163] In this invention, the server includes a photographing means for a user to photograph luxury goods, a communication means for transmitting image data photographed by the photographing means to the server, a server-side preprocessing means for receiving and preprocessing the image data, a feature extraction means for extracting features from the preprocessed image data, a determination means for determining the authenticity of the luxury goods based on the features extracted by the feature extraction means, a result transmission means for generating the determination results and a detailed report and transmitting them to the user's terminal, a result display means for displaying the results on the user's terminal and saving or sharing them, and a means for photographing the luxury goods and displaying the determination results via smart glasses or a head-mounted display in a physical store, thereby enabling fast and accurate authenticity determination in a physical store.

[0164] "Luxury goods" generally refer to items that are expensive, rare, and made using high-quality materials and sophisticated craftsmanship.

[0165] "Authenticity" refers to determining whether something is genuine or fake.

[0166] A "system" is a collective term for multiple components or means combined to achieve a specific function or purpose.

[0167] "Photographing means" refers to a camera or other photographing device that a user uses to photograph luxury items.

[0168] "Communication means" refers to an internet connection or other data transmission means for sending captured image data to a server.

[0169] The "preprocessing means" refers to a processing means on the server that performs preprocessing such as noise removal, normalization, and resizing on the received image data.

[0170] "Feature extraction means" refers to an algorithm or device for extracting product-specific features from pre-processed image data.

[0171] "Determination means" refers to an AI model or algorithm for determining the authenticity of luxury goods based on the features extracted by the feature extraction means.

[0172] "Result transmission means" refers to a communication means for generating a detailed report of the judgment results and transmitting them to the user's terminal.

[0173] "Result display means" refers to the user interface or software for displaying results on the user's terminal and saving or sharing the results.

[0174] "Smart glasses" refers to a wearable device that has display and camera functions and can send and receive data when worn by the user.

[0175] A "head-mounted display" refers to a display device that provides visual information when worn by a user on the head.

[0176] "Internet connection" refers to a network connection for uploading image data to a server via a communication means.

[0177] "Determination result" refers to the result of the AI ​​model determining the authenticity of a luxury item.

[0178] A "detailed report" refers to a report that details the evaluation results and reliability of each feature based on the judgment results.

[0179] System configuration

[0180] The system of the present invention is designed to determine the authenticity of luxury goods and can be used in brick-and-mortar stores. The system consists of the following components:

[0181] 1. Imaging method (smart glasses or head-mounted display)

[0182] The user wears smart glasses or a head-mounted display and takes a photo of a luxury item. The device has a built-in camera, allowing the product to be photographed naturally from the user's point of view.

[0183] 2. Communication method (Wi-Fi, etc.)

[0184] The captured image data is sent to a server via Wi-Fi, using an internet connection as the communication method, and the data is compressed before being sent.

[0185] 3. Preprocessing method (server side)

[0186] The server preprocesses the received image data, which includes normalizing, resizing, and removing noise, converting the image into a suitable format for subsequent analysis.

[0187] 4. Feature extraction method (server side)

[0188] The server extracts features from the preprocessed image data using a convolutional neural network (CNN) to extract product-specific features (e.g., logo position, stitching pattern, material texture).

[0189] 5. Judgment method (server side)

[0190] Based on the features obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[0191] 6. Result transmission method (server → terminal)

[0192] The server generates a detailed report with the results and transmits it to the user's smart glasses or head-mounted display via Wi-Fi.

[0193] 7. Display of results (smart glasses or head-mounted display)

[0194] The user's device displays the received judgment results, which are instantly displayed as "genuine" or "fake," and a detailed report can also be viewed.

[0195] Specific processing of the program

[0196] As an example of a physical store, we will demonstrate how the system works in a store that sells luxury brand watches. A salesperson wears smart glasses or a head-mounted display and takes a photo of the watch case or dial. The image data is sent to a server via Wi-Fi, where it is normalized and resized by pre-processing. Features are then extracted using a convolutional neural network (CNN), and an AI model makes a judgment. The judgment result is then sent back to the device via Wi-Fi, where the salesperson can check it on the spot.

[0197] The required hardware includes smart glasses (e.g., Google Glass®) or a head-mounted display (e.g., Microsoft® HoloLens®), and the server side requires a high-performance GPU. The software includes machine learning libraries such as Python and TensorFlow.

[0198] Specific examples

[0199] For example, in a store selling luxury brand watches, a salesperson uses smart glasses to take a photo of the watch case or dial. The image data is sent to a server via Wi-Fi and preprocessed. Features are then extracted using CNN, and an AI model determines its authenticity. The result, "This watch is genuine," is displayed on the smart glasses.

[0200] Prompt Sentence Examples

[0201] Prompt: "This image is of a luxury brand watch case. Use a convolutional neural network to determine whether it is authentic. Consider the shape of the case, the placement of the numerals on the dial, and the texture of the material as characteristics."

[0202] In this way, by using the system of the present invention, it becomes possible to quickly and accurately determine the authenticity of luxury goods even in physical stores, thereby realizing the provision of highly reliable information to customers.

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] The user wears smart glasses or a head-mounted display and takes pictures of luxury items.

[0206] Input: Images of luxury items captured through a camera built into smart glasses or a head-mounted display

[0207] Output: Image data of the luxury item photographed

[0208] Action: The user activates the camera and takes a picture of a specific part (such as the case or dial) of a luxury item (e.g., a luxury brand watch).

[0209] Step 2:

[0210] The device sends the captured image data to a server via Wi-Fi.

[0211] Input: Image data of the luxury item photographed

[0212] Output: Image data sent to the server

[0213] How it works: The communication module inside the device compresses the image data and uploads it to the server as an HTTP request.

[0214] Step 3:

[0215] The server pre-processes the received image data.

[0216] Input: Image data sent to the server

[0217] Output: Preprocessed image data (normalized, resized, and denoised)

[0218] How it works: A program on the server normalizes the image data, resizes it to a consistent size, and denoises it, using an image processing library such as OpenCV.

[0219] Step 4:

[0220] The server extracts features from the preprocessed image data.

[0221] Input: Preprocessed image data

[0222] Output: Feature vector

[0223] How it works: It uses a server-based convolutional neural network (CNN) to extract features from images, using machine learning frameworks such as TensorFlow and Keras.

[0224] Step 5:

[0225] The server determines the authenticity of the luxury item based on the features obtained by the feature extraction means.

[0226] Input: feature vector

[0227] Output: Verification result (e.g. "Genuine", "Fake")

[0228] How it works: The AI ​​model analyzes feature vectors and determines authenticity based on a pre-trained dataset.

[0229] Step 6:

[0230] The server generates a detailed report with the results of the assessment and sends it to the user's terminal.

[0231] Input: Judgment results, detailed report elements (e.g., evaluation of logo position and material texture)

[0232] Output: Verification results and detailed report

[0233] How it works: The server generates a text report with the results and a detailed report, which it then sends back to the user's device via Wi-Fi.

[0234] Step 7:

[0235] The terminal displays the received judgment result.

[0236] Input: Verification results and detailed report

[0237] Output: Judgment results and detailed reports displayed on smart glasses or a head-mounted display

[0238] How it works: Using the device's display function, the result is displayed as "genuine" or "fake," and a detailed report can also be viewed.

[0239] 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.

[0240] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0241] The present invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The present invention also combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[0242] System configuration

[0243] The system is broadly composed of the following components:

[0244] 1. Shooting method (device)

[0245] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button.

[0246] 2. Communication method (terminal → server)

[0247] The captured image data is sent to a server over an internet connection, specifically as an HTTP request to a server endpoint.

[0248] 3. Preprocessing means (server)

[0249] The server preprocesses the received image data, which includes removing noise from the image, normalizing the color, and resizing it to a size suitable for analysis.

[0250] 4. Feature extraction method (server)

[0251] The server extracts features from the pre-processed image data using advanced image recognition algorithms such as convolutional neural networks (CNNs).

[0252] 5. Determination means (server)

[0253] Based on the feature vectors obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[0254] 6. Result transmission method (server → terminal)

[0255] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone via the Internet.

[0256] 7. Result display means (terminal)

[0257] The user's smartphone uses an app that displays the received judgment results. The result is a rating of "genuine" or "fake," and a detailed report can be viewed. The app also incorporates an emotion engine that recognizes the user's emotions.

[0258] 8. Emotion Engine (Terminal)

[0259] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[0260] 9. Feedback means (terminal)

[0261] The emotion engine recognizes the user's emotions and then provides feedback based on those emotions. For example, if the user is shocked that the product is identified as fake, it will display a message of comfort and the next steps to take (e.g., guiding them through the return process).

[0262] Program processing

[0263] The system process proceeds as follows, with an example:

[0264] Example: Authentication of luxury brand bags and user emotion recognition

[0265] 1. User - Launches the camera app on the smartphone and takes a photo of a luxury brand bag. For example, the user takes a photo of the entire bag and a detailed image of the logo.

[0266] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[0267] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[0268] 4. Server - Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[0269] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[0270] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone. The report details the evaluation result and its reliability for each feature.

[0271] 7. Device - Displays the received judgment result. The user can check the judgment result of "genuine" or "fake" through the app. A detailed report can also be viewed.

[0272] 8. Device - While the user is checking the result, the emotion engine analyzes the user's facial expressions and voice. For example, if the user is surprised, the camera captures and analyzes their facial expression.

[0273] 9. Device - Feedback is generated based on emotions. For example, if the user is surprised, the message "You seem surprised. Don't worry, we'll provide you with more information."

[0274] 10. User - Review the results and feedback and decide on the next action. For example, if the bag is determined to be fake, they will be provided with information to proceed with the return process.

[0275] In this way, the present invention allows users to easily determine the authenticity of luxury items, and further improves the user experience by providing feedback according to the user's emotional state.

[0276] The processing flow will be explained below.

[0277] Step 1:

[0278] User - Launches the camera app on the smartphone and takes a picture of a luxury item (e.g., a designer bag). By pressing the capture button on the camera app, high-resolution image data is acquired.

[0279] Step 2:

[0280] Device - The acquired image data is temporarily stored in the device's memory, and a preview of the stored image is displayed, prompting the user for confirmation.

[0281] Step 3:

[0282] Device - Begin preparing to send the verified image data to the server. The image data is appropriately compressed and sent to the server endpoint in the form of an HTTP request. Specifically, the request is generated with the following information:

[0283] User ID

[0284] Image data

[0285] timestamp

[0286] Step 4:

[0287] Server - Receives and temporarily stores the image data sent to it. The server prepares the data for passing to the analysis module and checks the integrity of the data.

[0288] Step 5:

[0289] Server - Initiates preprocessing of the image data. This preprocessing includes denoising the image, color normalizing it, and resizing it to a size suitable for analysis. Specific tasks include:

[0290] Normalizing pixel values

[0291] Noise removal using a Gaussian filter

[0292] Resize

[0293] Step 6:

[0294] Server - Extracts features from the pre-processed image data. Convolutional neural networks (CNNs) are used to detect specific features in the image (e.g., logo location, stitching patterns, material textures, etc.).

[0295] Step 7:

[0296] Server - Using the results of feature extraction, the AI ​​model determines the authenticity of the image. The AI ​​model has been trained with a large amount of data in advance, and calculates the probability of whether an image is genuine or fake based on the extracted feature vector. The specific evaluation is as follows:

[0297] Does the logo shape and placement match the genuine product?

[0298] Do the stitch patterns match?

[0299] Is the texture of the material the same?

[0300] Step 8:

[0301] Server - Generates the assessment results and a detailed report detailing the assessment results and confidence levels for each feature, as well as the analysis of the images used to make the assessment.

[0302] Step 9:

[0303] Server - Sends generated verdicts and reports to the user's device, usually as HTTP responses, notifying the user in real time.

[0304] Step 10:

[0305] Device - Analyzes the received results and displays them in the user interface. The app displays a summary of the results and a detailed report for easy review by the user. Specifically, it displays the following information:

[0306] Verification result (genuine / fake)

[0307] Detailed characterization

[0308] Report download link

[0309] Step 11:

[0310] On your device - While you are checking your results, the app will use your smartphone's camera and microphone to analyze your facial expressions and voice with its emotion engine. This includes:

[0311] Face detection and facial expression analysis

[0312] Voice tone and pitch analysis

[0313] Step 12:

[0314] Terminal - Based on the analysis results of the emotion engine, identify the user's emotional state (e.g., joy, surprise, sadness, etc.) and generate a feedback message according to the emotional state.

[0315] Step 13:

[0316] Terminal - Display feedback to the user based on their emotions. For example, if the user is surprised, display "I see you're surprised. We'll provide you with more information, so don't worry." If the user is shocked, provide a comforting message or instructions on what to do next (e.g., instructions on how to return the product).

[0317] Step 14:

[0318] User - Review the results and feedback and decide on the next action. For example, if the bag is determined to be counterfeit, view information to proceed with the return process.

[0319] Example 2

[0320] 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."

[0321] Determining the authenticity of luxury goods requires expert knowledge and skills, making it difficult for users without advanced expertise. Furthermore, appropriately responding to the user's emotional reaction when receiving the results is important for improving the user experience. Given this situation, the present invention aims to provide a system that easily determines the authenticity of luxury goods and provides feedback based on the user's emotional state.

[0322] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0323] In this invention, the server includes a means for receiving and preprocessing image data, a means for extracting features from the preprocessed image data, and a means for determining the authenticity of an item based on the extracted features, thereby enabling highly accurate authentication and appropriate feedback based on the user's emotions.

[0324] "Photographing means" refers to a smartphone camera or other imaging device that a user uses to photograph an item.

[0325] The "communication means" refers to a means for transmitting image data acquired by the photographing means to a server via an Internet connection, and specifically, uses a protocol such as an HTTP request.

[0326] "Preprocessing means" refers to the process of performing noise removal, color normalization, resizing, etc. on the image data received on the server side and converting it into a format suitable for analysis.

[0327] "Feature extraction means" refers to algorithms and hardware for extracting article features (e.g., logo location, stitching pattern, material texture, etc.) from pre-processed image data.

[0328] "Determination means" refers to an AI model or algorithm that determines the authenticity of an item based on the features obtained by the feature extraction means.

[0329] The "result transmission means" is a means for generating the judgment results and a detailed report and transmitting them to the user's terminal, and utilizes an internet connection.

[0330] "Result display means" refers to an application or interface for displaying the assessment results and detailed reports on the user's device and saving or sharing them.

[0331] "Emotion recognition means" refers to hardware and software for identifying the emotional state of a user by analyzing the facial expression, voice, etc. of the user checking the judgment result.

[0332] The "feedback means" refers to software for generating appropriate feedback based on the emotion recognized by the emotion recognition means and providing it to the user.

[0333] The present invention is a system for determining the authenticity of luxury goods. This system operates primarily on the user's smartphone and combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[0334] System configuration

[0335] The system is broadly composed of the following components:

[0336] 1. Shooting method (device)

[0337] The user takes a photo of the luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button. Specifically, a high-definition camera or a standard camera on the smartphone can be used.

[0338] 2. Communication method (terminal → server)

[0339] The captured image data is sent to a server via an internet connection. Specifically, the image data is sent as an HTTP request to the server endpoint. HTTPS is the recommended communication protocol.

[0340] 3. Preprocessing means (server)

[0341] The server preprocesses the received image data, which includes removing noise, color normalizing, and resizing the image to a size suitable for analysis. Specifically, median filtering and histogram equalization are applied.

[0342] 4. Feature extraction method (server)

[0343] The server extracts features from the pre-processed image data using a sophisticated image recognition algorithm called a convolutional neural network (CNN), such as the location of logos, stitching patterns, and material textures.

[0344] 5. Determination means (server)

[0345] Based on the feature vectors obtained by the feature extraction method, an AI model determines the authenticity of luxury goods. This AI model has been trained on a large dataset in advance, enabling highly accurate judgment. For example, it evaluates whether the luxury brand logo or stitching pattern matches that of the genuine product.

[0346] 6. Result transmission method (server → terminal)

[0347] The server generates a detailed report of the results and sends it to the user's smartphone via the Internet. The report details the evaluation results and their reliability for each feature.

[0348] 7. Result display means (terminal)

[0349] The user's smartphone uses an app that displays the received judgment results, which are rated as "genuine" or "fake," and a detailed report can also be viewed.

[0350] 8. Emotion recognition means (terminal)

[0351] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[0352] 9. Feedback means (terminal)

[0353] The emotion engine recognizes the user's emotions and then provides feedback based on those emotions. For example, if the user is shocked that the product is identified as fake, it will display a message of comfort and the next steps to take (e.g., guiding them through the return process).

[0354] Specific examples

[0355] Example: Authentication of luxury brand bags and user emotion recognition

[0356] 1. User - Launches the smartphone camera app and takes a photo of a luxury brand bag, taking a full view of the bag and a detailed view of the logo.

[0357] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[0358] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[0359] 4. Server - Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[0360] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[0361] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone. The report details the evaluation result and its reliability for each feature.

[0362] 7. Device - The received judgment results are displayed in the app, and the user can check the "genuine" or "fake" judgment results and report.

[0363] 8. Device - While the user is checking the result, the emotion engine analyzes the user's facial expressions and voice. For example, if the user is surprised, the camera captures and analyzes their facial expression.

[0364] 9. Device - Generate feedback based on emotions. For example, if the user is surprised, display a message like "I see you're surprised. Don't worry, we'll provide you with more information."

[0365] Examples of typical prompt statements

[0366] "Explain the outline of a system that uses AI to determine the authenticity of a luxury brand bag using an image taken by the user, and then describe the entire process of recognizing the user's emotions and providing feedback."

[0367] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0368] Step 1:

[0369] The user launches the camera app on their smartphone and takes a picture of the luxury item.

[0370] Input: Item (e.g. luxury brand bag)

[0371] Output: Captured image data (high-resolution image)

[0372] What happens: The user points the camera at a luxury item, focuses it, and takes a photo in a well-lit area, capturing both the overall image of the bag and the details (logo, stitching, etc.).

[0373] Step 2:

[0374] The terminal transmits the captured image data to a server via the Internet.

[0375] Input: Captured image data

[0376] Output: Image data sent as an HTTP request

[0377] Specific behavior: The device compresses and encodes the image data, generates an HTTP POST request, and sends it to the server endpoint.

[0378] Step 3:

[0379] The server pre-processes the received image data.

[0380] Input: Received image data

[0381] Output: Preprocessed image data

[0382] Specific operation: The server performs noise removal (median filtering) on ​​the received image data, then performs color normalization (histogram equalization), and resizes it to a size suitable for analysis.

[0383] Step 4:

[0384] The server extracts features from the preprocessed image data.

[0385] Input: Preprocessed image data

[0386] Output: feature vector

[0387] How it works: The server uses a convolutional neural network (CNN) to extract important features in the image (such as the position of the logo, the stitching pattern, and the texture of the material) and represents these features as a feature vector.

[0388] Step 5:

[0389] The server uses an AI model to determine authenticity based on the feature vector obtained by the feature extraction means.

[0390] Input: feature vector

[0391] Output: Verification result (e.g. "Genuine" or "Fake")

[0392] How it works: The server inputs the feature vector into a trained AI model, which then makes a judgment, such as whether the logo position matches that of the genuine product or whether the stitching pattern matches that of the genuine product.

[0393] Step 6:

[0394] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone.

[0395] Input: Judgment result, feature vector and analysis result

[0396] Output: Verification report (including detailed evaluation results)

[0397] How it works: The server generates a report based on the results, detailing the evaluation result and confidence level for each feature. This report is securely sent to the device using HTTPS.

[0398] Step 7:

[0399] The terminal displays the received judgment result.

[0400] Input: Adjudication Report

[0401] Output: Displayed judgment results and detailed report

[0402] Specific operation: The device application displays the result of the judgment (e.g., "genuine" or "fake") to the user and allows them to view a detailed report.

[0403] Step 8:

[0404] The terminal recognizes the emotion of the user who is checking the judgment result.

[0405] Input: User's facial expression and voice data

[0406] Output: Recognized emotional state (e.g., happy, surprised, sad, etc.)

[0407] How it works: The device captures the user's facial expressions and voice through the camera and microphone, and uses facial recognition and voice analysis algorithms to identify their emotional state.

[0408] Step 9:

[0409] The device generates and displays feedback based on the recognized emotion.

[0410] Input: Perceived emotional state

[0411] Output: Feedback message

[0412] Specific operation: Based on the emotion recognition results, the device generates an appropriate message. For example, if the user is surprised, the device will display the message, "You seem surprised. Don't worry, we will provide you with more information."

[0413] (Application example 2)

[0414] 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."

[0415] Determining the authenticity of luxury goods is important to consumers, but it is difficult to do so quickly and accurately on-site. It is also necessary to provide appropriate feedback based on the user's reaction to the authentication results. Conventional systems have struggled to meet these needs, resulting in insufficient improvement in the user experience. Therefore, there is a need for a system that can quickly determine the authenticity of luxury goods and provide feedback based on the user's emotions.

[0416] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a preprocessing means, a feature extraction means, and a determination means. This makes it possible to quickly and accurately determine the authenticity of luxury goods. In addition, by using an emotion recognition means that recognizes the user's emotion and a result transmission means that transmits and displays the results on the user terminal, it is possible to provide appropriate feedback to the user and improve the user experience.

[0417] The "photography means" refers to a device that allows a user to photograph luxury items, specifically a smartphone camera or other image capture device.

[0418] The "communication means" is a means for transmitting image data captured by the image capturing means to a server, and is a device that includes a function for uploading data via an internet connection.

[0419] The "preprocessing means" is a device or software that receives image data on the server side and performs preprocessing such as noise removal and color normalization.

[0420] A "feature extraction means" is a means for extracting specific features from preprocessed image data, and is a device or software that includes an algorithm such as a convolutional neural network (CNN).

[0421] The "determination means" refers to a device or software that includes an AI model or algorithm for determining the authenticity of luxury goods based on the features extracted by the feature extraction means.

[0422] The "result transmission means" is a device or software that generates a detailed report of the judgment results and transmits them to the user's terminal.

[0423] The "result display means" is an application or interface for displaying the judgment results on the user's terminal and saving or sharing them.

[0424] The "emotion recognition means" is a device or software that uses a camera or microphone to analyze facial expressions and voice in order to recognize the user's emotions.

[0425] The "feedback means" is a means for generating and displaying appropriate feedback in accordance with the user's emotion recognized by the emotion recognition means.

[0426] The following describes an embodiment of the present invention. The present invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The present invention also combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[0427] Program processing overview

[0428] The system consists of the following components:

[0429] 1. Filming Method

[0430] 2. Means of communication

[0431] 3. Server-side preprocessing methods

[0432] 4. Feature Extraction Method

[0433] 5. Judgment means

[0434] 6. Means of sending results

[0435] 7. Results display means

[0436] 8. Emotion recognition means

[0437] 9. Feedback channels

[0438] Description of each component

[0439] Filming method

[0440] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button. The captured image is saved with appropriate image quality and resolution for analysis.

[0441] communication means

[0442] The captured image data is sent to a server via an internet connection. The image data is compressed and sent as an HTTP request to the server endpoint. This communication method ensures fast and reliable data transfer.

[0443] Server-side preprocessing measures

[0444] The server preprocesses the received image data, including removing noise, normalizing the color, and resizing the image to a size suitable for analysis. This ensures consistent image quality and facilitates processing by the feature extraction tool.

[0445] Feature Extraction Method

[0446] Features are extracted from the pre-processed image data. This process uses a convolutional neural network (CNN) as an advanced image recognition algorithm. The feature extraction method extracts important features from the image data, such as the position of the logo, seams, and the texture of the material.

[0447] Judgment means

[0448] Based on the feature vectors obtained by the feature extraction method, the AI ​​model determines the authenticity of luxury goods. The AI ​​model is trained on a large amount of data in advance, enabling highly accurate judgment. For example, it evaluates whether the logo is positioned correctly and whether the stitching pattern matches that of the genuine product.

[0449] Result transmission method

[0450] The server generates a detailed report of the results and sends it to the user's smartphone, which includes the evaluation results and their reliability for each feature.

[0451] Results display means

[0452] The user's smartphone uses an app that displays the received judgment results, allowing the user to confirm the "genuine" or "fake" rating and view a detailed report.

[0453] emotion recognition means

[0454] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[0455] Feedback Methods

[0456] After the emotion recognition means recognizes the user's emotion, it provides feedback according to that emotion. For example, if the user is shocked that the product is determined to be fake, it displays a message of comfort and the next steps to take (e.g., guidance on the return procedure).

[0457] Specific examples

[0458] Below are some examples of authenticating luxury brand bags and recognizing user emotions:

[0459] 1. The user launches the camera app on their smartphone and takes a photo of a luxury brand bag. For example, they take a photo of the entire bag and a detailed image of the logo.

[0460] 2. The captured image data is sent to the server as an HTTP request via the internet connection.

[0461] 3. The server preprocesses the received image data, removing noise and normalizing the image, and converts it into a format suitable for analysis.

[0462] 4. Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[0463] 5. Based on the extracted features, the AI ​​model determines the authenticity of the bag, assessing whether the logo is correctly positioned, whether the stitching pattern matches, etc.

[0464] Prompt Sentence Examples

[0465] Develop an app that uses a smartphone camera to take a photo of a luxury item (e.g., a designer bag) and sends the image to a server to determine its authenticity. After determining authenticity, please include a function that recognizes the user's emotions and provides appropriate feedback.

[0466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0467] Step 1:

[0468] A user launches the camera app on their smartphone and takes a picture of a luxury item. The captured image is the input, and the image data is output. The user presses the capture button on the camera app to take a picture of the entire product (e.g., a designer bag) and important logo details.

[0469] Step 2:

[0470] The device sends the captured image data to the server. The input is the image data acquired in step 1, and the output is the image data as an HTTP request to the server. The image data from the smartphone is compressed and sent to the specified server endpoint via the network.

[0471] Step 3:

[0472] The server preprocesses the image data it receives. The input is the image data sent to the server, and the output is the preprocessed image data. Preprocessing includes noise removal, color normalization, and resizing. This stabilizes the quality of the image data and makes subsequent processing easier.

[0473] Step 4:

[0474] The server extracts features from the preprocessed image data. The input is the preprocessed image data, and the output is a feature vector. Using a convolutional neural network (CNN), features such as the position of the logo, the stitching of the bag, and the texture of the material are extracted.

[0475] Step 5:

[0476] The server determines the authenticity of luxury goods based on the feature vector obtained by the feature extraction means. The input is the feature vector obtained by the feature extraction means, and the output is the authenticity determination result. An AI model is used to evaluate whether the logo is positioned correctly and whether the stitching pattern matches that of the genuine product, and to determine authenticity.

[0477] Step 6:

[0478] The server generates the judgment result and a detailed report and sends them to the user's device. The input is the authenticity judgment result, and the output is a detailed report and the judgment result data. The judgment result is compiled into a report and sent to the user's device via the Internet.

[0479] Step 7:

[0480] The device displays the received judgment results. The input is the judgment result and detailed report sent from the server, and the output is a screen display that can be viewed by the user. The user can check the results through the app and view the "genuine" or "fake" rating and detailed report.

[0481] Step 8:

[0482] The device recognizes the user's emotions. The input is facial expressions and voice data when the user confirms the judgment result, and the output is the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through the camera and microphone to identify the emotional state (e.g., joy, surprise, sadness, etc.).

[0483] Step 9:

[0484] The device provides appropriate feedback according to the user's emotion recognized by the emotion recognition means. The input is the user's emotional state, and the output is a feedback message. For example, if the user is shocked that the product is determined to be fake, the app will display a comforting message and the next steps to take (e.g., guiding them through the return procedure).

[0485] 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.

[0486] 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.

[0487] 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.

[0488] [Second embodiment]

[0489] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0490] 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.

[0491] 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).

[0492] 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.

[0493] 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.

[0494] 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).

[0495] 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. 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.

[0496] 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.

[0497] 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.

[0498] 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.

[0499] 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.

[0500] 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."

[0501] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0502] This invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The user uses their smartphone to take a picture of the luxury goods and send it to a server. The server analyzes the received image data and uses AI technology to determine the authenticity. The results are returned to the user and displayed on the smartphone.

[0503] System configuration

[0504] The system is broadly composed of the following components:

[0505] 1. Shooting method (device)

[0506] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button.

[0507] 2. Communication method (terminal → server)

[0508] The captured image data is sent to a server via an Internet connection. Specifically, the image data is uploaded to the server as an HTTP request.

[0509] 3. Preprocessing means (server)

[0510] The server preprocesses the received image data, which includes normalizing, resizing, and removing noise from the image.

[0511] 4. Feature extraction method (server)

[0512] The server extracts features from the pre-processed image data using advanced image recognition algorithms such as convolutional neural networks (CNNs).

[0513] 5. Determination means (server)

[0514] Based on the feature vectors obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[0515] 6. Result transmission method (server → terminal)

[0516] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone via the Internet.

[0517] 7. Result display means (terminal)

[0518] The user's smartphone uses an app that displays the received judgment results, which are rated as "genuine" or "fake," and a detailed report can also be viewed.

[0519] Program processing

[0520] The system process proceeds as follows, with an example:

[0521] Example: Authentication of luxury brand bags

[0522] 1. User - Launches the camera app on the smartphone and takes a photo of a luxury brand bag. For example, the user takes a photo of the entire bag and a detailed image of the logo.

[0523] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[0524] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[0525] 4. Server - Extract features from the preprocessed image data. Using a convolutional neural network (CNN), features such as the position of the logo, the stitching of the bag, and the texture of the material are extracted.

[0526] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[0527] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone, including the evaluation result and reliability of each feature.

[0528] 7. Device - The received judgment result is displayed. The user can confirm the judgment result of "genuine" or "fake" through the app. For example, the report will show an evaluation such as "The logo position is accurate and matches the genuine article."

[0529] As described above, by using the system of the present invention, users can easily determine the authenticity of luxury goods, providing reliability and peace of mind in the luxury goods market.

[0530] The processing flow will be explained below.

[0531] Step 1:

[0532] User - Launches the camera app on the smartphone and takes a picture of a luxury item (e.g., a bag). By pressing the capture button on the camera app, high-resolution image data is acquired.

[0533] Step 2:

[0534] Device - The captured image data is temporarily stored in the device's memory, and a preview of the stored image is displayed, prompting the user for confirmation.

[0535] Step 3:

[0536] Terminal - Prepares communication to send the confirmed image data to the server. Specifically, it compresses the image data appropriately and sends it to the server endpoint in the form of an HTTP request.

[0537] Step 4:

[0538] Server - Temporarily stores the received image data. The server prepares this data for passing to the analysis module.

[0539] Step 5:

[0540] Server - Initiates pre-processing of the image data, which includes denoising the image, color normalizing it, and resizing it to a size suitable for analysis.

[0541] Step 6:

[0542] Server - Extracts features from the pre-processed image data. Convolutional neural networks (CNNs) are used to detect specific features in the image (e.g., logo location, stitching patterns, material textures, etc.).

[0543] Step 7:

[0544] Server - Using the results of feature extraction, the AI ​​model determines the authenticity of the image. The AI ​​model has been trained with a large amount of data in advance, and calculates the probability that the image is genuine or fake based on the extracted features.

[0545] Step 8:

[0546] Server - Generates the assessment results and a detailed report detailing the assessment result and confidence level for each feature.

[0547] Step 9:

[0548] Server - Sends the generated verdicts and reports to the user's device, usually as an HTTP response, and notifies the user in real time.

[0549] Step 10:

[0550] Terminal - Analyzes the received judgment results and displays them on the user interface. Users can check the results and view detailed reports via a smartphone app.

[0551] Step 11:

[0552] Users can review the results and optionally save or share them with others, allowing them to quickly make the right decisions about the authenticity of luxury items.

[0553] Example 1

[0554] 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."

[0555] Counterfeits are rampant in the luxury goods market, and users are seeking a means to easily determine the authenticity of luxury goods. Conventional methods require advanced expertise and special equipment, making them difficult for average users to use. In addition, expert appraisals are time-consuming and expensive, and do not meet modern needs for immediacy. Therefore, there is a need for a system that can quickly and accurately determine the authenticity of luxury goods.

[0556] 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.

[0557] In this invention, the server includes a preprocessing means that receives image data and performs preprocessing such as noise removal, normalization, and resizing, a feature extraction means that extracts features from the preprocessed image data using a convolutional neural network, and a determination means that determines the authenticity of luxury goods using an AI model based on the feature vectors extracted by the feature extraction means. This enables users to easily verify the authenticity of luxury goods in real time.

[0558] "Photographing means" refers to a device or system that a user uses to capture images of luxury items, and includes a smartphone camera or dedicated photographic equipment.

[0559] The "communication means" refers to a mechanism or protocol for transmitting image data captured by the image capturing means to a server, and includes an internet connection, an HTTP request, and the like.

[0560] The "preprocessing means" is a function that performs processes such as noise removal, normalization, and resizing on the image data received by the server, and converts the image data into a format suitable for analysis.

[0561] The "feature extraction means" is a function for extracting useful features from preprocessed image data, and mainly uses algorithms such as convolutional neural networks (CNNs).

[0562] The "determination means" refers to a system or algorithm for determining the authenticity of luxury goods based on the feature vector obtained by the feature extraction means, and an AI model is mainly used.

[0563] The "result transmission means" is a function that allows the server to generate the authenticity determination result and a detailed report and transmit them to the user's terminal.

[0564] The "result display means" is a function that displays the authenticity determination results and detailed reports on the user's terminal, and provides information in a format that is easy for the user to understand.

[0565] An "AI model" is a mathematical model that uses machine learning and deep learning techniques to learn features from large amounts of data and perform highly accurate authenticity determinations.

[0566] A "convolutional neural network (CNN)" is a type of deep learning algorithm specialized in image recognition and feature extraction, which clarifies features by analyzing pixel data extracted from an input image across multiple layers.

[0567] This invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's device (e.g., a smartphone). The user takes a picture of the luxury goods using the device's camera and sends the image to a server. The server then preprocesses the received image data and uses AI technology to determine its authenticity. The results are returned to the user and displayed on the device.

[0568] Hardware and software used

[0569] 1. Device (smartphone)

[0570] Hardware: Smartphone (e.g. iPhone, Android)

[0571] Software: Camera app (e.g. iOS camera app, Google Camera)

[0572] 2. Means of communication

[0573] Network: Internet connection (e.g. Wi-Fi, LTE)

[0574] Communication library: HTTP communication library (e.g., OkHttp, Retrofit)

[0575] 3. Server

[0576] Hardware: Cloud servers (e.g., AWS EC2 instances, Google Cloud Platform GPU instances)

[0577] software:

[0578] Preprocessing library: Image processing library (e.g. OpenCV, Pillow)

[0579] AI / Deep Learning Frameworks: Deep Learning frameworks (e.g. TensorFlow, PyTorch)

[0580] System action

[0581] The system works as follows:

[0582] 1. User operation: The user launches the camera app on their smartphone and takes a picture of a luxury item, for example, taking a full picture of the bag and a detailed shot of the logo.

[0583] Example: A user takes a photo of the logo of a luxury brand bag with their smartphone.

[0584] 2. Image transmission from the device to the server: The device compresses the captured image data and sends it to the server as an HTTP request.

[0585] Example: An Android smartphone takes a picture, compresses it into JPEG format, and sends it to a server using an HTTP POST request.

[0586] 3. Preprocessing on the server: The server performs preprocessing on the received image data, such as noise removal, normalization, and resizing.

[0587] Example: A Python script on a server preprocesses image data using the Pillow library.

[0588] 4. Feature extraction on the server: Features are extracted from the preprocessed image data using a convolutional neural network (CNN).

[0589] Example: Using TensorFlow, a CNN model extracts features from the logo on a bag.

[0590] 5. Authentication on the server: Based on the feature vectors, the AI ​​model determines the authenticity of luxury goods, for example, by checking the placement of logos and stitching patterns.

[0591] Example: A PyTorch-based ResNet model analyzes logo placement and stitching patterns to determine authenticity.

[0592] 6. Sending results from the server to the device: The judgment results and a detailed report are generated and sent to the user's device as an HTTP response.

[0593] Example: As a result of the judgment, a report is generated stating that "The logo position matches precisely and the stitching matches that of the genuine product, so it has been judged to be genuine," and this is sent to the terminal in JSON format.

[0594] 7. Displaying results on the terminal: Displaying the received judgment results and providing a detailed report to the user.

[0595] Example: The dedicated verification app displays the results, stating that "the logo position is accurate and matches the genuine article."

[0596] Examples and prompts

[0597] Example: Authentication of luxury brand bags

[0598] The user launches the smartphone's camera app and takes a photo of the bag's overall appearance and the logo. The smartphone then compresses the image data and sends it as an HTTP request to the server. The server preprocesses the received image data and uses CNN to extract features such as the logo and stitching. Based on these features, the AI ​​model determines whether the bag is authentic or not, and generates and returns the results and a detailed report to the user. Finally, the smartphone displays the results, allowing the user to view the "genuine" or "fake" rating and detailed report.

[0599] Prompt Sentence Examples

[0600] "To determine the authenticity of a luxury brand bag, you take a photo of the entire bag and the logo with your smartphone and send the image to our server. The server preprocesses the image, extracts features using CNN, and then uses an AI model to make a determination. You can then check the determination results and a detailed report on your smartphone."

[0601] The present invention enables users to easily and quickly verify the authenticity of luxury goods, providing reliability and peace of mind in the luxury goods market.

[0602] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0603] Step 1:

[0604] User-generated photos

[0605] A user starts the camera app on their smartphone and takes a picture of a luxury item. For example, the user takes a picture of the entire luxury brand bag and the logo. The input at this stage is the start of the camera and the selection of the subject, and the output is the captured image data.

[0606] Step 2:

[0607] Sending images from the device to the server

[0608] The device compresses the captured image data and sends it as an HTTP request to a server via the Internet. The input is the captured image data, and the output is the compressed image data and its HTTP request. Specifically, the device compresses the image into JPEG format and sends it using an HTTP POST request.

[0609] Step 3:

[0610] Preprocessing on the server

[0611] The server reads the received image data and performs preprocessing such as noise removal, normalization, and resizing. The input of this step is compressed image data, and the output is preprocessed image data. Specifically, a Python script on the server uses the Pillow library to resize the image appropriately and remove noise.

[0612] Step 4:

[0613] Feature extraction on the server

[0614] The server extracts features from the preprocessed image data using a convolutional neural network (CNN). The input of this step is the preprocessed image data, and the output is a feature vector. For example, using TensorFlow, a CNN model extracts features such as the logo and stitching of a bag.

[0615] Step 5:

[0616] Authentication on the server

[0617] The server uses an AI model to determine the authenticity of luxury goods based on the extracted feature vectors. The input for this step is the feature vector, and the output is the authenticity determination result. Specifically, a PyTorch-based ResNet model analyzes the position of the logo and the stitching pattern to determine authenticity.

[0618] Step 6:

[0619] Sending results from the server to the device

[0620] The server generates the judgment result and a detailed report and sends them to the user's device as an HTTP response. The input to this step is the authenticity judgment result, and the output is a detailed report and its HTTP response. Specifically, the judgment result is converted to JSON format and sent.

[0621] Step 7:

[0622] Displaying results on your device

[0623] The device displays the received judgment result and provides it to the user. The input of this step is the detailed report received from the server, and the output is the judgment result displayed to the user. Specifically, the dedicated verification app displays the judgment result and a detailed report, informing the user that "the logo position is accurate and matches the genuine article."

[0624] (Application example 1)

[0625] 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."

[0626] Conventional systems for determining the authenticity of luxury goods are primarily designed for online use, and have the problem of difficulty in quickly and accurately determining authenticity in physical stores. In particular, there is a need to be able to instantly determine the authenticity of luxury goods when they are being explained to customers in physical stores, and to provide customers with highly reliable information. In addition, from the perspective of the devices used, there is a need to improve the work efficiency of store clerks by utilizing smart glasses and head-mounted displays.

[0627] 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.

[0628] In this invention, the server includes a photographing means for a user to photograph luxury goods, a communication means for transmitting image data photographed by the photographing means to the server, a server-side preprocessing means for receiving and preprocessing the image data, a feature extraction means for extracting features from the preprocessed image data, a determination means for determining the authenticity of the luxury goods based on the features extracted by the feature extraction means, a result transmission means for generating the determination results and a detailed report and transmitting them to the user's terminal, a result display means for displaying the results on the user's terminal and saving or sharing them, and a means for photographing the luxury goods and displaying the determination results via smart glasses or a head-mounted display in a physical store, thereby enabling fast and accurate authenticity determination in a physical store.

[0629] "Luxury goods" generally refer to items that are expensive, rare, and made using high-quality materials and sophisticated craftsmanship.

[0630] "Authenticity" refers to determining whether something is genuine or fake.

[0631] A "system" is a collective term for multiple components or means combined to achieve a specific function or purpose.

[0632] "Photographing means" refers to a camera or other photographing device that a user uses to photograph luxury items.

[0633] "Communication means" refers to an internet connection or other data transmission means for sending captured image data to a server.

[0634] The "preprocessing means" refers to a processing means on the server that performs preprocessing such as noise removal, normalization, and resizing on the received image data.

[0635] "Feature extraction means" refers to an algorithm or device for extracting product-specific features from pre-processed image data.

[0636] "Determination means" refers to an AI model or algorithm for determining the authenticity of luxury goods based on the features extracted by the feature extraction means.

[0637] "Result transmission means" refers to a communication means for generating a detailed report of the judgment results and transmitting them to the user's terminal.

[0638] "Result display means" refers to the user interface or software for displaying results on the user's terminal and saving or sharing the results.

[0639] "Smart glasses" refers to a wearable device that has display and camera functions and can send and receive data when worn by the user.

[0640] A "head-mounted display" refers to a display device that provides visual information when worn by a user on the head.

[0641] "Internet connection" refers to a network connection for uploading image data to a server via a communication means.

[0642] "Determination result" refers to the result of the AI ​​model determining the authenticity of a luxury item.

[0643] A "detailed report" refers to a report that details the evaluation results and reliability of each feature based on the judgment results.

[0644] System configuration

[0645] The system of the present invention is designed to determine the authenticity of luxury goods and can be used in brick-and-mortar stores. The system consists of the following components:

[0646] 1. Imaging method (smart glasses or head-mounted display)

[0647] The user wears smart glasses or a head-mounted display and takes a photo of a luxury item. The device has a built-in camera, allowing the product to be photographed naturally from the user's point of view.

[0648] 2. Communication method (Wi-Fi, etc.)

[0649] The captured image data is sent to a server via Wi-Fi, using an internet connection as the communication method, and the data is compressed before being sent.

[0650] 3. Preprocessing method (server side)

[0651] The server preprocesses the received image data, which includes normalizing, resizing, and removing noise, converting the image into a suitable format for subsequent analysis.

[0652] 4. Feature extraction method (server side)

[0653] The server extracts features from the preprocessed image data using a convolutional neural network (CNN) to extract product-specific features (e.g., logo position, stitching pattern, material texture).

[0654] 5. Judgment method (server side)

[0655] Based on the features obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[0656] 6. Result transmission method (server → terminal)

[0657] The server generates a detailed report with the results and transmits it to the user's smart glasses or head-mounted display via Wi-Fi.

[0658] 7. Display of results (smart glasses or head-mounted display)

[0659] The user's device displays the received judgment results, which are instantly displayed as "genuine" or "fake," and a detailed report can also be viewed.

[0660] Specific processing of the program

[0661] As an example of a physical store, we will demonstrate how the system works in a store that sells luxury brand watches. A salesperson wears smart glasses or a head-mounted display and takes a photo of the watch case or dial. The image data is sent to a server via Wi-Fi, where it is normalized and resized by pre-processing. Features are then extracted using a convolutional neural network (CNN), and an AI model makes a judgment. The judgment result is then sent back to the device via Wi-Fi, where the salesperson can check it on the spot.

[0662] The required hardware includes smart glasses (e.g., Google Glass) or a head-mounted display (e.g., Microsoft HoloLens), and the server side requires a high-performance GPU. The software includes machine learning libraries such as Python and TensorFlow.

[0663] Specific examples

[0664] For example, in a store selling luxury brand watches, a salesperson uses smart glasses to take a photo of the watch case or dial. The image data is sent to a server via Wi-Fi and preprocessed. Features are then extracted using CNN, and an AI model determines its authenticity. The result, "This watch is genuine," is displayed on the smart glasses.

[0665] Prompt Sentence Examples

[0666] Prompt: "This image is of a luxury brand watch case. Use a convolutional neural network to determine whether it is authentic. Consider the shape of the case, the placement of the numerals on the dial, and the texture of the material as characteristics."

[0667] In this way, by using the system of the present invention, it becomes possible to quickly and accurately determine the authenticity of luxury goods even in physical stores, thereby realizing the provision of highly reliable information to customers.

[0668] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0669] Step 1:

[0670] The user wears smart glasses or a head-mounted display and takes pictures of luxury items.

[0671] Input: Images of luxury items captured through a camera built into smart glasses or a head-mounted display

[0672] Output: Image data of the luxury item photographed

[0673] Action: The user activates the camera and takes a picture of a specific part (such as the case or dial) of a luxury item (e.g., a luxury brand watch).

[0674] Step 2:

[0675] The device sends the captured image data to a server via Wi-Fi.

[0676] Input: Image data of the luxury item photographed

[0677] Output: Image data sent to the server

[0678] How it works: The communication module inside the device compresses the image data and uploads it to the server as an HTTP request.

[0679] Step 3:

[0680] The server pre-processes the received image data.

[0681] Input: Image data sent to the server

[0682] Output: Preprocessed image data (normalized, resized, and denoised)

[0683] How it works: A program on the server normalizes the image data, resizes it to a consistent size, and denoises it, using an image processing library such as OpenCV.

[0684] Step 4:

[0685] The server extracts features from the preprocessed image data.

[0686] Input: Preprocessed image data

[0687] Output: Feature vector

[0688] How it works: It uses a server-based convolutional neural network (CNN) to extract features from images, using machine learning frameworks such as TensorFlow and Keras.

[0689] Step 5:

[0690] The server determines the authenticity of the luxury item based on the features obtained by the feature extraction means.

[0691] Input: feature vector

[0692] Output: Verification result (e.g. "Genuine", "Fake")

[0693] How it works: The AI ​​model analyzes feature vectors and determines authenticity based on a pre-trained dataset.

[0694] Step 6:

[0695] The server generates a detailed report with the results of the assessment and sends it to the user's terminal.

[0696] Input: Judgment results, detailed report elements (e.g., evaluation of logo position and material texture)

[0697] Output: Verification results and detailed report

[0698] How it works: The server generates a text report with the results and a detailed report, which it then sends back to the user's device via Wi-Fi.

[0699] Step 7:

[0700] The terminal displays the received judgment result.

[0701] Input: Verification results and detailed report

[0702] Output: Judgment results and detailed reports displayed on smart glasses or a head-mounted display

[0703] How it works: Using the device's display function, the result is displayed as "genuine" or "fake," and a detailed report can also be viewed.

[0704] 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.

[0705] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0706] The present invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The present invention also combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[0707] System configuration

[0708] The system is broadly composed of the following components:

[0709] 1. Shooting method (device)

[0710] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button.

[0711] 2. Communication method (terminal → server)

[0712] The captured image data is sent to a server over an internet connection, specifically as an HTTP request to a server endpoint.

[0713] 3. Preprocessing means (server)

[0714] The server preprocesses the received image data, which includes removing noise from the image, normalizing the color, and resizing it to a size suitable for analysis.

[0715] 4. Feature extraction method (server)

[0716] The server extracts features from the pre-processed image data using advanced image recognition algorithms such as convolutional neural networks (CNNs).

[0717] 5. Determination means (server)

[0718] Based on the feature vectors obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[0719] 6. Result transmission method (server → terminal)

[0720] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone via the Internet.

[0721] 7. Result display means (terminal)

[0722] The user's smartphone uses an app that displays the received judgment results. The result is a rating of "genuine" or "fake," and a detailed report can be viewed. The app also incorporates an emotion engine that recognizes the user's emotions.

[0723] 8. Emotion Engine (Terminal)

[0724] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[0725] 9. Feedback means (terminal)

[0726] The emotion engine recognizes the user's emotions and then provides feedback based on those emotions. For example, if the user is shocked that the product is identified as fake, it will display a message of comfort and the next steps to take (e.g., guiding them through the return process).

[0727] Program processing

[0728] The system process proceeds as follows, with an example:

[0729] Example: Authentication of luxury brand bags and user emotion recognition

[0730] 1. User - Launches the camera app on the smartphone and takes a photo of a luxury brand bag. For example, the user takes a photo of the entire bag and a detailed image of the logo.

[0731] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[0732] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[0733] 4. Server - Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[0734] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[0735] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone. The report details the evaluation result and its reliability for each feature.

[0736] 7. Device - Displays the received judgment result. The user can check the judgment result of "genuine" or "fake" through the app. A detailed report can also be viewed.

[0737] 8. Device - While the user is checking the result, the emotion engine analyzes the user's facial expressions and voice. For example, if the user is surprised, the camera captures and analyzes their facial expression.

[0738] 9. Device - Feedback is generated based on emotions. For example, if the user is surprised, the message "You seem surprised. Don't worry, we'll provide you with more information."

[0739] 10. User - Review the results and feedback and decide on the next action. For example, if the bag is determined to be fake, they will be provided with information to proceed with the return process.

[0740] In this way, the present invention allows users to easily determine the authenticity of luxury items, and further improves the user experience by providing feedback according to the user's emotional state.

[0741] The processing flow will be explained below.

[0742] Step 1:

[0743] User - Launches the camera app on the smartphone and takes a picture of a luxury item (e.g., a designer bag). By pressing the capture button on the camera app, high-resolution image data is acquired.

[0744] Step 2:

[0745] Device - The acquired image data is temporarily stored in the device's memory, and a preview of the stored image is displayed, prompting the user for confirmation.

[0746] Step 3:

[0747] Device - Begin preparing to send the verified image data to the server. The image data is appropriately compressed and sent to the server endpoint in the form of an HTTP request. Specifically, the request is generated with the following information:

[0748] User ID

[0749] Image data

[0750] timestamp

[0751] Step 4:

[0752] Server - Receives and temporarily stores the image data sent to it. The server prepares the data for passing to the analysis module and checks the integrity of the data.

[0753] Step 5:

[0754] Server - Initiates preprocessing of the image data. This preprocessing includes denoising the image, color normalizing it, and resizing it to a size suitable for analysis. Specific tasks include:

[0755] Normalizing pixel values

[0756] Noise removal using a Gaussian filter

[0757] Resize

[0758] Step 6:

[0759] Server - Extracts features from the pre-processed image data. Convolutional neural networks (CNNs) are used to detect specific features in the image (e.g., logo location, stitching patterns, material textures, etc.).

[0760] Step 7:

[0761] Server - Using the results of feature extraction, the AI ​​model determines the authenticity of the image. The AI ​​model has been trained with a large amount of data in advance, and calculates the probability of whether an image is genuine or fake based on the extracted feature vector. The specific evaluation is as follows:

[0762] Does the logo shape and placement match the genuine product?

[0763] Do the stitch patterns match?

[0764] Is the texture of the material the same?

[0765] Step 8:

[0766] Server - Generates the assessment results and a detailed report detailing the assessment results and confidence levels for each feature, as well as the analysis of the images used to make the assessment.

[0767] Step 9:

[0768] Server - Sends generated verdicts and reports to the user's device, usually as HTTP responses, notifying the user in real time.

[0769] Step 10:

[0770] Device - Analyzes the received results and displays them in the user interface. The app displays a summary of the results and a detailed report for easy review by the user. Specifically, it displays the following information:

[0771] Verification result (genuine / fake)

[0772] Detailed characterization

[0773] Report download link

[0774] Step 11:

[0775] On your device - While you are checking your results, the app will use your smartphone's camera and microphone to analyze your facial expressions and voice with its emotion engine. This includes:

[0776] Face detection and facial expression analysis

[0777] Voice tone and pitch analysis

[0778] Step 12:

[0779] Terminal - Based on the analysis results of the emotion engine, identify the user's emotional state (e.g., joy, surprise, sadness, etc.) and generate a feedback message according to the emotional state.

[0780] Step 13:

[0781] Terminal - Display feedback to the user based on their emotions. For example, if the user is surprised, display "I see you're surprised. We'll provide you with more information, so don't worry." If the user is shocked, provide a comforting message or instructions on what to do next (e.g., instructions on how to return the product).

[0782] Step 14:

[0783] User - Review the results and feedback and decide on the next action. For example, if the bag is determined to be counterfeit, view information to proceed with the return process.

[0784] Example 2

[0785] 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."

[0786] Determining the authenticity of luxury goods requires expert knowledge and skills, making it difficult for users without advanced expertise. Furthermore, appropriately responding to the user's emotional reaction when receiving the results is important for improving the user experience. Given this situation, the present invention aims to provide a system that easily determines the authenticity of luxury goods and provides feedback based on the user's emotional state.

[0787] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0788] In this invention, the server includes a means for receiving and preprocessing image data, a means for extracting features from the preprocessed image data, and a means for determining the authenticity of an item based on the extracted features, thereby enabling highly accurate authentication and appropriate feedback based on the user's emotions.

[0789] "Photographing means" refers to a smartphone camera or other imaging device that a user uses to photograph an item.

[0790] The "communication means" refers to a means for transmitting image data acquired by the photographing means to a server via an Internet connection, and specifically, uses a protocol such as an HTTP request.

[0791] "Preprocessing means" refers to the process of performing noise removal, color normalization, resizing, etc. on the image data received on the server side and converting it into a format suitable for analysis.

[0792] "Feature extraction means" refers to algorithms and hardware for extracting article features (e.g., logo location, stitching pattern, material texture, etc.) from pre-processed image data.

[0793] "Determination means" refers to an AI model or algorithm that determines the authenticity of an item based on the features obtained by the feature extraction means.

[0794] The "result transmission means" is a means for generating the judgment results and a detailed report and transmitting them to the user's terminal, and utilizes an internet connection.

[0795] "Result display means" refers to an application or interface for displaying the assessment results and detailed reports on the user's device and saving or sharing them.

[0796] "Emotion recognition means" refers to hardware and software for identifying the emotional state of a user by analyzing the facial expression, voice, etc. of the user checking the judgment result.

[0797] The "feedback means" refers to software for generating appropriate feedback based on the emotion recognized by the emotion recognition means and providing it to the user.

[0798] The present invention is a system for determining the authenticity of luxury goods. This system operates primarily on the user's smartphone and combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[0799] System configuration

[0800] The system is broadly composed of the following components:

[0801] 1. Shooting method (device)

[0802] The user takes a photo of the luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button. Specifically, a high-definition camera or a standard camera on the smartphone can be used.

[0803] 2. Communication method (terminal → server)

[0804] The captured image data is sent to a server via an internet connection. Specifically, the image data is sent as an HTTP request to the server endpoint. HTTPS is the recommended communication protocol.

[0805] 3. Preprocessing means (server)

[0806] The server preprocesses the received image data, which includes removing noise, color normalizing, and resizing the image to a size suitable for analysis. Specifically, median filtering and histogram equalization are applied.

[0807] 4. Feature extraction method (server)

[0808] The server extracts features from the pre-processed image data using a sophisticated image recognition algorithm called a convolutional neural network (CNN), such as the location of logos, stitching patterns, and material textures.

[0809] 5. Determination means (server)

[0810] Based on the feature vectors obtained by the feature extraction method, an AI model determines the authenticity of luxury goods. This AI model has been trained on a large dataset in advance, enabling highly accurate judgment. For example, it evaluates whether the luxury brand logo or stitching pattern matches that of the genuine product.

[0811] 6. Result transmission method (server → terminal)

[0812] The server generates a detailed report of the results and sends it to the user's smartphone via the Internet. The report details the evaluation results and their reliability for each feature.

[0813] 7. Result display means (terminal)

[0814] The user's smartphone uses an app that displays the received judgment results, which are rated as "genuine" or "fake," and a detailed report can also be viewed.

[0815] 8. Emotion recognition means (terminal)

[0816] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[0817] 9. Feedback means (terminal)

[0818] The emotion engine recognizes the user's emotions and then provides feedback based on those emotions. For example, if the user is shocked that the product is identified as fake, it will display a message of comfort and the next steps to take (e.g., guiding them through the return process).

[0819] Specific examples

[0820] Example: Authentication of luxury brand bags and user emotion recognition

[0821] 1. User - Launches the smartphone camera app and takes a photo of a luxury brand bag, taking a full view of the bag and a detailed view of the logo.

[0822] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[0823] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[0824] 4. Server - Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[0825] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[0826] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone. The report details the evaluation result and its reliability for each feature.

[0827] 7. Device - The received judgment results are displayed in the app, and the user can check the "genuine" or "fake" judgment results and report.

[0828] 8. Device - While the user is checking the result, the emotion engine analyzes the user's facial expressions and voice. For example, if the user is surprised, the camera captures and analyzes their facial expression.

[0829] 9. Device - Generate feedback based on emotions. For example, if the user is surprised, display a message like "I see you're surprised. Don't worry, we'll provide you with more information."

[0830] Examples of typical prompt statements

[0831] "Explain the outline of a system that uses AI to determine the authenticity of a luxury brand bag using an image taken by the user, and then describe the entire process of recognizing the user's emotions and providing feedback."

[0832] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0833] Step 1:

[0834] The user launches the camera app on their smartphone and takes a picture of the luxury item.

[0835] Input: Item (e.g. luxury brand bag)

[0836] Output: Captured image data (high-resolution image)

[0837] What happens: The user points the camera at a luxury item, focuses it, and takes a photo in a well-lit area, capturing both the overall image of the bag and the details (logo, stitching, etc.).

[0838] Step 2:

[0839] The terminal transmits the captured image data to a server via the Internet.

[0840] Input: Captured image data

[0841] Output: Image data sent as an HTTP request

[0842] Specific behavior: The device compresses and encodes the image data, generates an HTTP POST request, and sends it to the server endpoint.

[0843] Step 3:

[0844] The server pre-processes the received image data.

[0845] Input: Received image data

[0846] Output: Preprocessed image data

[0847] Specific operation: The server performs noise removal (median filtering) on ​​the received image data, then performs color normalization (histogram equalization), and resizes it to a size suitable for analysis.

[0848] Step 4:

[0849] The server extracts features from the preprocessed image data.

[0850] Input: Preprocessed image data

[0851] Output: feature vector

[0852] How it works: The server uses a convolutional neural network (CNN) to extract important features in the image (such as the position of the logo, the stitching pattern, and the texture of the material) and represents these features as a feature vector.

[0853] Step 5:

[0854] The server uses an AI model to determine authenticity based on the feature vector obtained by the feature extraction means.

[0855] Input: feature vector

[0856] Output: Verification result (e.g. "Genuine" or "Fake")

[0857] How it works: The server inputs the feature vector into a trained AI model, which then makes a judgment, such as whether the logo position matches that of the genuine product or whether the stitching pattern matches that of the genuine product.

[0858] Step 6:

[0859] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone.

[0860] Input: Judgment result, feature vector and analysis result

[0861] Output: Verification report (including detailed evaluation results)

[0862] How it works: The server generates a report based on the results, detailing the evaluation result and confidence level for each feature. This report is securely sent to the device using HTTPS.

[0863] Step 7:

[0864] The terminal displays the received judgment result.

[0865] Input: Adjudication Report

[0866] Output: Displayed judgment results and detailed report

[0867] Specific operation: The device application displays the result of the judgment (e.g., "genuine" or "fake") to the user and allows them to view a detailed report.

[0868] Step 8:

[0869] The terminal recognizes the emotion of the user who is checking the judgment result.

[0870] Input: User's facial expression and voice data

[0871] Output: Recognized emotional state (e.g., happy, surprised, sad, etc.)

[0872] How it works: The device captures the user's facial expressions and voice through the camera and microphone, and uses facial recognition and voice analysis algorithms to identify their emotional state.

[0873] Step 9:

[0874] The device generates and displays feedback based on the recognized emotion.

[0875] Input: Perceived emotional state

[0876] Output: Feedback message

[0877] Specific operation: Based on the emotion recognition results, the device generates an appropriate message. For example, if the user is surprised, the device will display the message, "You seem surprised. Don't worry, we will provide you with more information."

[0878] (Application example 2)

[0879] 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."

[0880] Determining the authenticity of luxury goods is important to consumers, but it is difficult to do so quickly and accurately on-site. It is also necessary to provide appropriate feedback based on the user's reaction to the authentication results. Conventional systems have struggled to meet these needs, resulting in insufficient improvement in the user experience. Therefore, there is a need for a system that can quickly determine the authenticity of luxury goods and provide feedback based on the user's emotions.

[0881] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a preprocessing means, a feature extraction means, and a determination means. This makes it possible to quickly and accurately determine the authenticity of luxury goods. In addition, by using an emotion recognition means that recognizes the user's emotion and a result transmission means that transmits and displays the results on the user terminal, it is possible to provide appropriate feedback to the user and improve the user experience.

[0882] The "photography means" refers to a device that allows a user to photograph luxury items, specifically a smartphone camera or other image capture device.

[0883] The "communication means" is a means for transmitting image data captured by the image capturing means to a server, and is a device that includes a function for uploading data via an internet connection.

[0884] The "preprocessing means" is a device or software that receives image data on the server side and performs preprocessing such as noise removal and color normalization.

[0885] A "feature extraction means" is a means for extracting specific features from preprocessed image data, and is a device or software that includes an algorithm such as a convolutional neural network (CNN).

[0886] The "determination means" refers to a device or software that includes an AI model or algorithm for determining the authenticity of luxury goods based on the features extracted by the feature extraction means.

[0887] The "result transmission means" is a device or software that generates a detailed report of the judgment results and transmits them to the user's terminal.

[0888] The "result display means" is an application or interface for displaying the judgment results on the user's terminal and saving or sharing them.

[0889] The "emotion recognition means" is a device or software that uses a camera or microphone to analyze facial expressions and voice in order to recognize the user's emotions.

[0890] The "feedback means" is a means for generating and displaying appropriate feedback in accordance with the user's emotion recognized by the emotion recognition means.

[0891] The following describes an embodiment of the present invention. The present invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The present invention also combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[0892] Program processing overview

[0893] The system consists of the following components:

[0894] 1. Filming Method

[0895] 2. Means of communication

[0896] 3. Server-side preprocessing methods

[0897] 4. Feature Extraction Method

[0898] 5. Judgment means

[0899] 6. Means of sending results

[0900] 7. Results display means

[0901] 8. Emotion recognition means

[0902] 9. Feedback channels

[0903] Description of each component

[0904] Filming method

[0905] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button. The captured image is saved with appropriate image quality and resolution for analysis.

[0906] communication means

[0907] The captured image data is sent to a server via an internet connection. The image data is compressed and sent as an HTTP request to the server endpoint. This communication method ensures fast and reliable data transfer.

[0908] Server-side preprocessing measures

[0909] The server preprocesses the received image data, including removing noise, normalizing the color, and resizing the image to a size suitable for analysis. This ensures consistent image quality and facilitates processing by the feature extraction tool.

[0910] Feature Extraction Method

[0911] Features are extracted from the pre-processed image data. This process uses a convolutional neural network (CNN) as an advanced image recognition algorithm. The feature extraction method extracts important features from the image data, such as the position of the logo, seams, and the texture of the material.

[0912] Judgment means

[0913] Based on the feature vectors obtained by the feature extraction method, the AI ​​model determines the authenticity of luxury goods. The AI ​​model is trained on a large amount of data in advance, enabling highly accurate judgment. For example, it evaluates whether the logo is positioned correctly and whether the stitching pattern matches that of the genuine product.

[0914] Result transmission method

[0915] The server generates a detailed report of the results and sends it to the user's smartphone, which includes the evaluation results and their reliability for each feature.

[0916] Results display means

[0917] The user's smartphone uses an app that displays the received judgment results, allowing the user to confirm the "genuine" or "fake" rating and view a detailed report.

[0918] emotion recognition means

[0919] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[0920] Feedback Methods

[0921] After the emotion recognition means recognizes the user's emotion, it provides feedback according to that emotion. For example, if the user is shocked that the product is determined to be fake, it displays a message of comfort and the next steps to take (e.g., guidance on the return procedure).

[0922] Specific examples

[0923] Below are some examples of authenticating luxury brand bags and recognizing user emotions:

[0924] 1. The user launches the camera app on their smartphone and takes a photo of a luxury brand bag. For example, they take a photo of the entire bag and a detailed image of the logo.

[0925] 2. The captured image data is sent to the server as an HTTP request via the internet connection.

[0926] 3. The server preprocesses the received image data, removing noise and normalizing the image, and converts it into a format suitable for analysis.

[0927] 4. Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[0928] 5. Based on the extracted features, the AI ​​model determines the authenticity of the bag, assessing whether the logo is correctly positioned, whether the stitching pattern matches, etc.

[0929] Prompt Sentence Examples

[0930] Develop an app that uses a smartphone camera to take a photo of a luxury item (e.g., a designer bag) and sends the image to a server to determine its authenticity. After determining authenticity, please include a function that recognizes the user's emotions and provides appropriate feedback.

[0931] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0932] Step 1:

[0933] A user launches the camera app on their smartphone and takes a picture of a luxury item. The captured image is the input, and the image data is output. The user presses the capture button on the camera app to take a picture of the entire product (e.g., a designer bag) and important logo details.

[0934] Step 2:

[0935] The device sends the captured image data to the server. The input is the image data acquired in step 1, and the output is the image data as an HTTP request to the server. The image data from the smartphone is compressed and sent to the specified server endpoint via the network.

[0936] Step 3:

[0937] The server preprocesses the image data it receives. The input is the image data sent to the server, and the output is the preprocessed image data. Preprocessing includes noise removal, color normalization, and resizing. This stabilizes the quality of the image data and makes subsequent processing easier.

[0938] Step 4:

[0939] The server extracts features from the preprocessed image data. The input is the preprocessed image data, and the output is a feature vector. Using a convolutional neural network (CNN), features such as the position of the logo, the stitching of the bag, and the texture of the material are extracted.

[0940] Step 5:

[0941] The server determines the authenticity of luxury goods based on the feature vector obtained by the feature extraction means. The input is the feature vector obtained by the feature extraction means, and the output is the authenticity determination result. An AI model is used to evaluate whether the logo is positioned correctly and whether the stitching pattern matches that of the genuine product, and to determine authenticity.

[0942] Step 6:

[0943] The server generates the judgment result and a detailed report and sends them to the user's device. The input is the authenticity judgment result, and the output is a detailed report and the judgment result data. The judgment result is compiled into a report and sent to the user's device via the Internet.

[0944] Step 7:

[0945] The device displays the received judgment results. The input is the judgment result and detailed report sent from the server, and the output is a screen display that can be viewed by the user. The user can check the results through the app and view the "genuine" or "fake" rating and detailed report.

[0946] Step 8:

[0947] The device recognizes the user's emotions. The input is facial expressions and voice data when the user confirms the judgment result, and the output is the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through the camera and microphone to identify the emotional state (e.g., joy, surprise, sadness, etc.).

[0948] Step 9:

[0949] The device provides appropriate feedback according to the user's emotion recognized by the emotion recognition means. The input is the user's emotional state, and the output is a feedback message. For example, if the user is shocked that the product is determined to be fake, the app will display a comforting message and the next steps to take (e.g., guiding them through the return procedure).

[0950] 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.

[0951] 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.

[0952] 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.

[0953] [Third embodiment]

[0954] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0955] 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.

[0956] 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).

[0957] 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.

[0958] 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.

[0959] 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).

[0960] 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. 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.

[0961] 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.

[0962] 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.

[0963] 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.

[0964] 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.

[0965] 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."

[0966] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[0967] This invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The user uses their smartphone to take a picture of the luxury goods and send it to a server. The server analyzes the received image data and uses AI technology to determine the authenticity. The results are returned to the user and displayed on the smartphone.

[0968] System configuration

[0969] The system is broadly composed of the following components:

[0970] 1. Shooting method (device)

[0971] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button.

[0972] 2. Communication method (terminal → server)

[0973] The captured image data is sent to a server via an Internet connection. Specifically, the image data is uploaded to the server as an HTTP request.

[0974] 3. Preprocessing means (server)

[0975] The server preprocesses the received image data, which includes normalizing, resizing, and removing noise from the image.

[0976] 4. Feature extraction method (server)

[0977] The server extracts features from the pre-processed image data using advanced image recognition algorithms such as convolutional neural networks (CNNs).

[0978] 5. Determination means (server)

[0979] Based on the feature vectors obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[0980] 6. Result transmission method (server → terminal)

[0981] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone via the Internet.

[0982] 7. Result display means (terminal)

[0983] The user's smartphone uses an app that displays the received judgment results, which are rated as "genuine" or "fake," and a detailed report can also be viewed.

[0984] Program processing

[0985] The system process proceeds as follows, with an example:

[0986] Example: Authentication of luxury brand bags

[0987] 1. User - Launches the camera app on the smartphone and takes a photo of a luxury brand bag. For example, the user takes a photo of the entire bag and a detailed image of the logo.

[0988] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[0989] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[0990] 4. Server - Extract features from the preprocessed image data. Using a convolutional neural network (CNN), features such as the position of the logo, the stitching of the bag, and the texture of the material are extracted.

[0991] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[0992] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone, including the evaluation result and reliability of each feature.

[0993] 7. Device - The received judgment result is displayed. The user can confirm the judgment result of "genuine" or "fake" through the app. For example, the report will show an evaluation such as "The logo position is accurate and matches the genuine article."

[0994] As described above, by using the system of the present invention, users can easily determine the authenticity of luxury goods, providing reliability and peace of mind in the luxury goods market.

[0995] The processing flow will be explained below.

[0996] Step 1:

[0997] User - Launches the camera app on the smartphone and takes a picture of a luxury item (e.g., a bag). By pressing the capture button on the camera app, high-resolution image data is acquired.

[0998] Step 2:

[0999] Device - The captured image data is temporarily stored in the device's memory, and a preview of the stored image is displayed, prompting the user for confirmation.

[1000] Step 3:

[1001] Terminal - Prepares communication to send the confirmed image data to the server. Specifically, it compresses the image data appropriately and sends it to the server endpoint in the form of an HTTP request.

[1002] Step 4:

[1003] Server - Temporarily stores the received image data. The server prepares this data for passing to the analysis module.

[1004] Step 5:

[1005] Server - Initiates pre-processing of the image data, which includes denoising the image, color normalizing it, and resizing it to a size suitable for analysis.

[1006] Step 6:

[1007] Server - Extracts features from the pre-processed image data. Convolutional neural networks (CNNs) are used to detect specific features in the image (e.g., logo location, stitching patterns, material textures, etc.).

[1008] Step 7:

[1009] Server - Using the results of feature extraction, the AI ​​model determines the authenticity of the image. The AI ​​model has been trained with a large amount of data in advance, and calculates the probability that the image is genuine or fake based on the extracted features.

[1010] Step 8:

[1011] Server - Generates the assessment results and a detailed report detailing the assessment result and confidence level for each feature.

[1012] Step 9:

[1013] Server - Sends the generated verdicts and reports to the user's device, usually as an HTTP response, and notifies the user in real time.

[1014] Step 10:

[1015] Terminal - Analyzes the received judgment results and displays them on the user interface. Users can check the results and view detailed reports via a smartphone app.

[1016] Step 11:

[1017] Users can review the results and optionally save or share them with others, allowing them to quickly make the right decisions about the authenticity of luxury items.

[1018] Example 1

[1019] 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."

[1020] Counterfeits are rampant in the luxury goods market, and users are seeking a means to easily determine the authenticity of luxury goods. Conventional methods require advanced expertise and special equipment, making them difficult for average users to use. In addition, expert appraisals are time-consuming and expensive, and do not meet modern needs for immediacy. Therefore, there is a need for a system that can quickly and accurately determine the authenticity of luxury goods.

[1021] 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.

[1022] In this invention, the server includes a preprocessing means that receives image data and performs preprocessing such as noise removal, normalization, and resizing, a feature extraction means that extracts features from the preprocessed image data using a convolutional neural network, and a determination means that determines the authenticity of luxury goods using an AI model based on the feature vectors extracted by the feature extraction means. This enables users to easily verify the authenticity of luxury goods in real time.

[1023] "Photographing means" refers to a device or system that a user uses to capture images of luxury items, and includes a smartphone camera or dedicated photographic equipment.

[1024] The "communication means" refers to a mechanism or protocol for transmitting image data captured by the image capturing means to a server, and includes an internet connection, an HTTP request, and the like.

[1025] The "preprocessing means" is a function that performs processes such as noise removal, normalization, and resizing on the image data received by the server, and converts the image data into a format suitable for analysis.

[1026] The "feature extraction means" is a function for extracting useful features from preprocessed image data, and mainly uses algorithms such as convolutional neural networks (CNNs).

[1027] The "determination means" refers to a system or algorithm for determining the authenticity of luxury goods based on the feature vector obtained by the feature extraction means, and an AI model is mainly used.

[1028] The "result transmission means" is a function that allows the server to generate the authenticity determination result and a detailed report and transmit them to the user's terminal.

[1029] The "result display means" is a function that displays the authenticity determination results and detailed reports on the user's terminal, and provides information in a format that is easy for the user to understand.

[1030] An "AI model" is a mathematical model that uses machine learning and deep learning techniques to learn features from large amounts of data and perform highly accurate authenticity determinations.

[1031] A "convolutional neural network (CNN)" is a type of deep learning algorithm specialized in image recognition and feature extraction, which clarifies features by analyzing pixel data extracted from an input image across multiple layers.

[1032] This invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's device (e.g., a smartphone). The user takes a picture of the luxury goods using the device's camera and sends the image to a server. The server then preprocesses the received image data and uses AI technology to determine its authenticity. The results are returned to the user and displayed on the device.

[1033] Hardware and software used

[1034] 1. Device (smartphone)

[1035] Hardware: Smartphone (e.g. iPhone, Android)

[1036] Software: Camera app (e.g. iOS camera app, Google Camera)

[1037] 2. Means of communication

[1038] Network: Internet connection (e.g. Wi-Fi, LTE)

[1039] Communication library: HTTP communication library (e.g., OkHttp, Retrofit)

[1040] 3. Server

[1041] Hardware: Cloud servers (e.g., AWS EC2 instances, Google Cloud Platform GPU instances)

[1042] software:

[1043] Preprocessing library: Image processing library (e.g. OpenCV, Pillow)

[1044] AI / Deep Learning Frameworks: Deep Learning frameworks (e.g. TensorFlow, PyTorch)

[1045] System action

[1046] The system works as follows:

[1047] 1. User operation: The user launches the camera app on their smartphone and takes a picture of a luxury item, for example, taking a full picture of the bag and a detailed shot of the logo.

[1048] Example: A user takes a photo of the logo of a luxury brand bag with their smartphone.

[1049] 2. Image transmission from the device to the server: The device compresses the captured image data and sends it to the server as an HTTP request.

[1050] Example: An Android smartphone takes a picture, compresses it into JPEG format, and sends it to a server using an HTTP POST request.

[1051] 3. Preprocessing on the server: The server performs preprocessing on the received image data, such as noise removal, normalization, and resizing.

[1052] Example: A Python script on a server preprocesses image data using the Pillow library.

[1053] 4. Feature extraction on the server: Features are extracted from the preprocessed image data using a convolutional neural network (CNN).

[1054] Example: Using TensorFlow, a CNN model extracts features from the logo on a bag.

[1055] 5. Authentication on the server: Based on the feature vectors, the AI ​​model determines the authenticity of luxury goods, for example, by checking the placement of logos and stitching patterns.

[1056] Example: A PyTorch-based ResNet model analyzes logo placement and stitching patterns to determine authenticity.

[1057] 6. Sending results from the server to the device: The judgment results and a detailed report are generated and sent to the user's device as an HTTP response.

[1058] Example: As a result of the judgment, a report is generated stating that "The logo position matches precisely and the stitching matches that of the genuine product, so it has been judged to be genuine," and this is sent to the terminal in JSON format.

[1059] 7. Displaying results on the terminal: Displaying the received judgment results and providing a detailed report to the user.

[1060] Example: The dedicated verification app displays the results, stating that "the logo position is accurate and matches the genuine article."

[1061] Examples and prompts

[1062] Example: Authentication of luxury brand bags

[1063] The user launches the smartphone's camera app and takes a photo of the bag's overall appearance and the logo. The smartphone then compresses the image data and sends it as an HTTP request to the server. The server preprocesses the received image data and uses CNN to extract features such as the logo and stitching. Based on these features, the AI ​​model determines whether the bag is authentic or not, and generates and returns the results and a detailed report to the user. Finally, the smartphone displays the results, allowing the user to view the "genuine" or "fake" rating and detailed report.

[1064] Prompt Sentence Examples

[1065] "To determine the authenticity of a luxury brand bag, you take a photo of the entire bag and the logo with your smartphone and send the image to our server. The server preprocesses the image, extracts features using CNN, and then uses an AI model to make a determination. You can then check the determination results and a detailed report on your smartphone."

[1066] The present invention enables users to easily and quickly verify the authenticity of luxury goods, providing reliability and peace of mind in the luxury goods market.

[1067] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1068] Step 1:

[1069] User-generated photos

[1070] A user starts the camera app on their smartphone and takes a picture of a luxury item. For example, the user takes a picture of the entire luxury brand bag and the logo. The input at this stage is the start of the camera and the selection of the subject, and the output is the captured image data.

[1071] Step 2:

[1072] Sending images from the device to the server

[1073] The device compresses the captured image data and sends it as an HTTP request to a server via the Internet. The input is the captured image data, and the output is the compressed image data and its HTTP request. Specifically, the device compresses the image into JPEG format and sends it using an HTTP POST request.

[1074] Step 3:

[1075] Preprocessing on the server

[1076] The server reads the received image data and performs preprocessing such as noise removal, normalization, and resizing. The input of this step is compressed image data, and the output is preprocessed image data. Specifically, a Python script on the server uses the Pillow library to resize the image appropriately and remove noise.

[1077] Step 4:

[1078] Feature extraction on the server

[1079] The server extracts features from the preprocessed image data using a convolutional neural network (CNN). The input of this step is the preprocessed image data, and the output is a feature vector. For example, using TensorFlow, a CNN model extracts features such as the logo and stitching of a bag.

[1080] Step 5:

[1081] Authentication on the server

[1082] The server uses an AI model to determine the authenticity of luxury goods based on the extracted feature vectors. The input for this step is the feature vector, and the output is the authenticity determination result. Specifically, a PyTorch-based ResNet model analyzes the position of the logo and the stitching pattern to determine authenticity.

[1083] Step 6:

[1084] Sending results from the server to the device

[1085] The server generates the judgment result and a detailed report and sends them to the user's device as an HTTP response. The input to this step is the authenticity judgment result, and the output is a detailed report and its HTTP response. Specifically, the judgment result is converted to JSON format and sent.

[1086] Step 7:

[1087] Displaying results on your device

[1088] The device displays the received judgment result and provides it to the user. The input of this step is the detailed report received from the server, and the output is the judgment result displayed to the user. Specifically, the dedicated verification app displays the judgment result and a detailed report, informing the user that "the logo position is accurate and matches the genuine article."

[1089] (Application example 1)

[1090] 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."

[1091] Conventional systems for determining the authenticity of luxury goods are primarily designed for online use, and have the problem of difficulty in quickly and accurately determining authenticity in physical stores. In particular, there is a need to be able to instantly determine the authenticity of luxury goods when they are being explained to customers in physical stores, and to provide customers with highly reliable information. In addition, from the perspective of the devices used, there is a need to improve the work efficiency of store clerks by utilizing smart glasses and head-mounted displays.

[1092] 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.

[1093] In this invention, the server includes a photographing means for a user to photograph luxury goods, a communication means for transmitting image data photographed by the photographing means to the server, a server-side preprocessing means for receiving and preprocessing the image data, a feature extraction means for extracting features from the preprocessed image data, a determination means for determining the authenticity of the luxury goods based on the features extracted by the feature extraction means, a result transmission means for generating the determination results and a detailed report and transmitting them to the user's terminal, a result display means for displaying the results on the user's terminal and saving or sharing them, and a means for photographing the luxury goods and displaying the determination results via smart glasses or a head-mounted display in a physical store, thereby enabling fast and accurate authenticity determination in a physical store.

[1094] "Luxury goods" generally refer to items that are expensive, rare, and made using high-quality materials and sophisticated craftsmanship.

[1095] "Authenticity" refers to determining whether something is genuine or fake.

[1096] A "system" is a collective term for multiple components or means combined to achieve a specific function or purpose.

[1097] "Photographing means" refers to a camera or other photographing device that a user uses to photograph luxury items.

[1098] "Communication means" refers to an internet connection or other data transmission means for sending captured image data to a server.

[1099] The "preprocessing means" refers to a processing means on the server that performs preprocessing such as noise removal, normalization, and resizing on the received image data.

[1100] "Feature extraction means" refers to an algorithm or device for extracting product-specific features from pre-processed image data.

[1101] "Determination means" refers to an AI model or algorithm for determining the authenticity of luxury goods based on the features extracted by the feature extraction means.

[1102] "Result transmission means" refers to a communication means for generating a detailed report of the judgment results and transmitting them to the user's terminal.

[1103] "Result display means" refers to the user interface or software for displaying results on the user's terminal and saving or sharing the results.

[1104] "Smart glasses" refers to a wearable device that has display and camera functions and can send and receive data when worn by the user.

[1105] A "head-mounted display" refers to a display device that provides visual information when worn by a user on the head.

[1106] "Internet connection" refers to a network connection for uploading image data to a server via a communication means.

[1107] "Determination result" refers to the result of the AI ​​model determining the authenticity of a luxury item.

[1108] A "detailed report" refers to a report that details the evaluation results and reliability of each feature based on the judgment results.

[1109] System configuration

[1110] The system of the present invention is designed to determine the authenticity of luxury goods and can be used in brick-and-mortar stores. The system consists of the following components:

[1111] 1. Imaging method (smart glasses or head-mounted display)

[1112] The user wears smart glasses or a head-mounted display and takes a photo of a luxury item. The device has a built-in camera, allowing the product to be photographed naturally from the user's point of view.

[1113] 2. Communication method (Wi-Fi, etc.)

[1114] The captured image data is sent to a server via Wi-Fi, using an internet connection as the communication method, and the data is compressed before being sent.

[1115] 3. Preprocessing method (server side)

[1116] The server preprocesses the received image data, which includes normalizing, resizing, and removing noise, converting the image into a suitable format for subsequent analysis.

[1117] 4. Feature extraction method (server side)

[1118] The server extracts features from the preprocessed image data using a convolutional neural network (CNN) to extract product-specific features (e.g., logo position, stitching pattern, material texture).

[1119] 5. Judgment method (server side)

[1120] Based on the features obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[1121] 6. Result transmission method (server → terminal)

[1122] The server generates a detailed report with the results and transmits it to the user's smart glasses or head-mounted display via Wi-Fi.

[1123] 7. Display of results (smart glasses or head-mounted display)

[1124] The user's device displays the received judgment results, which are instantly displayed as "genuine" or "fake," and a detailed report can also be viewed.

[1125] Specific processing of the program

[1126] As an example of a physical store, we will demonstrate how the system works in a store that sells luxury brand watches. A salesperson wears smart glasses or a head-mounted display and takes a photo of the watch case or dial. The image data is sent to a server via Wi-Fi, where it is normalized and resized by pre-processing. Features are then extracted using a convolutional neural network (CNN), and an AI model makes a judgment. The judgment result is then sent back to the device via Wi-Fi, where the salesperson can check it on the spot.

[1127] The required hardware includes smart glasses (e.g., Google Glass) or a head-mounted display (e.g., Microsoft HoloLens), and the server side requires a high-performance GPU. The software includes machine learning libraries such as Python and TensorFlow.

[1128] Specific examples

[1129] For example, in a store selling luxury brand watches, a salesperson uses smart glasses to take a photo of the watch case or dial. The image data is sent to a server via Wi-Fi and preprocessed. Features are then extracted using CNN, and an AI model determines its authenticity. The result, "This watch is genuine," is displayed on the smart glasses.

[1130] Prompt Sentence Examples

[1131] Prompt: "This image is of a luxury brand watch case. Use a convolutional neural network to determine whether it is authentic. Consider the shape of the case, the placement of the numerals on the dial, and the texture of the material as characteristics."

[1132] In this way, by using the system of the present invention, it becomes possible to quickly and accurately determine the authenticity of luxury goods even in physical stores, thereby realizing the provision of highly reliable information to customers.

[1133] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1134] Step 1:

[1135] The user wears smart glasses or a head-mounted display and takes pictures of luxury items.

[1136] Input: Images of luxury items captured through a camera built into smart glasses or a head-mounted display

[1137] Output: Image data of the luxury item photographed

[1138] Action: The user activates the camera and takes a picture of a specific part (such as the case or dial) of a luxury item (e.g., a luxury brand watch).

[1139] Step 2:

[1140] The device sends the captured image data to a server via Wi-Fi.

[1141] Input: Image data of the luxury item photographed

[1142] Output: Image data sent to the server

[1143] How it works: The communication module inside the device compresses the image data and uploads it to the server as an HTTP request.

[1144] Step 3:

[1145] The server pre-processes the received image data.

[1146] Input: Image data sent to the server

[1147] Output: Preprocessed image data (normalized, resized, and denoised)

[1148] How it works: A program on the server normalizes the image data, resizes it to a consistent size, and denoises it, using an image processing library such as OpenCV.

[1149] Step 4:

[1150] The server extracts features from the preprocessed image data.

[1151] Input: Preprocessed image data

[1152] Output: Feature vector

[1153] How it works: It uses a server-based convolutional neural network (CNN) to extract features from images, using machine learning frameworks such as TensorFlow and Keras.

[1154] Step 5:

[1155] The server determines the authenticity of the luxury item based on the features obtained by the feature extraction means.

[1156] Input: feature vector

[1157] Output: Verification result (e.g. "Genuine", "Fake")

[1158] How it works: The AI ​​model analyzes feature vectors and determines authenticity based on a pre-trained dataset.

[1159] Step 6:

[1160] The server generates a detailed report with the results of the assessment and sends it to the user's terminal.

[1161] Input: Judgment results, detailed report elements (e.g., evaluation of logo position and material texture)

[1162] Output: Verification results and detailed report

[1163] How it works: The server generates a text report with the results and a detailed report, which it then sends back to the user's device via Wi-Fi.

[1164] Step 7:

[1165] The terminal displays the received judgment result.

[1166] Input: Verification results and detailed report

[1167] Output: Judgment results and detailed reports displayed on smart glasses or a head-mounted display

[1168] How it works: Using the device's display function, the result is displayed as "genuine" or "fake," and a detailed report can also be viewed.

[1169] 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.

[1170] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[1171] The present invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The present invention also combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[1172] System configuration

[1173] The system is broadly composed of the following components:

[1174] 1. Shooting method (device)

[1175] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button.

[1176] 2. Communication method (terminal → server)

[1177] The captured image data is sent to a server over an internet connection, specifically as an HTTP request to a server endpoint.

[1178] 3. Preprocessing means (server)

[1179] The server preprocesses the received image data, which includes removing noise from the image, normalizing the color, and resizing it to a size suitable for analysis.

[1180] 4. Feature extraction method (server)

[1181] The server extracts features from the pre-processed image data using advanced image recognition algorithms such as convolutional neural networks (CNNs).

[1182] 5. Determination means (server)

[1183] Based on the feature vectors obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[1184] 6. Result transmission method (server → terminal)

[1185] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone via the Internet.

[1186] 7. Result display means (terminal)

[1187] The user's smartphone uses an app that displays the received judgment results. The result is displayed as "genuine" or "fake," and a detailed report can be viewed. The app also incorporates an emotion engine that recognizes the user's emotions.

[1188] 8. Emotion Engine (Terminal)

[1189] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[1190] 9. Feedback means (terminal)

[1191] The emotion engine recognizes the user's emotions and then provides feedback based on those emotions. For example, if the user is shocked that the product is identified as fake, it will display a message of comfort and the next steps to take (e.g., guiding them through the return process).

[1192] Program processing

[1193] The system process proceeds as follows, with an example:

[1194] Example: Authentication of luxury brand bags and user emotion recognition

[1195] 1. User - Launches the camera app on the smartphone and takes a photo of a luxury brand bag. For example, the user takes a photo of the entire bag and a detailed image of the logo.

[1196] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[1197] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[1198] 4. Server - Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[1199] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[1200] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone. The report details the evaluation result and its reliability for each feature.

[1201] 7. Device - Displays the received judgment result. The user can check the judgment result of "genuine" or "fake" through the app. A detailed report can also be viewed.

[1202] 8. Device - While the user is checking the result, the emotion engine analyzes the user's facial expressions and voice. For example, if the user is surprised, the camera captures and analyzes their facial expression.

[1203] 9. Device - Feedback is generated based on emotions. For example, if the user is surprised, the message "You seem surprised. Don't worry, we'll provide you with more information."

[1204] 10. User - Review the results and feedback and decide on the next action. For example, if the bag is determined to be fake, they will be provided with information to proceed with the return process.

[1205] In this way, the present invention allows users to easily determine the authenticity of luxury items, and further improves the user experience by providing feedback according to the user's emotional state.

[1206] The processing flow will be explained below.

[1207] Step 1:

[1208] User - Launches the camera app on the smartphone and takes a picture of a luxury item (e.g., a designer bag). By pressing the capture button on the camera app, high-resolution image data is acquired.

[1209] Step 2:

[1210] Device - The acquired image data is temporarily stored in the device's memory, and a preview of the stored image is displayed, prompting the user for confirmation.

[1211] Step 3:

[1212] Device - Begin preparing to send the verified image data to the server. The image data is appropriately compressed and sent to the server endpoint in the form of an HTTP request. Specifically, the request is generated with the following information:

[1213] User ID

[1214] Image data

[1215] timestamp

[1216] Step 4:

[1217] Server - Receives and temporarily stores the image data sent to it. The server prepares the data for passing to the analysis module and checks the integrity of the data.

[1218] Step 5:

[1219] Server - Initiates preprocessing of the image data. This preprocessing includes denoising the image, color normalizing it, and resizing it to a size suitable for analysis. Specific tasks include:

[1220] Normalizing pixel values

[1221] Noise removal using a Gaussian filter

[1222] Resize

[1223] Step 6:

[1224] Server - Extracts features from the pre-processed image data. Convolutional neural networks (CNNs) are used to detect specific features in the image (e.g., logo location, stitching patterns, material textures, etc.).

[1225] Step 7:

[1226] Server - Using the results of feature extraction, the AI ​​model determines the authenticity of the image. The AI ​​model has been trained with a large amount of data in advance, and calculates the probability of whether an image is genuine or fake based on the extracted feature vector. The specific evaluation is as follows:

[1227] Does the logo shape and placement match the genuine product?

[1228] Do the stitch patterns match?

[1229] Is the texture of the material the same?

[1230] Step 8:

[1231] Server - Generates the assessment results and a detailed report detailing the assessment results and confidence levels for each feature, as well as the analysis of the images used to make the assessment.

[1232] Step 9:

[1233] Server - Sends generated verdicts and reports to the user's device, usually as HTTP responses, notifying the user in real time.

[1234] Step 10:

[1235] Device - Analyzes the received results and displays them in the user interface. The app displays a summary of the results and a detailed report for easy review by the user. Specifically, it displays the following information:

[1236] Verification result (genuine / fake)

[1237] Detailed characterization

[1238] Report download link

[1239] Step 11:

[1240] On your device - While you are checking your results, the app will use your smartphone's camera and microphone to analyze your facial expressions and voice with its emotion engine. This includes:

[1241] Face detection and facial expression analysis

[1242] Voice tone and pitch analysis

[1243] Step 12:

[1244] Terminal - Based on the analysis results of the emotion engine, identify the user's emotional state (e.g., joy, surprise, sadness, etc.) and generate a feedback message according to the emotional state.

[1245] Step 13:

[1246] Terminal - Display feedback to the user based on their emotions. For example, if the user is surprised, display "I see you're surprised. We'll provide you with more information, so don't worry." If the user is shocked, provide a comforting message or instructions on what to do next (e.g., instructions on how to return the product).

[1247] Step 14:

[1248] User - Review the results and feedback and decide on the next action. For example, if the bag is determined to be counterfeit, view information to proceed with the return process.

[1249] Example 2

[1250] 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."

[1251] Determining the authenticity of luxury goods requires expert knowledge and skills, making it difficult for users without advanced expertise. Furthermore, appropriately responding to the user's emotional reaction when receiving the results is important for improving the user experience. Given this situation, the present invention aims to provide a system that easily determines the authenticity of luxury goods and provides feedback based on the user's emotional state.

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

[1253] In this invention, the server includes a means for receiving and preprocessing image data, a means for extracting features from the preprocessed image data, and a means for determining the authenticity of an item based on the extracted features, thereby enabling highly accurate authentication and appropriate feedback based on the user's emotions.

[1254] "Photographing means" refers to a smartphone camera or other imaging device that a user uses to photograph an item.

[1255] The "communication means" refers to a means for transmitting image data acquired by the photographing means to a server via an Internet connection, and specifically, uses a protocol such as an HTTP request.

[1256] "Preprocessing means" refers to the process of performing noise removal, color normalization, resizing, etc. on the image data received on the server side and converting it into a format suitable for analysis.

[1257] "Feature extraction means" refers to algorithms and hardware for extracting article features (e.g., logo location, stitching pattern, material texture, etc.) from pre-processed image data.

[1258] "Determination means" refers to an AI model or algorithm that determines the authenticity of an item based on the features obtained by the feature extraction means.

[1259] The "result transmission means" is a means for generating the judgment results and a detailed report and transmitting them to the user's terminal, and utilizes an internet connection.

[1260] "Result display means" refers to an application or interface for displaying the assessment results and detailed reports on the user's device and saving or sharing them.

[1261] "Emotion recognition means" refers to hardware and software for identifying the emotional state of a user by analyzing the facial expression, voice, etc. of the user checking the judgment result.

[1262] The "feedback means" refers to software for generating appropriate feedback based on the emotion recognized by the emotion recognition means and providing it to the user.

[1263] The present invention is a system for determining the authenticity of luxury goods. This system operates primarily on the user's smartphone and combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[1264] System configuration

[1265] The system is broadly composed of the following components:

[1266] 1. Shooting method (device)

[1267] The user takes a photo of the luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button. Specifically, a high-definition camera or a standard camera on the smartphone can be used.

[1268] 2. Communication method (terminal → server)

[1269] The captured image data is sent to a server via an internet connection. Specifically, the image data is sent as an HTTP request to the server endpoint. HTTPS is the recommended communication protocol.

[1270] 3. Preprocessing means (server)

[1271] The server preprocesses the received image data, which includes removing noise, color normalizing, and resizing the image to a size suitable for analysis. Specifically, median filtering and histogram equalization are applied.

[1272] 4. Feature extraction method (server)

[1273] The server extracts features from the pre-processed image data using a sophisticated image recognition algorithm called a convolutional neural network (CNN), such as the location of logos, stitching patterns, and material textures.

[1274] 5. Determination means (server)

[1275] Based on the feature vectors obtained by the feature extraction method, an AI model determines the authenticity of luxury goods. This AI model has been trained on a large dataset in advance, enabling highly accurate judgment. For example, it evaluates whether the luxury brand logo or stitching pattern matches that of the genuine product.

[1276] 6. Result transmission method (server → terminal)

[1277] The server generates a detailed report of the results and sends it to the user's smartphone via the Internet. The report details the evaluation results and their reliability for each feature.

[1278] 7. Result display means (terminal)

[1279] The user's smartphone uses an app that displays the received judgment results, which are rated as "genuine" or "fake," and a detailed report can also be viewed.

[1280] 8. Emotion recognition means (terminal)

[1281] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[1282] 9. Feedback means (terminal)

[1283] The emotion engine recognizes the user's emotions and then provides feedback based on those emotions. For example, if the user is shocked that the product is identified as fake, it will display a message of comfort and the next steps to take (e.g., guiding them through the return process).

[1284] Specific examples

[1285] Example: Authentication of luxury brand bags and user emotion recognition

[1286] 1. User - Launches the smartphone camera app and takes a photo of a luxury brand bag, taking a full view of the bag and a detailed view of the logo.

[1287] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[1288] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[1289] 4. Server - Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[1290] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[1291] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone. The report details the evaluation result and its reliability for each feature.

[1292] 7. Device - The received judgment results are displayed in the app, and the user can check the "genuine" or "fake" judgment results and report.

[1293] 8. Device - While the user is checking the result, the emotion engine analyzes the user's facial expressions and voice. For example, if the user is surprised, the camera captures and analyzes their facial expression.

[1294] 9. Device - Generate feedback based on emotions. For example, if the user is surprised, display a message like "I see you're surprised. Don't worry, we'll provide you with more information."

[1295] Examples of typical prompt statements

[1296] "Explain the outline of a system that uses AI to determine the authenticity of a luxury brand bag using an image taken by the user, and then describe the entire process of recognizing the user's emotions and providing feedback."

[1297] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1298] Step 1:

[1299] The user launches the camera app on their smartphone and takes a picture of the luxury item.

[1300] Input: Item (e.g. luxury brand bag)

[1301] Output: Captured image data (high-resolution image)

[1302] What happens: The user points the camera at a luxury item, focuses it, and takes a photo in a well-lit area, capturing both the overall image of the bag and the details (logo, stitching, etc.).

[1303] Step 2:

[1304] The terminal transmits the captured image data to a server via the Internet.

[1305] Input: Captured image data

[1306] Output: Image data sent as an HTTP request

[1307] Specific behavior: The device compresses and encodes the image data, generates an HTTP POST request, and sends it to the server endpoint.

[1308] Step 3:

[1309] The server pre-processes the received image data.

[1310] Input: Received image data

[1311] Output: Preprocessed image data

[1312] Specific operation: The server performs noise removal (median filtering) on ​​the received image data, then performs color normalization (histogram equalization), and resizes it to a size suitable for analysis.

[1313] Step 4:

[1314] The server extracts features from the preprocessed image data.

[1315] Input: Preprocessed image data

[1316] Output: feature vector

[1317] How it works: The server uses a convolutional neural network (CNN) to extract important features in the image (such as the position of the logo, the stitching pattern, and the texture of the material) and represents these features as a feature vector.

[1318] Step 5:

[1319] The server uses an AI model to determine authenticity based on the feature vector obtained by the feature extraction means.

[1320] Input: feature vector

[1321] Output: Verification result (e.g. "Genuine" or "Fake")

[1322] How it works: The server inputs the feature vector into a trained AI model, which then makes a judgment, such as whether the logo position matches that of the genuine product or whether the stitching pattern matches that of the genuine product.

[1323] Step 6:

[1324] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone.

[1325] Input: Judgment result, feature vector and analysis result

[1326] Output: Verification report (including detailed evaluation results)

[1327] How it works: The server generates a report based on the results, detailing the evaluation result and confidence level for each feature. This report is securely sent to the device using HTTPS.

[1328] Step 7:

[1329] The terminal displays the received judgment result.

[1330] Input: Adjudication Report

[1331] Output: Displayed judgment results and detailed report

[1332] Specific operation: The device application displays the result of the judgment (e.g., "genuine" or "fake") to the user and allows them to view a detailed report.

[1333] Step 8:

[1334] The terminal recognizes the emotion of the user who is checking the judgment result.

[1335] Input: User's facial expression and voice data

[1336] Output: Recognized emotional state (e.g., happy, surprised, sad, etc.)

[1337] How it works: The device captures the user's facial expressions and voice through the camera and microphone, and uses facial recognition and voice analysis algorithms to identify their emotional state.

[1338] Step 9:

[1339] The device generates and displays feedback based on the recognized emotion.

[1340] Input: Perceived emotional state

[1341] Output: Feedback message

[1342] Specific operation: Based on the emotion recognition results, the device generates an appropriate message. For example, if the user is surprised, the device will display the message, "You seem surprised. Don't worry, we will provide you with more information."

[1343] (Application example 2)

[1344] 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."

[1345] Determining the authenticity of luxury goods is important to consumers, but it is difficult to do so quickly and accurately on-site. It is also necessary to provide appropriate feedback based on the user's reaction to the authentication results. Conventional systems have struggled to meet these needs, resulting in insufficient improvement in the user experience. Therefore, there is a need for a system that can quickly determine the authenticity of luxury goods and provide feedback based on the user's emotions.

[1346] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a preprocessing means, a feature extraction means, and a determination means. This makes it possible to quickly and accurately determine the authenticity of luxury goods. In addition, by using an emotion recognition means that recognizes the user's emotion and a result transmission means that transmits and displays the results on the user terminal, it is possible to provide appropriate feedback to the user and improve the user experience.

[1347] The "photography means" refers to a device that allows a user to photograph luxury items, specifically a smartphone camera or other image capture device.

[1348] The "communication means" is a means for transmitting image data captured by the image capturing means to a server, and is a device that includes a function for uploading data via an internet connection.

[1349] The "preprocessing means" is a device or software that receives image data on the server side and performs preprocessing such as noise removal and color normalization.

[1350] A "feature extraction means" is a means for extracting specific features from preprocessed image data, and is a device or software that includes an algorithm such as a convolutional neural network (CNN).

[1351] The "determination means" refers to a device or software that includes an AI model or algorithm for determining the authenticity of luxury goods based on the features extracted by the feature extraction means.

[1352] The "result transmission means" is a device or software that generates a detailed report of the judgment results and transmits them to the user's terminal.

[1353] The "result display means" is an application or interface for displaying the judgment results on the user's terminal and saving or sharing them.

[1354] The "emotion recognition means" is a device or software that uses a camera or microphone to analyze facial expressions and voice in order to recognize the user's emotions.

[1355] The "feedback means" is a means for generating and displaying appropriate feedback in accordance with the user's emotion recognized by the emotion recognition means.

[1356] The following describes an embodiment of the present invention. The present invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The present invention also combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[1357] Program processing overview

[1358] The system consists of the following components:

[1359] 1. Filming Method

[1360] 2. Means of communication

[1361] 3. Server-side preprocessing methods

[1362] 4. Feature Extraction Method

[1363] 5. Judgment means

[1364] 6. Means of sending results

[1365] 7. Results display means

[1366] 8. Emotion recognition means

[1367] 9. Feedback channels

[1368] Description of each component

[1369] Filming method

[1370] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button. The captured image is saved with appropriate image quality and resolution for analysis.

[1371] communication means

[1372] The captured image data is sent to a server via an internet connection. The image data is compressed and sent as an HTTP request to the server endpoint. This communication method ensures fast and reliable data transfer.

[1373] Server-side preprocessing measures

[1374] The server preprocesses the received image data, including removing noise, normalizing the color, and resizing the image to a size suitable for analysis. This ensures consistent image quality and facilitates processing by the feature extraction tool.

[1375] Feature Extraction Method

[1376] Features are extracted from the pre-processed image data. This process uses a convolutional neural network (CNN) as an advanced image recognition algorithm. The feature extraction method extracts important features from the image data, such as the position of the logo, seams, and the texture of the material.

[1377] Judgment means

[1378] Based on the feature vectors obtained by the feature extraction method, the AI ​​model determines the authenticity of luxury goods. The AI ​​model is trained on a large amount of data in advance, enabling highly accurate judgment. For example, it evaluates whether the logo is positioned correctly and whether the stitching pattern matches that of the genuine product.

[1379] Result transmission method

[1380] The server generates a detailed report of the results and sends it to the user's smartphone, which includes the evaluation results and their reliability for each feature.

[1381] Results display means

[1382] The user's smartphone uses an app that displays the received judgment results, allowing the user to confirm the "genuine" or "fake" rating and view a detailed report.

[1383] emotion recognition means

[1384] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[1385] Feedback Methods

[1386] After the emotion recognition means recognizes the user's emotion, it provides feedback according to that emotion. For example, if the user is shocked that the product is determined to be fake, it displays a message of comfort and the next steps to take (e.g., guidance on the return procedure).

[1387] Specific examples

[1388] Below are some examples of authenticating luxury brand bags and recognizing user emotions:

[1389] 1. The user launches the camera app on their smartphone and takes a photo of a luxury brand bag. For example, they take a photo of the entire bag and a detailed image of the logo.

[1390] 2. The captured image data is sent to the server as an HTTP request via the internet connection.

[1391] 3. The server preprocesses the received image data, removing noise and normalizing the image, and converts it into a format suitable for analysis.

[1392] 4. Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[1393] 5. Based on the extracted features, the AI ​​model determines the authenticity of the bag, assessing whether the logo is correctly positioned, whether the stitching pattern matches, etc.

[1394] Prompt Sentence Examples

[1395] Develop an app that uses a smartphone camera to take a photo of a luxury item (e.g., a designer bag) and sends the image to a server to determine its authenticity. After determining authenticity, please include a function that recognizes the user's emotions and provides appropriate feedback.

[1396] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1397] Step 1:

[1398] A user launches the camera app on their smartphone and takes a picture of a luxury item. The captured image is the input, and the image data is output. The user presses the capture button on the camera app to take a picture of the entire product (e.g., a designer bag) and important logo details.

[1399] Step 2:

[1400] The device sends the captured image data to the server. The input is the image data acquired in step 1, and the output is the image data as an HTTP request to the server. The image data from the smartphone is compressed and sent to the specified server endpoint via the network.

[1401] Step 3:

[1402] The server preprocesses the image data it receives. The input is the image data sent to the server, and the output is the preprocessed image data. Preprocessing includes noise removal, color normalization, and resizing. This stabilizes the quality of the image data and makes subsequent processing easier.

[1403] Step 4:

[1404] The server extracts features from the preprocessed image data. The input is the preprocessed image data, and the output is a feature vector. Using a convolutional neural network (CNN), features such as the position of the logo, the stitching of the bag, and the texture of the material are extracted.

[1405] Step 5:

[1406] The server determines the authenticity of luxury goods based on the feature vector obtained by the feature extraction means. The input is the feature vector obtained by the feature extraction means, and the output is the authenticity determination result. An AI model is used to evaluate whether the logo is positioned correctly and whether the stitching pattern matches that of the genuine product, and to determine authenticity.

[1407] Step 6:

[1408] The server generates the judgment result and a detailed report and sends them to the user's device. The input is the authenticity judgment result, and the output is a detailed report and the judgment result data. The judgment result is compiled into a report and sent to the user's device via the Internet.

[1409] Step 7:

[1410] The device displays the received judgment results. The input is the judgment result and detailed report sent from the server, and the output is a screen display that can be viewed by the user. The user can check the results through the app and view the "genuine" or "fake" rating and detailed report.

[1411] Step 8:

[1412] The device recognizes the user's emotions. The input is facial expressions and voice data when the user confirms the judgment result, and the output is the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through the camera and microphone to identify the emotional state (e.g., joy, surprise, sadness, etc.).

[1413] Step 9:

[1414] The device provides appropriate feedback according to the user's emotion recognized by the emotion recognition means. The input is the user's emotional state, and the output is a feedback message. For example, if the user is shocked that the product is determined to be fake, the app will display a comforting message and the next steps to take (e.g., guiding them through the return procedure).

[1415] 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.

[1416] 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.

[1417] 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.

[1418] [Fourth embodiment]

[1419] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1420] 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.

[1421] 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).

[1422] 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.

[1423] 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.

[1424] 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).

[1425] 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. 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.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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."

[1432] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[1433] This invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The user uses their smartphone to take a picture of the luxury goods and send it to a server. The server analyzes the received image data and uses AI technology to determine the authenticity. The results are returned to the user and displayed on the smartphone.

[1434] System configuration

[1435] The system is broadly composed of the following components:

[1436] 1. Shooting method (device)

[1437] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button.

[1438] 2. Communication method (terminal → server)

[1439] The captured image data is sent to a server via an Internet connection. Specifically, the image data is uploaded to the server as an HTTP request.

[1440] 3. Preprocessing means (server)

[1441] The server preprocesses the received image data, which includes normalizing, resizing, and removing noise from the image.

[1442] 4. Feature extraction method (server)

[1443] The server extracts features from the pre-processed image data using advanced image recognition algorithms such as convolutional neural networks (CNNs).

[1444] 5. Determination means (server)

[1445] Based on the feature vectors obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[1446] 6. Result transmission method (server → terminal)

[1447] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone via the Internet.

[1448] 7. Result display means (terminal)

[1449] The user's smartphone uses an app that displays the received judgment results, which are rated as "genuine" or "fake," and a detailed report can also be viewed.

[1450] Program processing

[1451] The system process proceeds as follows, with an example:

[1452] Example: Authentication of luxury brand bags

[1453] 1. User - Launches the camera app on the smartphone and takes a photo of a luxury brand bag. For example, the user takes a photo of the entire bag and a detailed image of the logo.

[1454] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[1455] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[1456] 4. Server - Extract features from the preprocessed image data. Using a convolutional neural network (CNN), features such as the position of the logo, the stitching of the bag, and the texture of the material are extracted.

[1457] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[1458] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone, including the evaluation result and reliability of each feature.

[1459] 7. Device - The received judgment result is displayed. The user can confirm the judgment result of "genuine" or "fake" through the app. For example, the report will show an evaluation such as "The logo position is accurate and matches the genuine article."

[1460] As described above, by using the system of the present invention, users can easily determine the authenticity of luxury goods, providing reliability and peace of mind in the luxury goods market.

[1461] The processing flow will be explained below.

[1462] Step 1:

[1463] User - Launches the camera app on the smartphone and takes a picture of a luxury item (e.g., a bag). By pressing the capture button on the camera app, high-resolution image data is acquired.

[1464] Step 2:

[1465] Device - The captured image data is temporarily stored in the device's memory, and a preview of the stored image is displayed, prompting the user for confirmation.

[1466] Step 3:

[1467] Terminal - Prepares communication to send the confirmed image data to the server. Specifically, it compresses the image data appropriately and sends it to the server endpoint in the form of an HTTP request.

[1468] Step 4:

[1469] Server - Temporarily stores the received image data. The server prepares this data for passing to the analysis module.

[1470] Step 5:

[1471] Server - Initiates pre-processing of the image data, which includes denoising the image, color normalizing it, and resizing it to a size suitable for analysis.

[1472] Step 6:

[1473] Server - Extracts features from the pre-processed image data. Convolutional neural networks (CNNs) are used to detect specific features in the image (e.g., logo location, stitching patterns, material textures, etc.).

[1474] Step 7:

[1475] Server - Using the results of feature extraction, the AI ​​model determines the authenticity of the image. The AI ​​model has been trained with a large amount of data in advance, and calculates the probability that the image is genuine or fake based on the extracted features.

[1476] Step 8:

[1477] Server - Generates the assessment results and a detailed report detailing the assessment result and confidence level for each feature.

[1478] Step 9:

[1479] Server - Sends the generated verdicts and reports to the user's device, usually as an HTTP response, and notifies the user in real time.

[1480] Step 10:

[1481] Terminal - Analyzes the received judgment results and displays them on the user interface. Users can check the results and view detailed reports via a smartphone app.

[1482] Step 11:

[1483] Users can review the results and optionally save or share them with others, allowing them to quickly make the right decisions about the authenticity of luxury items.

[1484] Example 1

[1485] 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."

[1486] Counterfeits are rampant in the luxury goods market, and users are seeking a means to easily determine the authenticity of luxury goods. Conventional methods require advanced expertise and special equipment, making them difficult for average users to use. In addition, expert appraisals are time-consuming and expensive, and do not meet modern needs for immediacy. Therefore, there is a need for a system that can quickly and accurately determine the authenticity of luxury goods.

[1487] 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.

[1488] In this invention, the server includes a preprocessing means that receives image data and performs preprocessing such as noise removal, normalization, and resizing, a feature extraction means that extracts features from the preprocessed image data using a convolutional neural network, and a determination means that determines the authenticity of luxury goods using an AI model based on the feature vectors extracted by the feature extraction means. This enables users to easily verify the authenticity of luxury goods in real time.

[1489] "Photographing means" refers to a device or system that a user uses to capture images of luxury items, and includes a smartphone camera or dedicated photographic equipment.

[1490] The "communication means" refers to a mechanism or protocol for transmitting image data captured by the image capturing means to a server, and includes an internet connection, an HTTP request, and the like.

[1491] The "preprocessing means" is a function that performs processes such as noise removal, normalization, and resizing on the image data received by the server, and converts the image data into a format suitable for analysis.

[1492] The "feature extraction means" is a function for extracting useful features from preprocessed image data, and mainly uses algorithms such as convolutional neural networks (CNNs).

[1493] The "determination means" refers to a system or algorithm for determining the authenticity of luxury goods based on the feature vector obtained by the feature extraction means, and an AI model is mainly used.

[1494] The "result transmission means" is a function that allows the server to generate the authenticity determination result and a detailed report and transmit them to the user's terminal.

[1495] The "result display means" is a function that displays the authenticity determination results and detailed reports on the user's terminal, and provides information in a format that is easy for the user to understand.

[1496] An "AI model" is a mathematical model that uses machine learning and deep learning techniques to learn features from large amounts of data and perform highly accurate authenticity determinations.

[1497] A "convolutional neural network (CNN)" is a type of deep learning algorithm specialized in image recognition and feature extraction, which clarifies features by analyzing pixel data extracted from an input image across multiple layers.

[1498] This invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's device (e.g., a smartphone). The user takes a picture of the luxury goods using the device's camera and sends the image to a server. The server then preprocesses the received image data and uses AI technology to determine its authenticity. The results are returned to the user and displayed on the device.

[1499] Hardware and software used

[1500] 1. Device (smartphone)

[1501] Hardware: Smartphone (e.g. iPhone, Android)

[1502] Software: Camera app (e.g. iOS camera app, Google Camera)

[1503] 2. Means of communication

[1504] Network: Internet connection (e.g. Wi-Fi, LTE)

[1505] Communication library: HTTP communication library (e.g., OkHttp, Retrofit)

[1506] 3. Server

[1507] Hardware: Cloud servers (e.g., AWS EC2 instances, Google Cloud Platform GPU instances)

[1508] software:

[1509] Preprocessing library: Image processing library (e.g. OpenCV, Pillow)

[1510] AI / Deep Learning Frameworks: Deep Learning frameworks (e.g. TensorFlow, PyTorch)

[1511] System action

[1512] The system works as follows:

[1513] 1. User operation: The user launches the camera app on their smartphone and takes a picture of a luxury item, for example, taking a full picture of the bag and a detailed shot of the logo.

[1514] Example: A user takes a photo of the logo of a luxury brand bag with their smartphone.

[1515] 2. Image transmission from the device to the server: The device compresses the captured image data and sends it to the server as an HTTP request.

[1516] Example: An Android smartphone takes a picture, compresses it into JPEG format, and sends it to a server using an HTTP POST request.

[1517] 3. Preprocessing on the server: The server performs preprocessing on the received image data, such as noise removal, normalization, and resizing.

[1518] Example: A Python script on a server preprocesses image data using the Pillow library.

[1519] 4. Feature extraction on the server: Features are extracted from the preprocessed image data using a convolutional neural network (CNN).

[1520] Example: Using TensorFlow, a CNN model extracts features from the logo on a bag.

[1521] 5. Authentication on the server: Based on the feature vectors, the AI ​​model determines the authenticity of luxury goods, for example, by checking the placement of logos and stitching patterns.

[1522] Example: A PyTorch-based ResNet model analyzes logo placement and stitching patterns to determine authenticity.

[1523] 6. Sending results from the server to the device: The judgment results and a detailed report are generated and sent to the user's device as an HTTP response.

[1524] Example: As a result of the judgment, a report is generated stating that "The logo position matches precisely and the stitching matches that of the genuine product, so it has been judged to be genuine," and this is sent to the terminal in JSON format.

[1525] 7. Displaying results on the terminal: Displaying the received judgment results and providing a detailed report to the user.

[1526] Example: The dedicated verification app displays the results, stating that "the logo position is accurate and matches the genuine article."

[1527] Examples and prompts

[1528] Example: Authentication of luxury brand bags

[1529] The user launches the smartphone's camera app and takes a photo of the bag's overall appearance and the logo. The smartphone then compresses the image data and sends it as an HTTP request to the server. The server preprocesses the received image data and uses CNN to extract features such as the logo and stitching. Based on these features, the AI ​​model determines whether the bag is authentic or not, and generates and returns the results and a detailed report to the user. Finally, the smartphone displays the results, allowing the user to view the "genuine" or "fake" rating and detailed report.

[1530] Prompt Sentence Examples

[1531] "To determine the authenticity of a luxury brand bag, you take a photo of the entire bag and the logo with your smartphone and send the image to our server. The server preprocesses the image, extracts features using CNN, and then uses an AI model to make a determination. You can then check the determination results and a detailed report on your smartphone."

[1532] The present invention enables users to easily and quickly verify the authenticity of luxury goods, providing reliability and peace of mind in the luxury goods market.

[1533] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1534] Step 1:

[1535] User-generated photos

[1536] A user starts the camera app on their smartphone and takes a picture of a luxury item. For example, the user takes a picture of the entire luxury brand bag and the logo. The input at this stage is the start of the camera and the selection of the subject, and the output is the captured image data.

[1537] Step 2:

[1538] Sending images from the device to the server

[1539] The device compresses the captured image data and sends it as an HTTP request to a server via the Internet. The input is the captured image data, and the output is the compressed image data and its HTTP request. Specifically, the device compresses the image into JPEG format and sends it using an HTTP POST request.

[1540] Step 3:

[1541] Preprocessing on the server

[1542] The server reads the received image data and performs preprocessing such as noise removal, normalization, and resizing. The input of this step is compressed image data, and the output is preprocessed image data. Specifically, a Python script on the server uses the Pillow library to resize the image appropriately and remove noise.

[1543] Step 4:

[1544] Feature extraction on the server

[1545] The server extracts features from the preprocessed image data using a convolutional neural network (CNN). The input of this step is the preprocessed image data, and the output is a feature vector. For example, using TensorFlow, a CNN model extracts features such as the logo and stitching of a bag.

[1546] Step 5:

[1547] Authentication on the server

[1548] The server uses an AI model to determine the authenticity of luxury goods based on the extracted feature vectors. The input for this step is the feature vector, and the output is the authenticity determination result. Specifically, a PyTorch-based ResNet model analyzes the position of the logo and the stitching pattern to determine authenticity.

[1549] Step 6:

[1550] Sending results from the server to the device

[1551] The server generates the judgment result and a detailed report and sends them to the user's device as an HTTP response. The input to this step is the authenticity judgment result, and the output is a detailed report and its HTTP response. Specifically, the judgment result is converted to JSON format and sent.

[1552] Step 7:

[1553] Displaying results on your device

[1554] The device displays the received judgment result and provides it to the user. The input of this step is the detailed report received from the server, and the output is the judgment result displayed to the user. Specifically, the dedicated verification app displays the judgment result and a detailed report, informing the user that "the logo position is accurate and matches the genuine article."

[1555] (Application example 1)

[1556] 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."

[1557] Conventional systems for determining the authenticity of luxury goods are primarily designed for online use, and have the problem of difficulty in quickly and accurately determining authenticity in physical stores. In particular, there is a need to be able to instantly determine the authenticity of luxury goods when they are being explained to customers in physical stores, and to provide customers with highly reliable information. In addition, from the perspective of the devices used, there is a need to improve the work efficiency of store clerks by utilizing smart glasses and head-mounted displays.

[1558] 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.

[1559] In this invention, the server includes a photographing means for a user to photograph luxury goods, a communication means for transmitting image data photographed by the photographing means to the server, a server-side preprocessing means for receiving and preprocessing the image data, a feature extraction means for extracting features from the preprocessed image data, a determination means for determining the authenticity of the luxury goods based on the features extracted by the feature extraction means, a result transmission means for generating the determination results and a detailed report and transmitting them to the user's terminal, a result display means for displaying the results on the user's terminal and saving or sharing them, and a means for photographing the luxury goods and displaying the determination results via smart glasses or a head-mounted display in a physical store, thereby enabling fast and accurate authenticity determination in a physical store.

[1560] "Luxury goods" generally refer to items that are expensive, rare, and made using high-quality materials and sophisticated craftsmanship.

[1561] "Authenticity" refers to determining whether something is genuine or fake.

[1562] A "system" is a collective term for multiple components or means combined to achieve a specific function or purpose.

[1563] "Photographing means" refers to a camera or other photographing device that a user uses to photograph luxury items.

[1564] "Communication means" refers to an internet connection or other data transmission means for sending captured image data to a server.

[1565] The "preprocessing means" refers to a processing means on the server that performs preprocessing such as noise removal, normalization, and resizing on the received image data.

[1566] "Feature extraction means" refers to an algorithm or device for extracting product-specific features from pre-processed image data.

[1567] "Determination means" refers to an AI model or algorithm for determining the authenticity of luxury goods based on the features extracted by the feature extraction means.

[1568] "Result transmission means" refers to a communication means for generating a detailed report of the judgment results and transmitting them to the user's terminal.

[1569] "Result display means" refers to the user interface or software for displaying results on the user's terminal and saving or sharing the results.

[1570] "Smart glasses" refers to a wearable device that has display and camera functions and can send and receive data when worn by the user.

[1571] A "head-mounted display" refers to a display device that provides visual information when worn by a user on the head.

[1572] "Internet connection" refers to a network connection for uploading image data to a server via a communication means.

[1573] "Determination result" refers to the result of the AI ​​model determining the authenticity of a luxury item.

[1574] A "detailed report" refers to a report that details the evaluation results and reliability of each feature based on the judgment results.

[1575] System configuration

[1576] The system of the present invention is designed to determine the authenticity of luxury goods and can be used in brick-and-mortar stores. The system consists of the following components:

[1577] 1. Imaging method (smart glasses or head-mounted display)

[1578] The user wears smart glasses or a head-mounted display and takes a photo of a luxury item. The device has a built-in camera, allowing the product to be photographed naturally from the user's point of view.

[1579] 2. Communication method (Wi-Fi, etc.)

[1580] The captured image data is sent to a server via Wi-Fi, using an internet connection as the communication method, and the data is compressed before being sent.

[1581] 3. Preprocessing method (server side)

[1582] The server preprocesses the received image data, which includes normalizing, resizing, and removing noise, converting the image into a suitable format for subsequent analysis.

[1583] 4. Feature extraction method (server side)

[1584] The server extracts features from the preprocessed image data using a convolutional neural network (CNN) to extract product-specific features (e.g., logo position, stitching pattern, material texture).

[1585] 5. Judgment method (server side)

[1586] Based on the features obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[1587] 6. Result transmission method (server → terminal)

[1588] The server generates a detailed report with the results and transmits it to the user's smart glasses or head-mounted display via Wi-Fi.

[1589] 7. Display of results (smart glasses or head-mounted display)

[1590] The user's device displays the received judgment results, which are instantly displayed as "genuine" or "fake," and a detailed report can also be viewed.

[1591] Specific processing of the program

[1592] As an example of a physical store, we will demonstrate how the system works in a store that sells luxury brand watches. A salesperson wears smart glasses or a head-mounted display and takes a photo of the watch case or dial. The image data is sent to a server via Wi-Fi, where it is normalized and resized by pre-processing. Features are then extracted using a convolutional neural network (CNN), and an AI model makes a judgment. The judgment result is then sent back to the device via Wi-Fi, where the salesperson can check it on the spot.

[1593] The required hardware includes smart glasses (e.g., Google Glass) or a head-mounted display (e.g., Microsoft HoloLens), and the server side requires a high-performance GPU. The software includes machine learning libraries such as Python and TensorFlow.

[1594] Specific examples

[1595] For example, in a store selling luxury brand watches, a salesperson uses smart glasses to take a photo of the watch case or dial. The image data is sent to a server via Wi-Fi and preprocessed. Features are then extracted using CNN, and an AI model determines its authenticity. The result, "This watch is genuine," is displayed on the smart glasses.

[1596] Prompt Sentence Examples

[1597] Prompt: "This image is of a luxury brand watch case. Use a convolutional neural network to determine whether it is authentic. Consider the shape of the case, the placement of the numerals on the dial, and the texture of the material as characteristics."

[1598] In this way, by using the system of the present invention, it becomes possible to quickly and accurately determine the authenticity of luxury goods even in physical stores, thereby realizing the provision of highly reliable information to customers.

[1599] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1600] Step 1:

[1601] The user wears smart glasses or a head-mounted display and takes pictures of luxury items.

[1602] Input: Images of luxury items captured through a camera built into smart glasses or a head-mounted display

[1603] Output: Image data of the luxury item photographed

[1604] Action: The user activates the camera and takes a picture of a specific part (such as the case or dial) of a luxury item (e.g., a luxury brand watch).

[1605] Step 2:

[1606] The device sends the captured image data to a server via Wi-Fi.

[1607] Input: Image data of the luxury item photographed

[1608] Output: Image data sent to the server

[1609] How it works: The communication module inside the device compresses the image data and uploads it to the server as an HTTP request.

[1610] Step 3:

[1611] The server pre-processes the received image data.

[1612] Input: Image data sent to the server

[1613] Output: Preprocessed image data (normalized, resized, and denoised)

[1614] How it works: A program on the server normalizes the image data, resizes it to a consistent size, and denoises it, using an image processing library such as OpenCV.

[1615] Step 4:

[1616] The server extracts features from the preprocessed image data.

[1617] Input: Preprocessed image data

[1618] Output: Feature vector

[1619] How it works: It uses a server-based convolutional neural network (CNN) to extract features from images, using machine learning frameworks such as TensorFlow and Keras.

[1620] Step 5:

[1621] The server determines the authenticity of the luxury item based on the features obtained by the feature extraction means.

[1622] Input: feature vector

[1623] Output: Verification result (e.g. "Genuine", "Fake")

[1624] How it works: The AI ​​model analyzes feature vectors and determines authenticity based on a pre-trained dataset.

[1625] Step 6:

[1626] The server generates a detailed report with the results of the assessment and sends it to the user's terminal.

[1627] Input: Judgment results, detailed report elements (e.g., evaluation of logo position and material texture)

[1628] Output: Verification results and detailed report

[1629] How it works: The server generates a text report with the results and a detailed report, which it then sends back to the user's device via Wi-Fi.

[1630] Step 7:

[1631] The terminal displays the received judgment result.

[1632] Input: Verification results and detailed report

[1633] Output: Judgment results and detailed reports displayed on smart glasses or a head-mounted display

[1634] How it works: Using the device's display function, the result is displayed as "genuine" or "fake," and a detailed report can also be viewed.

[1635] 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.

[1636] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes an embodiment of the present invention.

[1637] The present invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The present invention also combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[1638] System configuration

[1639] The system is broadly composed of the following components:

[1640] 1. Shooting method (device)

[1641] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button.

[1642] 2. Communication method (terminal → server)

[1643] The captured image data is sent to a server over an internet connection, specifically as an HTTP request to a server endpoint.

[1644] 3. Preprocessing means (server)

[1645] The server preprocesses the received image data, which includes removing noise from the image, normalizing the color, and resizing it to a size suitable for analysis.

[1646] 4. Feature extraction method (server)

[1647] The server extracts features from the pre-processed image data using advanced image recognition algorithms such as convolutional neural networks (CNNs).

[1648] 5. Determination means (server)

[1649] Based on the feature vectors obtained by the feature extraction method, the AI ​​model judges the authenticity of luxury goods. The AI ​​model has been trained on a large amount of data in advance, enabling highly accurate judgments.

[1650] 6. Result transmission method (server → terminal)

[1651] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone via the Internet.

[1652] 7. Result display means (terminal)

[1653] The user's smartphone uses an app that displays the received judgment results. The result is a rating of "genuine" or "fake," and a detailed report can be viewed. The app also incorporates an emotion engine that recognizes the user's emotions.

[1654] 8. Emotion Engine (Terminal)

[1655] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[1656] 9. Feedback means (terminal)

[1657] The emotion engine recognizes the user's emotions and then provides feedback based on those emotions. For example, if the user is shocked that the product is identified as fake, it will display a message of comfort and the next steps to take (e.g., guiding them through the return process).

[1658] Program processing

[1659] The system process proceeds as follows, with an example:

[1660] Example: Authentication of luxury brand bags and user emotion recognition

[1661] 1. User - Launches the camera app on the smartphone and takes a photo of a luxury brand bag. For example, the user takes a photo of the entire bag and a detailed image of the logo.

[1662] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[1663] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[1664] 4. Server - Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[1665] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[1666] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone. The report details the evaluation result and its reliability for each feature.

[1667] 7. Device - Displays the received judgment result. The user can check the judgment result of "genuine" or "fake" through the app. A detailed report can also be viewed.

[1668] 8. Device - While the user is checking the result, the emotion engine analyzes the user's facial expressions and voice. For example, if the user is surprised, the camera captures and analyzes their facial expression.

[1669] 9. Device - Feedback is generated based on emotions. For example, if the user is surprised, the message "You seem surprised. Don't worry, we'll provide you with more information."

[1670] 10. User - Review the results and feedback and decide on the next action. For example, if the bag is determined to be fake, they will be provided with information to proceed with the return process.

[1671] In this way, the present invention allows users to easily determine the authenticity of luxury items, and further improves the user experience by providing feedback according to the user's emotional state.

[1672] The processing flow will be explained below.

[1673] Step 1:

[1674] User - Launches the camera app on the smartphone and takes a picture of a luxury item (e.g., a designer bag). By pressing the capture button on the camera app, high-resolution image data is acquired.

[1675] Step 2:

[1676] Device - The acquired image data is temporarily stored in the device's memory, and a preview of the stored image is displayed, prompting the user for confirmation.

[1677] Step 3:

[1678] Device - Begin preparing to send the verified image data to the server. The image data is appropriately compressed and sent to the server endpoint in the form of an HTTP request. Specifically, the request is generated with the following information:

[1679] User ID

[1680] Image data

[1681] timestamp

[1682] Step 4:

[1683] Server - Receives and temporarily stores the image data sent to it. The server prepares the data for passing to the analysis module and checks the integrity of the data.

[1684] Step 5:

[1685] Server - Initiates preprocessing of the image data. This preprocessing includes denoising the image, color normalizing it, and resizing it to a size suitable for analysis. Specific tasks include:

[1686] Normalizing pixel values

[1687] Noise removal using a Gaussian filter

[1688] Resize

[1689] Step 6:

[1690] Server - Extracts features from the pre-processed image data. Convolutional neural networks (CNNs) are used to detect specific features in the image (e.g., logo location, stitching patterns, material textures, etc.).

[1691] Step 7:

[1692] Server - Using the results of feature extraction, the AI ​​model determines the authenticity of the image. The AI ​​model has been trained with a large amount of data in advance, and calculates the probability of whether an image is genuine or fake based on the extracted feature vector. The specific evaluation is as follows:

[1693] Does the logo shape and placement match the genuine product?

[1694] Do the stitch patterns match?

[1695] Is the texture of the material the same?

[1696] Step 8:

[1697] Server - Generates the assessment results and a detailed report detailing the assessment results and confidence levels for each feature, as well as the analysis of the images used to make the assessment.

[1698] Step 9:

[1699] Server - Sends generated verdicts and reports to the user's device, usually as HTTP responses, notifying the user in real time.

[1700] Step 10:

[1701] Device - Analyzes the received results and displays them in the user interface. The app displays a summary of the results and a detailed report for easy review by the user. Specifically, it displays the following information:

[1702] Verification result (genuine / fake)

[1703] Detailed characterization

[1704] Report download link

[1705] Step 11:

[1706] On your device - While you are checking your results, the app will use your smartphone's camera and microphone to analyze your facial expressions and voice with its emotion engine. This includes:

[1707] Face detection and facial expression analysis

[1708] Voice tone and pitch analysis

[1709] Step 12:

[1710] Terminal - Based on the analysis results of the emotion engine, identify the user's emotional state (e.g., joy, surprise, sadness, etc.) and generate a feedback message according to the emotional state.

[1711] Step 13:

[1712] Terminal - Display feedback to the user based on their emotions. For example, if the user is surprised, display "I see you're surprised. We'll provide you with more information, so don't worry." If the user is shocked, provide a comforting message or instructions on what to do next (e.g., instructions on how to return the product).

[1713] Step 14:

[1714] User - Review the results and feedback and decide on the next action. For example, if the bag is determined to be counterfeit, view information to proceed with the return process.

[1715] Example 2

[1716] 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."

[1717] Determining the authenticity of luxury goods requires expert knowledge and skills, making it difficult for users without advanced expertise. Furthermore, appropriately responding to the user's emotional reaction when receiving the results is important for improving the user experience. Given this situation, the present invention aims to provide a system that easily determines the authenticity of luxury goods and provides feedback based on the user's emotional state.

[1718] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1719] In this invention, the server includes a means for receiving and preprocessing image data, a means for extracting features from the preprocessed image data, and a means for determining the authenticity of an item based on the extracted features, thereby enabling highly accurate authentication and appropriate feedback based on the user's emotions.

[1720] "Photographing means" refers to a smartphone camera or other imaging device that a user uses to photograph an item.

[1721] The "communication means" refers to a means for transmitting image data acquired by the photographing means to a server via an Internet connection, and specifically, uses a protocol such as an HTTP request.

[1722] "Preprocessing means" refers to the process of performing noise removal, color normalization, resizing, etc. on the image data received on the server side and converting it into a format suitable for analysis.

[1723] "Feature extraction means" refers to algorithms and hardware for extracting article features (e.g., logo location, stitching pattern, material texture, etc.) from pre-processed image data.

[1724] "Determination means" refers to an AI model or algorithm that determines the authenticity of an item based on the features obtained by the feature extraction means.

[1725] The "result transmission means" is a means for generating the judgment results and a detailed report and transmitting them to the user's terminal, and utilizes an internet connection.

[1726] "Result display means" refers to an application or interface for displaying the assessment results and detailed reports on the user's device and saving or sharing them.

[1727] "Emotion recognition means" refers to hardware and software for identifying the emotional state of a user by analyzing the facial expression, voice, etc. of the user checking the judgment result.

[1728] The "feedback means" refers to software for generating appropriate feedback based on the emotion recognized by the emotion recognition means and providing it to the user.

[1729] The present invention is a system for determining the authenticity of luxury goods. This system operates primarily on the user's smartphone and combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[1730] System configuration

[1731] The system is broadly composed of the following components:

[1732] 1. Shooting method (device)

[1733] The user takes a photo of the luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button. Specifically, a high-definition camera or a standard camera on the smartphone can be used.

[1734] 2. Communication method (terminal → server)

[1735] The captured image data is sent to a server via an internet connection. Specifically, the image data is sent as an HTTP request to the server endpoint. HTTPS is the recommended communication protocol.

[1736] 3. Preprocessing means (server)

[1737] The server preprocesses the received image data, which includes removing noise, color normalizing, and resizing the image to a size suitable for analysis. Specifically, median filtering and histogram equalization are applied.

[1738] 4. Feature extraction method (server)

[1739] The server extracts features from the pre-processed image data using a sophisticated image recognition algorithm called a convolutional neural network (CNN), such as the location of logos, stitching patterns, and material textures.

[1740] 5. Determination means (server)

[1741] Based on the feature vectors obtained by the feature extraction method, an AI model determines the authenticity of luxury goods. This AI model has been trained on a large dataset in advance, enabling highly accurate judgment. For example, it evaluates whether the luxury brand logo or stitching pattern matches that of the genuine product.

[1742] 6. Result transmission method (server → terminal)

[1743] The server generates a detailed report of the results and sends it to the user's smartphone via the Internet. The report details the evaluation results and their reliability for each feature.

[1744] 7. Result display means (terminal)

[1745] The user's smartphone uses an app that displays the received judgment results, which are rated as "genuine" or "fake," and a detailed report can also be viewed.

[1746] 8. Emotion recognition means (terminal)

[1747] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[1748] 9. Feedback means (terminal)

[1749] The emotion engine recognizes the user's emotions and then provides feedback based on those emotions. For example, if the user is shocked that the product is identified as fake, it will display a message of comfort and the next steps to take (e.g., guiding them through the return process).

[1750] Specific examples

[1751] Example: Authentication of luxury brand bags and user emotion recognition

[1752] 1. User - Launches the smartphone camera app and takes a photo of a luxury brand bag, taking a full view of the bag and a detailed view of the logo.

[1753] 2. Device - The captured image data is sent to the server via an internet connection. The image data is compressed and sent as an HTTP request.

[1754] 3. Server - Preprocesses the received image data, removing noise and normalizing the image, and converting it into a format suitable for analysis.

[1755] 4. Server - Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[1756] 5. Server - Based on the extracted features, the AI ​​model determines the authenticity of the bag, for example, whether the logo is correctly placed and whether the stitching pattern matches that of the genuine product.

[1757] 6. Server - Generates a detailed report of the results and sends it to the user's smartphone. The report details the evaluation result and its reliability for each feature.

[1758] 7. Device - The received judgment results are displayed in the app, and the user can check the "genuine" or "fake" judgment results and report.

[1759] 8. Device - While the user is checking the result, the emotion engine analyzes the user's facial expressions and voice. For example, if the user is surprised, the camera captures and analyzes their facial expression.

[1760] 9. Device - Generate feedback based on emotions. For example, if the user is surprised, display a message like "I see you're surprised. Don't worry, we'll provide you with more information."

[1761] Examples of typical prompt statements

[1762] "Explain the outline of a system that uses AI to determine the authenticity of a luxury brand bag using an image taken by the user, and then describe the entire process of recognizing the user's emotions and providing feedback."

[1763] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1764] Step 1:

[1765] The user launches the camera app on their smartphone and takes a picture of the luxury item.

[1766] Input: Item (e.g. luxury brand bag)

[1767] Output: Captured image data (high-resolution image)

[1768] What happens: The user points the camera at a luxury item, focuses it, and takes a photo in a well-lit area, capturing both the overall image of the bag and the details (logo, stitching, etc.).

[1769] Step 2:

[1770] The terminal transmits the captured image data to a server via the Internet.

[1771] Input: Captured image data

[1772] Output: Image data sent as an HTTP request

[1773] Specific behavior: The device compresses and encodes the image data, generates an HTTP POST request, and sends it to the server endpoint.

[1774] Step 3:

[1775] The server pre-processes the received image data.

[1776] Input: Received image data

[1777] Output: Preprocessed image data

[1778] Specific operation: The server performs noise removal (median filtering) on ​​the received image data, then performs color normalization (histogram equalization), and resizes it to a size suitable for analysis.

[1779] Step 4:

[1780] The server extracts features from the preprocessed image data.

[1781] Input: Preprocessed image data

[1782] Output: feature vector

[1783] How it works: The server uses a convolutional neural network (CNN) to extract important features in the image (such as the position of the logo, the stitching pattern, and the texture of the material) and represents these features as a feature vector.

[1784] Step 5:

[1785] The server uses an AI model to determine authenticity based on the feature vector obtained by the feature extraction means.

[1786] Input: feature vector

[1787] Output: Verification result (e.g. "Genuine" or "Fake")

[1788] How it works: The server inputs the feature vector into a trained AI model, which then makes a judgment, such as whether the logo position matches that of the genuine product or whether the stitching pattern matches that of the genuine product.

[1789] Step 6:

[1790] The server generates a detailed report with the results of the assessment and sends it to the user's smartphone.

[1791] Input: Judgment result, feature vector and analysis result

[1792] Output: Verification report (including detailed evaluation results)

[1793] How it works: The server generates a report based on the results, detailing the evaluation result and confidence level for each feature. This report is securely sent to the device using HTTPS.

[1794] Step 7:

[1795] The terminal displays the received judgment result.

[1796] Input: Adjudication Report

[1797] Output: Displayed judgment results and detailed report

[1798] Specific operation: The device application displays the result of the judgment (e.g., "genuine" or "fake") to the user and allows them to view a detailed report.

[1799] Step 8:

[1800] The terminal recognizes the emotion of the user who is checking the judgment result.

[1801] Input: User's facial expression and voice data

[1802] Output: Recognized emotional state (e.g., happy, surprised, sad, etc.)

[1803] How it works: The device captures the user's facial expressions and voice through the camera and microphone, and uses facial recognition and voice analysis algorithms to identify their emotional state.

[1804] Step 9:

[1805] The device generates and displays feedback based on the recognized emotion.

[1806] Input: Perceived emotional state

[1807] Output: Feedback message

[1808] Specific operation: Based on the emotion recognition results, the device generates an appropriate message. For example, if the user is surprised, the device will display the message, "You seem surprised. Don't worry, we will provide you with more information."

[1809] (Application example 2)

[1810] 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."

[1811] Determining the authenticity of luxury goods is important to consumers, but it is difficult to do so quickly and accurately on-site. It is also necessary to provide appropriate feedback based on the user's reaction to the authentication results. Conventional systems have had difficulty meeting these needs, resulting in a lack of improvement in the user experience. Therefore, there is a need for a system that can quickly determine the authenticity of luxury goods and provide feedback based on the user's emotions.

[1812] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a preprocessing means, a feature extraction means, and a determination means. This makes it possible to quickly and accurately determine the authenticity of luxury goods. In addition, by using an emotion recognition means that recognizes the user's emotion and a result transmission means that transmits and displays the results on the user terminal, it is possible to provide appropriate feedback to the user and improve the user experience.

[1813] The "photography means" refers to a device that allows a user to photograph luxury items, specifically a smartphone camera or other image capture device.

[1814] The "communication means" is a means for transmitting image data captured by the image capturing means to a server, and is a device that includes a function for uploading data via an internet connection.

[1815] The "preprocessing means" is a device or software that receives image data on the server side and performs preprocessing such as noise removal and color normalization.

[1816] A "feature extraction means" is a means for extracting specific features from preprocessed image data, and is a device or software that includes an algorithm such as a convolutional neural network (CNN).

[1817] The "determination means" refers to a device or software that includes an AI model or algorithm for determining the authenticity of luxury goods based on the features extracted by the feature extraction means.

[1818] The "result transmission means" is a device or software that generates a detailed report of the judgment results and transmits them to the user's terminal.

[1819] The "result display means" is an application or interface for displaying the judgment results on the user's terminal and saving or sharing them.

[1820] The "emotion recognition means" is a device or software that uses a camera or microphone to analyze facial expressions and voice in order to recognize the user's emotions.

[1821] The "feedback means" is a means for generating and displaying appropriate feedback in accordance with the user's emotion recognized by the emotion recognition means.

[1822] The following describes an embodiment of the present invention. The present invention is a system for determining the authenticity of luxury goods, which operates primarily on the user's smartphone. The present invention also combines an emotion engine that recognizes the user's emotions to provide a more interactive experience.

[1823] Program processing overview

[1824] The system consists of the following components:

[1825] 1. Filming Method

[1826] 2. Means of communication

[1827] 3. Server-side preprocessing methods

[1828] 4. Feature Extraction Method

[1829] 5. Judgment means

[1830] 6. Means of sending results

[1831] 7. Results display means

[1832] 8. Emotion recognition means

[1833] 9. Feedback channels

[1834] Description of each component

[1835] Filming method

[1836] The user takes a photo of a luxury item using the smartphone camera. The camera app is launched and image data is acquired by pressing the capture button. The captured image is saved with appropriate image quality and resolution for analysis.

[1837] communication means

[1838] The captured image data is sent to a server via an internet connection. The image data is compressed and sent as an HTTP request to the server endpoint. This communication method ensures fast and reliable data transfer.

[1839] Server-side preprocessing measures

[1840] The server preprocesses the received image data, including removing noise, normalizing the color, and resizing the image to a size suitable for analysis. This ensures consistent image quality and facilitates processing by the feature extraction tool.

[1841] Feature Extraction Method

[1842] Features are extracted from the pre-processed image data. This process uses a convolutional neural network (CNN) as an advanced image recognition algorithm. The feature extraction method extracts important features from the image data, such as the position of the logo, seams, and the texture of the material.

[1843] Judgment means

[1844] Based on the feature vectors obtained by the feature extraction method, the AI ​​model determines the authenticity of luxury goods. The AI ​​model is trained on a large amount of data in advance, enabling highly accurate judgment. For example, it evaluates whether the logo is positioned correctly and whether the stitching pattern matches that of the genuine product.

[1845] Result transmission method

[1846] The server generates a detailed report of the results and sends it to the user's smartphone, which includes the evaluation results and their reliability for each feature.

[1847] Results display means

[1848] The user's smartphone uses an app that displays the received judgment results, allowing the user to confirm the "genuine" or "fake" rating and view a detailed report.

[1849] emotion recognition means

[1850] When the user checks the judgment result, the smartphone's camera and microphone are used to recognize the user's emotions. The emotion engine analyzes facial expressions and voice to identify the user's emotional state (e.g., joy, surprise, sadness, etc.).

[1851] Feedback Methods

[1852] After the emotion recognition means recognizes the user's emotion, it provides feedback according to that emotion. For example, if the user is shocked that the product is determined to be fake, it displays a message of comfort and the next steps to take (e.g., guidance on the return procedure).

[1853] Specific examples

[1854] Below are some examples of authenticating luxury brand bags and recognizing user emotions:

[1855] 1. The user launches the camera app on their smartphone and takes a photo of a luxury brand bag. For example, they take a photo of the entire bag and a detailed image of the logo.

[1856] 2. The captured image data is sent to the server as an HTTP request via the internet connection.

[1857] 3. The server preprocesses the received image data, removing noise and normalizing the image, and converts it into a format suitable for analysis.

[1858] 4. Extract features from the preprocessed image data. Using CNN, we extract features such as the position of the logo, the stitching of the bag, and the texture of the material.

[1859] 5. Based on the extracted features, the AI ​​model determines the authenticity of the bag, assessing whether the logo is correctly positioned, whether the stitching pattern matches, etc.

[1860] Prompt Sentence Examples

[1861] Develop an app that uses a smartphone camera to take a photo of a luxury item (e.g., a designer bag) and sends the image to a server to determine its authenticity. After determining authenticity, please include a function that recognizes the user's emotions and provides appropriate feedback.

[1862] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1863] Step 1:

[1864] A user launches the camera app on their smartphone and takes a picture of a luxury item. The captured image is the input, and the image data is output. The user presses the capture button on the camera app to take a picture of the entire product (e.g., a designer bag) and important logo details.

[1865] Step 2:

[1866] The device sends the captured image data to the server. The input is the image data acquired in step 1, and the output is the image data as an HTTP request to the server. The image data from the smartphone is compressed and sent to the specified server endpoint via the network.

[1867] Step 3:

[1868] The server preprocesses the image data it receives. The input is the image data sent to the server, and the output is the preprocessed image data. Preprocessing includes noise removal, color normalization, and resizing. This stabilizes the quality of the image data and makes subsequent processing easier.

[1869] Step 4:

[1870] The server extracts features from the preprocessed image data. The input is the preprocessed image data, and the output is a feature vector. Using a convolutional neural network (CNN), features such as the position of the logo, the stitching of the bag, and the texture of the material are extracted.

[1871] Step 5:

[1872] The server determines the authenticity of luxury goods based on the feature vector obtained by the feature extraction means. The input is the feature vector obtained by the feature extraction means, and the output is the authenticity determination result. An AI model is used to evaluate whether the logo is positioned correctly and whether the stitching pattern matches that of the genuine product, and to determine authenticity.

[1873] Step 6:

[1874] The server generates the judgment result and a detailed report and sends them to the user's device. The input is the authenticity judgment result, and the output is a detailed report and the judgment result data. The judgment result is compiled into a report and sent to the user's device via the Internet.

[1875] Step 7:

[1876] The device displays the received judgment results. The input is the judgment result and detailed report sent from the server, and the output is a screen display that can be viewed by the user. The user can check the results through the app and view the "genuine" or "fake" rating and detailed report.

[1877] Step 8:

[1878] The device recognizes the user's emotions. The input is facial expressions and voice data when the user confirms the judgment result, and the output is the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through the camera and microphone to identify the emotional state (e.g., joy, surprise, sadness, etc.).

[1879] Step 9:

[1880] The device provides appropriate feedback according to the user's emotion recognized by the emotion recognition means. The input is the user's emotional state, and the output is a feedback message. For example, if the user is shocked that the product is determined to be fake, the app will display a comforting message and the next steps to take (e.g., guiding them through the return procedure).

[1881] 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.

[1882] 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.

[1883] 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.

[1884] 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.

[1885] 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.

[1886] 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.

[1887] 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).

[1888] 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.

[1889] 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."

[1890] 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.

[1891] 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).

[1892] 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.

[1893] 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.

[1894] 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.

[1895] 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.

[1896] 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.

[1897] 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.

[1898] 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.

[1899] 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.

[1900] 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.

[1901] 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.

[1902] The following is further disclosed regarding the above embodiment.

[1903] (Claim 1)

[1904] A system for determining the authenticity of luxury goods, comprising:

[1905] a photographing means for a user to photograph luxury items;

[1906] a communication means for transmitting image data captured by the imaging means to a server;

[1907] a server-side preprocessing means for receiving and preprocessing image data;

[1908] feature extraction means for extracting features from the preprocessed image data;

[1909] a determination means for determining the authenticity of the luxury item based on the features extracted by the feature extraction means;

[1910] a result transmission means for generating a judgment result and a detailed report and transmitting the result to a user's terminal;

[1911] A result display means for displaying the results on the user's terminal and saving or sharing the results;

[1912] A system including:

[1913] (Claim 2)

[1914] 10. The system of claim 1, wherein the communication means is configured to upload the image data to the server via an internet connection.

[1915] (Claim 3)

[1916] The system according to claim 1, wherein the result display means displays the evaluation of "genuine" or "fake" as the judgment result, and a detailed report can also be viewed.

[1917] "Example 1"

[1918] (Claim 1)

[1919] a photographing means for a user to photograph luxury items;

[1920] a communication means for transmitting image data captured by the imaging means to a server;

[1921] A server-side preprocessing means receives image data and performs preprocessing such as noise removal, normalization, and resizing;

[1922] a feature extraction means for extracting features from the preprocessed image data using a convolutional neural network;

[1923] A determination means for determining the authenticity of luxury goods using an AI model based on the feature vector extracted by the feature extraction means;

[1924] a result transmission means for generating a detailed report including the judgment result and the reliability and transmitting the report to the user's terminal;

[1925] a result display means for displaying the judgment result on a user's terminal and enabling the user to view a detailed report;

[1926] A system including:

[1927] (Claim 2)

[1928] 10. The system of claim 1, wherein the communication means is configured to upload the image data to the server via an internet connection.

[1929] (Claim 3)

[1930] The system according to claim 1, wherein the result display means displays the evaluation of "genuine" or "fake" as the judgment result, and a detailed report can also be viewed.

[1931] "Application Example 1"

[1932] (Claim 1)

[1933] A system for determining the authenticity of luxury goods, comprising:

[1934] a photographing means for a user to photograph luxury items;

[1935] a communication means for transmitting image data captured by the imaging means to a server;

[1936] a server-side preprocessing means for receiving and preprocessing image data;

[1937] feature extraction means for extracting features from the preprocessed image data;

[1938] a determination means for determining the authenticity of the luxury item based on the features extracted by the feature extraction means;

[1939] a result transmission means for generating a judgment result and a detailed report and transmitting the result to a user's terminal;

[1940] A result display means for displaying the results on the user's terminal and saving or sharing the results;

[1941] A means for taking a photo of a luxury item and displaying the evaluation result via smart glasses or a head-mounted display in a physical store;

[1942] A system including:

[1943] (Claim 2)

[1944] 10. The system of claim 1, wherein the communication means is configured to upload the image data to the server via an internet connection.

[1945] (Claim 3)

[1946] The system according to claim 1, wherein the result display means displays the evaluation of "genuine" or "fake" as the judgment result, and a detailed report can also be viewed.

[1947] "Example 2: Combining Emotion Engines"

[1948] (Claim 1)

[1949] an imaging means for a user to photograph an item;

[1950] a communication means for transmitting image data captured by the imaging means to a server;

[1951] a server-side preprocessing means for receiving and preprocessing image data;

[1952] feature extraction means for extracting features from the preprocessed image data;

[1953] a determination means for determining the authenticity of an article based on the features extracted by the feature extraction means;

[1954] a result transmission means for generating a judgment result and a report and transmitting the result to a user's terminal;

[1955] a result display means for displaying the judgment result and a detailed report on the user's terminal;

[1956] emotion recognition means for recognizing the emotion of the user while checking the judgment result;

[1957] feedback means for generating feedback based on the recognized emotion;

[1958] A system including:

[1959] (Claim 2)

[1960] 10. The system of claim 1, wherein the communication means is configured to upload the image data to the server via an internet connection.

[1961] (Claim 3)

[1962] 2. The system according to claim 1, wherein the result display means displays the evaluation of "genuine" or "fake" as the judgment result, and a detailed report can be viewed.

[1963] "Application example 2 when combining emotion engines"

[1964] (Claim 1)

[1965] A system for determining the authenticity of luxury goods, comprising:

[1966] a photographing means for a user to photograph luxury items;

[1967] a communication means for transmitting image data captured by the imaging means to a server;

[1968] a server-side preprocessing means for receiving and preprocessing image data;

[1969] feature extraction means for extracting features from the preprocessed image data;

[1970] a determination means for determining the authenticity of the luxury item based on the features extracted by the feature extraction means;

[1971] a result transmission means for generating a judgment result and a detailed report and transmitting the result to a user's terminal;

[1972] A result display means for displaying the results on the user's terminal and saving or sharing the results;

[1973] emotion recognition means for recognizing the user's emotion and generating appropriate feedback;

[1974] A system including:

[1975] (Claim 2)

[1976] 10. The system of claim 1, wherein the communication means is configured to upload the image data to the server via an internet connection.

[1977] (Claim 3)

[1978] The system of claim 1, wherein the result display means displays the evaluation of "genuine" or "fake" as the judgment result, a detailed report can also be viewed, and the emotion recognition means provides feedback according to the user's emotions. [Explanation of symbols]

[1979] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system for determining the authenticity of luxury goods, comprising: a photographing means for a user to photograph luxury items; a communication means for transmitting image data captured by the imaging means to a server; a server-side preprocessing means for receiving and preprocessing image data; feature extraction means for extracting features from the preprocessed image data; a determination means for determining the authenticity of the luxury item based on the features extracted by the feature extraction means; a result transmission means for generating a judgment result and a detailed report and transmitting the result to a user's terminal; A result display means for displaying the results on the user's terminal and saving or sharing the results; A system including:

2. 10. The system of claim 1, wherein the communication means is configured to upload the image data to a server via an internet connection.

3. 2. The system according to claim 1, wherein the result display means displays the evaluation of "genuine" or "fake" as the judgment result, and a detailed report can also be viewed.

Images