system

Abstract

Provide a system. A means for transmitting a product image photographed or selected from a terminal to a server; A means for analyzing the product image received by the server and identifying the product; means for retrieving the characteristics of the identified product from a database in the server; A means for performing a matching evaluation based on the product information acquired by the server and the user's preference information; means for transmitting product information and matching results from the server to the terminal; a means for displaying the received product information and matching results on the terminal; A system including:

Description

[Technical Field]

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

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

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

[0004] In conventional online shopping, when users want to obtain information about a product they are considering purchasing, they must manually research a vast amount of reviews and specifications, which is extremely time-consuming and laborious. It is also difficult to determine whether a product matches the user's preferences, which can lead to inappropriate purchases in some cases. Furthermore, when selecting a product in a physical store, there is currently no way to instantly obtain appropriate information. This has led to issues that make it difficult for users to have a satisfying shopping experience. [Means for solving the problem]

[0005] The present invention is a product recommendation system that includes a means for transmitting product images taken or selected from a terminal to a server, a means for analyzing the product images received by the server and identifying products, a means for acquiring the characteristics of the products identified by the server from a database, a means for performing a matching evaluation based on the product information acquired by the server and user preference information, a means for transmitting the product information and matching results from the server to the terminal, and a means for displaying the product information and matching results received by the terminal. This allows users to easily check detailed product information and how well it matches their preferences, significantly reducing time and effort. Furthermore, the use of AI technology enables highly accurate product recognition and matching to user preferences. This allows users to quickly receive appropriate purchasing information and achieve a highly satisfying shopping experience.

[0006] A "terminal" is an electronic device operated by a user, and is a device that is responsible for taking and selecting photos, transmitting data, and displaying information.

[0007] A "server" is a remote computer system that receives data sent from a terminal via a network, analyzes it, acquires information, and processes it for transmission.

[0008] A "product image" is digital image data that includes visual information of a product that a user is considering purchasing, and that is photographed or selected by the user using a terminal.

[0009] "Analysis" refers to the computational processes and algorithms used by the server to extract and identify product features from the product images received.

[0010] "Identification" is the process by which the server classifies products into specific categories or brands based on the features extracted through analysis.

[0011] "Features" are important attribute information about the analyzed product, including information such as color, shape, brand, and model name.

[0012] A "database" is a collection of information stored on a server, such as detailed product information, user preference information, reviews, and price information.

[0013] "Matching evaluation" refers to the process and results of comparing the product characteristics acquired by the server with the user's preference information and evaluating the suitability of the product.

[0014] "Information acquisition" refers to the process in which the server reads out necessary product information and user preference information from the database.

[0015] "Sending information" refers to the process in which the server sends the processed product information and matching results to the terminal.

[0016] "Displaying information" refers to a process in which the terminal visually presents the product information and matching results received from the server to the user.

[0017] "Preference information" is preference data related to product selection based on the purchase history and evaluation criteria provided by the user in the past. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[0040] First, the user launches the app on a device such as a smartphone or tablet. The user operates the app and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. This image is temporarily saved on the device.

[0041] The device then sends the captured or selected product image, along with the user's authentication information, to the server, which then activates an artificial intelligence (AI) module to analyze the received product image and identify the product.

[0042] The server extracts product features based on the analysis results and retrieves related information from a product information database, such as product reviews, price information, and detailed specifications.

[0043] In parallel, the server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[0044] The evaluation results and product information are summarized and sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommendation summaries.

[0045] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[0046] For example, the server can summarize the information, such as "These shoes are characterized by high cushioning and light weight, and are very suitable considering the user's past purchase history," and send it to the device along with an evaluation score.The user can then check this information on their smartphone and make an appropriate purchasing decision.

[0047] The above is an embodiment of the present invention. This system allows users to obtain product information that suits them more quickly and efficiently, resulting in a highly satisfying shopping experience.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] The user launches the app on their device. The user operates a device such as a smartphone or tablet and taps the app icon to launch the application.

[0051] Step 2:

[0052] The user takes or selects a product image. The user uses the in-app camera to take a photo of the product they are considering purchasing, or selects an existing image stored on their device.

[0053] Step 3:

[0054] The terminal transmits the product image and user authentication information to the server. The terminal then packets the photographed or selected product image data and authentication information such as the user ID, and transmits them to the server via the Internet.

[0055] Step 4:

[0056] The server launches an AI module to analyze product images. The server inputs the received image data into the image recognition AI and extracts features to identify the product. These features include the brand name, product category, model number, etc.

[0057] Step 5:

[0058] The server retrieves product information from the database. Based on the analysis results, the server searches the database for detailed information, product reviews, price information, etc. of the identified product.

[0059] Step 6:

[0060] The server refers to the user's preference information, and retrieves user profile data such as past purchase history, rating criteria, and preferred categories from a database based on the user authentication information.

[0061] Step 7:

[0062] The server performs a matching evaluation based on product information and user preference information. The server compares the acquired product information with the user preference information and calculates a compatibility score. For example, it evaluates whether the product information matches features that have received high ratings in the past.

[0063] Step 8:

[0064] The server generates a recommendation summary and matching results. Based on the acquired product information and matching evaluation, the server creates summary information to provide to the user. The summary includes product features, user reviews, price, matching score, etc.

[0065] Step 9:

[0066] The server sends the generated summary and matching results to the terminal, converts the summary and matching results into a data format such as JSON or XML, and sends it to the terminal.

[0067] Step 10:

[0068] The device analyzes the data received from the server and displays it on the user interface. The device analyzes the received data packets and displays product information, user reviews, prices, matching scores, and recommendation summaries on the app screen.

[0069] This series of processing steps allows the user to quickly and efficiently obtain product information and support purchasing decisions.

[0070] Example 1

[0071] 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."

[0072] Conventional product purchasing support systems have the problem that it is difficult for users to quickly and accurately obtain detailed information about products they are considering purchasing, and they do not perform appropriate matching evaluations based on the user's individual preferences. In particular, to understand the product's features and performance in detail, users must refer to multiple information sources, which is time-consuming and requires effort. Furthermore, product recommendations based on the user's preferences and past purchasing history may not be sufficient, resulting in a decrease in satisfaction.

[0073] 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.

[0074] In this invention, the server includes means for transmitting product images photographed or selected from the terminal to the server, means for analyzing the product images received by the server and identifying the products, means for acquiring characteristics of the products identified by the server from a database, means for performing a matching evaluation based on the product information acquired by the server and user preference information, means for transmitting the product information and matching results from the server to the terminal, and means for displaying the product information and matching results received by the terminal on a user interface. This enables users to quickly obtain detailed information about products they are considering purchasing and receive an appropriate matching evaluation based on their preferences.

[0075] A "terminal" is a computer device operated by a user, such as a smartphone or tablet.

[0076] A "server" is a computer device that receives data sent from a terminal on a network and analyzes and processes it.

[0077] "Photographed or selected product image" refers to image data of a product that the user photographs using the terminal or selects from existing images in the terminal.

[0078] "Means for transmitting" refers to a communication function for transferring data from a terminal to a server.

[0079] "Means for analyzing and identifying products" refers to the function of using artificial intelligence models and algorithms stored on the server to judge the content of the received product images and identify the type and characteristics of the product.

[0080] "Means for obtaining features from a database" refers to the function of the server searching and obtaining detailed product information from a related database based on the analysis results of the product image.

[0081] "Means for performing matching evaluation" refers to an algorithm or system for evaluating and recommending products based on product information acquired by the server and user preference information.

[0082] "User preference information" refers to individual information such as the user's past purchasing history, preferences, and evaluation criteria.

[0083] "Product information and matching results" refers to detailed product information obtained by the server from the database and evaluation results based on the user's preferences.

[0084] "Means for displaying on the user interface" refers to a function for displaying product information and matching results in an easy-to-read format on the terminal screen.

[0085] An "artificial intelligence model" refers to a software model that uses machine learning and deep learning techniques to analyze data and derive results.

[0086] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[0087] First, the user launches a dedicated app on a device such as a smartphone or tablet. The user operates the app to take a picture of the product they are considering purchasing with the camera or select from existing images on the device. This image is temporarily saved on the device.

[0088] Next, the device sends the photographed or selected product image to the server. At this time, the user's authentication information is also sent. HTTPS communication is used as the transmission method. The server launches an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product. This AI module uses deep learning frameworks such as TENSORFLOW (registered trademark) and PyTorch.

[0089] The server extracts product features based on the analysis results and retrieves related information from a product information database. Specifically, product reviews, price information, detailed specifications, etc. are retrieved from the database. For example, Amazon DynamoDB or Google (registered trademark) Cloud Firestore is used as the product information database.

[0090] In parallel, the server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[0091] The evaluation results and product information are summarized and sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommendation summaries.

[0092] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[0093] For example, the server can summarize the information, such as "These shoes are characterized by high cushioning and light weight, and are very suitable considering the user's past purchase history," and send it to the device along with an evaluation score.The user can then check this information on their smartphone and make an appropriate purchasing decision.

[0094] An example of a prompt for a generative AI model might be, "Analyze images of products I'm considering purchasing and display detailed information and ratings based on the user's preferences."

[0095] This system allows users to obtain product information that suits them more quickly and efficiently, resulting in a more satisfying shopping experience.

[0096] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0097] Step 1:

[0098] Launching the app

[0099] Users tap to launch the dedicated app installed on their smartphone or tablet.

[0100] Specific operation: When the user taps the app icon, the app launches and the initial screen is displayed.

[0101] Input: None

[0102] Output: Initial screen of the app

[0103] Step 2:

[0104] Taking or selecting an image

[0105] Users can use the in-app camera to take a picture of the product they are considering purchasing, or select an existing photo from their gallery.

[0106] Specific behavior: When the user taps the camera button in the app, the camera will launch and take a photo. When the user taps the gallery button, the photo gallery will be displayed and an existing image can be selected.

[0107] Input: User operation (take a photo with the camera or select from the gallery)

[0108] Output: Photographed or selected product images

[0109] Step 3:

[0110] Submit product images

[0111] The terminal sends the photographed or selected product image to the server, along with the user's authentication information.

[0112] Specific operation: The device sends image data and authentication information to the server using HTTPS communication.

[0113] Input: Photographed or selected product image, user authentication information

[0114] Output: Data is sent to the server

[0115] Step 4:

[0116] Image analysis on the server

[0117] The server decodes the received product images and launches an AI module (e.g., TensorFlow or PyTorch) to perform image analysis.

[0118] Specific operation: The server decodes the image data from binary format, inputs it into the AI ​​model, and performs inference.

[0119] Input: Received product image

[0120] Output: Product identification information (e.g. brand, model)

[0121] Step 5:

[0122] Product feature extraction

[0123] The server extracts product features from the image analysis results, such as identifying "running shoes" and "high cushioning."

[0124] Specific operation: The server applies a feature extraction algorithm based on the analysis results to generate product feature information.

[0125] Input: Product identification information

[0126] Output: Product feature information

[0127] Step 6:

[0128] Obtaining product information

[0129] The server retrieves detailed information from a product information database (such as Amazon DynamoDB or Google Cloud Firestore) based on the product's features, including product reviews, prices, and detailed specifications.

[0130] What happens: The server uses SQL queries or API requests to search the database and retrieve relevant information.

[0131] Input: Product feature information

[0132] Output: Product details

[0133] Step 7:

[0134] Referencing user preference information

[0135] The server references user preference information from an internal database, including past purchase history, rating criteria, and category preferences.

[0136] Specific operations: The server queries the user profile database to obtain preference information.

[0137] Input: User credentials

[0138] Output: User preference information

[0139] Step 8:

[0140] Product matching evaluation

[0141] The server evaluates the products based on the product information and the user's preferences. Evaluation criteria include price, design, cushioning, etc.

[0142] Specific operation: The server executes the matching evaluation algorithm and calculates the evaluation score of the product.

[0143] Input: detailed product information, user preferences

[0144] Output: Matching evaluation results (e.g., score, recommendation comments)

[0145] Step 9:

[0146] Sending evaluation results

[0147] The server summarizes the evaluation results and detailed product information and sends them to the terminal.

[0148] Specific operation: The server summarizes the evaluation results and detailed product information and sends them to the terminal using HTTPS communication.

[0149] Input: Matching evaluation results, product details

[0150] Output: Transmission data (evaluation results and detailed product information)

[0151] Step 10:

[0152] Receiving data

[0153] The terminal receives the evaluation results and product information sent from the server.

[0154] Specific operation: The device receives and decodes data using HTTPS communication.

[0155] Input: Data to be sent (evaluation results and detailed product information)

[0156] Output: Received data (evaluation results and detailed product information)

[0157] Step 11:

[0158] Display in the user interface

[0159] The device analyzes the received data and displays information about the product (such as reviews, price, matching score, and recommendation summary) in the app's user interface.

[0160] Specific operation: The device parses the data, binds it to UI components, and displays it.

[0161] Input: Received data (evaluation results and detailed product information)

[0162] Output: Display on the user interface

[0163] (Application example 1)

[0164] 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."

[0165] Conventional product purchasing support systems for brick-and-mortar stores have difficulty providing detailed product information or recommendations tailored to the user's preferences in real time when the user is selecting products in the store. As a result, users often spend time and effort finding the product that best suits them, resulting in an unsatisfactory purchasing experience. Furthermore, existing technologies rely on the use of terminals, so there is a demand for more portable and intuitive interaction. Therefore, there is a growing need for a system that can provide users with appropriate product information and recommendations in real time and intuitively.

[0166] 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.

[0167] In this invention, the server includes means for transmitting product images photographed or selected from the terminal to the server, means for analyzing the product images received by the server and identifying the products, means for acquiring the features of the products identified by the server from a database, means for performing a matching evaluation based on the product information acquired by the server and user preference information, means for transmitting the product information and matching results from the server to the terminal, means for displaying the product information and matching results received by the terminal, and means for analyzing the product images photographed by the smart glasses in real time, performing a matching evaluation based on the features of the identified products and user preference information, and displaying the evaluation on the smart glasses. This allows users to intuitively and quickly obtain product information in a physical store and easily select the product that best suits them.

[0168] "Terminal" refers to any device operated by a user, specifically including smartphones, tablets, smart glasses, and the like.

[0169] A "server" is a computer system that receives data sent from terminals via a network and analyzes and processes the data.

[0170] "Product image" is image data that includes visual information of a product that the user is considering purchasing.

[0171] "Analysis" is the process of extracting features from product images and identifying the product using specific algorithms.

[0172] "Identification" is the act of identifying a product from an analyzed product image and obtaining specific information about it.

[0173] "Features" refer to identifiable properties or attributes of a product, including information such as brand, model, price, and specifications.

[0174] A "database" is a collection of information that stores product information and user information, and is a system that a server accesses to obtain the necessary data.

[0175] "Matching evaluation" is a process of evaluating the suitability of a product based on the acquired product information and user preference information.

[0176] "Smart glasses" are wearable devices that can be worn by a user and digitally display information within their field of vision.

[0177] "Real-time" refers to data being processed and displayed immediately as it is generated.

[0178] "User preference information" is a group of data that collects information such as preferences, purchase history, and evaluation criteria that a user has previously shown.

[0179] "Product information" is detailed data about a product, including general information such as reviews, price, and specifications.

[0180] "Display" refers to the act of visually conveying the analysis results or evaluation results to the user.

[0181] This invention is a system that uses smart glasses to analyze product information in real time when a user selects a product in a physical store and recommends products based on the user's preferences. The system includes a terminal, a server, smart glasses, an artificial intelligence (AI) module, a product database, and a user interface.

[0182] First, a user puts on smart glasses and walks around a physical store, selecting products. When they find a product they are interested in, they use the smart glasses' camera to take a picture of the product. The captured product image is sent to a server via the smart glasses' terminal function. The user's authentication information is also attached when the image is sent.

[0183] The server launches an AI module to analyze the received product images. The AI ​​module uses an image analysis algorithm to identify the product and extract its features. This feature information includes the brand, model, price, and specifications. The server retrieves the identified product information from the product database and performs a matching evaluation with the user information.

[0184] The matching evaluation refers to the user's past purchase history, evaluation criteria, and preference information. The server evaluates the suitability of the product based on the acquired product information and the user's preference information. The evaluation results and product information are sent from the server to the smart glasses in real time.

[0185] The smart glasses display the received product information and matching evaluation results on a screen. The user can check the information displayed in their field of view and decide whether the product is one they are interested in purchasing. This real-time display allows users to quickly and efficiently obtain product information that suits them.

[0186] As a concrete example, let's say a user is looking for running shoes in a physical store. The user walks around the store using smart glasses, and when they find a pair of shoes they like, they take a picture of them. The server uses an AI module to analyze the image and identify the characteristics of the running shoes. For example, it might evaluate the shoes as "highly cushioned and lightweight, and considering your past purchase history, they are a perfect fit." This information and evaluation score are displayed on the smart glasses, allowing the user to quickly make the right purchase decision.

[0187] A specific example of a prompt sentence for a generative AI model is as follows:

[0188] Example prompt sentence:

[0189] "Based on the images taken by the user in the store, please perform the following analysis:

[0190] 1. Product Identification

[0191] 2. After product identification, return the product brand, model, and features

[0192] 3. Provide relevant information (reviews, prices, specs) based on each feature.

[0193] As described above, the present invention realizes a system that can provide detailed product information and recommendation information based on the user's preferences in real time when the user is selecting a product in a physical store.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] A user uses smart glasses to take an image of an item of interest.

[0197] Input: Product images taken by the smart glasses camera.

[0198] Output: Product image data temporarily saved on the device.

[0199] Specific operation: While walking around the store, the user uses the smart glasses to take a picture of a product they are interested in. This image data is temporarily stored in the smart glasses' memory.

[0200] Step 2:

[0201] The terminal sends the product image and the user's authentication information to the server.

[0202] Input: Product image data, user authentication information (user ID, etc.).

[0203] Output: Product image and authentication information sent to the server.

[0204] How it works: The application on the smart glasses terminal uploads product images and user authentication information to the server, where the data is encrypted and transmitted via a security protocol.

[0205] Step 3:

[0206] The server analyzes the received product image and activates an AI module to identify the product.

[0207] Input: Product image data sent to the server.

[0208] Output: Product identification results and feature extraction results.

[0209] How it works: The AI ​​module in the server analyzes product images and uses image recognition algorithms to identify the product's brand, model, and features. The results of this identification are temporarily stored on the server.

[0210] Step 4:

[0211] The server retrieves the characteristics of the identified product from a database.

[0212] Input: Product identification results (brand, model, features, etc.).

[0213] Output: Detailed product information (reviews, price, specs, etc.) retrieved from the database.

[0214] Specific operation: Based on the product identification results, the server sends a query to the product database to obtain related product information.

[0215] Step 5:

[0216] The server performs a matching evaluation based on the product information acquired and the user's preference information.

[0217] Input: Product information, user preference information (past purchase history, evaluation criteria, tastes).

[0218] Output: Matching evaluation results and scores.

[0219] Specific operation: The server retrieves the user's preference information from the database, compares it with product information, and uses an AI algorithm to evaluate the product's suitability.

[0220] Step 6:

[0221] The server transmits the product information and the matching evaluation result to the smart glasses.

[0222] Input: Product information, matching evaluation results.

[0223] Output: Product information and matching evaluation results sent to the smart glasses.

[0224] Specific operation: The server sends product information and matching scores to the smart glasses terminal. Communication is performed in real time, minimizing data delays.

[0225] Step 7:

[0226] The smart glasses display the received product information and matching evaluation results on a display.

[0227] Input: Received product information and matching evaluation results.

[0228] Output: Product information and matching evaluation results displayed on the smart glasses display.

[0229] Specific operation: The received information is overlaid on the smart glasses display, allowing the user to view this information within their field of vision.

[0230] These are the specific processing steps of the system. At each step, the AI ​​model and database are accessed effectively, and appropriate product information is immediately provided to the user.

[0231] 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.

[0232] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences.In addition, the system uses an emotion engine to recognize the user's emotions and optimize the display content.This system performs the following processes in cooperation between the terminal and the server.

[0233] First, the user launches the app on a device such as a smartphone or tablet. The user operates the app and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. This image is temporarily saved on the device.

[0234] Next, the device sends the photographed or selected product image and the user's authentication information to the server. Authentication information such as the user ID and location information is also sent. The server then activates an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product.

[0235] The server extracts product features based on the analysis results and retrieves related information from a product information database, such as product reviews, price information, and detailed specifications.

[0236] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of products based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[0237] At this stage, the system utilizes an emotion engine. The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The server uses this emotional information to optimize product recommendations and display content in real time. For example, it adjusts the display to show detailed information when the user is interested, or reduce the amount of information when the user is tired.

[0238] The server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommended summaries.

[0239] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[0240] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the key points of the product.

[0241] The server compiles this data, generates a summary and rating score, and sends it to the device, where users can check this information on their smartphone and make appropriate purchasing decisions.

[0242] The above is an embodiment of the present invention. This system allows users to obtain product information that suits them more quickly and efficiently, and in addition, the use of an emotion engine further improves the user experience.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] The user launches the app on their device. The user operates a device such as a smartphone or tablet and taps the app icon to launch the application.

[0246] Step 2:

[0247] The user takes or selects a product image. The user uses the in-app camera to take a photo of the product they are considering purchasing, or selects an existing image stored on their device. The selected image is temporarily stored on their device.

[0248] Step 3:

[0249] The terminal transmits the product image and user authentication information to the server. The terminal then packets the photographed or selected product image data and authentication information such as the user ID, and transmits them to the server via the Internet.

[0250] Step 4:

[0251] The server launches an AI module to analyze product images. The server inputs the received image data into the image recognition AI and extracts features to identify the product. These features include the brand name, product category, model number, etc.

[0252] Step 5:

[0253] The server retrieves product information from the database. Based on the analysis results, the server searches the database for detailed information, product reviews, price information, etc. of the identified product.

[0254] Step 6:

[0255] The server refers to the user's preference information, and retrieves user profile data such as past purchase history, rating criteria, and preferred categories from a database based on the user authentication information.

[0256] Step 7:

[0257] The server performs a matching evaluation based on product information and user preference information. The server compares the acquired product information with the user preference information and calculates a compatibility score. For example, it evaluates whether the product information matches features that have received high ratings in the past.

[0258] Step 8:

[0259] The emotion engine recognizes the user's emotions. The device's camera and microphone are used to collect the user's facial expressions, voice, and input patterns, and this data is sent to the emotion engine. The emotion engine analyzes this data and recognizes the user's current emotion (e.g., joy, excitement, fatigue, etc.).

[0260] Step 9:

[0261] The server receives the recognition results of the emotion engine and optimizes the display of product information and matching results. The server adjusts the amount and level of detail of the information to be displayed based on the user's emotional state. For example, if the user is excited, more detailed information is displayed, and if the user is tired, less information is displayed.

[0262] Step 10:

[0263] The server generates a recommendation summary and matching results. Based on the acquired product information, matching ratings, and emotion engine results, the server creates summary information to provide to the user. The summary includes product features, user reviews, prices, matching scores, etc.

[0264] Step 11:

[0265] The server sends the generated summary and matching results to the terminal, converts the summary and matching results into a data format such as JSON or XML, and sends it to the terminal.

[0266] Step 12:

[0267] The device analyzes the data received from the server and displays it on the user interface. The device analyzes the received data packets and displays product information, user reviews, prices, matching scores, and recommendation summaries on the app screen.

[0268] This allows the user to check appropriate product information as well as display content optimized for their own emotional state, allowing them to make a purchasing decision.

[0269] Example 2

[0270] 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."

[0271] Conventional product recommendation systems have difficulty efficiently obtaining detailed information about products that users are considering purchasing, and have a particular problem in that they are unable to provide optimal information based on the user's preferences and current emotional state. Furthermore, the inability to instantly provide the information users need causes a lot of stress and reduces their desire to purchase.

[0272] 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.

[0273] In this invention, the server includes a means for the terminal to collect user emotion data and transmit it to the server, a means for the server to optimize product information and display content in real time based on the emotion information, and a means for transmitting product information and matching results from the server to the terminal. This makes it possible to provide optimal product information based on the user's preferences and current emotional state, improving the user experience and encouraging purchasing motivation.

[0274] A "terminal" is an information device operated by a user, and specifically refers to a portable electronic device such as a smartphone or tablet.

[0275] "Server" refers to a central control device that processes data received from terminals via a network and sends analysis results and information to the terminals.

[0276] "Product images" are visual data of products that a user is considering purchasing, and include photographs taken with a camera and existing image files.

[0277] "Authentication information" is data for identifying a user, and specifically includes a user ID, location information, and the like.

[0278] "Artificial intelligence (AI)" refers to technology that uses machine learning models and image analysis algorithms to analyze data and recognize objects and patterns.

[0279] "Product information" refers to data such as product features, reviews, price information, detailed specifications, etc.

[0280] "User preference information" refers to data that indicates the user's preferences, such as the user's past purchasing history, evaluation criteria, and taste patterns.

[0281] The "matching rating" is an evaluation score generated based on product information and user preference information, and indicates how well the user's preferences match the product.

[0282] "Emotional data" refers to data that indicates the user's current emotional state, collected from the user's facial expressions, voice, input patterns, etc.

[0283] "Real-time optimization" refers to instantly adjusting information and display content based on the user's emotional data.

[0284] "Summary" refers to information that briefly summarizes the data that the server has consolidated.

[0285] The "evaluation score" is a numerical representation of the result of the matching evaluation, and indicates the suitability of the product for the user.

[0286] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[0287] First, the user launches a dedicated application on a device such as a smartphone or tablet. The user operates the app's interface and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. The image is then temporarily saved on the device.

[0288] Next, the device sends the captured or selected product image and the user's authentication information (user ID, location information, etc.) to the server. The HTTPS protocol is used for transmission, ensuring data security. The server then launches an artificial intelligence (AI) module such as TensorFlow or OpenCV to analyze the received product image and identify the product.

[0289] The server extracts product features based on the analysis results and retrieves product information from a database (e.g., MySQL (registered trademark) or PostgreSQL). The retrieved information includes product reviews, price information, and detailed specifications.

[0290] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation criteria are based on points that the user values, such as cushioning, color, design, and price.

[0291] Next, the device collects the user's emotional data (facial expressions, voice, input patterns, etc.) and sends it to the server. The device's camera, microphone, and touch sensor are used to collect the emotional data. The server analyzes the emotional data (using, for example, Azure (registered trademark) Face API or Google Cloud Speech-to-Text) and recognizes the user's current emotional state. Based on this emotional information, the server optimizes product recommendations and display content in real time. For example, if the user is excited, the server may display more detailed information, or conversely, if the user is tired, the server may reduce the amount of information.

[0292] Finally, the server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device, which interprets the received data and displays it on the user interface. The display contents include product details, user reviews, prices, matching scores, and recommended summaries.

[0293] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to the server via the app. The server then uses an AI module to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then rates the shoes based on the user's preferences.

[0294] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the product's key points. The server compiles this data, generates a summary and evaluation score, and sends it to the device. The user can then check this information on their smartphone and make an appropriate purchasing decision.

[0295] An example prompt is, "I'm looking to buy some new running shoes. I take a picture of a pair of shoes I'm interested in at the store with my smartphone and send the image to the server through the app. I want the system to analyze the image and retrieve detailed information and reviews about the shoes. I also want the system to optimize the content displayed to the user based on their current emotional state. Please explain the detailed process and how the information is provided to the user."

[0296] This concludes the description of the embodiment of the present invention. This system allows users to quickly and efficiently obtain product information that suits them, and by utilizing the emotion engine, it is possible to support optimal purchasing decisions.

[0297] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0298] Step 1:

[0299] The user launches the app and gets an image of the product.

[0300] Users launch the app on their smartphone or tablet and tap the "Product Photo" button. The camera opens, and the user can either take a photo of the product they are considering purchasing or select a product image from their existing image library. The captured image is temporarily stored in the device's internal storage.

[0301] Input: User operation (obtaining product image)

[0302] Output: Photographed or selected product images

[0303] Step 2:

[0304] The device sends the image and authentication information to the server.

[0305] The device sends the stored product image, user ID, location information (GPS data), and other authentication information to the server using the HTTPS protocol. At this time, the device uses appropriate data encryption methods to ensure the security of the transmitted data.

[0306] Input: Product image, authentication information

[0307] Output: Sends image and authentication information to the server

[0308] Step 3:

[0309] The server analyzes the image and identifies the product.

[0310] The server invokes artificial intelligence (AI) modules such as TensorFlow and OpenCV to analyze the received product image data. These tools are used to identify product details from the image, identifying the brand, model, and characteristics (e.g., shape, color, etc.).

[0311] Input: Product image

[0312] Output: Identified product information (brand, model, features)

[0313] Step 4:

[0314] The server retrieves the product details from the database.

[0315] The server retrieves detailed information about the identified products by querying a database such as MySQL or PostgreSQL, including product reviews, pricing information, and detailed specifications.

[0316] Input: Identified product information

[0317] Output: Product details (reviews, price, specs)

[0318] Step 5:

[0319] The server references the user's preference information.

[0320] The server collects user preference information by referencing the user's past purchase history, rating criteria, etc. from a NoSQL database (e.g., AWS (registered trademark) DynamoDB).

[0321] Input: User ID, past purchase history

[0322] Output: User preference information

[0323] Step 6:

[0324] The server evaluates the matching of the products.

[0325] Based on the acquired product information and the user's preference information, the server performs a matching evaluation of each product attribute (cushioning, color, design, price, etc.) and calculates an overall evaluation score.

[0326] Input: Product details, user preferences

[0327] Output: Matching evaluation score

[0328] Step 7:

[0329] The device collects the user's emotional data.

[0330] While the user is browsing product information, the device uses the front camera, microphone, and touch sensor to collect emotional data such as the user's facial expressions, voice, and tapping speed.

[0331] Input: User actions and behavior

[0332] Output: Collected emotion data

[0333] Step 8:

[0334] The server optimizes the display content based on emotional information.

[0335] The server analyzes the emotional data sent from the device and uses Azure Face API and Google Cloud Speech-to-Text to recognize the user's emotional state. Based on this information, the server optimizes product details and display content in real time. For example, if the user is excited, more details will be displayed, and if the user appears tired, the server will reduce the amount of information displayed.

[0336] Input: Emotion data

[0337] Output: Optimized display content

[0338] Step 9:

[0339] The server generates a summary and an evaluation score and sends them to the terminal.

[0340] The server generates a summary and rating score for each product based on the integrated data, and sends this information to the device in a data format such as JSON.

[0341] Input: Product details, emotion data, matching evaluation score

[0342] Output: Summary and rating score

[0343] Step 10:

[0344] The terminal displays the information on a user interface.

[0345] The device analyzes the received summary and rating score, and displays product information, user reviews, price, and matching score on the user interface, allowing the user to decide whether to purchase the product or not.

[0346] Input: Summary and rating score

[0347] Output: Information displayed in the user interface

[0348] (Application example 2)

[0349] 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."

[0350] In today's world, when users shop online, the wide variety of products available makes it difficult to select the right product. While there is a need to optimize the way product information is displayed based on the user's emotional state, existing systems lack the means to achieve this. Furthermore, there is a need to efficiently obtain detailed information about products that users are interested in, allowing them to make quick and reliable purchasing decisions. However, current technology is not sufficient to address this need.

[0351] 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 means for receiving and analyzing product images photographed or selected from the user's terminal, means for obtaining detailed information about the corresponding product from a database based on the analyzed product information, means for evaluating the matching with the product by referring to the user's preference information, and means for analyzing the user's emotional state using an emotion engine and generating optimized product information based on the results. This allows the user to efficiently obtain detailed information about products in which they are interested, and makes it possible to present information optimized for the user's current emotional state, thereby providing a more effective shopping experience.

[0352] A "terminal" is an electronic device such as a computer, smartphone, or tablet terminal that is operated by a user.

[0353] A "server" is a computer system that receives data from multiple terminals via a network and analyzes and processes it.

[0354] "Product image" refers to image data of a product obtained from the device's camera function or an existing photo.

[0355] "Analysis" is the process of extracting specific information from data and finding meaning and value.

[0356] A "database" is a system for efficiently managing large amounts of data and quickly retrieving necessary information.

[0357] "Matching evaluation" is the process of comparing acquired product information with the user's preference information to evaluate and recommend products that are suitable for the user.

[0358] An "emotion engine" is a system that analyzes a user's facial expressions, voice, and input patterns to recognize their emotional state.

[0359] "Display optimization" is the process of adjusting the amount and detail of information displayed based on the user's emotional state and interests.

[0360] "User preference information" is data such as the user's past purchase history, evaluation criteria, and category preferences.

[0361] This invention provides a system in which a user uses a terminal to take or select an image of a product they are considering purchasing, and the image is analyzed on the server side to obtain detailed product information and perform a matching evaluation based on the user's preferences, and a system that uses an emotion engine to recognize the user's emotional state and optimize the display content.

[0362] First, the user launches the application on a device such as a smartphone or tablet. The user then takes a photo of the product they are considering purchasing using the device's camera or selects a product image from existing photos. This product image is temporarily saved on the device.

[0363] Next, the device sends the photographed or selected product image and the user's authentication information to the server. When sending, authentication information such as the user ID and location information is also sent. The server activates an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product. For example, a "product identification AI model" is used to identify the product.

[0364] The server extracts product features based on the analysis results and retrieves related information from the product information database, such as product reviews, price information, and detailed specifications.

[0365] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of products based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as product functionality, design, and price.

[0366] At this stage, the system utilizes an emotion engine. The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The server uses this emotional information to optimize product recommendations and display content in real time. For example, if the user is excited, detailed information is displayed, and if the user is tired, the amount of information is reduced.

[0367] The server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommended summaries.

[0368] For example, if a user is considering purchasing a pair of running shoes, they can take a photo of the shoes they are interested in at the store with their smartphone and send the image to the server via the application. The server then uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from the database and then evaluates the shoes based on the user's preferences.

[0369] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the key points of the product.

[0370] This process allows users to acquire product information efficiently and accurately. Furthermore, by utilizing the emotion engine, it is possible to provide optimal information according to the user's emotional state, improving the user experience.

[0371] Example prompt sentence:

[0372] "Identify product models from images taken by the user's camera and display detailed information."

[0373] "Analyze the user's facial expressions to recognize their emotions and optimize the product information displayed."

[0374] This will realize a system that allows users to select products smoothly and without stress.

[0375] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0376] Step 1:

[0377] A user launches the application using a device. The user takes a picture of a product they are considering purchasing with the device's camera or selects a product image from existing photos. This product image is temporarily saved on the device. The input is the taken or selected product image, and the output is the saved product image.

[0378] Step 2:

[0379] The device sends the captured or selected product image and the user's authentication information to the server. At this time, authentication information such as the user ID and location information is also sent. The input is the product image and authentication information, and the output is the data sent to the server.

[0380] Step 3:

[0381] The server launches an artificial intelligence (AI) module to analyze the received product images and identify the products by analyzing the image data. For example, a product identification AI model is used. The input is the received product image, and the output is the identified product data. Specifically, deep learning technology is used to extract features within the image and identify the product model.

[0382] Step 4:

[0383] The server extracts product features based on the analysis results and retrieves related information from the product information database. Specifically, product reviews, price information, detailed specifications, etc. are retrieved from the database. The input is the identified product data, and the output is the retrieved product information.

[0384] Step 5:

[0385] The server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a product matching evaluation based on the acquired product information and the user's preference information. The input is product information and user preference information, and the output is the matching evaluation result. Specifically, scoring is performed according to the user's evaluation criteria.

[0386] Step 6:

[0387] The server uses the emotion engine to analyze the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The input is the user's facial expressions, voice, and input patterns, and the output is the recognition result of the emotional state. Specifically, the emotion engine identifies emotions by combining image analysis and voice analysis.

[0388] Step 7:

[0389] The server optimizes product recommendations and display content in real time based on the emotional information. For example, if the user is excited, detailed information is displayed, and if the user is tired, the amount of information is reduced. The input is the recognition result of the emotional state, and the output is the optimized display content.

[0390] Step 8:

[0391] The server integrates this information to generate a summary and an evaluation score. The generated summary and matching results are sent from the server to the device. The input is the optimized display content and matching results, and the output is the data sent to the device.

[0392] Step 9:

[0393] The device analyzes the received data and displays it on a user interface. The displayed content includes detailed product information, user reviews, prices, matching scores, and recommendation summaries. The input is the transmitted data, and the output is the content displayed on the user interface. Specifically, information optimized for the user's preferences and emotions is displayed.

[0394] Through the above steps, a system is realized that allows the user to efficiently obtain detailed information about a target product and presents optimal information based on the user's emotional state.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] [Second embodiment]

[0399] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0400] 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.

[0401] 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).

[0402] 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.

[0403] 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.

[0404] 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).

[0405] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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."

[0411] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[0412] First, the user launches the app on a device such as a smartphone or tablet. The user operates the app and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. This image is temporarily saved on the device.

[0413] The device then sends the captured or selected product image, along with the user's authentication information, to the server, which then activates an artificial intelligence (AI) module to analyze the received product image and identify the product.

[0414] The server extracts product features based on the analysis results and retrieves related information from a product information database, such as product reviews, price information, and detailed specifications.

[0415] In parallel, the server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[0416] The evaluation results and product information are summarized and sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommendation summaries.

[0417] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[0418] For example, the server can summarize the information, such as "These shoes are characterized by high cushioning and light weight, and are very suitable considering the user's past purchase history," and send it to the device along with an evaluation score.The user can then check this information on their smartphone and make an appropriate purchasing decision.

[0419] The above is an embodiment of the present invention. This system allows users to obtain product information that suits them more quickly and efficiently, resulting in a highly satisfying shopping experience.

[0420] The processing flow will be explained below.

[0421] Step 1:

[0422] The user launches the app on their device. The user operates a device such as a smartphone or tablet and taps the app icon to launch the application.

[0423] Step 2:

[0424] The user takes or selects a product image. The user uses the in-app camera to take a photo of the product they are considering purchasing, or selects an existing image stored on their device.

[0425] Step 3:

[0426] The terminal transmits the product image and user authentication information to the server. The terminal then packets the photographed or selected product image data and authentication information such as the user ID, and transmits them to the server via the Internet.

[0427] Step 4:

[0428] The server launches an AI module to analyze product images. The server inputs the received image data into the image recognition AI and extracts features to identify the product. These features include the brand name, product category, model number, etc.

[0429] Step 5:

[0430] The server retrieves product information from the database. Based on the analysis results, the server searches the database for detailed information, product reviews, price information, etc. of the identified product.

[0431] Step 6:

[0432] The server refers to the user's preference information, and retrieves user profile data such as past purchase history, rating criteria, and preferred categories from a database based on the user authentication information.

[0433] Step 7:

[0434] The server performs a matching evaluation based on product information and user preference information. The server compares the acquired product information with the user preference information and calculates a compatibility score. For example, it evaluates whether the product information matches features that have received high ratings in the past.

[0435] Step 8:

[0436] The server generates a recommendation summary and matching results. Based on the acquired product information and matching evaluation, the server creates summary information to provide to the user. The summary includes product features, user reviews, price, matching score, etc.

[0437] Step 9:

[0438] The server sends the generated summary and matching results to the terminal, converts the summary and matching results into a data format such as JSON or XML, and sends it to the terminal.

[0439] Step 10:

[0440] The device analyzes the data received from the server and displays it on the user interface. The device analyzes the received data packets and displays product information, user reviews, prices, matching scores, and recommendation summaries on the app screen.

[0441] This series of processing steps allows the user to quickly and efficiently obtain product information and support purchasing decisions.

[0442] Example 1

[0443] 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."

[0444] Conventional product purchasing support systems have the problem that it is difficult for users to quickly and accurately obtain detailed information about products they are considering purchasing, and they do not perform appropriate matching evaluations based on the user's individual preferences. In particular, to understand the product's features and performance in detail, users must refer to multiple information sources, which is time-consuming and requires effort. Furthermore, product recommendations based on the user's preferences and past purchasing history may not be sufficient, resulting in a decrease in satisfaction.

[0445] 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.

[0446] In this invention, the server includes means for transmitting product images photographed or selected from the terminal to the server, means for analyzing the product images received by the server and identifying the products, means for acquiring characteristics of the products identified by the server from a database, means for performing a matching evaluation based on the product information acquired by the server and user preference information, means for transmitting the product information and matching results from the server to the terminal, and means for displaying the product information and matching results received by the terminal on a user interface. This enables users to quickly obtain detailed information about products they are considering purchasing and receive an appropriate matching evaluation based on their preferences.

[0447] A "terminal" is a computer device operated by a user, such as a smartphone or tablet.

[0448] A "server" is a computer device that receives data sent from a terminal on a network and analyzes and processes it.

[0449] "Photographed or selected product image" refers to image data of a product that the user photographs using the terminal or selects from existing images in the terminal.

[0450] "Means for transmitting" refers to a communication function for transferring data from a terminal to a server.

[0451] "Means for analyzing and identifying products" refers to the function of using artificial intelligence models and algorithms stored on the server to judge the content of the received product images and identify the type and characteristics of the product.

[0452] "Means for obtaining features from a database" refers to the function of the server searching and obtaining detailed product information from a related database based on the analysis results of the product image.

[0453] "Means for performing matching evaluation" refers to an algorithm or system for evaluating and recommending products based on product information acquired by the server and user preference information.

[0454] "User preference information" refers to individual information such as the user's past purchasing history, preferences, and evaluation criteria.

[0455] "Product information and matching results" refers to detailed product information obtained by the server from the database and evaluation results based on the user's preferences.

[0456] "Means for displaying on the user interface" refers to a function for displaying product information and matching results in an easy-to-read format on the terminal screen.

[0457] An "artificial intelligence model" refers to a software model that uses machine learning and deep learning techniques to analyze data and derive results.

[0458] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[0459] First, the user launches a dedicated app on a device such as a smartphone or tablet. The user operates the app to take a picture of the product they are considering purchasing with the camera or select from existing images on the device. This image is temporarily saved on the device.

[0460] Next, the device sends the photographed or selected product image to the server, along with the user's authentication information. HTTPS communication is used as the transmission method. The server then launches an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product. This AI module uses deep learning frameworks such as TensorFlow and PyTorch.

[0461] The server extracts product features based on the analysis results and retrieves related information from a product information database. Specifically, product reviews, price information, detailed specifications, etc. are retrieved from the database. Examples of product information databases used here include Amazon DynamoDB and Google Cloud Firestore.

[0462] In parallel, the server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[0463] The evaluation results and product information are summarized and sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommendation summaries.

[0464] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[0465] For example, the server can summarize the information, such as "These shoes are characterized by high cushioning and light weight, and are very suitable considering the user's past purchase history," and send it to the device along with an evaluation score.The user can then check this information on their smartphone and make an appropriate purchasing decision.

[0466] An example of a prompt for a generative AI model might be, "Analyze images of products I'm considering purchasing and display detailed information and ratings based on the user's preferences."

[0467] This system allows users to obtain product information that suits them more quickly and efficiently, resulting in a more satisfying shopping experience.

[0468] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0469] Step 1:

[0470] Launching the app

[0471] Users tap to launch the dedicated app installed on their smartphone or tablet.

[0472] Specific operation: When the user taps the app icon, the app launches and the initial screen is displayed.

[0473] Input: None

[0474] Output: Initial screen of the app

[0475] Step 2:

[0476] Taking or selecting an image

[0477] Users can use the in-app camera to take a picture of the product they are considering purchasing, or select an existing photo from their gallery.

[0478] Specific behavior: When the user taps the camera button in the app, the camera will launch and take a photo. When the user taps the gallery button, the photo gallery will be displayed and an existing image can be selected.

[0479] Input: User operation (take a photo with the camera or select from the gallery)

[0480] Output: Photographed or selected product images

[0481] Step 3:

[0482] Submit product images

[0483] The terminal sends the photographed or selected product image to the server, along with the user's authentication information.

[0484] Specific operation: The device sends image data and authentication information to the server using HTTPS communication.

[0485] Input: Photographed or selected product image, user authentication information

[0486] Output: Data is sent to the server

[0487] Step 4:

[0488] Image analysis on the server

[0489] The server decodes the received product images and launches an AI module (e.g., TensorFlow or PyTorch) to perform image analysis.

[0490] Specific operation: The server decodes the image data from binary format, inputs it into the AI ​​model, and performs inference.

[0491] Input: Received product image

[0492] Output: Product identification information (e.g. brand, model)

[0493] Step 5:

[0494] Product feature extraction

[0495] The server extracts product features from the image analysis results, such as identifying "running shoes" and "high cushioning."

[0496] Specific operation: The server applies a feature extraction algorithm based on the analysis results to generate product feature information.

[0497] Input: Product identification information

[0498] Output: Product feature information

[0499] Step 6:

[0500] Obtaining product information

[0501] The server retrieves detailed information from a product information database (such as Amazon DynamoDB or Google Cloud Firestore) based on the product's features, including product reviews, prices, and detailed specifications.

[0502] What happens: The server uses SQL queries or API requests to search the database and retrieve relevant information.

[0503] Input: Product feature information

[0504] Output: Product details

[0505] Step 7:

[0506] Referencing user preference information

[0507] The server references user preference information from an internal database, including past purchase history, rating criteria, and category preferences.

[0508] Specific operations: The server queries the user profile database to obtain preference information.

[0509] Input: User credentials

[0510] Output: User preference information

[0511] Step 8:

[0512] Product matching evaluation

[0513] The server evaluates the products based on the product information and the user's preferences. Evaluation criteria include price, design, cushioning, etc.

[0514] Specific operation: The server executes the matching evaluation algorithm and calculates the evaluation score of the product.

[0515] Input: detailed product information, user preferences

[0516] Output: Matching evaluation results (e.g., score, recommendation comments)

[0517] Step 9:

[0518] Sending evaluation results

[0519] The server summarizes the evaluation results and detailed product information and sends them to the terminal.

[0520] Specific operation: The server summarizes the evaluation results and detailed product information and sends them to the terminal using HTTPS communication.

[0521] Input: Matching evaluation results, product details

[0522] Output: Transmission data (evaluation results and detailed product information)

[0523] Step 10:

[0524] Receiving data

[0525] The terminal receives the evaluation results and product information sent from the server.

[0526] Specific operation: The device receives and decodes data using HTTPS communication.

[0527] Input: Data to be sent (evaluation results and detailed product information)

[0528] Output: Received data (evaluation results and detailed product information)

[0529] Step 11:

[0530] Display in the user interface

[0531] The device analyzes the received data and displays information about the product (such as reviews, price, matching score, and recommendation summary) in the app's user interface.

[0532] Specific operation: The device parses the data, binds it to UI components, and displays it.

[0533] Input: Received data (evaluation results and detailed product information)

[0534] Output: Display on the user interface

[0535] (Application example 1)

[0536] 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."

[0537] Conventional product purchasing support systems for brick-and-mortar stores have difficulty providing detailed product information or recommendations tailored to the user's preferences in real time when the user is selecting products in the store. As a result, users often spend time and effort finding the product that best suits them, resulting in an unsatisfactory purchasing experience. Furthermore, existing technologies rely on the use of terminals, so there is a demand for more portable and intuitive interaction. Therefore, there is a growing need for a system that can provide users with appropriate product information and recommendations in real time and intuitively.

[0538] 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.

[0539] In this invention, the server includes means for transmitting product images photographed or selected from the terminal to the server, means for analyzing the product images received by the server and identifying the products, means for acquiring the features of the products identified by the server from a database, means for performing a matching evaluation based on the product information acquired by the server and user preference information, means for transmitting the product information and matching results from the server to the terminal, means for displaying the product information and matching results received by the terminal, and means for analyzing the product images photographed by the smart glasses in real time, performing a matching evaluation based on the features of the identified products and user preference information, and displaying the evaluation on the smart glasses. This allows users to intuitively and quickly obtain product information in a physical store and easily select the product that best suits them.

[0540] "Terminal" refers to any device operated by a user, specifically including smartphones, tablets, smart glasses, and the like.

[0541] A "server" is a computer system that receives data sent from terminals via a network and analyzes and processes the data.

[0542] "Product image" is image data that includes visual information of a product that the user is considering purchasing.

[0543] "Analysis" is the process of extracting features from product images and identifying the product using specific algorithms.

[0544] "Identification" is the act of identifying a product from an analyzed product image and obtaining specific information about it.

[0545] "Features" refer to identifiable properties or attributes of a product, including information such as brand, model, price, and specifications.

[0546] A "database" is a collection of information that stores product information and user information, and is a system that a server accesses to obtain the necessary data.

[0547] "Matching evaluation" is a process of evaluating the suitability of a product based on the acquired product information and user preference information.

[0548] "Smart glasses" are wearable devices that can be worn by a user and digitally display information within their field of vision.

[0549] "Real-time" refers to data being processed and displayed immediately as it is generated.

[0550] "User preference information" is a group of data that collects information such as preferences, purchase history, and evaluation criteria that a user has previously shown.

[0551] "Product information" is detailed data about a product, including general information such as reviews, price, and specifications.

[0552] "Display" refers to the act of visually conveying the analysis results or evaluation results to the user.

[0553] This invention is a system that uses smart glasses to analyze product information in real time when a user selects a product in a physical store and recommends products based on the user's preferences. The system includes a terminal, a server, smart glasses, an artificial intelligence (AI) module, a product database, and a user interface.

[0554] First, a user puts on smart glasses and walks around a physical store, selecting products. When they find a product they are interested in, they use the smart glasses' camera to take a picture of the product. The captured product image is sent to a server via the smart glasses' terminal function. The user's authentication information is also attached when the image is sent.

[0555] The server launches an AI module to analyze the received product images. The AI ​​module uses an image analysis algorithm to identify the product and extract its features. This feature information includes the brand, model, price, and specifications. The server retrieves the identified product information from the product database and performs a matching evaluation with the user information.

[0556] The matching evaluation refers to the user's past purchase history, evaluation criteria, and preference information. The server evaluates the suitability of the product based on the acquired product information and the user's preference information. The evaluation results and product information are sent from the server to the smart glasses in real time.

[0557] The smart glasses display the received product information and matching evaluation results on a screen. The user can check the information displayed in their field of view and decide whether the product is one they are interested in purchasing. This real-time display allows users to quickly and efficiently obtain product information that suits them.

[0558] As a concrete example, let's say a user is looking for running shoes in a physical store. The user walks around the store using smart glasses, and when they find a pair of shoes they like, they take a picture of them. The server uses an AI module to analyze the image and identify the characteristics of the running shoes. For example, it might evaluate the shoes as "highly cushioned and lightweight, and considering your past purchase history, they are a perfect fit." This information and evaluation score are displayed on the smart glasses, allowing the user to quickly make the right purchase decision.

[0559] A specific example of a prompt sentence for a generative AI model is as follows:

[0560] Example prompt sentence:

[0561] "Based on the images taken by the user in the store, please perform the following analysis:

[0562] 1. Product Identification

[0563] 2. After product identification, return the product brand, model, and features

[0564] 3. Provide relevant information (reviews, prices, specs) based on each feature.

[0565] As described above, the present invention realizes a system that can provide detailed product information and recommendation information based on the user's preferences in real time when the user is selecting a product in a physical store.

[0566] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0567] Step 1:

[0568] A user uses smart glasses to take an image of an item of interest.

[0569] Input: Product images taken by the smart glasses camera.

[0570] Output: Product image data temporarily saved on the device.

[0571] Specific operation: While walking around the store, the user uses the smart glasses to take a picture of a product they are interested in. This image data is temporarily stored in the smart glasses' memory.

[0572] Step 2:

[0573] The terminal sends the product image and the user's authentication information to the server.

[0574] Input: Product image data, user authentication information (user ID, etc.).

[0575] Output: Product image and authentication information sent to the server.

[0576] How it works: The application on the smart glasses terminal uploads product images and user authentication information to the server, where the data is encrypted and transmitted via a security protocol.

[0577] Step 3:

[0578] The server analyzes the received product image and activates an AI module to identify the product.

[0579] Input: Product image data sent to the server.

[0580] Output: Product identification results and feature extraction results.

[0581] How it works: The AI ​​module in the server analyzes product images and uses image recognition algorithms to identify the product's brand, model, and features. The results of this identification are temporarily stored on the server.

[0582] Step 4:

[0583] The server retrieves the characteristics of the identified product from a database.

[0584] Input: Product identification results (brand, model, features, etc.).

[0585] Output: Detailed product information (reviews, price, specs, etc.) retrieved from the database.

[0586] Specific operation: Based on the product identification results, the server sends a query to the product database to obtain related product information.

[0587] Step 5:

[0588] The server performs a matching evaluation based on the product information acquired and the user's preference information.

[0589] Input: Product information, user preference information (past purchase history, evaluation criteria, tastes).

[0590] Output: Matching evaluation results and scores.

[0591] Specific operation: The server retrieves the user's preference information from the database, compares it with product information, and uses an AI algorithm to evaluate the product's suitability.

[0592] Step 6:

[0593] The server transmits the product information and the matching evaluation result to the smart glasses.

[0594] Input: Product information, matching evaluation results.

[0595] Output: Product information and matching evaluation results sent to the smart glasses.

[0596] Specific operation: The server sends product information and matching scores to the smart glasses terminal. Communication is performed in real time, minimizing data delays.

[0597] Step 7:

[0598] The smart glasses display the received product information and matching evaluation results on a display.

[0599] Input: Received product information and matching evaluation results.

[0600] Output: Product information and matching evaluation results displayed on the smart glasses display.

[0601] Specific operation: The received information is overlaid on the smart glasses display, allowing the user to view this information within their field of vision.

[0602] These are the specific processing steps of the system. At each step, the AI ​​model and database are accessed effectively, and appropriate product information is immediately provided to the user.

[0603] 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.

[0604] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences.In addition, the system uses an emotion engine to recognize the user's emotions and optimize the display content.This system performs the following processes in cooperation between the terminal and the server.

[0605] First, the user launches the app on a device such as a smartphone or tablet. The user operates the app and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. This image is temporarily saved on the device.

[0606] Next, the device sends the photographed or selected product image and the user's authentication information to the server. Authentication information such as the user ID and location information is also sent. The server then activates an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product.

[0607] The server extracts product features based on the analysis results and retrieves related information from a product information database, such as product reviews, price information, and detailed specifications.

[0608] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of products based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[0609] At this stage, the system utilizes an emotion engine. The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The server uses this emotional information to optimize product recommendations and display content in real time. For example, it adjusts the display to show detailed information when the user is interested, or reduce the amount of information when the user is tired.

[0610] The server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommended summaries.

[0611] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[0612] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the key points of the product.

[0613] The server compiles this data, generates a summary and rating score, and sends it to the device, where users can check this information on their smartphone and make appropriate purchasing decisions.

[0614] The above is an embodiment of the present invention. This system allows users to obtain product information that suits them more quickly and efficiently, and in addition, the use of an emotion engine further improves the user experience.

[0615] The processing flow will be explained below.

[0616] Step 1:

[0617] The user launches the app on their device. The user operates a device such as a smartphone or tablet and taps the app icon to launch the application.

[0618] Step 2:

[0619] The user takes or selects a product image. The user uses the in-app camera to take a photo of the product they are considering purchasing, or selects an existing image stored on their device. The selected image is temporarily stored on their device.

[0620] Step 3:

[0621] The terminal transmits the product image and user authentication information to the server. The terminal then packets the photographed or selected product image data and authentication information such as the user ID, and transmits them to the server via the Internet.

[0622] Step 4:

[0623] The server launches an AI module to analyze product images. The server inputs the received image data into the image recognition AI and extracts features to identify the product. These features include the brand name, product category, model number, etc.

[0624] Step 5:

[0625] The server retrieves product information from the database. Based on the analysis results, the server searches the database for detailed information, product reviews, price information, etc. of the identified product.

[0626] Step 6:

[0627] The server refers to the user's preference information, and retrieves user profile data such as past purchase history, rating criteria, and preferred categories from a database based on the user authentication information.

[0628] Step 7:

[0629] The server performs a matching evaluation based on product information and user preference information. The server compares the acquired product information with the user preference information and calculates a compatibility score. For example, it evaluates whether the product information matches features that have received high ratings in the past.

[0630] Step 8:

[0631] The emotion engine recognizes the user's emotions. The device's camera and microphone are used to collect the user's facial expressions, voice, and input patterns, and this data is sent to the emotion engine. The emotion engine analyzes this data and recognizes the user's current emotion (e.g., joy, excitement, fatigue, etc.).

[0632] Step 9:

[0633] The server receives the recognition results of the emotion engine and optimizes the display of product information and matching results. The server adjusts the amount and level of detail of the information to be displayed based on the user's emotional state. For example, if the user is excited, more detailed information is displayed, and if the user is tired, less information is displayed.

[0634] Step 10:

[0635] The server generates a recommendation summary and matching results. Based on the acquired product information, matching ratings, and emotion engine results, the server creates summary information to provide to the user. The summary includes product features, user reviews, prices, matching scores, etc.

[0636] Step 11:

[0637] The server sends the generated summary and matching results to the terminal, converts the summary and matching results into a data format such as JSON or XML, and sends it to the terminal.

[0638] Step 12:

[0639] The device analyzes the data received from the server and displays it on the user interface. The device analyzes the received data packets and displays product information, user reviews, prices, matching scores, and recommendation summaries on the app screen.

[0640] This allows the user to check appropriate product information as well as display content optimized for their own emotional state, allowing them to make a purchasing decision.

[0641] Example 2

[0642] 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."

[0643] Conventional product recommendation systems have difficulty efficiently obtaining detailed information about products that users are considering purchasing, and have a particular problem in that they are unable to provide optimal information based on the user's preferences and current emotional state. Furthermore, the inability to instantly provide the information users need causes a lot of stress and reduces their desire to purchase.

[0644] 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.

[0645] In this invention, the server includes a means for the terminal to collect user emotion data and transmit it to the server, a means for the server to optimize product information and display content in real time based on the emotion information, and a means for transmitting product information and matching results from the server to the terminal. This makes it possible to provide optimal product information based on the user's preferences and current emotional state, improving the user experience and encouraging purchasing motivation.

[0646] A "terminal" is an information device operated by a user, and specifically refers to a portable electronic device such as a smartphone or tablet.

[0647] "Server" refers to a central control device that processes data received from terminals via a network and sends analysis results and information to the terminals.

[0648] "Product images" are visual data of products that a user is considering purchasing, and include photographs taken with a camera and existing image files.

[0649] "Authentication information" is data for identifying a user, and specifically includes a user ID, location information, and the like.

[0650] "Artificial intelligence (AI)" refers to technology that uses machine learning models and image analysis algorithms to analyze data and recognize objects and patterns.

[0651] "Product information" refers to data such as product features, reviews, price information, detailed specifications, etc.

[0652] "User preference information" refers to data that indicates the user's preferences, such as the user's past purchasing history, evaluation criteria, and taste patterns.

[0653] The "matching rating" is an evaluation score generated based on product information and user preference information, and indicates how well the user's preferences match the product.

[0654] "Emotional data" refers to data that indicates the user's current emotional state, collected from the user's facial expressions, voice, input patterns, etc.

[0655] "Real-time optimization" refers to instantly adjusting information and display content based on the user's emotional data.

[0656] "Summary" refers to information that briefly summarizes the data that the server has consolidated.

[0657] The "evaluation score" is a numerical representation of the result of the matching evaluation, and indicates the suitability of the product for the user.

[0658] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[0659] First, the user launches a dedicated application on a device such as a smartphone or tablet. The user operates the app's interface and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. The image is then temporarily saved on the device.

[0660] Next, the device sends the captured or selected product image and the user's authentication information (user ID, location information, etc.) to the server. The HTTPS protocol is used for transmission, ensuring data security. The server then launches an artificial intelligence (AI) module such as TensorFlow or OpenCV to analyze the received product image and identify the product.

[0661] The server extracts product features based on the analysis results and retrieves product information from a database (e.g., MySQL or PostgreSQL). The retrieved information includes product reviews, price information, and detailed specifications.

[0662] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation criteria are based on points that the user values, such as cushioning, color, design, and price.

[0663] Next, the device collects the user's emotional data (facial expressions, voice, input patterns, etc.) and sends it to the server. The device's camera, microphone, and touch sensor are used to collect the emotional data. The server analyzes the emotional data (using, for example, Azure Face API or Google Cloud Speech-to-Text) and recognizes the user's current emotional state. Based on this emotional information, the server optimizes product recommendations and display content in real time. For example, if the user is excited, the server may display more detailed information, or, conversely, if the user is tired, it may reduce the amount of information.

[0664] Finally, the server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device, which interprets the received data and displays it on the user interface. The display contents include product details, user reviews, prices, matching scores, and recommended summaries.

[0665] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to the server via the app. The server then uses an AI module to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then rates the shoes based on the user's preferences.

[0666] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the product's key points. The server compiles this data, generates a summary and evaluation score, and sends it to the device. The user can then check this information on their smartphone and make an appropriate purchasing decision.

[0667] An example prompt is, "I'm looking to buy some new running shoes. I take a picture of a pair of shoes I'm interested in at the store with my smartphone and send the image to the server through the app. I want the system to analyze the image and retrieve detailed information and reviews about the shoes. I also want the system to optimize the content displayed to the user based on their current emotional state. Please explain the detailed process and how the information is provided to the user."

[0668] This concludes the description of the embodiment of the present invention. This system allows users to quickly and efficiently obtain product information that suits them, and by utilizing the emotion engine, it is possible to support optimal purchasing decisions.

[0669] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0670] Step 1:

[0671] The user launches the app and gets an image of the product.

[0672] Users launch the app on their smartphone or tablet and tap the "Product Photo" button. The camera opens, and the user can either take a photo of the product they are considering purchasing or select a product image from their existing image library. The captured image is temporarily stored in the device's internal storage.

[0673] Input: User operation (obtaining product image)

[0674] Output: Photographed or selected product images

[0675] Step 2:

[0676] The device sends the image and authentication information to the server.

[0677] The device sends the stored product image, user ID, location information (GPS data), and other authentication information to the server using the HTTPS protocol. At this time, the device uses appropriate data encryption methods to ensure the security of the transmitted data.

[0678] Input: Product image, authentication information

[0679] Output: Sends image and authentication information to the server

[0680] Step 3:

[0681] The server analyzes the image and identifies the product.

[0682] The server invokes artificial intelligence (AI) modules such as TensorFlow and OpenCV to analyze the received product image data. These tools are used to identify product details from the image, identifying the brand, model, and characteristics (e.g., shape, color, etc.).

[0683] Input: Product image

[0684] Output: Identified product information (brand, model, features)

[0685] Step 4:

[0686] The server retrieves the product details from the database.

[0687] The server retrieves detailed information about the identified products by querying a database such as MySQL or PostgreSQL, including product reviews, pricing information, and detailed specifications.

[0688] Input: Identified product information

[0689] Output: Product details (reviews, price, specs)

[0690] Step 5:

[0691] The server references the user's preference information.

[0692] The server collects user preference information by referencing the user's past purchase history and evaluation criteria from a NoSQL database (e.g., AWS DynamoDB).

[0693] Input: User ID, past purchase history

[0694] Output: User preference information

[0695] Step 6:

[0696] The server evaluates the matching of the products.

[0697] Based on the acquired product information and the user's preference information, the server performs a matching evaluation of each product attribute (cushioning, color, design, price, etc.) and calculates an overall evaluation score.

[0698] Input: Product details, user preferences

[0699] Output: Matching evaluation score

[0700] Step 7:

[0701] The device collects the user's emotional data.

[0702] While the user is browsing product information, the device uses the front camera, microphone, and touch sensor to collect emotional data such as the user's facial expressions, voice, and tapping speed.

[0703] Input: User actions and behavior

[0704] Output: Collected emotion data

[0705] Step 8:

[0706] The server optimizes the display content based on emotional information.

[0707] The server analyzes the emotional data sent from the device and uses Azure Face API and Google Cloud Speech-to-Text to recognize the user's emotional state. Based on this information, the server optimizes product details and display content in real time. For example, if the user is excited, more details will be displayed, and if the user appears tired, the server will reduce the amount of information displayed.

[0708] Input: Emotion data

[0709] Output: Optimized display content

[0710] Step 9:

[0711] The server generates a summary and an evaluation score and sends them to the terminal.

[0712] The server generates a summary and rating score for each product based on the integrated data, and sends this information to the device in a data format such as JSON.

[0713] Input: Product details, emotion data, matching evaluation score

[0714] Output: Summary and rating score

[0715] Step 10:

[0716] The terminal displays the information on a user interface.

[0717] The device analyzes the received summary and rating score, and displays product information, user reviews, price, and matching score on the user interface, allowing the user to decide whether to purchase the product or not.

[0718] Input: Summary and rating score

[0719] Output: Information displayed in the user interface

[0720] (Application example 2)

[0721] 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."

[0722] In today's world, when users shop online, the wide variety of products available makes it difficult to select the right product. While there is a need to optimize the way product information is displayed based on the user's emotional state, existing systems lack the means to achieve this. Furthermore, there is a need to efficiently obtain detailed information about products that users are interested in, allowing them to make quick and reliable purchasing decisions. However, current technology is not sufficient to address this need.

[0723] 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 means for receiving and analyzing product images photographed or selected from the user's terminal, means for obtaining detailed information about the corresponding product from a database based on the analyzed product information, means for evaluating the matching with the product by referring to the user's preference information, and means for analyzing the user's emotional state using an emotion engine and generating optimized product information based on the results. This allows the user to efficiently obtain detailed information about products in which they are interested, and makes it possible to present information optimized for the user's current emotional state, thereby providing a more effective shopping experience.

[0724] A "terminal" is an electronic device such as a computer, smartphone, or tablet terminal that is operated by a user.

[0725] A "server" is a computer system that receives data from multiple terminals via a network and analyzes and processes it.

[0726] "Product image" refers to image data of a product obtained from the device's camera function or an existing photo.

[0727] "Analysis" is the process of extracting specific information from data and finding meaning and value.

[0728] A "database" is a system for efficiently managing large amounts of data and quickly retrieving necessary information.

[0729] "Matching evaluation" is the process of comparing acquired product information with the user's preference information to evaluate and recommend products that are suitable for the user.

[0730] An "emotion engine" is a system that analyzes a user's facial expressions, voice, and input patterns to recognize their emotional state.

[0731] "Display optimization" is the process of adjusting the amount and detail of information displayed based on the user's emotional state and interests.

[0732] "User preference information" is data such as the user's past purchase history, evaluation criteria, and category preferences.

[0733] This invention provides a system in which a user uses a terminal to take or select an image of a product they are considering purchasing, and the image is analyzed on the server side to obtain detailed product information and perform a matching evaluation based on the user's preferences, and a system that uses an emotion engine to recognize the user's emotional state and optimize the display content.

[0734] First, the user launches the application on a device such as a smartphone or tablet. The user then takes a photo of the product they are considering purchasing using the device's camera or selects a product image from existing photos. This product image is temporarily saved on the device.

[0735] Next, the device sends the photographed or selected product image and the user's authentication information to the server. When sending, authentication information such as the user ID and location information is also sent. The server activates an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product. For example, a "product identification AI model" is used to identify the product.

[0736] The server extracts product features based on the analysis results and retrieves related information from the product information database, such as product reviews, price information, and detailed specifications.

[0737] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of products based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as product functionality, design, and price.

[0738] At this stage, the system utilizes an emotion engine. The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The server uses this emotional information to optimize product recommendations and display content in real time. For example, if the user is excited, detailed information is displayed, and if the user is tired, the amount of information is reduced.

[0739] The server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommended summaries.

[0740] For example, if a user is considering purchasing a pair of running shoes, they can take a photo of the shoes they are interested in at the store with their smartphone and send the image to the server via the application. The server then uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from the database and then evaluates the shoes based on the user's preferences.

[0741] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the key points of the product.

[0742] This process allows users to acquire product information efficiently and accurately. Furthermore, by utilizing the emotion engine, it is possible to provide optimal information according to the user's emotional state, improving the user experience.

[0743] Example prompt sentence:

[0744] "Identify product models from images taken by the user's camera and display detailed information."

[0745] "Analyze the user's facial expressions to recognize their emotions and optimize the product information displayed."

[0746] This will realize a system that allows users to select products smoothly and without stress.

[0747] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0748] Step 1:

[0749] A user launches the application using a device. The user takes a picture of a product they are considering purchasing with the device's camera or selects a product image from existing photos. This product image is temporarily saved on the device. The input is the taken or selected product image, and the output is the saved product image.

[0750] Step 2:

[0751] The device sends the captured or selected product image and the user's authentication information to the server. At this time, authentication information such as the user ID and location information is also sent. The input is the product image and authentication information, and the output is the data sent to the server.

[0752] Step 3:

[0753] The server launches an artificial intelligence (AI) module to analyze the received product images and identify the products by analyzing the image data. For example, a product identification AI model is used. The input is the received product image, and the output is the identified product data. Specifically, deep learning technology is used to extract features within the image and identify the product model.

[0754] Step 4:

[0755] The server extracts product features based on the analysis results and retrieves related information from the product information database. Specifically, product reviews, price information, detailed specifications, etc. are retrieved from the database. The input is the identified product data, and the output is the retrieved product information.

[0756] Step 5:

[0757] The server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a product matching evaluation based on the acquired product information and the user's preference information. The input is product information and user preference information, and the output is the matching evaluation result. Specifically, scoring is performed according to the user's evaluation criteria.

[0758] Step 6:

[0759] The server uses the emotion engine to analyze the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The input is the user's facial expressions, voice, and input patterns, and the output is the recognition result of the emotional state. Specifically, the emotion engine identifies emotions by combining image analysis and voice analysis.

[0760] Step 7:

[0761] The server optimizes product recommendations and display content in real time based on the emotional information. For example, if the user is excited, detailed information is displayed, and if the user is tired, the amount of information is reduced. The input is the recognition result of the emotional state, and the output is the optimized display content.

[0762] Step 8:

[0763] The server integrates this information to generate a summary and an evaluation score. The generated summary and matching results are sent from the server to the device. The input is the optimized display content and matching results, and the output is the data sent to the device.

[0764] Step 9:

[0765] The device analyzes the received data and displays it on a user interface. The displayed content includes detailed product information, user reviews, prices, matching scores, and recommendation summaries. The input is the transmitted data, and the output is the content displayed on the user interface. Specifically, information optimized for the user's preferences and emotions is displayed.

[0766] Through the above steps, a system is realized that allows the user to efficiently obtain detailed information about a target product and presents optimal information based on the user's emotional state.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] [Third embodiment]

[0771] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0772] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0773] 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).

[0774] 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.

[0775] 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.

[0776] 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).

[0777] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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."

[0783] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[0784] First, the user launches the app on a device such as a smartphone or tablet. The user operates the app and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. This image is temporarily saved on the device.

[0785] The device then sends the captured or selected product image, along with the user's authentication information, to the server, which then activates an artificial intelligence (AI) module to analyze the received product image and identify the product.

[0786] The server extracts product features based on the analysis results and retrieves related information from a product information database, such as product reviews, price information, and detailed specifications.

[0787] In parallel, the server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[0788] The evaluation results and product information are summarized and sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommendation summaries.

[0789] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[0790] For example, the server can summarize the information, such as "These shoes are characterized by high cushioning and light weight, and are very suitable considering the user's past purchase history," and send it to the device along with an evaluation score.The user can then check this information on their smartphone and make an appropriate purchasing decision.

[0791] The above is an embodiment of the present invention. This system allows users to obtain product information that suits them more quickly and efficiently, resulting in a highly satisfying shopping experience.

[0792] The processing flow will be explained below.

[0793] Step 1:

[0794] The user launches the app on their device. The user operates a device such as a smartphone or tablet and taps the app icon to launch the application.

[0795] Step 2:

[0796] The user takes or selects a product image. The user uses the in-app camera to take a photo of the product they are considering purchasing, or selects an existing image stored on their device.

[0797] Step 3:

[0798] The terminal transmits the product image and user authentication information to the server. The terminal then packets the photographed or selected product image data and authentication information such as the user ID, and transmits them to the server via the Internet.

[0799] Step 4:

[0800] The server launches an AI module to analyze product images. The server inputs the received image data into the image recognition AI and extracts features to identify the product. These features include the brand name, product category, model number, etc.

[0801] Step 5:

[0802] The server retrieves product information from the database. Based on the analysis results, the server searches the database for detailed information, product reviews, price information, etc. of the identified product.

[0803] Step 6:

[0804] The server refers to the user's preference information, and retrieves user profile data such as past purchase history, rating criteria, and preferred categories from a database based on the user authentication information.

[0805] Step 7:

[0806] The server performs a matching evaluation based on product information and user preference information. The server compares the acquired product information with the user preference information and calculates a compatibility score. For example, it evaluates whether the product information matches features that have received high ratings in the past.

[0807] Step 8:

[0808] The server generates a recommendation summary and matching results. Based on the acquired product information and matching evaluation, the server creates summary information to provide to the user. The summary includes product features, user reviews, price, matching score, etc.

[0809] Step 9:

[0810] The server sends the generated summary and matching results to the terminal, converts the summary and matching results into a data format such as JSON or XML, and sends it to the terminal.

[0811] Step 10:

[0812] The device analyzes the data received from the server and displays it on the user interface. The device analyzes the received data packets and displays product information, user reviews, prices, matching scores, and recommendation summaries on the app screen.

[0813] This series of processing steps allows the user to quickly and efficiently obtain product information and support purchasing decisions.

[0814] Example 1

[0815] 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."

[0816] Conventional product purchasing support systems have the problem that it is difficult for users to quickly and accurately obtain detailed information about products they are considering purchasing, and they do not perform appropriate matching evaluations based on the user's individual preferences. In particular, to understand the product's features and performance in detail, users must refer to multiple information sources, which is time-consuming and requires effort. Furthermore, product recommendations based on the user's preferences and past purchasing history may not be sufficient, resulting in a decrease in satisfaction.

[0817] 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.

[0818] In this invention, the server includes means for transmitting product images photographed or selected from the terminal to the server, means for analyzing the product images received by the server and identifying the products, means for acquiring characteristics of the products identified by the server from a database, means for performing a matching evaluation based on the product information acquired by the server and user preference information, means for transmitting the product information and matching results from the server to the terminal, and means for displaying the product information and matching results received by the terminal on a user interface. This enables users to quickly obtain detailed information about products they are considering purchasing and receive an appropriate matching evaluation based on their preferences.

[0819] A "terminal" is a computer device operated by a user, such as a smartphone or tablet.

[0820] A "server" is a computer device that receives data sent from a terminal on a network and analyzes and processes it.

[0821] "Photographed or selected product image" refers to image data of a product that the user photographs using the terminal or selects from existing images in the terminal.

[0822] "Means for transmitting" refers to a communication function for transferring data from a terminal to a server.

[0823] "Means for analyzing and identifying products" refers to the function of using artificial intelligence models and algorithms stored on the server to judge the content of the received product images and identify the type and characteristics of the product.

[0824] "Means for obtaining features from a database" refers to the function of the server searching and obtaining detailed product information from a related database based on the analysis results of the product image.

[0825] "Means for performing matching evaluation" refers to an algorithm or system for evaluating and recommending products based on product information acquired by the server and user preference information.

[0826] "User preference information" refers to individual information such as the user's past purchasing history, preferences, and evaluation criteria.

[0827] "Product information and matching results" refers to detailed product information obtained by the server from the database and evaluation results based on the user's preferences.

[0828] "Means for displaying on the user interface" refers to a function for displaying product information and matching results in an easy-to-read format on the terminal screen.

[0829] An "artificial intelligence model" refers to a software model that uses machine learning and deep learning techniques to analyze data and derive results.

[0830] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[0831] First, the user launches a dedicated app on a device such as a smartphone or tablet. The user operates the app to take a picture of the product they are considering purchasing with the camera or select from existing images on the device. This image is temporarily saved on the device.

[0832] Next, the device sends the photographed or selected product image to the server, along with the user's authentication information. HTTPS communication is used as the transmission method. The server then launches an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product. This AI module uses deep learning frameworks such as TensorFlow and PyTorch.

[0833] The server extracts product features based on the analysis results and retrieves related information from a product information database. Specifically, product reviews, price information, detailed specifications, etc. are retrieved from the database. Examples of product information databases used here include Amazon DynamoDB and Google Cloud Firestore.

[0834] In parallel, the server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[0835] The evaluation results and product information are summarized and sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommendation summaries.

[0836] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[0837] For example, the server can summarize the information, such as "These shoes are characterized by high cushioning and light weight, and are very suitable considering the user's past purchase history," and send it to the device along with an evaluation score.The user can then check this information on their smartphone and make an appropriate purchasing decision.

[0838] An example of a prompt for a generative AI model might be, "Analyze images of products I'm considering purchasing and display detailed information and ratings based on the user's preferences."

[0839] This system allows users to obtain product information that suits them more quickly and efficiently, resulting in a more satisfying shopping experience.

[0840] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0841] Step 1:

[0842] Launching the app

[0843] Users tap to launch the dedicated app installed on their smartphone or tablet.

[0844] Specific operation: When the user taps the app icon, the app launches and the initial screen is displayed.

[0845] Input: None

[0846] Output: Initial screen of the app

[0847] Step 2:

[0848] Taking or selecting an image

[0849] Users can use the in-app camera to take a picture of the product they are considering purchasing, or select an existing photo from their gallery.

[0850] Specific behavior: When the user taps the camera button in the app, the camera will launch and take a photo. When the user taps the gallery button, the photo gallery will be displayed and an existing image can be selected.

[0851] Input: User operation (take a photo with the camera or select from the gallery)

[0852] Output: Photographed or selected product images

[0853] Step 3:

[0854] Submit product images

[0855] The terminal sends the photographed or selected product image to the server, along with the user's authentication information.

[0856] Specific operation: The device sends image data and authentication information to the server using HTTPS communication.

[0857] Input: Photographed or selected product image, user authentication information

[0858] Output: Data is sent to the server

[0859] Step 4:

[0860] Image analysis on the server

[0861] The server decodes the received product images and launches an AI module (e.g., TensorFlow or PyTorch) to perform image analysis.

[0862] Specific operation: The server decodes the image data from binary format, inputs it into the AI ​​model, and performs inference.

[0863] Input: Received product image

[0864] Output: Product identification information (e.g. brand, model)

[0865] Step 5:

[0866] Product feature extraction

[0867] The server extracts product features from the image analysis results, such as identifying "running shoes" and "high cushioning."

[0868] Specific operation: The server applies a feature extraction algorithm based on the analysis results to generate product feature information.

[0869] Input: Product identification information

[0870] Output: Product feature information

[0871] Step 6:

[0872] Obtaining product information

[0873] The server retrieves detailed information from a product information database (such as Amazon DynamoDB or Google Cloud Firestore) based on the product's features, including product reviews, prices, and detailed specifications.

[0874] What happens: The server uses SQL queries or API requests to search the database and retrieve relevant information.

[0875] Input: Product feature information

[0876] Output: Product details

[0877] Step 7:

[0878] Referencing user preference information

[0879] The server references user preference information from an internal database, including past purchase history, rating criteria, and category preferences.

[0880] Specific operations: The server queries the user profile database to obtain preference information.

[0881] Input: User credentials

[0882] Output: User preference information

[0883] Step 8:

[0884] Product matching evaluation

[0885] The server evaluates the products based on the product information and the user's preferences. Evaluation criteria include price, design, cushioning, etc.

[0886] Specific operation: The server executes the matching evaluation algorithm and calculates the evaluation score of the product.

[0887] Input: detailed product information, user preferences

[0888] Output: Matching evaluation results (e.g., score, recommendation comments)

[0889] Step 9:

[0890] Sending evaluation results

[0891] The server summarizes the evaluation results and detailed product information and sends them to the terminal.

[0892] Specific operation: The server summarizes the evaluation results and detailed product information and sends them to the terminal using HTTPS communication.

[0893] Input: Matching evaluation results, product details

[0894] Output: Transmission data (evaluation results and detailed product information)

[0895] Step 10:

[0896] Receiving data

[0897] The terminal receives the evaluation results and product information sent from the server.

[0898] Specific operation: The device receives and decodes data using HTTPS communication.

[0899] Input: Data to be sent (evaluation results and detailed product information)

[0900] Output: Received data (evaluation results and detailed product information)

[0901] Step 11:

[0902] Display in the user interface

[0903] The device analyzes the received data and displays information about the product (such as reviews, price, matching score, and recommendation summary) in the app's user interface.

[0904] Specific operation: The device parses the data, binds it to UI components, and displays it.

[0905] Input: Received data (evaluation results and detailed product information)

[0906] Output: Display on the user interface

[0907] (Application example 1)

[0908] 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."

[0909] Conventional product purchasing support systems for brick-and-mortar stores have difficulty providing detailed product information or recommendations tailored to the user's preferences in real time when the user is selecting products in the store. As a result, users often spend time and effort finding the product that best suits them, resulting in an unsatisfactory purchasing experience. Furthermore, existing technologies rely on the use of terminals, so there is a demand for more portable and intuitive interaction. Therefore, there is a growing need for a system that can provide users with appropriate product information and recommendations in real time and intuitively.

[0910] 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.

[0911] In this invention, the server includes means for transmitting product images photographed or selected from the terminal to the server, means for analyzing the product images received by the server and identifying the products, means for acquiring the features of the products identified by the server from a database, means for performing a matching evaluation based on the product information acquired by the server and user preference information, means for transmitting the product information and matching results from the server to the terminal, means for displaying the product information and matching results received by the terminal, and means for analyzing the product images photographed by the smart glasses in real time, performing a matching evaluation based on the features of the identified products and user preference information, and displaying the evaluation on the smart glasses. This allows users to intuitively and quickly obtain product information in a physical store and easily select the product that best suits them.

[0912] "Terminal" refers to any device operated by a user, specifically including smartphones, tablets, smart glasses, and the like.

[0913] A "server" is a computer system that receives data sent from terminals via a network and analyzes and processes the data.

[0914] "Product image" is image data that includes visual information of a product that the user is considering purchasing.

[0915] "Analysis" is the process of extracting features from product images and identifying the product using specific algorithms.

[0916] "Identification" is the act of identifying a product from an analyzed product image and obtaining specific information about it.

[0917] "Features" refer to identifiable properties or attributes of a product, including information such as brand, model, price, and specifications.

[0918] A "database" is a collection of information that stores product information and user information, and is a system that a server accesses to obtain the necessary data.

[0919] "Matching evaluation" is a process of evaluating the suitability of a product based on the acquired product information and user preference information.

[0920] "Smart glasses" are wearable devices that can be worn by a user and digitally display information within their field of vision.

[0921] "Real-time" refers to data being processed and displayed immediately as it is generated.

[0922] "User preference information" is a group of data that collects information such as preferences, purchase history, and evaluation criteria that a user has previously shown.

[0923] "Product information" is detailed data about a product, including general information such as reviews, price, and specifications.

[0924] "Display" refers to the act of visually conveying the analysis results or evaluation results to the user.

[0925] This invention is a system that uses smart glasses to analyze product information in real time when a user selects a product in a physical store and recommends products based on the user's preferences. The system includes a terminal, a server, smart glasses, an artificial intelligence (AI) module, a product database, and a user interface.

[0926] First, a user puts on smart glasses and walks around a physical store, selecting products. When they find a product they are interested in, they use the smart glasses' camera to take a picture of the product. The captured product image is sent to a server via the smart glasses' terminal function. The user's authentication information is also attached when the image is sent.

[0927] The server launches an AI module to analyze the received product images. The AI ​​module uses an image analysis algorithm to identify the product and extract its features. This feature information includes the brand, model, price, and specifications. The server retrieves the identified product information from the product database and performs a matching evaluation with the user information.

[0928] The matching evaluation refers to the user's past purchase history, evaluation criteria, and preference information. The server evaluates the suitability of the product based on the acquired product information and the user's preference information. The evaluation results and product information are sent from the server to the smart glasses in real time.

[0929] The smart glasses display the received product information and matching evaluation results on a screen. The user can check the information displayed in their field of view and decide whether the product is one they are interested in purchasing. This real-time display allows users to quickly and efficiently obtain product information that suits them.

[0930] As a concrete example, let's say a user is looking for running shoes in a physical store. The user walks around the store using smart glasses, and when they find a pair of shoes they like, they take a picture of them. The server uses an AI module to analyze the image and identify the characteristics of the running shoes. For example, it might evaluate the shoes as "highly cushioned and lightweight, and considering your past purchase history, they are a perfect fit." This information and evaluation score are displayed on the smart glasses, allowing the user to quickly make the right purchase decision.

[0931] A specific example of a prompt sentence for a generative AI model is as follows:

[0932] Example prompt sentence:

[0933] "Based on the images taken by the user in the store, please perform the following analysis:

[0934] 1. Product Identification

[0935] 2. After product identification, return the product brand, model, and features

[0936] 3. Provide relevant information (reviews, prices, specs) based on each feature.

[0937] As described above, the present invention realizes a system that can provide detailed product information and recommendation information based on the user's preferences in real time when the user is selecting a product in a physical store.

[0938] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0939] Step 1:

[0940] A user uses smart glasses to take an image of an item of interest.

[0941] Input: Product images taken by the smart glasses camera.

[0942] Output: Product image data temporarily saved on the device.

[0943] Specific operation: While walking around the store, the user uses the smart glasses to take a picture of a product they are interested in. This image data is temporarily stored in the smart glasses' memory.

[0944] Step 2:

[0945] The terminal sends the product image and the user's authentication information to the server.

[0946] Input: Product image data, user authentication information (user ID, etc.).

[0947] Output: Product image and authentication information sent to the server.

[0948] How it works: The application on the smart glasses terminal uploads product images and user authentication information to the server, where the data is encrypted and transmitted via a security protocol.

[0949] Step 3:

[0950] The server analyzes the received product image and activates an AI module to identify the product.

[0951] Input: Product image data sent to the server.

[0952] Output: Product identification results and feature extraction results.

[0953] How it works: The AI ​​module in the server analyzes product images and uses image recognition algorithms to identify the product's brand, model, and features. The results of this identification are temporarily stored on the server.

[0954] Step 4:

[0955] The server retrieves the characteristics of the identified product from a database.

[0956] Input: Product identification results (brand, model, features, etc.).

[0957] Output: Detailed product information (reviews, price, specs, etc.) retrieved from the database.

[0958] Specific operation: Based on the product identification results, the server sends a query to the product database to obtain related product information.

[0959] Step 5:

[0960] The server performs a matching evaluation based on the product information acquired and the user's preference information.

[0961] Input: Product information, user preference information (past purchase history, evaluation criteria, tastes).

[0962] Output: Matching evaluation results and scores.

[0963] Specific operation: The server retrieves the user's preference information from the database, compares it with product information, and uses an AI algorithm to evaluate the product's suitability.

[0964] Step 6:

[0965] The server transmits the product information and the matching evaluation result to the smart glasses.

[0966] Input: Product information, matching evaluation results.

[0967] Output: Product information and matching evaluation results sent to the smart glasses.

[0968] Specific operation: The server sends product information and matching scores to the smart glasses terminal. Communication is performed in real time, minimizing data delays.

[0969] Step 7:

[0970] The smart glasses display the received product information and matching evaluation results on a display.

[0971] Input: Received product information and matching evaluation results.

[0972] Output: Product information and matching evaluation results displayed on the smart glasses display.

[0973] Specific operation: The received information is overlaid on the smart glasses display, allowing the user to view this information within their field of vision.

[0974] These are the specific processing steps of the system. At each step, the AI ​​model and database are accessed effectively, and appropriate product information is immediately provided to the user.

[0975] 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.

[0976] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences.In addition, the system uses an emotion engine to recognize the user's emotions and optimize the display content.This system performs the following processes in cooperation between the terminal and the server.

[0977] First, the user launches the app on a device such as a smartphone or tablet. The user operates the app and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. This image is temporarily saved on the device.

[0978] Next, the device sends the photographed or selected product image and the user's authentication information to the server. Authentication information such as the user ID and location information is also sent. The server then activates an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product.

[0979] The server extracts product features based on the analysis results and retrieves related information from a product information database, such as product reviews, price information, and detailed specifications.

[0980] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of products based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[0981] At this stage, the system utilizes an emotion engine. The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The server uses this emotional information to optimize product recommendations and display content in real time. For example, it adjusts the display to show detailed information when the user is interested, or reduce the amount of information when the user is tired.

[0982] The server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommended summaries.

[0983] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[0984] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the key points of the product.

[0985] The server compiles this data, generates a summary and rating score, and sends it to the device, where users can check this information on their smartphone and make appropriate purchasing decisions.

[0986] The above is an embodiment of the present invention. This system allows users to obtain product information that suits them more quickly and efficiently, and in addition, the use of an emotion engine further improves the user experience.

[0987] The processing flow will be explained below.

[0988] Step 1:

[0989] The user launches the app on their device. The user operates a device such as a smartphone or tablet and taps the app icon to launch the application.

[0990] Step 2:

[0991] The user takes or selects a product image. The user uses the in-app camera to take a photo of the product they are considering purchasing, or selects an existing image stored on their device. The selected image is temporarily stored on their device.

[0992] Step 3:

[0993] The terminal transmits the product image and user authentication information to the server. The terminal then packets the photographed or selected product image data and authentication information such as the user ID, and transmits them to the server via the Internet.

[0994] Step 4:

[0995] The server launches an AI module to analyze product images. The server inputs the received image data into the image recognition AI and extracts features to identify the product. These features include the brand name, product category, model number, etc.

[0996] Step 5:

[0997] The server retrieves product information from the database. Based on the analysis results, the server searches the database for detailed information, product reviews, price information, etc. of the identified product.

[0998] Step 6:

[0999] The server refers to the user's preference information, and retrieves user profile data such as past purchase history, rating criteria, and preferred categories from a database based on the user authentication information.

[1000] Step 7:

[1001] The server performs a matching evaluation based on product information and user preference information. The server compares the acquired product information with the user preference information and calculates a compatibility score. For example, it evaluates whether the product information matches features that have received high ratings in the past.

[1002] Step 8:

[1003] The emotion engine recognizes the user's emotions. The device's camera and microphone are used to collect the user's facial expressions, voice, and input patterns, and this data is sent to the emotion engine. The emotion engine analyzes this data and recognizes the user's current emotion (e.g., joy, excitement, fatigue, etc.).

[1004] Step 9:

[1005] The server receives the recognition results of the emotion engine and optimizes the display of product information and matching results. The server adjusts the amount and level of detail of the information to be displayed based on the user's emotional state. For example, if the user is excited, more detailed information is displayed, and if the user is tired, less information is displayed.

[1006] Step 10:

[1007] The server generates a recommendation summary and matching results. Based on the acquired product information, matching ratings, and emotion engine results, the server creates summary information to provide to the user. The summary includes product features, user reviews, prices, matching scores, etc.

[1008] Step 11:

[1009] The server sends the generated summary and matching results to the terminal, converts the summary and matching results into a data format such as JSON or XML, and sends it to the terminal.

[1010] Step 12:

[1011] The device analyzes the data received from the server and displays it on the user interface. The device analyzes the received data packets and displays product information, user reviews, prices, matching scores, and recommendation summaries on the app screen.

[1012] This allows the user to check appropriate product information as well as display content optimized for their own emotional state, allowing them to make a purchasing decision.

[1013] Example 2

[1014] 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."

[1015] Conventional product recommendation systems have difficulty efficiently obtaining detailed information about products that users are considering purchasing, and have a particular problem in that they are unable to provide optimal information based on the user's preferences and current emotional state. Furthermore, the inability to instantly provide the information users need causes a lot of stress and reduces their desire to purchase.

[1016] 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.

[1017] In this invention, the server includes a means for the terminal to collect user emotion data and transmit it to the server, a means for the server to optimize product information and display content in real time based on the emotion information, and a means for transmitting product information and matching results from the server to the terminal. This makes it possible to provide optimal product information based on the user's preferences and current emotional state, improving the user experience and encouraging purchasing motivation.

[1018] A "terminal" is an information device operated by a user, and specifically refers to a portable electronic device such as a smartphone or tablet.

[1019] "Server" refers to a central control device that processes data received from terminals via a network and sends analysis results and information to the terminals.

[1020] "Product images" are visual data of products that a user is considering purchasing, and include photographs taken with a camera and existing image files.

[1021] "Authentication information" is data for identifying a user, and specifically includes a user ID, location information, and the like.

[1022] "Artificial intelligence (AI)" refers to technology that uses machine learning models and image analysis algorithms to analyze data and recognize objects and patterns.

[1023] "Product information" refers to data such as product features, reviews, price information, detailed specifications, etc.

[1024] "User preference information" refers to data that indicates the user's preferences, such as the user's past purchasing history, evaluation criteria, and taste patterns.

[1025] The "matching rating" is an evaluation score generated based on product information and user preference information, and indicates how well the user's preferences match the product.

[1026] "Emotional data" refers to data that indicates the user's current emotional state, collected from the user's facial expressions, voice, input patterns, etc.

[1027] "Real-time optimization" refers to instantly adjusting information and display content based on the user's emotional data.

[1028] "Summary" refers to information that briefly summarizes the data that the server has consolidated.

[1029] The "evaluation score" is a numerical representation of the result of the matching evaluation, and indicates the suitability of the product for the user.

[1030] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[1031] First, the user launches a dedicated application on a device such as a smartphone or tablet. The user operates the app's interface and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. The image is then temporarily saved on the device.

[1032] Next, the device sends the captured or selected product image and the user's authentication information (user ID, location information, etc.) to the server. The HTTPS protocol is used for transmission, ensuring data security. The server then launches an artificial intelligence (AI) module such as TensorFlow or OpenCV to analyze the received product image and identify the product.

[1033] The server extracts product features based on the analysis results and retrieves product information from a database (e.g., MySQL or PostgreSQL). The retrieved information includes product reviews, price information, and detailed specifications.

[1034] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation criteria are based on points that the user values, such as cushioning, color, design, and price.

[1035] Next, the device collects the user's emotional data (facial expressions, voice, input patterns, etc.) and sends it to the server. The device's camera, microphone, and touch sensor are used to collect the emotional data. The server analyzes the emotional data (using, for example, Azure Face API or Google Cloud Speech-to-Text) and recognizes the user's current emotional state. Based on this emotional information, the server optimizes product recommendations and display content in real time. For example, if the user is excited, the server may display more detailed information, or, conversely, if the user is tired, it may reduce the amount of information.

[1036] Finally, the server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device, which interprets the received data and displays it on the user interface. The display contents include product details, user reviews, prices, matching scores, and recommended summaries.

[1037] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to the server via the app. The server then uses an AI module to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then rates the shoes based on the user's preferences.

[1038] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the product's key points. The server compiles this data, generates a summary and evaluation score, and sends it to the device. The user can then check this information on their smartphone and make an appropriate purchasing decision.

[1039] An example prompt is, "I'm looking to buy some new running shoes. I take a picture of a pair of shoes I'm interested in at the store with my smartphone and send the image to the server through the app. I want the system to analyze the image and retrieve detailed information and reviews about the shoes. I also want the system to optimize the content displayed to the user based on their current emotional state. Please explain the detailed process and how the information is provided to the user."

[1040] This concludes the description of the embodiment of the present invention. This system allows users to quickly and efficiently obtain product information that suits them, and by utilizing the emotion engine, it is possible to support optimal purchasing decisions.

[1041] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1042] Step 1:

[1043] The user launches the app and gets an image of the product.

[1044] Users launch the app on their smartphone or tablet and tap the "Product Photo" button. The camera opens, and the user can either take a photo of the product they are considering purchasing or select a product image from their existing image library. The captured image is temporarily stored in the device's internal storage.

[1045] Input: User operation (obtaining product image)

[1046] Output: Photographed or selected product images

[1047] Step 2:

[1048] The device sends the image and authentication information to the server.

[1049] The device sends the stored product image, user ID, location information (GPS data), and other authentication information to the server using the HTTPS protocol. At this time, the device uses appropriate data encryption methods to ensure the security of the transmitted data.

[1050] Input: Product image, authentication information

[1051] Output: Sends image and authentication information to the server

[1052] Step 3:

[1053] The server analyzes the image and identifies the product.

[1054] The server invokes artificial intelligence (AI) modules such as TensorFlow and OpenCV to analyze the received product image data. These tools are used to identify product details from the image, identifying the brand, model, and characteristics (e.g., shape, color, etc.).

[1055] Input: Product image

[1056] Output: Identified product information (brand, model, features)

[1057] Step 4:

[1058] The server retrieves the product details from the database.

[1059] The server retrieves detailed information about the identified products by querying a database such as MySQL or PostgreSQL, including product reviews, pricing information, and detailed specifications.

[1060] Input: Identified product information

[1061] Output: Product details (reviews, price, specs)

[1062] Step 5:

[1063] The server references the user's preference information.

[1064] The server collects user preference information by referencing the user's past purchase history and evaluation criteria from a NoSQL database (e.g., AWS DynamoDB).

[1065] Input: User ID, past purchase history

[1066] Output: User preference information

[1067] Step 6:

[1068] The server evaluates the matching of the products.

[1069] Based on the acquired product information and the user's preference information, the server performs a matching evaluation of each product attribute (cushioning, color, design, price, etc.) and calculates an overall evaluation score.

[1070] Input: Product details, user preferences

[1071] Output: Matching evaluation score

[1072] Step 7:

[1073] The device collects the user's emotional data.

[1074] While the user is browsing product information, the device uses the front camera, microphone, and touch sensor to collect emotional data such as the user's facial expressions, voice, and tapping speed.

[1075] Input: User actions and behavior

[1076] Output: Collected emotion data

[1077] Step 8:

[1078] The server optimizes the display content based on emotional information.

[1079] The server analyzes the emotional data sent from the device and uses Azure Face API and Google Cloud Speech-to-Text to recognize the user's emotional state. Based on this information, the server optimizes product details and display content in real time. For example, if the user is excited, more details will be displayed, and if the user appears tired, the server will reduce the amount of information displayed.

[1080] Input: Emotion data

[1081] Output: Optimized display content

[1082] Step 9:

[1083] The server generates a summary and an evaluation score and sends them to the terminal.

[1084] The server generates a summary and rating score for each product based on the integrated data, and sends this information to the device in a data format such as JSON.

[1085] Input: Product details, emotion data, matching evaluation score

[1086] Output: Summary and rating score

[1087] Step 10:

[1088] The terminal displays the information on a user interface.

[1089] The device analyzes the received summary and rating score, and displays product information, user reviews, price, and matching score on the user interface, allowing the user to decide whether to purchase the product or not.

[1090] Input: Summary and rating score

[1091] Output: Information displayed in the user interface

[1092] (Application example 2)

[1093] 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."

[1094] In today's world, when users shop online, the wide variety of products available makes it difficult to select the right product. While there is a need to optimize the way product information is displayed based on the user's emotional state, existing systems lack the means to achieve this. Furthermore, there is a need to efficiently obtain detailed information about products that users are interested in, allowing them to make quick and reliable purchasing decisions. However, current technology is not sufficient to address this need.

[1095] 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 means for receiving and analyzing product images photographed or selected from the user's terminal, means for obtaining detailed information about the corresponding product from a database based on the analyzed product information, means for evaluating the matching with the product by referring to the user's preference information, and means for analyzing the user's emotional state using an emotion engine and generating optimized product information based on the results. This allows the user to efficiently obtain detailed information about products in which they are interested, and makes it possible to present information optimized for the user's current emotional state, thereby providing a more effective shopping experience.

[1096] A "terminal" is an electronic device such as a computer, smartphone, or tablet terminal that is operated by a user.

[1097] A "server" is a computer system that receives data from multiple terminals via a network and analyzes and processes it.

[1098] "Product image" refers to image data of a product obtained from the device's camera function or an existing photo.

[1099] "Analysis" is the process of extracting specific information from data and finding meaning and value.

[1100] A "database" is a system for efficiently managing large amounts of data and quickly retrieving necessary information.

[1101] "Matching evaluation" is the process of comparing acquired product information with the user's preference information to evaluate and recommend products that are suitable for the user.

[1102] An "emotion engine" is a system that analyzes a user's facial expressions, voice, and input patterns to recognize their emotional state.

[1103] "Display optimization" is the process of adjusting the amount and detail of information displayed based on the user's emotional state and interests.

[1104] "User preference information" is data such as the user's past purchase history, evaluation criteria, and category preferences.

[1105] This invention provides a system in which a user uses a terminal to take or select an image of a product they are considering purchasing, and the image is analyzed on the server side to obtain detailed product information and perform a matching evaluation based on the user's preferences, and a system that uses an emotion engine to recognize the user's emotional state and optimize the display content.

[1106] First, the user launches the application on a device such as a smartphone or tablet. The user then takes a photo of the product they are considering purchasing using the device's camera or selects a product image from existing photos. This product image is temporarily saved on the device.

[1107] Next, the device sends the photographed or selected product image and the user's authentication information to the server. When sending, authentication information such as the user ID and location information is also sent. The server activates an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product. For example, a "product identification AI model" is used to identify the product.

[1108] The server extracts product features based on the analysis results and retrieves related information from the product information database, such as product reviews, price information, and detailed specifications.

[1109] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of products based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as product functionality, design, and price.

[1110] At this stage, the system utilizes an emotion engine. The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The server uses this emotional information to optimize product recommendations and display content in real time. For example, if the user is excited, detailed information is displayed, and if the user is tired, the amount of information is reduced.

[1111] The server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommended summaries.

[1112] For example, if a user is considering purchasing a pair of running shoes, they can take a photo of the shoes they are interested in at the store with their smartphone and send the image to the server via the application. The server then uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from the database and then evaluates the shoes based on the user's preferences.

[1113] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the key points of the product.

[1114] This process allows users to acquire product information efficiently and accurately. Furthermore, by utilizing the emotion engine, it is possible to provide optimal information according to the user's emotional state, improving the user experience.

[1115] Example prompt sentence:

[1116] "Identify product models from images taken by the user's camera and display detailed information."

[1117] "Analyze the user's facial expressions to recognize their emotions and optimize the product information displayed."

[1118] This will realize a system that allows users to select products smoothly and without stress.

[1119] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1120] Step 1:

[1121] A user launches the application using a device. The user takes a picture of a product they are considering purchasing with the device's camera or selects a product image from existing photos. This product image is temporarily saved on the device. The input is the taken or selected product image, and the output is the saved product image.

[1122] Step 2:

[1123] The device sends the captured or selected product image and the user's authentication information to the server. At this time, authentication information such as the user ID and location information is also sent. The input is the product image and authentication information, and the output is the data sent to the server.

[1124] Step 3:

[1125] The server launches an artificial intelligence (AI) module to analyze the received product images and identify the products by analyzing the image data. For example, a product identification AI model is used. The input is the received product image, and the output is the identified product data. Specifically, deep learning technology is used to extract features within the image and identify the product model.

[1126] Step 4:

[1127] The server extracts product features based on the analysis results and retrieves related information from the product information database. Specifically, product reviews, price information, detailed specifications, etc. are retrieved from the database. The input is the identified product data, and the output is the retrieved product information.

[1128] Step 5:

[1129] The server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a product matching evaluation based on the acquired product information and the user's preference information. The input is product information and user preference information, and the output is the matching evaluation result. Specifically, scoring is performed according to the user's evaluation criteria.

[1130] Step 6:

[1131] The server uses the emotion engine to analyze the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The input is the user's facial expressions, voice, and input patterns, and the output is the recognition result of the emotional state. Specifically, the emotion engine identifies emotions by combining image analysis and voice analysis.

[1132] Step 7:

[1133] The server optimizes product recommendations and display content in real time based on the emotional information. For example, if the user is excited, detailed information is displayed, and if the user is tired, the amount of information is reduced. The input is the recognition result of the emotional state, and the output is the optimized display content.

[1134] Step 8:

[1135] The server integrates this information to generate a summary and an evaluation score. The generated summary and matching results are sent from the server to the device. The input is the optimized display content and matching results, and the output is the data sent to the device.

[1136] Step 9:

[1137] The device analyzes the received data and displays it on a user interface. The displayed content includes detailed product information, user reviews, prices, matching scores, and recommendation summaries. The input is the transmitted data, and the output is the content displayed on the user interface. Specifically, information optimized for the user's preferences and emotions is displayed.

[1138] Through the above steps, a system is realized that allows the user to efficiently obtain detailed information about a target product and presents optimal information based on the user's emotional state.

[1139] 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.

[1140] 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.

[1141] 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.

[1142] [Fourth embodiment]

[1143] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1144] 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.

[1145] 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).

[1146] 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.

[1147] 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.

[1148] 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).

[1149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1150] 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.

[1151] 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.

[1152] 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.

[1153] 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.

[1154] 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.

[1155] 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."

[1156] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[1157] First, the user launches the app on a device such as a smartphone or tablet. The user operates the app and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. This image is temporarily saved on the device.

[1158] The device then sends the captured or selected product image, along with the user's authentication information, to the server, which then activates an artificial intelligence (AI) module to analyze the received product image and identify the product.

[1159] The server extracts product features based on the analysis results and retrieves related information from a product information database, such as product reviews, price information, and detailed specifications.

[1160] In parallel, the server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[1161] The evaluation results and product information are summarized and sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommendation summaries.

[1162] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[1163] For example, the server can summarize the information, such as "These shoes are characterized by high cushioning and light weight, and are very suitable considering the user's past purchase history," and send it to the device along with an evaluation score.The user can then check this information on their smartphone and make an appropriate purchasing decision.

[1164] The above is an embodiment of the present invention. This system allows users to obtain product information that suits them more quickly and efficiently, resulting in a highly satisfying shopping experience.

[1165] The processing flow will be explained below.

[1166] Step 1:

[1167] The user launches the app on their device. The user operates a device such as a smartphone or tablet and taps the app icon to launch the application.

[1168] Step 2:

[1169] The user takes or selects a product image. The user uses the in-app camera to take a photo of the product they are considering purchasing, or selects an existing image stored on their device.

[1170] Step 3:

[1171] The terminal transmits the product image and user authentication information to the server. The terminal then packets the photographed or selected product image data and authentication information such as the user ID, and transmits them to the server via the Internet.

[1172] Step 4:

[1173] The server launches an AI module to analyze product images. The server inputs the received image data into the image recognition AI and extracts features to identify the product. These features include the brand name, product category, model number, etc.

[1174] Step 5:

[1175] The server retrieves product information from the database. Based on the analysis results, the server searches the database for detailed information, product reviews, price information, etc. of the identified product.

[1176] Step 6:

[1177] The server refers to the user's preference information, and retrieves user profile data such as past purchase history, rating criteria, and preferred categories from a database based on the user authentication information.

[1178] Step 7:

[1179] The server performs a matching evaluation based on product information and user preference information. The server compares the acquired product information with the user preference information and calculates a compatibility score. For example, it evaluates whether the product information matches features that have received high ratings in the past.

[1180] Step 8:

[1181] The server generates a recommendation summary and matching results. Based on the acquired product information and matching evaluation, the server creates summary information to provide to the user. The summary includes product features, user reviews, price, matching score, etc.

[1182] Step 9:

[1183] The server sends the generated summary and matching results to the terminal, converts the summary and matching results into a data format such as JSON or XML, and sends it to the terminal.

[1184] Step 10:

[1185] The device analyzes the data received from the server and displays it on the user interface. The device analyzes the received data packets and displays product information, user reviews, prices, matching scores, and recommendation summaries on the app screen.

[1186] This series of processing steps allows the user to quickly and efficiently obtain product information and support purchasing decisions.

[1187] Example 1

[1188] 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."

[1189] Conventional product purchasing support systems have the problem that it is difficult for users to quickly and accurately obtain detailed information about products they are considering purchasing, and they do not perform appropriate matching evaluations based on the user's individual preferences. In particular, to understand the product's features and performance in detail, users must refer to multiple information sources, which is time-consuming and requires effort. Furthermore, product recommendations based on the user's preferences and past purchasing history may not be sufficient, resulting in a decrease in satisfaction.

[1190] 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.

[1191] In this invention, the server includes means for transmitting product images photographed or selected from the terminal to the server, means for analyzing the product images received by the server and identifying the products, means for acquiring characteristics of the products identified by the server from a database, means for performing a matching evaluation based on the product information acquired by the server and user preference information, means for transmitting the product information and matching results from the server to the terminal, and means for displaying the product information and matching results received by the terminal on a user interface. This enables users to quickly obtain detailed information about products they are considering purchasing and receive an appropriate matching evaluation based on their preferences.

[1192] A "terminal" is a computer device operated by a user, such as a smartphone or tablet.

[1193] A "server" is a computer device that receives data sent from a terminal on a network and analyzes and processes it.

[1194] "Photographed or selected product image" refers to image data of a product that the user photographs using the terminal or selects from existing images in the terminal.

[1195] "Means for transmitting" refers to a communication function for transferring data from a terminal to a server.

[1196] "Means for analyzing and identifying products" refers to the function of using artificial intelligence models and algorithms stored on the server to judge the content of the received product images and identify the type and characteristics of the product.

[1197] "Means for obtaining features from a database" refers to the function of the server searching and obtaining detailed product information from a related database based on the analysis results of the product image.

[1198] "Means for performing matching evaluation" refers to an algorithm or system for evaluating and recommending products based on product information acquired by the server and user preference information.

[1199] "User preference information" refers to individual information such as the user's past purchasing history, preferences, and evaluation criteria.

[1200] "Product information and matching results" refers to detailed product information obtained by the server from the database and evaluation results based on the user's preferences.

[1201] "Means for displaying on the user interface" refers to a function for displaying product information and matching results in an easy-to-read format on the terminal screen.

[1202] An "artificial intelligence model" refers to a software model that uses machine learning and deep learning techniques to analyze data and derive results.

[1203] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[1204] First, the user launches a dedicated app on a device such as a smartphone or tablet. The user operates the app to take a picture of the product they are considering purchasing with the camera or select from existing images on the device. This image is temporarily saved on the device.

[1205] Next, the device sends the photographed or selected product image to the server, along with the user's authentication information. HTTPS communication is used as the transmission method. The server then launches an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product. This AI module uses deep learning frameworks such as TensorFlow and PyTorch.

[1206] The server extracts product features based on the analysis results and retrieves related information from a product information database. Specifically, product reviews, price information, detailed specifications, etc. are retrieved from the database. Examples of product information databases used here include Amazon DynamoDB and Google Cloud Firestore.

[1207] In parallel, the server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[1208] The evaluation results and product information are summarized and sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommendation summaries.

[1209] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[1210] For example, the server can summarize the information, such as "These shoes are characterized by high cushioning and light weight, and are very suitable considering the user's past purchase history," and send it to the device along with an evaluation score.The user can then check this information on their smartphone and make an appropriate purchasing decision.

[1211] An example of a prompt for a generative AI model might be, "Analyze images of products I'm considering purchasing and display detailed information and ratings based on the user's preferences."

[1212] This system allows users to obtain product information that suits them more quickly and efficiently, resulting in a more satisfying shopping experience.

[1213] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1214] Step 1:

[1215] Launching the app

[1216] Users tap to launch the dedicated app installed on their smartphone or tablet.

[1217] Specific operation: When the user taps the app icon, the app launches and the initial screen is displayed.

[1218] Input: None

[1219] Output: Initial screen of the app

[1220] Step 2:

[1221] Taking or selecting an image

[1222] Users can use the in-app camera to take a picture of the product they are considering purchasing, or select an existing photo from their gallery.

[1223] Specific behavior: When the user taps the camera button in the app, the camera will launch and take a photo. When the user taps the gallery button, the photo gallery will be displayed and an existing image can be selected.

[1224] Input: User operation (take a photo with the camera or select from the gallery)

[1225] Output: Photographed or selected product images

[1226] Step 3:

[1227] Submit product images

[1228] The terminal sends the photographed or selected product image to the server, along with the user's authentication information.

[1229] Specific operation: The device sends image data and authentication information to the server using HTTPS communication.

[1230] Input: Photographed or selected product image, user authentication information

[1231] Output: Data is sent to the server

[1232] Step 4:

[1233] Image analysis on the server

[1234] The server decodes the received product images and launches an AI module (e.g., TensorFlow or PyTorch) to perform image analysis.

[1235] Specific operation: The server decodes the image data from binary format, inputs it into the AI ​​model, and performs inference.

[1236] Input: Received product image

[1237] Output: Product identification information (e.g. brand, model)

[1238] Step 5:

[1239] Product feature extraction

[1240] The server extracts product features from the image analysis results, such as identifying "running shoes" and "high cushioning."

[1241] Specific operation: The server applies a feature extraction algorithm based on the analysis results to generate product feature information.

[1242] Input: Product identification information

[1243] Output: Product feature information

[1244] Step 6:

[1245] Obtaining product information

[1246] The server retrieves detailed information from a product information database (such as Amazon DynamoDB or Google Cloud Firestore) based on the product's features, including product reviews, prices, and detailed specifications.

[1247] What happens: The server uses SQL queries or API requests to search the database and retrieve relevant information.

[1248] Input: Product feature information

[1249] Output: Product details

[1250] Step 7:

[1251] Referencing user preference information

[1252] The server references user preference information from an internal database, including past purchase history, rating criteria, and category preferences.

[1253] Specific operations: The server queries the user profile database to obtain preference information.

[1254] Input: User credentials

[1255] Output: User preference information

[1256] Step 8:

[1257] Product matching evaluation

[1258] The server evaluates the products based on the product information and the user's preferences. Evaluation criteria include price, design, cushioning, etc.

[1259] Specific operation: The server executes the matching evaluation algorithm and calculates the evaluation score of the product.

[1260] Input: detailed product information, user preferences

[1261] Output: Matching evaluation results (e.g., score, recommendation comments)

[1262] Step 9:

[1263] Sending evaluation results

[1264] The server summarizes the evaluation results and detailed product information and sends them to the terminal.

[1265] Specific operation: The server summarizes the evaluation results and detailed product information and sends them to the terminal using HTTPS communication.

[1266] Input: Matching evaluation results, product details

[1267] Output: Transmission data (evaluation results and detailed product information)

[1268] Step 10:

[1269] Receiving data

[1270] The terminal receives the evaluation results and product information sent from the server.

[1271] Specific operation: The device receives and decodes data using HTTPS communication.

[1272] Input: Data to be sent (evaluation results and detailed product information)

[1273] Output: Received data (evaluation results and detailed product information)

[1274] Step 11:

[1275] Display in the user interface

[1276] The device analyzes the received data and displays information about the product (such as reviews, price, matching score, and recommendation summary) in the app's user interface.

[1277] Specific operation: The device parses the data, binds it to UI components, and displays it.

[1278] Input: Received data (evaluation results and detailed product information)

[1279] Output: Display on the user interface

[1280] (Application example 1)

[1281] 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."

[1282] Conventional product purchasing support systems for brick-and-mortar stores have difficulty providing detailed product information or recommendations tailored to the user's preferences in real time when the user is selecting products in the store. As a result, users often spend time and effort finding the product that best suits them, resulting in an unsatisfactory purchasing experience. Furthermore, existing technologies rely on the use of terminals, so there is a demand for more portable and intuitive interaction. Therefore, there is a growing need for a system that can provide users with appropriate product information and recommendations in real time and intuitively.

[1283] 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.

[1284] In this invention, the server includes means for transmitting product images photographed or selected from the terminal to the server, means for analyzing the product images received by the server and identifying the products, means for acquiring the features of the products identified by the server from a database, means for performing a matching evaluation based on the product information acquired by the server and user preference information, means for transmitting the product information and matching results from the server to the terminal, means for displaying the product information and matching results received by the terminal, and means for analyzing the product images photographed by the smart glasses in real time, performing a matching evaluation based on the features of the identified products and user preference information, and displaying the evaluation on the smart glasses. This allows users to intuitively and quickly obtain product information in a physical store and easily select the product that best suits them.

[1285] "Terminal" refers to any device operated by a user, specifically including smartphones, tablets, smart glasses, and the like.

[1286] A "server" is a computer system that receives data sent from terminals via a network and analyzes and processes the data.

[1287] "Product image" is image data that includes visual information of a product that the user is considering purchasing.

[1288] "Analysis" is the process of extracting features from product images and identifying the product using specific algorithms.

[1289] "Identification" is the act of identifying a product from an analyzed product image and obtaining specific information about it.

[1290] "Features" refer to identifiable properties or attributes of a product, including information such as brand, model, price, and specifications.

[1291] A "database" is a collection of information that stores product information and user information, and is a system that a server accesses to obtain the necessary data.

[1292] "Matching evaluation" is a process of evaluating the suitability of a product based on the acquired product information and user preference information.

[1293] "Smart glasses" are wearable devices that can be worn by a user and digitally display information within their field of vision.

[1294] "Real-time" refers to data being processed and displayed immediately as it is generated.

[1295] "User preference information" is a group of data that collects information such as preferences, purchase history, and evaluation criteria that a user has previously shown.

[1296] "Product information" is detailed data about a product, including general information such as reviews, price, and specifications.

[1297] "Display" refers to the act of visually conveying the analysis results or evaluation results to the user.

[1298] This invention is a system that uses smart glasses to analyze product information in real time when a user selects a product in a physical store and recommends products based on the user's preferences. The system includes a terminal, a server, smart glasses, an artificial intelligence (AI) module, a product database, and a user interface.

[1299] First, a user puts on smart glasses and walks around a physical store, selecting products. When they find a product they are interested in, they use the smart glasses' camera to take a picture of the product. The captured product image is sent to a server via the smart glasses' terminal function. The user's authentication information is also attached when the image is sent.

[1300] The server launches an AI module to analyze the received product images. The AI ​​module uses an image analysis algorithm to identify the product and extract its features. This feature information includes the brand, model, price, and specifications. The server retrieves the identified product information from the product database and performs a matching evaluation with the user information.

[1301] The matching evaluation refers to the user's past purchase history, evaluation criteria, and preference information. The server evaluates the suitability of the product based on the acquired product information and the user's preference information. The evaluation results and product information are sent from the server to the smart glasses in real time.

[1302] The smart glasses display the received product information and matching evaluation results on a screen. The user can check the information displayed in their field of view and decide whether the product is one they are interested in purchasing. This real-time display allows users to quickly and efficiently obtain product information that suits them.

[1303] As a concrete example, let's say a user is looking for running shoes in a physical store. The user walks around the store using smart glasses, and when they find a pair of shoes they like, they take a picture of them. The server uses an AI module to analyze the image and identify the characteristics of the running shoes. For example, it might evaluate the shoes as "highly cushioned and lightweight, and considering your past purchase history, they are a perfect fit." This information and evaluation score are displayed on the smart glasses, allowing the user to quickly make the right purchase decision.

[1304] A specific example of a prompt sentence for a generative AI model is as follows:

[1305] Example prompt sentence:

[1306] "Based on the images taken by the user in the store, please perform the following analysis:

[1307] 1. Product Identification

[1308] 2. After product identification, return the product brand, model, and features

[1309] 3. Provide relevant information (reviews, prices, specs) based on each feature.

[1310] As described above, the present invention realizes a system that can provide detailed product information and recommendation information based on the user's preferences in real time when the user is selecting a product in a physical store.

[1311] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1312] Step 1:

[1313] A user uses smart glasses to take an image of an item of interest.

[1314] Input: Product images taken by the smart glasses camera.

[1315] Output: Product image data temporarily saved on the device.

[1316] Specific operation: While walking around the store, the user uses the smart glasses to take a picture of a product they are interested in. This image data is temporarily stored in the smart glasses' memory.

[1317] Step 2:

[1318] The terminal sends the product image and the user's authentication information to the server.

[1319] Input: Product image data, user authentication information (user ID, etc.).

[1320] Output: Product image and authentication information sent to the server.

[1321] How it works: The application on the smart glasses terminal uploads product images and user authentication information to the server, where the data is encrypted and transmitted via a security protocol.

[1322] Step 3:

[1323] The server analyzes the received product image and activates an AI module to identify the product.

[1324] Input: Product image data sent to the server.

[1325] Output: Product identification results and feature extraction results.

[1326] How it works: The AI ​​module in the server analyzes product images and uses image recognition algorithms to identify the product's brand, model, and features. The results of this identification are temporarily stored on the server.

[1327] Step 4:

[1328] The server retrieves the characteristics of the identified product from a database.

[1329] Input: Product identification results (brand, model, features, etc.).

[1330] Output: Detailed product information (reviews, price, specs, etc.) retrieved from the database.

[1331] Specific operation: Based on the product identification results, the server sends a query to the product database to obtain related product information.

[1332] Step 5:

[1333] The server performs a matching evaluation based on the product information acquired and the user's preference information.

[1334] Input: Product information, user preference information (past purchase history, evaluation criteria, tastes).

[1335] Output: Matching evaluation results and scores.

[1336] Specific operation: The server retrieves the user's preference information from the database, compares it with product information, and uses an AI algorithm to evaluate the product's suitability.

[1337] Step 6:

[1338] The server transmits the product information and the matching evaluation result to the smart glasses.

[1339] Input: Product information, matching evaluation results.

[1340] Output: Product information and matching evaluation results sent to the smart glasses.

[1341] Specific operation: The server sends product information and matching scores to the smart glasses terminal. Communication is performed in real time, minimizing data delays.

[1342] Step 7:

[1343] The smart glasses display the received product information and matching evaluation results on a display.

[1344] Input: Received product information and matching evaluation results.

[1345] Output: Product information and matching evaluation results displayed on the smart glasses display.

[1346] Specific operation: The received information is overlaid on the smart glasses display, allowing the user to view this information within their field of vision.

[1347] These are the specific processing steps of the system. At each step, the AI ​​model and database are accessed effectively, and appropriate product information is immediately provided to the user.

[1348] 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.

[1349] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences.In addition, the system uses an emotion engine to recognize the user's emotions and optimize the display content.This system performs the following processes in cooperation between the terminal and the server.

[1350] First, the user launches the app on a device such as a smartphone or tablet. The user operates the app and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. This image is temporarily saved on the device.

[1351] Next, the device sends the photographed or selected product image and the user's authentication information to the server. Authentication information such as the user ID and location information is also sent. The server then activates an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product.

[1352] The server extracts product features based on the analysis results and retrieves related information from a product information database, such as product reviews, price information, and detailed specifications.

[1353] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of products based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as cushioning, color, design, and price.

[1354] At this stage, the system utilizes an emotion engine. The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The server uses this emotional information to optimize product recommendations and display content in real time. For example, it adjusts the display to show detailed information when the user is interested, or reduce the amount of information when the user is tired.

[1355] The server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommended summaries.

[1356] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to a server via the app. The server uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then evaluates the shoes based on the user's preferences.

[1357] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the key points of the product.

[1358] The server compiles this data, generates a summary and rating score, and sends it to the device, where users can check this information on their smartphone and make appropriate purchasing decisions.

[1359] The above is an embodiment of the present invention. This system allows users to obtain product information that suits them more quickly and efficiently, and in addition, the use of an emotion engine further improves the user experience.

[1360] The processing flow will be explained below.

[1361] Step 1:

[1362] The user launches the app on their device. The user operates a device such as a smartphone or tablet and taps the app icon to launch the application.

[1363] Step 2:

[1364] The user takes or selects a product image. The user uses the in-app camera to take a photo of the product they are considering purchasing, or selects an existing image stored on their device. The selected image is temporarily stored on their device.

[1365] Step 3:

[1366] The terminal transmits the product image and user authentication information to the server. The terminal then packets the photographed or selected product image data and authentication information such as the user ID, and transmits them to the server via the Internet.

[1367] Step 4:

[1368] The server launches an AI module to analyze product images. The server inputs the received image data into the image recognition AI and extracts features to identify the product. These features include the brand name, product category, model number, etc.

[1369] Step 5:

[1370] The server retrieves product information from the database. Based on the analysis results, the server searches the database for detailed information, product reviews, price information, etc. of the identified product.

[1371] Step 6:

[1372] The server refers to the user's preference information, and retrieves user profile data such as past purchase history, rating criteria, and preferred categories from a database based on the user authentication information.

[1373] Step 7:

[1374] The server performs a matching evaluation based on product information and user preference information. The server compares the acquired product information with the user preference information and calculates a compatibility score. For example, it evaluates whether the product information matches features that have received high ratings in the past.

[1375] Step 8:

[1376] The emotion engine recognizes the user's emotions. The device's camera and microphone are used to collect the user's facial expressions, voice, and input patterns, and this data is sent to the emotion engine. The emotion engine analyzes this data and recognizes the user's current emotion (e.g., joy, excitement, fatigue, etc.).

[1377] Step 9:

[1378] The server receives the recognition results of the emotion engine and optimizes the display of product information and matching results. The server adjusts the amount and level of detail of the information to be displayed based on the user's emotional state. For example, if the user is excited, more detailed information is displayed, and if the user is tired, less information is displayed.

[1379] Step 10:

[1380] The server generates a recommendation summary and matching results. Based on the acquired product information, matching ratings, and emotion engine results, the server creates summary information to provide to the user. The summary includes product features, user reviews, prices, matching scores, etc.

[1381] Step 11:

[1382] The server sends the generated summary and matching results to the terminal, converts the summary and matching results into a data format such as JSON or XML, and sends it to the terminal.

[1383] Step 12:

[1384] The device analyzes the data received from the server and displays it on the user interface. The device analyzes the received data packets and displays product information, user reviews, prices, matching scores, and recommendation summaries on the app screen.

[1385] This allows the user to check appropriate product information as well as display content optimized for their own emotional state, allowing them to make a purchasing decision.

[1386] Example 2

[1387] 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."

[1388] Conventional product recommendation systems have difficulty efficiently obtaining detailed information about products that users are considering purchasing, and have a particular problem in that they are unable to provide optimal information based on the user's preferences and current emotional state. Furthermore, the inability to instantly provide the information users need causes a lot of stress and reduces their desire to purchase.

[1389] 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.

[1390] In this invention, the server includes a means for the terminal to collect user emotion data and transmit it to the server, a means for the server to optimize product information and display content in real time based on the emotion information, and a means for transmitting product information and matching results from the server to the terminal. This makes it possible to provide optimal product information based on the user's preferences and current emotional state, improving the user experience and encouraging purchasing motivation.

[1391] A "terminal" is an information device operated by a user, and specifically refers to a portable electronic device such as a smartphone or tablet.

[1392] "Server" refers to a central control device that processes data received from terminals via a network and sends analysis results and information to the terminals.

[1393] "Product images" are visual data of products that a user is considering purchasing, and include photographs taken with a camera and existing image files.

[1394] "Authentication information" is data for identifying a user, and specifically includes a user ID, location information, and the like.

[1395] "Artificial intelligence (AI)" refers to technology that uses machine learning models and image analysis algorithms to analyze data and recognize objects and patterns.

[1396] "Product information" refers to data such as product features, reviews, price information, detailed specifications, etc.

[1397] "User preference information" refers to data that indicates the user's preferences, such as the user's past purchasing history, evaluation criteria, and taste patterns.

[1398] The "matching rating" is an evaluation score generated based on product information and user preference information, and indicates how well the user's preferences match the product.

[1399] "Emotional data" refers to data that indicates the user's current emotional state, collected from the user's facial expressions, voice, input patterns, etc.

[1400] "Real-time optimization" refers to instantly adjusting information and display content based on the user's emotional data.

[1401] "Summary" refers to information that briefly summarizes the data that the server has consolidated.

[1402] The "evaluation score" is a numerical representation of the result of the matching evaluation, and indicates the suitability of the product for the user.

[1403] The present invention is a product recommendation system that allows a user to take or select an image of a product they are considering purchasing on a terminal, and then analyzes the image on a server to obtain detailed product information and perform a matching evaluation based on the user's preferences. This system performs the following processes in cooperation between the terminal and the server.

[1404] First, the user launches a dedicated application on a device such as a smartphone or tablet. The user operates the app's interface and takes a photo of the product they are considering purchasing with their camera or selects from existing photos. The image is then temporarily saved on the device.

[1405] Next, the device sends the captured or selected product image and the user's authentication information (user ID, location information, etc.) to the server. The HTTPS protocol is used for transmission, ensuring data security. The server then launches an artificial intelligence (AI) module such as TensorFlow or OpenCV to analyze the received product image and identify the product.

[1406] The server extracts product features based on the analysis results and retrieves product information from a database (e.g., MySQL or PostgreSQL). The retrieved information includes product reviews, price information, and detailed specifications.

[1407] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of the product based on the acquired product information and the user's preference information. The evaluation criteria are based on points that the user values, such as cushioning, color, design, and price.

[1408] Next, the device collects the user's emotional data (facial expressions, voice, input patterns, etc.) and sends it to the server. The device's camera, microphone, and touch sensor are used to collect the emotional data. The server analyzes the emotional data (using, for example, Azure Face API or Google Cloud Speech-to-Text) and recognizes the user's current emotional state. Based on this emotional information, the server optimizes product recommendations and display content in real time. For example, if the user is excited, the server may display more detailed information, or, conversely, if the user is tired, it may reduce the amount of information.

[1409] Finally, the server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device, which interprets the received data and displays it on the user interface. The display contents include product details, user reviews, prices, matching scores, and recommended summaries.

[1410] As a concrete example, consider a user considering purchasing new running shoes. The user takes a photo of a pair of shoes they are interested in at a store with their smartphone and sends the image to the server via the app. The server then uses an AI module to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from a database and then rates the shoes based on the user's preferences.

[1411] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the product's key points. The server compiles this data, generates a summary and evaluation score, and sends it to the device. The user can then check this information on their smartphone and make an appropriate purchasing decision.

[1412] An example prompt is, "I'm looking to buy some new running shoes. I take a picture of a pair of shoes I'm interested in at the store with my smartphone and send the image to the server through the app. I want the system to analyze the image and retrieve detailed information and reviews about the shoes. I also want the system to optimize the content displayed to the user based on their current emotional state. Please explain the detailed process and how the information is provided to the user."

[1413] This concludes the description of the embodiment of the present invention. This system allows users to quickly and efficiently obtain product information that suits them, and by utilizing the emotion engine, it is possible to support optimal purchasing decisions.

[1414] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1415] Step 1:

[1416] The user launches the app and gets an image of the product.

[1417] Users launch the app on their smartphone or tablet and tap the "Product Photo" button. The camera opens, and the user can either take a photo of the product they are considering purchasing or select a product image from their existing image library. The captured image is temporarily stored in the device's internal storage.

[1418] Input: User operation (obtaining product image)

[1419] Output: Photographed or selected product images

[1420] Step 2:

[1421] The device sends the image and authentication information to the server.

[1422] The device sends the stored product image, user ID, location information (GPS data), and other authentication information to the server using the HTTPS protocol. At this time, the device uses appropriate data encryption methods to ensure the security of the transmitted data.

[1423] Input: Product image, authentication information

[1424] Output: Sends image and authentication information to the server

[1425] Step 3:

[1426] The server analyzes the image and identifies the product.

[1427] The server invokes artificial intelligence (AI) modules such as TensorFlow and OpenCV to analyze the received product image data. These tools are used to identify product details from the image, identifying the brand, model, and characteristics (e.g., shape, color, etc.).

[1428] Input: Product image

[1429] Output: Identified product information (brand, model, features)

[1430] Step 4:

[1431] The server retrieves the product details from the database.

[1432] The server retrieves detailed information about the identified products by querying a database such as MySQL or PostgreSQL, including product reviews, pricing information, and detailed specifications.

[1433] Input: Identified product information

[1434] Output: Product details (reviews, price, specs)

[1435] Step 5:

[1436] The server references the user's preference information.

[1437] The server collects user preference information by referencing the user's past purchase history and evaluation criteria from a NoSQL database (e.g., AWS DynamoDB).

[1438] Input: User ID, past purchase history

[1439] Output: User preference information

[1440] Step 6:

[1441] The server evaluates the matching of the products.

[1442] Based on the acquired product information and the user's preference information, the server performs a matching evaluation of each product attribute (cushioning, color, design, price, etc.) and calculates an overall evaluation score.

[1443] Input: Product details, user preferences

[1444] Output: Matching evaluation score

[1445] Step 7:

[1446] The device collects the user's emotional data.

[1447] While the user is browsing product information, the device uses the front camera, microphone, and touch sensor to collect emotional data such as the user's facial expressions, voice, and tapping speed.

[1448] Input: User actions and behavior

[1449] Output: Collected emotion data

[1450] Step 8:

[1451] The server optimizes the display content based on emotional information.

[1452] The server analyzes the emotional data sent from the device and uses Azure Face API and Google Cloud Speech-to-Text to recognize the user's emotional state. Based on this information, the server optimizes product details and display content in real time. For example, if the user is excited, more details will be displayed, and if the user appears tired, the server will reduce the amount of information displayed.

[1453] Input: Emotion data

[1454] Output: Optimized display content

[1455] Step 9:

[1456] The server generates a summary and an evaluation score and sends them to the terminal.

[1457] The server generates a summary and rating score for each product based on the integrated data, and sends this information to the device in a data format such as JSON.

[1458] Input: Product details, emotion data, matching evaluation score

[1459] Output: Summary and rating score

[1460] Step 10:

[1461] The terminal displays the information on a user interface.

[1462] The device analyzes the received summary and rating score, and displays product information, user reviews, price, and matching score on the user interface, allowing the user to decide whether to purchase the product or not.

[1463] Input: Summary and rating score

[1464] Output: Information displayed in the user interface

[1465] (Application example 2)

[1466] 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."

[1467] In today's world, when users shop online, the wide variety of products available makes it difficult to select the right product. While there is a need to optimize the way product information is displayed based on the user's emotional state, existing systems lack the means to achieve this. Furthermore, there is a need to efficiently obtain detailed information about products that users are interested in, allowing them to make quick and reliable purchasing decisions. However, current technology is not sufficient to address this need.

[1468] 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 means for receiving and analyzing product images photographed or selected from the user's terminal, means for obtaining detailed information about the corresponding product from a database based on the analyzed product information, means for evaluating the matching with the product by referring to the user's preference information, and means for analyzing the user's emotional state using an emotion engine and generating optimized product information based on the results. This allows the user to efficiently obtain detailed information about products in which they are interested, and makes it possible to present information optimized for the user's current emotional state, thereby providing a more effective shopping experience.

[1469] A "terminal" is an electronic device such as a computer, smartphone, or tablet terminal that is operated by a user.

[1470] A "server" is a computer system that receives data from multiple terminals via a network and analyzes and processes it.

[1471] "Product image" refers to image data of a product obtained from the device's camera function or an existing photo.

[1472] "Analysis" is the process of extracting specific information from data and finding meaning and value.

[1473] A "database" is a system for efficiently managing large amounts of data and quickly retrieving necessary information.

[1474] "Matching evaluation" is the process of comparing acquired product information with the user's preference information to evaluate and recommend products that are suitable for the user.

[1475] An "emotion engine" is a system that analyzes a user's facial expressions, voice, and input patterns to recognize their emotional state.

[1476] "Display optimization" is the process of adjusting the amount and detail of information displayed based on the user's emotional state and interests.

[1477] "User preference information" is data such as the user's past purchase history, evaluation criteria, and category preferences.

[1478] This invention provides a system in which a user uses a terminal to take or select an image of a product they are considering purchasing, and the image is analyzed on the server side to obtain detailed product information and perform a matching evaluation based on the user's preferences, and a system that uses an emotion engine to recognize the user's emotional state and optimize the display content.

[1479] First, the user launches the application on a device such as a smartphone or tablet. The user then takes a photo of the product they are considering purchasing using the device's camera or selects a product image from existing photos. This product image is temporarily saved on the device.

[1480] Next, the device sends the photographed or selected product image and the user's authentication information to the server. When sending, authentication information such as the user ID and location information is also sent. The server activates an artificial intelligence (AI) module to analyze the received product image, and analyzes the image data to identify the product. For example, a "product identification AI model" is used to identify the product.

[1481] The server extracts product features based on the analysis results and retrieves related information from the product information database, such as product reviews, price information, and detailed specifications.

[1482] The server also references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a matching evaluation of products based on the acquired product information and the user's preference information. The evaluation is based on the points that the user values, such as product functionality, design, and price.

[1483] At this stage, the system utilizes an emotion engine. The emotion engine analyzes the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The server uses this emotional information to optimize product recommendations and display content in real time. For example, if the user is excited, detailed information is displayed, and if the user is tired, the amount of information is reduced.

[1484] The server integrates this information to generate a summary and a rating score. The generated summary and matching results are sent from the server to the device. The device analyzes the received data and displays it on the user interface. The displayed content includes product details, user reviews, prices, matching scores, and recommended summaries.

[1485] For example, if a user is considering purchasing a pair of running shoes, they can take a photo of the shoes they are interested in at the store with their smartphone and send the image to the server via the application. The server then uses AI to analyze the image and identify the brand, model, and features of the running shoes. Based on the identification results, the server retrieves detailed information and reviews from the database and then evaluates the shoes based on the user's preferences.

[1486] The emotion engine then analyzes the user's facial expressions and voice to recognize their current emotional state. For example, if the user is excited, the system will display more detailed product information and optimize the display to support the purchase decision. Conversely, if the user is tired, the system will reduce the amount of information and adjust the display to succinctly convey the key points of the product.

[1487] This process allows users to acquire product information efficiently and accurately. Furthermore, by utilizing the emotion engine, it is possible to provide optimal information according to the user's emotional state, improving the user experience.

[1488] Example prompt sentence:

[1489] "Identify product models from images taken by the user's camera and display detailed information."

[1490] "Analyze the user's facial expressions to recognize their emotions and optimize the product information displayed."

[1491] This will realize a system that allows users to select products smoothly and without stress.

[1492] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1493] Step 1:

[1494] A user launches the application using a device. The user takes a picture of a product they are considering purchasing with the device's camera or selects a product image from existing photos. This product image is temporarily saved on the device. The input is the taken or selected product image, and the output is the saved product image.

[1495] Step 2:

[1496] The device sends the captured or selected product image and the user's authentication information to the server. At this time, authentication information such as the user ID and location information is also sent. The input is the product image and authentication information, and the output is the data sent to the server.

[1497] Step 3:

[1498] The server launches an artificial intelligence (AI) module to analyze the received product images and identify the products by analyzing the image data. For example, a product identification AI model is used. The input is the received product image, and the output is the identified product data. Specifically, deep learning technology is used to extract features within the image and identify the product model.

[1499] Step 4:

[1500] The server extracts product features based on the analysis results and retrieves related information from the product information database. Specifically, product reviews, price information, detailed specifications, etc. are retrieved from the database. The input is the identified product data, and the output is the retrieved product information.

[1501] Step 5:

[1502] The server references the user's preference information, which includes the user's past purchase history, evaluation criteria, and category preferences. The server performs a product matching evaluation based on the acquired product information and the user's preference information. The input is product information and user preference information, and the output is the matching evaluation result. Specifically, scoring is performed according to the user's evaluation criteria.

[1503] Step 6:

[1504] The server uses the emotion engine to analyze the user's facial expressions, voice, and input patterns to recognize the user's current emotional state. The emotion results recognized by the emotion engine are sent to the server. The input is the user's facial expressions, voice, and input patterns, and the output is the recognition result of the emotional state. Specifically, the emotion engine identifies emotions by combining image analysis and voice analysis.

[1505] Step 7:

[1506] The server optimizes product recommendations and display content in real time based on the emotional information. For example, if the user is excited, detailed information is displayed, and if the user is tired, the amount of information is reduced. The input is the recognition result of the emotional state, and the output is the optimized display content.

[1507] Step 8:

[1508] The server integrates this information to generate a summary and an evaluation score. The generated summary and matching results are sent from the server to the device. The input is the optimized display content and matching results, and the output is the data sent to the device.

[1509] Step 9:

[1510] The device analyzes the received data and displays it on a user interface. The displayed content includes detailed product information, user reviews, prices, matching scores, and recommendation summaries. The input is the transmitted data, and the output is the content displayed on the user interface. Specifically, information optimized for the user's preferences and emotions is displayed.

[1511] Through the above steps, a system is realized that allows the user to efficiently obtain detailed information about a target product and presents optimal information based on the user's emotional state.

[1512] 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.

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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).

[1519] 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.

[1520] 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."

[1521] 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.

[1522] 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).

[1523] 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.

[1524] 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.

[1525] 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.

[1526] 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.

[1527] 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.

[1528] 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.

[1529] 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.

[1530] 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.

[1531] 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.

[1532] 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.

[1533] The following is further disclosed regarding the above embodiment.

[1534] (Claim 1)

[1535] A means for transmitting a photographed or selected product image from the terminal to a server;

[1536] A means for analyzing the product image received by the server and identifying the product;

[1537] means for retrieving the characteristics of the identified product from a database in the server;

[1538] A means for performing a matching evaluation based on the product information acquired by the server and the user's preference information;

[1539] means for transmitting product information and matching results from the server to the terminal;

[1540] a means for displaying the received product information and matching results on the terminal;

[1541] A system including:

[1542] (Claim 2)

[1543] 10. The system of claim 1, including means for identifying products using artificial intelligence when analyzing product images at the server.

[1544] (Claim 3)

[1545] 2. The system according to claim 1, further comprising means for the terminal to transmit user authentication information to the server and for the server to refer to preference information for each user.

[1546] "Example 1"

[1547] (Claim 1)

[1548] A means for transmitting a photographed or selected product image from the terminal to a server;

[1549] A means for analyzing the product image received by the server and identifying the product;

[1550] means for retrieving the characteristics of the identified product from a database in the server;

[1551] A means for performing a matching evaluation based on the product information acquired by the server and the user's preference information;

[1552] means for transmitting product information and matching results from the server to the terminal;

[1553] means for displaying the received product information and matching results on a user interface;

[1554] A system including:

[1555] (Claim 2)

[1556] 10. The system of claim 1, including means for identifying products using an artificial intelligence model when analyzing product images at the server.

[1557] (Claim 3)

[1558] 2. The system according to claim 1, further comprising means for the terminal to transmit user authentication information to the server and for the server to refer to type information for each user.

[1559] "Application Example 1"

[1560] (Claim 1)

[1561] A means for transmitting a photographed or selected product image from the terminal to a server;

[1562] A means for analyzing the product image received by the server and identifying the product;

[1563] means for retrieving the characteristics of the identified product from a database in the server;

[1564] A means for performing a matching evaluation based on the product information acquired by the server and the user's preference information;

[1565] means for transmitting product information and matching results from the server to the terminal;

[1566] a means for displaying the received product information and matching results on the terminal;

[1567] a means for analyzing product images captured by the smart glasses in real time, performing a matching evaluation based on the identified product features and user preference information, and displaying the evaluation results on the smart glasses;

[1568] A system including:

[1569] (Claim 2)

[1570] 10. The system of claim 1, including means for identifying products using artificial intelligence when analyzing product images at the server.

[1571] (Claim 3...

Claims

1. A means for transmitting a photographed or selected product image from the terminal to a server; A means for analyzing the product image received by the server and identifying the product; means for retrieving the characteristics of the identified product from a database in the server; A means for performing a matching evaluation based on the product information acquired by the server and the user's preference information; means for transmitting product information and matching results from the server to the terminal; a means for displaying the received product information and matching results on the terminal; A system including:

2. 10. The system of claim 1, further comprising means for using artificial intelligence to identify products when analyzing product images at the server.

3. 2. The system according to claim 1, further comprising means for the terminal to transmit user authentication information to the server and for the server to refer to preference information for each user.

Images