system

Abstract

We provide a system that can deliver the latest fashion trends to users. [Solution] A system comprising: means for uploading images of clothes, shoes, bags, etc. owned by the user; means for analyzing the uploaded images and saving their respective characteristics in a database; means for requesting outfits suitable for a specific occasion from the user; means for obtaining weather and temperature information based on the request; means for generating the optimal outfit based on the obtained weather and temperature information and information in the database; means for searching for trending products from external shopping sites based on the generated outfit; and means for displaying the optimal outfit and trending products on the user's terminal.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] ---

[0005] In recent years, although the number of coordination proposal systems in fashion has increased, there are few systems that present coordinates according to specific events or scenes based on the items that users have. In addition, there are limited systems that can propose coordinates considering weather and temperature, and they do not sufficiently meet the needs of users. Furthermore, there is no system that integrates functions of providing trend information and related products. As a result, users have problems such as spending time on coordination and having difficulty finding appropriate items.

Means for Solving the Problems

[0006] This invention provides a system that allows users to upload images of their clothing, shoes, bags, etc., and analyzes those images to store their features in a database. This system accepts requests from users for outfits suitable for specific occasions, obtains weather and temperature information, and generates the optimal outfit. Furthermore, based on the generated outfit, it searches for trending items from external shopping sites and displays them on the user's device, enabling users to efficiently decide on outfits and promoting the purchase of related products. By using machine learning algorithms, the accuracy of image analysis is improved, enabling outfit suggestions that meet user needs. Additionally, by utilizing e-commerce sites, the system can provide users with the latest fashion trends.

[0007] ---

[0008] A "user" refers to a person who uses the system to upload images of their belongings and make styling requests.

[0009] "Clothing, shoes, bags, etc." refers to all fashion items owned by users that they upload as images.

[0010] "Means for uploading images" refers to the function that allows users to send photos of fashion items to the system.

[0011] "Methods for analyzing images" refers to technologies that identify and extract features (color, shape, brand, etc.) of clothing, shoes, bags, etc., from uploaded images.

[0012] A "database" refers to a system that stores and manages the characteristic information of analyzed fashion items in a searchable and accessible format.

[0013] "Method for requesting a coordinated outfit" refers to a function that allows users to request a fashion coordinated outfit from the system for a specific event or occasion.

[0014] "Means for obtaining weather and temperature information" refers to technology that obtains weather and temperature data for a specified day from external weather information services.

[0015] "Methods for generating outfits" refers to technology that creates fashion combinations suitable for the user based on acquired weather information and fashion items in a database.

[0016] "Methods for searching for trending products from external shopping sites" refers to technologies that obtain the latest fashion items that match a suggested outfit from external e-commerce sites.

[0017] "Means of displaying on the user's device" refers to a function that presents the generated outfits and related trending products on the user's device (such as a smartphone or PC).

[0018] "Machine learning algorithms" refer to artificial intelligence technologies that analyze data, learn patterns and features, and improve the accuracy of image recognition.

[0019] An "e-commerce site" refers to a web platform used for selling and purchasing goods and services over the internet. [Brief explanation of the drawing]

[0020] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5]It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0022] First, the language used in the following description will be explained.

[0023] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the 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.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0034] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] ---

[0042] The system for implementing this invention involves the user uploading images of their clothes, shoes, bags, etc., and analyzing those images to store their features in a database. Furthermore, when the user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on that information. This generated outfit is displayed on the user's terminal along with trending items found on external shopping sites.

[0043] 1. Uploading images owned by the user

[0044] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0045] 2. Image Analysis and Feature Extraction

[0046] The server receives the uploaded image and description data, and uses image analysis technology to extract item features (color, shape, brand, etc.) from the image. The extracted features and description are stored in a database.

[0047] 3. Coordination Request

[0048] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[0049] 4. Obtaining weather and temperature information

[0050] The server uses a weather API service to retrieve weather and temperature information for the specified day. The retrieved information is then reflected in the outfit the user desires.

[0051] 5. Coordination generation

[0052] The server generates the optimal outfit based on weather and temperature information, as well as the user's fashion item information in the database. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans."

[0053] 6. Searching for trending products

[0054] Based on the generated outfit, the server searches for trending items from external shopping sites. This allows users to find the latest fashion items that match their existing wardrobe.

[0055] 7. Display of proposed content

[0056] The server sends the generated outfit and searched trending items to the user's terminal and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[0057] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." It then suggests an optimal outfit consisting of a "white shirt," "black sneakers," and "blue jeans," and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0058] ---

[0059] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products.

[0060] The following describes the processing flow.

[0061] ---

[0062] Step 1:

[0063] Users upload images of their own clothes, shoes, bags, etc., to the system from their smartphones or PCs. Users also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0064] Step 2:

[0065] The device sends the uploaded image and description data to the server. Images are sent in JPEG or PNG format, and descriptions are sent as text data.

[0066] Step 3:

[0067] The server analyzes the received images and uses image recognition technology to extract features (color, shape, brand, etc.) of clothing, shoes, bags, etc. It also analyzes the descriptive text and stores it together in the database.

[0068] Step 4:

[0069] Users log in and request outfit coordination from the system for a specific occasion or event. They also enter whether weather and temperature should be considered, and specify a budget limit.

[0070] Step 5:

[0071] The device sends user request data to the server. This data includes event information, weather selection, budget, etc.

[0072] Step 6:

[0073] The server uses a weather API to retrieve weather and temperature information for the requested day. It then retrieves and analyzes data from the weather API service.

[0074] Step 7:

[0075] The server searches and extracts matching items from the database based on the user's request and the weather and temperature information it has obtained. For example, if it is sunny and the temperature is 25 degrees Celsius, it will select suitable clothing, shoes, and bags.

[0076] Step 8:

[0077] Based on the items the server searches and extracts, it generates the most suitable outfit for the user's request. For example, it might suggest a "white shirt," "blue jeans," and "black sneakers" that would be suitable for a casual lunch.

[0078] Step 9:

[0079] The server calls the Yahoo Shopping API to search for the latest items that match the suggested outfit. This retrieves related products as trending information.

[0080] Step 10:

[0081] The server generates coordinated outfits and combines them with trending products found through Yahoo Shopping searches to create a single suggested package.

[0082] Step 11:

[0083] The terminal sends the suggested package to the user's terminal and displays it on the screen. It is displayed in a format that is easy for the user to understand.

[0084] Step 12:

[0085] Users review suggested outfits and trendy items, and if they find items they need, they click the purchase link to proceed with the purchase on e-commerce sites such as Yahoo Shopping.

[0086] ---

[0087] (Example 1)

[0088] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Traditional fashion coordination systems struggled to efficiently match users' existing items with new, trendy products. Furthermore, they had difficulty considering external factors such as weather and temperature when suggesting outfits, making it challenging to provide optimal coordination tailored to users' specific needs. This often led to users feeling dissatisfied with their daily clothing choices and new item purchases.

[0090] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0091] In this invention, the server includes means for uploading images of clothing, footwear, bags, etc., owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; and means for receiving requests from the user for outfits suitable for specific occasions. This allows the system to incorporate detailed information about the items owned by the user and provide optimal outfits tailored to each individual user.

[0092] ---

[0093] ---

[0094] A "user" refers to someone who uses this system to manage their fashion items and receive styling suggestions.

[0095] "Clothing" refers to the clothes that users wear on a daily basis.

[0096] "Footwear" refers to shoes, sandals, and other items worn on the user's feet.

[0097] "Bag" refers to bags used by users to carry things.

[0098] "Images" refer to digital data containing visual information such as clothing, footwear, and bags uploaded by users.

[0099] "Analysis" refers to the process by which a server extracts features and information from uploaded images.

[0100] "Features" refer to attribute information such as the color, shape, and brand of an item obtained through analysis.

[0101] A "database" refers to an information management system used to store analyzed features and descriptions.

[0102] A "request" refers to an inquiry that a user sends to the system to request an outfit suitable for a specific occasion.

[0103] "Weather" refers to environmental information such as weather and temperature.

[0104] "Temperature" refers to the temperature reflected in the resulting outfit.

[0105] "Generation" refers to the process by which the server creates coordination suggestions based on the necessary information.

[0106] An "e-commerce site" refers to an online platform that includes external shopping sites.

[0107] "Terminal" refers to devices such as smartphones and personal computers that users use to operate the system.

[0108] "Display" refers to the act of visually showing information on a device screen.

[0109] A "machine learning algorithm" refers to a computer model that a server uses for image analysis.

[0110] A "product sales site" includes online shops where users can purchase items necessary for coordinating outfits.

[0111] ---

[0112] The above are the definitions of the important words.

[0113] ---

[0114] The system for implementing this invention begins with the user uploading images of their clothing, footwear, bags, etc., to the system using a smartphone or PC. The user enters a brief description for each image (e.g., "white shirt," "leather boots"), and this information is sent to the server.

[0115] The server receives the uploaded image and description data. Next, it uses image analysis technologies such as Google® Cloud Vision API to extract item features (color, shape, brand, etc.) from the image. The extracted features and descriptions are stored in a database. At this stage, machine learning algorithms are used for analysis, improving accuracy.

[0116] Users can submit requests to the system for outfits suitable for specific occasions or events (e.g., casual lunch, business meeting). When submitting a request, they can select options to consider weather and temperature, and set a budget limit.

[0117] The server uses weather API services such as the OpenWeatherMap API to obtain weather and temperature information for a specified day. The obtained information is then reflected in the outfit chosen by the user.

[0118] Next, the server generates the optimal outfit based on weather and temperature information and the user's fashion item information in the database. For example, if it's sunny and the temperature is 25 degrees Celsius, it might suggest a "white shirt" and "blue jeans."

[0119] Based on the generated outfit, the server searches for trending items from external e-commerce sites. Specifically, it uses online shopping sites such as Amazon and Rakuten to suggest the latest fashion items that match the user's belongings.

[0120] Finally, the server sends the generated outfit and searched trending items to the user's device and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[0121] Specific example

[0122] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers," and adds descriptions to them as "white shirt" and "leather boots," respectively. Next, the user requests an outfit for a casual weekend lunch, turns on the setting to consider the weather, and sets a budget of 10,000 yen. The server retrieves from the OpenWeatherMap API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items containing "white shirt" and "black sneakers" from its database. It then suggests the optimal outfit as "white shirt," "black sneakers," and "blue jeans," and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. This information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0123] Examples of prompts for generative AI models

[0124] The following is an example of a prompt:

[0125] A user uploaded images of their "white shirt" and "black sneakers" to the system. The system labeled these images "white shirt" and "leather boots." Next, the user requested an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server determined the weekend weather would be sunny with a temperature of 25 degrees Celsius and extracted items from its database that included a "white shirt" and "black sneakers." The server then suggested a suitable outfit: "white shirt," "black sneakers," and "blue jeans." Furthermore, it searched for and suggested related items such as casual sneakers and accessories from external shopping sites. All information was displayed on the user's device, allowing the user to review the suggestions and purchase items they liked.

[0126] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0127] ---

[0128] Step 1: The user uploads an image.

[0129] Users upload images of clothing, footwear, bags, etc., to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0130] Input: Image file and descriptive text

[0131] Output: Image file and descriptive text are sent to the server.

[0132] Specific actions: The user taps the "Upload" button, selects an image of a "white shirt," enters the description "white shirt," and presses the "Submit" button.

[0133] Step 2: The server receives the image and description.

[0134] The server receives the image file and descriptive text sent by the user.

[0135] Input: Image file and descriptive text

[0136] Output: Received image file and description text

[0137] Specific operation: The server retrieves data sent by the user and prepares for subsequent processing.

[0138] Step 3: Image analysis and feature extraction

[0139] The server uses image analysis technologies such as the Google Cloud Vision API to extract item features (color, shape, brand, etc.) from the image.

[0140] Input: Image file

[0141] Output: Extracted feature data (color, shape, brand, etc.)

[0142] Specific operation: The server sends the image file to the Google Cloud Vision API and analyzes the returned analysis results.

[0143] Step 4: Saving Feature Data

[0144] The server stores the extracted features and descriptive text in a database.

[0145] Input: Feature data, descriptive text

[0146] Output: Saved to database successfully

[0147] Specific operation: The server stores the feature data and descriptive text in the database in the appropriate format.

[0148] Step 5: The user requests an outfit.

[0149] Users request outfits suitable for specific occasions or events from the system. This includes specifying settings that take weather and temperature into consideration, as well as a budget limit.

[0150] Input: Event type, weather consideration options, budget limit

[0151] Output: Request data is sent to the server.

[0152] Specific actions: The user presses the "Coordination Request" button in the app, selects "Casual Lunch," turns "Weather Consideration On," and sets a budget of 10,000 yen.

[0153] Step 6: Obtain weather and temperature information

[0154] The server uses weather API services such as the OpenWeatherMap API to obtain weather and temperature information for a specified day.

[0155] Input: Request data, specified date

[0156] Output: Weather and temperature information

[0157] Specific operation: The server sends a request to the OpenWeatherMap API to retrieve information that the weather for the weekend will be sunny with a temperature of 25 degrees Celsius.

[0158] Step 7: Creating the outfit

[0159] The server generates the optimal outfit based on weather and temperature information, as well as the user's fashion item information in the database.

[0160] Input: Weather and temperature information, item information in the database.

[0161] Output: Generated coordinate data

[0162] Specific operation: The server extracts "white shirt," "black sneakers," and "blue jeans" from the database and combines them to create the optimal outfit.

[0163] Step 8: Search for trending products

[0164] Based on the generated coordinates, the server searches for trending products from external e-commerce sites.

[0165] Input: Generated coordinate data

[0166] Output: List of trending products

[0167] Specific operation: The server sends a request to the Amazon API with keywords such as "casual sneakers" and retrieves a list of related products.

[0168] Step 9: Display the proposed content

[0169] The server sends the generated outfits and searched trending items to the user's device and displays them on the screen.

[0170] Input: Generated outfit data, list of trending items

[0171] Output: Coordination suggestions displayed on the user's device

[0172] Specific operation: The app receives a notification on the user's device and displays "recommended outfits" including a "white shirt," "black sneakers," and "blue jeans." At the bottom, it displays "recommended casual sneakers" from Amazon with a link.

[0173] ---

[0174] The above is a description of the specific processing steps of this system's program.

[0175] (Application Example 1)

[0176] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0177] In recent years, consumer demand for fashion item coordination has increased, and there is a growing need for efficient and accurate suggestions. However, conventional systems struggle to suggest optimal outfits that combine the user's existing items with the latest fashion trends, and they lack suggestions that reflect specific situations or weather conditions. Furthermore, there are insufficient means to recommend trendy items that match individual user preferences, resulting in a lack of effective methods to increase purchasing intent.

[0178] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0179] In this invention, the server includes means for uploading images of clothes, shoes, bags, etc. owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; means for receiving requests from the user for outfits suitable for a specific occasion; means for obtaining weather and temperature information based on the request; means for generating the optimal outfit based on the obtained weather and temperature information and information in the database; means for searching for trending products from external e-commerce sites based on the generated outfit; means for displaying the optimal outfit and trending products on the user's terminal; and means for inputting the generated outfit and trending product information in prompt format into a generation AI model to display more refined outfits and recommended products. This makes it possible to provide the optimal outfit suitable for a specific occasion and weather using items owned by the user, and to make suggestions that also include trending products.

[0180] "A means for users to upload images of their own clothes, shoes, bags, etc." refers to a function that allows users to send image data of their own fashion items (clothes, shoes, or bags, etc.) to the system via the user interface.

[0181] "A means of analyzing uploaded images and saving their characteristics to a database" refers to a function that uses image analysis technology to extract characteristics such as color, shape, and material from images of fashion items uploaded by users, and saves them to a database.

[0182] "A means for users to request outfits suitable for specific situations" refers to a function that allows users to request the system to suggest fashion outfits suitable for specific situations or events they wish to attend.

[0183] "Means for obtaining weather and temperature information based on requests" refers to a function that obtains weather and temperature data for a specific day or region from external weather information services, according to the user's request.

[0184] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to a function that automatically generates clothing suggestions suitable for a specific situation by combining acquired weather and temperature data with the user's fashion item information stored in the database.

[0185] "A means of searching for trending products from external e-commerce sites based on generated outfits" refers to a function that searches for the latest trending fashion items from external e-commerce sites based on generated fashion outfits.

[0186] "A means of displaying optimal outfits and trendy products on the user's device" refers to a function that displays the generated optimal outfits and related trendy products on the screen of the user's device, such as a smartphone or personal computer.

[0187] "A means of inputting generated coordinate and trend product information into a generation AI model in prompt format to display more refined coordinates and recommended products" refers to a function that inputs generated fashion coordinate and trend product information into a generation AI model in text format, and then derives and displays more refined coordinates and recommended products based on that input.

[0188] The system for implementing this invention involves uploading images of clothing, shoes, bags, etc., owned by the user, and analyzing those images to store their features in a database. Furthermore, when the user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit. Based on this outfit, the system has the function of searching for trending products from external e-commerce sites and displaying them on the user's terminal.

[0189] 1. Uploading images owned by the user

[0190] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0191] 2. Image Analysis and Feature Extraction

[0192] The server receives the image and its description data uploaded by the user. Next, it uses a machine learning algorithm to analyze the image and extract item features (color, shape, brand, etc.). These extracted features and descriptions are stored in a database.

[0193] 3. Coordination Request

[0194] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[0195] 4. Obtaining weather and temperature information

[0196] The server uses a weather API service (e.g., WeatherAPI) to retrieve weather and temperature information for a specified day. The retrieved information is then used to generate the outfit requested by the user.

[0197] 5. Coordination generation

[0198] The server generates the optimal outfit based on the acquired weather and temperature information and the user's fashion item information in the database. For example, on a sunny day with a temperature of 25 degrees Celsius, it will suggest cool items such as a "white shirt" and "blue jeans."

[0199] 6. Searching for trending products

[0200] Based on the generated outfit, the server searches for trending items from external e-commerce sites. This allows users to find the latest fashion items that match their existing wardrobe.

[0201] 7. Display of proposed content and use of the generated AI model

[0202] The server sends the generated outfits and searched trending products to the user's device and displays them on the screen. It also inputs this information into a generation AI model in the form of prompts, which then generates and displays more refined outfits and recommended products.

[0203] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" they own, and labels each item. Next, they request an outfit for a casual weekend lunch, enabling weather consideration and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items containing "white shirt" and "black sneakers" from its database. It then suggests an optimal outfit consisting of "white shirt," "black sneakers," and "blue jeans," and further searches and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, the following prompt is entered into the generative AI model to display a refined suggestion:

[0204] "Could you recommend some outfits and the latest trendy items for a casual weekend lunch?"

[0205] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products.

[0206] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0207] Step 1:

[0208] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. The input consists of image data of the fashion item taken by the user and a brief description (e.g., "white shirt," "leather boots"). The output is the user's uploaded image and its corresponding description data.

[0209] Step 2:

[0210] The server receives images and descriptive data uploaded by users. Next, it uses machine learning algorithms to analyze the images and extract features such as color, shape, and brand. The input is the image data and descriptive data uploaded by the user, and the output is the feature data extracted through image analysis. The server stores this feature and descriptive data in a database.

[0211] Step 3:

[0212] Users can use their smartphones or PCs to request outfits suitable for specific occasions or events (e.g., casual lunch, business meeting). Input includes information about the occasion or event selected by the user, as well as options to consider weather and temperature, and a budget limit. Output is the request data sent to the server.

[0213] Step 4:

[0214] The server uses a weather API service to retrieve weather and temperature information for a specified date. The input is date and region information based on the user's request data. The output is the retrieved weather and temperature data. The server uses this data to generate coordinated outfits.

[0215] Step 5:

[0216] The server generates the optimal outfit based on acquired weather and temperature information and the user's fashion item information in the database. Specifically, it selects items suitable for the weather and temperature and suggests combinations appropriate for specific occasions or events. The inputs are weather and temperature data and fashion item information from the database. The output is the generated optimal outfit suggestion.

[0217] Step 6:

[0218] The server searches for trending products from external e-commerce sites based on the generated outfit. The input is the generated outfit proposal, and the output is information on the related trending products.

[0219] Step 7:

[0220] The server inputs the generated outfits and trending items into the AI ​​model in the form of prompt sentences. The AI ​​model then uses this information to generate more refined outfits and recommended items. The input is the information generated in the form of prompt sentences, and the output is the information on the final outfits and recommended items.

[0221] Step 8:

[0222] The server sends the final coordinated outfit and recommended items to the user's device and displays them on the screen. The input is the coordinated outfit and recommended items information generated by the generative AI model, and the output is the data displayed on the user's device. The user can review this and make purchases as needed.

[0223] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0224] ---

[0225] The system for implementing this invention involves the user uploading images of their clothes, shoes, bags, etc., and analyzing those images to store their features in a database. Furthermore, when a user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on that information and the user's emotional state. This generated outfit is displayed on the user's device along with trending items found on external shopping sites.

[0226] 1. Uploading images owned by the user

[0227] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0228] 2. Image Analysis and Feature Extraction

[0229] The server receives the uploaded image and description data, and uses image analysis technology to extract item features (color, shape, brand, etc.) from the image. The extracted features and description are stored in a database.

[0230] 3. Obtaining user sentiment information

[0231] The system incorporates an emotion engine that analyzes the user's image and voice data. When a user accesses the system, it uses a camera and microphone to capture the user's facial expressions and voice, and analyzes this data to identify the user's emotions.

[0232] 4. Coordination Request

[0233] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[0234] 5. Obtaining weather and temperature information

[0235] The server uses a weather API service to retrieve weather and temperature information for the specified day. The retrieved information is then reflected in the outfit the user desires.

[0236] 6. Coordination Generation

[0237] The server generates the optimal outfit based on weather and temperature information, the user's fashion item information in the database, and emotional information. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans," and if the user has a cheerful expression, it recommends an outfit with bright colors.

[0238] 7. Searching for trending products

[0239] Based on the generated outfit, the server searches for trending items from external shopping sites. This allows users to find the latest fashion items that match their existing wardrobe.

[0240] 8. Display of proposed content

[0241] The server sends the generated outfit and searched trending items to the user's terminal and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[0242] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server then suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0243] ---

[0244] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products. Furthermore, by reflecting the user's emotional information, it enables even more personalized coordinate suggestions.

[0245] The following describes the processing flow.

[0246] ---

[0247] Step 1:

[0248] Users upload images of their own clothes, shoes, bags, etc., to the system from their smartphones or PCs. Users also enter a brief description for each image.

[0249] Step 2:

[0250] The device sends the uploaded image and description data to the server. Images are sent in JPEG or PNG format, and descriptions are sent as text data.

[0251] Step 3:

[0252] The server analyzes the received images and uses image analysis technology to extract features (color, shape, brand, etc.) of clothing, shoes, bags, etc. The extracted features and descriptions are stored in a database.

[0253] Step 4:

[0254] Users log in and request outfit coordination from the system for specific occasions or events. When making a request, they can also set options such as considering weather and temperature, as well as a budget limit.

[0255] Step 5:

[0256] The device sends user request data to the server. This data includes event information, weather selection, budget, etc.

[0257] Step 6:

[0258] The server uses a weather API to retrieve weather and temperature information for the requested day. It then retrieves and analyzes data from the weather API service.

[0259] Step 7:

[0260] When a user accesses the system, the emotion engine uses the camera and microphone to capture the user's facial expressions and voice. The captured data is sent to the server.

[0261] Step 8:

[0262] The server analyzes the received image and audio data to identify the user's emotions. The identified emotion information is stored in a database.

[0263] Step 9:

[0264] The server generates the optimal outfit based on the user's request, acquired weather and temperature information, item information in the database, and the user's emotional state. For example, on a sunny day with a temperature of 25 degrees Celsius, if the user has a happy expression, the server will suggest a "white shirt," "blue jeans," and "black sneakers."

[0265] Step 10:

[0266] The server calls an API from an external shopping site to search for the latest items that match the suggested outfit. This retrieves related products as trend information.

[0267] Step 11:

[0268] The server generates coordinated outfits and combines them with trending products found on external shopping sites to create a single suggested package.

[0269] Step 12:

[0270] The terminal sends the suggested package to the user's terminal and displays it on the screen. It is presented in a format that is easy for the user to understand.

[0271] Step 13:

[0272] Users review suggested outfits and trendy items, and if necessary, click purchase links to proceed with the purchase process on external e-commerce sites.

[0273] ---

[0274] By dividing the processing steps in this way, the system can efficiently suggest fashion coordinates to the user and, by reflecting the user's emotional information, can achieve more personalized suggestions.

[0275] (Example 2)

[0276] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 will be referred to as the "terminal".

[0277] Traditional fashion coordination systems offer features for registering and managing user-owned items, but they lack personalized coordination suggestions that incorporate user emotional information. This means that suggested outfits may not match the user's mood or preferences. Furthermore, the lack of consideration for weather and temperature information results in impractical outfit suggestions. Additionally, the function for searching for trending items suffers from insufficient integration with external e-commerce sites, preventing timely information provision.

[0278] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0279] In this invention, the server includes means for uploading images of clothing, footwear, bags, etc., owned by the user; means for analyzing the uploaded images and saving their respective characteristics to a database; means for analyzing the user's facial expressions and voice data to obtain emotional information; means for personalizing outfits based on the obtained emotional information; means for obtaining weather and temperature information based on a request; means for generating an optimal outfit based on the obtained weather and temperature information and information in the database; means for searching for trending products from external e-commerce sites based on the generated outfit; and means for displaying the optimal outfit and trending products on the user's terminal. This makes it possible to provide more personalized and practical outfit suggestions that take into account the user's emotions and weather information.

[0280] "A means for users to upload images of clothing, footwear, bags, etc. they own" refers to a function that allows users to send images of their fashion items to the system using their smartphones or PCs.

[0281] The means of "analyzing the uploaded image and storing each feature in a database" is a function for extracting features such as color, shape, brand, etc. based on the received image and storing that information in a database.

[0282] The means of "analyzing the user's facial expressions and voice data to obtain emotional information" is a function for analyzing the user's facial expressions and voice, and identifying and obtaining the emotions at that time (e.g., happy, sad, surprised, etc.).

[0283] The means of "personalizing coordinates based on the obtained emotional information" is a function for utilizing the user's emotional information to propose the most suitable fashion coordinates according to the mood at that time.

[0284] The means of "obtaining weather and temperature information based on a request" is a function for obtaining the weather and temperature information of the specified date, time, and location based on the coordinate request from the user.

[0285] The means of "generating the most suitable coordinates based on the obtained weather and temperature information and the information in the database" is a function for creating the most suitable coordinates suitable for the date, time, and location by utilizing the weather information, temperature information, and the user's fashion item information stored in the database.

[0286] The means of "searching for trendy products from an external e-commerce site based on the generated coordinates" is a function for searching for relevant latest fashion items from an external e-commerce site based on the generated fashion coordinates.

[0287] The means of "displaying the most suitable coordinates and trendy products on the user's terminal" is a function for displaying the information of the generated coordinates and related trendy products on the user's terminal such as a smartphone or PC.

[0288] Modes for carrying out the invention

[0289] The system for implementing this invention uploads images of fashion items such as clothing, footwear, and bags owned by the user, analyzes the images to extract features, and stores them in a database. Furthermore, when a user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on this information and the user's emotional state. This generated outfit is displayed on the user's terminal along with trending items found on external e-commerce sites.

[0290] Hardware and software

[0291] Hardware:

[0292] This system uses devices such as smartphones, personal computers, and servers.

[0293] software:

[0294] Image analysis uses common image recognition APIs (e.g., Google Vision API). Sentiment analysis uses common sentiment engines (e.g., Microsoft® Azure® Face API). Weather information is obtained using weather API services (e.g., OpenWeatherMap API). Database management uses a relational database management system (RDBMS).

[0295] Program processing

[0296] When a user uploads an image, the server receives it and extracts features from the image using an image recognition API. The extracted features, along with labels, are stored in a database. When a user accesses the system, the camera and microphone are used to capture the user's facial expressions and voice, and an emotion engine is used to analyze the emotional information. When a user requests a specific outfit, the server calls a non-essential data API to obtain weather and temperature information for the specified day and location. Based on the obtained weather and temperature information, the user's item information, and emotional information, the server generates the optimal outfit. Furthermore, based on the generated outfit, it searches for relevant trending products from external e-commerce sites. The optimal outfit and trending products are then displayed on the user's device.

[0297] Specific example

[0298] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, the user requests an outfit for a casual weekend lunch, turns on the setting to consider the weather, and sets a budget of 10,000 yen. The server retrieves from the weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from the database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0299] Example of a prompt

[0300] Upload an image of yourself wearing a white shirt and black sneakers, and request an outfit suggestion for a casual lunch. Turn on weather consideration and set a budget limit of 10,000 yen.

[0301] In this way, the system improves the user's fashion experience by efficiently proposing the user's fashion coordination and providing related trendy products. Also, by reflecting the user's emotional information, it is possible to further realize a more personalized coordination proposal.

[0302] The flow of the specific process in Example 2 will be described using FIG. 13.

[0303] Step 1:

[0304] The user uploads an image.

[0305] Input: Images of clothing, shoes, bags, etc. taken by the user, and description labels for them (e.g., "white shirt").

[0306] Specific operation: The user opens an application on a smartphone or PC, clicks the upload button to select an image of a "white shirt", and enters label information.

[0307] Output: Image data and its label information sent to the server.

[0308] Step 2:

[0309] The server receives the image.

[0310] Input: Image data and label information sent by the user.

[0311] Specific operation: The server receives the upload request and captures the image data and label information.

[0312] Output: Received image data and label information.

[0313] Step 3:

[0314] The server performs image analysis and extracts features.

[0315] Input: Image data received by the server.

[0316] Specific operation: The server uses image analysis technologies such as the Google Vision API to extract features such as color, shape, and brand from an image. For example, it might detect "Color: White" and "Item: Shirt".

[0317] Output: Extracted feature information.

[0318] Step 4:

[0319] The server saves the features to the database.

[0320] Input: Extracted feature information and label information.

[0321] Specific operation: The server saves the extracted feature information (color: white, item: shirt) and label information (white shirt) to a relational database.

[0322] Output: Feature information and label information stored in the database.

[0323] Step 5:

[0324] Obtain user sentiment information.

[0325] Input: User's facial image and voice data acquired from a camera and microphone connected to the application.

[0326] Specific operation: When a user accesses the application, the system activates the camera to capture the user's facial expression and uses an emotion engine (such as the Microsoft Azure Face API) to analyze emotions such as "smile."

[0327] Output: Acquired emotion information (e.g., "happy").

[0328] Step 6:

[0329] The user requests an outfit coordination.

[0330] Input: User-entered outfit request information (e.g., casual lunch, weather consideration setting on, budget limit of 10,000 yen).

[0331] Specific action: The user selects "Casual Lunch" in the application, turns on the weather consideration setting, sets a budget limit of 10,000 yen, and submits the request.

[0332] Output: Coordination request information.

[0333] Step 7:

[0334] The server retrieves weather and temperature information.

[0335] Input: User's coordination request information and request date, time, and location information.

[0336] Specific operation: The server calls the OpenWeatherMap API to retrieve weather and temperature information (e.g., sunny, temperature 25 degrees) for a specified date, time, and location.

[0337] Output: Acquired weather and temperature information.

[0338] Step 8:

[0339] The server generates the optimal coordination.

[0340] Input: Acquired weather and temperature information, user item information in the database, and acquired sentiment information.

[0341] Specific operation: The server generates the optimal outfit (white shirt, blue jeans) based on weather and temperature information (sunny, 25 degrees), item information stored in the database (white shirt, black sneakers), and user emotion information (happy).

[0342] Output: Generated coordination information.

[0343] Step 9:

[0344] The server searches for trending products.

[0345] Input: Generated outfit information.

[0346] Specific operation: The server uses APIs from external e-commerce sites such as Amazon and Rakuten to search for trending products (e.g., blue cap, casual sneakers) based on the generated outfit.

[0347] Output: Searched trending product information.

[0348] Step 10:

[0349] The server displays the suggested content on the user's terminal.

[0350] Input: Generated outfit information and searched trend product information.

[0351] Specific operation: The server sends the generated outfit and the searched trending items (blue cap, casual sneakers) to the user's device and displays them on the application screen.

[0352] Output: The suggested content displayed on the user's terminal.

[0353] (Application Example 2)

[0354] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0355] Conventional fashion coordination suggestion systems generated outfits using image analysis of items owned by the user and weather information, but they lacked individuality and immediacy because they did not take into account the user's emotions or real-time display of outfits. As a result, it was difficult for users to obtain appropriate outfits that suited their emotions and specific situations. Furthermore, they did not support intuitive interaction using new devices such as smart glasses. The objective of this invention is to solve these problems.

[0356] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0357] In this invention, the server includes means for uploading images of clothes, shoes, bags, etc., owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; means for receiving requests from the user for outfits suitable for a specific occasion; means for acquiring weather and temperature information based on the requests; means for generating the optimal outfit based on the acquired weather and temperature information and information in the database; means for searching for trendy products from external shopping sites based on the generated outfit; means for displaying the optimal outfit and trendy products on the user's terminal; means for acquiring the user's emotional information and adjusting the outfit based on it; and means for using smart glasses as the user's terminal. This makes it possible to suggest personalized outfits that respond to the user's emotions and real-time situation.

[0358] "Means for uploading images of clothing, shoes, bags, etc. owned by users" refers to software and hardware that allows users to send images of their fashion items to a server via the internet.

[0359] "A means of analyzing uploaded images and saving their characteristics to a database" refers to software that uses image analysis technology to extract the characteristics of uploaded fashion items and stores that information in a database within the system.

[0360] "A means for users to request outfits suitable for specific occasions" refers to an interface and function that allows users to request fashion suggestions appropriate for events or situations.

[0361] "Means for obtaining weather and temperature information based on requests" refers to communication and software for obtaining weather and temperature data for a requested date, time, and location from an external weather information service.

[0362] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to an algorithm and software that automatically creates appropriate fashion outfits by combining weather, temperature, and the characteristics of the user's owned items.

[0363] "A means of searching for trendy items from external shopping sites based on a generated outfit" refers to a communication function and software for searching for the latest fashion items related to an automatically generated outfit from an external e-commerce site.

[0364] "Means for displaying optimal outfits and trendy products on the user's device" refers to an interface and software for displaying generated outfits and related trendy product information on the user's smart device.

[0365] "Means for acquiring user emotional information and adjusting outfits based on it" refers to technology that analyzes the user's facial expressions and voice to identify emotions and adjust fashion outfits accordingly.

[0366] "Means of using smart glasses as a user terminal" refers to the technology and software for displaying outfit suggestions and information on trending products via smart glasses worn by the user.

[0367] This invention is a system that allows users to upload images of fashion items such as clothes, shoes, and bags they own, analyzes these images to extract features, and stores that information in a database. Furthermore, when providing outfit suggestions based on user requests, it also includes a function to search for trending items from external e-commerce sites, taking into account weather and temperature information as well as the user's emotional state. The following describes a specific embodiment of this invention.

[0368] 1. Uploading images owned by the user

[0369] Users upload images of their own fashion items, such as clothes, shoes, and bags, to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0370] 2. Image Analysis and Feature Extraction

[0371] The server receives the uploaded image and description data, performs image analysis using machine learning algorithms, and extracts item features (color, shape, brand, etc.). The extracted features and descriptions are stored in a database.

[0372] 3. Obtaining user sentiment information

[0373] When a user accesses the system, the smart glasses' built-in camera and microphone capture the user's facial expressions and voice, and EmotionRecognizer identifies the user's emotions. The identified emotion information is used to generate coordinates.

[0374] 4. Coordination Request

[0375] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they can submit a request to the system via voice commands or gesture interface on their smart glasses. When making a request, they can also set settings that consider weather and temperature, as well as a budget limit.

[0376] 5. Obtaining weather and temperature information

[0377] The server uses the WeatherAPI service to retrieve weather and temperature information for a specified day. This retrieved weather and temperature information is then combined with the user's fashion item information stored in the database to generate outfit ideas.

[0378] 6. Coordination Generation

[0379] The server generates the optimal outfit based on weather and temperature information, the user's fashion item information in the database, and emotional information. The generated outfit is adjusted according to the user's requests and mood. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans," and if the user has a cheerful expression, it recommends an outfit with bright colors.

[0380] 7. Searching for trending products

[0381] Based on the generated outfit, the server searches for trending products from external e-commerce sites and suggests related fashion items to the user.

[0382] 8. Display of proposed content

[0383] The server sends the generated outfits and searched trending items to the user's smart glasses for real-time display. This allows the user to intuitively check the outfits and purchase trending items as needed.

[0384] Specific example

[0385] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from the WeatherAPI that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server then suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches for and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, this information is displayed on the user's smart glasses, allowing the user to review the suggestions and purchase items they like.

[0386] Example of a prompt

[0387] User: I live in Tokyo today and it's sunny with a temperature of 25 degrees Celsius. I'm planning to go out for a casual lunch. I'm in a very good mood. What kind of outfit would be appropriate?

[0388] This invention allows users to receive personalized outfit suggestions through smart glasses that are tailored to their emotions and real-time circumstances.

[0389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0390] Step 1:

[0391] Users upload images of fashion items they own.

[0392] Input: Images of clothing, shoes, bags, etc., uploaded from the user's smartphone or PC, along with a brief description.

[0393] Processing: The terminal sends the specified image file to the server.

[0394] Output: Image files and descriptive data sent to the server.

[0395] Step 2:

[0396] The uploaded image is analyzed, and its features are saved to a database.

[0397] Input: Image and description data of fashion items received by the server.

[0398] Processing: The server uses image analysis techniques (including machine learning algorithms) to extract features such as color, shape, and brand from the image.

[0399] Output: The extracted feature and descriptive data are stored in the database.

[0400] Step 3:

[0401] Obtain user sentiment information.

[0402] Input: User's facial image and voice data captured through the smart glasses' built-in camera and microphone.

[0403] Processing: The server uses EmotionRecognizer to analyze facial images and audio data to identify the user's emotions.

[0404] Output: Identified sentiment information.

[0405] Step 4:

[0406] Users can request outfits suitable for specific occasions.

[0407] Input: Event information entered by the user via voice commands or gesture interface on smart glasses, settings that take weather into consideration, and budget limits.

[0408] Processing: The terminal sends the user's request information to the server.

[0409] Output: Request information sent to the server.

[0410] Step 5:

[0411] Obtain weather and temperature information.

[0412] Input: The request that the server sends to the WeatherAPI service (date, time, and location of the request).

[0413] Processing: The WeatherAPI service returns weather and temperature information for the specified day to the server.

[0414] Output: Acquired weather and temperature information.

[0415] Step 6:

[0416] Based on acquired weather and temperature information, as well as emotional information, the system generates the optimal outfit.

[0417] Input: Weather and temperature information, sentiment information, and user fashion item information.

[0418] Processing: The server combines this information and uses an algorithm to generate the optimal coordination.

[0419] Output: The generated outfit.

[0420] Step 7:

[0421] Based on the generated outfit, search for trending items from external shopping sites.

[0422] Input: Generated outfit information.

[0423] Processing: The server sends a request to the e-commerce site to search for information on relevant trending products.

[0424] Output: A list of searched trending products.

[0425] Step 8:

[0426] The system displays optimal outfits and trending products on the user's device (smart glasses).

[0427] Input: A list of generated outfits and trending items.

[0428] Processing: The server sends this information to the smart glasses and presents it to the user through the display interface.

[0429] Output: Coordination and trending product information displayed on smart glasses.

[0430] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0431] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0432] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0433] [Second Embodiment]

[0434] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0435] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0436] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0437] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0438] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0439] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0440] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0441] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0442] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0443] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0444] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0445] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0446] ---

[0447] The system for implementing this invention involves the user uploading images of their clothes, shoes, bags, etc., and analyzing those images to store their features in a database. Furthermore, when the user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on that information. This generated outfit is displayed on the user's terminal along with trending items found on external shopping sites.

[0448] 1. Uploading images owned by the user

[0449] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0450] 2. Image Analysis and Feature Extraction

[0451] The server receives the uploaded image and description data, and uses image analysis technology to extract item features (color, shape, brand, etc.) from the image. The extracted features and description are stored in a database.

[0452] 3. Coordination Request

[0453] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[0454] 4. Obtaining weather and temperature information

[0455] The server uses a weather API service to retrieve weather and temperature information for the specified day. The retrieved information is then reflected in the outfit the user desires.

[0456] 5. Coordination generation

[0457] The server generates the optimal outfit based on weather and temperature information, as well as the user's fashion item information in the database. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans."

[0458] 6. Searching for trending products

[0459] Based on the generated outfit, the server searches for trending items from external shopping sites. This allows users to find the latest fashion items that match their existing wardrobe.

[0460] 7. Display of proposed content

[0461] The server sends the generated outfit and searched trending items to the user's terminal and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[0462] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." It then suggests an optimal outfit consisting of a "white shirt," "black sneakers," and "blue jeans," and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0463] ---

[0464] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products.

[0465] The following describes the processing flow.

[0466] ---

[0467] Step 1:

[0468] Users upload images of their own clothes, shoes, bags, etc., to the system from their smartphones or PCs. Users also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0469] Step 2:

[0470] The device sends the uploaded image and description data to the server. Images are sent in JPEG or PNG format, and descriptions are sent as text data.

[0471] Step 3:

[0472] The server analyzes the received images and uses image recognition technology to extract features (color, shape, brand, etc.) of clothing, shoes, bags, etc. It also analyzes the descriptive text and stores it together in the database.

[0473] Step 4:

[0474] Users log in and request outfit coordination from the system for a specific occasion or event. They also enter whether weather and temperature should be considered, and specify a budget limit.

[0475] Step 5:

[0476] The device sends user request data to the server. This data includes event information, weather selection, budget, etc.

[0477] Step 6:

[0478] The server uses a weather API to retrieve weather and temperature information for the requested day. It then retrieves and analyzes data from the weather API service.

[0479] Step 7:

[0480] The server searches and extracts matching items from the database based on the user's request and the weather and temperature information it has obtained. For example, if it is sunny and the temperature is 25 degrees Celsius, it will select suitable clothing, shoes, and bags.

[0481] Step 8:

[0482] Based on the items the server searches and extracts, it generates the most suitable outfit for the user's request. For example, it might suggest a "white shirt," "blue jeans," and "black sneakers" that would be suitable for a casual lunch.

[0483] Step 9:

[0484] The server calls the Yahoo Shopping API to search for the latest items that match the suggested outfit. This retrieves related products as trending information.

[0485] Step 10:

[0486] The server generates coordinated outfits and combines them with trending products found through Yahoo Shopping searches to create a single suggested package.

[0487] Step 11:

[0488] The terminal sends the suggested package to the user's terminal and displays it on the screen. It is displayed in a format that is easy for the user to understand.

[0489] Step 12:

[0490] Users review suggested outfits and trendy items, and if they find items they need, they click the purchase link to proceed with the purchase on e-commerce sites such as Yahoo Shopping.

[0491] ---

[0492] (Example 1)

[0493] Next, we will describe Example 1. 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."

[0494] Traditional fashion coordination systems struggled to efficiently match users' existing items with new, trendy products. Furthermore, they had difficulty considering external factors such as weather and temperature when suggesting outfits, making it challenging to provide optimal coordination tailored to users' specific needs. This often led to users feeling dissatisfied with their daily clothing choices and new item purchases.

[0495] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0496] In this invention, the server includes means for uploading images of clothing, footwear, bags, etc., owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; and means for receiving requests from the user for outfits suitable for specific occasions. This allows the system to incorporate detailed information about the items owned by the user and provide optimal outfits tailored to each individual user.

[0497] ---

[0498] ---

[0499] A "user" refers to someone who uses this system to manage their fashion items and receive styling suggestions.

[0500] "Clothing" refers to the clothes that users wear on a daily basis.

[0501] "Footwear" refers to shoes, sandals, and other items worn on the user's feet.

[0502] "Bag" refers to bags used by users to carry things.

[0503] "Images" refer to digital data containing visual information such as clothing, footwear, and bags uploaded by users.

[0504] "Analysis" refers to the process by which a server extracts features and information from uploaded images.

[0505] "Features" refer to attribute information such as the color, shape, and brand of an item obtained through analysis.

[0506] A "database" refers to an information management system used to store analyzed features and descriptions.

[0507] A "request" refers to an inquiry that a user sends to the system to request an outfit suitable for a specific occasion.

[0508] "Weather" refers to environmental information such as weather and temperature.

[0509] "Temperature" refers to the temperature reflected in the resulting outfit.

[0510] "Generation" refers to the process by which the server creates coordination suggestions based on the necessary information.

[0511] An "e-commerce site" refers to an online platform that includes external shopping sites.

[0512] "Terminal" refers to devices such as smartphones and personal computers that users use to operate the system.

[0513] "Display" refers to the act of visually showing information on a device screen.

[0514] A "machine learning algorithm" refers to a computer model that a server uses for image analysis.

[0515] A "product sales site" includes online shops where users can purchase items necessary for coordinating outfits.

[0516] ---

[0517] The above are the definitions of the important words.

[0518] ---

[0519] The system for implementing this invention begins with the user uploading images of their clothing, footwear, bags, etc., to the system using a smartphone or PC. The user enters a brief description for each image (e.g., "white shirt," "leather boots"), and this information is sent to the server.

[0520] The server receives the uploaded image and description data. Next, it uses image analysis technologies such as the Google Cloud Vision API to extract item features (color, shape, brand, etc.) from the image. The extracted features and descriptions are stored in a database. At this stage, machine learning algorithms are used for analysis, improving accuracy.

[0521] Users can submit requests to the system for outfits suitable for specific occasions or events (e.g., casual lunch, business meeting). When submitting a request, they can select options to consider weather and temperature, and set a budget limit.

[0522] The server uses weather API services such as the OpenWeatherMap API to obtain weather and temperature information for a specified day. The obtained information is then reflected in the outfit chosen by the user.

[0523] Next, the server generates the optimal outfit based on weather and temperature information and the user's fashion item information in the database. For example, if it's sunny and the temperature is 25 degrees Celsius, it might suggest a "white shirt" and "blue jeans."

[0524] Based on the generated outfit, the server searches for trending items from external e-commerce sites. Specifically, it uses online shopping sites such as Amazon and Rakuten to suggest the latest fashion items that match the user's belongings.

[0525] Finally, the server sends the generated outfit and searched trending items to the user's device and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[0526] Specific example

[0527] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers," and adds descriptions to them as "white shirt" and "leather boots," respectively. Next, the user requests an outfit for a casual weekend lunch, turns on the setting to consider the weather, and sets a budget of 10,000 yen. The server retrieves from the OpenWeatherMap API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items containing "white shirt" and "black sneakers" from its database. It then suggests the optimal outfit as "white shirt," "black sneakers," and "blue jeans," and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. This information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0528] Examples of prompts for generative AI models

[0529] The following is an example of a prompt:

[0530] A user uploaded images of their "white shirt" and "black sneakers" to the system. The system labeled these images "white shirt" and "leather boots." Next, the user requested an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server determined the weekend weather would be sunny with a temperature of 25 degrees Celsius and extracted items from its database that included a "white shirt" and "black sneakers." The server then suggested a suitable outfit: "white shirt," "black sneakers," and "blue jeans." Furthermore, it searched for and suggested related items such as casual sneakers and accessories from external shopping sites. All information was displayed on the user's device, allowing the user to review the suggestions and purchase items they liked.

[0531] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0532] ---

[0533] Step 1: The user uploads an image.

[0534] Users upload images of clothing, footwear, bags, etc., to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0535] Input: Image file and descriptive text

[0536] Output: Image file and descriptive text are sent to the server.

[0537] Specific actions: The user taps the "Upload" button, selects an image of a "white shirt," enters the description "white shirt," and presses the "Submit" button.

[0538] Step 2: The server receives the image and description.

[0539] The server receives the image file and descriptive text sent by the user.

[0540] Input: Image file and descriptive text

[0541] Output: Received image file and description text

[0542] Specific operation: The server retrieves data sent by the user and prepares for subsequent processing.

[0543] Step 3: Image analysis and feature extraction

[0544] The server uses image analysis technologies such as the Google Cloud Vision API to extract item features (color, shape, brand, etc.) from the image.

[0545] Input: Image file

[0546] Output: Extracted feature data (color, shape, brand, etc.)

[0547] Specific operation: The server sends the image file to the Google Cloud Vision API and analyzes the returned analysis results.

[0548] Step 4: Saving Feature Data

[0549] The server stores the extracted features and descriptive text in a database.

[0550] Input: Feature data, descriptive text

[0551] Output: Saved to database successfully

[0552] Specific operation: The server stores the feature data and descriptive text in the database in the appropriate format.

[0553] Step 5: The user requests an outfit.

[0554] Users request outfits suitable for specific occasions or events from the system. This includes specifying settings that take weather and temperature into consideration, as well as a budget limit.

[0555] Input: Event type, weather consideration options, budget limit

[0556] Output: Request data is sent to the server.

[0557] Specific actions: The user presses the "Coordination Request" button in the app, selects "Casual Lunch," turns "Weather Consideration On," and sets a budget of 10,000 yen.

[0558] Step 6: Obtain weather and temperature information

[0559] The server uses weather API services such as the OpenWeatherMap API to obtain weather and temperature information for a specified day.

[0560] Input: Request data, specified date

[0561] Output: Weather and temperature information

[0562] Specific operation: The server sends a request to the OpenWeatherMap API to retrieve information that the weather for the weekend will be sunny with a temperature of 25 degrees Celsius.

[0563] Step 7: Creating the outfit

[0564] The server generates the optimal outfit based on weather and temperature information, as well as the user's fashion item information in the database.

[0565] Input: Weather and temperature information, item information in the database.

[0566] Output: Generated coordinate data

[0567] Specific operation: The server extracts "white shirt," "black sneakers," and "blue jeans" from the database and combines them to create the optimal outfit.

[0568] Step 8: Search for trending products

[0569] Based on the generated coordinates, the server searches for trending products from external e-commerce sites.

[0570] Input: Generated coordinate data

[0571] Output: List of trending products

[0572] Specific operation: The server sends a request to the Amazon API with keywords such as "casual sneakers" and retrieves a list of related products.

[0573] Step 9: Display the proposed content

[0574] The server sends the generated outfits and searched trending items to the user's device and displays them on the screen.

[0575] Input: Generated outfit data, list of trending items

[0576] Output: Coordination suggestions displayed on the user's device

[0577] Specific operation: The app receives a notification on the user's device and displays "recommended outfits" including a "white shirt," "black sneakers," and "blue jeans." At the bottom, it displays "recommended casual sneakers" from Amazon with a link.

[0578] ---

[0579] The above is a description of the specific processing steps of this system's program.

[0580] (Application Example 1)

[0581] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0582] In recent years, consumer demand for fashion item coordination has increased, and there is a growing need for efficient and accurate suggestions. However, conventional systems struggle to suggest optimal outfits that combine the user's existing items with the latest fashion trends, and they lack suggestions that reflect specific situations or weather conditions. Furthermore, there are insufficient means to recommend trendy items that match individual user preferences, resulting in a lack of effective methods to increase purchasing intent.

[0583] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0584] In this invention, the server includes means for uploading images of clothes, shoes, bags, etc. owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; means for receiving requests from the user for outfits suitable for a specific occasion; means for obtaining weather and temperature information based on the request; means for generating the optimal outfit based on the obtained weather and temperature information and information in the database; means for searching for trending products from external e-commerce sites based on the generated outfit; means for displaying the optimal outfit and trending products on the user's terminal; and means for inputting the generated outfit and trending product information in prompt format into a generation AI model to display more refined outfits and recommended products. This makes it possible to provide the optimal outfit suitable for a specific occasion and weather using items owned by the user, and to make suggestions that also include trending products.

[0585] "A means for users to upload images of their own clothes, shoes, bags, etc." refers to a function that allows users to send image data of their own fashion items (clothes, shoes, or bags, etc.) to the system via the user interface.

[0586] "A means of analyzing uploaded images and saving their characteristics to a database" refers to a function that uses image analysis technology to extract characteristics such as color, shape, and material from images of fashion items uploaded by users, and saves them to a database.

[0587] "A means for users to request outfits suitable for specific situations" refers to a function that allows users to request the system to suggest fashion outfits suitable for specific situations or events they wish to attend.

[0588] "Means for obtaining weather and temperature information based on requests" refers to a function that obtains weather and temperature data for a specific day or region from external weather information services, according to the user's request.

[0589] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to a function that automatically generates clothing suggestions suitable for a specific situation by combining acquired weather and temperature data with the user's fashion item information stored in the database.

[0590] "A means of searching for trending products from external e-commerce sites based on generated outfits" refers to a function that searches for the latest trending fashion items from external e-commerce sites based on generated fashion outfits.

[0591] "A means of displaying optimal outfits and trendy products on the user's device" refers to a function that displays the generated optimal outfits and related trendy products on the screen of the user's device, such as a smartphone or personal computer.

[0592] "A means of inputting generated coordinate and trend product information into a generation AI model in prompt format to display more refined coordinates and recommended products" refers to a function that inputs generated fashion coordinate and trend product information into a generation AI model in text format, and then derives and displays more refined coordinates and recommended products based on that input.

[0593] The system for implementing this invention involves uploading images of clothing, shoes, bags, etc., owned by the user, and analyzing those images to store their features in a database. Furthermore, when the user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit. Based on this outfit, the system has the function of searching for trending products from external e-commerce sites and displaying them on the user's terminal.

[0594] 1. Uploading images owned by the user

[0595] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0596] 2. Image Analysis and Feature Extraction

[0597] The server receives the image and its description data uploaded by the user. Next, it uses a machine learning algorithm to analyze the image and extract item features (color, shape, brand, etc.). These extracted features and descriptions are stored in a database.

[0598] 3. Coordination Request

[0599] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[0600] 4. Obtaining weather and temperature information

[0601] The server uses a weather API service (e.g., WeatherAPI) to retrieve weather and temperature information for a specified day. The retrieved information is then used to generate the outfit requested by the user.

[0602] 5. Coordination generation

[0603] The server generates the optimal outfit based on the acquired weather and temperature information and the user's fashion item information in the database. For example, on a sunny day with a temperature of 25 degrees Celsius, it will suggest cool items such as a "white shirt" and "blue jeans."

[0604] 6. Searching for trending products

[0605] Based on the generated outfit, the server searches for trending items from external e-commerce sites. This allows users to find the latest fashion items that match their existing wardrobe.

[0606] 7. Display of proposed content and use of the generated AI model

[0607] The server sends the generated outfits and searched trending products to the user's device and displays them on the screen. It also inputs this information into a generation AI model in the form of prompts, which then generates and displays more refined outfits and recommended products.

[0608] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" they own, and labels each item. Next, they request an outfit for a casual weekend lunch, enabling weather consideration and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items containing "white shirt" and "black sneakers" from its database. It then suggests an optimal outfit consisting of "white shirt," "black sneakers," and "blue jeans," and further searches and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, the following prompt is entered into the generative AI model to display a refined suggestion:

[0609] "Could you recommend some outfits and the latest trendy items for a casual weekend lunch?"

[0610] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products.

[0611] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0612] Step 1:

[0613] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. The input consists of image data of the fashion item taken by the user and a brief description (e.g., "white shirt," "leather boots"). The output is the user's uploaded image and its corresponding description data.

[0614] Step 2:

[0615] The server receives images and descriptive data uploaded by users. Next, it uses machine learning algorithms to analyze the images and extract features such as color, shape, and brand. The input is the image data and descriptive data uploaded by the user, and the output is the feature data extracted through image analysis. The server stores this feature and descriptive data in a database.

[0616] Step 3:

[0617] Users can use their smartphones or PCs to request outfits suitable for specific occasions or events (e.g., casual lunch, business meeting). Input includes information about the occasion or event selected by the user, as well as options to consider weather and temperature, and a budget limit. Output is the request data sent to the server.

[0618] Step 4:

[0619] The server uses a weather API service to retrieve weather and temperature information for a specified date. The input is date and region information based on the user's request data. The output is the retrieved weather and temperature data. The server uses this data to generate coordinated outfits.

[0620] Step 5:

[0621] The server generates the optimal outfit based on acquired weather and temperature information and the user's fashion item information in the database. Specifically, it selects items suitable for the weather and temperature and suggests combinations appropriate for specific occasions or events. The inputs are weather and temperature data and fashion item information from the database. The output is the generated optimal outfit suggestion.

[0622] Step 6:

[0623] The server searches for trending products from external e-commerce sites based on the generated outfit. The input is the generated outfit proposal, and the output is information on the related trending products.

[0624] Step 7:

[0625] The server inputs the generated outfits and trending items into the AI ​​model in the form of prompt sentences. The AI ​​model then uses this information to generate more refined outfits and recommended items. The input is the information generated in the form of prompt sentences, and the output is the information on the final outfits and recommended items.

[0626] Step 8:

[0627] The server sends the final coordinated outfit and recommended items to the user's device and displays them on the screen. The input is the coordinated outfit and recommended items information generated by the generative AI model, and the output is the data displayed on the user's device. The user can review this and make purchases as needed.

[0628] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0629] ---

[0630] The system for implementing this invention involves the user uploading images of their clothes, shoes, bags, etc., and analyzing those images to store their features in a database. Furthermore, when a user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on that information and the user's emotional state. This generated outfit is displayed on the user's device along with trending items found on external shopping sites.

[0631] 1. Uploading images owned by the user

[0632] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0633] 2. Image Analysis and Feature Extraction

[0634] The server receives the uploaded image and description data, and uses image analysis technology to extract item features (color, shape, brand, etc.) from the image. The extracted features and description are stored in a database.

[0635] 3. Obtaining user sentiment information

[0636] The system incorporates an emotion engine that analyzes the user's image and voice data. When a user accesses the system, it uses a camera and microphone to capture the user's facial expressions and voice, and analyzes this data to identify the user's emotions.

[0637] 4. Coordination Request

[0638] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[0639] 5. Obtaining weather and temperature information

[0640] The server uses a weather API service to retrieve weather and temperature information for the specified day. The retrieved information is then reflected in the outfit the user desires.

[0641] 6. Coordination Generation

[0642] The server generates the optimal outfit based on weather and temperature information, the user's fashion item information in the database, and emotional information. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans," and if the user has a cheerful expression, it recommends an outfit with bright colors.

[0643] 7. Searching for trending products

[0644] Based on the generated outfit, the server searches for trending items from external shopping sites. This allows users to find the latest fashion items that match their existing wardrobe.

[0645] 8. Display of proposed content

[0646] The server sends the generated outfit and searched trending items to the user's terminal and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[0647] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server then suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0648] ---

[0649] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products. Furthermore, by reflecting the user's emotional information, it enables even more personalized coordinate suggestions.

[0650] The following describes the processing flow.

[0651] ---

[0652] Step 1:

[0653] Users upload images of their own clothes, shoes, bags, etc., to the system from their smartphones or PCs. Users also enter a brief description for each image.

[0654] Step 2:

[0655] The device sends the uploaded image and description data to the server. Images are sent in JPEG or PNG format, and descriptions are sent as text data.

[0656] Step 3:

[0657] The server analyzes the received images and uses image analysis technology to extract features (color, shape, brand, etc.) of clothing, shoes, bags, etc. The extracted features and descriptions are stored in a database.

[0658] Step 4:

[0659] Users log in and request outfit coordination from the system for specific occasions or events. When making a request, they can also set options such as considering weather and temperature, as well as a budget limit.

[0660] Step 5:

[0661] The device sends user request data to the server. This data includes event information, weather selection, budget, etc.

[0662] Step 6:

[0663] The server uses a weather API to retrieve weather and temperature information for the requested day. It then retrieves and analyzes data from the weather API service.

[0664] Step 7:

[0665] When a user accesses the system, the emotion engine uses the camera and microphone to capture the user's facial expressions and voice. The captured data is sent to the server.

[0666] Step 8:

[0667] The server analyzes the received image and audio data to identify the user's emotions. The identified emotion information is stored in a database.

[0668] Step 9:

[0669] The server generates the optimal outfit based on the user's request, acquired weather and temperature information, item information in the database, and the user's emotional state. For example, on a sunny day with a temperature of 25 degrees Celsius, if the user has a happy expression, the server will suggest a "white shirt," "blue jeans," and "black sneakers."

[0670] Step 10:

[0671] The server calls an API from an external shopping site to search for the latest items that match the suggested outfit. This retrieves related products as trend information.

[0672] Step 11:

[0673] The server generates coordinated outfits and combines them with trending products found on external shopping sites to create a single suggested package.

[0674] Step 12:

[0675] The terminal sends the suggested package to the user's terminal and displays it on the screen. It is presented in a format that is easy for the user to understand.

[0676] Step 13:

[0677] Users review suggested outfits and trendy items, and if necessary, click purchase links to proceed with the purchase process on external e-commerce sites.

[0678] ---

[0679] By dividing the processing steps in this way, the system can efficiently suggest fashion coordinates to the user and, by reflecting the user's emotional information, can achieve more personalized suggestions.

[0680] (Example 2)

[0681] Next, we will describe Example 2. 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".

[0682] Traditional fashion coordination systems offer features for registering and managing user-owned items, but they lack personalized coordination suggestions that incorporate user emotional information. This means that suggested outfits may not match the user's mood or preferences. Furthermore, the lack of consideration for weather and temperature information results in impractical outfit suggestions. Additionally, the function for searching for trending items suffers from insufficient integration with external e-commerce sites, preventing timely information provision.

[0683] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0684] In this invention, the server includes means for uploading images of clothing, footwear, bags, etc., owned by the user; means for analyzing the uploaded images and saving their respective characteristics to a database; means for analyzing the user's facial expressions and voice data to obtain emotional information; means for personalizing outfits based on the obtained emotional information; means for obtaining weather and temperature information based on a request; means for generating an optimal outfit based on the obtained weather and temperature information and information in the database; means for searching for trending products from external e-commerce sites based on the generated outfit; and means for displaying the optimal outfit and trending products on the user's terminal. This makes it possible to provide more personalized and practical outfit suggestions that take into account the user's emotions and weather information.

[0685] "A means for users to upload images of clothing, footwear, bags, etc. they own" refers to a function that allows users to send images of their fashion items to the system using their smartphones or PCs.

[0686] "A means of analyzing uploaded images and saving their features to a database" refers to a function that extracts features such as color, shape, and brand based on received images and stores that information in a database.

[0687] "Means for analyzing user facial expressions and voice data to obtain emotional information" refers to a function that analyzes the user's facial expressions and voice to identify and obtain their emotions at that time (e.g., happy, sad, surprised, etc.).

[0688] "A means of personalizing outfits based on acquired emotional information" refers to a function that utilizes the user's emotional information to suggest the optimal fashion outfit that matches their mood at that time.

[0689] "Means for obtaining weather and temperature information based on requests" refers to a function for obtaining weather and temperature information for a specified date, time, and location based on coordination requests from users.

[0690] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to a function that utilizes weather information, temperature information, and user fashion item information stored in the database to create the optimal outfit suitable for the date, time, and location.

[0691] "A means of searching for trending products from external e-commerce sites based on generated outfits" refers to a function that searches for the latest related fashion items from external e-commerce sites based on generated fashion outfits.

[0692] "A means of displaying optimal outfits and trending products on the user's device" refers to a function that displays generated outfits and related trending product information on the user's smartphone, PC, or other device.

[0693] Modes for carrying out the invention

[0694] The system for implementing this invention uploads images of fashion items such as clothing, footwear, and bags owned by the user, analyzes the images to extract features, and stores them in a database. Furthermore, when a user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on this information and the user's emotional state. This generated outfit is displayed on the user's terminal along with trending items found on external e-commerce sites.

[0695] Hardware and software

[0696] Hardware:

[0697] This system uses devices such as smartphones, personal computers, and servers.

[0698] software:

[0699] Image analysis uses common image recognition APIs (e.g., Google Vision API). Sentiment analysis uses a common sentiment engine (e.g., Microsoft Azure Face API). Weather information is obtained using weather API services (e.g., OpenWeatherMap API). Database management uses a relational database management system (RDBMS).

[0700] Program processing

[0701] When a user uploads an image, the server receives it and extracts features from the image using an image recognition API. The extracted features, along with labels, are stored in a database. When a user accesses the system, the camera and microphone are used to capture the user's facial expressions and voice, and an emotion engine is used to analyze the emotional information. When a user requests a specific outfit, the server calls a non-essential data API to obtain weather and temperature information for the specified day and location. Based on the obtained weather and temperature information, the user's item information, and emotional information, the server generates the optimal outfit. Furthermore, based on the generated outfit, it searches for relevant trending products from external e-commerce sites. The optimal outfit and trending products are then displayed on the user's device.

[0702] Specific example

[0703] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, the user requests an outfit for a casual weekend lunch, turns on the setting to consider the weather, and sets a budget of 10,000 yen. The server retrieves from the weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from the database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0704] Example of a prompt

[0705] Upload an image of yourself wearing a white shirt and black sneakers, and request an outfit suggestion for a casual lunch. Turn on weather consideration and set a budget limit of 10,000 yen.

[0706] In this way, this system efficiently suggests fashion coordinates to users and provides related trendy products, thereby improving the user's fashion experience. Furthermore, by reflecting the user's emotional information, it is possible to achieve even more personalized coordinate suggestions.

[0707] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0708] Step 1:

[0709] The user uploads an image.

[0710] Input: Images of clothing, footwear, bags, etc., taken by the user, and their corresponding descriptive labels (e.g., "white shirt").

[0711] Specific steps: The user opens the application on their smartphone or PC, clicks the upload button, selects an image of a "white shirt," and enters label information.

[0712] Output: Image data and its label information sent to the server.

[0713] Step 2:

[0714] The server receives the image.

[0715] Input: Image data and label information submitted by the user.

[0716] Specific operation: The server receives the upload request and retrieves the image data and label information.

[0717] Output: Received image data and label information.

[0718] Step 3:

[0719] The server performs image analysis and extracts features.

[0720] Input: Image data received by the server.

[0721] Specific operation: The server uses image analysis technologies such as the Google Vision API to extract features such as color, shape, and brand from an image. For example, it might detect "Color: White" and "Item: Shirt".

[0722] Output: Extracted feature information.

[0723] Step 4:

[0724] The server saves the features to the database.

[0725] Input: Extracted feature information and label information.

[0726] Specific operation: The server saves the extracted feature information (color: white, item: shirt) and label information (white shirt) to a relational database.

[0727] Output: Feature information and label information stored in the database.

[0728] Step 5:

[0729] Obtain user sentiment information.

[0730] Input: User's facial image and voice data acquired from a camera and microphone connected to the application.

[0731] Specific operation: When a user accesses the application, the system activates the camera to capture the user's facial expression and uses an emotion engine (such as the Microsoft Azure Face API) to analyze emotions such as "smile."

[0732] Output: Acquired emotion information (e.g., "happy").

[0733] Step 6:

[0734] The user requests an outfit coordination.

[0735] Input: User-entered outfit request information (e.g., casual lunch, weather consideration setting on, budget limit of 10,000 yen).

[0736] Specific action: The user selects "Casual Lunch" in the application, turns on the weather consideration setting, sets a budget limit of 10,000 yen, and submits the request.

[0737] Output: Coordination request information.

[0738] Step 7:

[0739] The server retrieves weather and temperature information.

[0740] Input: User's coordination request information and request date, time, and location information.

[0741] Specific operation: The server calls the OpenWeatherMap API to retrieve weather and temperature information (e.g., sunny, temperature 25 degrees) for a specified date, time, and location.

[0742] Output: Acquired weather and temperature information.

[0743] Step 8:

[0744] The server generates the optimal coordination.

[0745] Input: Acquired weather and temperature information, user item information in the database, and acquired sentiment information.

[0746] Specific operation: The server generates the optimal outfit (white shirt, blue jeans) based on weather and temperature information (sunny, 25 degrees), item information stored in the database (white shirt, black sneakers), and user emotion information (happy).

[0747] Output: Generated coordination information.

[0748] Step 9:

[0749] The server searches for trending products.

[0750] Input: Generated outfit information.

[0751] Specific operation: The server uses APIs from external e-commerce sites such as Amazon and Rakuten to search for trending products (e.g., blue cap, casual sneakers) based on the generated outfit.

[0752] Output: Searched trending product information.

[0753] Step 10:

[0754] The server displays the suggested content on the user's terminal.

[0755] Input: Generated outfit information and searched trend product information.

[0756] Specific operation: The server sends the generated outfit and the searched trending items (blue cap, casual sneakers) to the user's device and displays them on the application screen.

[0757] Output: The suggested content displayed on the user's terminal.

[0758] (Application Example 2)

[0759] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0760] Conventional fashion coordination suggestion systems generated outfits using image analysis of items owned by the user and weather information, but they lacked individuality and immediacy because they did not take into account the user's emotions or real-time display of outfits. As a result, it was difficult for users to obtain appropriate outfits that suited their emotions and specific situations. Furthermore, they did not support intuitive interaction using new devices such as smart glasses. The objective of this invention is to solve these problems.

[0761] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0762] In this invention, the server includes means for uploading images of clothes, shoes, bags, etc., owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; means for receiving requests from the user for outfits suitable for a specific occasion; means for acquiring weather and temperature information based on the requests; means for generating the optimal outfit based on the acquired weather and temperature information and information in the database; means for searching for trendy products from external shopping sites based on the generated outfit; means for displaying the optimal outfit and trendy products on the user's terminal; means for acquiring the user's emotional information and adjusting the outfit based on it; and means for using smart glasses as the user's terminal. This makes it possible to suggest personalized outfits that respond to the user's emotions and real-time situation.

[0763] "Means for uploading images of clothing, shoes, bags, etc. owned by users" refers to software and hardware that allows users to send images of their fashion items to a server via the internet.

[0764] "A means of analyzing uploaded images and saving their characteristics to a database" refers to software that uses image analysis technology to extract the characteristics of uploaded fashion items and stores that information in a database within the system.

[0765] "A means for users to request outfits suitable for specific occasions" refers to an interface and function that allows users to request fashion suggestions appropriate for events or situations.

[0766] "Means for obtaining weather and temperature information based on requests" refers to communication and software for obtaining weather and temperature data for a requested date, time, and location from an external weather information service.

[0767] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to an algorithm and software that automatically creates appropriate fashion outfits by combining weather, temperature, and the characteristics of the user's owned items.

[0768] "A means of searching for trendy items from external shopping sites based on a generated outfit" refers to a communication function and software for searching for the latest fashion items related to an automatically generated outfit from an external e-commerce site.

[0769] "Means for displaying optimal outfits and trendy products on the user's device" refers to an interface and software for displaying generated outfits and related trendy product information on the user's smart device.

[0770] "Means for acquiring user emotional information and adjusting outfits based on it" refers to technology that analyzes the user's facial expressions and voice to identify emotions and adjust fashion outfits accordingly.

[0771] "Means of using smart glasses as a user terminal" refers to the technology and software for displaying outfit suggestions and information on trending products via smart glasses worn by the user.

[0772] This invention is a system that allows users to upload images of fashion items such as clothes, shoes, and bags they own, analyzes these images to extract features, and stores that information in a database. Furthermore, when providing outfit suggestions based on user requests, it also includes a function to search for trending items from external e-commerce sites, taking into account weather and temperature information as well as the user's emotional state. The following describes a specific embodiment of this invention.

[0773] 1. Uploading images owned by the user

[0774] Users upload images of their own fashion items, such as clothes, shoes, and bags, to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0775] 2. Image Analysis and Feature Extraction

[0776] The server receives the uploaded image and description data, performs image analysis using machine learning algorithms, and extracts item features (color, shape, brand, etc.). The extracted features and descriptions are stored in a database.

[0777] 3. Obtaining user sentiment information

[0778] When a user accesses the system, the smart glasses' built-in camera and microphone capture the user's facial expressions and voice, and EmotionRecognizer identifies the user's emotions. The identified emotion information is used to generate coordinates.

[0779] 4. Coordination Request

[0780] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they can submit a request to the system via voice commands or gesture interface on their smart glasses. When making a request, they can also set settings that consider weather and temperature, as well as a budget limit.

[0781] 5. Obtaining weather and temperature information

[0782] The server uses the WeatherAPI service to retrieve weather and temperature information for a specified day. This retrieved weather and temperature information is then combined with the user's fashion item information stored in the database to generate outfit ideas.

[0783] 6. Coordination Generation

[0784] The server generates the optimal outfit based on weather and temperature information, the user's fashion item information in the database, and emotional information. The generated outfit is adjusted according to the user's requests and mood. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans," and if the user has a cheerful expression, it recommends an outfit with bright colors.

[0785] 7. Searching for trending products

[0786] Based on the generated outfit, the server searches for trending products from external e-commerce sites and suggests related fashion items to the user.

[0787] 8. Display of proposed content

[0788] The server sends the generated outfits and searched trending items to the user's smart glasses for real-time display. This allows the user to intuitively check the outfits and purchase trending items as needed.

[0789] Specific example

[0790] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from the WeatherAPI that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server then suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches for and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, this information is displayed on the user's smart glasses, allowing the user to review the suggestions and purchase items they like.

[0791] Example of a prompt

[0792] User: I live in Tokyo today and it's sunny with a temperature of 25 degrees Celsius. I'm planning to go out for a casual lunch. I'm in a very good mood. What kind of outfit would be appropriate?

[0793] This invention allows users to receive personalized outfit suggestions through smart glasses that are tailored to their emotions and real-time circumstances.

[0794] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0795] Step 1:

[0796] Users upload images of fashion items they own.

[0797] Input: Images of clothing, shoes, bags, etc., uploaded from the user's smartphone or PC, along with a brief description.

[0798] Processing: The terminal sends the specified image file to the server.

[0799] Output: Image files and descriptive data sent to the server.

[0800] Step 2:

[0801] The uploaded image is analyzed, and its features are saved to a database.

[0802] Input: Image and description data of fashion items received by the server.

[0803] Processing: The server uses image analysis techniques (including machine learning algorithms) to extract features such as color, shape, and brand from the image.

[0804] Output: The extracted feature and descriptive data are stored in the database.

[0805] Step 3:

[0806] Obtain user sentiment information.

[0807] Input: User's facial image and voice data captured through the smart glasses' built-in camera and microphone.

[0808] Processing: The server uses EmotionRecognizer to analyze facial images and audio data to identify the user's emotions.

[0809] Output: Identified sentiment information.

[0810] Step 4:

[0811] Users can request outfits suitable for specific occasions.

[0812] Input: Event information entered by the user via voice commands or gesture interface on smart glasses, settings that take weather into consideration, and budget limits.

[0813] Processing: The terminal sends the user's request information to the server.

[0814] Output: Request information sent to the server.

[0815] Step 5:

[0816] Obtain weather and temperature information.

[0817] Input: The request that the server sends to the WeatherAPI service (date, time, and location of the request).

[0818] Processing: The WeatherAPI service returns weather and temperature information for the specified day to the server.

[0819] Output: Acquired weather and temperature information.

[0820] Step 6:

[0821] Based on acquired weather and temperature information, as well as emotional information, the system generates the optimal outfit.

[0822] Input: Weather and temperature information, sentiment information, and user fashion item information.

[0823] Processing: The server combines this information and uses an algorithm to generate the optimal coordination.

[0824] Output: The generated outfit.

[0825] Step 7:

[0826] Based on the generated outfit, search for trending items from external shopping sites.

[0827] Input: Generated outfit information.

[0828] Processing: The server sends a request to the e-commerce site to search for information on relevant trending products.

[0829] Output: A list of searched trending products.

[0830] Step 8:

[0831] The system displays optimal outfits and trending products on the user's device (smart glasses).

[0832] Input: A list of generated outfits and trending items.

[0833] Processing: The server sends this information to the smart glasses and presents it to the user through the display interface.

[0834] Output: Coordination and trending product information displayed on smart glasses.

[0835] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0836] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0837] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0838] [Third Embodiment]

[0839] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0840] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0841] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0842] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0843] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0844] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0845] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0846] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0847] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0848] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0849] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0850] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0851] ---

[0852] The system for implementing this invention involves the user uploading images of their clothes, shoes, bags, etc., and analyzing those images to store their features in a database. Furthermore, when the user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on that information. This generated outfit is displayed on the user's terminal along with trending items found on external shopping sites.

[0853] 1. Uploading images owned by the user

[0854] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0855] 2. Image Analysis and Feature Extraction

[0856] The server receives the uploaded image and description data, and uses image analysis technology to extract item features (color, shape, brand, etc.) from the image. The extracted features and description are stored in a database.

[0857] 3. Coordination Request

[0858] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[0859] 4. Obtaining weather and temperature information

[0860] The server uses a weather API service to retrieve weather and temperature information for the specified day. The retrieved information is then reflected in the outfit the user desires.

[0861] 5. Coordination generation

[0862] The server generates the optimal outfit based on weather and temperature information, as well as the user's fashion item information in the database. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans."

[0863] 6. Searching for trending products

[0864] Based on the generated outfit, the server searches for trending items from external shopping sites. This allows users to find the latest fashion items that match their existing wardrobe.

[0865] 7. Display of proposed content

[0866] The server sends the generated outfit and searched trending items to the user's terminal and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[0867] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." It then suggests an optimal outfit consisting of a "white shirt," "black sneakers," and "blue jeans," and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0868] ---

[0869] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products.

[0870] The following describes the processing flow.

[0871] ---

[0872] Step 1:

[0873] Users upload images of their own clothes, shoes, bags, etc., to the system from their smartphones or PCs. Users also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0874] Step 2:

[0875] The device sends the uploaded image and description data to the server. Images are sent in JPEG or PNG format, and descriptions are sent as text data.

[0876] Step 3:

[0877] The server analyzes the received images and uses image recognition technology to extract features (color, shape, brand, etc.) of clothing, shoes, bags, etc. It also analyzes the descriptive text and stores it together in the database.

[0878] Step 4:

[0879] Users log in and request outfit coordination from the system for a specific occasion or event. They also enter whether weather and temperature should be considered, and specify a budget limit.

[0880] Step 5:

[0881] The device sends user request data to the server. This data includes event information, weather selection, budget, etc.

[0882] Step 6:

[0883] The server uses a weather API to retrieve weather and temperature information for the requested day. It then retrieves and analyzes data from the weather API service.

[0884] Step 7:

[0885] The server searches and extracts matching items from the database based on the user's request and the weather and temperature information it has obtained. For example, if it is sunny and the temperature is 25 degrees Celsius, it will select suitable clothing, shoes, and bags.

[0886] Step 8:

[0887] Based on the items the server searches and extracts, it generates the most suitable outfit for the user's request. For example, it might suggest a "white shirt," "blue jeans," and "black sneakers" that would be suitable for a casual lunch.

[0888] Step 9:

[0889] The server calls the Yahoo Shopping API to search for the latest items that match the suggested outfit. This retrieves related products as trending information.

[0890] Step 10:

[0891] The server generates coordinated outfits and combines them with trending products found through Yahoo Shopping searches to create a single suggested package.

[0892] Step 11:

[0893] The terminal sends the suggested package to the user's terminal and displays it on the screen. It is displayed in a format that is easy for the user to understand.

[0894] Step 12:

[0895] Users review suggested outfits and trendy items, and if they find items they need, they click the purchase link to proceed with the purchase on e-commerce sites such as Yahoo Shopping.

[0896] ---

[0897] (Example 1)

[0898] Next, we will describe Example 1. 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."

[0899] Traditional fashion coordination systems struggled to efficiently match users' existing items with new, trendy products. Furthermore, they had difficulty considering external factors such as weather and temperature when suggesting outfits, making it challenging to provide optimal coordination tailored to users' specific needs. This often led to users feeling dissatisfied with their daily clothing choices and new item purchases.

[0900] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0901] In this invention, the server includes means for uploading images of clothing, footwear, bags, etc., owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; and means for receiving requests from the user for outfits suitable for specific occasions. This allows the system to incorporate detailed information about the items owned by the user and provide optimal outfits tailored to each individual user.

[0902] ---

[0903] ---

[0904] A "user" refers to someone who uses this system to manage their fashion items and receive styling suggestions.

[0905] "Clothing" refers to the clothes that users wear on a daily basis.

[0906] "Footwear" refers to shoes, sandals, and other items worn on the user's feet.

[0907] "Bag" refers to bags used by users to carry things.

[0908] "Images" refer to digital data containing visual information such as clothing, footwear, and bags uploaded by users.

[0909] "Analysis" refers to the process by which a server extracts features and information from uploaded images.

[0910] "Features" refer to attribute information such as the color, shape, and brand of an item obtained through analysis.

[0911] A "database" refers to an information management system used to store analyzed features and descriptions.

[0912] A "request" refers to an inquiry that a user sends to the system to request an outfit suitable for a specific occasion.

[0913] "Weather" refers to environmental information such as weather and temperature.

[0914] "Temperature" refers to the temperature reflected in the resulting outfit.

[0915] "Generation" refers to the process by which the server creates coordination suggestions based on the necessary information.

[0916] An "e-commerce site" refers to an online platform that includes external shopping sites.

[0917] "Terminal" refers to devices such as smartphones and personal computers that users use to operate the system.

[0918] "Display" refers to the act of visually showing information on a device screen.

[0919] A "machine learning algorithm" refers to a computer model that a server uses for image analysis.

[0920] A "product sales site" includes online shops where users can purchase items necessary for coordinating outfits.

[0921] ---

[0922] The above are the definitions of the important words.

[0923] ---

[0924] The system for implementing this invention begins with the user uploading images of their clothing, footwear, bags, etc., to the system using a smartphone or PC. The user enters a brief description for each image (e.g., "white shirt," "leather boots"), and this information is sent to the server.

[0925] The server receives the uploaded image and description data. Next, it uses image analysis technologies such as the Google Cloud Vision API to extract item features (color, shape, brand, etc.) from the image. The extracted features and descriptions are stored in a database. At this stage, machine learning algorithms are used for analysis, improving accuracy.

[0926] Users can submit requests to the system for outfits suitable for specific occasions or events (e.g., casual lunch, business meeting). When submitting a request, they can select options to consider weather and temperature, and set a budget limit.

[0927] The server uses weather API services such as the OpenWeatherMap API to obtain weather and temperature information for a specified day. The obtained information is then reflected in the outfit chosen by the user.

[0928] Next, the server generates the optimal outfit based on weather and temperature information and the user's fashion item information in the database. For example, if it's sunny and the temperature is 25 degrees Celsius, it might suggest a "white shirt" and "blue jeans."

[0929] Based on the generated outfit, the server searches for trending items from external e-commerce sites. Specifically, it uses online shopping sites such as Amazon and Rakuten to suggest the latest fashion items that match the user's belongings.

[0930] Finally, the server sends the generated outfit and searched trending items to the user's device and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[0931] Specific example

[0932] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers," and adds descriptions to them as "white shirt" and "leather boots," respectively. Next, the user requests an outfit for a casual weekend lunch, turns on the setting to consider the weather, and sets a budget of 10,000 yen. The server retrieves from the OpenWeatherMap API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items containing "white shirt" and "black sneakers" from its database. It then suggests the optimal outfit as "white shirt," "black sneakers," and "blue jeans," and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. This information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[0933] Examples of prompts for generative AI models

[0934] The following is an example of a prompt:

[0935] A user uploaded images of their "white shirt" and "black sneakers" to the system. The system labeled these images "white shirt" and "leather boots." Next, the user requested an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server determined the weekend weather would be sunny with a temperature of 25 degrees Celsius and extracted items from its database that included a "white shirt" and "black sneakers." The server then suggested a suitable outfit: "white shirt," "black sneakers," and "blue jeans." Furthermore, it searched for and suggested related items such as casual sneakers and accessories from external shopping sites. All information was displayed on the user's device, allowing the user to review the suggestions and purchase items they liked.

[0936] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0937] ---

[0938] Step 1: The user uploads an image.

[0939] Users upload images of clothing, footwear, bags, etc., to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[0940] Input: Image file and descriptive text

[0941] Output: Image file and descriptive text are sent to the server.

[0942] Specific actions: The user taps the "Upload" button, selects an image of a "white shirt," enters the description "white shirt," and presses the "Submit" button.

[0943] Step 2: The server receives the image and description.

[0944] The server receives the image file and descriptive text sent by the user.

[0945] Input: Image file and descriptive text

[0946] Output: Received image file and description text

[0947] Specific operation: The server retrieves data sent by the user and prepares for subsequent processing.

[0948] Step 3: Image analysis and feature extraction

[0949] The server uses image analysis technologies such as the Google Cloud Vision API to extract item features (color, shape, brand, etc.) from the image.

[0950] Input: Image file

[0951] Output: Extracted feature data (color, shape, brand, etc.)

[0952] Specific operation: The server sends the image file to the Google Cloud Vision API and analyzes the returned analysis results.

[0953] Step 4: Saving Feature Data

[0954] The server stores the extracted features and descriptive text in a database.

[0955] Input: Feature data, descriptive text

[0956] Output: Saved to database successfully

[0957] Specific operation: The server stores the feature data and descriptive text in the database in the appropriate format.

[0958] Step 5: The user requests an outfit.

[0959] Users request outfits suitable for specific occasions or events from the system. This includes specifying settings that take weather and temperature into consideration, as well as a budget limit.

[0960] Input: Event type, weather consideration options, budget limit

[0961] Output: Request data is sent to the server.

[0962] Specific actions: The user presses the "Coordination Request" button in the app, selects "Casual Lunch," turns "Weather Consideration On," and sets a budget of 10,000 yen.

[0963] Step 6: Obtain weather and temperature information

[0964] The server uses weather API services such as the OpenWeatherMap API to obtain weather and temperature information for a specified day.

[0965] Input: Request data, specified date

[0966] Output: Weather and temperature information

[0967] Specific operation: The server sends a request to the OpenWeatherMap API to retrieve information that the weather for the weekend will be sunny with a temperature of 25 degrees Celsius.

[0968] Step 7: Creating the outfit

[0969] The server generates the optimal outfit based on weather and temperature information, as well as the user's fashion item information in the database.

[0970] Input: Weather and temperature information, item information in the database.

[0971] Output: Generated coordinate data

[0972] Specific operation: The server extracts "white shirt," "black sneakers," and "blue jeans" from the database and combines them to create the optimal outfit.

[0973] Step 8: Search for trending products

[0974] Based on the generated coordinates, the server searches for trending products from external e-commerce sites.

[0975] Input: Generated coordinate data

[0976] Output: List of trending products

[0977] Specific operation: The server sends a request to the Amazon API with keywords such as "casual sneakers" and retrieves a list of related products.

[0978] Step 9: Display the proposed content

[0979] The server sends the generated outfits and searched trending items to the user's device and displays them on the screen.

[0980] Input: Generated outfit data, list of trending items

[0981] Output: Coordination suggestions displayed on the user's device

[0982] Specific operation: The app receives a notification on the user's device and displays "recommended outfits" including a "white shirt," "black sneakers," and "blue jeans." At the bottom, it displays "recommended casual sneakers" from Amazon with a link.

[0983] ---

[0984] The above is a description of the specific processing steps of this system's program.

[0985] (Application Example 1)

[0986] Next, we will explain Application Example 1. In the following explanation, 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."

[0987] In recent years, consumer demand for fashion item coordination has increased, and there is a growing need for efficient and accurate suggestions. However, conventional systems struggle to suggest optimal outfits that combine the user's existing items with the latest fashion trends, and they lack suggestions that reflect specific situations or weather conditions. Furthermore, there are insufficient means to recommend trendy items that match individual user preferences, resulting in a lack of effective methods to increase purchasing intent.

[0988] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0989] In this invention, the server includes means for uploading images of clothes, shoes, bags, etc. owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; means for receiving requests from the user for outfits suitable for a specific occasion; means for obtaining weather and temperature information based on the request; means for generating the optimal outfit based on the obtained weather and temperature information and information in the database; means for searching for trending products from external e-commerce sites based on the generated outfit; means for displaying the optimal outfit and trending products on the user's terminal; and means for inputting the generated outfit and trending product information in prompt format into a generation AI model to display more refined outfits and recommended products. This makes it possible to provide the optimal outfit suitable for a specific occasion and weather using items owned by the user, and to make suggestions that also include trending products.

[0990] "A means for users to upload images of their own clothes, shoes, bags, etc." refers to a function that allows users to send image data of their own fashion items (clothes, shoes, or bags, etc.) to the system via the user interface.

[0991] "A means of analyzing uploaded images and saving their characteristics to a database" refers to a function that uses image analysis technology to extract characteristics such as color, shape, and material from images of fashion items uploaded by users, and saves them to a database.

[0992] "A means for users to request outfits suitable for specific situations" refers to a function that allows users to request the system to suggest fashion outfits suitable for specific situations or events they wish to attend.

[0993] "Means for obtaining weather and temperature information based on requests" refers to a function that obtains weather and temperature data for a specific day or region from external weather information services, according to the user's request.

[0994] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to a function that automatically generates clothing suggestions suitable for a specific situation by combining acquired weather and temperature data with the user's fashion item information stored in the database.

[0995] "A means of searching for trending products from external e-commerce sites based on generated outfits" refers to a function that searches for the latest trending fashion items from external e-commerce sites based on generated fashion outfits.

[0996] "A means of displaying optimal outfits and trendy products on the user's device" refers to a function that displays the generated optimal outfits and related trendy products on the screen of the user's device, such as a smartphone or personal computer.

[0997] "A means of inputting generated coordinate and trend product information into a generation AI model in prompt format to display more refined coordinates and recommended products" refers to a function that inputs generated fashion coordinate and trend product information into a generation AI model in text format, and then derives and displays more refined coordinates and recommended products based on that input.

[0998] The system for implementing this invention involves uploading images of clothing, shoes, bags, etc., owned by the user, and analyzing those images to store their features in a database. Furthermore, when the user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit. Based on this outfit, the system has the function of searching for trending products from external e-commerce sites and displaying them on the user's terminal.

[0999] 1. Uploading images owned by the user

[1000] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[1001] 2. Image Analysis and Feature Extraction

[1002] The server receives the image and its description data uploaded by the user. Next, it uses a machine learning algorithm to analyze the image and extract item features (color, shape, brand, etc.). These extracted features and descriptions are stored in a database.

[1003] 3. Coordination Request

[1004] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[1005] 4. Obtaining weather and temperature information

[1006] The server uses a weather API service (e.g., WeatherAPI) to retrieve weather and temperature information for a specified day. The retrieved information is then used to generate the outfit requested by the user.

[1007] 5. Coordination generation

[1008] The server generates the optimal outfit based on the acquired weather and temperature information and the user's fashion item information in the database. For example, on a sunny day with a temperature of 25 degrees Celsius, it will suggest cool items such as a "white shirt" and "blue jeans."

[1009] 6. Searching for trending products

[1010] Based on the generated outfit, the server searches for trending items from external e-commerce sites. This allows users to find the latest fashion items that match their existing wardrobe.

[1011] 7. Display of proposed content and use of the generated AI model

[1012] The server sends the generated outfits and searched trending products to the user's device and displays them on the screen. It also inputs this information into a generation AI model in the form of prompts, which then generates and displays more refined outfits and recommended products.

[1013] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" they own, and labels each item. Next, they request an outfit for a casual weekend lunch, enabling weather consideration and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items containing "white shirt" and "black sneakers" from its database. It then suggests an optimal outfit consisting of "white shirt," "black sneakers," and "blue jeans," and further searches and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, the following prompt is entered into the generative AI model to display a refined suggestion:

[1014] "Could you recommend some outfits and the latest trendy items for a casual weekend lunch?"

[1015] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products.

[1016] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1017] Step 1:

[1018] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. The input consists of image data of the fashion item taken by the user and a brief description (e.g., "white shirt," "leather boots"). The output is the user's uploaded image and its corresponding description data.

[1019] Step 2:

[1020] The server receives images and descriptive data uploaded by users. Next, it uses machine learning algorithms to analyze the images and extract features such as color, shape, and brand. The input is the image data and descriptive data uploaded by the user, and the output is the feature data extracted through image analysis. The server stores this feature and descriptive data in a database.

[1021] Step 3:

[1022] Users can use their smartphones or PCs to request outfits suitable for specific occasions or events (e.g., casual lunch, business meeting). Input includes information about the occasion or event selected by the user, as well as options to consider weather and temperature, and a budget limit. Output is the request data sent to the server.

[1023] Step 4:

[1024] The server uses a weather API service to retrieve weather and temperature information for a specified date. The input is date and region information based on the user's request data. The output is the retrieved weather and temperature data. The server uses this data to generate coordinated outfits.

[1025] Step 5:

[1026] The server generates the optimal outfit based on acquired weather and temperature information and the user's fashion item information in the database. Specifically, it selects items suitable for the weather and temperature and suggests combinations appropriate for specific occasions or events. The inputs are weather and temperature data and fashion item information from the database. The output is the generated optimal outfit suggestion.

[1027] Step 6:

[1028] The server searches for trending products from external e-commerce sites based on the generated outfit. The input is the generated outfit proposal, and the output is information on the related trending products.

[1029] Step 7:

[1030] The server inputs the generated outfits and trending items into the AI ​​model in the form of prompt sentences. The AI ​​model then uses this information to generate more refined outfits and recommended items. The input is the information generated in the form of prompt sentences, and the output is the information on the final outfits and recommended items.

[1031] Step 8:

[1032] The server sends the final coordinated outfit and recommended items to the user's device and displays them on the screen. The input is the coordinated outfit and recommended items information generated by the generative AI model, and the output is the data displayed on the user's device. The user can review this and make purchases as needed.

[1033] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1034] ---

[1035] The system for implementing this invention involves the user uploading images of their clothes, shoes, bags, etc., and analyzing those images to store their features in a database. Furthermore, when a user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on that information and the user's emotional state. This generated outfit is displayed on the user's device along with trending items found on external shopping sites.

[1036] 1. Uploading images owned by the user

[1037] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[1038] 2. Image Analysis and Feature Extraction

[1039] The server receives the uploaded image and description data, and uses image analysis technology to extract item features (color, shape, brand, etc.) from the image. The extracted features and description are stored in a database.

[1040] 3. Obtaining user sentiment information

[1041] The system incorporates an emotion engine that analyzes the user's image and voice data. When a user accesses the system, it uses a camera and microphone to capture the user's facial expressions and voice, and analyzes this data to identify the user's emotions.

[1042] 4. Coordination Request

[1043] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[1044] 5. Obtaining weather and temperature information

[1045] The server uses a weather API service to retrieve weather and temperature information for the specified day. The retrieved information is then reflected in the outfit the user desires.

[1046] 6. Coordination Generation

[1047] The server generates the optimal outfit based on weather and temperature information, the user's fashion item information in the database, and emotional information. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans," and if the user has a cheerful expression, it recommends an outfit with bright colors.

[1048] 7. Searching for trending products

[1049] Based on the generated outfit, the server searches for trending items from external shopping sites. This allows users to find the latest fashion items that match their existing wardrobe.

[1050] 8. Display of proposed content

[1051] The server sends the generated outfit and searched trending items to the user's terminal and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[1052] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server then suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[1053] ---

[1054] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products. Furthermore, by reflecting the user's emotional information, it enables even more personalized coordinate suggestions.

[1055] The following describes the processing flow.

[1056] ---

[1057] Step 1:

[1058] Users upload images of their own clothes, shoes, bags, etc., to the system from their smartphones or PCs. Users also enter a brief description for each image.

[1059] Step 2:

[1060] The device sends the uploaded image and description data to the server. Images are sent in JPEG or PNG format, and descriptions are sent as text data.

[1061] Step 3:

[1062] The server analyzes the received images and uses image analysis technology to extract features (color, shape, brand, etc.) of clothing, shoes, bags, etc. The extracted features and descriptions are stored in a database.

[1063] Step 4:

[1064] Users log in and request outfit coordination from the system for specific occasions or events. When making a request, they can also set options such as considering weather and temperature, as well as a budget limit.

[1065] Step 5:

[1066] The device sends user request data to the server. This data includes event information, weather selection, budget, etc.

[1067] Step 6:

[1068] The server uses a weather API to retrieve weather and temperature information for the requested day. It then retrieves and analyzes data from the weather API service.

[1069] Step 7:

[1070] When a user accesses the system, the emotion engine uses the camera and microphone to capture the user's facial expressions and voice. The captured data is sent to the server.

[1071] Step 8:

[1072] The server analyzes the received image and audio data to identify the user's emotions. The identified emotion information is stored in a database.

[1073] Step 9:

[1074] The server generates the optimal outfit based on the user's request, acquired weather and temperature information, item information in the database, and the user's emotional state. For example, on a sunny day with a temperature of 25 degrees Celsius, if the user has a happy expression, the server will suggest a "white shirt," "blue jeans," and "black sneakers."

[1075] Step 10:

[1076] The server calls an API from an external shopping site to search for the latest items that match the suggested outfit. This retrieves related products as trend information.

[1077] Step 11:

[1078] The server generates coordinated outfits and combines them with trending products found on external shopping sites to create a single suggested package.

[1079] Step 12:

[1080] The terminal sends the suggested package to the user's terminal and displays it on the screen. It is presented in a format that is easy for the user to understand.

[1081] Step 13:

[1082] Users review suggested outfits and trendy items, and if necessary, click purchase links to proceed with the purchase process on external e-commerce sites.

[1083] ---

[1084] By dividing the processing steps in this way, the system can efficiently suggest fashion coordinates to the user and, by reflecting the user's emotional information, can achieve more personalized suggestions.

[1085] (Example 2)

[1086] Next, we will describe Example 2. 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."

[1087] Traditional fashion coordination systems offer features for registering and managing user-owned items, but they lack personalized coordination suggestions that incorporate user emotional information. This means that suggested outfits may not match the user's mood or preferences. Furthermore, the lack of consideration for weather and temperature information results in impractical outfit suggestions. Additionally, the function for searching for trending items suffers from insufficient integration with external e-commerce sites, preventing timely information provision.

[1088] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1089] In this invention, the server includes means for uploading images of clothing, footwear, bags, etc., owned by the user; means for analyzing the uploaded images and saving their respective characteristics to a database; means for analyzing the user's facial expressions and voice data to obtain emotional information; means for personalizing outfits based on the obtained emotional information; means for obtaining weather and temperature information based on a request; means for generating an optimal outfit based on the obtained weather and temperature information and information in the database; means for searching for trending products from external e-commerce sites based on the generated outfit; and means for displaying the optimal outfit and trending products on the user's terminal. This makes it possible to provide more personalized and practical outfit suggestions that take into account the user's emotions and weather information.

[1090] "A means for users to upload images of clothing, footwear, bags, etc. they own" refers to a function that allows users to send images of their fashion items to the system using their smartphones or PCs.

[1091] "A means of analyzing uploaded images and saving their features to a database" refers to a function that extracts features such as color, shape, and brand based on received images and stores that information in a database.

[1092] "Means for analyzing user facial expressions and voice data to obtain emotional information" refers to a function that analyzes the user's facial expressions and voice to identify and obtain their emotions at that time (e.g., happy, sad, surprised, etc.).

[1093] "A means of personalizing outfits based on acquired emotional information" refers to a function that utilizes the user's emotional information to suggest the optimal fashion outfit that matches their mood at that time.

[1094] "Means for obtaining weather and temperature information based on requests" refers to a function for obtaining weather and temperature information for a specified date, time, and location based on coordination requests from users.

[1095] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to a function that utilizes weather information, temperature information, and user fashion item information stored in the database to create the optimal outfit suitable for the date, time, and location.

[1096] "A means of searching for trending products from external e-commerce sites based on generated outfits" refers to a function that searches for the latest related fashion items from external e-commerce sites based on generated fashion outfits.

[1097] "A means of displaying optimal outfits and trending products on the user's device" refers to a function that displays generated outfits and related trending product information on the user's smartphone, PC, or other device.

[1098] Modes for carrying out the invention

[1099] The system for implementing this invention uploads images of fashion items such as clothing, footwear, and bags owned by the user, analyzes the images to extract features, and stores them in a database. Furthermore, when a user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on this information and the user's emotional state. This generated outfit is displayed on the user's terminal along with trending items found on external e-commerce sites.

[1100] Hardware and software

[1101] Hardware:

[1102] This system uses devices such as smartphones, personal computers, and servers.

[1103] software:

[1104] Image analysis uses common image recognition APIs (e.g., Google Vision API). Sentiment analysis uses a common sentiment engine (e.g., Microsoft Azure Face API). Weather information is obtained using weather API services (e.g., OpenWeatherMap API). Database management uses a relational database management system (RDBMS).

[1105] Program processing

[1106] When a user uploads an image, the server receives it and extracts features from the image using an image recognition API. The extracted features, along with labels, are stored in a database. When a user accesses the system, the camera and microphone are used to capture the user's facial expressions and voice, and an emotion engine is used to analyze the emotional information. When a user requests a specific outfit, the server calls a non-essential data API to obtain weather and temperature information for the specified day and location. Based on the obtained weather and temperature information, the user's item information, and emotional information, the server generates the optimal outfit. Furthermore, based on the generated outfit, it searches for relevant trending products from external e-commerce sites. The optimal outfit and trending products are then displayed on the user's device.

[1107] Specific example

[1108] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, the user requests an outfit for a casual weekend lunch, turns on the setting to consider the weather, and sets a budget of 10,000 yen. The server retrieves from the weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from the database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[1109] Example of a prompt

[1110] Upload an image of yourself wearing a white shirt and black sneakers, and request an outfit suggestion for a casual lunch. Turn on weather consideration and set a budget limit of 10,000 yen.

[1111] In this way, this system efficiently suggests fashion coordinates to users and provides related trendy products, thereby improving the user's fashion experience. Furthermore, by reflecting the user's emotional information, it is possible to achieve even more personalized coordinate suggestions.

[1112] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1113] Step 1:

[1114] The user uploads an image.

[1115] Input: Images of clothing, footwear, bags, etc., taken by the user, and their corresponding descriptive labels (e.g., "white shirt").

[1116] Specific steps: The user opens the application on their smartphone or PC, clicks the upload button, selects an image of a "white shirt," and enters label information.

[1117] Output: Image data and its label information sent to the server.

[1118] Step 2:

[1119] The server receives the image.

[1120] Input: Image data and label information submitted by the user.

[1121] Specific operation: The server receives the upload request and retrieves the image data and label information.

[1122] Output: Received image data and label information.

[1123] Step 3:

[1124] The server performs image analysis and extracts features.

[1125] Input: Image data received by the server.

[1126] Specific operation: The server uses image analysis technologies such as the Google Vision API to extract features such as color, shape, and brand from an image. For example, it might detect "Color: White" and "Item: Shirt".

[1127] Output: Extracted feature information.

[1128] Step 4:

[1129] The server saves the features to the database.

[1130] Input: Extracted feature information and label information.

[1131] Specific operation: The server saves the extracted feature information (color: white, item: shirt) and label information (white shirt) to a relational database.

[1132] Output: Feature information and label information stored in the database.

[1133] Step 5:

[1134] Obtain user sentiment information.

[1135] Input: User's facial image and voice data acquired from a camera and microphone connected to the application.

[1136] Specific operation: When a user accesses the application, the system activates the camera to capture the user's facial expression and uses an emotion engine (such as the Microsoft Azure Face API) to analyze emotions such as "smile."

[1137] Output: Acquired emotion information (e.g., "happy").

[1138] Step 6:

[1139] The user requests an outfit coordination.

[1140] Input: User-entered outfit request information (e.g., casual lunch, weather consideration setting on, budget limit of 10,000 yen).

[1141] Specific action: The user selects "Casual Lunch" in the application, turns on the weather consideration setting, sets a budget limit of 10,000 yen, and submits the request.

[1142] Output: Coordination request information.

[1143] Step 7:

[1144] The server retrieves weather and temperature information.

[1145] Input: User's coordination request information and request date, time, and location information.

[1146] Specific operation: The server calls the OpenWeatherMap API to retrieve weather and temperature information (e.g., sunny, temperature 25 degrees) for a specified date, time, and location.

[1147] Output: Acquired weather and temperature information.

[1148] Step 8:

[1149] The server generates the optimal coordination.

[1150] Input: Acquired weather and temperature information, user item information in the database, and acquired sentiment information.

[1151] Specific operation: The server generates the optimal outfit (white shirt, blue jeans) based on weather and temperature information (sunny, 25 degrees), item information stored in the database (white shirt, black sneakers), and user emotion information (happy).

[1152] Output: Generated coordination information.

[1153] Step 9:

[1154] The server searches for trending products.

[1155] Input: Generated outfit information.

[1156] Specific operation: The server uses APIs from external e-commerce sites such as Amazon and Rakuten to search for trending products (e.g., blue cap, casual sneakers) based on the generated outfit.

[1157] Output: Searched trending product information.

[1158] Step 10:

[1159] The server displays the suggested content on the user's terminal.

[1160] Input: Generated outfit information and searched trend product information.

[1161] Specific operation: The server sends the generated outfit and the searched trending items (blue cap, casual sneakers) to the user's device and displays them on the application screen.

[1162] Output: The suggested content displayed on the user's terminal.

[1163] (Application Example 2)

[1164] Next, we will explain application example 2. In the following explanation, 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."

[1165] Conventional fashion coordination suggestion systems generated outfits using image analysis of items owned by the user and weather information, but they lacked individuality and immediacy because they did not take into account the user's emotions or real-time display of outfits. As a result, it was difficult for users to obtain appropriate outfits that suited their emotions and specific situations. Furthermore, they did not support intuitive interaction using new devices such as smart glasses. The objective of this invention is to solve these problems.

[1166] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1167] In this invention, the server includes means for uploading images of clothes, shoes, bags, etc., owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; means for receiving requests from the user for outfits suitable for a specific occasion; means for acquiring weather and temperature information based on the requests; means for generating the optimal outfit based on the acquired weather and temperature information and information in the database; means for searching for trendy products from external shopping sites based on the generated outfit; means for displaying the optimal outfit and trendy products on the user's terminal; means for acquiring the user's emotional information and adjusting the outfit based on it; and means for using smart glasses as the user's terminal. This makes it possible to suggest personalized outfits that respond to the user's emotions and real-time situation.

[1168] "Means for uploading images of clothing, shoes, bags, etc. owned by users" refers to software and hardware that allows users to send images of their fashion items to a server via the internet.

[1169] "A means of analyzing uploaded images and saving their characteristics to a database" refers to software that uses image analysis technology to extract the characteristics of uploaded fashion items and stores that information in a database within the system.

[1170] "A means for users to request outfits suitable for specific occasions" refers to an interface and function that allows users to request fashion suggestions appropriate for events or situations.

[1171] "Means for obtaining weather and temperature information based on requests" refers to communication and software for obtaining weather and temperature data for a requested date, time, and location from an external weather information service.

[1172] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to an algorithm and software that automatically creates appropriate fashion outfits by combining weather, temperature, and the characteristics of the user's owned items.

[1173] "A means of searching for trendy items from external shopping sites based on a generated outfit" refers to a communication function and software for searching for the latest fashion items related to an automatically generated outfit from an external e-commerce site.

[1174] "Means for displaying optimal outfits and trendy products on the user's device" refers to an interface and software for displaying generated outfits and related trendy product information on the user's smart device.

[1175] "Means for acquiring user emotional information and adjusting outfits based on it" refers to technology that analyzes the user's facial expressions and voice to identify emotions and adjust fashion outfits accordingly.

[1176] "Means of using smart glasses as a user terminal" refers to the technology and software for displaying outfit suggestions and information on trending products via smart glasses worn by the user.

[1177] This invention is a system that allows users to upload images of fashion items such as clothes, shoes, and bags they own, analyzes these images to extract features, and stores that information in a database. Furthermore, when providing outfit suggestions based on user requests, it also includes a function to search for trending items from external e-commerce sites, taking into account weather and temperature information as well as the user's emotional state. The following describes a specific embodiment of this invention.

[1178] 1. Uploading images owned by the user

[1179] Users upload images of their own fashion items, such as clothes, shoes, and bags, to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[1180] 2. Image Analysis and Feature Extraction

[1181] The server receives the uploaded image and description data, performs image analysis using machine learning algorithms, and extracts item features (color, shape, brand, etc.). The extracted features and descriptions are stored in a database.

[1182] 3. Obtaining user sentiment information

[1183] When a user accesses the system, the smart glasses' built-in camera and microphone capture the user's facial expressions and voice, and EmotionRecognizer identifies the user's emotions. The identified emotion information is used to generate coordinates.

[1184] 4. Coordination Request

[1185] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they can submit a request to the system via voice commands or gesture interface on their smart glasses. When making a request, they can also set settings that consider weather and temperature, as well as a budget limit.

[1186] 5. Obtaining weather and temperature information

[1187] The server uses the WeatherAPI service to retrieve weather and temperature information for a specified day. This retrieved weather and temperature information is then combined with the user's fashion item information stored in the database to generate outfit ideas.

[1188] 6. Coordination Generation

[1189] The server generates the optimal outfit based on weather and temperature information, the user's fashion item information in the database, and emotional information. The generated outfit is adjusted according to the user's requests and mood. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans," and if the user has a cheerful expression, it recommends an outfit with bright colors.

[1190] 7. Searching for trending products

[1191] Based on the generated outfit, the server searches for trending products from external e-commerce sites and suggests related fashion items to the user.

[1192] 8. Display of proposed content

[1193] The server sends the generated outfits and searched trending items to the user's smart glasses for real-time display. This allows the user to intuitively check the outfits and purchase trending items as needed.

[1194] Specific example

[1195] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from the WeatherAPI that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server then suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches for and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, this information is displayed on the user's smart glasses, allowing the user to review the suggestions and purchase items they like.

[1196] Example of a prompt

[1197] User: I live in Tokyo today and it's sunny with a temperature of 25 degrees Celsius. I'm planning to go out for a casual lunch. I'm in a very good mood. What kind of outfit would be appropriate?

[1198] This invention allows users to receive personalized outfit suggestions through smart glasses that are tailored to their emotions and real-time circumstances.

[1199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1200] Step 1:

[1201] Users upload images of fashion items they own.

[1202] Input: Images of clothing, shoes, bags, etc., uploaded from the user's smartphone or PC, along with a brief description.

[1203] Processing: The terminal sends the specified image file to the server.

[1204] Output: Image files and descriptive data sent to the server.

[1205] Step 2:

[1206] The uploaded image is analyzed, and its features are saved to a database.

[1207] Input: Image and description data of fashion items received by the server.

[1208] Processing: The server uses image analysis techniques (including machine learning algorithms) to extract features such as color, shape, and brand from the image.

[1209] Output: The extracted feature and descriptive data are stored in the database.

[1210] Step 3:

[1211] Obtain user sentiment information.

[1212] Input: User's facial image and voice data captured through the smart glasses' built-in camera and microphone.

[1213] Processing: The server uses EmotionRecognizer to analyze facial images and audio data to identify the user's emotions.

[1214] Output: Identified sentiment information.

[1215] Step 4:

[1216] Users can request outfits suitable for specific occasions.

[1217] Input: Event information entered by the user via voice commands or gesture interface on smart glasses, settings that take weather into consideration, and budget limits.

[1218] Processing: The terminal sends the user's request information to the server.

[1219] Output: Request information sent to the server.

[1220] Step 5:

[1221] Obtain weather and temperature information.

[1222] Input: The request that the server sends to the WeatherAPI service (date, time, and location of the request).

[1223] Processing: The WeatherAPI service returns weather and temperature information for the specified day to the server.

[1224] Output: Acquired weather and temperature information.

[1225] Step 6:

[1226] Based on acquired weather and temperature information, as well as emotional information, the system generates the optimal outfit.

[1227] Input: Weather and temperature information, sentiment information, and user fashion item information.

[1228] Processing: The server combines this information and uses an algorithm to generate the optimal coordination.

[1229] Output: The generated outfit.

[1230] Step 7:

[1231] Based on the generated outfit, search for trending items from external shopping sites.

[1232] Input: Generated outfit information.

[1233] Processing: The server sends a request to the e-commerce site to search for information on relevant trending products.

[1234] Output: A list of searched trending products.

[1235] Step 8:

[1236] The system displays optimal outfits and trending products on the user's device (smart glasses).

[1237] Input: A list of generated outfits and trending items.

[1238] Processing: The server sends this information to the smart glasses and presents it to the user through the display interface.

[1239] Output: Coordination and trending product information displayed on smart glasses.

[1240] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1241] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1242] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1243] [Fourth Embodiment]

[1244] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1245] As shown in Figure 7, the 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.

[1246] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1247] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1248] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1249] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1250] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1251] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1252] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1253] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1254] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1255] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1256] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1257] ---

[1258] The system for implementing this invention involves the user uploading images of their clothes, shoes, bags, etc., and analyzing those images to store their features in a database. Furthermore, when the user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on that information. This generated outfit is displayed on the user's terminal along with trending items found on external shopping sites.

[1259] 1. Uploading images owned by the user

[1260] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[1261] 2. Image Analysis and Feature Extraction

[1262] The server receives the uploaded image and description data, and uses image analysis technology to extract item features (color, shape, brand, etc.) from the image. The extracted features and description are stored in a database.

[1263] 3. Coordination Request

[1264] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[1265] 4. Obtaining weather and temperature information

[1266] The server uses a weather API service to retrieve weather and temperature information for the specified day. The retrieved information is then reflected in the outfit the user desires.

[1267] 5. Coordination generation

[1268] The server generates the optimal outfit based on weather and temperature information, as well as the user's fashion item information in the database. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans."

[1269] 6. Searching for trending products

[1270] Based on the generated outfit, the server searches for trending items from external shopping sites. This allows users to find the latest fashion items that match their existing wardrobe.

[1271] 7. Display of proposed content

[1272] The server sends the generated outfit and searched trending items to the user's terminal and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[1273] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." It then suggests an optimal outfit consisting of a "white shirt," "black sneakers," and "blue jeans," and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[1274] ---

[1275] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products.

[1276] The following describes the processing flow.

[1277] ---

[1278] Step 1:

[1279] Users upload images of their own clothes, shoes, bags, etc., to the system from their smartphones or PCs. Users also enter a brief description for each image (e.g., "white shirt," "leather boots").

[1280] Step 2:

[1281] The device sends the uploaded image and description data to the server. Images are sent in JPEG or PNG format, and descriptions are sent as text data.

[1282] Step 3:

[1283] The server analyzes the received images and uses image recognition technology to extract features (color, shape, brand, etc.) of clothing, shoes, bags, etc. It also analyzes the descriptive text and stores it together in the database.

[1284] Step 4:

[1285] Users log in and request outfit coordination from the system for a specific occasion or event. They also enter whether weather and temperature should be considered, and specify a budget limit.

[1286] Step 5:

[1287] The device sends user request data to the server. This data includes event information, weather selection, budget, etc.

[1288] Step 6:

[1289] The server uses a weather API to retrieve weather and temperature information for the requested day. It then retrieves and analyzes data from the weather API service.

[1290] Step 7:

[1291] The server searches and extracts matching items from the database based on the user's request and the weather and temperature information it has obtained. For example, if it is sunny and the temperature is 25 degrees Celsius, it will select suitable clothing, shoes, and bags.

[1292] Step 8:

[1293] Based on the items the server searches and extracts, it generates the most suitable outfit for the user's request. For example, it might suggest a "white shirt," "blue jeans," and "black sneakers" that would be suitable for a casual lunch.

[1294] Step 9:

[1295] The server calls the Yahoo Shopping API to search for the latest items that match the suggested outfit. This retrieves related products as trending information.

[1296] Step 10:

[1297] The server generates coordinated outfits and combines them with trending products found through Yahoo Shopping searches to create a single suggested package.

[1298] Step 11:

[1299] The terminal sends the suggested package to the user's terminal and displays it on the screen. It is displayed in a format that is easy for the user to understand.

[1300] Step 12:

[1301] Users review suggested outfits and trendy items, and if they find items they need, they click the purchase link to proceed with the purchase on e-commerce sites such as Yahoo Shopping.

[1302] ---

[1303] (Example 1)

[1304] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1305] Traditional fashion coordination systems struggled to efficiently match users' existing items with new, trendy products. Furthermore, they had difficulty considering external factors such as weather and temperature when suggesting outfits, making it challenging to provide optimal coordination tailored to users' specific needs. This often led to users feeling dissatisfied with their daily clothing choices and new item purchases.

[1306] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1307] In this invention, the server includes means for uploading images of clothing, footwear, bags, etc., owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; and means for receiving requests from the user for outfits suitable for specific occasions. This allows the system to incorporate detailed information about the items owned by the user and provide optimal outfits tailored to each individual user.

[1308] ---

[1309] ---

[1310] A "user" refers to someone who uses this system to manage their fashion items and receive styling suggestions.

[1311] "Clothing" refers to the clothes that users wear on a daily basis.

[1312] "Footwear" refers to shoes, sandals, and other items worn on the user's feet.

[1313] "Bag" refers to bags used by users to carry things.

[1314] "Images" refer to digital data containing visual information such as clothing, footwear, and bags uploaded by users.

[1315] "Analysis" refers to the process by which a server extracts features and information from uploaded images.

[1316] "Features" refer to attribute information such as the color, shape, and brand of an item obtained through analysis.

[1317] A "database" refers to an information management system used to store analyzed features and descriptions.

[1318] A "request" refers to an inquiry that a user sends to the system to request an outfit suitable for a specific occasion.

[1319] "Weather" refers to environmental information such as weather and temperature.

[1320] "Temperature" refers to the temperature reflected in the resulting outfit.

[1321] "Generation" refers to the process by which the server creates coordination suggestions based on the necessary information.

[1322] An "e-commerce site" refers to an online platform that includes external shopping sites.

[1323] "Terminal" refers to devices such as smartphones and personal computers that users use to operate the system.

[1324] "Display" refers to the act of visually showing information on a device screen.

[1325] A "machine learning algorithm" refers to a computer model that a server uses for image analysis.

[1326] A "product sales site" includes online shops where users can purchase items necessary for coordinating outfits.

[1327] ---

[1328] The above are the definitions of the important words.

[1329] ---

[1330] The system for implementing this invention begins with the user uploading images of their clothing, footwear, bags, etc., to the system using a smartphone or PC. The user enters a brief description for each image (e.g., "white shirt," "leather boots"), and this information is sent to the server.

[1331] The server receives the uploaded image and description data. Next, it uses image analysis technologies such as the Google Cloud Vision API to extract item features (color, shape, brand, etc.) from the image. The extracted features and descriptions are stored in a database. At this stage, machine learning algorithms are used for analysis, improving accuracy.

[1332] Users can submit requests to the system for outfits suitable for specific occasions or events (e.g., casual lunch, business meeting). When submitting a request, they can select options to consider weather and temperature, and set a budget limit.

[1333] The server uses weather API services such as the OpenWeatherMap API to obtain weather and temperature information for a specified day. The obtained information is then reflected in the outfit chosen by the user.

[1334] Next, the server generates the optimal outfit based on weather and temperature information and the user's fashion item information in the database. For example, if it's sunny and the temperature is 25 degrees Celsius, it might suggest a "white shirt" and "blue jeans."

[1335] Based on the generated outfit, the server searches for trending items from external e-commerce sites. Specifically, it uses online shopping sites such as Amazon and Rakuten to suggest the latest fashion items that match the user's belongings.

[1336] Finally, the server sends the generated outfit and searched trending items to the user's device and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[1337] Specific example

[1338] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers," and adds descriptions to them as "white shirt" and "leather boots," respectively. Next, the user requests an outfit for a casual weekend lunch, turns on the setting to consider the weather, and sets a budget of 10,000 yen. The server retrieves from the OpenWeatherMap API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items containing "white shirt" and "black sneakers" from its database. It then suggests the optimal outfit as "white shirt," "black sneakers," and "blue jeans," and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. This information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[1339] Examples of prompts for generative AI models

[1340] The following is an example of a prompt:

[1341] A user uploaded images of their "white shirt" and "black sneakers" to the system. The system labeled these images "white shirt" and "leather boots." Next, the user requested an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server determined the weekend weather would be sunny with a temperature of 25 degrees Celsius and extracted items from its database that included a "white shirt" and "black sneakers." The server then suggested a suitable outfit: "white shirt," "black sneakers," and "blue jeans." Furthermore, it searched for and suggested related items such as casual sneakers and accessories from external shopping sites. All information was displayed on the user's device, allowing the user to review the suggestions and purchase items they liked.

[1342] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1343] ---

[1344] Step 1: The user uploads an image.

[1345] Users upload images of clothing, footwear, bags, etc., to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[1346] Input: Image file and descriptive text

[1347] Output: Image file and descriptive text are sent to the server.

[1348] Specific actions: The user taps the "Upload" button, selects an image of a "white shirt," enters the description "white shirt," and presses the "Submit" button.

[1349] Step 2: The server receives the image and description.

[1350] The server receives the image file and descriptive text sent by the user.

[1351] Input: Image file and descriptive text

[1352] Output: Received image file and description text

[1353] Specific operation: The server retrieves data sent by the user and prepares for subsequent processing.

[1354] Step 3: Image analysis and feature extraction

[1355] The server uses image analysis technologies such as the Google Cloud Vision API to extract item features (color, shape, brand, etc.) from the image.

[1356] Input: Image file

[1357] Output: Extracted feature data (color, shape, brand, etc.)

[1358] Specific operation: The server sends the image file to the Google Cloud Vision API and analyzes the returned analysis results.

[1359] Step 4: Saving Feature Data

[1360] The server stores the extracted features and descriptive text in a database.

[1361] Input: Feature data, descriptive text

[1362] Output: Saved to database successfully

[1363] Specific operation: The server stores the feature data and descriptive text in the database in the appropriate format.

[1364] Step 5: The user requests an outfit.

[1365] Users request outfits suitable for specific occasions or events from the system. This includes specifying settings that take weather and temperature into consideration, as well as a budget limit.

[1366] Input: Event type, weather consideration options, budget limit

[1367] Output: Request data is sent to the server.

[1368] Specific actions: The user presses the "Coordination Request" button in the app, selects "Casual Lunch," turns "Weather Consideration On," and sets a budget of 10,000 yen.

[1369] Step 6: Obtain weather and temperature information

[1370] The server uses weather API services such as the OpenWeatherMap API to obtain weather and temperature information for a specified day.

[1371] Input: Request data, specified date

[1372] Output: Weather and temperature information

[1373] Specific operation: The server sends a request to the OpenWeatherMap API to retrieve information that the weather for the weekend will be sunny with a temperature of 25 degrees Celsius.

[1374] Step 7: Creating the outfit

[1375] The server generates the optimal outfit based on weather and temperature information, as well as the user's fashion item information in the database.

[1376] Input: Weather and temperature information, item information in the database.

[1377] Output: Generated coordinate data

[1378] Specific operation: The server extracts "white shirt," "black sneakers," and "blue jeans" from the database and combines them to create the optimal outfit.

[1379] Step 8: Search for trending products

[1380] Based on the generated coordinates, the server searches for trending products from external e-commerce sites.

[1381] Input: Generated coordinate data

[1382] Output: List of trending products

[1383] Specific operation: The server sends a request to the Amazon API with keywords such as "casual sneakers" and retrieves a list of related products.

[1384] Step 9: Display the proposed content

[1385] The server sends the generated outfits and searched trending items to the user's device and displays them on the screen.

[1386] Input: Generated outfit data, list of trending items

[1387] Output: Coordination suggestions displayed on the user's device

[1388] Specific operation: The app receives a notification on the user's device and displays "recommended outfits" including a "white shirt," "black sneakers," and "blue jeans." At the bottom, it displays "recommended casual sneakers" from Amazon with a link.

[1389] ---

[1390] The above is a description of the specific processing steps of this system's program.

[1391] (Application Example 1)

[1392] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1393] In recent years, consumer demand for fashion item coordination has increased, and there is a growing need for efficient and accurate suggestions. However, conventional systems struggle to suggest optimal outfits that combine the user's existing items with the latest fashion trends, and they lack suggestions that reflect specific situations or weather conditions. Furthermore, there are insufficient means to recommend trendy items that match individual user preferences, resulting in a lack of effective methods to increase purchasing intent.

[1394] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1395] In this invention, the server includes means for uploading images of clothes, shoes, bags, etc. owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; means for receiving requests from the user for outfits suitable for a specific occasion; means for obtaining weather and temperature information based on the request; means for generating the optimal outfit based on the obtained weather and temperature information and information in the database; means for searching for trending products from external e-commerce sites based on the generated outfit; means for displaying the optimal outfit and trending products on the user's terminal; and means for inputting the generated outfit and trending product information in prompt format into a generation AI model to display more refined outfits and recommended products. This makes it possible to provide the optimal outfit suitable for a specific occasion and weather using items owned by the user, and to make suggestions that also include trending products.

[1396] "A means for users to upload images of their own clothes, shoes, bags, etc." refers to a function that allows users to send image data of their own fashion items (clothes, shoes, or bags, etc.) to the system via the user interface.

[1397] "A means of analyzing uploaded images and saving their characteristics to a database" refers to a function that uses image analysis technology to extract characteristics such as color, shape, and material from images of fashion items uploaded by users, and saves them to a database.

[1398] "A means for users to request outfits suitable for specific situations" refers to a function that allows users to request the system to suggest fashion outfits suitable for specific situations or events they wish to attend.

[1399] "Means for obtaining weather and temperature information based on requests" refers to a function that obtains weather and temperature data for a specific day or region from external weather information services, according to the user's request.

[1400] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to a function that automatically generates clothing suggestions suitable for a specific situation by combining acquired weather and temperature data with the user's fashion item information stored in the database.

[1401] "A means of searching for trending products from external e-commerce sites based on generated outfits" refers to a function that searches for the latest trending fashion items from external e-commerce sites based on generated fashion outfits.

[1402] "A means of displaying optimal outfits and trendy products on the user's device" refers to a function that displays the generated optimal outfits and related trendy products on the screen of the user's device, such as a smartphone or personal computer.

[1403] "A means of inputting generated coordinate and trend product information into a generation AI model in prompt format to display more refined coordinates and recommended products" refers to a function that inputs generated fashion coordinate and trend product information into a generation AI model in text format, and then derives and displays more refined coordinates and recommended products based on that input.

[1404] The system for implementing this invention involves uploading images of clothing, shoes, bags, etc., owned by the user, and analyzing those images to store their features in a database. Furthermore, when the user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit. Based on this outfit, the system has the function of searching for trending products from external e-commerce sites and displaying them on the user's terminal.

[1405] 1. Uploading images owned by the user

[1406] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[1407] 2. Image Analysis and Feature Extraction

[1408] The server receives the image and its description data uploaded by the user. Next, it uses a machine learning algorithm to analyze the image and extract item features (color, shape, brand, etc.). These extracted features and descriptions are stored in a database.

[1409] 3. Coordination Request

[1410] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[1411] 4. Obtaining weather and temperature information

[1412] The server uses a weather API service (e.g., WeatherAPI) to retrieve weather and temperature information for a specified day. The retrieved information is then used to generate the outfit requested by the user.

[1413] 5. Coordination generation

[1414] The server generates the optimal outfit based on the acquired weather and temperature information and the user's fashion item information in the database. For example, on a sunny day with a temperature of 25 degrees Celsius, it will suggest cool items such as a "white shirt" and "blue jeans."

[1415] 6. Searching for trending products

[1416] Based on the generated outfit, the server searches for trending items from external e-commerce sites. This allows users to find the latest fashion items that match their existing wardrobe.

[1417] 7. Display of proposed content and use of the generated AI model

[1418] The server sends the generated outfits and searched trending products to the user's device and displays them on the screen. It also inputs this information into a generation AI model in the form of prompts, which then generates and displays more refined outfits and recommended products.

[1419] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" they own, and labels each item. Next, they request an outfit for a casual weekend lunch, enabling weather consideration and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items containing "white shirt" and "black sneakers" from its database. It then suggests an optimal outfit consisting of "white shirt," "black sneakers," and "blue jeans," and further searches and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, the following prompt is entered into the generative AI model to display a refined suggestion:

[1420] "Could you recommend some outfits and the latest trendy items for a casual weekend lunch?"

[1421] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products.

[1422] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1423] Step 1:

[1424] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. The input consists of image data of the fashion item taken by the user and a brief description (e.g., "white shirt," "leather boots"). The output is the user's uploaded image and its corresponding description data.

[1425] Step 2:

[1426] The server receives images and descriptive data uploaded by users. Next, it uses machine learning algorithms to analyze the images and extract features such as color, shape, and brand. The input is the image data and descriptive data uploaded by the user, and the output is the feature data extracted through image analysis. The server stores this feature and descriptive data in a database.

[1427] Step 3:

[1428] Users can use their smartphones or PCs to request outfits suitable for specific occasions or events (e.g., casual lunch, business meeting). Input includes information about the occasion or event selected by the user, as well as options to consider weather and temperature, and a budget limit. Output is the request data sent to the server.

[1429] Step 4:

[1430] The server uses a weather API service to retrieve weather and temperature information for a specified date. The input is date and region information based on the user's request data. The output is the retrieved weather and temperature data. The server uses this data to generate coordinated outfits.

[1431] Step 5:

[1432] The server generates the optimal outfit based on acquired weather and temperature information and the user's fashion item information in the database. Specifically, it selects items suitable for the weather and temperature and suggests combinations appropriate for specific occasions or events. The inputs are weather and temperature data and fashion item information from the database. The output is the generated optimal outfit suggestion.

[1433] Step 6:

[1434] The server searches for trending products from external e-commerce sites based on the generated outfit. The input is the generated outfit proposal, and the output is information on the related trending products.

[1435] Step 7:

[1436] The server inputs the generated outfits and trending items into the AI ​​model in the form of prompt sentences. The AI ​​model then uses this information to generate more refined outfits and recommended items. The input is the information generated in the form of prompt sentences, and the output is the information on the final outfits and recommended items.

[1437] Step 8:

[1438] The server sends the final coordinated outfit and recommended items to the user's device and displays them on the screen. The input is the coordinated outfit and recommended items information generated by the generative AI model, and the output is the data displayed on the user's device. The user can review this and make purchases as needed.

[1439] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1440] ---

[1441] The system for implementing this invention involves the user uploading images of their clothes, shoes, bags, etc., and analyzing those images to store their features in a database. Furthermore, when a user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on that information and the user's emotional state. This generated outfit is displayed on the user's device along with trending items found on external shopping sites.

[1442] 1. Uploading images owned by the user

[1443] Users upload images of their own clothing, shoes, bags, and other fashion items to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[1444] 2. Image Analysis and Feature Extraction

[1445] The server receives the uploaded image and description data, and uses image analysis technology to extract item features (color, shape, brand, etc.) from the image. The extracted features and description are stored in a database.

[1446] 3. Obtaining user sentiment information

[1447] The system incorporates an emotion engine that analyzes the user's image and voice data. When a user accesses the system, it uses a camera and microphone to capture the user's facial expressions and voice, and analyzes this data to identify the user's emotions.

[1448] 4. Coordination Request

[1449] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they enter a request into the system. Options such as considering weather and temperature, as well as setting a budget limit, can be included in the request.

[1450] 5. Obtaining weather and temperature information

[1451] The server uses a weather API service to retrieve weather and temperature information for the specified day. The retrieved information is then reflected in the outfit the user desires.

[1452] 6. Coordination Generation

[1453] The server generates the optimal outfit based on weather and temperature information, the user's fashion item information in the database, and emotional information. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans," and if the user has a cheerful expression, it recommends an outfit with bright colors.

[1454] 7. Searching for trending products

[1455] Based on the generated outfit, the server searches for trending items from external shopping sites. This allows users to find the latest fashion items that match their existing wardrobe.

[1456] 8. Display of proposed content

[1457] The server sends the generated outfit and searched trending items to the user's terminal and displays them on the screen. The user can review the suggested outfit and purchase trending items as needed.

[1458] As a concrete example, consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from a weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server then suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches for and suggests related items such as casual sneakers and accessories from external shopping sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[1459] ---

[1460] In this way, this system improves the user's fashion experience by efficiently suggesting fashion coordinates and providing related trendy products. Furthermore, by reflecting the user's emotional information, it enables even more personalized coordinate suggestions.

[1461] The following describes the processing flow.

[1462] ---

[1463] Step 1:

[1464] Users upload images of their own clothes, shoes, bags, etc., to the system from their smartphones or PCs. Users also enter a brief description for each image.

[1465] Step 2:

[1466] The device sends the uploaded image and description data to the server. Images are sent in JPEG or PNG format, and descriptions are sent as text data.

[1467] Step 3:

[1468] The server analyzes the received images and uses image analysis technology to extract features (color, shape, brand, etc.) of clothing, shoes, bags, etc. The extracted features and descriptions are stored in a database.

[1469] Step 4:

[1470] Users log in and request outfit coordination from the system for specific occasions or events. When making a request, they can also set options such as considering weather and temperature, as well as a budget limit.

[1471] Step 5:

[1472] The device sends user request data to the server. This data includes event information, weather selection, budget, etc.

[1473] Step 6:

[1474] The server uses a weather API to retrieve weather and temperature information for the requested day. It then retrieves and analyzes data from the weather API service.

[1475] Step 7:

[1476] When a user accesses the system, the emotion engine uses the camera and microphone to capture the user's facial expressions and voice. The captured data is sent to the server.

[1477] Step 8:

[1478] The server analyzes the received image and audio data to identify the user's emotions. The identified emotion information is stored in a database.

[1479] Step 9:

[1480] The server generates the optimal outfit based on the user's request, acquired weather and temperature information, item information in the database, and the user's emotional state. For example, on a sunny day with a temperature of 25 degrees Celsius, if the user has a happy expression, the server will suggest a "white shirt," "blue jeans," and "black sneakers."

[1481] Step 10:

[1482] The server calls an API from an external shopping site to search for the latest items that match the suggested outfit. This retrieves related products as trend information.

[1483] Step 11:

[1484] The server generates coordinated outfits and combines them with trending products found on external shopping sites to create a single suggested package.

[1485] Step 12:

[1486] The terminal sends the suggested package to the user's terminal and displays it on the screen. It is presented in a format that is easy for the user to understand.

[1487] Step 13:

[1488] Users review suggested outfits and trendy items, and if necessary, click purchase links to proceed with the purchase process on external e-commerce sites.

[1489] ---

[1490] By dividing the processing steps in this way, the system can efficiently suggest fashion coordinates to the user and, by reflecting the user's emotional information, can achieve more personalized suggestions.

[1491] (Example 2)

[1492] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1493] Traditional fashion coordination systems offer features for registering and managing user-owned items, but they lack personalized coordination suggestions that incorporate user emotional information. This means that suggested outfits may not match the user's mood or preferences. Furthermore, the lack of consideration for weather and temperature information results in impractical outfit suggestions. Additionally, the function for searching for trending items suffers from insufficient integration with external e-commerce sites, preventing timely information provision.

[1494] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1495] In this invention, the server includes means for uploading images of clothing, footwear, bags, etc., owned by the user; means for analyzing the uploaded images and saving their respective characteristics to a database; means for analyzing the user's facial expressions and voice data to obtain emotional information; means for personalizing outfits based on the obtained emotional information; means for obtaining weather and temperature information based on a request; means for generating an optimal outfit based on the obtained weather and temperature information and information in the database; means for searching for trending products from external e-commerce sites based on the generated outfit; and means for displaying the optimal outfit and trending products on the user's terminal. This makes it possible to provide more personalized and practical outfit suggestions that take into account the user's emotions and weather information.

[1496] "A means for users to upload images of clothing, footwear, bags, etc. they own" refers to a function that allows users to send images of their fashion items to the system using their smartphones or PCs.

[1497] "A means of analyzing uploaded images and saving their features to a database" refers to a function that extracts features such as color, shape, and brand based on received images and stores that information in a database.

[1498] "Means for analyzing user facial expressions and voice data to obtain emotional information" refers to a function that analyzes the user's facial expressions and voice to identify and obtain their emotions at that time (e.g., happy, sad, surprised, etc.).

[1499] "A means of personalizing outfits based on acquired emotional information" refers to a function that utilizes the user's emotional information to suggest the optimal fashion outfit that matches their mood at that time.

[1500] "Means for obtaining weather and temperature information based on requests" refers to a function for obtaining weather and temperature information for a specified date, time, and location based on coordination requests from users.

[1501] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to a function that utilizes weather information, temperature information, and user fashion item information stored in the database to create the optimal outfit suitable for the date, time, and location.

[1502] "A means of searching for trending products from external e-commerce sites based on generated outfits" refers to a function that searches for the latest related fashion items from external e-commerce sites based on generated fashion outfits.

[1503] "A means of displaying optimal outfits and trending products on the user's device" refers to a function that displays generated outfits and related trending product information on the user's smartphone, PC, or other device.

[1504] Modes for carrying out the invention

[1505] The system for implementing this invention uploads images of fashion items such as clothing, footwear, and bags owned by the user, analyzes the images to extract features, and stores them in a database. Furthermore, when a user requests an outfit suitable for a specific occasion, the system acquires weather and temperature information and generates an optimal outfit based on this information and the user's emotional state. This generated outfit is displayed on the user's terminal along with trending items found on external e-commerce sites.

[1506] Hardware and software

[1507] Hardware:

[1508] This system uses devices such as smartphones, personal computers, and servers.

[1509] software:

[1510] Image analysis uses common image recognition APIs (e.g., Google Vision API). Sentiment analysis uses a common sentiment engine (e.g., Microsoft Azure Face API). Weather information is obtained using weather API services (e.g., OpenWeatherMap API). Database management uses a relational database management system (RDBMS).

[1511] Program processing

[1512] When a user uploads an image, the server receives it and extracts features from the image using an image recognition API. The extracted features, along with labels, are stored in a database. When a user accesses the system, the camera and microphone are used to capture the user's facial expressions and voice, and an emotion engine is used to analyze the emotional information. When a user requests a specific outfit, the server calls a non-essential data API to obtain weather and temperature information for the specified day and location. Based on the obtained weather and temperature information, the user's item information, and emotional information, the server generates the optimal outfit. Furthermore, based on the generated outfit, it searches for relevant trending products from external e-commerce sites. The optimal outfit and trending products are then displayed on the user's device.

[1513] Specific example

[1514] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, the user requests an outfit for a casual weekend lunch, turns on the setting to consider the weather, and sets a budget of 10,000 yen. The server retrieves from the weather API that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from the database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, this information is displayed on the user's device, allowing the user to review the suggestions and purchase items they like.

[1515] Example of a prompt

[1516] Upload an image of yourself wearing a white shirt and black sneakers, and request an outfit suggestion for a casual lunch. Turn on weather consideration and set a budget limit of 10,000 yen.

[1517] In this way, this system efficiently suggests fashion coordinates to users and provides related trendy products, thereby improving the user's fashion experience. Furthermore, by reflecting the user's emotional information, it is possible to achieve even more personalized coordinate suggestions.

[1518] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1519] Step 1:

[1520] The user uploads an image.

[1521] Input: Images of clothing, footwear, bags, etc., taken by the user, and their corresponding descriptive labels (e.g., "white shirt").

[1522] Specific steps: The user opens the application on their smartphone or PC, clicks the upload button, selects an image of a "white shirt," and enters label information.

[1523] Output: Image data and its label information sent to the server.

[1524] Step 2:

[1525] The server receives the image.

[1526] Input: Image data and label information submitted by the user.

[1527] Specific operation: The server receives the upload request and retrieves the image data and label information.

[1528] Output: Received image data and label information.

[1529] Step 3:

[1530] The server performs image analysis and extracts features.

[1531] Input: Image data received by the server.

[1532] Specific operation: The server uses image analysis technologies such as the Google Vision API to extract features such as color, shape, and brand from an image. For example, it might detect "Color: White" and "Item: Shirt".

[1533] Output: Extracted feature information.

[1534] Step 4:

[1535] The server saves the features to the database.

[1536] Input: Extracted feature information and label information.

[1537] Specific operation: The server saves the extracted feature information (color: white, item: shirt) and label information (white shirt) to a relational database.

[1538] Output: Feature information and label information stored in the database.

[1539] Step 5:

[1540] Obtain user sentiment information.

[1541] Input: User's facial image and voice data acquired from a camera and microphone connected to the application.

[1542] Specific operation: When a user accesses the application, the system activates the camera to capture the user's facial expression and uses an emotion engine (such as the Microsoft Azure Face API) to analyze emotions such as "smile."

[1543] Output: Acquired emotion information (e.g., "happy").

[1544] Step 6:

[1545] The user requests an outfit coordination.

[1546] Input: User-entered outfit request information (e.g., casual lunch, weather consideration setting on, budget limit of 10,000 yen).

[1547] Specific action: The user selects "Casual Lunch" in the application, turns on the weather consideration setting, sets a budget limit of 10,000 yen, and submits the request.

[1548] Output: Coordination request information.

[1549] Step 7:

[1550] The server retrieves weather and temperature information.

[1551] Input: User's coordination request information and request date, time, and location information.

[1552] Specific operation: The server calls the OpenWeatherMap API to retrieve weather and temperature information (e.g., sunny, temperature 25 degrees) for a specified date, time, and location.

[1553] Output: Acquired weather and temperature information.

[1554] Step 8:

[1555] The server generates the optimal coordination.

[1556] Input: Acquired weather and temperature information, user item information in the database, and acquired sentiment information.

[1557] Specific operation: The server generates the optimal outfit (white shirt, blue jeans) based on weather and temperature information (sunny, 25 degrees), item information stored in the database (white shirt, black sneakers), and user emotion information (happy).

[1558] Output: Generated coordination information.

[1559] Step 9:

[1560] The server searches for trending products.

[1561] Input: Generated outfit information.

[1562] Specific operation: The server uses APIs from external e-commerce sites such as Amazon and Rakuten to search for trending products (e.g., blue cap, casual sneakers) based on the generated outfit.

[1563] Output: Searched trending product information.

[1564] Step 10:

[1565] The server displays the suggested content on the user's terminal.

[1566] Input: Generated outfit information and searched trend product information.

[1567] Specific operation: The server sends the generated outfit and the searched trending items (blue cap, casual sneakers) to the user's device and displays them on the application screen.

[1568] Output: The suggested content displayed on the user's terminal.

[1569] (Application Example 2)

[1570] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1571] Conventional fashion coordination suggestion systems generated outfits using image analysis of items owned by the user and weather information, but they lacked individuality and immediacy because they did not take into account the user's emotions or real-time display of outfits. As a result, it was difficult for users to obtain appropriate outfits that suited their emotions and specific situations. Furthermore, they did not support intuitive interaction using new devices such as smart glasses. The objective of this invention is to solve these problems.

[1572] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1573] In this invention, the server includes means for uploading images of clothes, shoes, bags, etc., owned by the user; means for analyzing the uploaded images and saving their characteristics in a database; means for receiving requests from the user for outfits suitable for a specific occasion; means for acquiring weather and temperature information based on the requests; means for generating the optimal outfit based on the acquired weather and temperature information and information in the database; means for searching for trendy products from external shopping sites based on the generated outfit; means for displaying the optimal outfit and trendy products on the user's terminal; means for acquiring the user's emotional information and adjusting the outfit based on it; and means for using smart glasses as the user's terminal. This makes it possible to suggest personalized outfits that respond to the user's emotions and real-time situation.

[1574] "Means for uploading images of clothing, shoes, bags, etc. owned by users" refers to software and hardware that allows users to send images of their fashion items to a server via the internet.

[1575] "A means of analyzing uploaded images and saving their characteristics to a database" refers to software that uses image analysis technology to extract the characteristics of uploaded fashion items and stores that information in a database within the system.

[1576] "A means for users to request outfits suitable for specific occasions" refers to an interface and function that allows users to request fashion suggestions appropriate for events or situations.

[1577] "Means for obtaining weather and temperature information based on requests" refers to communication and software for obtaining weather and temperature data for a requested date, time, and location from an external weather information service.

[1578] "A means of generating the optimal outfit based on acquired weather and temperature information and information in the database" refers to an algorithm and software that automatically creates appropriate fashion outfits by combining weather, temperature, and the characteristics of the user's owned items.

[1579] "A means of searching for trendy items from external shopping sites based on a generated outfit" refers to a communication function and software for searching for the latest fashion items related to an automatically generated outfit from an external e-commerce site.

[1580] "Means for displaying optimal outfits and trendy products on the user's device" refers to an interface and software for displaying generated outfits and related trendy product information on the user's smart device.

[1581] "Means for acquiring user emotional information and adjusting outfits based on it" refers to technology that analyzes the user's facial expressions and voice to identify emotions and adjust fashion outfits accordingly.

[1582] "Means of using smart glasses as a user terminal" refers to the technology and software for displaying outfit suggestions and information on trending products via smart glasses worn by the user.

[1583] This invention is a system that allows users to upload images of fashion items such as clothes, shoes, and bags they own, analyzes these images to extract features, and stores that information in a database. Furthermore, when providing outfit suggestions based on user requests, it also includes a function to search for trending items from external e-commerce sites, taking into account weather and temperature information as well as the user's emotional state. The following describes a specific embodiment of this invention.

[1584] 1. Uploading images owned by the user

[1585] Users upload images of their own fashion items, such as clothes, shoes, and bags, to the system using their smartphones or PCs. They also enter a brief description for each image (e.g., "white shirt," "leather boots").

[1586] 2. Image Analysis and Feature Extraction

[1587] The server receives the uploaded image and description data, performs image analysis using machine learning algorithms, and extracts item features (color, shape, brand, etc.). The extracted features and descriptions are stored in a database.

[1588] 3. Obtaining user sentiment information

[1589] When a user accesses the system, the smart glasses' built-in camera and microphone capture the user's facial expressions and voice, and EmotionRecognizer identifies the user's emotions. The identified emotion information is used to generate coordinates.

[1590] 4. Coordination Request

[1591] When a user wants an outfit suitable for a specific occasion or event (e.g., a casual lunch, a business meeting), they can submit a request to the system via voice commands or gesture interface on their smart glasses. When making a request, they can also set settings that consider weather and temperature, as well as a budget limit.

[1592] 5. Obtaining weather and temperature information

[1593] The server uses the WeatherAPI service to retrieve weather and temperature information for a specified day. This retrieved weather and temperature information is then combined with the user's fashion item information stored in the database to generate outfit ideas.

[1594] 6. Coordination Generation

[1595] The server generates the optimal outfit based on weather and temperature information, the user's fashion item information in the database, and emotional information. The generated outfit is adjusted according to the user's requests and mood. For example, on a sunny day with a temperature of 25 degrees Celsius, it suggests cool items such as a "white shirt" and "blue jeans," and if the user has a cheerful expression, it recommends an outfit with bright colors.

[1596] 7. Searching for trending products

[1597] Based on the generated outfit, the server searches for trending products from external e-commerce sites and suggests related fashion items to the user.

[1598] 8. Display of proposed content

[1599] The server sends the generated outfits and searched trending items to the user's smart glasses for real-time display. This allows the user to intuitively check the outfits and purchase trending items as needed.

[1600] Specific example

[1601] Let's consider a scenario where a user uploads images of a "white shirt" and "black sneakers" and labels them accordingly. Next, they request an outfit for a casual weekend lunch, enabling weather considerations and setting a budget of 10,000 yen. The server retrieves from the WeatherAPI that the weekend weather will be sunny with a temperature of 25 degrees Celsius, and extracts items from its database that include a "white shirt" and "black sneakers." If the user appears cheerful, the server then suggests a "white shirt," "blue jeans," and "black sneakers" based on this information, and further searches for and suggests related items such as casual sneakers and accessories from external e-commerce sites. Finally, this information is displayed on the user's smart glasses, allowing the user to review the suggestions and purchase items they like.

[1602] Example of a prompt

[1603] User: I live in Tokyo today and it's sunny with a temperature of 25 degrees Celsius. I'm planning to go out for a casual lunch. I'm in a very good mood. What kind of outfit would be appropriate?

[1604] This invention allows users to receive personalized outfit suggestions through smart glasses that are tailored to their emotions and real-time circumstances.

[1605] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1606] Step 1:

[1607] Users upload images of fashion items they own.

[1608] Input: Images of clothing, shoes, bags, etc., uploaded from the user's smartphone or PC, along with a brief description.

[1609] Processing: The terminal sends the specified image file to the server.

[1610] Output: Image files and descriptive data sent to the server.

[1611] Step 2:

[1612] The uploaded image is analyzed, and its features are saved to a database.

[1613] Input: Image and description data of fashion items received by the server.

[1614] Processing: The server uses image analysis techniques (including machine learning algorithms) to extract features such as color, shape, and brand from the image.

[1615] Output: The extracted feature and descriptive data are stored in the database.

[1616] Step 3:

[1617] Obtain user sentiment information.

[1618] Input: User's facial image and voice data captured through the smart glasses' built-in camera and microphone.

[1619] Processing: The server uses EmotionRecognizer to analyze facial images and audio data to identify the user's emotions.

[1620] Output: Identified sentiment information.

[1621] Step 4:

[1622] Users can request outfits suitable for specific occasions.

[1623] Input: Event information entered by the user via voice commands or gesture interface on smart glasses, settings that take weather into consideration, and budget limits.

[1624] Processing: The terminal sends the user's request information to the server.

[1625] Output: Request information sent to the server.

[1626] Step 5:

[1627] Obtain weather and temperature information.

[1628] Input: The request that the server sends to the WeatherAPI service (date, time, and location of the request).

[1629] Processing: The WeatherAPI service returns weather and temperature information for the specified day to the server.

[1630] Output: Acquired weather and temperature information.

[1631] Step 6:

[1632] Based on acquired weather and temperature information, as well as emotional information, the system generates the optimal outfit.

[1633] Input: Weather and temperature information, sentiment information, and user fashion item information.

[1634] Processing: The server combines this information and uses an algorithm to generate the optimal coordination.

[1635] Output: The generated outfit.

[1636] Step 7:

[1637] Based on the generated outfit, search for trending items from external shopping sites.

[1638] Input: Generated outfit information.

[1639] Processing: The server sends a request to the e-commerce site to search for information on relevant trending products.

[1640] Output: A list of searched trending products.

[1641] Step 8:

[1642] The system displays optimal outfits and trending products on the user's device (smart glasses).

[1643] Input: A list of generated outfits and trending items.

[1644] Processing: The server sends this information to the smart glasses and presents it to the user through the display interface.

[1645] Output: Coordination and trending product information displayed on smart glasses.

[1646] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1647] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1648] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1649] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1650] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1651] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1652] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1653] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1654] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1655] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1656] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1657] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1658] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1659] 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.

[1660] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1661] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1662] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1663] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1664] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1665] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1666] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1667] The following is further disclosed regarding the embodiments described above.

[1668] ---

[1669] (Claim 1)

[1670] A means for users to upload images of clothes, shoes, bags, etc. that they own,

[1671] A method for analyzing uploaded images and saving their individual features to a database,

[1672] A means for users to request outfits suitable for specific occasions,

[1673] A means of obtaining weather and temperature information based on a request,

[1674] A means for generating the optimal coordination based on acquired weather and temperature information and information in the database,

[1675] Based on the generated outfit, a means of searching for trending products from external shopping sites,

[1676] A means of displaying optimal outfits and trendy products on the user's device,

[1677] A system that includes this.

[1678] (Claim 2)

[1679] The system according to claim 1, which uses a machine learning algorithm as an image analysis means.

[1680] (Claim 3)

[1681] The system according to claim 1, wherein an e-commerce site is used as an external shopping site.

[1682] "Example 1"

[1683] ---

[1684] (Claim 1)

[1685] A means for users to upload images of clothing, footwear, bags, etc. that they own,

[1686] A method for analyzing uploaded images and saving their individual features to a database,

[1687] A means for users to request outfits suitable for specific occasions,

[1688] A means of obtaining weather and temperature information based on a request,

[1689] A means for generating the optimal coordination based on acquired weather and temperature information and information in a database,

[1690] Based on the generated coordinates, a means of searching for trending products from external e-commerce sites,

[1691] A means of displaying optimal outfits and trendy products on the user's device,

[1692] A system that includes this.

[1693] (Claim 2)

[1694] The system according to claim 1, which uses a machine learning algorithm as an image analysis means.

[1695] (Claim 3)

[1696] The system according to claim 1, wherein a product sales site is used as an external e-commerce site.

[1697] ---

[1698] "Application Example 1"

[1699] (Claim 1)

[1700] A means for users to upload images of clothes, shoes, bags, etc. that they own,

[1701] A method for analyzing uploaded images and saving their individual features to a database,

[1702] A means for users to request outfits suitable for specific occasions,

[1703] A means of obtaining weather and temperature information based on a request,

[1704] A means for generating the optimal coordination based on acquired weather and temperature information and information in the database,

[1705] Based on the generated coordinates, a means of searching for trending products from external e-commerce sites,

[1706] A means of displaying optimal outfits and trendy products on the user's device,

[1707] A system that includes this.

[1708] (Claim 2)

[1709] The system according to claim 1, which uses a machine learning algorithm as an image analysis means.

[1710] (Claim 3)

[1711] The system according to claim 1, which inputs generated coordinates and trend product information into a generation AI model in the form of prompt sentences, and displays more refined coordinates and recommended products.

[1712] "Example 2 of combining an emotion engine"

[1713] (Claim 1)

[1714] A means for users to upload images of clothing, footwear, bags, etc. that they own,

[1715] A method for analyzing uploaded images and saving their individual features to a database,

[1716] A means for users to request outfits suitable for specific occasions,

[1717] A means of obtaining weather and temperature information based on a request,

[1718] A means for generating the optimal coordination based on acquired weather and temperature information and information in the database,

[1719] A means of analyzing the user's facial expressions and voice data to obtain emotional information,

[1720] A method for personalizing outfits based on acquired emotional information,

[1721] Based on the generated coordinates, a means of searching for trending products from external e-commerce sites,

[1722] A means of displaying optimal outfits and trendy products on the user's device,

[1723] A system that includes this.

[1724] (Claim 2)

[1725] The system according to claim 1, which uses a machine learning algorithm as an image analysis means.

[1726] (Claim 3)

[1727] The system according to claim 1, which uses an emotion engine to analyze the user's facial expressions and voice data.

[1728] "Application example 2 when combining with an emotional engine"

[1729] (Claim 1)

[1730] A means for users to upload images of clothes, shoes, bags, etc. that they own,

[1731] A method for analyzing uploaded images and saving their individual features to a database,

[1732] A means for users to request outfits suitable for specific occasions,

[1733] A means of obtaining weather and temperature information based on a request,

[1734] A means for generating the optimal coordination based on acquired weather and temperature information and information in the database,

[1735] Based on the generated outfit, a means of searching for trending products from external shopping sites,

[1736] A means of displaying optimal outfits and trendy products on the user's device,

[1737] A means of acquiring user emotional information and adjusting the coordination based on that information,

[1738] A means of using smart glasses as a user's terminal,

[1739] A system that includes this.

[1740] (Claim 2)

[1741] The system according to claim 1, which uses a machine learning algorithm as an image analysis means.

[1742] (Claim 3)

[1743] The system according to claim 1, wherein an e-commerce site is used as an external shopping site. [Explanation of Symbols]

[1744] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to upload images of clothes, shoes, bags, etc. that they own, A method for analyzing uploaded images and saving their individual features to a database, A means for users to request outfits suitable for specific occasions, A means of obtaining weather and temperature information based on a request, A means for generating the optimal coordination based on acquired weather and temperature information and information in the database, Based on the generated outfit, a means of searching for trending products from external shopping sites, A means of displaying optimal outfits and trendy products on the user's device, A system that includes this.

2. The system according to claim 1, which uses a machine learning algorithm as an image analysis means.

3. The system according to claim 1, wherein an e-commerce site is used as an external shopping site.

Images