System

Abstract

A system is provided.SOLUTION: A system, comprising: means for analyzing a user's past clothes photos and preferences to generate a personal style profile; means for obtaining up-to-date weather data of a travel destination to grasp climate information in real time; means for proposing clothes matching a style in consideration of a culture and a trend of the travel destination; means for automatically generating a necessary gear list based on the proposed clothes; means for assisting the user to prevent duplication and shortage at the time of packing; and means for recommending environmentally friendly fashion items.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] It is difficult for travelers to choose clothing appropriate for the climate and culture of their destination, and they also face complex issues regarding whether to bring too much or too little and choosing sustainable fashion. Furthermore, it is difficult to efficiently find clothing that fits their individual style. To address these issues, the present invention aims to provide a system that suggests clothing appropriate for the climate and cultural background of the destination based on the individual traveler's style, supports efficient packing, and helps select environmentally friendly fashion items. [Means for solving the problem]

[0005] The present invention first includes a means for analyzing a user's past clothing photos and preferences to generate a personal style profile. It then includes a means for acquiring the latest weather data for the travel destination and understanding weather information in real time. It also includes a means for suggesting clothing that matches the user's style, taking into account the culture and trends of the travel destination. It also includes a means for automatically generating a packing list based on the suggested clothing, helping the user avoid duplication or shortages when packing. It also includes a means for recommending environmentally friendly fashion items. In this way, personalized clothing suggestions and packing lists are provided for each individual user, supporting a satisfying travel experience.

[0006] "User" refers to a person who uses the system to receive suggestions for clothing appropriate for their travel destination.

[0007] "Past clothing photos" refers to photo data of clothing previously worn by a user.

[0008] "Preferences" refer to personal preferences that users have for particular colors, materials, designs, etc.

[0009] "Style profile" refers to a collection of information about a user's fashion style that is generated by analyzing the user's past clothing photos and preferences.

[0010] "Destination" means a geographic location that you intend to visit.

[0011] "Latest weather data" refers to real-time weather information (temperature, humidity, weather forecast, etc.) for your travel destination.

[0012] "Climate information" refers to information about the weather at your travel destination, such as the weather, temperature, and humidity.

[0013] "Culture and trends" refers to the generally accepted style of clothing and current fashions in the area you are traveling to.

[0014] "Clothing suggestions" refers to the act of recommending the most suitable clothing for a user, taking into consideration the user's style profile and the climate and culture of the travel destination.

[0015] A "packing list" is a list of items necessary for a trip that serves as a guide for users to pack efficiently.

[0016] "Packing" refers to the act of organizing and packing the luggage you will be taking on a trip.

[0017] "Eco-conscious fashion items" refer to clothing and accessories made from materials and using manufacturing methods that minimize the impact on the environment.

[0018] "Auto-generation" refers to the process by which the system uses algorithms to automatically generate packing lists and outfit suggestions based on data provided by the user.

[0019] "Assistance" refers to the act of providing assistance or support to help a user smoothly prepare for a trip. [Brief explanation of the drawings]

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

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

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

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

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

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

[0030] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0037] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0041] MODE FOR CARRYING OUT THE INVENTION

[0042] The system of the present invention includes a means for analyzing a user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination and understanding climate information in real time, a means for suggesting clothing that matches the style taking into account the culture and trends of the travel destination, a means for automatically generating a list of necessary items to bring based on the suggested clothing, a means for supporting the user in preventing duplication or shortages when packing, and a means for recommending environmentally friendly fashion items.

[0043] Program processing and explanation

[0044] When a user logs in to the app, they first upload photos of their previous outfits and their preferences (color, design, etc.), then enter the details in an input form. The device then sends this data to the server.

[0045] The server uses image analysis and natural language processing to generate a style profile for the user and stores it in a database, revealing the user's past style information and preferences.

[0046] After the user inputs the travel destination information, the user device sends the travel destination, travel duration, and planned activities to the server, which then retrieves real-time weather data from an external weather API and associates it with the weather conditions of the travel destination.

[0047] The server combines the user profile with the destination's climate and cultural background, and uses generative AI to create an optimal outfit list. This list includes not only weather-appropriate clothing but also culturally appropriate clothing. It also includes recommendations for environmentally friendly items and local brands.

[0048] The generated clothing list is sent to the user's device and notified to the user, who can then review the list and make adjustments as necessary.

[0049] Next, the server automatically generates a list of necessary items based on the recommended outfit. This list is used to prevent duplication or shortages when packing. The list is also sent to the user's device and notified to the user.

[0050] Specific examples

[0051] Example 1: Summer trip to Tokyo

[0052] user:

[0053] He likes old photos of his outfits and casual styles. His personal items include T-shirts, shorts, and sneakers.

[0054] Travel information:

[0055] Travel destination: Tokyo

[0056] Period: July 20th to July 25th

[0057] Activities: Sightseeing, shopping, cafe hopping

[0058] server:

[0059] Analyzes past clothing photos and preferences to generate a casual style profile.

[0060] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were both high.

[0061] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[0062] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[0063] User device:

[0064] The user is notified of the clothing list and belongings list sent from the server, and the user can confirm and adjust the list.

[0065] Example 2: Winter business trip to New York

[0066] user:

[0067] He prefers a formal yet business casual style, and owns a suit, dress shoes, and coat.

[0068] Travel information:

[0069] Travel destination: New York

[0070] Period: December 1st to December 5th

[0071] Activities: Meetings, business dinners

[0072] server:

[0073] Analyzes past clothing photos and preferences to generate a formal style profile.

[0074] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[0075] The store offers warm and formal clothing, including wool coats, suits, and dress shoes, as well as items made from eco-friendly materials and local brands.

[0076] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[0077] User device:

[0078] The user is notified of the clothing list and belongings list sent from the server, and the user can confirm and adjust the list.

[0079] This system allows users to efficiently prepare for their trip and easily select the style that best suits their destination.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] The user logs in to the application. The user uploads past clothing photos and preference information (color, material, design preferences, etc.) and enters detailed information into the input form. The user's device sends this data to the server.

[0083] Step 2:

[0084] The server inputs the received image data into an image analysis model to extract the user's style characteristics. At the same time, it inputs the text data into a natural language processing model to analyze preferences such as color and design. This generates a user profile and stores it in a database.

[0085] Step 3:

[0086] The user inputs travel information (destination, duration, planned activities) into the application, and the user terminal sends this information to the server.

[0087] Step 4:

[0088] Based on the submitted travel information, the server retrieves real-time weather data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API, stores the retrieved weather data in a database, and associates it with the user's travel information.

[0089] Step 5:

[0090] The server uses generative AI to create an optimal outfit list based on the user's profile, weather information, and cultural background. The generated outfit list includes items that are climate-appropriate and culturally appropriate, as well as recommendations for sustainable items and local brands.

[0091] Step 6:

[0092] The generated clothing suggestion list is sent from the server to the user's terminal and notified to the user, who can then review the suggested clothing list and make corrections or adjustments as necessary.

[0093] Step 7:

[0094] The server automatically generates a list of necessary items based on the recommended outfit. This list is intended to prevent duplication or shortages. The list is sent from the server to the user's device and notified to the user.

[0095] Step 8:

[0096] Using the user terminal, users can check their packing list and pack efficiently, allowing them to smoothly prepare for their trip.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] When traveling or on a business trip, selecting appropriate clothing and efficiently preparing belongings is a time-consuming and labor-intensive task. It is particularly difficult to select clothing that takes into account weather conditions and cultural backgrounds, and finding environmentally friendly items can be time-consuming. A convenient and effective system is needed to solve these problems.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0101] In this invention, the server includes means for analyzing a user's past clothing photos and preferences to generate a personal style profile, means for acquiring the latest weather data for the travel destination and grasping climate information in real time, and means for integrating the weather data for the travel destination, the user's style profile, and cultural background and generating an appropriate clothing list using a generative AI model. This allows users to easily select clothing appropriate for the weather conditions and cultural background of their travel destination and efficiently prepare their belongings.

[0102] A "user" is an individual who uses this system and provides past clothing photos and preference data.

[0103] "Clothing photos" are images or photos of clothing worn by a user in the past.

[0104] A "style profile" is data that indicates a user's personal style and fashion trends, generated based on past clothing photos and preferences of the user.

[0105] "Weather data" refers to data that indicates information about the climate, such as the current and forecast weather and temperature at the travel destination.

[0106] "Real-time" refers to a method of data acquisition and processing that occurs nearly simultaneously with the present time.

[0107] "Cultural background" refers to information related to culture, such as customs, values, and typical styles in the region you are traveling to.

[0108] A "generative AI model" is an artificial intelligence model trained from large amounts of data, which is used to generate an appropriate outfit list by integrating a user's style profile, weather data, and cultural background.

[0109] A "packing list" is a list of items that a user needs to carry with them when traveling or on a business trip.

[0110] A "user terminal" is an electronic device, such as a smartphone or PC, that a user uses to access this system.

[0111] "Notification" is a means of communicating information to the user about the generated clothing list and belongings list.

[0112] "Eco-friendly fashion items" are clothing and accessories made using sustainable materials and processes that take into consideration their environmental impact.

[0113] MODE FOR CARRYING OUT THE INVENTION

[0114] The system of the present invention is designed to enable users planning a trip or business trip to efficiently select appropriate clothing and generate a packing list. The system includes a means for analyzing the user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination to understand climate information in real time, a means for suggesting appropriate clothing taking into account the culture and trends of the travel destination, a means for automatically generating a necessary packing list based on the suggested clothing, a means for providing support in preventing duplications and shortages when packing, and a means for recommending environmentally friendly fashion items.

[0115] To use this system, users use devices such as smartphones or PCs. First, they log in to the application, upload photos of their previous outfits, and enter their preferred styles, colors, and designs in the input form. This data is then sent from the device to the server.

[0116] The server analyzes the data using image analysis tools (e.g., OpenCV and TensorFlow) and natural language processing tools (e.g., NLTK and spaCy) to generate a style profile for the user, which is then stored in a database.

[0117] Next, the user inputs their travel destination, travel duration, and planned activities. This information is also sent to the server via the device. The server retrieves real-time weather data from external weather APIs (e.g., OpenWeatherMap API or Weatherstack API) and correlates it with the weather conditions at the travel destination.

[0118] The server provides the user's style profile, weather data, and cultural background as input data to a generative AI model (e.g., GPT-4) and sends a prompt. Specific examples of prompts are as follows:

[0119] "The user's style profile is casual. The travel destination is Tokyo, where the temperature is high and humidity is high in July. The primary focus is sightseeing. Please generate an optimal outfit list."

[0120] Based on these prompts, the generative AI model generates a list of appropriate outfits, which the server then sends to the user's device. The list includes items that match the user's preferences, as well as items suited to the climate and culture of the destination. It also suggests eco-friendly fashion items and local brand options.

[0121] The server then automatically generates a list of necessary items to bring based on the clothing list and sends it to the user's device, allowing the user to efficiently prepare for a trip or business trip and easily select appropriate clothing and items to bring.

[0122] For example, if a user is traveling to Tokyo in July, a casual T-shirt, shorts, and breathable sneakers will be recommended based on temperature and humidity information obtained from the weather API. Additional necessary items (e.g., sunscreen, hat, sunglasses, etc.) will also be automatically added to the recommended list. The device will notify the user of this information, allowing them to review and adjust the recommended list as needed.

[0123] The above is a specific embodiment for carrying out the present invention. This system allows the user to easily select clothing and items suitable for the weather and specific activities of the day.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1: Collect user information

[0126] Users log in to the app, upload photos of their previous outfits, and enter their preferred styles, colors, and designs into an input form. The input data includes the outfit photo file and text information.

[0127] Specifically, users select a photo from their smartphone or computer, fill out the form with details about their style (e.g., "casual" or "formal"), and their preferred colors and design, and then press the "Submit" button.

[0128] Input: Clothing photo file, preferred style, color, design (text)

[0129] Output: User information dataset (photo files and text information)

[0130] Step 2: Send user data

[0131] The device packages the collected user data into packets and sends them to the server as HTTP requests.

[0132] In specific operation, the terminal transmits photo data and text data to the server via the network.

[0133] Input: User information dataset

[0134] Output: User information data sent to the server

[0135] Step 3: Generate a User Style Profile

[0136] The server analyzes the clothing photos using image analysis tools (e.g., OpenCV and TensorFlow) and analyzes the text data using natural language processing tools (e.g., NLTK and spaCy), generating a style profile for the user and storing it in a database.

[0137] In concrete terms, the server uses image recognition algorithms to extract style elements from photos and then integrates them with the results of analyzing text data to build a style profile.

[0138] Input: User information data (photo and text)

[0139] Output: Style profile (stored in database)

[0140] Step 4: Enter your destination information

[0141] The user enters the travel destination, travel duration, and planned activities into the application's travel information input form.

[0142] Specifically, the user fills in the form with "travel destination," "travel period," and "activities," and presses the "Submit" button.

[0143] Input: Travel destination, travel period, activities (text)

[0144] Output: Travel information dataset

[0145] Step 5: Obtaining Weather Data

[0146] The server sends a request to an external weather API (e.g., OpenWeatherMap API or Weatherstack API) to obtain real-time weather data for the travel destination.

[0147] In specific operation, the server sends an HTTP request to the API and receives the acquired weather data.

[0148] Input: Travel destination information (text)

[0149] Output: Real-time weather data

[0150] Step 6: Generate the outfit list

[0151] The server sends prompts to a generative AI model (e.g., GPT-4) that integrates the user's style profile, weather data, and cultural background, and the generative AI model generates a list of appropriate outfits.

[0152] Specifically, the AI ​​provides a prompt example that reads, "The user's style profile is casual. The travel destination is Tokyo, where the temperature and humidity are high in July. Sightseeing will be the main focus. Please generate a list of the most suitable outfits." The AI ​​then returns a list of T-shirts, shorts, sneakers, etc.

[0153] Input: Style profile, weather data, cultural background

[0154] Output: A list of the best outfits

[0155] Step 7: Generate a packing list

[0156] The server automatically generates an inventory list based on the generated clothing list, including any additional items required (e.g., sunscreen, sunglasses, etc.).

[0157] In particular, the server analyzes the clothing list and automatically adds related items (e.g., sunscreen for a T-shirt) to generate the list.

[0158] Input: Best Outfit List

[0159] Output: Inventory list

[0160] Step 8: Notification and confirmation of results

[0161] The device will then notify the user of the generated clothing and belongings list, which the user can review and adjust as necessary.

[0162] Specifically, the device will notify the user of the list via push or email notification, allowing them to view and adjust it within the app.

[0163] Input: List of suitable clothes, list of things to bring

[0164] Output: An interface to inform the user and allow them to review and adjust

[0165] (Application example 1)

[0166] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0167] In today's busy lifestyles, it is important for delivery workers to be equipped with the appropriate clothing and equipment to perform their deliveries efficiently and effectively. However, selecting the most appropriate clothing and equipment for each weather and cultural background is time-consuming and inefficient. Also, choosing eco-friendly items is a must. A system that solves these problems and allows delivery workers to perform their work smoothly is needed.

[0168] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0169] In this invention, the server includes means for analyzing past clothing photos and equipment and preferences of the user and delivery person to generate personal style and equipment profiles, means for obtaining the latest weather data for the travel destination and delivery area to grasp weather information in real time, means for suggesting clothing and equipment that matches the style taking into consideration the culture and trends of the travel destination and delivery area, and means for automatically generating a list of necessary items to bring based on the suggested clothing and equipment, thereby enabling delivery people to prepare efficiently and environmentally friendly.

[0170] "User" refers to an individual who uses the system to generate their own style profile and receive clothing and belongings suggestions.

[0171] "Delivery personnel" refers to personnel who use this system to receive suggestions on optimal clothing and equipment for performing tasks such as food delivery.

[0172] "Past clothing photos" are image data of clothing worn by users and delivery personnel in the past.

[0173] "Style profile" refers to information about a person's fashion style generated by analyzing past clothing photos and preferences of the user and delivery person.

[0174] "Weather data" refers to information such as the current and forecasted weather, temperature, humidity, etc. at the travel destination or delivery area.

[0175] "Culture and trends" refers to the customs and fashion trends of clothing and behavior in a particular region or society.

[0176] A "packing list" is an automatically generated list of necessary items to bring based on the suggested clothing and equipment.

[0177] "Environmentally friendly fashion items" refer to clothing, accessories, etc. that are made from eco-friendly materials and are intended to reduce the burden on the environment.

[0178] "Equipment Profile" refers to information about a delivery person's personal equipment generated by analyzing their past equipment and preferences.

[0179] "Means of understanding weather information in real time" refers to a method of obtaining the latest weather data from an external weather API to understand the weather conditions at the travel destination or delivery area in real time.

[0180] "Means for suggesting optimal clothing and equipment" refers to a method that uses AI to integrate personal profiles, climate information, and cultural backgrounds to suggest optimal clothing and equipment.

[0181] "Means for automatically generating a packing list" refers to a method for automatically generating a list of necessary packing items based on the suggested clothing and equipment.

[0182] "Delivery area" refers to the region or area in which a delivery person makes deliveries.

[0183] "Eco-friendly items" refer to products and equipment that are made using environmentally friendly materials and manufacturing processes.

[0184] The system for realizing this invention includes a server, a terminal, and a user. The roles and processes of each will be described in detail below.

[0185] Server Roles

[0186] The server first receives and analyzes data from users and delivery staff. Specifically, it handles the following data:

[0187] Image data of past photos of clothing and equipment of users and delivery personnel

[0188] Text data on the fashion and equipment preferences of users and delivery personnel

[0189] The server uses TensorFlow for image analysis and GPT-4 for analyzing text data of preferences, which generates a style profile and equipment profile for each individual. The server also uses an external weather API (OpenWeatherMap API) to obtain real-time weather information for travel destinations and delivery areas.

[0190] The server then integrates this data and uses a generative AI model to generate a list of optimal clothing and equipment, based on style profile, equipment profile, weather information, and cultural background.

[0191] Additionally, the server automatically generates a list of necessary items based on the generated clothing and equipment list, including eco-friendly items and local brand options in the process.

[0192] Device Role

[0193] The terminal functions as a user interface. First, the user or delivery person uploads photos of their previous outfits and their preferences, which are then sent to the server. The server then displays a list of optimal outfits and equipment, as well as a list of items to bring. The user or delivery person can review this information and make adjustments as necessary.

[0194] User Roles

[0195] The user inputs their own data into the terminal, receives suggestions from the server, and makes preparations based on them. Specifically, the user uses the system as follows:

[0196] 1. Upload past clothing photos and preferences to your device.

[0197] 2. Enter travel destination and delivery area information into the device.

[0198] 3. Check the suggested clothing and packing list and prepare accordingly.

[0199] Specific examples

[0200] Example 1: Rainy day delivery in Shibuya

[0201] User: Upload data on the delivery person's past preferences for waterproof jackets and shoes.

[0202] Server: Analyzes past photos of equipment and preferences to generate a profile. Checks the weather in Shibuya using the OpenWeatherMap API and suggests waterproof jackets, waterproof shoes, and rain bags for rainy days.

[0203] Terminal: Notifies the delivery person of the clothing list and belongings list sent from the server, and allows them to confirm and make adjustments.

[0204] Example prompts to be input to the generative AI model:

[0205] "Please suggest the best clothing and equipment for rainy days for food delivery in Shibuya. Delivery people prefer waterproof jackets and shoes. Also, please suggest eco-friendly items."

[0206] The system allows delivery personnel to prepare efficiently and environmentally, making it easy to select equipment appropriate for weather conditions and cultural backgrounds.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] The user inputs past clothing photos and information about their preferences into the terminal. This data is sent from the terminal to the server as image data and text data. The input data includes information such as photos of clothing worn in the past, favorite colors, designs, and particularly favorite fashion styles.

[0210] Input: Past clothing photos (image data), preference information (text data)

[0211] Output: Send data to the server

[0212] Step 2:

[0213] The server analyzes the received data. First, it uses TensorFlow to analyze the image data and generate a style profile for the user. Then it uses GPT-4 to analyze the text data of user preferences and create a detailed profile of the individual's fashion style.

[0214] Input: Past clothing photos (image data), preference information (text data)

[0215] Output: Style Profile

[0216] Step 3:

[0217] The user inputs information about the travel destination and delivery area into the terminal, including the name of the destination, the duration, the planned activities and tasks, etc. This information is then sent to the server.

[0218] Input: Travel destination information, delivery area information (text data)

[0219] Output: Send data to the server

[0220] Step 4:

[0221] The server uses the OpenWeatherMap API to obtain real-time weather data for the entered travel destination and delivery area, and uses this information to understand the weather conditions of the travel destination and delivery area.

[0222] Input: Travel destination information, delivery area information (text data)

[0223] Output: Get real-time weather data

[0224] Step 5:

[0225] The server combines the acquired weather data with the generated style and equipment profiles, as well as the input cultural background and trend information. Based on this, a generative AI model (GPT-4) is used to generate the optimal outfit and equipment list. Eco-friendly items and local brand options are also taken into consideration.

[0226] Inputs: Style profile, equipment profile, real-time weather data, cultural context information

[0227] Output: Optimal clothing and equipment list

[0228] Step 6:

[0229] The server sends the generated list of optimal clothing and equipment to the device, which receives it and notifies the user. The user can then check the displayed list and make adjustments as necessary.

[0230] Input: Optimal clothing and equipment list

[0231] Output: Notification to terminal

[0232] Step 7:

[0233] The server automatically generates a list of necessary items to bring based on the suggested clothing and equipment, including eco-friendly items and local brand options, and sends the list to the device and notifies the user.

[0234] Input: Optimal clothing and equipment list

[0235] Output: Generates and notifies inventory list

[0236] Example prompt

[0237] "Please suggest the best clothing and equipment for rainy days for food delivery in Shibuya. Delivery people prefer waterproof jackets and shoes. Also, please suggest eco-friendly items."

[0238] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0239] MODE FOR CARRYING OUT THE INVENTION

[0240] The system of the present invention combines a means for analyzing a user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination and understanding climate information in real time, a means for suggesting clothing that matches the style taking into consideration the culture and trends of the travel destination, a means for automatically generating a list of necessary items to bring based on the suggested clothing, a means for supporting the user in preventing duplication or shortages when packing, a means for recommending environmentally friendly fashion items, and an emotion engine that recognizes the user's emotions.

[0241] Program processing and explanation

[0242] Generate a style profile

[0243] When a user logs in to the application, they first upload photos of their previous outfits and their preferences (color, design, etc.), then enter their details into an input form. The device then sends this data to the server.

[0244] The server uses an image analysis model to extract the user's style characteristics from the uploaded image data. At the same time, it uses a natural language processing model to analyze the text data and identify specific preferences for color, design, material, etc. Based on this information, the server creates a user profile and stores it in a database. This clarifies the user's past style information and preferences.

[0245] Obtaining travel information

[0246] After the user inputs the travel destination information, the user's device then transmits the travel destination, travel period, and planned activities to the server. Based on the received information, the server obtains real-time weather data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API, stores this weather data in a database, and associates it with the user's travel information.

[0247] Generating recommendations

[0248] The server uses generative AI to create an optimal outfit list based on the user's profile, weather information, and cultural background. The generated outfit list includes items that are appropriate for the weather conditions as well as culturally appropriate items. The emotion engine also assesses the user's emotional state at that time and can suggest outfits that are more psychologically satisfying. The recommendations also include environmentally friendly items and local brand options.

[0249] Generate suggestions and packing lists

[0250] The generated clothing suggestion list is sent from the server to the user's device and notified to the user. The user can check the suggested list and make adjustments as necessary. Based on the list, the server automatically generates a list of necessary items to bring, which is also sent to the user's device and notified to the user.

[0251] Specific examples

[0252] Example 1: Summer trip to Tokyo (casual style)

[0253] user:

[0254] He likes a casual style and owns T-shirts, shorts, and sneakers.

[0255] Travel information:

[0256] Travel destination: Tokyo

[0257] Period: July 20th to July 25th

[0258] Activities: Sightseeing, shopping, cafe hopping

[0259] server:

[0260] Analyzes past clothing photos and preferences to generate a casual style profile.

[0261] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were high.

[0262] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[0263] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[0264] An emotional engine assesses the user's emotional state and reflects this in the selection of suggested items.

[0265] User device:

[0266] You can check the clothing and item lists sent from the server and make adjustments as needed.

[0267] Example 2: Winter business trip to New York (formal style)

[0268] user:

[0269] He prefers a formal yet business casual style, and his personal belongings include suits, dress shoes, and coats.

[0270] Travel information:

[0271] Travel destination: New York

[0272] Period: December 1st to December 5th

[0273] Activities: Meetings, business dinners

[0274] server:

[0275] Analyzes past clothing photos and preferences to generate a formal style profile.

[0276] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[0277] The site offers warm and formal clothing such as wool coats, suits, and dress shoes, and also recommends items made from eco-friendly materials and local brands.

[0278] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[0279] An emotional engine assesses the user's emotional state and reflects this in the selection of suggested items.

[0280] User device:

[0281] You can check the clothing and item lists sent from the server and make adjustments as needed.

[0282] This system allows users to efficiently prepare for their trip, easily select a style that suits their destination, and provides a more fulfilling travel experience by taking into account the user's emotional state.

[0283] The processing flow will be explained below.

[0284] Step 1:

[0285] The user logs in to the application. First, the user uploads photos of their previous outfits and their preferred information (color, design, etc.), and then enters the details into an input form. The user's device sends this data to the server.

[0286] Step 2:

[0287] The server inputs the received image data into an image analysis model to extract the user's style characteristics. At the same time, it inputs the received text data into a natural language processing model to analyze color and design preferences. The server then generates a user profile based on these analysis results and stores it in a database.

[0288] Step 3:

[0289] The user inputs travel information (travel destination, duration, planned activities) into the application. The user terminal sends this information to the server, which stores it in a database.

[0290] Step 4:

[0291] The server retrieves real-time weather data for the travel destination from an external weather API based on the submitted travel information, stores the retrieved weather data in a database, and associates it with the user's travel information.

[0292] Step 5:

[0293] The server integrates user profiles, climate information, and cultural backgrounds, and uses generative AI to create an optimal outfit list, which includes items suitable for the weather conditions, culturally compatible items, and eco-friendly fashion items.

[0294] Step 6:

[0295] The server uses an emotion engine to evaluate the user's emotional state in real time, and based on the results, dynamically adjusts the outfit list to suggest outfits that suit the user's emotions.

[0296] Step 7:

[0297] The generated clothing suggestion list is sent from the server to the user's terminal and notified to the user, who can then check the suggested clothing list and make adjustments as necessary.

[0298] Step 8:

[0299] The server automatically generates a list of necessary items based on the recommended outfits, and the list is sent from the server to the user's device and notified to the user.

[0300] Step 9:

[0301] Users can check their packing list on their device and pack efficiently, allowing them to smoothly prepare for their trip.

[0302] Specific examples

[0303] Example 1: Summer trip to Tokyo

[0304] user:

[0305] He prefers a casual style and his personal items include t-shirts, shorts, and sneakers.

[0306] Travel information:

[0307] Travel destination: Tokyo

[0308] Period: July 20th to July 25th

[0309] Activities: Sightseeing, shopping, cafe hopping

[0310] Step 1:

[0311] The user logs in, uploads photos of past outfits, and enters their casual preferences. The user's device sends the data to the server.

[0312] Step 2:

[0313] The server performs image analysis and natural language processing to generate and store user profiles.

[0314] Step 3:

[0315] The user enters travel information for Tokyo, July 20th to July 25th, sightseeing and shopping, and the user's device sends the data to the server.

[0316] Step 4:

[0317] The server collects real-time weather data for Tokyo and stores it in a database.

[0318] Step 5:

[0319] The server uses generated AI to create a list of outfits, such as a T-shirt, shorts, and breathable sneakers.

[0320] Step 6:

[0321] The sentiment engine evaluates the user's emotions and adjusts the listing to enhance the travel experience.

[0322] Step 7:

[0323] The server transmits the clothing list to the user terminal, and the user checks the list.

[0324] Step 8:

[0325] The server generates a list of belongings and transmits it to the user terminal.

[0326] Step 9:

[0327] The user checks the list of belongings and packs.

[0328] Example 2: Winter business trip to New York

[0329] user:

[0330] He prefers a formal yet business casual style, and his personal belongings include a suit, dress shoes, and coat.

[0331] Travel information:

[0332] Travel destination: New York

[0333] Period: December 1st to December 5th

[0334] Activities: Meetings, business dinners

[0335] Step 1:

[0336] The user logs in, uploads photos of past outfits, and enters their formal preferences. The user's device sends the data to the server.

[0337] Step 2:

[0338] The server performs image analysis and natural language processing to generate and store user profiles.

[0339] Step 3:

[0340] The user enters travel information such as New York, December 1st to December 5th, meeting and business dinner, and the user terminal sends the data to the server.

[0341] Step 4:

[0342] The server retrieves real-time weather data for New York and stores it in a database.

[0343] Step 5:

[0344] The server uses generated AI to create a list of clothing items such as wool coats, suits, and dress shoes.

[0345] Step 6:

[0346] An emotion engine assesses the user's emotions and tailors the list to ease tension in business meetings.

[0347] Step 7:

[0348] The server transmits the clothing list to the user terminal, and the user checks the list.

[0349] Step 8:

[0350] The server generates a list of belongings and transmits it to the user terminal.

[0351] Step 9:

[0352] The user checks the list of belongings and packs.

[0353] Example 2

[0354] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0355] Modern travelers need to choose appropriate clothing, taking into account the climate, culture, and trends of their destination. Automatically generating a packing list and incorporating environmental considerations and personal emotional state is a time-consuming and labor-intensive task. Conventional systems were unable to perform these processes efficiently and comprehensively, placing a heavy burden on travel preparation.

[0356] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing the user's past clothing photos and preferences to generate a personal style profile, a means for acquiring the latest weather data for the travel destination and understanding the weather information in real time, and a means for evaluating the user's emotional state and suggesting optimal clothing based on the evaluation. This allows travelers to efficiently prepare for their trip and select appropriate clothing that suits the climate and culture.

[0357] "User" refers to an individual who uses the system to prepare for a trip or select fashion.

[0358] "Past clothing photos" refer to photos of clothing previously worn by a user, and are data used to generate a style profile.

[0359] "Preferences" refers to information about the user's preferred fashion style, color, design, and material.

[0360] A "style profile" is data that represents a user's personal fashion trends and is generated based on the user's past clothing photos and preferences.

[0361] "Travel Destination" refers to the place that the User intends to visit.

[0362] "Weather data" refers to real-time weather information such as weather forecast, temperature, and humidity at your travel destination.

[0363] "Culture" refers to the social, historical, and regional background of a travel destination, and is a factor that influences clothing choices.

[0364] "Trends" refers to the latest fashions and trends in the destination.

[0365] A "packing list" refers to a list of items needed for a trip based on a suggested outfit.

[0366] "Duplicates and shortages" refers to users packing multiple items of the same kind, or leaving on a trip without an important item.

[0367] "Eco-conscious fashion items" refer to clothing and accessories made from sustainable materials and eco-friendly manufacturing methods.

[0368] "Emotional state" refers to the result of an assessment of the user's current psychological state.

[0369] "Recommendations" refers to a list of the best clothing and items to bring based on analyzed data.

[0370] "Generative AI" refers to an artificial intelligence model trained on a large dataset, which is used here to generate the outfit list.

[0371] This invention is a system that streamlines travel preparation for users and suggests clothing appropriate for the climate and culture. This system is composed of interactions between a server, a terminal, and a user. The specific processing procedures and technologies used are described below.

[0372] Generate a style profile

[0373] When a user logs in to the application, they first upload previous clothing photos and personal preferences, and then enter their details. This includes preferences for color, design, and materials. The device then sends this data to the server. The server then uses an image analysis model (e.g., Google Cloud Vision API) to extract the user's style features from the uploaded image data. At the same time, it uses a natural language processing model (e.g., BERT) to analyze the text data and understand the user's preferences. Based on these analysis results, the server creates a user profile and stores it in a database.

[0374] Obtaining travel information

[0375] When a user inputs travel destination information, the device sends the travel destination, travel duration, and planned activities to the server. Based on the received information, the server retrieves real-time climate data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API (e.g., OpenWeatherMap API). The retrieved climate data is stored in a database and associated with the user's travel information.

[0376] Generating recommendations

[0377] The server uses a generative AI model (e.g., GPT-4) to generate an optimal outfit list based on the user profile, weather information, and cultural background. This outfit list includes items appropriate for the weather conditions as well as culturally appropriate items. It also uses an emotion engine (e.g., Azure Emotion API) to evaluate the user's emotional state at that time and suggests outfits based on that emotional state. Furthermore, recommendations can also include eco-friendly items and local brand options.

[0378] Generate suggestions and packing lists

[0379] The generated clothing suggestion list is sent from the server to the user's device and notified to the user. The user can review the suggested list and make adjustments as necessary. For example, they can exclude specific items or request additional items. Based on this, the server automatically generates a list of necessary items to bring. This list is also sent to the user's device and notified to the user.

[0380] Specific examples

[0381] Example 1: Summer trip to Tokyo (casual style)

[0382] User: Prefers casual style and owns T-shirts, shorts, and sneakers.

[0383] Travel Information: Destination: Tokyo, Period: July 20th - July 25th, Activities: Sightseeing, Shopping, Cafe Hopping

[0384] server:

[0385] Analyzes past clothing photos and preferences to generate a casual style profile.

[0386] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were high.

[0387] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[0388] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[0389] An emotional engine assesses the user's emotional state and reflects it in the selection of suggested items.

[0390] User device: Check the clothing list and belongings list sent from the server and make adjustments as necessary.

[0391] Example 2: Winter business trip to New York (formal style)

[0392] User: Prefers a formal yet business casual style and owns a suit, dress shoes, coat, etc.

[0393] Travel Information: Destination: New York, Period: December 1st - December 5th, Activities: Meetings, Business Dinner

[0394] server:

[0395] Analyzes past clothing photos and preferences to generate a formal style profile.

[0396] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[0397] The site offers warm and formal clothing such as wool coats, suits, and dress shoes, and also recommends items made from eco-friendly materials and local brands.

[0398] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[0399] An emotional engine assesses the user's emotional state and reflects it in the selection of suggested items.

[0400] User device: Check the clothing list and belongings list sent from the server and make adjustments as necessary.

[0401] Prompt Sentence Examples

[0402] Example prompt 1:

[0403] Based on the user's style profile, suggest a casual outfit list for a trip to Tokyo in July. The weather is hot and humid, and the user's past clothing data indicates that they prefer T-shirts, shorts, and sneakers. Include items made from eco-friendly materials and local brands.

[0404] Example prompt 2:

[0405] Generate an appropriate attire list for a business meeting and dinner in New York in December for a user who prefers a formal yet business casual style. The weather will be cold and likely to snow. Include items made from eco-friendly materials and local brands.

[0406] This system allows users to efficiently prepare for their trip, easily select a style that suits their destination, and provides a more fulfilling travel experience by taking into account the user's emotional state.

[0407] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0408] Step 1: A user logs in to the application and uploads photos of their previous outfits and their preferences.

[0409] Input: User ID, past clothing photos, and text information of your preferences (color, design, material, etc.).

[0410] How it works: A user logs into the application, selects a photo of an outfit from a previous outfit, and fills out a form with their preferences.

[0411] Output: The device sends these data to the server.

[0412] Step 2: The server analyzes the data using image analysis and natural language processing models to generate a style profile.

[0413] Input: Clothing photo data, text information of user preferences.

[0414] How it works: The server uses an image analysis model (e.g., Google Cloud Vision API) to extract clothing features (e.g., color, shape, material) from the photo, and simultaneously analyzes the text information using a natural language processing model (e.g., BERT).

[0415] Data processing / calculation: Extract the characteristics of fashion items through image data analysis, and analyze preferences from text data.

[0416] Output: A style profile generated based on the analysis results, which is stored in a database.

[0417] Step 3: The user inputs the travel destination information, and the terminal sends the information to the server.

[0418] Input: Travel destination, travel duration, planned activities.

[0419] Action: A user fills out a travel destination information form and presses the submit button.

[0420] Output: The device sends this travel destination information to the server.

[0421] Step 4: The server retrieves the weather data and stores it in a database.

[0422] Input: Travel destination information (destination, duration).

[0423] How it works: The server uses a weather API (e.g. OpenWeatherMap API) to get real-time weather data.

[0424] Data processing / calculation: Call the API, analyze the acquired data, and save information such as weather forecast, temperature, and humidity in a database.

[0425] Output: Weather data is stored in a database and linked to the user's travel information.

[0426] Step 5: The server uses the generative AI model to generate the optimal outfit list.

[0427] Input: User profile, destination climate data, cultural background.

[0428] How it works: The server uses a generative AI model (e.g., GPT-4) to generate an outfit list based on the input data, and an emotion engine (e.g., Azure Emotion API) to assess the user's current emotional state.

[0429] Data processing / calculation: Combining the user's past data with real-time weather data and cultural background, the system generates an optimal outfit list. It also takes into account emotional data.

[0430] Output: The generated outfit list, which is provided to the user as a suggestion list.

[0431] Step 6: The server automatically generates a list of items to bring based on the suggested clothing list.

[0432] Input: Generated outfit list.

[0433] How it works: The server automatically lists the necessary items based on the clothing list.

[0434] Data processing / calculation: Analyze the suggested clothing items and select the necessary items based on them.

[0435] Output: An automatically generated inventory list, which is sent to the user's device.

[0436] Step 7: The user terminal notifies the user of the clothing list and belongings list, and the user confirms and adjusts them.

[0437] Input: Outfit list and inventory list sent from the server.

[0438] Action: The user device presents the list to the user, who can review it and make adjustments as needed, for example, adding or removing specific items.

[0439] Output: Finalized outfit and packing list.

[0440] (Application example 2)

[0441] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0442] Traditionally, food delivery services have struggled to suggest the best dishes to suit a user's style, mood, and climate. They also lacked the functionality to recommend environmentally friendly ingredients and local brands, which resulted in an unsatisfactory user experience. Therefore, there is a need for a system that provides food delivery options that take into account a user's style, mood, climate, and environmental considerations.

[0443] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0444] In this invention, the server includes means for analyzing a user's past clothing photos and preferences to generate a personal style profile, means for acquiring the latest weather data for the user's current location to grasp climate information in real time, means for integrating the generated style profile with the climate information and cultural background to propose optimal food delivery options, means for automatically generating an optimal dish list based on the proposed food delivery options, and means for recommending dishes made with environmentally friendly ingredients and local brands, thereby making it possible to provide optimal food delivery options that suit the user's style, mood, and climate.

[0445] "Photos of the user's past clothing" are photos of clothing worn by the user in the past, and are data for generating a style profile.

[0446] "Preferences" refers to the user's fashion-related preferences, such as favorite colors, designs, and materials.

[0447] A "style profile" refers to the results of an analysis of a user's personal fashion style based on past clothing photos and preferences.

[0448] "Weather data" refers to information related to the climate, such as temperature, humidity, and weather forecasts, and is data that can be obtained in real time.

[0449] "Means for grasping weather information in real time" refers to a means for quickly obtaining the latest weather data and accurately grasping the weather conditions at the user's current location.

[0450] "Food delivery options" refers to the types of food and restaurants available for delivery, and are used to fulfill a customer's order.

[0451] "Dish List" means a list of specific dishes based on a proposed food delivery option.

[0452] "Environmentally conscious ingredients" are sustainable ingredients selected to contribute to environmental protection.

[0453] "Locally branded cuisine" refers to food and drink produced and served within a region, reflecting local culture and flavors.

[0454] A "generative AI model" is an artificial intelligence model that generates natural language and images based on input data.

[0455] A "prompt" is an instruction given to a generative AI model to obtain an appropriate output.

[0456] This invention is a system that generates a personal style profile based on the user's past clothing photos and preferences, and also obtains the latest weather data to suggest optimal options for food delivery services. The system is implemented by a user terminal and a server working together.

[0457] Program processing explanation

[0458] 1. Create a user profile

[0459] The user's device uploads photos of their previous clothing and their preferences to the application. The uploaded data is analyzed using an image analysis model (TensorFlow or PyTorch) to extract the user's fashion style characteristics. In addition, text information about the user's preferences is analyzed using a natural language processing model (such as BERT). Based on these analysis results, the server generates the user's style profile and stores it in a cloud database (such as Firebase).

[0460] 2. Obtaining weather information

[0461] The user's device acquires their current location information and sends it to the server. The server then retrieves real-time weather data from a weather data API (such as OpenWeatherMap) based on the location information. This weather data is stored in a cloud database and associated with the user's style profile.

[0462] 3. Generating Recommendations

[0463] The server integrates the generated style profile with weather data and uses a generative AI model (such as GPT-3) to suggest optimal food delivery options. The generated list includes meal options that suit the user's current style and weather conditions, allowing them to choose the best dishes to suit their mood and environment.

[0464] 4. Suggestions and Notifications

[0465] The generated food list is sent from the server to the user's device and notified to the user. The user can review the suggested dish list and make adjustments as necessary. This allows the user to order the meal that best suits their mood and environment that day.

[0466] Specific examples

[0467] Example 1: Lunch on a hot summer day (casual style)

[0468] User: Prefers casual style and has often worn T-shirts and shorts in the past.

[0469] Current location and climate: Tokyo, July, temperature 35°C, humidity 75%

[0470] session:

[0471] The user's device uploads past clothing photos and preferences to the server.

[0472] The server generates a style profile using image analysis and natural language processing.

[0473] The server uses a weather data API to obtain weather information for the current location.

[0474] A generative AI model (GPT-3) generates suggestions such as cold drinks and light salads.

[0475] A list of suggested foods is sent to the user's device, such as chilled salad, iced latte, and chilled tofu.

[0476] Example prompt: "Please suggest some dishes that would make you feel casual in Tokyo during the summer. The user's preference is casual, and the days are often hot."

[0477] Example 2: Winter evening dinner (formal style)

[0478] User: Prefers formal style and has worn suits and coats many times in the past.

[0479] Current location and climate: New York, December, 0°C, snow

[0480] session:

[0481] The user's device uploads past clothing photos and preferences to the server.

[0482] The server generates a style profile using image analysis and natural language processing.

[0483] The server uses a weather data API to obtain weather information for the current location.

[0484] A generative AI model (GPT-3) generates suggestions for hot soups, stews, and other dishes.

[0485] A list of suggested foods is sent to the user's device, such as tomato soup, a glass of wine, and warm bread.

[0486] Example prompt: "What are some recommendations for a formal winter dinner in New York? Something suitable for a cold or snowy day would be good."

[0487] In this way, our system can provide optimal food delivery options by integrating a user's past clothing photos and preferences with current weather information and using a generative AI model, allowing users to enjoy the food that best suits their mood and environment.

[0488] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0489] Step 1:

[0490] When a user logs in to the application, the user's device uploads past clothing photos and preference data. The user enters past clothing photos (image files) and text information about preferences (color, design, material, etc.) into an input form. The uploaded data is sent to the server. (Input): Past clothing photos, text information about the user's preferences (Output): Data sent to the server

[0491] Step 2:

[0492] The server performs image analysis based on the received data. The image analysis model (TensorFlow or PyTorch) analyzes the uploaded image file and extracts the user's style characteristics (type of clothing, color, design, material, etc.). At the same time, a natural language processing model (BERT, etc.) analyzes the text information to specifically understand the user's preferences. (Input): Uploaded image file and text information (Output): Analysis results of style characteristics and preferences

[0493] Step 3:

[0494] The server generates a style profile for the user based on the analysis results. The style profile integrates data extracted from the user's past clothing photos and preferences, and clearly indicates the user's fashion trends. The generated style profile is stored in a cloud database (such as Firebase). (Input): Analysis results of style features and preferences (Output): Generated style profile

[0495] Step 4:

[0496] The user device acquires the user's current location information and sends it to the server. The server uses a weather data API (such as OpenWeatherMap) based on the received current location information to acquire real-time weather data (temperature, humidity, weather forecast, etc.). The acquired weather data is stored in a cloud database and associated with the user's style profile. (Input): Current location information (Output): Acquired weather data

[0497] Step 5:

[0498] The server combines the generated style profile with weather data and generates optimal food delivery options using a generative AI model (such as GPT-3). The generative AI model creates an optimal dish list based on the user's mood, style, and climate based on the prompt. (Input): Style profile, weather data, prompt (Output): Optimal food delivery options

[0499] Step 6:

[0500] The server sends the generated food list to the user's device and notifies the user. The user can review the proposed food list and make adjustments as necessary. The final adjusted list is sent back to the server, and the necessary information is stored in the cloud database. (Input): Generated food list (Output): Food list sent to the user's device

[0501] This allows users to choose the dish that best suits their mood and the environment at the time and enjoy a comfortable meal.

[0502] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0503] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0504] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0505] [Second embodiment]

[0506] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0507] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0508] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0509] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0510] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0511] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0512] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0513] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0514] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0515] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0516] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0517] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0518] MODE FOR CARRYING OUT THE INVENTION

[0519] The system of the present invention includes a means for analyzing a user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination and understanding climate information in real time, a means for suggesting clothing that matches the style taking into account the culture and trends of the travel destination, a means for automatically generating a list of necessary items to bring based on the suggested clothing, a means for supporting the user in preventing duplication or shortages when packing, and a means for recommending environmentally friendly fashion items.

[0520] Program processing and explanation

[0521] When a user logs in to the app, they first upload photos of their previous outfits and their preferences (color, design, etc.), then enter the details in an input form. The device then sends this data to the server.

[0522] The server uses image analysis and natural language processing to generate a style profile for the user and stores it in a database, revealing the user's past style information and preferences.

[0523] After the user inputs the travel destination information, the user device sends the travel destination, travel duration, and planned activities to the server, which then retrieves real-time weather data from an external weather API and associates it with the weather conditions of the travel destination.

[0524] The server combines the user profile with the destination's climate and cultural background, and uses generative AI to create an optimal outfit list. This list includes not only weather-appropriate clothing but also culturally appropriate clothing. It also includes recommendations for environmentally friendly items and local brands.

[0525] The generated clothing list is sent to the user's device and notified to the user, who can then review the list and make adjustments as necessary.

[0526] Next, the server automatically generates a list of necessary items based on the recommended outfit. This list is used to prevent duplication or shortages when packing. The list is also sent to the user's device and notified to the user.

[0527] Specific examples

[0528] Example 1: Summer trip to Tokyo

[0529] user:

[0530] He likes old photos of his outfits and casual styles. His personal items include T-shirts, shorts, and sneakers.

[0531] Travel information:

[0532] Travel destination: Tokyo

[0533] Period: July 20th to July 25th

[0534] Activities: Sightseeing, shopping, cafe hopping

[0535] server:

[0536] Analyzes past clothing photos and preferences to generate a casual style profile.

[0537] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were both high.

[0538] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[0539] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[0540] User device:

[0541] The user is notified of the clothing list and belongings list sent from the server, and the user can confirm and adjust the list.

[0542] Example 2: Winter business trip to New York

[0543] user:

[0544] He prefers a formal yet business casual style, and owns a suit, dress shoes, and coat.

[0545] Travel information:

[0546] Travel destination: New York

[0547] Period: December 1st to December 5th

[0548] Activities: Meetings, business dinners

[0549] server:

[0550] Analyzes past clothing photos and preferences to generate a formal style profile.

[0551] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[0552] The store offers warm and formal clothing, including wool coats, suits, and dress shoes, as well as items made from eco-friendly materials and local brands.

[0553] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[0554] User device:

[0555] The user is notified of the clothing list and belongings list sent from the server, and the user can confirm and adjust the list.

[0556] This system allows users to efficiently prepare for their trip and easily select the style that best suits their destination.

[0557] The processing flow will be explained below.

[0558] Step 1:

[0559] The user logs in to the application. The user uploads past clothing photos and preference information (color, material, design preferences, etc.) and enters detailed information into the input form. The user's device sends this data to the server.

[0560] Step 2:

[0561] The server inputs the received image data into an image analysis model to extract the user's style characteristics. At the same time, it inputs the text data into a natural language processing model to analyze preferences such as color and design. This generates a user profile and stores it in a database.

[0562] Step 3:

[0563] The user inputs travel information (destination, duration, planned activities) into the application, and the user terminal sends this information to the server.

[0564] Step 4:

[0565] Based on the submitted travel information, the server retrieves real-time weather data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API, stores the retrieved weather data in a database, and associates it with the user's travel information.

[0566] Step 5:

[0567] The server uses generative AI to create an optimal outfit list based on the user's profile, weather information, and cultural background. The generated outfit list includes items that are climate-appropriate and culturally appropriate, as well as recommendations for sustainable items and local brands.

[0568] Step 6:

[0569] The generated clothing suggestion list is sent from the server to the user's terminal and notified to the user, who can then review the suggested clothing list and make corrections or adjustments as necessary.

[0570] Step 7:

[0571] The server automatically generates a list of necessary items based on the recommended outfit. This list is intended to prevent duplication or shortages. The list is sent from the server to the user's device and notified to the user.

[0572] Step 8:

[0573] Using the user terminal, users can check their packing list and pack efficiently, allowing them to smoothly prepare for their trip.

[0574] Example 1

[0575] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0576] When traveling or on a business trip, selecting appropriate clothing and efficiently preparing belongings is a time-consuming and labor-intensive task. It is particularly difficult to select clothing that takes into account weather conditions and cultural backgrounds, and finding environmentally friendly items can be time-consuming. A convenient and effective system is needed to solve these problems.

[0577] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0578] In this invention, the server includes means for analyzing a user's past clothing photos and preferences to generate a personal style profile, means for acquiring the latest weather data for the travel destination and grasping climate information in real time, and means for integrating the weather data for the travel destination, the user's style profile, and cultural background and generating an appropriate clothing list using a generative AI model. This allows users to easily select clothing appropriate for the weather conditions and cultural background of their travel destination and efficiently prepare their belongings.

[0579] A "user" is an individual who uses this system and provides past clothing photos and preference data.

[0580] "Clothing photos" are images or photos of clothing worn by a user in the past.

[0581] A "style profile" is data that indicates a user's personal style and fashion trends, generated based on past clothing photos and preferences of the user.

[0582] "Weather data" refers to data that indicates information about the climate, such as the current and forecast weather and temperature at the travel destination.

[0583] "Real-time" refers to a method of data acquisition and processing that occurs nearly simultaneously with the present time.

[0584] "Cultural background" refers to information related to culture, such as customs, values, and typical styles in the region you are traveling to.

[0585] A "generative AI model" is an artificial intelligence model trained from large amounts of data, which is used to generate an appropriate outfit list by integrating a user's style profile, weather data, and cultural background.

[0586] A "packing list" is a list of items that a user needs to carry with them when traveling or on a business trip.

[0587] A "user terminal" is an electronic device, such as a smartphone or PC, that a user uses to access this system.

[0588] "Notification" is a means of communicating information to the user about the generated clothing list and belongings list.

[0589] "Eco-friendly fashion items" are clothing and accessories made using sustainable materials and processes that take into consideration their environmental impact.

[0590] MODE FOR CARRYING OUT THE INVENTION

[0591] The system of the present invention is designed to enable users planning a trip or business trip to efficiently select appropriate clothing and generate a packing list. The system includes a means for analyzing the user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination to understand climate information in real time, a means for suggesting appropriate clothing taking into account the culture and trends of the travel destination, a means for automatically generating a necessary packing list based on the suggested clothing, a means for providing support in preventing duplications and shortages when packing, and a means for recommending environmentally friendly fashion items.

[0592] To use this system, users use devices such as smartphones or PCs. First, they log in to the application, upload photos of their previous outfits, and enter their preferred styles, colors, and designs in the input form. This data is then sent from the device to the server.

[0593] The server analyzes the data using image analysis tools (e.g., OpenCV and TensorFlow) and natural language processing tools (e.g., NLTK and spaCy) to generate a style profile for the user, which is then stored in a database.

[0594] Next, the user inputs their travel destination, travel duration, and planned activities. This information is also sent to the server via the device. The server retrieves real-time weather data from external weather APIs (e.g., OpenWeatherMap API or Weatherstack API) and correlates it with the weather conditions at the travel destination.

[0595] The server provides the user's style profile, weather data, and cultural background as input data to a generative AI model (e.g., GPT-4) and sends a prompt. Specific examples of prompts are as follows:

[0596] "The user's style profile is casual. The travel destination is Tokyo, where the temperature is high and humidity is high in July. The primary focus is sightseeing. Please generate an optimal outfit list."

[0597] Based on these prompts, the generative AI model generates a list of appropriate outfits, which the server then sends to the user's device. The list includes items that match the user's preferences, as well as items suited to the climate and culture of the destination. It also suggests eco-friendly fashion items and local brand options.

[0598] The server then automatically generates a list of necessary items to bring based on the clothing list and sends it to the user's device, allowing the user to efficiently prepare for a trip or business trip and easily select appropriate clothing and items to bring.

[0599] For example, if a user is traveling to Tokyo in July, a casual T-shirt, shorts, and breathable sneakers will be recommended based on temperature and humidity information obtained from the weather API. Additional necessary items (e.g., sunscreen, hat, sunglasses, etc.) will also be automatically added to the recommended list. The device will notify the user of this information, allowing them to review and adjust the recommended list as needed.

[0600] The above is a specific embodiment for carrying out the present invention. This system allows the user to easily select clothing and items suitable for the weather and specific activities of the day.

[0601] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0602] Step 1: Collect user information

[0603] Users log in to the app, upload photos of their previous outfits, and enter their preferred styles, colors, and designs into an input form. The input data includes the outfit photo file and text information.

[0604] Specifically, users select a photo from their smartphone or computer, fill out the form with details about their style (e.g., "casual" or "formal"), and their preferred colors and design, and then press the "Submit" button.

[0605] Input: Clothing photo file, preferred style, color, design (text)

[0606] Output: User information dataset (photo files and text information)

[0607] Step 2: Send user data

[0608] The device packages the collected user data into packets and sends them to the server as HTTP requests.

[0609] In specific operation, the terminal transmits photo data and text data to the server via the network.

[0610] Input: User information dataset

[0611] Output: User information data sent to the server

[0612] Step 3: Generate a User Style Profile

[0613] The server analyzes the clothing photos using image analysis tools (e.g., OpenCV and TensorFlow) and analyzes the text data using natural language processing tools (e.g., NLTK and spaCy), generating a style profile for the user and storing it in a database.

[0614] In concrete terms, the server uses image recognition algorithms to extract style elements from photos and then integrates them with the results of analyzing text data to build a style profile.

[0615] Input: User information data (photo and text)

[0616] Output: Style profile (stored in database)

[0617] Step 4: Enter your destination information

[0618] The user enters the travel destination, travel duration, and planned activities into the application's travel information input form.

[0619] Specifically, the user fills in the form with "travel destination," "travel period," and "activities," and presses the "Submit" button.

[0620] Input: Travel destination, travel period, activities (text)

[0621] Output: Travel information dataset

[0622] Step 5: Obtaining Weather Data

[0623] The server sends a request to an external weather API (e.g., OpenWeatherMap API or Weatherstack API) to obtain real-time weather data for the travel destination.

[0624] In specific operation, the server sends an HTTP request to the API and receives the acquired weather data.

[0625] Input: Travel destination information (text)

[0626] Output: Real-time weather data

[0627] Step 6: Generate the outfit list

[0628] The server sends prompts to a generative AI model (e.g., GPT-4) that integrates the user's style profile, weather data, and cultural background, and the generative AI model generates a list of appropriate outfits.

[0629] Specifically, the AI ​​provides a prompt example that reads, "The user's style profile is casual. The travel destination is Tokyo, where the temperature and humidity are high in July. Sightseeing will be the main focus. Please generate a list of the most suitable outfits." The AI ​​then returns a list of T-shirts, shorts, sneakers, etc.

[0630] Input: Style profile, weather data, cultural background

[0631] Output: A list of the best outfits

[0632] Step 7: Generate a packing list

[0633] The server automatically generates an inventory list based on the generated clothing list, including any additional items required (e.g., sunscreen, sunglasses, etc.).

[0634] In particular, the server analyzes the clothing list and automatically adds related items (e.g., sunscreen for a T-shirt) to generate the list.

[0635] Input: Best Outfit List

[0636] Output: Inventory list

[0637] Step 8: Notification and confirmation of results

[0638] The device will then notify the user of the generated clothing and belongings list, which the user can review and adjust as necessary.

[0639] Specifically, the device will notify the user of the list via push or email notification, allowing them to view and adjust it within the app.

[0640] Input: List of suitable clothes, list of things to bring

[0641] Output: An interface to inform the user and allow them to review and adjust

[0642] (Application example 1)

[0643] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0644] In today's busy lifestyles, it is important for delivery workers to be equipped with the appropriate clothing and equipment to perform their deliveries efficiently and effectively. However, selecting the most appropriate clothing and equipment for each weather and cultural background is time-consuming and inefficient. Also, choosing eco-friendly items is a must. A system that solves these problems and allows delivery workers to perform their work smoothly is needed.

[0645] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0646] In this invention, the server includes means for analyzing past clothing photos and equipment and preferences of the user and delivery person to generate personal style and equipment profiles, means for obtaining the latest weather data for the travel destination and delivery area to grasp weather information in real time, means for suggesting clothing and equipment that matches the style taking into consideration the culture and trends of the travel destination and delivery area, and means for automatically generating a list of necessary items to bring based on the suggested clothing and equipment, thereby enabling delivery people to prepare efficiently and environmentally friendly.

[0647] "User" refers to an individual who uses the system to generate their own style profile and receive clothing and belongings suggestions.

[0648] "Delivery personnel" refers to personnel who use this system to receive suggestions on optimal clothing and equipment for performing tasks such as food delivery.

[0649] "Past clothing photos" are image data of clothing worn by users and delivery personnel in the past.

[0650] "Style profile" refers to information about a person's fashion style generated by analyzing past clothing photos and preferences of the user and delivery person.

[0651] "Weather data" refers to information such as the current and forecasted weather, temperature, humidity, etc. at the travel destination or delivery area.

[0652] "Culture and trends" refers to the customs and fashion trends of clothing and behavior in a particular region or society.

[0653] A "packing list" is an automatically generated list of necessary items to bring based on the suggested clothing and equipment.

[0654] "Environmentally friendly fashion items" refer to clothing, accessories, etc. that are made from eco-friendly materials and are intended to reduce the burden on the environment.

[0655] "Equipment Profile" refers to information about a delivery person's personal equipment generated by analyzing their past equipment and preferences.

[0656] "Means of understanding weather information in real time" refers to a method of obtaining the latest weather data from an external weather API to understand the weather conditions at the travel destination or delivery area in real time.

[0657] "Means for suggesting optimal clothing and equipment" refers to a method that uses AI to integrate personal profiles, climate information, and cultural backgrounds to suggest optimal clothing and equipment.

[0658] "Means for automatically generating a packing list" refers to a method for automatically generating a list of necessary packing items based on the suggested clothing and equipment.

[0659] "Delivery area" refers to the region or area in which a delivery person makes deliveries.

[0660] "Eco-friendly items" refer to products and equipment that are made using environmentally friendly materials and manufacturing processes.

[0661] The system for realizing this invention includes a server, a terminal, and a user. The roles and processes of each will be described in detail below.

[0662] Server Roles

[0663] The server first receives and analyzes data from users and delivery staff. Specifically, it handles the following data:

[0664] Image data of past photos of clothing and equipment of users and delivery personnel

[0665] Text data on the fashion and equipment preferences of users and delivery personnel

[0666] The server uses TensorFlow for image analysis and GPT-4 for analyzing text data of preferences, which generates a style profile and equipment profile for each individual. The server also uses an external weather API (OpenWeatherMap API) to obtain real-time weather information for travel destinations and delivery areas.

[0667] The server then integrates this data and uses a generative AI model to generate a list of optimal clothing and equipment, based on style profile, equipment profile, weather information, and cultural background.

[0668] Additionally, the server automatically generates a list of necessary items based on the generated clothing and equipment list, including eco-friendly items and local brand options in the process.

[0669] Device Role

[0670] The terminal functions as a user interface. First, the user or delivery person uploads photos of their previous outfits and their preferences, which are then sent to the server. The server then displays a list of optimal outfits and equipment, as well as a list of items to bring. The user or delivery person can review this information and make adjustments as necessary.

[0671] User Roles

[0672] The user inputs their own data into the terminal, receives suggestions from the server, and makes preparations based on them. Specifically, the user uses the system as follows:

[0673] 1. Upload past clothing photos and preferences to your device.

[0674] 2. Enter travel destination and delivery area information into the device.

[0675] 3. Check the suggested clothing and packing list and prepare accordingly.

[0676] Specific examples

[0677] Example 1: Rainy day delivery in Shibuya

[0678] User: Upload data on the delivery person's past preferences for waterproof jackets and shoes.

[0679] Server: Analyzes past photos of equipment and preferences to generate a profile. Checks the weather in Shibuya using the OpenWeatherMap API and suggests waterproof jackets, waterproof shoes, and rain bags for rainy days.

[0680] Terminal: Notifies the delivery person of the clothing list and belongings list sent from the server, and allows them to confirm and make adjustments.

[0681] Example prompts to be input to the generative AI model:

[0682] "Please suggest the best clothing and equipment for rainy days for food delivery in Shibuya. Delivery people prefer waterproof jackets and shoes. Also, please suggest eco-friendly items."

[0683] The system allows delivery personnel to prepare efficiently and environmentally, making it easy to select equipment appropriate for weather conditions and cultural backgrounds.

[0684] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0685] Step 1:

[0686] The user inputs past clothing photos and information about their preferences into the terminal. This data is sent from the terminal to the server as image data and text data. The input data includes information such as photos of clothing worn in the past, favorite colors, designs, and particularly favorite fashion styles.

[0687] Input: Past clothing photos (image data), preference information (text data)

[0688] Output: Send data to the server

[0689] Step 2:

[0690] The server analyzes the received data. First, it uses TensorFlow to analyze the image data and generate a style profile for the user. Then it uses GPT-4 to analyze the text data of user preferences and create a detailed profile of the individual's fashion style.

[0691] Input: Past clothing photos (image data), preference information (text data)

[0692] Output: Style Profile

[0693] Step 3:

[0694] The user inputs information about the travel destination and delivery area into the terminal, including the name of the destination, the duration, the planned activities and tasks, etc. This information is then sent to the server.

[0695] Input: Travel destination information, delivery area information (text data)

[0696] Output: Send data to the server

[0697] Step 4:

[0698] The server uses the OpenWeatherMap API to obtain real-time weather data for the entered travel destination and delivery area, and uses this information to understand the weather conditions of the travel destination and delivery area.

[0699] Input: Travel destination information, delivery area information (text data)

[0700] Output: Get real-time weather data

[0701] Step 5:

[0702] The server combines the acquired weather data with the generated style and equipment profiles, as well as the input cultural background and trend information. Based on this, a generative AI model (GPT-4) is used to generate the optimal outfit and equipment list. Eco-friendly items and local brand options are also taken into consideration.

[0703] Inputs: Style profile, equipment profile, real-time weather data, cultural context information

[0704] Output: Optimal clothing and equipment list

[0705] Step 6:

[0706] The server sends the generated list of optimal clothing and equipment to the device, which receives it and notifies the user. The user can then check the displayed list and make adjustments as necessary.

[0707] Input: Optimal clothing and equipment list

[0708] Output: Notification to terminal

[0709] Step 7:

[0710] The server automatically generates a list of necessary items to bring based on the suggested clothing and equipment, including eco-friendly items and local brand options, and sends the list to the device and notifies the user.

[0711] Input: Optimal clothing and equipment list

[0712] Output: Generates and notifies inventory list

[0713] Example prompt

[0714] "Please suggest the best clothing and equipment for rainy days for food delivery in Shibuya. Delivery people prefer waterproof jackets and shoes. Also, please suggest eco-friendly items."

[0715] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0716] MODE FOR CARRYING OUT THE INVENTION

[0717] The system of the present invention combines a means for analyzing a user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination and understanding climate information in real time, a means for suggesting clothing that matches the style taking into consideration the culture and trends of the travel destination, a means for automatically generating a list of necessary items to bring based on the suggested clothing, a means for supporting the user in preventing duplication or shortages when packing, a means for recommending environmentally friendly fashion items, and an emotion engine that recognizes the user's emotions.

[0718] Program processing and explanation

[0719] Generate a style profile

[0720] When a user logs in to the application, they first upload photos of their previous outfits and their preferences (color, design, etc.), then enter their details into an input form. The device then sends this data to the server.

[0721] The server uses an image analysis model to extract the user's style characteristics from the uploaded image data. At the same time, it uses a natural language processing model to analyze the text data and identify specific preferences for color, design, material, etc. Based on this information, the server creates a user profile and stores it in a database. This clarifies the user's past style information and preferences.

[0722] Obtaining travel information

[0723] After the user inputs the travel destination information, the user's device then transmits the travel destination, travel period, and planned activities to the server. Based on the received information, the server obtains real-time weather data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API, stores this weather data in a database, and associates it with the user's travel information.

[0724] Generating recommendations

[0725] The server uses generative AI to create an optimal outfit list based on the user's profile, weather information, and cultural background. The generated outfit list includes items that are appropriate for the weather conditions as well as culturally appropriate items. The emotion engine also assesses the user's emotional state at that time and can suggest outfits that are more psychologically satisfying. The recommendations also include environmentally friendly items and local brand options.

[0726] Generate suggestions and packing lists

[0727] The generated clothing suggestion list is sent from the server to the user's device and notified to the user. The user can check the suggested list and make adjustments as necessary. Based on the list, the server automatically generates a list of necessary items to bring, which is also sent to the user's device and notified to the user.

[0728] Specific examples

[0729] Example 1: Summer trip to Tokyo (casual style)

[0730] user:

[0731] He likes a casual style and owns T-shirts, shorts, and sneakers.

[0732] Travel information:

[0733] Travel destination: Tokyo

[0734] Period: July 20th to July 25th

[0735] Activities: Sightseeing, shopping, cafe hopping

[0736] server:

[0737] Analyzes past clothing photos and preferences to generate a casual style profile.

[0738] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were high.

[0739] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[0740] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[0741] An emotional engine assesses the user's emotional state and reflects this in the selection of suggested items.

[0742] User device:

[0743] You can check the clothing and item lists sent from the server and make adjustments as needed.

[0744] Example 2: Winter business trip to New York (formal style)

[0745] user:

[0746] He prefers a formal yet business casual style, and his personal belongings include suits, dress shoes, and coats.

[0747] Travel information:

[0748] Travel destination: New York

[0749] Period: December 1st to December 5th

[0750] Activities: Meetings, business dinners

[0751] server:

[0752] Analyzes past clothing photos and preferences to generate a formal style profile.

[0753] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[0754] The site offers warm and formal clothing such as wool coats, suits, and dress shoes, and also recommends items made from eco-friendly materials and local brands.

[0755] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[0756] An emotional engine assesses the user's emotional state and reflects this in the selection of suggested items.

[0757] User device:

[0758] You can check the clothing and item lists sent from the server and make adjustments as needed.

[0759] This system allows users to efficiently prepare for their trip, easily select a style that suits their destination, and provides a more fulfilling travel experience by taking into account the user's emotional state.

[0760] The processing flow will be explained below.

[0761] Step 1:

[0762] The user logs in to the application. First, the user uploads photos of their previous outfits and their preferred information (color, design, etc.), and then enters the details into an input form. The user's device sends this data to the server.

[0763] Step 2:

[0764] The server inputs the received image data into an image analysis model to extract the user's style characteristics. At the same time, it inputs the received text data into a natural language processing model to analyze color and design preferences. The server then generates a user profile based on these analysis results and stores it in a database.

[0765] Step 3:

[0766] The user inputs travel information (travel destination, duration, planned activities) into the application. The user terminal sends this information to the server, which stores it in a database.

[0767] Step 4:

[0768] The server retrieves real-time weather data for the travel destination from an external weather API based on the submitted travel information, stores the retrieved weather data in a database, and associates it with the user's travel information.

[0769] Step 5:

[0770] The server integrates user profiles, climate information, and cultural backgrounds, and uses generative AI to create an optimal outfit list, which includes items suitable for the weather conditions, culturally compatible items, and eco-friendly fashion items.

[0771] Step 6:

[0772] The server uses an emotion engine to evaluate the user's emotional state in real time, and based on the results, dynamically adjusts the outfit list to suggest outfits that suit the user's emotions.

[0773] Step 7:

[0774] The generated clothing suggestion list is sent from the server to the user's terminal and notified to the user, who can then check the suggested clothing list and make adjustments as necessary.

[0775] Step 8:

[0776] The server automatically generates a list of necessary items based on the recommended outfits, and the list is sent from the server to the user's device and notified to the user.

[0777] Step 9:

[0778] Users can check their packing list on their device and pack efficiently, allowing them to smoothly prepare for their trip.

[0779] Specific examples

[0780] Example 1: Summer trip to Tokyo

[0781] user:

[0782] He prefers a casual style and his personal items include t-shirts, shorts, and sneakers.

[0783] Travel information:

[0784] Travel destination: Tokyo

[0785] Period: July 20th to July 25th

[0786] Activities: Sightseeing, shopping, cafe hopping

[0787] Step 1:

[0788] The user logs in, uploads photos of past outfits, and enters their casual preferences. The user's device sends the data to the server.

[0789] Step 2:

[0790] The server performs image analysis and natural language processing to generate and store user profiles.

[0791] Step 3:

[0792] The user enters travel information for Tokyo, July 20th to July 25th, sightseeing and shopping, and the user's device sends the data to the server.

[0793] Step 4:

[0794] The server collects real-time weather data for Tokyo and stores it in a database.

[0795] Step 5:

[0796] The server uses generated AI to create a list of outfits, such as a T-shirt, shorts, and breathable sneakers.

[0797] Step 6:

[0798] The sentiment engine evaluates the user's emotions and adjusts the listing to enhance the travel experience.

[0799] Step 7:

[0800] The server transmits the clothing list to the user terminal, and the user checks the list.

[0801] Step 8:

[0802] The server generates a list of belongings and transmits it to the user terminal.

[0803] Step 9:

[0804] The user checks the list of belongings and packs.

[0805] Example 2: Winter business trip to New York

[0806] user:

[0807] He prefers a formal yet business casual style, and his personal belongings include a suit, dress shoes, and coat.

[0808] Travel information:

[0809] Travel destination: New York

[0810] Period: December 1st to December 5th

[0811] Activities: Meetings, business dinners

[0812] Step 1:

[0813] The user logs in, uploads photos of past outfits, and enters their formal preferences. The user's device sends the data to the server.

[0814] Step 2:

[0815] The server performs image analysis and natural language processing to generate and store user profiles.

[0816] Step 3:

[0817] The user enters travel information such as New York, December 1st to December 5th, meeting and business dinner, and the user terminal sends the data to the server.

[0818] Step 4:

[0819] The server retrieves real-time weather data for New York and stores it in a database.

[0820] Step 5:

[0821] The server uses generated AI to create a list of clothing items such as wool coats, suits, and dress shoes.

[0822] Step 6:

[0823] An emotion engine assesses the user's emotions and tailors the list to ease tension in business meetings.

[0824] Step 7:

[0825] The server transmits the clothing list to the user terminal, and the user checks the list.

[0826] Step 8:

[0827] The server generates a list of belongings and transmits it to the user terminal.

[0828] Step 9:

[0829] The user checks the list of belongings and packs.

[0830] Example 2

[0831] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0832] Modern travelers need to choose appropriate clothing, taking into account the climate, culture, and trends of their destination. Automatically generating a packing list and incorporating environmental considerations and personal emotional state is a time-consuming and labor-intensive task. Conventional systems were unable to perform these processes efficiently and comprehensively, placing a heavy burden on travel preparation.

[0833] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing the user's past clothing photos and preferences to generate a personal style profile, a means for acquiring the latest weather data for the travel destination and understanding the weather information in real time, and a means for evaluating the user's emotional state and suggesting optimal clothing based on the evaluation. This allows travelers to efficiently prepare for their trip and select appropriate clothing that suits the climate and culture.

[0834] "User" refers to an individual who uses the system to prepare for a trip or select fashion.

[0835] "Past clothing photos" refer to photos of clothing previously worn by a user, and are data used to generate a style profile.

[0836] "Preferences" refers to information about the user's preferred fashion style, color, design, and material.

[0837] A "style profile" is data that represents a user's personal fashion trends and is generated based on the user's past clothing photos and preferences.

[0838] "Travel Destination" refers to the place that the User intends to visit.

[0839] "Weather data" refers to real-time weather information such as weather forecast, temperature, and humidity at your travel destination.

[0840] "Culture" refers to the social, historical, and regional background of a travel destination, and is a factor that influences clothing choices.

[0841] "Trends" refers to the latest fashions and trends in the destination.

[0842] A "packing list" refers to a list of items needed for a trip based on a suggested outfit.

[0843] "Duplicates and shortages" refers to users packing multiple items of the same kind, or leaving on a trip without an important item.

[0844] "Eco-conscious fashion items" refer to clothing and accessories made from sustainable materials and eco-friendly manufacturing methods.

[0845] "Emotional state" refers to the result of an assessment of the user's current psychological state.

[0846] "Recommendations" refers to a list of the best clothing and items to bring based on analyzed data.

[0847] "Generative AI" refers to an artificial intelligence model trained on a large dataset, which is used here to generate the outfit list.

[0848] This invention is a system that streamlines travel preparation for users and suggests clothing appropriate for the climate and culture. This system is composed of interactions between a server, a terminal, and a user. The specific processing procedures and technologies used are described below.

[0849] Generate a style profile

[0850] When a user logs in to the application, they first upload previous clothing photos and personal preferences, and then enter their details. This includes preferences for color, design, and materials. The device then sends this data to the server. The server then uses an image analysis model (e.g., Google Cloud Vision API) to extract the user's style features from the uploaded image data. At the same time, it uses a natural language processing model (e.g., BERT) to analyze the text data and understand the user's preferences. Based on these analysis results, the server creates a user profile and stores it in a database.

[0851] Obtaining travel information

[0852] When a user inputs travel destination information, the device sends the travel destination, travel duration, and planned activities to the server. Based on the received information, the server retrieves real-time climate data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API (e.g., OpenWeatherMap API). The retrieved climate data is stored in a database and associated with the user's travel information.

[0853] Generating recommendations

[0854] The server uses a generative AI model (e.g., GPT-4) to generate an optimal outfit list based on the user profile, weather information, and cultural background. This outfit list includes items appropriate for the weather conditions as well as culturally appropriate items. It also uses an emotion engine (e.g., Azure Emotion API) to evaluate the user's emotional state at that time and suggests outfits based on that emotional state. Furthermore, recommendations can also include eco-friendly items and local brand options.

[0855] Generate suggestions and packing lists

[0856] The generated clothing suggestion list is sent from the server to the user's device and notified to the user. The user can review the suggested list and make adjustments as necessary. For example, they can exclude specific items or request additional items. Based on this, the server automatically generates a list of necessary items to bring. This list is also sent to the user's device and notified to the user.

[0857] Specific examples

[0858] Example 1: Summer trip to Tokyo (casual style)

[0859] User: Prefers casual style and owns T-shirts, shorts, and sneakers.

[0860] Travel Information: Destination: Tokyo, Period: July 20th - July 25th, Activities: Sightseeing, Shopping, Cafe Hopping

[0861] server:

[0862] Analyzes past clothing photos and preferences to generate a casual style profile.

[0863] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were high.

[0864] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[0865] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[0866] An emotional engine assesses the user's emotional state and reflects it in the selection of suggested items.

[0867] User device: Check the clothing list and belongings list sent from the server and make adjustments as necessary.

[0868] Example 2: Winter business trip to New York (formal style)

[0869] User: Prefers a formal yet business casual style and owns a suit, dress shoes, coat, etc.

[0870] Travel Information: Destination: New York, Period: December 1st - December 5th, Activities: Meetings, Business Dinner

[0871] server:

[0872] Analyzes past clothing photos and preferences to generate a formal style profile.

[0873] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[0874] The site offers warm and formal clothing such as wool coats, suits, and dress shoes, and also recommends items made from eco-friendly materials and local brands.

[0875] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[0876] An emotional engine assesses the user's emotional state and reflects it in the selection of suggested items.

[0877] User device: Check the clothing list and belongings list sent from the server and make adjustments as necessary.

[0878] Prompt Sentence Examples

[0879] Example prompt 1:

[0880] Based on the user's style profile, suggest a casual outfit list for a trip to Tokyo in July. The weather is hot and humid, and the user's past clothing data indicates that they prefer T-shirts, shorts, and sneakers. Include items made from eco-friendly materials and local brands.

[0881] Example prompt 2:

[0882] Generate an appropriate attire list for a business meeting and dinner in New York in December for a user who prefers a formal yet business casual style. The weather will be cold and likely to snow. Include items made from eco-friendly materials and local brands.

[0883] This system allows users to efficiently prepare for their trip, easily select a style that suits their destination, and provides a more fulfilling travel experience by taking into account the user's emotional state.

[0884] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0885] Step 1: A user logs in to the application and uploads photos of their previous outfits and their preferences.

[0886] Input: User ID, past clothing photos, and text information of your preferences (color, design, material, etc.).

[0887] How it works: A user logs into the application, selects a photo of an outfit from a previous outfit, and fills out a form with their preferences.

[0888] Output: The device sends these data to the server.

[0889] Step 2: The server analyzes the data using image analysis and natural language processing models to generate a style profile.

[0890] Input: Clothing photo data, text information of user preferences.

[0891] How it works: The server uses an image analysis model (e.g., Google Cloud Vision API) to extract clothing features (e.g., color, shape, material) from the photo, and simultaneously analyzes the text information using a natural language processing model (e.g., BERT).

[0892] Data processing / calculation: Extract the characteristics of fashion items through image data analysis, and analyze preferences from text data.

[0893] Output: A style profile generated based on the analysis results, which is stored in a database.

[0894] Step 3: The user inputs the travel destination information, and the terminal sends the information to the server.

[0895] Input: Travel destination, travel duration, planned activities.

[0896] Action: A user fills out a travel destination information form and presses the submit button.

[0897] Output: The device sends this travel destination information to the server.

[0898] Step 4: The server retrieves the weather data and stores it in a database.

[0899] Input: Travel destination information (destination, duration).

[0900] How it works: The server uses a weather API (e.g. OpenWeatherMap API) to get real-time weather data.

[0901] Data processing / calculation: Call the API, analyze the acquired data, and save information such as weather forecast, temperature, and humidity in a database.

[0902] Output: Weather data is stored in a database and linked to the user's travel information.

[0903] Step 5: The server uses the generative AI model to generate the optimal outfit list.

[0904] Input: User profile, destination climate data, cultural background.

[0905] How it works: The server uses a generative AI model (e.g., GPT-4) to generate an outfit list based on the input data, and an emotion engine (e.g., Azure Emotion API) to assess the user's current emotional state.

[0906] Data processing / calculation: Combining the user's past data with real-time weather data and cultural background, the system generates an optimal outfit list. It also takes into account emotional data.

[0907] Output: The generated outfit list, which is provided to the user as a suggestion list.

[0908] Step 6: The server automatically generates a list of items to bring based on the suggested clothing list.

[0909] Input: Generated outfit list.

[0910] How it works: The server automatically lists the necessary items based on the clothing list.

[0911] Data processing / calculation: Analyze the suggested clothing items and select the necessary items based on them.

[0912] Output: An automatically generated inventory list, which is sent to the user's device.

[0913] Step 7: The user terminal notifies the user of the clothing list and belongings list, and the user confirms and adjusts them.

[0914] Input: Outfit list and inventory list sent from the server.

[0915] Action: The user device presents the list to the user, who can review it and make adjustments as needed, for example, adding or removing specific items.

[0916] Output: Finalized outfit and packing list.

[0917] (Application example 2)

[0918] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0919] Traditionally, food delivery services have struggled to suggest the best dishes to suit a user's style, mood, and climate. They also lacked the functionality to recommend environmentally friendly ingredients and local brands, which resulted in an unsatisfactory user experience. Therefore, there is a need for a system that provides food delivery options that take into account a user's style, mood, climate, and environmental considerations.

[0920] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0921] In this invention, the server includes means for analyzing a user's past clothing photos and preferences to generate a personal style profile, means for acquiring the latest weather data for the user's current location to grasp climate information in real time, means for integrating the generated style profile with the climate information and cultural background to propose optimal food delivery options, means for automatically generating an optimal dish list based on the proposed food delivery options, and means for recommending dishes made with environmentally friendly ingredients and local brands, thereby making it possible to provide optimal food delivery options that suit the user's style, mood, and climate.

[0922] "Photos of the user's past clothing" are photos of clothing worn by the user in the past, and are data for generating a style profile.

[0923] "Preferences" refers to the user's fashion-related preferences, such as favorite colors, designs, and materials.

[0924] A "style profile" refers to the results of an analysis of a user's personal fashion style based on past clothing photos and preferences.

[0925] "Weather data" refers to information related to the climate, such as temperature, humidity, and weather forecasts, and is data that can be obtained in real time.

[0926] "Means for grasping weather information in real time" refers to a means for quickly obtaining the latest weather data and accurately grasping the weather conditions at the user's current location.

[0927] "Food delivery options" refers to the types of food and restaurants available for delivery, and are used to fulfill a customer's order.

[0928] "Dish List" means a list of specific dishes based on a proposed food delivery option.

[0929] "Environmentally conscious ingredients" are sustainable ingredients selected to contribute to environmental protection.

[0930] "Locally branded cuisine" refers to food and drink produced and served within a region, reflecting local culture and flavors.

[0931] A "generative AI model" is an artificial intelligence model that generates natural language and images based on input data.

[0932] A "prompt" is an instruction given to a generative AI model to obtain an appropriate output.

[0933] This invention is a system that generates a personal style profile based on the user's past clothing photos and preferences, and also obtains the latest weather data to suggest optimal options for food delivery services. The system is implemented by a user terminal and a server working together.

[0934] Program processing explanation

[0935] 1. Create a user profile

[0936] The user's device uploads photos of their previous clothing and their preferences to the application. The uploaded data is analyzed using an image analysis model (TensorFlow or PyTorch) to extract the user's fashion style characteristics. In addition, text information about the user's preferences is analyzed using a natural language processing model (such as BERT). Based on these analysis results, the server generates the user's style profile and stores it in a cloud database (such as Firebase).

[0937] 2. Obtaining weather information

[0938] The user's device acquires their current location information and sends it to the server. The server then retrieves real-time weather data from a weather data API (such as OpenWeatherMap) based on the location information. This weather data is stored in a cloud database and associated with the user's style profile.

[0939] 3. Generating Recommendations

[0940] The server integrates the generated style profile with weather data and uses a generative AI model (such as GPT-3) to suggest optimal food delivery options. The generated list includes meal options that suit the user's current style and weather conditions, allowing them to choose the best dishes to suit their mood and environment.

[0941] 4. Suggestions and Notifications

[0942] The generated food list is sent from the server to the user's device and notified to the user. The user can review the suggested dish list and make adjustments as necessary. This allows the user to order the meal that best suits their mood and environment that day.

[0943] Specific examples

[0944] Example 1: Lunch on a hot summer day (casual style)

[0945] User: Prefers casual style and has often worn T-shirts and shorts in the past.

[0946] Current location and climate: Tokyo, July, temperature 35°C, humidity 75%

[0947] session:

[0948] The user's device uploads past clothing photos and preferences to the server.

[0949] The server generates a style profile using image analysis and natural language processing.

[0950] The server uses a weather data API to obtain weather information for the current location.

[0951] A generative AI model (GPT-3) generates suggestions such as cold drinks and light salads.

[0952] A list of suggested foods is sent to the user's device, such as chilled salad, iced latte, and chilled tofu.

[0953] Example prompt: "Please suggest some dishes that would make you feel casual in Tokyo during the summer. The user's preference is casual, and the days are often hot."

[0954] Example 2: Winter evening dinner (formal style)

[0955] User: Prefers formal style and has worn suits and coats many times in the past.

[0956] Current location and climate: New York, December, 0°C, snow

[0957] session:

[0958] The user's device uploads past clothing photos and preferences to the server.

[0959] The server generates a style profile using image analysis and natural language processing.

[0960] The server uses a weather data API to obtain weather information for the current location.

[0961] A generative AI model (GPT-3) generates suggestions for hot soups, stews, and other dishes.

[0962] A list of suggested foods is sent to the user's device, such as tomato soup, a glass of wine, and warm bread.

[0963] Example prompt: "What are some recommendations for a formal winter dinner in New York? Something suitable for a cold or snowy day would be good."

[0964] In this way, our system can provide optimal food delivery options by integrating a user's past clothing photos and preferences with current weather information and using a generative AI model, allowing users to enjoy the food that best suits their mood and environment.

[0965] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0966] Step 1:

[0967] When a user logs in to the application, the user's device uploads past clothing photos and preference data. The user enters past clothing photos (image files) and text information about preferences (color, design, material, etc.) into an input form. The uploaded data is sent to the server. (Input): Past clothing photos, text information about the user's preferences (Output): Data sent to the server

[0968] Step 2:

[0969] The server performs image analysis based on the received data. The image analysis model (TensorFlow or PyTorch) analyzes the uploaded image file and extracts the user's style characteristics (type of clothing, color, design, material, etc.). At the same time, a natural language processing model (BERT, etc.) analyzes the text information to specifically understand the user's preferences. (Input): Uploaded image file and text information (Output): Analysis results of style characteristics and preferences

[0970] Step 3:

[0971] The server generates a style profile for the user based on the analysis results. The style profile integrates data extracted from the user's past clothing photos and preferences, and clearly indicates the user's fashion trends. The generated style profile is stored in a cloud database (such as Firebase). (Input): Analysis results of style features and preferences (Output): Generated style profile

[0972] Step 4:

[0973] The user device acquires the user's current location information and sends it to the server. The server uses a weather data API (such as OpenWeatherMap) based on the received current location information to acquire real-time weather data (temperature, humidity, weather forecast, etc.). The acquired weather data is stored in a cloud database and associated with the user's style profile. (Input): Current location information (Output): Acquired weather data

[0974] Step 5:

[0975] The server combines the generated style profile with weather data and generates optimal food delivery options using a generative AI model (such as GPT-3). The generative AI model creates an optimal dish list based on the user's mood, style, and climate based on the prompt. (Input): Style profile, weather data, prompt (Output): Optimal food delivery options

[0976] Step 6:

[0977] The server sends the generated food list to the user's device and notifies the user. The user can review the proposed food list and make adjustments as necessary. The final adjusted list is sent back to the server, and the necessary information is stored in the cloud database. (Input): Generated food list (Output): Food list sent to the user's device

[0978] This allows users to choose the dish that best suits their mood and the environment at the time and enjoy a comfortable meal.

[0979] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0980] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0981] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0982] [Third embodiment]

[0983] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0984] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0985] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0986] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0987] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0988] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0989] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0990] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0991] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0992] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0993] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0994] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0995] MODE FOR CARRYING OUT THE INVENTION

[0996] The system of the present invention includes a means for analyzing a user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination and understanding climate information in real time, a means for suggesting clothing that matches the style taking into account the culture and trends of the travel destination, a means for automatically generating a list of necessary items to bring based on the suggested clothing, a means for supporting the user in preventing duplication or shortages when packing, and a means for recommending environmentally friendly fashion items.

[0997] Program processing and explanation

[0998] When a user logs in to the app, they first upload photos of their previous outfits and their preferences (color, design, etc.), then enter the details in an input form. The device then sends this data to the server.

[0999] The server uses image analysis and natural language processing to generate a style profile for the user and stores it in a database, revealing the user's past style information and preferences.

[1000] After the user inputs the travel destination information, the user device sends the travel destination, travel duration, and planned activities to the server, which then retrieves real-time weather data from an external weather API and associates it with the weather conditions of the travel destination.

[1001] The server combines the user profile with the destination's climate and cultural background, and uses generative AI to create an optimal outfit list. This list includes not only weather-appropriate clothing but also culturally appropriate clothing. It also includes recommendations for environmentally friendly items and local brands.

[1002] The generated clothing list is sent to the user's device and notified to the user, who can then review the list and make adjustments as necessary.

[1003] Next, the server automatically generates a list of necessary items based on the recommended outfit. This list is used to prevent duplication or shortages when packing. The list is also sent to the user's device and notified to the user.

[1004] Specific examples

[1005] Example 1: Summer trip to Tokyo

[1006] user:

[1007] He likes old photos of his outfits and casual styles. His personal items include T-shirts, shorts, and sneakers.

[1008] Travel information:

[1009] Travel destination: Tokyo

[1010] Period: July 20th to July 25th

[1011] Activities: Sightseeing, shopping, cafe hopping

[1012] server:

[1013] Analyzes past clothing photos and preferences to generate a casual style profile.

[1014] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were both high.

[1015] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[1016] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[1017] User device:

[1018] The user is notified of the clothing list and belongings list sent from the server, and the user can confirm and adjust the list.

[1019] Example 2: Winter business trip to New York

[1020] user:

[1021] He prefers a formal yet business casual style, and owns a suit, dress shoes, and coat.

[1022] Travel information:

[1023] Travel destination: New York

[1024] Period: December 1st to December 5th

[1025] Activities: Meetings, business dinners

[1026] server:

[1027] Analyzes past clothing photos and preferences to generate a formal style profile.

[1028] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[1029] The store offers warm and formal clothing, including wool coats, suits, and dress shoes, as well as items made from eco-friendly materials and local brands.

[1030] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[1031] User device:

[1032] The user is notified of the clothing list and belongings list sent from the server, and the user can confirm and adjust the list.

[1033] This system allows users to efficiently prepare for their trip and easily select the style that best suits their destination.

[1034] The processing flow will be explained below.

[1035] Step 1:

[1036] The user logs in to the application. The user uploads past clothing photos and preference information (color, material, design preferences, etc.) and enters detailed information into the input form. The user's device sends this data to the server.

[1037] Step 2:

[1038] The server inputs the received image data into an image analysis model to extract the user's style characteristics. At the same time, it inputs the text data into a natural language processing model to analyze preferences such as color and design. This generates a user profile and stores it in a database.

[1039] Step 3:

[1040] The user inputs travel information (destination, duration, planned activities) into the application, and the user terminal sends this information to the server.

[1041] Step 4:

[1042] Based on the submitted travel information, the server retrieves real-time weather data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API, stores the retrieved weather data in a database, and associates it with the user's travel information.

[1043] Step 5:

[1044] The server uses generative AI to create an optimal outfit list based on the user's profile, weather information, and cultural background. The generated outfit list includes items that are climate-appropriate and culturally appropriate, as well as recommendations for sustainable items and local brands.

[1045] Step 6:

[1046] The generated clothing suggestion list is sent from the server to the user's terminal and notified to the user, who can then review the suggested clothing list and make corrections or adjustments as necessary.

[1047] Step 7:

[1048] The server automatically generates a list of necessary items based on the recommended outfit. This list is intended to prevent duplication or shortages. The list is sent from the server to the user's device and notified to the user.

[1049] Step 8:

[1050] Using the user terminal, users can check their packing list and pack efficiently, allowing them to smoothly prepare for their trip.

[1051] Example 1

[1052] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1053] When traveling or on a business trip, selecting appropriate clothing and efficiently preparing belongings is a time-consuming and labor-intensive task. It is particularly difficult to select clothing that takes into account weather conditions and cultural backgrounds, and finding environmentally friendly items can be time-consuming. A convenient and effective system is needed to solve these problems.

[1054] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1055] In this invention, the server includes means for analyzing a user's past clothing photos and preferences to generate a personal style profile, means for acquiring the latest weather data for the travel destination and grasping climate information in real time, and means for integrating the weather data for the travel destination, the user's style profile, and cultural background and generating an appropriate clothing list using a generative AI model. This allows users to easily select clothing appropriate for the weather conditions and cultural background of their travel destination and efficiently prepare their belongings.

[1056] A "user" is an individual who uses this system and provides past clothing photos and preference data.

[1057] "Clothing photos" are images or photos of clothing worn by a user in the past.

[1058] A "style profile" is data that indicates a user's personal style and fashion trends, generated based on past clothing photos and preferences of the user.

[1059] "Weather data" refers to data that indicates information about the climate, such as the current and forecast weather and temperature at the travel destination.

[1060] "Real-time" refers to a method of data acquisition and processing that occurs nearly simultaneously with the present time.

[1061] "Cultural background" refers to information related to culture, such as customs, values, and typical styles in the region you are traveling to.

[1062] A "generative AI model" is an artificial intelligence model trained from large amounts of data, which is used to generate an appropriate outfit list by integrating a user's style profile, weather data, and cultural background.

[1063] A "packing list" is a list of items that a user needs to carry with them when traveling or on a business trip.

[1064] A "user terminal" is an electronic device, such as a smartphone or PC, that a user uses to access this system.

[1065] "Notification" is a means of communicating information to the user about the generated clothing list and belongings list.

[1066] "Eco-friendly fashion items" are clothing and accessories made using sustainable materials and processes that take into consideration their environmental impact.

[1067] MODE FOR CARRYING OUT THE INVENTION

[1068] The system of the present invention is designed to enable users planning a trip or business trip to efficiently select appropriate clothing and generate a packing list. The system includes a means for analyzing the user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination to understand climate information in real time, a means for suggesting appropriate clothing taking into account the culture and trends of the travel destination, a means for automatically generating a necessary packing list based on the suggested clothing, a means for providing support in preventing duplications and shortages when packing, and a means for recommending environmentally friendly fashion items.

[1069] To use this system, users use devices such as smartphones or PCs. First, they log in to the application, upload photos of their previous outfits, and enter their preferred styles, colors, and designs in the input form. This data is then sent from the device to the server.

[1070] The server analyzes the data using image analysis tools (e.g., OpenCV and TensorFlow) and natural language processing tools (e.g., NLTK and spaCy) to generate a style profile for the user, which is then stored in a database.

[1071] Next, the user inputs their travel destination, travel duration, and planned activities. This information is also sent to the server via the device. The server retrieves real-time weather data from external weather APIs (e.g., OpenWeatherMap API or Weatherstack API) and correlates it with the weather conditions at the travel destination.

[1072] The server provides the user's style profile, weather data, and cultural background as input data to a generative AI model (e.g., GPT-4) and sends a prompt. Specific examples of prompts are as follows:

[1073] "The user's style profile is casual. The travel destination is Tokyo, where the temperature is high and humidity is high in July. The primary focus is sightseeing. Please generate an optimal outfit list."

[1074] Based on these prompts, the generative AI model generates a list of appropriate outfits, which the server then sends to the user's device. The list includes items that match the user's preferences, as well as items suited to the climate and culture of the destination. It also suggests eco-friendly fashion items and local brand options.

[1075] The server then automatically generates a list of necessary items to bring based on the clothing list and sends it to the user's device, allowing the user to efficiently prepare for a trip or business trip and easily select appropriate clothing and items to bring.

[1076] For example, if a user is traveling to Tokyo in July, a casual T-shirt, shorts, and breathable sneakers will be recommended based on temperature and humidity information obtained from the weather API. Additional necessary items (e.g., sunscreen, hat, sunglasses, etc.) will also be automatically added to the recommended list. The device will notify the user of this information, allowing them to review and adjust the recommended list as needed.

[1077] The above is a specific embodiment for carrying out the present invention. This system allows the user to easily select clothing and items suitable for the weather and specific activities of the day.

[1078] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1079] Step 1: Collect user information

[1080] Users log in to the app, upload photos of their previous outfits, and enter their preferred styles, colors, and designs into an input form. The input data includes the outfit photo file and text information.

[1081] Specifically, users select a photo from their smartphone or computer, fill out the form with details about their style (e.g., "casual" or "formal"), and their preferred colors and design, and then press the "Submit" button.

[1082] Input: Clothing photo file, preferred style, color, design (text)

[1083] Output: User information dataset (photo files and text information)

[1084] Step 2: Send user data

[1085] The device packages the collected user data into packets and sends them to the server as HTTP requests.

[1086] In specific operation, the terminal transmits photo data and text data to the server via the network.

[1087] Input: User information dataset

[1088] Output: User information data sent to the server

[1089] Step 3: Generate a User Style Profile

[1090] The server analyzes the clothing photos using image analysis tools (e.g., OpenCV and TensorFlow) and analyzes the text data using natural language processing tools (e.g., NLTK and spaCy), generating a style profile for the user and storing it in a database.

[1091] In concrete terms, the server uses image recognition algorithms to extract style elements from photos and then integrates them with the results of analyzing text data to build a style profile.

[1092] Input: User information data (photo and text)

[1093] Output: Style profile (stored in database)

[1094] Step 4: Enter your destination information

[1095] The user enters the travel destination, travel duration, and planned activities into the application's travel information input form.

[1096] Specifically, the user fills in the form with "travel destination," "travel period," and "activities," and presses the "Submit" button.

[1097] Input: Travel destination, travel period, activities (text)

[1098] Output: Travel information dataset

[1099] Step 5: Obtaining Weather Data

[1100] The server sends a request to an external weather API (e.g., OpenWeatherMap API or Weatherstack API) to obtain real-time weather data for the travel destination.

[1101] In specific operation, the server sends an HTTP request to the API and receives the acquired weather data.

[1102] Input: Travel destination information (text)

[1103] Output: Real-time weather data

[1104] Step 6: Generate the outfit list

[1105] The server sends prompts to a generative AI model (e.g., GPT-4) that integrates the user's style profile, weather data, and cultural background, and the generative AI model generates a list of appropriate outfits.

[1106] Specifically, the AI ​​provides a prompt example that reads, "The user's style profile is casual. The travel destination is Tokyo, where the temperature and humidity are high in July. Sightseeing will be the main focus. Please generate a list of the most suitable outfits." The AI ​​then returns a list of T-shirts, shorts, sneakers, etc.

[1107] Input: Style profile, weather data, cultural background

[1108] Output: A list of the best outfits

[1109] Step 7: Generate a packing list

[1110] The server automatically generates an inventory list based on the generated clothing list, including any additional items required (e.g., sunscreen, sunglasses, etc.).

[1111] In particular, the server analyzes the clothing list and automatically adds related items (e.g., sunscreen for a T-shirt) to generate the list.

[1112] Input: Best Outfit List

[1113] Output: Inventory list

[1114] Step 8: Notification and confirmation of results

[1115] The device will then notify the user of the generated clothing and belongings list, which the user can review and adjust as necessary.

[1116] Specifically, the device will notify the user of the list via push or email notification, allowing them to view and adjust it within the app.

[1117] Input: List of suitable clothes, list of things to bring

[1118] Output: An interface to inform the user and allow them to review and adjust

[1119] (Application example 1)

[1120] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1121] In today's busy lifestyles, it is important for delivery workers to be equipped with the appropriate clothing and equipment to perform their deliveries efficiently and effectively. However, selecting the most appropriate clothing and equipment for each weather and cultural background is time-consuming and inefficient. Also, choosing eco-friendly items is a must. A system that solves these problems and allows delivery workers to perform their work smoothly is needed.

[1122] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1123] In this invention, the server includes means for analyzing past clothing photos and equipment and preferences of the user and delivery person to generate personal style and equipment profiles, means for obtaining the latest weather data for the travel destination and delivery area to grasp weather information in real time, means for suggesting clothing and equipment that matches the style taking into consideration the culture and trends of the travel destination and delivery area, and means for automatically generating a list of necessary items to bring based on the suggested clothing and equipment, thereby enabling delivery people to prepare efficiently and environmentally friendly.

[1124] "User" refers to an individual who uses the system to generate their own style profile and receive clothing and belongings suggestions.

[1125] "Delivery personnel" refers to personnel who use this system to receive suggestions on optimal clothing and equipment for performing tasks such as food delivery.

[1126] "Past clothing photos" are image data of clothing worn by users and delivery personnel in the past.

[1127] "Style profile" refers to information about a person's fashion style generated by analyzing past clothing photos and preferences of the user and delivery person.

[1128] "Weather data" refers to information such as the current and forecasted weather, temperature, humidity, etc. at the travel destination or delivery area.

[1129] "Culture and trends" refers to the customs and fashion trends of clothing and behavior in a particular region or society.

[1130] A "packing list" is an automatically generated list of necessary items to bring based on the suggested clothing and equipment.

[1131] "Environmentally friendly fashion items" refer to clothing, accessories, etc. that are made from eco-friendly materials and are intended to reduce the burden on the environment.

[1132] "Equipment Profile" refers to information about a delivery person's personal equipment generated by analyzing their past equipment and preferences.

[1133] "Means of understanding weather information in real time" refers to a method of obtaining the latest weather data from an external weather API to understand the weather conditions at the travel destination or delivery area in real time.

[1134] "Means for suggesting optimal clothing and equipment" refers to a method that uses AI to integrate personal profiles, climate information, and cultural backgrounds to suggest optimal clothing and equipment.

[1135] "Means for automatically generating a packing list" refers to a method for automatically generating a list of necessary packing items based on the suggested clothing and equipment.

[1136] "Delivery area" refers to the region or area in which a delivery person makes deliveries.

[1137] "Eco-friendly items" refer to products and equipment that are made using environmentally friendly materials and manufacturing processes.

[1138] The system for realizing this invention includes a server, a terminal, and a user. The roles and processes of each will be described in detail below.

[1139] Server Roles

[1140] The server first receives and analyzes data from users and delivery staff. Specifically, it handles the following data:

[1141] Image data of past photos of clothing and equipment of users and delivery personnel

[1142] Text data on the fashion and equipment preferences of users and delivery personnel

[1143] The server uses TensorFlow for image analysis and GPT-4 for analyzing text data of preferences, which generates a style profile and equipment profile for each individual. The server also uses an external weather API (OpenWeatherMap API) to obtain real-time weather information for travel destinations and delivery areas.

[1144] The server then integrates this data and uses a generative AI model to generate a list of optimal clothing and equipment, based on style profile, equipment profile, weather information, and cultural background.

[1145] Additionally, the server automatically generates a list of necessary items based on the generated clothing and equipment list, including eco-friendly items and local brand options in the process.

[1146] Device Role

[1147] The terminal functions as a user interface. First, the user or delivery person uploads photos of their previous outfits and their preferences, which are then sent to the server. The server then displays a list of optimal outfits and equipment, as well as a list of items to bring. The user or delivery person can review this information and make adjustments as necessary.

[1148] User Roles

[1149] The user inputs their own data into the terminal, receives suggestions from the server, and makes preparations based on them. Specifically, the user uses the system as follows:

[1150] 1. Upload past clothing photos and preferences to your device.

[1151] 2. Enter travel destination and delivery area information into the device.

[1152] 3. Check the suggested clothing and packing list and prepare accordingly.

[1153] Specific examples

[1154] Example 1: Rainy day delivery in Shibuya

[1155] User: Upload data on the delivery person's past preferences for waterproof jackets and shoes.

[1156] Server: Analyzes past photos of equipment and preferences to generate a profile. Checks the weather in Shibuya using the OpenWeatherMap API and suggests waterproof jackets, waterproof shoes, and rain bags for rainy days.

[1157] Terminal: Notifies the delivery person of the clothing list and belongings list sent from the server, and allows them to confirm and make adjustments.

[1158] Example prompts to be input to the generative AI model:

[1159] "Please suggest the best clothing and equipment for rainy days for food delivery in Shibuya. Delivery people prefer waterproof jackets and shoes. Also, please suggest eco-friendly items."

[1160] The system allows delivery personnel to prepare efficiently and environmentally, making it easy to select equipment appropriate for weather conditions and cultural backgrounds.

[1161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1162] Step 1:

[1163] The user inputs past clothing photos and information about their preferences into the terminal. This data is sent from the terminal to the server as image data and text data. The input data includes information such as photos of clothing worn in the past, favorite colors, designs, and particularly favorite fashion styles.

[1164] Input: Past clothing photos (image data), preference information (text data)

[1165] Output: Send data to the server

[1166] Step 2:

[1167] The server analyzes the received data. First, it uses TensorFlow to analyze the image data and generate a style profile for the user. Then it uses GPT-4 to analyze the text data of user preferences and create a detailed profile of the individual's fashion style.

[1168] Input: Past clothing photos (image data), preference information (text data)

[1169] Output: Style Profile

[1170] Step 3:

[1171] The user inputs information about the travel destination and delivery area into the terminal, including the name of the destination, the duration, the planned activities and tasks, etc. This information is then sent to the server.

[1172] Input: Travel destination information, delivery area information (text data)

[1173] Output: Send data to the server

[1174] Step 4:

[1175] The server uses the OpenWeatherMap API to obtain real-time weather data for the entered travel destination and delivery area, and uses this information to understand the weather conditions of the travel destination and delivery area.

[1176] Input: Travel destination information, delivery area information (text data)

[1177] Output: Get real-time weather data

[1178] Step 5:

[1179] The server combines the acquired weather data with the generated style and equipment profiles, as well as the input cultural background and trend information. Based on this, a generative AI model (GPT-4) is used to generate the optimal outfit and equipment list. Eco-friendly items and local brand options are also taken into consideration.

[1180] Inputs: Style profile, equipment profile, real-time weather data, cultural context information

[1181] Output: Optimal clothing and equipment list

[1182] Step 6:

[1183] The server sends the generated list of optimal clothing and equipment to the device, which receives it and notifies the user. The user can then check the displayed list and make adjustments as necessary.

[1184] Input: Optimal clothing and equipment list

[1185] Output: Notification to terminal

[1186] Step 7:

[1187] The server automatically generates a list of necessary items to bring based on the suggested clothing and equipment, including eco-friendly items and local brand options, and sends the list to the device and notifies the user.

[1188] Input: Optimal clothing and equipment list

[1189] Output: Generates and notifies inventory list

[1190] Example prompt

[1191] "Please suggest the best clothing and equipment for rainy days for food delivery in Shibuya. Delivery people prefer waterproof jackets and shoes. Also, please suggest eco-friendly items."

[1192] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1193] MODE FOR CARRYING OUT THE INVENTION

[1194] The system of the present invention combines a means for analyzing a user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination and understanding climate information in real time, a means for suggesting clothing that matches the style taking into consideration the culture and trends of the travel destination, a means for automatically generating a list of necessary items to bring based on the suggested clothing, a means for supporting the user in preventing duplication or shortages when packing, a means for recommending environmentally friendly fashion items, and an emotion engine that recognizes the user's emotions.

[1195] Program processing and explanation

[1196] Generate a style profile

[1197] When a user logs in to the application, they first upload photos of their previous outfits and their preferences (color, design, etc.), then enter their details into an input form. The device then sends this data to the server.

[1198] The server uses an image analysis model to extract the user's style characteristics from the uploaded image data. At the same time, it uses a natural language processing model to analyze the text data and identify specific preferences for color, design, material, etc. Based on this information, the server creates a user profile and stores it in a database. This clarifies the user's past style information and preferences.

[1199] Obtaining travel information

[1200] After the user inputs the travel destination information, the user's device then transmits the travel destination, travel period, and planned activities to the server. Based on the received information, the server obtains real-time weather data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API, stores this weather data in a database, and associates it with the user's travel information.

[1201] Generating recommendations

[1202] The server uses generative AI to create an optimal outfit list based on the user's profile, weather information, and cultural background. The generated outfit list includes items that are appropriate for the weather conditions as well as culturally appropriate items. The emotion engine also assesses the user's emotional state at that time and can suggest outfits that are more psychologically satisfying. The recommendations also include environmentally friendly items and local brand options.

[1203] Generate suggestions and packing lists

[1204] The generated clothing suggestion list is sent from the server to the user's device and notified to the user. The user can check the suggested list and make adjustments as necessary. Based on the list, the server automatically generates a list of necessary items to bring, which is also sent to the user's device and notified to the user.

[1205] Specific examples

[1206] Example 1: Summer trip to Tokyo (casual style)

[1207] user:

[1208] He likes a casual style and owns T-shirts, shorts, and sneakers.

[1209] Travel information:

[1210] Travel destination: Tokyo

[1211] Period: July 20th to July 25th

[1212] Activities: Sightseeing, shopping, cafe hopping

[1213] server:

[1214] Analyzes past clothing photos and preferences to generate a casual style profile.

[1215] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were high.

[1216] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[1217] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[1218] An emotional engine assesses the user's emotional state and reflects this in the selection of suggested items.

[1219] User device:

[1220] You can check the clothing and item lists sent from the server and make adjustments as needed.

[1221] Example 2: Winter business trip to New York (formal style)

[1222] user:

[1223] He prefers a formal yet business casual style, and his personal belongings include suits, dress shoes, and coats.

[1224] Travel information:

[1225] Travel destination: New York

[1226] Period: December 1st to December 5th

[1227] Activities: Meetings, business dinners

[1228] server:

[1229] Analyzes past clothing photos and preferences to generate a formal style profile.

[1230] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[1231] The site offers warm and formal clothing such as wool coats, suits, and dress shoes, and also recommends items made from eco-friendly materials and local brands.

[1232] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[1233] An emotional engine assesses the user's emotional state and reflects this in the selection of suggested items.

[1234] User device:

[1235] You can check the clothing and item lists sent from the server and make adjustments as needed.

[1236] This system allows users to efficiently prepare for their trip, easily select a style that suits their destination, and provides a more fulfilling travel experience by taking into account the user's emotional state.

[1237] The processing flow will be explained below.

[1238] Step 1:

[1239] The user logs in to the application. First, the user uploads photos of their previous outfits and their preferred information (color, design, etc.), and then enters the details into an input form. The user's device sends this data to the server.

[1240] Step 2:

[1241] The server inputs the received image data into an image analysis model to extract the user's style characteristics. At the same time, it inputs the received text data into a natural language processing model to analyze color and design preferences. The server then generates a user profile based on these analysis results and stores it in a database.

[1242] Step 3:

[1243] The user inputs travel information (travel destination, duration, planned activities) into the application. The user terminal sends this information to the server, which stores it in a database.

[1244] Step 4:

[1245] The server retrieves real-time weather data for the travel destination from an external weather API based on the submitted travel information, stores the retrieved weather data in a database, and associates it with the user's travel information.

[1246] Step 5:

[1247] The server integrates user profiles, climate information, and cultural backgrounds, and uses generative AI to create an optimal outfit list, which includes items suitable for the weather conditions, culturally compatible items, and eco-friendly fashion items.

[1248] Step 6:

[1249] The server uses an emotion engine to evaluate the user's emotional state in real time, and based on the results, dynamically adjusts the outfit list to suggest outfits that suit the user's emotions.

[1250] Step 7:

[1251] The generated clothing suggestion list is sent from the server to the user's terminal and notified to the user, who can then check the suggested clothing list and make adjustments as necessary.

[1252] Step 8:

[1253] The server automatically generates a list of necessary items based on the recommended outfits, and the list is sent from the server to the user's device and notified to the user.

[1254] Step 9:

[1255] Users can check their packing list on their device and pack efficiently, allowing them to smoothly prepare for their trip.

[1256] Specific examples

[1257] Example 1: Summer trip to Tokyo

[1258] user:

[1259] He prefers a casual style and his personal items include t-shirts, shorts, and sneakers.

[1260] Travel information:

[1261] Travel destination: Tokyo

[1262] Period: July 20th to July 25th

[1263] Activities: Sightseeing, shopping, cafe hopping

[1264] Step 1:

[1265] The user logs in, uploads photos of past outfits, and enters their casual preferences. The user's device sends the data to the server.

[1266] Step 2:

[1267] The server performs image analysis and natural language processing to generate and store user profiles.

[1268] Step 3:

[1269] The user enters travel information for Tokyo, July 20th to July 25th, sightseeing and shopping, and the user's device sends the data to the server.

[1270] Step 4:

[1271] The server collects real-time weather data for Tokyo and stores it in a database.

[1272] Step 5:

[1273] The server uses generated AI to create a list of outfits, such as a T-shirt, shorts, and breathable sneakers.

[1274] Step 6:

[1275] The sentiment engine evaluates the user's emotions and adjusts the listing to enhance the travel experience.

[1276] Step 7:

[1277] The server transmits the clothing list to the user terminal, and the user checks the list.

[1278] Step 8:

[1279] The server generates a list of belongings and transmits it to the user terminal.

[1280] Step 9:

[1281] The user checks the list of belongings and packs.

[1282] Example 2: Winter business trip to New York

[1283] user:

[1284] He prefers a formal yet business casual style, and his personal belongings include a suit, dress shoes, and coat.

[1285] Travel information:

[1286] Travel destination: New York

[1287] Period: December 1st to December 5th

[1288] Activities: Meetings, business dinners

[1289] Step 1:

[1290] The user logs in, uploads photos of past outfits, and enters their formal preferences. The user's device sends the data to the server.

[1291] Step 2:

[1292] The server performs image analysis and natural language processing to generate and store user profiles.

[1293] Step 3:

[1294] The user enters travel information such as New York, December 1st to December 5th, meeting and business dinner, and the user terminal sends the data to the server.

[1295] Step 4:

[1296] The server retrieves real-time weather data for New York and stores it in a database.

[1297] Step 5:

[1298] The server uses generated AI to create a list of clothing items such as wool coats, suits, and dress shoes.

[1299] Step 6:

[1300] An emotion engine assesses the user's emotions and tailors the list to ease tension in business meetings.

[1301] Step 7:

[1302] The server transmits the clothing list to the user terminal, and the user checks the list.

[1303] Step 8:

[1304] The server generates a list of belongings and transmits it to the user terminal.

[1305] Step 9:

[1306] The user checks the list of belongings and packs.

[1307] Example 2

[1308] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1309] Modern travelers need to choose appropriate clothing, taking into account the climate, culture, and trends of their destination. Automatically generating a packing list and incorporating environmental considerations and personal emotional state is a time-consuming and labor-intensive task. Conventional systems were unable to perform these processes efficiently and comprehensively, placing a heavy burden on travel preparation.

[1310] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing the user's past clothing photos and preferences to generate a personal style profile, a means for acquiring the latest weather data for the travel destination and understanding the weather information in real time, and a means for evaluating the user's emotional state and suggesting optimal clothing based on the evaluation. This allows travelers to efficiently prepare for their trip and select appropriate clothing that suits the climate and culture.

[1311] "User" refers to an individual who uses the system to prepare for a trip or select fashion.

[1312] "Past clothing photos" refer to photos of clothing previously worn by a user, and are data used to generate a style profile.

[1313] "Preferences" refers to information about the user's preferred fashion style, color, design, and material.

[1314] A "style profile" is data that represents a user's personal fashion trends and is generated based on the user's past clothing photos and preferences.

[1315] "Travel Destination" refers to the place that the User intends to visit.

[1316] "Weather data" refers to real-time weather information such as weather forecast, temperature, and humidity at your travel destination.

[1317] "Culture" refers to the social, historical, and regional background of a travel destination, and is a factor that influences clothing choices.

[1318] "Trends" refers to the latest fashions and trends in the destination.

[1319] A "packing list" refers to a list of items needed for a trip based on a suggested outfit.

[1320] "Duplicates and shortages" refers to users packing multiple items of the same kind, or leaving on a trip without an important item.

[1321] "Eco-conscious fashion items" refer to clothing and accessories made from sustainable materials and eco-friendly manufacturing methods.

[1322] "Emotional state" refers to the result of an assessment of the user's current psychological state.

[1323] "Recommendations" refers to a list of the best clothing and items to bring based on analyzed data.

[1324] "Generative AI" refers to an artificial intelligence model trained on a large dataset, which is used here to generate the outfit list.

[1325] This invention is a system that streamlines travel preparation for users and suggests clothing appropriate for the climate and culture. This system is composed of interactions between a server, a terminal, and a user. The specific processing procedures and technologies used are described below.

[1326] Generate a style profile

[1327] When a user logs in to the application, they first upload previous clothing photos and personal preferences, and then enter their details. This includes preferences for color, design, and materials. The device then sends this data to the server. The server then uses an image analysis model (e.g., Google Cloud Vision API) to extract the user's style features from the uploaded image data. At the same time, it uses a natural language processing model (e.g., BERT) to analyze the text data and understand the user's preferences. Based on these analysis results, the server creates a user profile and stores it in a database.

[1328] Obtaining travel information

[1329] When a user inputs travel destination information, the device sends the travel destination, travel duration, and planned activities to the server. Based on the received information, the server retrieves real-time climate data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API (e.g., OpenWeatherMap API). The retrieved climate data is stored in a database and associated with the user's travel information.

[1330] Generating recommendations

[1331] The server uses a generative AI model (e.g., GPT-4) to generate an optimal outfit list based on the user profile, weather information, and cultural background. This outfit list includes items appropriate for the weather conditions as well as culturally appropriate items. It also uses an emotion engine (e.g., Azure Emotion API) to evaluate the user's emotional state at that time and suggests outfits based on that emotional state. Furthermore, recommendations can also include eco-friendly items and local brand options.

[1332] Generate suggestions and packing lists

[1333] The generated clothing suggestion list is sent from the server to the user's device and notified to the user. The user can review the suggested list and make adjustments as necessary. For example, they can exclude specific items or request additional items. Based on this, the server automatically generates a list of necessary items to bring. This list is also sent to the user's device and notified to the user.

[1334] Specific examples

[1335] Example 1: Summer trip to Tokyo (casual style)

[1336] User: Prefers casual style and owns T-shirts, shorts, and sneakers.

[1337] Travel Information: Destination: Tokyo, Period: July 20th - July 25th, Activities: Sightseeing, Shopping, Cafe Hopping

[1338] server:

[1339] Analyzes past clothing photos and preferences to generate a casual style profile.

[1340] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were high.

[1341] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[1342] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[1343] An emotional engine assesses the user's emotional state and reflects it in the selection of suggested items.

[1344] User device: Check the clothing list and belongings list sent from the server and make adjustments as necessary.

[1345] Example 2: Winter business trip to New York (formal style)

[1346] User: Prefers a formal yet business casual style and owns a suit, dress shoes, coat, etc.

[1347] Travel Information: Destination: New York, Period: December 1st - December 5th, Activities: Meetings, Business Dinner

[1348] server:

[1349] Analyzes past clothing photos and preferences to generate a formal style profile.

[1350] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[1351] The site offers warm and formal clothing such as wool coats, suits, and dress shoes, and also recommends items made from eco-friendly materials and local brands.

[1352] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[1353] An emotional engine assesses the user's emotional state and reflects it in the selection of suggested items.

[1354] User device: Check the clothing list and belongings list sent from the server and make adjustments as necessary.

[1355] Prompt Sentence Examples

[1356] Example prompt 1:

[1357] Based on the user's style profile, suggest a casual outfit list for a trip to Tokyo in July. The weather is hot and humid, and the user's past clothing data indicates that they prefer T-shirts, shorts, and sneakers. Include items made from eco-friendly materials and local brands.

[1358] Example prompt 2:

[1359] Generate an appropriate attire list for a business meeting and dinner in New York in December for a user who prefers a formal yet business casual style. The weather will be cold and likely to snow. Include items made from eco-friendly materials and local brands.

[1360] This system allows users to efficiently prepare for their trip, easily select a style that suits their destination, and provides a more fulfilling travel experience by taking into account the user's emotional state.

[1361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1362] Step 1: A user logs in to the application and uploads photos of their previous outfits and their preferences.

[1363] Input: User ID, past clothing photos, and text information of your preferences (color, design, material, etc.).

[1364] How it works: A user logs into the application, selects a photo of an outfit from a previous outfit, and fills out a form with their preferences.

[1365] Output: The device sends these data to the server.

[1366] Step 2: The server analyzes the data using image analysis and natural language processing models to generate a style profile.

[1367] Input: Clothing photo data, text information of user preferences.

[1368] How it works: The server uses an image analysis model (e.g., Google Cloud Vision API) to extract clothing features (e.g., color, shape, material) from the photo, and simultaneously analyzes the text information using a natural language processing model (e.g., BERT).

[1369] Data processing / calculation: Extract the characteristics of fashion items through image data analysis, and analyze preferences from text data.

[1370] Output: A style profile generated based on the analysis results, which is stored in a database.

[1371] Step 3: The user inputs the travel destination information, and the terminal sends the information to the server.

[1372] Input: Travel destination, travel duration, planned activities.

[1373] Action: A user fills out a travel destination information form and presses the submit button.

[1374] Output: The device sends this travel destination information to the server.

[1375] Step 4: The server retrieves the weather data and stores it in a database.

[1376] Input: Travel destination information (destination, duration).

[1377] How it works: The server uses a weather API (e.g. OpenWeatherMap API) to get real-time weather data.

[1378] Data processing / calculation: Call the API, analyze the acquired data, and save information such as weather forecast, temperature, and humidity in a database.

[1379] Output: Weather data is stored in a database and linked to the user's travel information.

[1380] Step 5: The server uses the generative AI model to generate the optimal outfit list.

[1381] Input: User profile, destination climate data, cultural background.

[1382] How it works: The server uses a generative AI model (e.g., GPT-4) to generate an outfit list based on the input data, and an emotion engine (e.g., Azure Emotion API) to assess the user's current emotional state.

[1383] Data processing / calculation: Combining the user's past data with real-time weather data and cultural background, the system generates an optimal outfit list. It also takes into account emotional data.

[1384] Output: The generated outfit list, which is provided to the user as a suggestion list.

[1385] Step 6: The server automatically generates a list of items to bring based on the suggested clothing list.

[1386] Input: Generated outfit list.

[1387] How it works: The server automatically lists the necessary items based on the clothing list.

[1388] Data processing / calculation: Analyze the suggested clothing items and select the necessary items based on them.

[1389] Output: An automatically generated inventory list, which is sent to the user's device.

[1390] Step 7: The user terminal notifies the user of the clothing list and belongings list, and the user confirms and adjusts them.

[1391] Input: Outfit list and inventory list sent from the server.

[1392] Action: The user device presents the list to the user, who can review it and make adjustments as needed, for example, adding or removing specific items.

[1393] Output: Finalized outfit and packing list.

[1394] (Application example 2)

[1395] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1396] Traditionally, food delivery services have struggled to suggest the best dishes to suit a user's style, mood, and climate. They also lacked the functionality to recommend environmentally friendly ingredients and local brands, which resulted in an unsatisfactory user experience. Therefore, there is a need for a system that provides food delivery options that take into account a user's style, mood, climate, and environmental considerations.

[1397] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1398] In this invention, the server includes means for analyzing a user's past clothing photos and preferences to generate a personal style profile, means for acquiring the latest weather data for the user's current location to grasp climate information in real time, means for integrating the generated style profile with the climate information and cultural background to propose optimal food delivery options, means for automatically generating an optimal dish list based on the proposed food delivery options, and means for recommending dishes made with environmentally friendly ingredients and local brands, thereby making it possible to provide optimal food delivery options that suit the user's style, mood, and climate.

[1399] "Photos of the user's past clothing" are photos of clothing worn by the user in the past, and are data for generating a style profile.

[1400] "Preferences" refers to the user's fashion-related preferences, such as favorite colors, designs, and materials.

[1401] A "style profile" refers to the results of an analysis of a user's personal fashion style based on past clothing photos and preferences.

[1402] "Weather data" refers to information related to the climate, such as temperature, humidity, and weather forecasts, and is data that can be obtained in real time.

[1403] "Means for grasping weather information in real time" refers to a means for quickly obtaining the latest weather data and accurately grasping the weather conditions at the user's current location.

[1404] "Food delivery options" refers to the types of food and restaurants available for delivery, and are used to fulfill a customer's order.

[1405] "Dish List" means a list of specific dishes based on a proposed food delivery option.

[1406] "Environmentally conscious ingredients" are sustainable ingredients selected to contribute to environmental protection.

[1407] "Locally branded cuisine" refers to food and drink produced and served within a region, reflecting local culture and flavors.

[1408] A "generative AI model" is an artificial intelligence model that generates natural language and images based on input data.

[1409] A "prompt" is an instruction given to a generative AI model to obtain an appropriate output.

[1410] This invention is a system that generates a personal style profile based on the user's past clothing photos and preferences, and also obtains the latest weather data to suggest optimal options for food delivery services. The system is implemented by a user terminal and a server working together.

[1411] Program processing explanation

[1412] 1. Create a user profile

[1413] The user's device uploads photos of their previous clothing and their preferences to the application. The uploaded data is analyzed using an image analysis model (TensorFlow or PyTorch) to extract the user's fashion style characteristics. In addition, text information about the user's preferences is analyzed using a natural language processing model (such as BERT). Based on these analysis results, the server generates the user's style profile and stores it in a cloud database (such as Firebase).

[1414] 2. Obtaining weather information

[1415] The user's device acquires their current location information and sends it to the server. The server then retrieves real-time weather data from a weather data API (such as OpenWeatherMap) based on the location information. This weather data is stored in a cloud database and associated with the user's style profile.

[1416] 3. Generating Recommendations

[1417] The server integrates the generated style profile with weather data and uses a generative AI model (such as GPT-3) to suggest optimal food delivery options. The generated list includes meal options that suit the user's current style and weather conditions, allowing them to choose the best dishes to suit their mood and environment.

[1418] 4. Suggestions and Notifications

[1419] The generated food list is sent from the server to the user's device and notified to the user. The user can review the suggested dish list and make adjustments as necessary. This allows the user to order the meal that best suits their mood and environment that day.

[1420] Specific examples

[1421] Example 1: Lunch on a hot summer day (casual style)

[1422] User: Prefers casual style and has often worn T-shirts and shorts in the past.

[1423] Current location and climate: Tokyo, July, temperature 35°C, humidity 75%

[1424] session:

[1425] The user's device uploads past clothing photos and preferences to the server.

[1426] The server generates a style profile using image analysis and natural language processing.

[1427] The server uses a weather data API to obtain weather information for the current location.

[1428] A generative AI model (GPT-3) generates suggestions such as cold drinks and light salads.

[1429] A list of suggested foods is sent to the user's device, such as chilled salad, iced latte, and chilled tofu.

[1430] Example prompt: "Please suggest some dishes that would make you feel casual in Tokyo during the summer. The user's preference is casual, and the days are often hot."

[1431] Example 2: Winter evening dinner (formal style)

[1432] User: Prefers formal style and has worn suits and coats many times in the past.

[1433] Current location and climate: New York, December, 0°C, snow

[1434] session:

[1435] The user's device uploads past clothing photos and preferences to the server.

[1436] The server generates a style profile using image analysis and natural language processing.

[1437] The server uses a weather data API to obtain weather information for the current location.

[1438] A generative AI model (GPT-3) generates suggestions for hot soups, stews, and other dishes.

[1439] A list of suggested foods is sent to the user's device, such as tomato soup, a glass of wine, and warm bread.

[1440] Example prompt: "What are some recommendations for a formal winter dinner in New York? Something suitable for a cold or snowy day would be good."

[1441] In this way, our system can provide optimal food delivery options by integrating a user's past clothing photos and preferences with current weather information and using a generative AI model, allowing users to enjoy the food that best suits their mood and environment.

[1442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1443] Step 1:

[1444] When a user logs in to the application, the user's device uploads past clothing photos and preference data. The user enters past clothing photos (image files) and text information about preferences (color, design, material, etc.) into an input form. The uploaded data is sent to the server. (Input): Past clothing photos, text information about the user's preferences (Output): Data sent to the server

[1445] Step 2:

[1446] The server performs image analysis based on the received data. The image analysis model (TensorFlow or PyTorch) analyzes the uploaded image file and extracts the user's style characteristics (type of clothing, color, design, material, etc.). At the same time, a natural language processing model (BERT, etc.) analyzes the text information to specifically understand the user's preferences. (Input): Uploaded image file and text information (Output): Analysis results of style characteristics and preferences

[1447] Step 3:

[1448] The server generates a style profile for the user based on the analysis results. The style profile integrates data extracted from the user's past clothing photos and preferences, and clearly indicates the user's fashion trends. The generated style profile is stored in a cloud database (such as Firebase). (Input): Analysis results of style features and preferences (Output): Generated style profile

[1449] Step 4:

[1450] The user device acquires the user's current location information and sends it to the server. The server uses a weather data API (such as OpenWeatherMap) based on the received current location information to acquire real-time weather data (temperature, humidity, weather forecast, etc.). The acquired weather data is stored in a cloud database and associated with the user's style profile. (Input): Current location information (Output): Acquired weather data

[1451] Step 5:

[1452] The server combines the generated style profile with weather data and generates optimal food delivery options using a generative AI model (such as GPT-3). The generative AI model creates an optimal dish list based on the user's mood, style, and climate based on the prompt. (Input): Style profile, weather data, prompt (Output): Optimal food delivery options

[1453] Step 6:

[1454] The server sends the generated food list to the user's device and notifies the user. The user can review the proposed food list and make adjustments as necessary. The final adjusted list is sent back to the server, and the necessary information is stored in the cloud database. (Input): Generated food list (Output): Food list sent to the user's device

[1455] This allows users to choose the dish that best suits their mood and the environment at the time and enjoy a comfortable meal.

[1456] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1457] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1458] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1459] [Fourth embodiment]

[1460] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1461] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1462] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1463] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1464] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1465] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1466] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1467] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1468] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1469] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1470] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1471] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1472] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1473] MODE FOR CARRYING OUT THE INVENTION

[1474] The system of the present invention includes a means for analyzing a user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination and understanding climate information in real time, a means for suggesting clothing that matches the style taking into account the culture and trends of the travel destination, a means for automatically generating a list of necessary items to bring based on the suggested clothing, a means for supporting the user in preventing duplication or shortages when packing, and a means for recommending environmentally friendly fashion items.

[1475] Program processing and explanation

[1476] When a user logs in to the app, they first upload photos of their previous outfits and their preferences (color, design, etc.), then enter the details in an input form. The device then sends this data to the server.

[1477] The server uses image analysis and natural language processing to generate a style profile for the user and stores it in a database, revealing the user's past style information and preferences.

[1478] After the user inputs the travel destination information, the user device sends the travel destination, travel duration, and planned activities to the server, which then retrieves real-time weather data from an external weather API and associates it with the weather conditions of the travel destination.

[1479] The server combines the user profile with the destination's climate and cultural background, and uses generative AI to create an optimal outfit list. This list includes not only weather-appropriate clothing but also culturally appropriate clothing. It also includes recommendations for environmentally friendly items and local brands.

[1480] The generated clothing list is sent to the user's device and notified to the user, who can then review the list and make adjustments as necessary.

[1481] Next, the server automatically generates a list of necessary items based on the recommended outfit. This list is used to prevent duplication or shortages when packing. The list is also sent to the user's device and notified to the user.

[1482] Specific examples

[1483] Example 1: Summer trip to Tokyo

[1484] user:

[1485] He likes old photos of his outfits and casual styles. His personal items include T-shirts, shorts, and sneakers.

[1486] Travel information:

[1487] Travel destination: Tokyo

[1488] Period: July 20th to July 25th

[1489] Activities: Sightseeing, shopping, cafe hopping

[1490] server:

[1491] Analyzes past clothing photos and preferences to generate a casual style profile.

[1492] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were both high.

[1493] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[1494] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[1495] User device:

[1496] The user is notified of the clothing list and belongings list sent from the server, and the user can confirm and adjust the list.

[1497] Example 2: Winter business trip to New York

[1498] user:

[1499] He prefers a formal yet business casual style, and owns a suit, dress shoes, and coat.

[1500] Travel information:

[1501] Travel destination: New York

[1502] Period: December 1st to December 5th

[1503] Activities: Meetings, business dinners

[1504] server:

[1505] Analyzes past clothing photos and preferences to generate a formal style profile.

[1506] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[1507] The store offers warm and formal clothing, including wool coats, suits, and dress shoes, as well as items made from eco-friendly materials and local brands.

[1508] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[1509] User device:

[1510] The user is notified of the clothing list and belongings list sent from the server, and the user can confirm and adjust the list.

[1511] This system allows users to efficiently prepare for their trip and easily select the style that best suits their destination.

[1512] The processing flow will be explained below.

[1513] Step 1:

[1514] The user logs in to the application. The user uploads past clothing photos and preference information (color, material, design preferences, etc.) and enters detailed information into the input form. The user's device sends this data to the server.

[1515] Step 2:

[1516] The server inputs the received image data into an image analysis model to extract the user's style characteristics. At the same time, it inputs the text data into a natural language processing model to analyze preferences such as color and design. This generates a user profile and stores it in a database.

[1517] Step 3:

[1518] The user inputs travel information (destination, duration, planned activities) into the application, and the user terminal sends this information to the server.

[1519] Step 4:

[1520] Based on the submitted travel information, the server retrieves real-time weather data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API, stores the retrieved weather data in a database, and associates it with the user's travel information.

[1521] Step 5:

[1522] The server uses generative AI to create an optimal outfit list based on the user's profile, weather information, and cultural background. The generated outfit list includes items that are climate-appropriate and culturally appropriate, as well as recommendations for sustainable items and local brands.

[1523] Step 6:

[1524] The generated clothing suggestion list is sent from the server to the user's terminal and notified to the user, who can then review the suggested clothing list and make corrections or adjustments as necessary.

[1525] Step 7:

[1526] The server automatically generates a list of necessary items based on the recommended outfit. This list is intended to prevent duplication or shortages. The list is sent from the server to the user's device and notified to the user.

[1527] Step 8:

[1528] Using the user terminal, users can check their packing list and pack efficiently, allowing them to smoothly prepare for their trip.

[1529] Example 1

[1530] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1531] When traveling or on a business trip, selecting appropriate clothing and efficiently preparing belongings is a time-consuming and labor-intensive task. It is particularly difficult to select clothing that takes into account weather conditions and cultural backgrounds, and finding environmentally friendly items can be time-consuming. A convenient and effective system is needed to solve these problems.

[1532] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1533] In this invention, the server includes means for analyzing a user's past clothing photos and preferences to generate a personal style profile, means for acquiring the latest weather data for the travel destination and grasping climate information in real time, and means for integrating the weather data for the travel destination, the user's style profile, and cultural background and generating an appropriate clothing list using a generative AI model. This allows users to easily select clothing appropriate for the weather conditions and cultural background of their travel destination and efficiently prepare their belongings.

[1534] A "user" is an individual who uses this system and provides past clothing photos and preference data.

[1535] "Clothing photos" are images or photos of clothing worn by a user in the past.

[1536] A "style profile" is data that indicates a user's personal style and fashion trends, generated based on past clothing photos and preferences of the user.

[1537] "Weather data" refers to data that indicates information about the climate, such as the current and forecast weather and temperature at the travel destination.

[1538] "Real-time" refers to a method of data acquisition and processing that occurs nearly simultaneously with the present time.

[1539] "Cultural background" refers to information related to culture, such as customs, values, and typical styles in the region you are traveling to.

[1540] A "generative AI model" is an artificial intelligence model trained from large amounts of data, which is used to generate an appropriate outfit list by integrating a user's style profile, weather data, and cultural background.

[1541] A "packing list" is a list of items that a user needs to carry with them when traveling or on a business trip.

[1542] A "user terminal" is an electronic device, such as a smartphone or PC, that a user uses to access this system.

[1543] "Notification" is a means of communicating information to the user about the generated clothing list and belongings list.

[1544] "Eco-friendly fashion items" are clothing and accessories made using sustainable materials and processes that take into consideration their environmental impact.

[1545] MODE FOR CARRYING OUT THE INVENTION

[1546] The system of the present invention is designed to enable users planning a trip or business trip to efficiently select appropriate clothing and generate a packing list. The system includes a means for analyzing the user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination to understand climate information in real time, a means for suggesting appropriate clothing taking into account the culture and trends of the travel destination, a means for automatically generating a necessary packing list based on the suggested clothing, a means for providing support in preventing duplications and shortages when packing, and a means for recommending environmentally friendly fashion items.

[1547] To use this system, users use devices such as smartphones or PCs. First, they log in to the application, upload photos of their previous outfits, and enter their preferred styles, colors, and designs in the input form. This data is then sent from the device to the server.

[1548] The server analyzes the data using image analysis tools (e.g., OpenCV and TensorFlow) and natural language processing tools (e.g., NLTK and spaCy) to generate a style profile for the user, which is then stored in a database.

[1549] Next, the user inputs their travel destination, travel duration, and planned activities. This information is also sent to the server via the device. The server retrieves real-time weather data from external weather APIs (e.g., OpenWeatherMap API or Weatherstack API) and correlates it with the weather conditions at the travel destination.

[1550] The server provides the user's style profile, weather data, and cultural background as input data to a generative AI model (e.g., GPT-4) and sends a prompt. Specific examples of prompts are as follows:

[1551] "The user's style profile is casual. The travel destination is Tokyo, where the temperature is high and humidity is high in July. The primary focus is sightseeing. Please generate an optimal outfit list."

[1552] Based on these prompts, the generative AI model generates a list of appropriate outfits, which the server then sends to the user's device. The list includes items that match the user's preferences, as well as items suited to the climate and culture of the destination. It also suggests eco-friendly fashion items and local brand options.

[1553] The server then automatically generates a list of necessary items to bring based on the clothing list and sends it to the user's device, allowing the user to efficiently prepare for a trip or business trip and easily select appropriate clothing and items to bring.

[1554] For example, if a user is traveling to Tokyo in July, a casual T-shirt, shorts, and breathable sneakers will be recommended based on temperature and humidity information obtained from the weather API. Additional necessary items (e.g., sunscreen, hat, sunglasses, etc.) will also be automatically added to the recommended list. The device will notify the user of this information, allowing them to review and adjust the recommended list as needed.

[1555] The above is a specific embodiment for carrying out the present invention. This system allows the user to easily select clothing and items suitable for the weather and specific activities of the day.

[1556] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1557] Step 1: Collect user information

[1558] Users log in to the app, upload photos of their previous outfits, and enter their preferred styles, colors, and designs into an input form. The input data includes the outfit photo file and text information.

[1559] Specifically, users select a photo from their smartphone or computer, fill out the form with details about their style (e.g., "casual" or "formal"), and their preferred colors and design, and then press the "Submit" button.

[1560] Input: Clothing photo file, preferred style, color, design (text)

[1561] Output: User information dataset (photo files and text information)

[1562] Step 2: Send user data

[1563] The device packages the collected user data into packets and sends them to the server as HTTP requests.

[1564] In specific operation, the terminal transmits photo data and text data to the server via the network.

[1565] Input: User information dataset

[1566] Output: User information data sent to the server

[1567] Step 3: Generate a User Style Profile

[1568] The server analyzes the clothing photos using image analysis tools (e.g., OpenCV and TensorFlow) and analyzes the text data using natural language processing tools (e.g., NLTK and spaCy), generating a style profile for the user and storing it in a database.

[1569] In concrete terms, the server uses image recognition algorithms to extract style elements from photos and then integrates them with the results of analyzing text data to build a style profile.

[1570] Input: User information data (photo and text)

[1571] Output: Style profile (stored in database)

[1572] Step 4: Enter your destination information

[1573] The user enters the travel destination, travel duration, and planned activities into the application's travel information input form.

[1574] Specifically, the user fills in the form with "travel destination," "travel period," and "activities," and presses the "Submit" button.

[1575] Input: Travel destination, travel period, activities (text)

[1576] Output: Travel information dataset

[1577] Step 5: Obtaining Weather Data

[1578] The server sends a request to an external weather API (e.g., OpenWeatherMap API or Weatherstack API) to obtain real-time weather data for the travel destination.

[1579] In specific operation, the server sends an HTTP request to the API and receives the acquired weather data.

[1580] Input: Travel destination information (text)

[1581] Output: Real-time weather data

[1582] Step 6: Generate the outfit list

[1583] The server sends prompts to a generative AI model (e.g., GPT-4) that integrates the user's style profile, weather data, and cultural background, and the generative AI model generates a list of appropriate outfits.

[1584] Specifically, the AI ​​provides a prompt example that reads, "The user's style profile is casual. The travel destination is Tokyo, where the temperature and humidity are high in July. Sightseeing will be the main focus. Please generate a list of the most suitable outfits." The AI ​​then returns a list of T-shirts, shorts, sneakers, etc.

[1585] Input: Style profile, weather data, cultural background

[1586] Output: A list of the best outfits

[1587] Step 7: Generate a packing list

[1588] The server automatically generates an inventory list based on the generated clothing list, including any additional items required (e.g., sunscreen, sunglasses, etc.).

[1589] In particular, the server analyzes the clothing list and automatically adds related items (e.g., sunscreen for a T-shirt) to generate the list.

[1590] Input: Best Outfit List

[1591] Output: Inventory list

[1592] Step 8: Notification and confirmation of results

[1593] The device will then notify the user of the generated clothing and belongings list, which the user can review and adjust as necessary.

[1594] Specifically, the device will notify the user of the list via push or email notification, allowing them to view and adjust it within the app.

[1595] Input: List of suitable clothes, list of things to bring

[1596] Output: An interface to inform the user and allow them to review and adjust

[1597] (Application example 1)

[1598] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1599] In today's busy lifestyles, it is important for delivery workers to be equipped with the appropriate clothing and equipment to perform their deliveries efficiently and effectively. However, selecting the most appropriate clothing and equipment for each weather and cultural background is time-consuming and inefficient. Also, choosing eco-friendly items is a must. A system that solves these problems and allows delivery workers to perform their work smoothly is needed.

[1600] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1601] In this invention, the server includes means for analyzing past clothing photos and equipment and preferences of the user and delivery person to generate personal style and equipment profiles, means for obtaining the latest weather data for the travel destination and delivery area to grasp weather information in real time, means for suggesting clothing and equipment that matches the style taking into consideration the culture and trends of the travel destination and delivery area, and means for automatically generating a list of necessary items to bring based on the suggested clothing and equipment, thereby enabling delivery people to prepare efficiently and environmentally friendly.

[1602] "User" refers to an individual who uses the system to generate their own style profile and receive clothing and belongings suggestions.

[1603] "Delivery personnel" refers to personnel who use this system to receive suggestions on optimal clothing and equipment for performing tasks such as food delivery.

[1604] "Past clothing photos" are image data of clothing worn by users and delivery personnel in the past.

[1605] "Style profile" refers to information about a person's fashion style generated by analyzing past clothing photos and preferences of the user and delivery person.

[1606] "Weather data" refers to information such as the current and forecasted weather, temperature, humidity, etc. at the travel destination or delivery area.

[1607] "Culture and trends" refers to the customs and fashion trends of clothing and behavior in a particular region or society.

[1608] A "packing list" is an automatically generated list of necessary items to bring based on the suggested clothing and equipment.

[1609] "Environmentally friendly fashion items" refer to clothing, accessories, etc. that are made from eco-friendly materials and are intended to reduce the burden on the environment.

[1610] "Equipment Profile" refers to information about a delivery person's personal equipment generated by analyzing their past equipment and preferences.

[1611] "Means of understanding weather information in real time" refers to a method of obtaining the latest weather data from an external weather API to understand the weather conditions at the travel destination or delivery area in real time.

[1612] "Means for suggesting optimal clothing and equipment" refers to a method that uses AI to integrate personal profiles, climate information, and cultural backgrounds to suggest optimal clothing and equipment.

[1613] "Means for automatically generating a packing list" refers to a method for automatically generating a list of necessary packing items based on the suggested clothing and equipment.

[1614] "Delivery area" refers to the region or area in which a delivery person makes deliveries.

[1615] "Eco-friendly items" refer to products and equipment that are made using environmentally friendly materials and manufacturing processes.

[1616] The system for realizing this invention includes a server, a terminal, and a user. The roles and processes of each will be described in detail below.

[1617] Server Roles

[1618] The server first receives and analyzes data from users and delivery staff. Specifically, it handles the following data:

[1619] Image data of past photos of clothing and equipment of users and delivery personnel

[1620] Text data on the fashion and equipment preferences of users and delivery personnel

[1621] The server uses TensorFlow for image analysis and GPT-4 for analyzing text data of preferences, which generates a style profile and equipment profile for each individual. The server also uses an external weather API (OpenWeatherMap API) to obtain real-time weather information for travel destinations and delivery areas.

[1622] The server then integrates this data and uses a generative AI model to generate a list of optimal clothing and equipment, based on style profile, equipment profile, weather information, and cultural background.

[1623] Additionally, the server automatically generates a list of necessary items based on the generated clothing and equipment list, including eco-friendly items and local brand options in the process.

[1624] Device Role

[1625] The terminal functions as a user interface. First, the user or delivery person uploads photos of their previous outfits and their preferences, which are then sent to the server. The server then displays a list of optimal outfits and equipment, as well as a list of items to bring. The user or delivery person can review this information and make adjustments as necessary.

[1626] User Roles

[1627] The user inputs their own data into the terminal, receives suggestions from the server, and makes preparations based on them. Specifically, the user uses the system as follows:

[1628] 1. Upload past clothing photos and preferences to your device.

[1629] 2. Enter travel destination and delivery area information into the device.

[1630] 3. Check the suggested clothing and packing list and prepare accordingly.

[1631] Specific examples

[1632] Example 1: Rainy day delivery in Shibuya

[1633] User: Upload data on the delivery person's past preferences for waterproof jackets and shoes.

[1634] Server: Analyzes past photos of equipment and preferences to generate a profile. Checks the weather in Shibuya using the OpenWeatherMap API and suggests waterproof jackets, waterproof shoes, and rain bags for rainy days.

[1635] Terminal: Notifies the delivery person of the clothing list and belongings list sent from the server, and allows them to confirm and make adjustments.

[1636] Example prompts to be input to the generative AI model:

[1637] "Please suggest the best clothing and equipment for rainy days for food delivery in Shibuya. Delivery people prefer waterproof jackets and shoes. Also, please suggest eco-friendly items."

[1638] The system allows delivery personnel to prepare efficiently and environmentally, making it easy to select equipment appropriate for weather conditions and cultural backgrounds.

[1639] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1640] Step 1:

[1641] The user inputs past clothing photos and information about their preferences into the terminal. This data is sent from the terminal to the server as image data and text data. The input data includes information such as photos of clothing worn in the past, favorite colors, designs, and particularly favorite fashion styles.

[1642] Input: Past clothing photos (image data), preference information (text data)

[1643] Output: Send data to the server

[1644] Step 2:

[1645] The server analyzes the received data. First, it uses TensorFlow to analyze the image data and generate a style profile for the user. Then it uses GPT-4 to analyze the text data of user preferences and create a detailed profile of the individual's fashion style.

[1646] Input: Past clothing photos (image data), preference information (text data)

[1647] Output: Style Profile

[1648] Step 3:

[1649] The user inputs information about the travel destination and delivery area into the terminal, including the name of the destination, the duration, the planned activities and tasks, etc. This information is then sent to the server.

[1650] Input: Travel destination information, delivery area information (text data)

[1651] Output: Send data to the server

[1652] Step 4:

[1653] The server uses the OpenWeatherMap API to obtain real-time weather data for the entered travel destination and delivery area, and uses this information to understand the weather conditions of the travel destination and delivery area.

[1654] Input: Travel destination information, delivery area information (text data)

[1655] Output: Get real-time weather data

[1656] Step 5:

[1657] The server combines the acquired weather data with the generated style and equipment profiles, as well as the input cultural background and trend information. Based on this, a generative AI model (GPT-4) is used to generate the optimal outfit and equipment list. Eco-friendly items and local brand options are also taken into consideration.

[1658] Inputs: Style profile, equipment profile, real-time weather data, cultural context information

[1659] Output: Optimal clothing and equipment list

[1660] Step 6:

[1661] The server sends the generated list of optimal clothing and equipment to the device, which receives it and notifies the user. The user can then check the displayed list and make adjustments as necessary.

[1662] Input: Optimal clothing and equipment list

[1663] Output: Notification to terminal

[1664] Step 7:

[1665] The server automatically generates a list of necessary items to bring based on the suggested clothing and equipment, including eco-friendly items and local brand options, and sends the list to the device and notifies the user.

[1666] Input: Optimal clothing and equipment list

[1667] Output: Generates and notifies inventory list

[1668] Example prompt

[1669] "Please suggest the best clothing and equipment for rainy days for food delivery in Shibuya. Delivery people prefer waterproof jackets and shoes. Also, please suggest eco-friendly items."

[1670] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1671] MODE FOR CARRYING OUT THE INVENTION

[1672] The system of the present invention combines a means for analyzing a user's past clothing photos and preferences to generate a personal style profile, a means for obtaining the latest weather data for the travel destination and understanding climate information in real time, a means for suggesting clothing that matches the style taking into consideration the culture and trends of the travel destination, a means for automatically generating a list of necessary items to bring based on the suggested clothing, a means for supporting the user in preventing duplication or shortages when packing, a means for recommending environmentally friendly fashion items, and an emotion engine that recognizes the user's emotions.

[1673] Program processing and explanation

[1674] Generate a style profile

[1675] When a user logs in to the application, they first upload photos of their previous outfits and their preferences (color, design, etc.), then enter their details into an input form. The device then sends this data to the server.

[1676] The server uses an image analysis model to extract the user's style characteristics from the uploaded image data. At the same time, it uses a natural language processing model to analyze the text data and identify specific preferences for color, design, material, etc. Based on this information, the server creates a user profile and stores it in a database. This clarifies the user's past style information and preferences.

[1677] Obtaining travel information

[1678] After the user inputs the travel destination information, the user's device then transmits the travel destination, travel period, and planned activities to the server. Based on the received information, the server obtains real-time weather data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API, stores this weather data in a database, and associates it with the user's travel information.

[1679] Generating recommendations

[1680] The server uses generative AI to create an optimal outfit list based on the user's profile, weather information, and cultural background. The generated outfit list includes items that are appropriate for the weather conditions as well as culturally appropriate items. The emotion engine also assesses the user's emotional state at that time and can suggest outfits that are more psychologically satisfying. The recommendations also include environmentally friendly items and local brand options.

[1681] Generate suggestions and packing lists

[1682] The generated clothing suggestion list is sent from the server to the user's device and notified to the user. The user can check the suggested list and make adjustments as necessary. Based on the list, the server automatically generates a list of necessary items to bring, which is also sent to the user's device and notified to the user.

[1683] Specific examples

[1684] Example 1: Summer trip to Tokyo (casual style)

[1685] user:

[1686] He likes a casual style and owns T-shirts, shorts, and sneakers.

[1687] Travel information:

[1688] Travel destination: Tokyo

[1689] Period: July 20th to July 25th

[1690] Activities: Sightseeing, shopping, cafe hopping

[1691] server:

[1692] Analyzes past clothing photos and preferences to generate a casual style profile.

[1693] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were high.

[1694] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[1695] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[1696] An emotional engine assesses the user's emotional state and reflects this in the selection of suggested items.

[1697] User device:

[1698] You can check the clothing and item lists sent from the server and make adjustments as needed.

[1699] Example 2: Winter business trip to New York (formal style)

[1700] user:

[1701] He prefers a formal yet business casual style, and his personal belongings include suits, dress shoes, and coats.

[1702] Travel information:

[1703] Travel destination: New York

[1704] Period: December 1st to December 5th

[1705] Activities: Meetings, business dinners

[1706] server:

[1707] Analyzes past clothing photos and preferences to generate a formal style profile.

[1708] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[1709] The site offers warm and formal clothing such as wool coats, suits, and dress shoes, and also recommends items made from eco-friendly materials and local brands.

[1710] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[1711] An emotional engine assesses the user's emotional state and reflects this in the selection of suggested items.

[1712] User device:

[1713] You can check the clothing and item lists sent from the server and make adjustments as needed.

[1714] This system allows users to efficiently prepare for their trip, easily select a style that suits their destination, and provides a more fulfilling travel experience by taking into account the user's emotional state.

[1715] The processing flow will be explained below.

[1716] Step 1:

[1717] The user logs in to the application. First, the user uploads photos of their previous outfits and their preferred information (color, design, etc.), and then enters the details into an input form. The user's device sends this data to the server.

[1718] Step 2:

[1719] The server inputs the received image data into an image analysis model to extract the user's style characteristics. At the same time, it inputs the received text data into a natural language processing model to analyze color and design preferences. The server then generates a user profile based on these analysis results and stores it in a database.

[1720] Step 3:

[1721] The user inputs travel information (travel destination, duration, planned activities) into the application. The user terminal sends this information to the server, which stores it in a database.

[1722] Step 4:

[1723] The server retrieves real-time weather data for the travel destination from an external weather API based on the submitted travel information, stores the retrieved weather data in a database, and associates it with the user's travel information.

[1724] Step 5:

[1725] The server integrates user profiles, climate information, and cultural backgrounds, and uses generative AI to create an optimal outfit list, which includes items suitable for the weather conditions, culturally compatible items, and eco-friendly fashion items.

[1726] Step 6:

[1727] The server uses an emotion engine to evaluate the user's emotional state in real time, and based on the results, dynamically adjusts the outfit list to suggest outfits that suit the user's emotions.

[1728] Step 7:

[1729] The generated clothing suggestion list is sent from the server to the user's terminal and notified to the user, who can then check the suggested clothing list and make adjustments as necessary.

[1730] Step 8:

[1731] The server automatically generates a list of necessary items based on the recommended outfits, and the list is sent from the server to the user's device and notified to the user.

[1732] Step 9:

[1733] Users can check their packing list on their device and pack efficiently, allowing them to smoothly prepare for their trip.

[1734] Specific examples

[1735] Example 1: Summer trip to Tokyo

[1736] user:

[1737] He prefers a casual style and his personal items include t-shirts, shorts, and sneakers.

[1738] Travel information:

[1739] Travel destination: Tokyo

[1740] Period: July 20th to July 25th

[1741] Activities: Sightseeing, shopping, cafe hopping

[1742] Step 1:

[1743] The user logs in, uploads photos of past outfits, and enters their casual preferences. The user's device sends the data to the server.

[1744] Step 2:

[1745] The server performs image analysis and natural language processing to generate and store user profiles.

[1746] Step 3:

[1747] The user enters travel information for Tokyo, July 20th to July 25th, sightseeing and shopping, and the user's device sends the data to the server.

[1748] Step 4:

[1749] The server collects real-time weather data for Tokyo and stores it in a database.

[1750] Step 5:

[1751] The server uses generated AI to create a list of outfits, such as a T-shirt, shorts, and breathable sneakers.

[1752] Step 6:

[1753] The sentiment engine evaluates the user's emotions and adjusts the listing to enhance the travel experience.

[1754] Step 7:

[1755] The server transmits the clothing list to the user terminal, and the user checks the list.

[1756] Step 8:

[1757] The server generates a list of belongings and transmits it to the user terminal.

[1758] Step 9:

[1759] The user checks the list of belongings and packs.

[1760] Example 2: Winter business trip to New York

[1761] user:

[1762] He prefers a formal yet business casual style, and his personal belongings include a suit, dress shoes, and coat.

[1763] Travel information:

[1764] Travel destination: New York

[1765] Period: December 1st to December 5th

[1766] Activities: Meetings, business dinners

[1767] Step 1:

[1768] The user logs in, uploads photos of past outfits, and enters their formal preferences. The user's device sends the data to the server.

[1769] Step 2:

[1770] The server performs image analysis and natural language processing to generate and store user profiles.

[1771] Step 3:

[1772] The user enters travel information such as New York, December 1st to December 5th, meeting and business dinner, and the user terminal sends the data to the server.

[1773] Step 4:

[1774] The server retrieves real-time weather data for New York and stores it in a database.

[1775] Step 5:

[1776] The server uses generated AI to create a list of clothing items such as wool coats, suits, and dress shoes.

[1777] Step 6:

[1778] An emotion engine assesses the user's emotions and tailors the list to ease tension in business meetings.

[1779] Step 7:

[1780] The server transmits the clothing list to the user terminal, and the user checks the list.

[1781] Step 8:

[1782] The server generates a list of belongings and transmits it to the user terminal.

[1783] Step 9:

[1784] The user checks the list of belongings and packs.

[1785] Example 2

[1786] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1787] Modern travelers need to choose appropriate clothing, taking into account the climate, culture, and trends of their destination. Automatically generating a packing list and incorporating environmental considerations and personal emotional state is a time-consuming and labor-intensive task. Conventional systems were unable to perform these processes efficiently and comprehensively, placing a heavy burden on travel preparation.

[1788] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing the user's past clothing photos and preferences to generate a personal style profile, a means for acquiring the latest weather data for the travel destination and understanding the weather information in real time, and a means for evaluating the user's emotional state and suggesting optimal clothing based on the evaluation. This allows travelers to efficiently prepare for their trip and select appropriate clothing that suits the climate and culture.

[1789] "User" refers to an individual who uses the system to prepare for a trip or select fashion.

[1790] "Past clothing photos" refer to photos of clothing previously worn by a user, and are data used to generate a style profile.

[1791] "Preferences" refers to information about the user's preferred fashion style, color, design, and material.

[1792] A "style profile" is data that represents a user's personal fashion trends and is generated based on the user's past clothing photos and preferences.

[1793] "Travel Destination" refers to the place that the User intends to visit.

[1794] "Weather data" refers to real-time weather information such as weather forecast, temperature, and humidity at your travel destination.

[1795] "Culture" refers to the social, historical, and regional background of a travel destination, and is a factor that influences clothing choices.

[1796] "Trends" refers to the latest fashions and trends in the destination.

[1797] A "packing list" refers to a list of items needed for a trip based on a suggested outfit.

[1798] "Duplicates and shortages" refers to users packing multiple items of the same kind, or leaving on a trip without an important item.

[1799] "Eco-conscious fashion items" refer to clothing and accessories made from sustainable materials and eco-friendly manufacturing methods.

[1800] "Emotional state" refers to the result of an assessment of the user's current psychological state.

[1801] "Recommendations" refers to a list of the best clothing and items to bring based on analyzed data.

[1802] "Generative AI" refers to an artificial intelligence model trained on a large dataset, which is used here to generate the outfit list.

[1803] This invention is a system that streamlines travel preparation for users and suggests clothing appropriate for the climate and culture. This system is composed of interactions between a server, a terminal, and a user. The specific processing procedures and technologies used are described below.

[1804] Generate a style profile

[1805] When a user logs in to the application, they first upload previous clothing photos and personal preferences, and then enter their details. This includes preferences for color, design, and materials. The device then sends this data to the server. The server then uses an image analysis model (e.g., Google Cloud Vision API) to extract the user's style features from the uploaded image data. At the same time, it uses a natural language processing model (e.g., BERT) to analyze the text data and understand the user's preferences. Based on these analysis results, the server creates a user profile and stores it in a database.

[1806] Obtaining travel information

[1807] When a user inputs travel destination information, the device sends the travel destination, travel duration, and planned activities to the server. Based on the received information, the server retrieves real-time climate data (weather forecast, temperature, humidity, etc.) for the travel destination from an external weather API (e.g., OpenWeatherMap API). The retrieved climate data is stored in a database and associated with the user's travel information.

[1808] Generating recommendations

[1809] The server uses a generative AI model (e.g., GPT-4) to generate an optimal outfit list based on the user profile, weather information, and cultural background. This outfit list includes items appropriate for the weather conditions as well as culturally appropriate items. It also uses an emotion engine (e.g., Azure Emotion API) to evaluate the user's emotional state at that time and suggests outfits based on that emotional state. Furthermore, recommendations can also include eco-friendly items and local brand options.

[1810] Generate suggestions and packing lists

[1811] The generated clothing suggestion list is sent from the server to the user's device and notified to the user. The user can review the suggested list and make adjustments as necessary. For example, they can exclude specific items or request additional items. Based on this, the server automatically generates a list of necessary items to bring. This list is also sent to the user's device and notified to the user.

[1812] Specific examples

[1813] Example 1: Summer trip to Tokyo (casual style)

[1814] User: Prefers casual style and owns T-shirts, shorts, and sneakers.

[1815] Travel Information: Destination: Tokyo, Period: July 20th - July 25th, Activities: Sightseeing, Shopping, Cafe Hopping

[1816] server:

[1817] Analyzes past clothing photos and preferences to generate a casual style profile.

[1818] We retrieved Tokyo's climate data for July from the weather API and confirmed that the temperature and humidity were high.

[1819] The store offers casual t-shirts, shorts, and breathable sneakers, and also recommends items made from eco-friendly materials and local brands.

[1820] Based on the suggested outfit, a list of items to bring is automatically generated, including three T-shirts, two shorts, one pair of sneakers, sunscreen, a hat, sunglasses, etc.

[1821] An emotional engine assesses the user's emotional state and reflects it in the selection of suggested items.

[1822] User device: Check the clothing list and belongings list sent from the server and make adjustments as necessary.

[1823] Example 2: Winter business trip to New York (formal style)

[1824] User: Prefers a formal yet business casual style and owns a suit, dress shoes, coat, etc.

[1825] Travel Information: Destination: New York, Period: December 1st - December 5th, Activities: Meetings, Business Dinner

[1826] server:

[1827] Analyzes past clothing photos and preferences to generate a formal style profile.

[1828] Get weather data for New York in December from a weather API to see the chance of cold and snow.

[1829] The site offers warm and formal clothing such as wool coats, suits, and dress shoes, and also recommends items made from eco-friendly materials and local brands.

[1830] Based on the suggested outfit, an item list is automatically generated, including two suits, one wool coat, one pair of dress shoes, a scarf, gloves, a hat, etc.

[1831] An emotional engine assesses the user's emotional state and reflects it in the selection of suggested items.

[1832] User device: Check the clothing list and belongings list sent from the server and make adjustments as necessary.

[1833] Prompt Sentence Examples

[1834] Example prompt 1:

[1835] Based on the user's style profile, suggest a casual outfit list for a trip to Tokyo in July. The weather is hot and humid, and the user's past clothing data indicates that they prefer T-shirts, shorts, and sneakers. Include items made from eco-friendly materials and local brands.

[1836] Example prompt 2:

[1837] Generate an appropriate attire list for a business meeting and dinner in New York in December for a user who prefers a formal yet business casual style. The weather will be cold and likely to snow. Include items made from eco-friendly materials and local brands.

[1838] This system allows users to efficiently prepare for their trip, easily select a style that suits their destination, and provides a more fulfilling travel experience by taking into account the user's emotional state.

[1839] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1840] Step 1: A user logs in to the application and uploads photos of their previous outfits and their preferences.

[1841] Input: User ID, past clothing photos, and text information of your preferences (color, design, material, etc.).

[1842] How it works: A user logs into the application, selects a photo of an outfit from a previous outfit, and fills out a form with their preferences.

[1843] Output: The device sends these data to the server.

[1844] Step 2: The server analyzes the data using image analysis and natural language processing models to generate a style profile.

[1845] Input: Clothing photo data, text information of user preferences.

[1846] How it works: The server uses an image analysis model (e.g., Google Cloud Vision API) to extract clothing features (e.g., color, shape, material) from the photo, and simultaneously analyzes the text information using a natural language processing model (e.g., BERT).

[1847] Data processing / calculation: Extract the characteristics of fashion items through image data analysis, and analyze preferences from text data.

[1848] Output: A style profile generated based on the analysis results, which is stored in a database.

[1849] Step 3: The user inputs the travel destination information, and the terminal sends the information to the server.

[1850] Input: Travel destination, travel duration, planned activities.

[1851] Action: A user fills out a travel destination information form and presses the submit button.

[1852] Output: The device sends this travel destination information to the server.

[1853] Step 4: The server retrieves the weather data and stores it in a database.

[1854] Input: Travel destination information (destination, duration).

[1855] How it works: The server uses a weather API (e.g. OpenWeatherMap API) to get real-time weather data.

[1856] Data processing / calculation: Call the API, analyze the acquired data, and save information such as weather forecast, temperature, and humidity in a database.

[1857] Output: Weather data is stored in a database and linked to the user's travel information.

[1858] Step 5: The server uses the generative AI model to generate the optimal outfit list.

[1859] Input: User profile, destination climate data, cultural background.

[1860] How it works: The server uses a generative AI model (e.g., GPT-4) to generate an outfit list based on the input data, and an emotion engine (e.g., Azure Emotion API) to assess the user's current emotional state.

[1861] Data processing / calculation: Combining the user's past data with real-time weather data and cultural background, the system generates an optimal outfit list. It also takes into account emotional data.

[1862] Output: The generated outfit list, which is provided to the user as a suggestion list.

[1863] Step 6: The server automatically generates a list of items to bring based on the suggested clothing list.

[1864] Input: Generated outfit list.

[1865] How it works: The server automatically lists the necessary items based on the clothing list.

[1866] Data processing / calculation: Analyze the suggested clothing items and select the necessary items based on them.

[1867] Output: An automatically generated inventory list, which is sent to the user's device.

[1868] Step 7: The user terminal notifies the user of the clothing list and belongings list, and the user confirms and adjusts them.

[1869] Input: Outfit list and inventory list sent from the server.

[1870] Action: The user device presents the list to the user, who can review it and make adjustments as needed, for example, adding or removing specific items.

[1871] Output: Finalized outfit and packing list.

[1872] (Application example 2)

[1873] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1874] Traditionally, food delivery services have struggled to suggest the best dishes to suit a user's style, mood, and climate. They also lacked the functionality to recommend environmentally friendly ingredients and local brands, which resulted in an unsatisfactory user experience. Therefore, there is a need for a system that provides food delivery options that take into account a user's style, mood, climate, and environmental considerations.

[1875] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1876] In this invention, the server includes means for analyzing a user's past clothing photos and preferences to generate a personal style profile, means for acquiring the latest weather data for the user's current location to grasp climate information in real time, means for integrating the generated style profile with the climate information and cultural background to propose optimal food delivery options, means for automatically generating an optimal dish list based on the proposed food delivery options, and means for recommending dishes made with environmentally friendly ingredients and local brands, thereby making it possible to provide optimal food delivery options that suit the user's style, mood, and climate.

[1877] "Photos of the user's past clothing" are photos of clothing worn by the user in the past, and are data for generating a style profile.

[1878] "Preferences" refers to the user's fashion-related preferences, such as favorite colors, designs, and materials.

[1879] A "style profile" refers to the results of an analysis of a user's personal fashion style based on past clothing photos and preferences.

[1880] "Weather data" refers to information related to the climate, such as temperature, humidity, and weather forecasts, and is data that can be obtained in real time.

[1881] "Means for grasping weather information in real time" refers to a means for quickly obtaining the latest weather data and accurately grasping the weather conditions at the user's current location.

[1882] "Food delivery options" refers to the types of food and restaurants available for delivery, and are used to fulfill a customer's order.

[1883] "Dish List" means a list of specific dishes based on a proposed food delivery option.

[1884] "Environmentally conscious ingredients" are sustainable ingredients selected to contribute to environmental protection.

[1885] "Locally branded cuisine" refers to food and drink produced and served within a region, reflecting local culture and flavors.

[1886] A "generative AI model" is an artificial intelligence model that generates natural language and images based on input data.

[1887] A "prompt" is an instruction given to a generative AI model to obtain an appropriate output.

[1888] This invention is a system that generates a personal style profile based on the user's past clothing photos and preferences, and also obtains the latest weather data to suggest optimal options for food delivery services. The system is implemented by a user terminal and a server working together.

[1889] Program processing explanation

[1890] 1. Create a user profile

[1891] The user's device uploads photos of their previous clothing and their preferences to the application. The uploaded data is analyzed using an image analysis model (TensorFlow or PyTorch) to extract the user's fashion style characteristics. In addition, text information about the user's preferences is analyzed using a natural language processing model (such as BERT). Based on these analysis results, the server generates the user's style profile and stores it in a cloud database (such as Firebase).

[1892] 2. Obtaining weather information

[1893] The user's device acquires their current location information and sends it to the server. The server then retrieves real-time weather data from a weather data API (such as OpenWeatherMap) based on the location information. This weather data is stored in a cloud database and associated with the user's style profile.

[1894] 3. Generating Recommendations

[1895] The server integrates the generated style profile with weather data and uses a generative AI model (such as GPT-3) to suggest optimal food delivery options. The generated list includes meal options that suit the user's current style and weather conditions, allowing them to choose the best dishes to suit their mood and environment.

[1896] 4. Suggestions and Notifications

[1897] The generated food list is sent from the server to the user's device and notified to the user. The user can review the suggested dish list and make adjustments as necessary. This allows the user to order the meal that best suits their mood and environment that day.

[1898] Specific examples

[1899] Example 1: Lunch on a hot summer day (casual style)

[1900] User: Prefers casual style and has often worn T-shirts and shorts in the past.

[1901] Current location and climate: Tokyo, July, temperature 35°C, humidity 75%

[1902] session:

[1903] The user's device uploads past clothing photos and preferences to the server.

[1904] The server generates a style profile using image analysis and natural language processing.

[1905] The server uses a weather data API to obtain weather information for the current location.

[1906] A generative AI model (GPT-3) generates suggestions such as cold drinks and light salads.

[1907] A list of suggested foods is sent to the user's device, such as chilled salad, iced latte, and chilled tofu.

[1908] Example prompt: "Please suggest some dishes that would make you feel casual in Tokyo during the summer. The user's preference is casual, and the days are often hot."

[1909] Example 2: Winter evening dinner (formal style)

[1910] User: Prefers formal style and has worn suits and coats many times in the past.

[1911] Current location and climate: New York, December, 0°C, snow

[1912] session:

[1913] The user's device uploads past clothing photos and preferences to the server.

[1914] The server generates a style profile using image analysis and natural language processing.

[1915] The server uses a weather data API to obtain weather information for the current location.

[1916] A generative AI model (GPT-3) generates suggestions for hot soups, stews, and other dishes.

[1917] A list of suggested foods is sent to the user's device, such as tomato soup, a glass of wine, and warm bread.

[1918] Example prompt: "What are some recommendations for a formal winter dinner in New York? Something suitable for a cold or snowy day would be good."

[1919] In this way, our system can provide optimal food delivery options by integrating a user's past clothing photos and preferences with current weather information and using a generative AI model, allowing users to enjoy the food that best suits their mood and environment.

[1920] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1921] Step 1:

[1922] When a user logs in to the application, the user's device uploads past clothing photos and preference data. The user enters past clothing photos (image files) and text information about preferences (color, design, material, etc.) into an input form. The uploaded data is sent to the server. (Input): Past clothing photos, text information about the user's preferences (Output): Data sent to the server

[1923] Step 2:

[1924] The server performs image analysis based on the received data. The image analysis model (TensorFlow or PyTorch) analyzes the uploaded image file and extracts the user's style characteristics (type of clothing, color, design, material, etc.). At the same time, a natural language processing model (BERT, etc.) analyzes the text information to specifically understand the user's preferences. (Input): Uploaded image file and text information (Output): Analysis results of style characteristics and preferences

[1925] Step 3:

[1926] The server generates a style profile for the user based on the analysis results. The style profile integrates data extracted from the user's past clothing photos and preferences, and clearly indicates the user's fashion trends. The generated style profile is stored in a cloud database (such as Firebase). (Input): Analysis results of style features and preferences (Output): Generated style profile

[1927] Step 4:

[1928] The user device acquires the user's current location information and sends it to the server. The server uses a weather data API (such as OpenWeatherMap) based on the received current location information to acquire real-time weather data (temperature, humidity, weather forecast, etc.). The acquired weather data is stored in a cloud database and associated with the user's style profile. (Input): Current location information (Output): Acquired weather data

[1929] Step 5:

[1930] The server combines the generated style profile with weather data and generates optimal food delivery options using a generative AI model (such as GPT-3). The generative AI model creates an optimal dish list based on the user's mood, style, and climate based on the prompt. (Input): Style profile, weather data, prompt (Output): Optimal food delivery options

[1931] Step 6:

[1932] The server sends the generated food list to the user's device and notifies the user. The user can review the proposed food list and make adjustments as necessary. The final adjusted list is sent back to the server, and the necessary information is stored in the cloud database. (Input): Generated food list (Output): Food list sent to the user's device

[1933] This allows users to choose the dish that best suits their mood and the environment at the time and enjoy a comfortable meal.

[1934] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1935] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1936] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1937] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1938] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1939] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1940] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1941] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1942] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1943] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1944] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1945] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1946] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1947] 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.

[1948] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1949] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1950] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1951] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1952] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1953] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1954] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1955] The following is further disclosed regarding the above embodiment.

[1956] (Claim 1)

[1957] means for analyzing a user's past clothing photos and preferences to generate a personal style profile;

[1958] A way to obtain the latest weather data for your travel destination and understand climate information in real time.

[1959] A way to suggest clothing that matches your style, taking into account the culture and trends of the destination, and

[1960] A means for automatically generating a list of necessary items based on the suggested outfit;

[1961] A means for assisting users in preventing duplication and shortages when packing;

[1962] A means to promote environmentally friendly fashion items,

[1963] A system including:

[1964] (Claim 2)

[1965] The system according to claim 1, further comprising means for integrating the generated style profile with climate information and cultural background of the travel destination and generating an optimal outfit list using AI.

[1966] (Claim 3)

[1967] 10. The system of claim 1, further comprising means for recommending environmentally friendly options and locally branded fashion items to the user.

[1968] "Example 1"

[1969] (Claim 1)

[1970] means for analyzing a user's past clothing photos and preferences to generate a personal style profile;

[1971] A way to obtain the latest weather data for your travel destination and understand climate ...

Claims

1. means for analyzing a user's past clothing photos and preferences to generate a personal style profile; A way to obtain the latest weather data for your travel destination and understand climate information in real time. A way to suggest clothing that matches your style, taking into account the culture and trends of the destination, and A means for automatically generating a list of necessary items based on the suggested outfit; A means for assisting users in preventing duplication and shortages when packing; A means to promote environmentally friendly fashion items, A system including:

2. The system according to claim 1, further comprising means for integrating the generated style profile with climate information and cultural background of the travel destination and generating an optimal outfit list using AI.

3. The system of claim 1 , further comprising means for recommending environmentally friendly options and locally branded fashion items to the user.

Images