System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring an image of clothes of a user; means for analyzing the acquired image and identifying a type, color, and style of the clothes worn by the user; means for inputting information on a destination and weather of the user; means for generating appropriate coordination based on the analysis result and the input information; means for presenting the generated coordination to the user; means for receiving feedback from the user, learning the feedback, and reflecting the feedback in next coordination generation; and means for recommending a purchase source of lacking furnishings.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] Many consumers lack confidence in fashion or have difficulty coordinating their outfits, and so they need a system that can properly evaluate their outfits and suggest optimal outfits. Conventional approaches have generally relied on individual stylists or static advice sites or applications, but these have the problem of being unable to adequately reflect real-time situations or individual preferences. [Means for solving the problem]

[0005] The present invention includes a means for acquiring an image of a user's outfit and analyzing the image to identify the type, color, and style of the outfit. It also includes a means for the user to input information about their destination and weather, and provides a means for generating an optimal outfit based on this information. It also includes a means for presenting the generated outfit to the user, receiving feedback, learning from it, and incorporating it into future suggestions. It also includes a means for recommending where to purchase items missing from the user's current outfit. This overall process realizes a real-time system that supports users in choosing fashion.

[0006] "User" refers to an individual who uses the system to receive advice on their clothing and suggestions for outfit coordination.

[0007] "Clothing image" refers to a video or photograph of the clothing currently being worn by the user, and includes still images or videos captured using a camera.

[0008] "Analysis" refers to the process of identifying attributes such as clothing type, color, and style based on the captured clothing image and converting them into data.

[0009] "Destination" refers to the place or destination that the user will visit that day, and is an element that is taken into consideration when suggesting outfits.

[0010] "Weather information" refers to the weather conditions (e.g. sunny, rainy, cloudy, temperature, etc.) for the date and time the user has planned, and is external data necessary to suggest the best outfit.

[0011] "Coordination" refers to suggestions regarding the user's outfit, including the combination of clothing and the selection of accessories to create the optimal outfit.

[0012] "Feedback" refers to the opinions and thoughts that users provide about the proposed outfits, and is data that the system uses to reflect in future suggestions.

[0013] "Learning" refers to the process of analyzing feedback data from users and using that information to improve the accuracy of the system's next suggestions.

[0014] "Missing items" refer to clothing or accessories that the user does not currently own but are necessary for the suggested outfit.

[0015] "Purchase locations" refers to information about online shops and physical stores where users can purchase missing items. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is composed of a user, a server, and a terminal.

[0038] overview

[0039] Users take a photo of their outfit using the camera on their smartphone or computer and send the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothing they are wearing. The user then uses their device to input information about their destination and weather for the day, which is then sent to the server. The server combines the analysis data with the input information, generates an optimal outfit, and presents it to the user. The user provides feedback, and the server uses that feedback to improve its next outfit suggestions. It also recommends places to purchase any clothing items the user is missing.

[0040] Program processing

[0041] Video Analysis

[0042] The server analyzes the received video data to identify the type of clothing (shirt, pants, accessories, etc.), color, and style the user is wearing. This analysis is performed using image recognition technology. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the style of the clothing. The resulting analysis data is stored in the server's internal database.

[0043] Coordinate generation

[0044] The device provides a means for the user to input information about their destination and weather, and sends that information to the server. Based on this information, the server uses a coordination suggestion module to generate optimal outfits. This module generates multiple coordination suggestions and evaluates each one. It also references an external fashion database, taking into account the latest fashion trends and seasonal styles.

[0045] Coordination presentation and feedback

[0046] The server selects the optimal outfit suggestions and sends them to the device as a recommendation list. The device displays them to the user. The user then enters feedback on the suggested outfits, which is sent to the server. The server stores the feedback and uses it in a machine learning module to learn about the user's preferences and patterns.

[0047] Purchase recommendation

[0048] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and sends information on where to purchase them to the device. The device displays this information to the user, providing links to online shops and information on nearby stores.

[0049] Specific examples

[0050] scenario

[0051] The user is going out to lunch with a friend this morning and is already dressed in a white shirt and jeans. The weather forecast predicts cloudy skies with rain.

[0052] flow

[0053] 1. The user takes a picture of a white shirt and jeans using the smartphone camera.

[0054] 2. The device sends the video data to the server.

[0055] 3. The server analyzes the video and identifies the white shirt and jeans.

[0056] 4. The user inputs the destination (lunch with a friend) and the weather (cloudy with rain) into the terminal.

[0057] 5. The device sends the input information to the server.

[0058] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[0059] 7. The server sends the proposal to the device.

[0060] 8. The device displays the suggestions to the user.

[0061] 9. The user provides feedback that they do not own a cardigan.

[0062] 10. The device sends the feedback to the server.

[0063] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[0064] 12. The terminal displays the supplier information to the user.

[0065] This process allows users to receive optimal fashion suggestions and easily obtain purchasing information to supplement any clothing shortages, thereby improving their fashion sense and giving them confidence in their everyday coordination.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The user takes a photo of their outfit using the camera on their smartphone or computer.

[0069] Step 2:

[0070] The video data acquired by the terminal is transmitted to the server.

[0071] Step 3:

[0072] The server begins analyzing the received video data.

[0073] Step 4:

[0074] The server's image recognition module identifies the type of clothing the user is wearing (e.g., shirt, pants, accessories, etc.) from the video.

[0075] Step 5:

[0076] The server's color recognition algorithm analyzes the color of each item.

[0077] Step 6:

[0078] The server's style recognition algorithm identifies the clothing style (e.g., casual, formal, etc.).

[0079] Step 7:

[0080] The server stores the analysis results in an internal database.

[0081] Step 8:

[0082] The user uses the terminal to input information about the destination and weather for the day.

[0083] Step 9:

[0084] The terminal sends the entered destination, schedule and weather data to the server.

[0085] Step 10:

[0086] The server combines the received destination and weather data with the analysis data.

[0087] Step 11:

[0088] The server's coordination suggestion module generates optimal coordination based on the analysis data and user information.

[0089] Step 12:

[0090] The server creates multiple coordination proposals and evaluates each one.

[0091] Step 13:

[0092] The server selects the most suitable coordination plan based on the evaluation results.

[0093] Step 14:

[0094] The server creates a recommendation list and sends it to the device.

[0095] Step 15:

[0096] The device displays the recommendation list to the user.

[0097] Step 16:

[0098] The user inputs feedback on the coordination into the terminal.

[0099] Step 17:

[0100] The terminal transmits the user's feedback data to the server.

[0101] Step 18:

[0102] The server stores the feedback data, and the machine learning module uses it to learn user preferences and patterns.

[0103] Step 19:

[0104] The server's item recommendation module identifies items that are missing from the user's outfit or outfit.

[0105] Step 20:

[0106] The server generates supplier information for the missing items.

[0107] Step 21:

[0108] The server sends the supplier information to the terminal.

[0109] Step 22:

[0110] The terminal displays the supplier information to the user.

[0111] Example 1

[0112] 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."

[0113] Conventional fashion coordination suggestion systems have problems such as difficulty in suggesting outfits that reflect the user's appropriate destination or weather information, or when the user does not accurately understand their own outfit. Furthermore, if the user is not satisfied with the suggested outfit, there is no mechanism to reflect that feedback in the next suggestion. Furthermore, there is also a lack of a way to quickly provide information on where to purchase missing items.

[0114] 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.

[0115] In this invention, the server includes: means for acquiring an image of the user's clothing; means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user; means for inputting information about the user's destination and weather; means for generating an appropriate outfit based on the analysis results and the input information; means for presenting the generated outfit to the user; means for receiving feedback from the user, learning from the feedback, and incorporating it into the next outfit generation; means for recommending where to purchase missing clothing accessories; means for identifying the color and style of clothing using image recognition technology; means for learning the user's preferences and patterns using a machine learning module; means for referencing an external fashion database to generate outfits; means for evaluating outfit suggestions based on the user's destination and weather information; and means for providing links to online shops and nearby store information. This allows the server to accurately analyze the user's current fashion situation and propose optimal outfits based on the weather and destination. Furthermore, the server can reflect the user's feedback in the next outfit proposal and quickly provide information on where to purchase missing items.

[0116] "User" refers to an individual who uses the system to photograph, input, and provide feedback about their outfit.

[0117] "Server" refers to a central processing unit that receives data sent by users, analyzes, stores, learns from, and reflects coordination suggestions and feedback.

[0118] A "terminal" is a device used by a user, such as a smartphone or PC, and refers to an interface means for taking images, inputting information, displaying outfit suggestions, etc.

[0119] "Image recognition technology" is a technology that automatically identifies objects, shapes, colors, etc. from acquired image data, and primarily utilizes deep learning models and algorithms.

[0120] "Machine learning module" refers to artificial intelligence (AI) technology or software programs that learn from user feedback data and improve the accuracy of future outfit suggestions.

[0121] The "coordination suggestion module" refers to a software program that generates optimal outfit combinations by referencing a fashion database based on the user's clothing analysis data and input information.

[0122] A "fashion database" refers to a database that contains the latest fashion trends, style information according to the season, brand information, etc.

[0123] "Feedback" refers to input information such as evaluations, opinions, and comments made by users regarding the proposed coordination.

[0124] "Purchaser information" refers to links to online shops and information on physical stores provided as places to purchase new clothing items that the user needs.

[0125] "Destination information" refers to information about places and events that the user plans to go to.

[0126] "Weather information" refers to information about the weather conditions at the user's location or the location where the user plans to go.

[0127] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is mainly composed of a user, a server, and a terminal.

[0128] System Overview

[0129] The user uses the camera on their smartphone or computer to take a picture of their current outfit and sends the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothes the user is wearing. The user then uses their device to input information such as their destination and weather, which is then sent to the server. The server then combines the analysis data with the input information to generate an optimal outfit and present it to the user. It receives feedback from the user and reflects it in generating the next outfit. It also provides information on where to purchase any clothing items the user does not own.

[0130] System configuration and processing

[0131] Video Analysis

[0132] The server analyzes the received video data. This analysis uses image recognition technologies such as TensorFlow and OpenCV. Specifically, it extracts contours from the transmitted image data, identifies the color of the clothing using a color recognition algorithm, and determines the type of clothing and silhouette using a style recognition algorithm. The resulting data is stored in the server's internal database.

[0133] Coordinate generation

[0134] The device provides a means for users to input destination and weather information, and sends that information to the server. The server then uses a coordination suggestion module to combine the user's clothing analysis data with the input information to generate optimal outfits. This module references an external fashion database (e.g., Polyvore API) and takes into account the latest fashion trends and seasonal styles.

[0135] Coordination presentation and feedback

[0136] The server sends the generated outfits to the device, which displays them to the user. The user can then enter feedback about the outfit suggestions, which is then sent back to the server. The server stores the feedback and uses a machine learning module to improve the accuracy of the next outfit suggestions.

[0137] Purchase recommendation

[0138] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and generates information on where to purchase them. The generated information is sent to the user's device and provided to them. Specifically, it includes links to online shops and information on nearby stores.

[0139] Specific examples

[0140] Consider a scenario where a user is going out to lunch with a friend on the following date and is wearing a white shirt and jeans. The weather forecast is cloudy with rain.

[0141] flow

[0142] 1. A user takes a picture of a white shirt and jeans using the smartphone camera.

[0143] 2. The device sends the video data to the server.

[0144] 3. The server analyzes the video and identifies the white shirt and jeans.

[0145] 4. The user inputs the destination ("lunch with a friend") and the weather ("cloudy with rain") into the terminal.

[0146] 5. The device sends the input information to the server.

[0147] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[0148] 7. The server sends the proposal to the device.

[0149] 8. The device displays the suggestions to the user.

[0150] 9. The user provides feedback that they do not own a cardigan.

[0151] 10. The device sends the feedback to the server.

[0152] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[0153] 12. The terminal displays the supplier information to the user.

[0154] Prompt Sentence Examples

[0155] User outfit image: [image file]

[0156] Destination: Lunch with a friend

[0157] Weather: Cloudy with rain

[0158] Please suggest the best outfit to go with my current outfit. Also, please let me know where to buy any items that are missing from the suggested outfit.

[0159] This system not only allows users to receive suggestions for the perfect outfit for the day, but also makes it easy to find out how to purchase any missing items. Through this process, users can improve their fashion sense and gain confidence.

[0160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0161] Step 1:

[0162] The user takes a photo of their own outfit using the camera on their smartphone or computer. The input is image data of the outfit. Specifically, the user launches the camera app and presses the capture button to take a full-body shot of the outfit they are currently wearing. The output is the captured image data.

[0163] Step 2:

[0164] The device sends the captured image data to the server. The input is the image data captured by the user. Specifically, the device uploads this image data to the specified server URL via the Internet. The output is the image data sent to the server.

[0165] Step 3:

[0166] The server analyzes the received image data and identifies the type, color, and style of clothing worn by the user. The input is image data sent from the device. Specifically, the server first preprocesses the image (e.g., noise removal), then uses TensorFlow or OpenCV to identify the color of the clothing using k-means clustering, and uses a deep learning model (e.g., ResNet or YOLO) to determine the type of clothing and silhouette. The output is analytical data related to the type, color, and style of clothing.

[0167] Step 4:

[0168] The user uses the device to input destination and weather information. The input includes clothing data after video analysis, the destination (e.g., "lunch with friends"), and the weather (e.g., "cloudy with rain"). Specifically, the user enters the destination and weather information into the app's input form and presses the send button. The output is the destination and weather information entered into the device.

[0169] Step 5:

[0170] The terminal transmits the destination and weather information input by the user to the server. The input is the destination and weather information input by the user to the terminal. In concrete terms, the terminal transmits this information to the server via the Internet. The output is the destination and weather information transmitted to the server.

[0171] Step 6:

[0172] The server integrates the analysis data with the information entered by the user and generates the optimal outfit using the outfit suggestion module. The input is the clothing analysis data, destination, and weather information. Specifically, the server queries an external fashion database, generates multiple outfit suggestions that meet the conditions, and selects the optimal suggestion based on the destination and weather conditions. The output is the outfit suggestion presented to the user.

[0173] Step 7:

[0174] The server transmits the generated coordination plan to the terminal. The input is the optimal coordination plan. In concrete terms, the server transmits the selected coordination plan to the terminal via the Internet. The output is the coordination plan transmitted to the terminal.

[0175] Step 8:

[0176] The terminal displays the outfit suggestions received from the server to the user. The input is the outfit suggestions sent from the server. As a specific operation, the outfit suggestions are visually displayed on the screen of the terminal. The output is the outfit suggestions that the user can view.

[0177] Step 9:

[0178] The user inputs feedback on the proposed outfit. The input is the proposed outfit. Specifically, the user enters comments and ratings into the app's feedback form and presses the send button. The output is the feedback information entered into the device.

[0179] Step 10:

[0180] The terminal sends the feedback information to the server. The input is the feedback information entered by the user. In concrete terms, the terminal sends this information to the server via the Internet. The output is the feedback information sent to the server.

[0181] Step 11:

[0182] The server stores the feedback and uses it in a machine learning module to improve the next coordination proposal. The input is the feedback information. Specifically, the server stores the feedback information in a database and uses it to update the machine learning model. The output is an improved coordination model.

[0183] Step 12:

[0184] The server's item recommendation module identifies missing items in the user's outfit or the proposed outfit, and generates information on where to purchase them. The input is the proposed outfit and feedback information. Specifically, the server identifies the missing item (e.g., a "gray cardigan") and collects information on online shops and nearby stores. The output is information on where to purchase them.

[0185] Step 13:

[0186] The server sends the generated supplier information to the terminal. The input is the supplier information. In concrete terms, the server sends the supplier information to the terminal via the Internet. The output is the supplier information sent to the terminal.

[0187] Step 14:

[0188] The terminal displays the supplier information to the user. The input is the supplier information sent from the server. As a specific operation, the supplier information is visually displayed on the terminal screen. The output is the supplier information that the user can view.

[0189] (Application example 1)

[0190] 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."

[0191] In modern society, there is a demand for assistance in optimizing the coordination of users' clothing. Efficient and personalized coordination suggestions and purchasing support are essential, especially for users who struggle with daily fashion choices. However, current systems struggle to analyze users' clothing in real time and provide optimal coordination suggestions based on various criteria, as well as information on where to purchase missing items. Furthermore, there is a lack of systems that allow users to virtually try on suggested coordinations. Therefore, a means is needed that allows users to easily receive high-quality fashion advice while also receiving purchasing support.

[0192] 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.

[0193] In this invention, the server includes means for acquiring an image of the user's clothing, means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user, and means for inputting information on the user's destination and weather, thereby enabling the user to receive optimal outfit suggestions.

[0194] The server further includes a means for generating an appropriate outfit based on the analysis results and input information, a means for presenting the generated outfit to the user and enabling virtual try-on, a means for receiving feedback from the user, learning from it, and reflecting it in generating the next outfit, and a means for recommending places to purchase missing clothing items and providing links to online stores. This allows the user to not only receive outfit suggestions in real time, but also personalized suggestions that reflect the user's feedback, and easily purchase missing items.

[0195] "Image acquisition means" refers to a device or function for capturing images of a user's clothing in real time, and includes image capture devices such as smartphones, smart glasses, and head-mounted displays.

[0196] "Video analysis means" refers to software or algorithms that analyze captured video data in real time and identify the type, color, and style of clothing worn by the user.

[0197] "Information input means" refers to a function that provides an interface for users to input destination and weather information, and includes the use of a mobile information terminal or a personal computer.

[0198] "Coordination generation means" refers to an algorithm or module that generates appropriate clothing combinations based on the results of video analysis and information entered by the user.

[0199] The "coordinate presentation means" refers to an interface or device for visually displaying the generated coordinates to the user, and also includes a function that allows virtual try-on.

[0200] "Feedback means" refers to a function that provides an interface for receiving opinions and reactions from users regarding coordination suggestions, learns from them, and reflects them in the next suggestion.

[0201] "Purchase recommendation means" refers to a function for providing information on where to purchase items that are missing from the proposed outfit, and includes providing links to online stores.

[0202] "Internal database" refers to a database that stores analyzed data and user feedback and is used within the system.

[0203] "External database" refers to an external fashion information service that is referenced to obtain the latest fashion trends and seasonal style information.

[0204] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is composed of a user, a server, and a terminal.

[0205] System Configuration

[0206] The system includes the following main measures:

[0207] 1. Image acquisition means: A device or function for capturing images of the user's clothing in real time. This uses an image capture device such as a smartphone, smart glasses, or a head-mounted display.

[0208] 2. Video analysis means: This refers to software and algorithms that analyze captured video data in real time and identify the type, color, and style of clothing worn by the user. Specifically, OpenCV and TensorFlow are used.

[0209] 3. Information input means: This function provides an interface for users to input destination and weather information, and uses the user interface of a smartphone or PC.

[0210] 4. Coordination generation means: Algorithms and modules that generate appropriate clothing combinations based on the results of video analysis and input information, taking into account the user's preferences and the latest fashion database.

[0211] 5. Coordination presentation means: A function for visually displaying the generated coordination to the user, including an interface that allows virtual try-on.

[0212] 6. Feedback means: This function provides an interface for receiving opinions and reactions from users regarding coordination suggestions, and learns from that feedback and reflects it in future suggestions.

[0213] 7. Purchasing recommendation tool: This function provides information on where to purchase items that are missing from the suggested outfit, including links to online stores.

[0214] System Operation

[0215] 1. Image acquisition:

[0216] Users take photos of their outfits in real time using the camera on their smartphone or smart glasses.

[0217] The captured video data is immediately sent to a server for analysis.

[0218] 2. Video analysis:

[0219] The server uses OpenCV and TensorFlow to analyze the transmitted video data and identify the type of clothing (e.g., shirt, pants, dress, etc.), color, and style the user is wearing.

[0220] 3. Enter your information:

[0221] The user inputs destination and weather information through the terminal interface, which is then sent to the server.

[0222] Example prompt statement:

[0223] user_info = {

[0224] 'location': 'Tokyo',

[0225] 'event': 'Lunch with a friend'

[0226] }

[0227] 4. Coordinate generation:

[0228] Based on the video analysis results and the input information, the server refers to the latest fashion database and the user's past feedback information to generate the optimal outfit.

[0229] The generated coordinates are saved as information and sent to the user's terminal.

[0230] 5. Coordination presentation and virtual try-on:

[0231] The terminal visually displays the generated outfits to the user, allowing the user to virtually try on the suggested outfits.

[0232] 6. Feedback:

[0233] The user inputs their opinions and reactions to the proposed coordination through the terminal, which are then sent to the server.

[0234] The server learns from the feedback it receives and understands the user's preferences and patterns.

[0235] 7. Purchase recommendation:

[0236] The server's item recommendation module identifies items missing from the proposed outfit and generates purchasing information and links to online shops.

[0237] The terminal displays the recommended vendor information to the user.

[0238] Specific examples

[0239] For example, if a user is going out to lunch with a friend this morning and is wearing a white shirt and jeans, and the weather forecast predicts cloudy skies with rain, the system will operate as follows:

[0240] 1. The user uses the smartphone camera to take a picture of a white shirt and jeans.

[0241] 2. The captured video data is sent to the server.

[0242] 3. The server analyzes the video and identifies the white shirt and jeans.

[0243] 4. The user inputs the destination (lunch with a friend) and the weather (cloudy with rain) into the terminal.

[0244] 5. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[0245] 6. The server sends the proposal to the device.

[0246] 7. The device displays the suggestions to the user, who then virtually tries them on.

[0247] 8. The user provides feedback that they do not own a cardigan.

[0248] 9. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[0249] 10. The terminal displays the purchasing information to the user, and the user can purchase the cardigan from the online shop.

[0250] By following this process, users can easily purchase any missing items while receiving suggestions for optimal outfits.

[0251] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0252] Step 1: The user takes a picture of their outfit in real time using the camera on their smartphone or smart glasses. The captured video data is immediately sent to the server.

[0253] Input: Video data of the clothes worn by the user.

[0254] Output: Sending video data to the server.

[0255] How it works: The user turns on the camera on their smartphone and takes a full-body video of themselves. This video data is then uploaded to a cloud server in real time.

[0256] Step 2: The server uses OpenCV and TensorFlow to analyze the transmitted video data and identify the type, color, and style of clothing the user is wearing.

[0257] Input: Video data sent to the server.

[0258] Output: Analyzed data about clothing type, color, and style.

[0259] How it works: Image recognition algorithms running on the server identify the type of clothing (shirt, pants, etc.) as well as their color and style from the video data. The resulting analysis data is stored in an internal database.

[0260] Step 3: The user inputs destination and weather information through the terminal interface, which is then sent to the server.

[0261] Input: Destination and weather information.

[0262] Output: Sending information to the server.

[0263] Specific operation: The user uses a smartphone app to enter the location they plan to go to that day and weather forecast information, and then submits the form.

[0264] Step 4: The server's coordinate generation means generates an optimal coordinate based on the video analysis results and the information input by the user, by referring to the latest fashion database and the user's past feedback information.

[0265] Input: Analysis data, user destination and weather information.

[0266] Output: Optimal outfit ideas.

[0267] Specific operation: The server searches a fashion database for the latest trends and weather-appropriate combinations, and generates optimal outfit suggestions for shirts, pants, and accessories.

[0268] Step 5: The terminal visually displays the generated outfit to the user, allowing the user to virtually try on the suggested outfit.

[0269] Input: Generated coordinate plan.

[0270] Output: Visual presentation of outfits and virtual try-on.

[0271] Specific operation: The device displays outfit ideas on the application interface, and the user tries them on in a virtual environment.

[0272] Step 6: The user inputs their opinions and reactions to the proposed coordination through the terminal, which are then sent to the server.

[0273] Input: User feedback.

[0274] Output: Sending feedback to the server.

[0275] Specific operation: The user enters their thoughts and opinions about the outfit into the feedback form within the application and presses the submit button.

[0276] Step 7: The server learns from the received feedback and understands the user's preferences and patterns. It uses the generative AI model to reflect this in the next outfit suggestions.

[0277] Input: User feedback data.

[0278] Output: Improved outfit suggestions.

[0279] How it works: The server stores the feedback information in a database, and the generative AI model uses this information to learn user preferences and patterns.

[0280] Step 8: The server's item recommendation module identifies the missing items and generates purchasing information and links to online shops.

[0281] Input: User's current belongings information and coordination suggestions.

[0282] Output: Purchase information and online shop link.

[0283] Specific operation: The server retrieves purchasing information from an internal database and external shopping sites and sends it to the user's device.

[0284] Step 9: The terminal displays the recommended purchasing information to the user, and the user can purchase the missing items online based on the recommended purchasing information.

[0285] Input: Supplier information and shopping links.

[0286] Output: Providing information to the user and assisting them in making a purchase.

[0287] Specific operation: The device displays the purchasing information and link on the application display screen, and the user can purchase the item from the online shop by clicking the link.

[0288] This flow of processing steps allows the user to efficiently receive suggestions for optimal outfits while easily obtaining the items they need.

[0289] 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.

[0290] This invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. This system is comprised of a user, a server, and a terminal, and also incorporates an emotion engine that recognizes the user's emotions.

[0291] overview

[0292] Users take pictures of their outfits using the camera on their smartphone or computer and send the images to the server. The server analyzes the image data and identifies the type, color, and style of the clothes they are wearing. The user then inputs their destination and weather information for the day using their device, which is then sent to the server. The server then combines the analysis data, the input information, and the user's emotions, as recognized by the emotion engine, to generate an optimal outfit. This generated outfit matches the user's mood. The user provides feedback on the suggested outfit, and the server uses that feedback to improve its next outfit suggestions. The server also recommends places to purchase any clothing items the user is missing.

[0293] Program processing

[0294] Video Analysis

[0295] The server analyzes the received video data and identifies the type of clothing (e.g., shirt, pants, accessories, etc.), color, and style) worn by the user. This analysis is performed using image recognition technology. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the style of the clothing. The resulting analysis data is stored in the server's internal database.

[0296] Emotion analysis

[0297] The device provides a means to acquire the user's facial expressions and voice in real time and transmits the data to a server. An emotion engine installed on the server analyzes the user's emotions based on this data. The emotion engine uses facial expression recognition and voice analysis technology to determine the user's current emotion (e.g., joy, sadness, excitement, fatigue).

[0298] Coordinate generation

[0299] The device provides a means for the user to input information about their destination and weather, and sends that information to the server. Based on this, the server uses a coordination suggestion module to generate optimal outfits. This module generates multiple outfit suggestions based on analytical data, emotional data, and user information, and evaluates each one. It also references an external fashion database, taking into account the latest fashion trends and seasonal styles. It also adjusts the style of the suggested outfits based on the user's emotions, presenting outfits that suit the user's mood.

[0300] Coordination presentation and feedback

[0301] The server selects the optimal outfit suggestions and sends them to the device as a recommendation list. The device displays them to the user. The user then enters feedback on the suggested outfits, which is sent to the server. The server stores the feedback and uses it in a machine learning module to learn about the user's preferences and patterns.

[0302] Purchase recommendation

[0303] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and sends information on where to purchase them to the device. The device displays this information to the user, providing links to online shops and information on nearby stores.

[0304] Specific examples

[0305] scenario

[0306] The user is planning to go out to lunch with a friend this morning and is already dressed in a white shirt and jeans. The weather forecast predicts cloudy skies with rain. The user is feeling a little tired, but is looking forward to a fun lunch.

[0307] flow

[0308] 1. A user takes a picture of a white shirt and jeans using their smartphone camera.

[0309] 2. The device sends the video data to the server.

[0310] 3. The server analyzes the video and identifies the white shirt and jeans.

[0311] 4. The user inputs a destination (lunch with a friend) and weather (cloudy with rain) into the terminal.

[0312] 5. The device sends the input information to the server.

[0313] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[0314] 7. The server sends the proposal to the device.

[0315] 8. The device displays the suggestions to the user.

[0316] 9. The user provides feedback that they do not own a cardigan.

[0317] 10. The device sends the feedback to the server.

[0318] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[0319] 12. The terminal displays the supplier information to the user.

[0320] 13. The user provides facial expression and voice data through the terminal.

[0321] 14. The device sends facial expression and voice data to the server.

[0322] 15. The server's emotion engine analyzes the user's emotions and suggests additional outfits that emphasize a happy mood (e.g., brightly colored accessories).

[0323] This process allows users to receive optimal fashion suggestions and easily obtain purchasing information to supplement any clothing shortages. Furthermore, adjustments are made to match the user's emotions, further increasing satisfaction with everyday coordination.

[0324] The processing flow will be explained below.

[0325] Step 1:

[0326] The user takes a photo of their outfit using the camera on their smartphone or computer.

[0327] Step 2:

[0328] The video data acquired by the terminal is transmitted to the server.

[0329] Step 3:

[0330] The server begins analyzing the received video data.

[0331] Step 4:

[0332] The server's image recognition module identifies the type of clothing the user is wearing (e.g., shirt, pants, accessories, etc.) from the video.

[0333] Step 5:

[0334] The server's color recognition algorithm analyzes the color of each item.

[0335] Step 6:

[0336] The server's style recognition algorithm identifies the clothing style (e.g., casual, formal, etc.).

[0337] Step 7:

[0338] The server stores the analysis results in an internal database.

[0339] Step 8:

[0340] The user uses the terminal to input information about the destination and weather for the day.

[0341] Step 9:

[0342] The terminal sends the entered destination, schedule and weather data to the server.

[0343] Step 10:

[0344] The server combines the received destination and weather data with the analysis data.

[0345] Step 11:

[0346] The user provides emotional data such as facial expressions and voice through the terminal.

[0347] Step 12:

[0348] The device transmits the emotion data to the server.

[0349] Step 13:

[0350] The server's emotion engine uses facial expression recognition and voice analysis technology to analyze the user's emotions (e.g., joy, sadness, excitement, fatigue, etc.).

[0351] Step 14:

[0352] The server's coordination suggestion module generates optimal coordination based on analysis data, emotion data, and user information.

[0353] Step 15:

[0354] The server creates multiple coordination proposals and evaluates each one.

[0355] Step 16:

[0356] The server selects the most suitable coordination plan based on the evaluation results.

[0357] Step 17:

[0358] The server creates a recommendation list and sends it to the device.

[0359] Step 18:

[0360] The device displays the recommendation list to the user.

[0361] Step 19:

[0362] The user inputs feedback on the proposed coordination into the terminal.

[0363] Step 20:

[0364] The terminal transmits the user's feedback data to the server.

[0365] Step 21:

[0366] The server stores the feedback data, and the machine learning module uses it to learn user preferences and patterns.

[0367] Step 22:

[0368] The server's item recommendation module identifies items that are missing from the user's outfit or outfit.

[0369] Step 23:

[0370] The server generates information on where to purchase the missing items and transmits it to the terminal.

[0371] Step 24:

[0372] The terminal displays the supplier information to the user.

[0373] Example 2

[0374] 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."

[0375] Conventional fashion coordination assistant systems can make suggestions based on the user's clothing and style, destination, weather information, etc., but they cannot generate coordinations that take the user's emotions into consideration, so they have the problem of not being able to make suggestions that fully reflect the user's mood.In addition, they lack the function to specifically recommend clothing items that the user is lacking, making it difficult for users to easily purchase the items needed for the suggested coordination.

[0376] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring an image of the user's clothing, means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user, means for inputting information about the user's destination and weather, means for generating an appropriate outfit based on the analysis results and the input information, means for presenting the generated outfit to the user, means for receiving feedback from the user, learning from the feedback, and reflecting it in generating the next outfit, means for analyzing the user's emotions, means for adjusting the outfit based on the emotions, and means for recommending where to purchase missing clothing and accessories. This makes it possible to suggest an optimal outfit based on the user's mood, and by specifically recommending where to purchase missing items, the user can quickly obtain the items they need.

[0377] "User" refers to a person who uses the system to improve or receive suggestions for their own clothing coordination.

[0378] "Outfit image" refers to digital image data that contains visual information about the clothing and accessories worn by a user.

[0379] "Means for acquiring" refers to a device or technology that allows a user to take an image of the outfit and send the image to the system.

[0380] "Means for analyzing" refers to technology for identifying the type, color, and style of clothing worn by a user based on the acquired image data.

[0381] "Means for identifying" refers to technology for identifying specific attributes of the clothing worn by the user based on the analysis results.

[0382] "Input means" refers to the devices and technologies that allow users to input destination and weather information.

[0383] "Means for generating appropriate coordination" refers to technology for proposing optimal clothing combinations to users based on analysis results and input information.

[0384] "Presenting means" refers to a device or technology for showing the generated coordinates to the user.

[0385] "Means for receiving feedback" refers to technology that allows users to input their thoughts and requests regarding the proposed outfits and send that information to the system.

[0386] "Means of learning" refers to technology that uses user feedback to improve the next outfit suggestion.

[0387] "Means for analyzing emotions" refers to technology for identifying emotions based on a user's facial expressions and voice data.

[0388] The term "means for adjusting a coordination based on emotions" refers to a technique for adjusting an optimal coordination for a user in consideration of the analyzed emotions of the user.

[0389] "Means for recommending where to purchase missing clothing items" refers to technology for showing a user where to purchase missing items based on the suggested outfit.

[0390] This invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. This system is comprised of a user, a server, and a terminal, and also incorporates an emotion analysis engine that recognizes the user's emotions.

[0391] Hardware and software used

[0392] The server is equipped with image recognition technology, an emotion analysis engine, a coordination suggestion module, an item recommendation module, and a machine learning algorithm, which utilize the following specific technologies:

[0393] Image recognition technology: color recognition algorithm, style recognition algorithm

[0394] Emotion analysis engine: facial expression recognition technology, voice analysis technology

[0395] Coordination suggestion module: Includes the function to refer to external fashion databases

[0396] Item recommendation module: Online shop link generation function, nearby store information acquisition function

[0397] Machine learning algorithms: Ability to learn from feedback data

[0398] The device includes a camera that captures images of the user's outfit, an interface for inputting destination and weather information, and a display that shows suggested outfits and shopping information.

[0399] Users can use these functions using smartphones or computers.

[0400] Coordination proposal process

[0401] Users use their smartphone or PC camera to take a picture of their outfit and send the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothes they are wearing. The user then inputs their destination and weather information for the day via their device, which is then sent to the server. The server then combines the analysis data, the input information, and the user's emotional data recognized by an emotion analysis engine to generate the optimal outfit. The generated outfit matches the user's mood.

[0402] For example, suppose a user is planning to go out to lunch with a friend this morning and is wearing a white shirt and jeans. The weather forecast predicts cloudy skies with rain, and the user is feeling a little tired but is looking forward to a pleasant lunch. In this situation, the flow of using the system is as follows:

[0403] 1. A user takes a picture of a white shirt and jeans using their smartphone camera.

[0404] 2. The device sends the video data to the server.

[0405] 3. The server analyzes the video and identifies the white shirt and jeans.

[0406] 4. The user inputs a destination (lunch with a friend) and weather (cloudy with rain) into the terminal.

[0407] 5. The device sends the input information to the server.

[0408] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots.

[0409] 7. The server sends the proposal to the terminal, which displays it to the user.

[0410] 8. The user provides feedback that they do not own a cardigan.

[0411] 9. The device sends the feedback to the server.

[0412] 10. The server stores the feedback and generates and sends information about where to buy the cardigan to the device.

[0413] 11. The device displays the retailer information to the user.

[0414] 12. The user provides facial expression and voice data through the terminal.

[0415] 13. The device sends facial expression and voice data to the server.

[0416] 14. The server's emotion analysis engine analyzes the user's emotions and suggests additional accessories that emphasize a happy mood (e.g., a brightly colored scarf).

[0417] 15. The server sends the additional suggestions to the terminal, which displays them to the user.

[0418] This process not only allows users to receive optimal fashion suggestions, but also provides information on purchasing clothing items that they are lacking, and improves their satisfaction with their everyday outfits.

[0419] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0420] Step 1:

[0421] Users take a photo of their outfit using the camera on their smartphone or computer. Specifically, the user stands in front of a mirror and takes a photo that captures their entire body. The captured image is then saved as digital data on the device.

[0422] Input: Image of the user's outfit

[0423] Output: Digital image data

[0424] Step 2:

[0425] The terminal transmits the captured digital image data to a server via the Internet.

[0426] Input: Digital image data

[0427] Output: Image data sent to the server

[0428] Step 3:

[0429] The server analyzes the received digital image data. It uses image recognition technology to identify the type of clothing (e.g., shirt, pants), color, and style the user is wearing. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the type of clothing. The analysis results are stored in an internal database.

[0430] Input: Digital image data

[0431] Data processing and calculation: Color recognition algorithm, style recognition algorithm

[0432] Output: Analysis results (clothing type, color, style)

[0433] Step 4:

[0434] The user inputs information about the destination and weather for the day through the terminal, and the input information is sent from the terminal to the server.

[0435] Input: Destination information, weather information

[0436] Output: Destination information and weather information sent to the server

[0437] Step 5:

[0438] The server uses the outfit suggestion module to generate optimal outfits based on the analysis results and the destination and weather information entered by the user. During this process, it references an external fashion database to consider the latest trends and seasonal styles. It also uses the user's emotional data to consider outfits that suit their mood.

[0439] Input: Analysis results, destination information, weather information, emotion data

[0440] Data processing and calculation: External fashion database reference, coordinate generation algorithm

[0441] Output: Generated coordinate plan

[0442] Step 6:

[0443] The server selects one of the generated coordination plans and sends it to the terminal, which displays it to the user.

[0444] Input: Generated coordination plan

[0445] Output: Coordination ideas displayed to the user

[0446] Step 7:

[0447] The user inputs feedback about the proposed outfit. For example, the user inputs feedback such as "I don't own a cardigan" into the terminal. The feedback is sent from the terminal to the server.

[0448] Input: User feedback

[0449] Output: Feedback sent to the server

[0450] Step 8:

[0451] The server uses machine learning algorithms to learn from user feedback and suggests outfits, storing the feedback to improve future suggestions.

[0452] Input: Feedback data

[0453] Data processing and calculation: Machine learning algorithms

[0454] Output: Improved outfit suggestion data

[0455] Step 9:

[0456] The server's item recommendation module generates purchasing information for missing items (e.g., cardigans) based on the suggested outfits, including online shop links and nearby store locations.

[0457] Input: Feedback data

[0458] Data processing and calculation: Item recommendation algorithm

[0459] Output: Generated supplier information

[0460] Step 10:

[0461] The server transmits the generated supplier information to the terminal, which displays it to the user.

[0462] Input: Generated supplier information

[0463] Output: Supplier information displayed to the user

[0464] Step 11:

[0465] The user provides facial expression and voice data through the device, which is collected in real time and sent to the server.

[0466] Input: facial expression data, voice data

[0467] Output: Emotion data sent to the server

[0468] Step 12:

[0469] The server's emotion analysis engine analyzes the user's emotions from their facial expressions and voice. For example, it can use facial recognition technology to determine if the user is slightly tired. The results of this emotion analysis are also reflected in the outfit suggestions.

[0470] Input: facial expression data, voice data

[0471] Data processing and calculation: Emotion analysis algorithm

[0472] Output: Emotion analysis results

[0473] Step 13:

[0474] Based on the results of the emotion analysis, the server adjusts the outfit to suit the user's mood and generates additional suggestions, such as an accessory (such as a brightly colored scarf) that emphasizes a happy mood.

[0475] Input: Sentiment analysis results

[0476] Data processing and calculation: Coordinate adjustment algorithm

[0477] Output: Additional suggested coordinates

[0478] Step 14:

[0479] The server sends the additional suggestions to the terminal, which displays them to the user.

[0480] Input:Add suggested coordinates

[0481] Output: Additional outfit suggestions displayed to the user

[0482] In this way, users can not only receive optimal fashion suggestions through the system, but also obtain purchasing information for items they are lacking, and can receive coordination suggestions that correspond to their emotions.

[0483] (Application example 2)

[0484] 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."

[0485] Conventional outfit suggestion systems only consider the user's clothing and preferences, but do not consider emotions or real-time environmental changes. As a result, suggestions may be made that do not match the user's mood or the weather, resulting in low satisfaction. Also, if a suggested outfit is missing an item, there is insufficient means to supplement it. These issues need to be resolved.

[0486] 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.

[0487] In this invention, the server includes means for acquiring images of the user's clothing, means for analyzing the acquired images and identifying the type, color, and style of the clothing worn by the user, means for inputting information about the user's destination and weather conditions, means for acquiring the user's facial expressions and voice in real time and analyzing their emotions, means for adjusting and presenting the generated outfit in accordance with the user's emotions, means for receiving feedback from the user, learning from it, and reflecting it in generating the next outfit, and means for recommending where to purchase missing clothing accessories. This makes it possible to propose optimal outfits that take into account the user's emotions and real-time environmental changes.

[0488] The "means for acquiring an image of the user's clothing" refers to a device or technology for photographing the clothing currently being worn by the user.

[0489] "Means for analyzing the captured image and identifying the type, color, and style of clothing worn by the user" refers to technology that processes captured image data and identifies detailed characteristics of the clothing worn by the user.

[0490] The "means for inputting information on the user's destination and weather conditions" refers to a device or method for inputting the user's planned location and weather information for the day into the system.

[0491] "Means for acquiring a user's facial expressions and voice in real time and analyzing their emotions" refers to technology that acquires a user's facial expressions and tone of voice in real time and determines the user's emotional state based on that data.

[0492] "Means for adjusting and presenting the generated coordination in accordance with the user's emotions" refers to a device or method for optimizing the generated coordination to reflect the user's current emotional state and presenting it to the user.

[0493] "Means for receiving feedback from the user, learning from it, and reflecting it in the next coordination generation" refers to a learning technology that records the user's reactions and opinions and uses them to help generate the next coordination.

[0494] The "means for recommending where to purchase missing clothing accessories" is a technology that detects items that are missing from a proposed outfit and provides the user with information on where to purchase those items.

[0495] This invention is a system that acquires images of a user's clothing, analyzes them, and suggests outfits that suit the user's outfit. The system consists of a terminal, a server, and a user's device. Using smart glasses, a smartphone, a PC, or other devices, users can easily try on clothes virtually and receive fashion advice from the comfort of their own home.

[0496] 1. How to obtain images of the user's clothing

[0497] The user uses the camera in the smart glasses to take a picture of their own clothes in real time and captures the image. The smart glasses device collects the image data and sends it to the server.

[0498] 2. A means of analyzing the captured image and identifying the type, color, and style of clothing worn by the user.

[0499] The server analyzes the received image data to identify the type, color, and style of the user's clothing. This analysis is performed using algorithms from image recognition technologies (e.g., OpenCV and TensorFlow). For example, a color recognition algorithm determines the color, and a style recognition algorithm identifies the style of the clothing.

[0500] 3. A means of inputting information about the user's destination and weather conditions

[0501] Users can input their destination and weather information for the day through the smart glasses' voice assistant, which is then sent to the server and integrated with analytical data.

[0502] 4. A means of capturing the user's facial expressions and voice in real time and analyzing their emotions

[0503] The image data sent to the server is used to analyze the user's facial expressions and voice. Facial expression recognition technology (e.g., face_recognition) and voice analysis technology (e.g., emotion_recognition) are used to detect the user's current emotion (happiness, sadness, excitement, fatigue, etc.).

[0504] 5. A method for adjusting and presenting the generated outfits according to the user's emotions

[0505] Based on the analysis results, input information, and emotional data, the outfit suggestion module generates the optimal outfit. This module uses a generative AI model (e.g., a TensorFlow model) to evaluate multiple outfit suggestions. It also references an external fashion database to consider the latest fashion trends and seasonal styles. It adjusts the suggestions based on the user's emotions and presents outfits that suit the user's mood.

[0506] 6. A means to receive feedback from users, learn from it, and reflect it in the next coordinate generation

[0507] Users can provide feedback on the suggested outfits through the smart glasses, which is then sent to the server, where the machine learning module learns the user's preferences and patterns and reflects them in the next outfit suggestions.

[0508] 7. Recommendations for purchasing clothing items in short supply

[0509] The server's item recommendation module identifies missing items in an outfit and provides the user with information on where to purchase them. The suggested outfits and item information are displayed on the smart glasses, allowing the user to easily access links to online shops and nearby store locations.

[0510] Examples of concrete examples and prompts

[0511] Specific examples

[0512] For example, a user uses smart glasses to wear a white shirt and jeans at home. The user plans to go on a picnic in the park with friends the next day, and the weather forecast predicts sunny skies. The system also determines that the user is feeling a little tired. The system then suggests a bright-colored cardigan or colorful scarf to go with the white shirt and jeans, providing an outfit that will lift the user's spirits.

[0513] Prompt Sentence Examples

[0514] "Tomorrow I'm going to have a picnic in the park with a friend. The weather is sunny. I'm a little tired. Can you suggest some outfits that will make me feel energized?"

[0515] In this way, the present invention provides a system that takes into consideration the user's emotions and real-time environmental changes and proposes optimal outfits.

[0516] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0517] Step 1:

[0518] The user uses the camera in the smart glasses to take a picture of their clothing.

[0519] Specific operation: The user wears the smart glasses and captures an image of their entire outfit with the camera to obtain image data.

[0520] Input: Real-time clothing image

[0521] Output: Acquired clothing image data

[0522] Step 2:

[0523] The terminal transmits the acquired image data to the server.

[0524] Specific operation: The smart glasses are connected via Wi-Fi or Bluetooth and transmit the acquired image data to the server.

[0525] Input: Clothing image data

[0526] Output: Image data sent to the server

[0527] Step 3:

[0528] The server analyzes the transmitted image data and identifies the type, color, and style of clothing the user is wearing.

[0529] How it works: An image recognition algorithm running on the server extracts clothing features (type, color, style) from image data. It uses an image recognition model such as TensorFlow.

[0530] Input: Clothing image data

[0531] Output: Analysis results for clothing type, color, and style

[0532] Step 4:

[0533] The user inputs information about their destination and weather conditions through the voice assistant in the smart glasses.

[0534] Specific Actions: A user uses voice input to provide information about the destination for the day (e.g., going to the park) and weather conditions (sunny).

[0535] Input: Voice input information (destination, weather conditions)

[0536] Output: Destination and weather information in text format

[0537] Step 5:

[0538] The terminal transmits the voice input information to the server.

[0539] Specific operation: The analyzed destination and weather condition information is sent from the terminal to the server.

[0540] Input: Destination and weather information in text format

[0541] Output: Destination and weather information sent to the server

[0542] Step 6:

[0543] The server captures the user's facial expressions and voice in real time and analyzes their emotions.

[0544] Specific operation: The server captures the user's facial expressions and voice through the camera and microphone of the smart glasses, and analyzes emotions using facial expression recognition technology (face_recognition) and voice analysis technology (emotion_recognition).

[0545] Input: Real-time facial expression and voice data

[0546] Output: User's emotional state (e.g., happy, sad, excited, tired)

[0547] Step 7:

[0548] The server generates an appropriate outfit based on the analysis results (type, color, and style of clothing), destination, and weather condition information.

[0549] How it works: Using a generative AI model (TensorFlow model), the analysis results are integrated with the input information to generate multiple outfit ideas. It also references an external fashion database.

[0550] Input: Clothing analysis results, destination information, weather condition information, emotional state

[0551] Output: Coordination proposal

[0552] Step 8:

[0553] The server adjusts the generated coordinates according to the user's emotions and displays them on the smart glasses.

[0554] Specific operation: Based on the user's emotional state, the suggested outfits are adjusted and displayed on the smart glasses display. For example, if the user is tired, cheerful and uplifting outfits will be displayed first.

[0555] Input: Coordination proposal, emotional state

[0556] Output: Coordinate suggestions presented to the user

[0557] Step 9:

[0558] The user inputs feedback on the coordination proposal.

[0559] Specific operation: Using the voice input function or touch interface of the smart glasses, the user provides feedback on their opinions and thoughts about the suggested outfits.

[0560] Input: User feedback (e.g., I don't own a cardigan)

[0561] Output: Feedback information

[0562] Step 10:

[0563] The terminal sends feedback information to the server.

[0564] Specific operation: The terminal transmits the feedback information obtained from the user to the server.

[0565] Input: Feedback information

[0566] Output: Feedback information sent to the server

[0567] Step 11:

[0568] The server will reflect the feedback information in the next coordinate generation.

[0569] How it works: The machine learning module learns from the feedback information and improves the next outfit suggestions by reflecting the user's preferences and patterns.

[0570] Input: Feedback information

[0571] Output: Improved coordinate generation algorithm

[0572] Step 12:

[0573] The server recommends where to buy clothing items that are in short supply.

[0574] Specific operation: The item recommendation module identifies missing items in the proposed outfit and generates purchasing information. The smart glasses display online shop links and nearby store information.

[0575] Input: Proposed outfit ideas, missing item information

[0576] Output: Purchase information (links and store information)

[0577] 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.

[0578] 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.

[0579] 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.

[0580] [Second embodiment]

[0581] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0582] 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.

[0583] 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).

[0584] 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.

[0585] 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.

[0586] 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).

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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.

[0591] 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.

[0592] 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."

[0593] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is composed of a user, a server, and a terminal.

[0594] overview

[0595] Users take a photo of their outfit using the camera on their smartphone or computer and send the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothing they are wearing. The user then uses their device to input information about their destination and weather for the day, which is then sent to the server. The server combines the analysis data with the input information, generates an optimal outfit, and presents it to the user. The user provides feedback, and the server uses that feedback to improve its next outfit suggestions. It also recommends places to purchase any clothing items the user is missing.

[0596] Program processing

[0597] Video Analysis

[0598] The server analyzes the received video data to identify the type of clothing (shirt, pants, accessories, etc.), color, and style the user is wearing. This analysis is performed using image recognition technology. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the style of the clothing. The resulting analysis data is stored in the server's internal database.

[0599] Coordinate generation

[0600] The device provides a means for the user to input information about their destination and weather, and sends that information to the server. Based on this information, the server uses a coordination suggestion module to generate optimal outfits. This module generates multiple coordination suggestions and evaluates each one. It also references an external fashion database, taking into account the latest fashion trends and seasonal styles.

[0601] Coordination presentation and feedback

[0602] The server selects the optimal outfit suggestions and sends them to the device as a recommendation list. The device displays them to the user. The user then enters feedback on the suggested outfits, which is sent to the server. The server stores the feedback and uses it in a machine learning module to learn about the user's preferences and patterns.

[0603] Purchase recommendation

[0604] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and sends information on where to purchase them to the device. The device displays this information to the user, providing links to online shops and information on nearby stores.

[0605] Specific examples

[0606] scenario

[0607] The user is going out to lunch with a friend this morning and is already dressed in a white shirt and jeans. The weather forecast predicts cloudy skies with rain.

[0608] flow

[0609] 1. The user takes a picture of a white shirt and jeans using the smartphone camera.

[0610] 2. The device sends the video data to the server.

[0611] 3. The server analyzes the video and identifies the white shirt and jeans.

[0612] 4. The user inputs the destination (lunch with a friend) and the weather (cloudy with rain) into the terminal.

[0613] 5. The device sends the input information to the server.

[0614] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[0615] 7. The server sends the proposal to the device.

[0616] 8. The device displays the suggestions to the user.

[0617] 9. The user provides feedback that they do not own a cardigan.

[0618] 10. The device sends the feedback to the server.

[0619] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[0620] 12. The terminal displays the supplier information to the user.

[0621] This process allows users to receive optimal fashion suggestions and easily obtain purchasing information to supplement any clothing shortages, thereby improving their fashion sense and giving them confidence in their everyday coordination.

[0622] The processing flow will be explained below.

[0623] Step 1:

[0624] The user takes a photo of their outfit using the camera on their smartphone or computer.

[0625] Step 2:

[0626] The video data acquired by the terminal is transmitted to the server.

[0627] Step 3:

[0628] The server begins analyzing the received video data.

[0629] Step 4:

[0630] The server's image recognition module identifies the type of clothing the user is wearing (e.g., shirt, pants, accessories, etc.) from the video.

[0631] Step 5:

[0632] The server's color recognition algorithm analyzes the color of each item.

[0633] Step 6:

[0634] The server's style recognition algorithm identifies the clothing style (e.g., casual, formal, etc.).

[0635] Step 7:

[0636] The server stores the analysis results in an internal database.

[0637] Step 8:

[0638] The user uses the terminal to input information about the destination and weather for the day.

[0639] Step 9:

[0640] The terminal sends the entered destination, schedule and weather data to the server.

[0641] Step 10:

[0642] The server combines the received destination and weather data with the analysis data.

[0643] Step 11:

[0644] The server's coordination suggestion module generates optimal coordination based on the analysis data and user information.

[0645] Step 12:

[0646] The server creates multiple coordination proposals and evaluates each one.

[0647] Step 13:

[0648] The server selects the most suitable coordination plan based on the evaluation results.

[0649] Step 14:

[0650] The server creates a recommendation list and sends it to the device.

[0651] Step 15:

[0652] The device displays the recommendation list to the user.

[0653] Step 16:

[0654] The user inputs feedback on the coordination into the terminal.

[0655] Step 17:

[0656] The terminal transmits the user's feedback data to the server.

[0657] Step 18:

[0658] The server stores the feedback data, and the machine learning module uses it to learn user preferences and patterns.

[0659] Step 19:

[0660] The server's item recommendation module identifies items that are missing from the user's outfit or outfit.

[0661] Step 20:

[0662] The server generates supplier information for the missing items.

[0663] Step 21:

[0664] The server sends the supplier information to the terminal.

[0665] Step 22:

[0666] The terminal displays the supplier information to the user.

[0667] Example 1

[0668] 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."

[0669] Conventional fashion coordination suggestion systems have problems such as difficulty in suggesting outfits that reflect the user's appropriate destination or weather information, or when the user does not accurately understand their own outfit. Furthermore, if the user is not satisfied with the suggested outfit, there is no mechanism to reflect that feedback in the next suggestion. Furthermore, there is also a lack of a way to quickly provide information on where to purchase missing items.

[0670] 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.

[0671] In this invention, the server includes: means for acquiring an image of the user's clothing; means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user; means for inputting information about the user's destination and weather; means for generating an appropriate outfit based on the analysis results and the input information; means for presenting the generated outfit to the user; means for receiving feedback from the user, learning from the feedback, and incorporating it into the next outfit generation; means for recommending where to purchase missing clothing accessories; means for identifying the color and style of clothing using image recognition technology; means for learning the user's preferences and patterns using a machine learning module; means for referencing an external fashion database to generate outfits; means for evaluating outfit suggestions based on the user's destination and weather information; and means for providing links to online shops and nearby store information. This allows the server to accurately analyze the user's current fashion situation and propose optimal outfits based on the weather and destination. Furthermore, the server can reflect the user's feedback in the next outfit proposal and quickly provide information on where to purchase missing items.

[0672] "User" refers to an individual who uses the system to photograph, input, and provide feedback about their outfit.

[0673] "Server" refers to a central processing unit that receives data sent by users, analyzes, stores, learns from, and reflects coordination suggestions and feedback.

[0674] A "terminal" is a device used by a user, such as a smartphone or PC, and refers to an interface means for taking images, inputting information, displaying outfit suggestions, etc.

[0675] "Image recognition technology" is a technology that automatically identifies objects, shapes, colors, etc. from acquired image data, and primarily utilizes deep learning models and algorithms.

[0676] "Machine learning module" refers to artificial intelligence (AI) technology or software programs that learn from user feedback data and improve the accuracy of future outfit suggestions.

[0677] The "coordination suggestion module" refers to a software program that generates optimal outfit combinations by referencing a fashion database based on the user's clothing analysis data and input information.

[0678] A "fashion database" refers to a database that contains the latest fashion trends, style information according to the season, brand information, etc.

[0679] "Feedback" refers to input information such as evaluations, opinions, and comments made by users regarding the proposed coordination.

[0680] "Purchaser information" refers to links to online shops and information on physical stores provided as places to purchase new clothing items that the user needs.

[0681] "Destination information" refers to information about places and events that the user plans to go to.

[0682] "Weather information" refers to information about the weather conditions at the user's location or the location where the user plans to go.

[0683] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is mainly composed of a user, a server, and a terminal.

[0684] System Overview

[0685] The user uses the camera on their smartphone or computer to take a picture of their current outfit and sends the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothes the user is wearing. The user then uses their device to input information such as their destination and weather, which is then sent to the server. The server then combines the analysis data with the input information to generate an optimal outfit and present it to the user. It receives feedback from the user and reflects it in generating the next outfit. It also provides information on where to purchase any clothing items the user does not own.

[0686] System configuration and processing

[0687] Video Analysis

[0688] The server analyzes the received video data. This analysis uses image recognition technologies such as TensorFlow and OpenCV. Specifically, it extracts contours from the transmitted image data, identifies the color of the clothing using a color recognition algorithm, and determines the type of clothing and silhouette using a style recognition algorithm. The resulting data is stored in the server's internal database.

[0689] Coordinate generation

[0690] The device provides a means for users to input destination and weather information, and sends that information to the server. The server then uses a coordination suggestion module to combine the user's clothing analysis data with the input information to generate optimal outfits. This module references an external fashion database (e.g., Polyvore API) and takes into account the latest fashion trends and seasonal styles.

[0691] Coordination presentation and feedback

[0692] The server sends the generated outfits to the device, which displays them to the user. The user can then enter feedback about the outfit suggestions, which is then sent back to the server. The server stores the feedback and uses a machine learning module to improve the accuracy of the next outfit suggestions.

[0693] Purchase recommendation

[0694] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and generates information on where to purchase them. The generated information is sent to the user's device and provided to them. Specifically, it includes links to online shops and information on nearby stores.

[0695] Specific examples

[0696] Consider a scenario where a user is going out to lunch with a friend on the following date and is wearing a white shirt and jeans. The weather forecast is cloudy with rain.

[0697] flow

[0698] 1. A user takes a picture of a white shirt and jeans using the smartphone camera.

[0699] 2. The device sends the video data to the server.

[0700] 3. The server analyzes the video and identifies the white shirt and jeans.

[0701] 4. The user inputs the destination ("lunch with a friend") and the weather ("cloudy with rain") into the terminal.

[0702] 5. The device sends the input information to the server.

[0703] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[0704] 7. The server sends the proposal to the device.

[0705] 8. The device displays the suggestions to the user.

[0706] 9. The user provides feedback that they do not own a cardigan.

[0707] 10. The device sends the feedback to the server.

[0708] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[0709] 12. The terminal displays the supplier information to the user.

[0710] Prompt Sentence Examples

[0711] User outfit image: [image file]

[0712] Destination: Lunch with a friend

[0713] Weather: Cloudy with rain

[0714] Please suggest the best outfit to go with my current outfit. Also, please let me know where to buy any items that are missing from the suggested outfit.

[0715] This system not only allows users to receive suggestions for the perfect outfit for the day, but also makes it easy to find out how to purchase any missing items. Through this process, users can improve their fashion sense and gain confidence.

[0716] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0717] Step 1:

[0718] The user takes a photo of their own outfit using the camera on their smartphone or computer. The input is image data of the outfit. Specifically, the user launches the camera app and presses the capture button to take a full-body shot of the outfit they are currently wearing. The output is the captured image data.

[0719] Step 2:

[0720] The device sends the captured image data to the server. The input is the image data captured by the user. Specifically, the device uploads this image data to the specified server URL via the Internet. The output is the image data sent to the server.

[0721] Step 3:

[0722] The server analyzes the received image data and identifies the type, color, and style of clothing worn by the user. The input is image data sent from the device. Specifically, the server first preprocesses the image (e.g., noise removal), then uses TensorFlow or OpenCV to identify the color of the clothing using k-means clustering, and uses a deep learning model (e.g., ResNet or YOLO) to determine the type of clothing and silhouette. The output is analytical data related to the type, color, and style of clothing.

[0723] Step 4:

[0724] The user uses the device to input destination and weather information. The input includes clothing data after video analysis, the destination (e.g., "lunch with friends"), and the weather (e.g., "cloudy with rain"). Specifically, the user enters the destination and weather information into the app's input form and presses the send button. The output is the destination and weather information entered into the device.

[0725] Step 5:

[0726] The terminal transmits the destination and weather information input by the user to the server. The input is the destination and weather information input by the user to the terminal. In concrete terms, the terminal transmits this information to the server via the Internet. The output is the destination and weather information transmitted to the server.

[0727] Step 6:

[0728] The server integrates the analysis data with the information entered by the user and generates the optimal outfit using the outfit suggestion module. The input is the clothing analysis data, destination, and weather information. Specifically, the server queries an external fashion database, generates multiple outfit suggestions that meet the conditions, and selects the optimal suggestion based on the destination and weather conditions. The output is the outfit suggestion presented to the user.

[0729] Step 7:

[0730] The server transmits the generated coordination plan to the terminal. The input is the optimal coordination plan. In concrete terms, the server transmits the selected coordination plan to the terminal via the Internet. The output is the coordination plan transmitted to the terminal.

[0731] Step 8:

[0732] The terminal displays the outfit suggestions received from the server to the user. The input is the outfit suggestions sent from the server. As a specific operation, the outfit suggestions are visually displayed on the screen of the terminal. The output is the outfit suggestions that the user can view.

[0733] Step 9:

[0734] The user inputs feedback on the proposed outfit. The input is the proposed outfit. Specifically, the user enters comments and ratings into the app's feedback form and presses the send button. The output is the feedback information entered into the device.

[0735] Step 10:

[0736] The terminal sends the feedback information to the server. The input is the feedback information entered by the user. In concrete terms, the terminal sends this information to the server via the Internet. The output is the feedback information sent to the server.

[0737] Step 11:

[0738] The server stores the feedback and uses it in a machine learning module to improve the next coordination proposal. The input is the feedback information. Specifically, the server stores the feedback information in a database and uses it to update the machine learning model. The output is an improved coordination model.

[0739] Step 12:

[0740] The server's item recommendation module identifies missing items in the user's outfit or the proposed outfit, and generates information on where to purchase them. The input is the proposed outfit and feedback information. Specifically, the server identifies the missing item (e.g., a "gray cardigan") and collects information on online shops and nearby stores. The output is information on where to purchase them.

[0741] Step 13:

[0742] The server sends the generated supplier information to the terminal. The input is the supplier information. In concrete terms, the server sends the supplier information to the terminal via the Internet. The output is the supplier information sent to the terminal.

[0743] Step 14:

[0744] The terminal displays the supplier information to the user. The input is the supplier information sent from the server. As a specific operation, the supplier information is visually displayed on the terminal screen. The output is the supplier information that the user can view.

[0745] (Application example 1)

[0746] 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."

[0747] In modern society, there is a demand for assistance in optimizing the coordination of users' clothing. Efficient and personalized coordination suggestions and purchasing support are essential, especially for users who struggle with daily fashion choices. However, current systems struggle to analyze users' clothing in real time and provide optimal coordination suggestions based on various criteria, as well as information on where to purchase missing items. Furthermore, there is a lack of systems that allow users to virtually try on suggested coordinations. Therefore, a means is needed that allows users to easily receive high-quality fashion advice while also receiving purchasing support.

[0748] 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.

[0749] In this invention, the server includes means for acquiring an image of the user's clothing, means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user, and means for inputting information on the user's destination and weather, thereby enabling the user to receive optimal outfit suggestions.

[0750] The server further includes a means for generating an appropriate outfit based on the analysis results and input information, a means for presenting the generated outfit to the user and enabling virtual try-on, a means for receiving feedback from the user, learning from it, and reflecting it in generating the next outfit, and a means for recommending places to purchase missing clothing items and providing links to online stores. This allows the user to not only receive outfit suggestions in real time, but also personalized suggestions that reflect the user's feedback, and easily purchase missing items.

[0751] "Image acquisition means" refers to a device or function for capturing images of a user's clothing in real time, and includes image capture devices such as smartphones, smart glasses, and head-mounted displays.

[0752] "Video analysis means" refers to software or algorithms that analyze captured video data in real time and identify the type, color, and style of clothing worn by the user.

[0753] "Information input means" refers to a function that provides an interface for users to input destination and weather information, and includes the use of a mobile information terminal or a personal computer.

[0754] "Coordination generation means" refers to an algorithm or module that generates appropriate clothing combinations based on the results of video analysis and information entered by the user.

[0755] The "coordinate presentation means" refers to an interface or device for visually displaying the generated coordinates to the user, and also includes a function that allows virtual try-on.

[0756] "Feedback means" refers to a function that provides an interface for receiving opinions and reactions from users regarding coordination suggestions, learns from them, and reflects them in the next suggestion.

[0757] "Purchase recommendation means" refers to a function for providing information on where to purchase items that are missing from the proposed outfit, and includes providing links to online stores.

[0758] "Internal database" refers to a database that stores analyzed data and user feedback and is used within the system.

[0759] "External database" refers to an external fashion information service that is referenced to obtain the latest fashion trends and seasonal style information.

[0760] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is composed of a user, a server, and a terminal.

[0761] System Configuration

[0762] The system includes the following main measures:

[0763] 1. Image acquisition means: A device or function for capturing images of the user's clothing in real time. This uses an image capture device such as a smartphone, smart glasses, or a head-mounted display.

[0764] 2. Video analysis means: This refers to software and algorithms that analyze captured video data in real time and identify the type, color, and style of clothing worn by the user. Specifically, OpenCV and TensorFlow are used.

[0765] 3. Information input means: This function provides an interface for users to input destination and weather information, and uses the user interface of a smartphone or PC.

[0766] 4. Coordination generation means: Algorithms and modules that generate appropriate clothing combinations based on the results of video analysis and input information, taking into account the user's preferences and the latest fashion database.

[0767] 5. Coordination presentation means: A function for visually displaying the generated coordination to the user, including an interface that allows virtual try-on.

[0768] 6. Feedback means: This function provides an interface for receiving opinions and reactions from users regarding coordination suggestions, and learns from that feedback and reflects it in future suggestions.

[0769] 7. Purchasing recommendation tool: This function provides information on where to purchase items that are missing from the suggested outfit, including links to online stores.

[0770] System Operation

[0771] 1. Image acquisition:

[0772] Users take photos of their outfits in real time using the camera on their smartphone or smart glasses.

[0773] The captured video data is immediately sent to a server for analysis.

[0774] 2. Video analysis:

[0775] The server uses OpenCV and TensorFlow to analyze the transmitted video data and identify the type of clothing (e.g., shirt, pants, dress, etc.), color, and style the user is wearing.

[0776] 3. Enter your information:

[0777] The user inputs destination and weather information through the terminal interface, which is then sent to the server.

[0778] Example prompt statement:

[0779] user_info = {

[0780] 'location': 'Tokyo',

[0781] 'event': 'Lunch with a friend'

[0782] }

[0783] 4. Coordinate generation:

[0784] Based on the video analysis results and the input information, the server refers to the latest fashion database and the user's past feedback information to generate the optimal outfit.

[0785] The generated coordinates are saved as information and sent to the user's terminal.

[0786] 5. Coordination presentation and virtual try-on:

[0787] The terminal visually displays the generated outfits to the user, allowing the user to virtually try on the suggested outfits.

[0788] 6. Feedback:

[0789] The user inputs their opinions and reactions to the proposed coordination through the terminal, which are then sent to the server.

[0790] The server learns from the feedback it receives and understands the user's preferences and patterns.

[0791] 7. Purchase recommendation:

[0792] The server's item recommendation module identifies items missing from the proposed outfit and generates purchasing information and links to online shops.

[0793] The terminal displays the recommended vendor information to the user.

[0794] Specific examples

[0795] For example, if a user is going out to lunch with a friend this morning and is wearing a white shirt and jeans, and the weather forecast predicts cloudy skies with rain, the system will operate as follows:

[0796] 1. The user uses the smartphone camera to take a picture of a white shirt and jeans.

[0797] 2. The captured video data is sent to the server.

[0798] 3. The server analyzes the video and identifies the white shirt and jeans.

[0799] 4. The user inputs the destination (lunch with a friend) and the weather (cloudy with rain) into the terminal.

[0800] 5. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[0801] 6. The server sends the proposal to the device.

[0802] 7. The device displays the suggestions to the user, who then virtually tries them on.

[0803] 8. The user provides feedback that they do not own a cardigan.

[0804] 9. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[0805] 10. The terminal displays the purchasing information to the user, and the user can purchase the cardigan from the online shop.

[0806] By following this process, users can easily purchase any missing items while receiving suggestions for optimal outfits.

[0807] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0808] Step 1: The user takes a picture of their outfit in real time using the camera on their smartphone or smart glasses. The captured video data is immediately sent to the server.

[0809] Input: Video data of the clothes worn by the user.

[0810] Output: Sending video data to the server.

[0811] How it works: The user turns on the camera on their smartphone and takes a full-body video of themselves. This video data is then uploaded to a cloud server in real time.

[0812] Step 2: The server uses OpenCV and TensorFlow to analyze the transmitted video data and identify the type, color, and style of clothing the user is wearing.

[0813] Input: Video data sent to the server.

[0814] Output: Analyzed data about clothing type, color, and style.

[0815] How it works: Image recognition algorithms running on the server identify the type of clothing (shirt, pants, etc.) as well as their color and style from the video data. The resulting analysis data is stored in an internal database.

[0816] Step 3: The user inputs destination and weather information through the terminal interface, which is then sent to the server.

[0817] Input: Destination and weather information.

[0818] Output: Sending information to the server.

[0819] Specific operation: The user uses a smartphone app to enter the location they plan to go to that day and weather forecast information, and then submits the form.

[0820] Step 4: The server's coordinate generation means generates an optimal coordinate based on the video analysis results and the information input by the user, by referring to the latest fashion database and the user's past feedback information.

[0821] Input: Analysis data, user destination and weather information.

[0822] Output: Optimal outfit ideas.

[0823] Specific operation: The server searches a fashion database for the latest trends and weather-appropriate combinations, and generates optimal outfit suggestions for shirts, pants, and accessories.

[0824] Step 5: The terminal visually displays the generated outfit to the user, allowing the user to virtually try on the suggested outfit.

[0825] Input: Generated coordinate plan.

[0826] Output: Visual presentation of outfits and virtual try-on.

[0827] Specific operation: The device displays outfit ideas on the application interface, and the user tries them on in a virtual environment.

[0828] Step 6: The user inputs their opinions and reactions to the proposed coordination through the terminal, which are then sent to the server.

[0829] Input: User feedback.

[0830] Output: Sending feedback to the server.

[0831] Specific operation: The user enters their thoughts and opinions about the outfit into the feedback form within the application and presses the submit button.

[0832] Step 7: The server learns from the received feedback and understands the user's preferences and patterns. It uses the generative AI model to reflect this in the next outfit suggestions.

[0833] Input: User feedback data.

[0834] Output: Improved outfit suggestions.

[0835] How it works: The server stores the feedback information in a database, and the generative AI model uses this information to learn user preferences and patterns.

[0836] Step 8: The server's item recommendation module identifies the missing items and generates purchasing information and links to online shops.

[0837] Input: User's current belongings information and coordination suggestions.

[0838] Output: Purchase information and online shop link.

[0839] Specific operation: The server retrieves purchasing information from an internal database and external shopping sites and sends it to the user's device.

[0840] Step 9: The terminal displays the recommended purchasing information to the user, and the user can purchase the missing items online based on the recommended purchasing information.

[0841] Input: Supplier information and shopping links.

[0842] Output: Providing information to the user and assisting them in making a purchase.

[0843] Specific operation: The device displays the purchasing information and link on the application display screen, and the user can purchase the item from the online shop by clicking the link.

[0844] This flow of processing steps allows the user to efficiently receive suggestions for optimal outfits while easily obtaining the items they need.

[0845] 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.

[0846] This invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. This system is comprised of a user, a server, and a terminal, and also incorporates an emotion engine that recognizes the user's emotions.

[0847] overview

[0848] Users take pictures of their outfits using the camera on their smartphone or computer and send the images to the server. The server analyzes the image data and identifies the type, color, and style of the clothes they are wearing. The user then inputs their destination and weather information for the day using their device, which is then sent to the server. The server then combines the analysis data, the input information, and the user's emotions, as recognized by the emotion engine, to generate an optimal outfit. This generated outfit matches the user's mood. The user provides feedback on the suggested outfit, and the server uses that feedback to improve its next outfit suggestions. The server also recommends places to purchase any clothing items the user is missing.

[0849] Program processing

[0850] Video Analysis

[0851] The server analyzes the received video data and identifies the type of clothing (e.g., shirt, pants, accessories, etc.), color, and style) worn by the user. This analysis is performed using image recognition technology. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the style of the clothing. The resulting analysis data is stored in the server's internal database.

[0852] Emotion analysis

[0853] The device provides a means to acquire the user's facial expressions and voice in real time and transmits the data to a server. An emotion engine installed on the server analyzes the user's emotions based on this data. The emotion engine uses facial expression recognition and voice analysis technology to determine the user's current emotion (e.g., joy, sadness, excitement, fatigue).

[0854] Coordinate generation

[0855] The device provides a means for the user to input information about their destination and weather, and sends that information to the server. Based on this, the server uses a coordination suggestion module to generate optimal outfits. This module generates multiple outfit suggestions based on analytical data, emotional data, and user information, and evaluates each one. It also references an external fashion database, taking into account the latest fashion trends and seasonal styles. It also adjusts the style of the suggested outfits based on the user's emotions, presenting outfits that suit the user's mood.

[0856] Coordination presentation and feedback

[0857] The server selects the optimal outfit suggestions and sends them to the device as a recommendation list. The device displays them to the user. The user then enters feedback on the suggested outfits, which is sent to the server. The server stores the feedback and uses it in a machine learning module to learn about the user's preferences and patterns.

[0858] Purchase recommendation

[0859] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and sends information on where to purchase them to the device. The device displays this information to the user, providing links to online shops and information on nearby stores.

[0860] Specific examples

[0861] scenario

[0862] The user is planning to go out to lunch with a friend this morning and is already dressed in a white shirt and jeans. The weather forecast predicts cloudy skies with rain. The user is feeling a little tired, but is looking forward to a fun lunch.

[0863] flow

[0864] 1. A user takes a picture of a white shirt and jeans using their smartphone camera.

[0865] 2. The device sends the video data to the server.

[0866] 3. The server analyzes the video and identifies the white shirt and jeans.

[0867] 4. The user inputs a destination (lunch with a friend) and weather (cloudy with rain) into the terminal.

[0868] 5. The device sends the input information to the server.

[0869] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[0870] 7. The server sends the proposal to the device.

[0871] 8. The device displays the suggestions to the user.

[0872] 9. The user provides feedback that they do not own a cardigan.

[0873] 10. The device sends the feedback to the server.

[0874] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[0875] 12. The terminal displays the supplier information to the user.

[0876] 13. The user provides facial expression and voice data through the terminal.

[0877] 14. The device sends facial expression and voice data to the server.

[0878] 15. The server's emotion engine analyzes the user's emotions and suggests additional outfits that emphasize a happy mood (e.g., brightly colored accessories).

[0879] This process allows users to receive optimal fashion suggestions and easily obtain purchasing information to supplement any clothing shortages. Furthermore, adjustments are made to match the user's emotions, further increasing satisfaction with everyday coordination.

[0880] The processing flow will be explained below.

[0881] Step 1:

[0882] The user takes a photo of their outfit using the camera on their smartphone or computer.

[0883] Step 2:

[0884] The video data acquired by the terminal is transmitted to the server.

[0885] Step 3:

[0886] The server begins analyzing the received video data.

[0887] Step 4:

[0888] The server's image recognition module identifies the type of clothing the user is wearing (e.g., shirt, pants, accessories, etc.) from the video.

[0889] Step 5:

[0890] The server's color recognition algorithm analyzes the color of each item.

[0891] Step 6:

[0892] The server's style recognition algorithm identifies the clothing style (e.g., casual, formal, etc.).

[0893] Step 7:

[0894] The server stores the analysis results in an internal database.

[0895] Step 8:

[0896] The user uses the terminal to input information about the destination and weather for the day.

[0897] Step 9:

[0898] The terminal sends the entered destination, schedule and weather data to the server.

[0899] Step 10:

[0900] The server combines the received destination and weather data with the analysis data.

[0901] Step 11:

[0902] The user provides emotional data such as facial expressions and voice through the terminal.

[0903] Step 12:

[0904] The device transmits the emotion data to the server.

[0905] Step 13:

[0906] The server's emotion engine uses facial expression recognition and voice analysis technology to analyze the user's emotions (e.g., joy, sadness, excitement, fatigue, etc.).

[0907] Step 14:

[0908] The server's coordination suggestion module generates optimal coordination based on analysis data, emotion data, and user information.

[0909] Step 15:

[0910] The server creates multiple coordination proposals and evaluates each one.

[0911] Step 16:

[0912] The server selects the most suitable coordination plan based on the evaluation results.

[0913] Step 17:

[0914] The server creates a recommendation list and sends it to the device.

[0915] Step 18:

[0916] The device displays the recommendation list to the user.

[0917] Step 19:

[0918] The user inputs feedback on the proposed coordination into the terminal.

[0919] Step 20:

[0920] The terminal transmits the user's feedback data to the server.

[0921] Step 21:

[0922] The server stores the feedback data, and the machine learning module uses it to learn user preferences and patterns.

[0923] Step 22:

[0924] The server's item recommendation module identifies items that are missing from the user's outfit or outfit.

[0925] Step 23:

[0926] The server generates information on where to purchase the missing items and transmits it to the terminal.

[0927] Step 24:

[0928] The terminal displays the supplier information to the user.

[0929] Example 2

[0930] 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."

[0931] Conventional fashion coordination assistant systems can make suggestions based on the user's clothing and style, destination, weather information, etc., but they cannot generate coordinations that take the user's emotions into consideration, so they have the problem of not being able to make suggestions that fully reflect the user's mood.In addition, they lack the function to specifically recommend clothing items that the user is lacking, making it difficult for users to easily purchase the items needed for the suggested coordination.

[0932] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring an image of the user's clothing, means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user, means for inputting information about the user's destination and weather, means for generating an appropriate outfit based on the analysis results and the input information, means for presenting the generated outfit to the user, means for receiving feedback from the user, learning from the feedback, and reflecting it in generating the next outfit, means for analyzing the user's emotions, means for adjusting the outfit based on the emotions, and means for recommending where to purchase missing clothing and accessories. This makes it possible to suggest an optimal outfit based on the user's mood, and by specifically recommending where to purchase missing items, the user can quickly obtain the items they need.

[0933] "User" refers to a person who uses the system to improve or receive suggestions for their own clothing coordination.

[0934] "Outfit image" refers to digital image data that contains visual information about the clothing and accessories worn by a user.

[0935] "Means for acquiring" refers to a device or technology that allows a user to take an image of the outfit and send the image to the system.

[0936] "Means for analyzing" refers to technology for identifying the type, color, and style of clothing worn by a user based on the acquired image data.

[0937] "Means for identifying" refers to technology for identifying specific attributes of the clothing worn by the user based on the analysis results.

[0938] "Input means" refers to the devices and technologies that allow users to input destination and weather information.

[0939] "Means for generating appropriate coordination" refers to technology for proposing optimal clothing combinations to users based on analysis results and input information.

[0940] "Presenting means" refers to a device or technology for showing the generated coordinates to the user.

[0941] "Means for receiving feedback" refers to technology that allows users to input their thoughts and requests regarding the proposed outfits and send that information to the system.

[0942] "Means of learning" refers to technology that uses user feedback to improve the next outfit suggestion.

[0943] "Means for analyzing emotions" refers to technology for identifying emotions based on a user's facial expressions and voice data.

[0944] The term "means for adjusting a coordination based on emotions" refers to a technique for adjusting an optimal coordination for a user in consideration of the analyzed emotions of the user.

[0945] "Means for recommending where to purchase missing clothing items" refers to technology for showing a user where to purchase missing items based on the suggested outfit.

[0946] This invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. This system is comprised of a user, a server, and a terminal, and also incorporates an emotion analysis engine that recognizes the user's emotions.

[0947] Hardware and software used

[0948] The server is equipped with image recognition technology, an emotion analysis engine, a coordination suggestion module, an item recommendation module, and a machine learning algorithm, which utilize the following specific technologies:

[0949] Image recognition technology: color recognition algorithm, style recognition algorithm

[0950] Emotion analysis engine: facial expression recognition technology, voice analysis technology

[0951] Coordination suggestion module: Includes the function to refer to external fashion databases

[0952] Item recommendation module: Online shop link generation function, nearby store information acquisition function

[0953] Machine learning algorithms: Ability to learn from feedback data

[0954] The device includes a camera that captures images of the user's outfit, an interface for inputting destination and weather information, and a display that shows suggested outfits and shopping information.

[0955] Users can use these functions using smartphones or computers.

[0956] Coordination proposal process

[0957] Users use their smartphone or PC camera to take a picture of their outfit and send the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothes they are wearing. The user then inputs their destination and weather information for the day via their device, which is then sent to the server. The server then combines the analysis data, the input information, and the user's emotional data recognized by an emotion analysis engine to generate the optimal outfit. The generated outfit matches the user's mood.

[0958] For example, suppose a user is planning to go out to lunch with a friend this morning and is wearing a white shirt and jeans. The weather forecast predicts cloudy skies with rain, and the user is feeling a little tired but is looking forward to a pleasant lunch. In this situation, the flow of using the system is as follows:

[0959] 1. A user takes a picture of a white shirt and jeans using their smartphone camera.

[0960] 2. The device sends the video data to the server.

[0961] 3. The server analyzes the video and identifies the white shirt and jeans.

[0962] 4. The user inputs a destination (lunch with a friend) and weather (cloudy with rain) into the terminal.

[0963] 5. The device sends the input information to the server.

[0964] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots.

[0965] 7. The server sends the proposal to the terminal, which displays it to the user.

[0966] 8. The user provides feedback that they do not own a cardigan.

[0967] 9. The device sends the feedback to the server.

[0968] 10. The server stores the feedback and generates and sends information about where to buy the cardigan to the device.

[0969] 11. The device displays the retailer information to the user.

[0970] 12. The user provides facial expression and voice data through the terminal.

[0971] 13. The device sends facial expression and voice data to the server.

[0972] 14. The server's emotion analysis engine analyzes the user's emotions and suggests additional accessories that emphasize a happy mood (e.g., a brightly colored scarf).

[0973] 15. The server sends the additional suggestions to the terminal, which displays them to the user.

[0974] This process not only allows users to receive optimal fashion suggestions, but also provides information on purchasing clothing items that they are lacking, and improves their satisfaction with their everyday outfits.

[0975] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0976] Step 1:

[0977] Users take a photo of their outfit using the camera on their smartphone or computer. Specifically, the user stands in front of a mirror and takes a photo that captures their entire body. The captured image is then saved as digital data on the device.

[0978] Input: Image of the user's outfit

[0979] Output: Digital image data

[0980] Step 2:

[0981] The terminal transmits the captured digital image data to a server via the Internet.

[0982] Input: Digital image data

[0983] Output: Image data sent to the server

[0984] Step 3:

[0985] The server analyzes the received digital image data. It uses image recognition technology to identify the type of clothing (e.g., shirt, pants), color, and style the user is wearing. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the type of clothing. The analysis results are stored in an internal database.

[0986] Input: Digital image data

[0987] Data processing and calculation: Color recognition algorithm, style recognition algorithm

[0988] Output: Analysis results (clothing type, color, style)

[0989] Step 4:

[0990] The user inputs information about the destination and weather for the day through the terminal, and the input information is sent from the terminal to the server.

[0991] Input: Destination information, weather information

[0992] Output: Destination information and weather information sent to the server

[0993] Step 5:

[0994] The server uses the outfit suggestion module to generate optimal outfits based on the analysis results and the destination and weather information entered by the user. During this process, it references an external fashion database to consider the latest trends and seasonal styles. It also uses the user's emotional data to consider outfits that suit their mood.

[0995] Input: Analysis results, destination information, weather information, emotion data

[0996] Data processing and calculation: External fashion database reference, coordinate generation algorithm

[0997] Output: Generated coordinate plan

[0998] Step 6:

[0999] The server selects one of the generated coordination plans and sends it to the terminal, which displays it to the user.

[1000] Input: Generated coordination plan

[1001] Output: Coordination ideas displayed to the user

[1002] Step 7:

[1003] The user inputs feedback about the proposed outfit. For example, the user inputs feedback such as "I don't own a cardigan" into the terminal. The feedback is sent from the terminal to the server.

[1004] Input: User feedback

[1005] Output: Feedback sent to the server

[1006] Step 8:

[1007] The server uses machine learning algorithms to learn from user feedback and suggests outfits, storing the feedback to improve future suggestions.

[1008] Input: Feedback data

[1009] Data processing and calculation: Machine learning algorithms

[1010] Output: Improved outfit suggestion data

[1011] Step 9:

[1012] The server's item recommendation module generates purchasing information for missing items (e.g., cardigans) based on the suggested outfits, including online shop links and nearby store locations.

[1013] Input: Feedback data

[1014] Data processing and calculation: Item recommendation algorithm

[1015] Output: Generated supplier information

[1016] Step 10:

[1017] The server transmits the generated supplier information to the terminal, which displays it to the user.

[1018] Input: Generated supplier information

[1019] Output: Supplier information displayed to the user

[1020] Step 11:

[1021] The user provides facial expression and voice data through the device, which is collected in real time and sent to the server.

[1022] Input: facial expression data, voice data

[1023] Output: Emotion data sent to the server

[1024] Step 12:

[1025] The server's emotion analysis engine analyzes the user's emotions from their facial expressions and voice. For example, it can use facial recognition technology to determine if the user is slightly tired. The results of this emotion analysis are also reflected in the outfit suggestions.

[1026] Input: facial expression data, voice data

[1027] Data processing and calculation: Emotion analysis algorithm

[1028] Output: Emotion analysis results

[1029] Step 13:

[1030] Based on the results of the emotion analysis, the server adjusts the outfit to suit the user's mood and generates additional suggestions, such as an accessory (such as a brightly colored scarf) that emphasizes a happy mood.

[1031] Input: Sentiment analysis results

[1032] Data processing and calculation: Coordinate adjustment algorithm

[1033] Output: Additional suggested coordinates

[1034] Step 14:

[1035] The server sends the additional suggestions to the terminal, which displays them to the user.

[1036] Input:Add suggested coordinates

[1037] Output: Additional outfit suggestions displayed to the user

[1038] In this way, users can not only receive optimal fashion suggestions through the system, but also obtain purchasing information for items they are lacking, and can receive coordination suggestions that correspond to their emotions.

[1039] (Application example 2)

[1040] 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."

[1041] Conventional outfit suggestion systems only consider the user's clothing and preferences, but do not consider emotions or real-time environmental changes. As a result, suggestions may be made that do not match the user's mood or the weather, resulting in low satisfaction. Also, if a suggested outfit is missing an item, there is insufficient means to supplement it. These issues need to be resolved.

[1042] 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.

[1043] In this invention, the server includes means for acquiring images of the user's clothing, means for analyzing the acquired images and identifying the type, color, and style of the clothing worn by the user, means for inputting information about the user's destination and weather conditions, means for acquiring the user's facial expressions and voice in real time and analyzing their emotions, means for adjusting and presenting the generated outfit in accordance with the user's emotions, means for receiving feedback from the user, learning from it, and reflecting it in generating the next outfit, and means for recommending where to purchase missing clothing accessories. This makes it possible to propose optimal outfits that take into account the user's emotions and real-time environmental changes.

[1044] The "means for acquiring an image of the user's clothing" refers to a device or technology for photographing the clothing currently being worn by the user.

[1045] "Means for analyzing the captured image and identifying the type, color, and style of clothing worn by the user" refers to technology that processes captured image data and identifies detailed characteristics of the clothing worn by the user.

[1046] The "means for inputting information on the user's destination and weather conditions" refers to a device or method for inputting the user's planned location and weather information for the day into the system.

[1047] "Means for acquiring a user's facial expressions and voice in real time and analyzing their emotions" refers to technology that acquires a user's facial expressions and tone of voice in real time and determines the user's emotional state based on that data.

[1048] "Means for adjusting and presenting the generated coordination in accordance with the user's emotions" refers to a device or method for optimizing the generated coordination to reflect the user's current emotional state and presenting it to the user.

[1049] "Means for receiving feedback from the user, learning from it, and reflecting it in the next coordination generation" refers to a learning technology that records the user's reactions and opinions and uses them to help generate the next coordination.

[1050] The "means for recommending where to purchase missing clothing accessories" is a technology that detects items that are missing from a proposed outfit and provides the user with information on where to purchase those items.

[1051] This invention is a system that acquires images of a user's clothing, analyzes them, and suggests outfits that suit the user's outfit. The system consists of a terminal, a server, and a user's device. Using smart glasses, a smartphone, a PC, or other devices, users can easily try on clothes virtually and receive fashion advice from the comfort of their own home.

[1052] 1. How to obtain images of the user's clothing

[1053] The user uses the camera in the smart glasses to take a picture of their own clothes in real time and captures the image. The smart glasses device collects the image data and sends it to the server.

[1054] 2. A means of analyzing the captured image and identifying the type, color, and style of clothing worn by the user.

[1055] The server analyzes the received image data to identify the type, color, and style of the user's clothing. This analysis is performed using algorithms from image recognition technologies (e.g., OpenCV and TensorFlow). For example, a color recognition algorithm determines the color, and a style recognition algorithm identifies the style of the clothing.

[1056] 3. A means of inputting information about the user's destination and weather conditions

[1057] Users can input their destination and weather information for the day through the smart glasses' voice assistant, which is then sent to the server and integrated with analytical data.

[1058] 4. A means of capturing the user's facial expressions and voice in real time and analyzing their emotions

[1059] The image data sent to the server is used to analyze the user's facial expressions and voice. Facial expression recognition technology (e.g., face_recognition) and voice analysis technology (e.g., emotion_recognition) are used to detect the user's current emotion (happiness, sadness, excitement, fatigue, etc.).

[1060] 5. A method for adjusting and presenting the generated outfits according to the user's emotions

[1061] Based on the analysis results, input information, and emotional data, the outfit suggestion module generates the optimal outfit. This module uses a generative AI model (e.g., a TensorFlow model) to evaluate multiple outfit suggestions. It also references an external fashion database to consider the latest fashion trends and seasonal styles. It adjusts the suggestions based on the user's emotions and presents outfits that suit the user's mood.

[1062] 6. A means to receive feedback from users, learn from it, and reflect it in the next coordinate generation

[1063] Users can provide feedback on the suggested outfits through the smart glasses, which is then sent to the server, where the machine learning module learns the user's preferences and patterns and reflects them in the next outfit suggestions.

[1064] 7. Recommendations for purchasing clothing items in short supply

[1065] The server's item recommendation module identifies missing items in an outfit and provides the user with information on where to purchase them. The suggested outfits and item information are displayed on the smart glasses, allowing the user to easily access links to online shops and nearby store locations.

[1066] Examples of concrete examples and prompts

[1067] Specific examples

[1068] For example, a user uses smart glasses to wear a white shirt and jeans at home. The user plans to go on a picnic in the park with friends the next day, and the weather forecast predicts sunny skies. The system also determines that the user is feeling a little tired. The system then suggests a bright-colored cardigan or colorful scarf to go with the white shirt and jeans, providing an outfit that will lift the user's spirits.

[1069] Prompt Sentence Examples

[1070] "Tomorrow I'm going to have a picnic in the park with a friend. The weather is sunny. I'm a little tired. Can you suggest some outfits that will make me feel energized?"

[1071] In this way, the present invention provides a system that takes into consideration the user's emotions and real-time environmental changes and proposes optimal outfits.

[1072] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1073] Step 1:

[1074] The user uses the camera in the smart glasses to take a picture of their clothing.

[1075] Specific operation: The user wears the smart glasses and captures an image of their entire outfit with the camera to obtain image data.

[1076] Input: Real-time clothing image

[1077] Output: Acquired clothing image data

[1078] Step 2:

[1079] The terminal transmits the acquired image data to the server.

[1080] Specific operation: The smart glasses are connected via Wi-Fi or Bluetooth and transmit the acquired image data to the server.

[1081] Input: Clothing image data

[1082] Output: Image data sent to the server

[1083] Step 3:

[1084] The server analyzes the transmitted image data and identifies the type, color, and style of clothing the user is wearing.

[1085] How it works: An image recognition algorithm running on the server extracts clothing features (type, color, style) from image data. It uses an image recognition model such as TensorFlow.

[1086] Input: Clothing image data

[1087] Output: Analysis results for clothing type, color, and style

[1088] Step 4:

[1089] The user inputs information about their destination and weather conditions through the voice assistant in the smart glasses.

[1090] Specific Actions: A user uses voice input to provide information about the destination for the day (e.g., going to the park) and weather conditions (sunny).

[1091] Input: Voice input information (destination, weather conditions)

[1092] Output: Destination and weather information in text format

[1093] Step 5:

[1094] The terminal transmits the voice input information to the server.

[1095] Specific operation: The analyzed destination and weather condition information is sent from the terminal to the server.

[1096] Input: Destination and weather information in text format

[1097] Output: Destination and weather information sent to the server

[1098] Step 6:

[1099] The server captures the user's facial expressions and voice in real time and analyzes their emotions.

[1100] Specific operation: The server captures the user's facial expressions and voice through the camera and microphone of the smart glasses, and analyzes emotions using facial expression recognition technology (face_recognition) and voice analysis technology (emotion_recognition).

[1101] Input: Real-time facial expression and voice data

[1102] Output: User's emotional state (e.g., happy, sad, excited, tired)

[1103] Step 7:

[1104] The server generates an appropriate outfit based on the analysis results (type, color, and style of clothing), destination, and weather condition information.

[1105] How it works: Using a generative AI model (TensorFlow model), the analysis results are integrated with the input information to generate multiple outfit ideas. It also references an external fashion database.

[1106] Input: Clothing analysis results, destination information, weather condition information, emotional state

[1107] Output: Coordination proposal

[1108] Step 8:

[1109] The server adjusts the generated coordinates according to the user's emotions and displays them on the smart glasses.

[1110] Specific operation: Based on the user's emotional state, the suggested outfits are adjusted and displayed on the smart glasses display. For example, if the user is tired, cheerful and uplifting outfits will be displayed first.

[1111] Input: Coordination proposal, emotional state

[1112] Output: Coordinate suggestions presented to the user

[1113] Step 9:

[1114] The user inputs feedback on the coordination proposal.

[1115] Specific operation: Using the voice input function or touch interface of the smart glasses, the user provides feedback on their opinions and thoughts about the suggested outfits.

[1116] Input: User feedback (e.g., I don't own a cardigan)

[1117] Output: Feedback information

[1118] Step 10:

[1119] The terminal sends feedback information to the server.

[1120] Specific operation: The terminal transmits the feedback information obtained from the user to the server.

[1121] Input: Feedback information

[1122] Output: Feedback information sent to the server

[1123] Step 11:

[1124] The server will reflect the feedback information in the next coordinate generation.

[1125] How it works: The machine learning module learns from the feedback information and improves the next outfit suggestions by reflecting the user's preferences and patterns.

[1126] Input: Feedback information

[1127] Output: Improved coordinate generation algorithm

[1128] Step 12:

[1129] The server recommends where to buy clothing items that are in short supply.

[1130] Specific operation: The item recommendation module identifies missing items in the proposed outfit and generates purchasing information. The smart glasses display online shop links and nearby store information.

[1131] Input: Proposed outfit ideas, missing item information

[1132] Output: Purchase information (links and store information)

[1133] 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.

[1134] 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.

[1135] 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.

[1136] [Third embodiment]

[1137] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1138] 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.

[1139] 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).

[1140] 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.

[1141] 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.

[1142] 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).

[1143] 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.

[1144] 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.

[1145] 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.

[1146] 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.

[1147] 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.

[1148] 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."

[1149] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is composed of a user, a server, and a terminal.

[1150] overview

[1151] Users take a photo of their outfit using the camera on their smartphone or computer and send the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothing they are wearing. The user then uses their device to input information about their destination and weather for the day, which is then sent to the server. The server combines the analysis data with the input information, generates an optimal outfit, and presents it to the user. The user provides feedback, and the server uses that feedback to improve its next outfit suggestions. It also recommends places to purchase any clothing items the user is missing.

[1152] Program processing

[1153] Video Analysis

[1154] The server analyzes the received video data to identify the type of clothing (shirt, pants, accessories, etc.), color, and style the user is wearing. This analysis is performed using image recognition technology. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the style of the clothing. The resulting analysis data is stored in the server's internal database.

[1155] Coordinate generation

[1156] The device provides a means for the user to input information about their destination and weather, and sends that information to the server. Based on this information, the server uses a coordination suggestion module to generate optimal outfits. This module generates multiple coordination suggestions and evaluates each one. It also references an external fashion database, taking into account the latest fashion trends and seasonal styles.

[1157] Coordination presentation and feedback

[1158] The server selects the optimal outfit suggestions and sends them to the device as a recommendation list. The device displays them to the user. The user then enters feedback on the suggested outfits, which is sent to the server. The server stores the feedback and uses it in a machine learning module to learn about the user's preferences and patterns.

[1159] Purchase recommendation

[1160] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and sends information on where to purchase them to the device. The device displays this information to the user, providing links to online shops and information on nearby stores.

[1161] Specific examples

[1162] scenario

[1163] The user is going out to lunch with a friend this morning and is already dressed in a white shirt and jeans. The weather forecast predicts cloudy skies with rain.

[1164] flow

[1165] 1. The user takes a picture of a white shirt and jeans using the smartphone camera.

[1166] 2. The device sends the video data to the server.

[1167] 3. The server analyzes the video and identifies the white shirt and jeans.

[1168] 4. The user inputs the destination (lunch with a friend) and the weather (cloudy with rain) into the terminal.

[1169] 5. The device sends the input information to the server.

[1170] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[1171] 7. The server sends the proposal to the device.

[1172] 8. The device displays the suggestions to the user.

[1173] 9. The user provides feedback that they do not own a cardigan.

[1174] 10. The device sends the feedback to the server.

[1175] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[1176] 12. The terminal displays the supplier information to the user.

[1177] This process allows users to receive optimal fashion suggestions and easily obtain purchasing information to supplement any clothing shortages, thereby improving their fashion sense and giving them confidence in their everyday coordination.

[1178] The processing flow will be explained below.

[1179] Step 1:

[1180] The user takes a photo of their outfit using the camera on their smartphone or computer.

[1181] Step 2:

[1182] The video data acquired by the terminal is transmitted to the server.

[1183] Step 3:

[1184] The server begins analyzing the received video data.

[1185] Step 4:

[1186] The server's image recognition module identifies the type of clothing the user is wearing (e.g., shirt, pants, accessories, etc.) from the video.

[1187] Step 5:

[1188] The server's color recognition algorithm analyzes the color of each item.

[1189] Step 6:

[1190] The server's style recognition algorithm identifies the clothing style (e.g., casual, formal, etc.).

[1191] Step 7:

[1192] The server stores the analysis results in an internal database.

[1193] Step 8:

[1194] The user uses the terminal to input information about the destination and weather for the day.

[1195] Step 9:

[1196] The terminal sends the entered destination, schedule and weather data to the server.

[1197] Step 10:

[1198] The server combines the received destination and weather data with the analysis data.

[1199] Step 11:

[1200] The server's coordination suggestion module generates optimal coordination based on the analysis data and user information.

[1201] Step 12:

[1202] The server creates multiple coordination proposals and evaluates each one.

[1203] Step 13:

[1204] The server selects the most suitable coordination plan based on the evaluation results.

[1205] Step 14:

[1206] The server creates a recommendation list and sends it to the device.

[1207] Step 15:

[1208] The device displays the recommendation list to the user.

[1209] Step 16:

[1210] The user inputs feedback on the coordination into the terminal.

[1211] Step 17:

[1212] The terminal transmits the user's feedback data to the server.

[1213] Step 18:

[1214] The server stores the feedback data, and the machine learning module uses it to learn user preferences and patterns.

[1215] Step 19:

[1216] The server's item recommendation module identifies items that are missing from the user's outfit or outfit.

[1217] Step 20:

[1218] The server generates supplier information for the missing items.

[1219] Step 21:

[1220] The server sends the supplier information to the terminal.

[1221] Step 22:

[1222] The terminal displays the supplier information to the user.

[1223] Example 1

[1224] 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."

[1225] Conventional fashion coordination suggestion systems have problems such as difficulty in suggesting outfits that reflect the user's appropriate destination or weather information, or when the user does not accurately understand their own outfit. Furthermore, if the user is not satisfied with the suggested outfit, there is no mechanism to reflect that feedback in the next suggestion. Furthermore, there is also a lack of a way to quickly provide information on where to purchase missing items.

[1226] 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.

[1227] In this invention, the server includes: means for acquiring an image of the user's clothing; means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user; means for inputting information about the user's destination and weather; means for generating an appropriate outfit based on the analysis results and the input information; means for presenting the generated outfit to the user; means for receiving feedback from the user, learning from the feedback, and incorporating it into the next outfit generation; means for recommending where to purchase missing clothing accessories; means for identifying the color and style of clothing using image recognition technology; means for learning the user's preferences and patterns using a machine learning module; means for referencing an external fashion database to generate outfits; means for evaluating outfit suggestions based on the user's destination and weather information; and means for providing links to online shops and nearby store information. This allows the server to accurately analyze the user's current fashion situation and propose optimal outfits based on the weather and destination. Furthermore, the server can reflect the user's feedback in the next outfit proposal and quickly provide information on where to purchase missing items.

[1228] "User" refers to an individual who uses the system to photograph, input, and provide feedback about their outfit.

[1229] "Server" refers to a central processing unit that receives data sent by users, analyzes, stores, learns from, and reflects coordination suggestions and feedback.

[1230] A "terminal" is a device used by a user, such as a smartphone or PC, and refers to an interface means for taking images, inputting information, displaying outfit suggestions, etc.

[1231] "Image recognition technology" is a technology that automatically identifies objects, shapes, colors, etc. from acquired image data, and primarily utilizes deep learning models and algorithms.

[1232] "Machine learning module" refers to artificial intelligence (AI) technology or software programs that learn from user feedback data and improve the accuracy of future outfit suggestions.

[1233] The "coordination suggestion module" refers to a software program that generates optimal outfit combinations by referencing a fashion database based on the user's clothing analysis data and input information.

[1234] A "fashion database" refers to a database that contains the latest fashion trends, style information according to the season, brand information, etc.

[1235] "Feedback" refers to input information such as evaluations, opinions, and comments made by users regarding the proposed coordination.

[1236] "Purchaser information" refers to links to online shops and information on physical stores provided as places to purchase new clothing items that the user needs.

[1237] "Destination information" refers to information about places and events that the user plans to go to.

[1238] "Weather information" refers to information about the weather conditions at the user's location or the location where the user plans to go.

[1239] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is mainly composed of a user, a server, and a terminal.

[1240] System Overview

[1241] The user uses the camera on their smartphone or computer to take a picture of their current outfit and sends the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothes the user is wearing. The user then uses their device to input information such as their destination and weather, which is then sent to the server. The server then combines the analysis data with the input information to generate an optimal outfit and present it to the user. It receives feedback from the user and reflects it in generating the next outfit. It also provides information on where to purchase any clothing items the user does not own.

[1242] System configuration and processing

[1243] Video Analysis

[1244] The server analyzes the received video data. This analysis uses image recognition technologies such as TensorFlow and OpenCV. Specifically, it extracts contours from the transmitted image data, identifies the color of the clothing using a color recognition algorithm, and determines the type of clothing and silhouette using a style recognition algorithm. The resulting data is stored in the server's internal database.

[1245] Coordinate generation

[1246] The device provides a means for users to input destination and weather information, and sends that information to the server. The server then uses a coordination suggestion module to combine the user's clothing analysis data with the input information to generate optimal outfits. This module references an external fashion database (e.g., Polyvore API) and takes into account the latest fashion trends and seasonal styles.

[1247] Coordination presentation and feedback

[1248] The server sends the generated outfits to the device, which displays them to the user. The user can then enter feedback about the outfit suggestions, which is then sent back to the server. The server stores the feedback and uses a machine learning module to improve the accuracy of the next outfit suggestions.

[1249] Purchase recommendation

[1250] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and generates information on where to purchase them. The generated information is sent to the user's device and provided to them. Specifically, it includes links to online shops and information on nearby stores.

[1251] Specific examples

[1252] Consider a scenario where a user is going out to lunch with a friend on the following date and is wearing a white shirt and jeans. The weather forecast is cloudy with rain.

[1253] flow

[1254] 1. A user takes a picture of a white shirt and jeans using the smartphone camera.

[1255] 2. The device sends the video data to the server.

[1256] 3. The server analyzes the video and identifies the white shirt and jeans.

[1257] 4. The user inputs the destination ("lunch with a friend") and the weather ("cloudy with rain") into the terminal.

[1258] 5. The device sends the input information to the server.

[1259] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[1260] 7. The server sends the proposal to the device.

[1261] 8. The device displays the suggestions to the user.

[1262] 9. The user provides feedback that they do not own a cardigan.

[1263] 10. The device sends the feedback to the server.

[1264] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[1265] 12. The terminal displays the supplier information to the user.

[1266] Prompt Sentence Examples

[1267] User outfit image: [image file]

[1268] Destination: Lunch with a friend

[1269] Weather: Cloudy with rain

[1270] Please suggest the best outfit to go with my current outfit. Also, please let me know where to buy any items that are missing from the suggested outfit.

[1271] This system not only allows users to receive suggestions for the perfect outfit for the day, but also makes it easy to find out how to purchase any missing items. Through this process, users can improve their fashion sense and gain confidence.

[1272] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1273] Step 1:

[1274] The user takes a photo of their own outfit using the camera on their smartphone or computer. The input is image data of the outfit. Specifically, the user launches the camera app and presses the capture button to take a full-body shot of the outfit they are currently wearing. The output is the captured image data.

[1275] Step 2:

[1276] The device sends the captured image data to the server. The input is the image data captured by the user. Specifically, the device uploads this image data to the specified server URL via the Internet. The output is the image data sent to the server.

[1277] Step 3:

[1278] The server analyzes the received image data and identifies the type, color, and style of clothing worn by the user. The input is image data sent from the device. Specifically, the server first preprocesses the image (e.g., noise removal), then uses TensorFlow or OpenCV to identify the color of the clothing using k-means clustering, and uses a deep learning model (e.g., ResNet or YOLO) to determine the type of clothing and silhouette. The output is analytical data related to the type, color, and style of clothing.

[1279] Step 4:

[1280] The user uses the device to input destination and weather information. The input includes clothing data after video analysis, the destination (e.g., "lunch with friends"), and the weather (e.g., "cloudy with rain"). Specifically, the user enters the destination and weather information into the app's input form and presses the send button. The output is the destination and weather information entered into the device.

[1281] Step 5:

[1282] The terminal transmits the destination and weather information input by the user to the server. The input is the destination and weather information input by the user to the terminal. In concrete terms, the terminal transmits this information to the server via the Internet. The output is the destination and weather information transmitted to the server.

[1283] Step 6:

[1284] The server integrates the analysis data with the information entered by the user and generates the optimal outfit using the outfit suggestion module. The input is the clothing analysis data, destination, and weather information. Specifically, the server queries an external fashion database, generates multiple outfit suggestions that meet the conditions, and selects the optimal suggestion based on the destination and weather conditions. The output is the outfit suggestion presented to the user.

[1285] Step 7:

[1286] The server transmits the generated coordination plan to the terminal. The input is the optimal coordination plan. In concrete terms, the server transmits the selected coordination plan to the terminal via the Internet. The output is the coordination plan transmitted to the terminal.

[1287] Step 8:

[1288] The terminal displays the outfit suggestions received from the server to the user. The input is the outfit suggestions sent from the server. As a specific operation, the outfit suggestions are visually displayed on the screen of the terminal. The output is the outfit suggestions that the user can view.

[1289] Step 9:

[1290] The user inputs feedback on the proposed outfit. The input is the proposed outfit. Specifically, the user enters comments and ratings into the app's feedback form and presses the send button. The output is the feedback information entered into the device.

[1291] Step 10:

[1292] The terminal sends the feedback information to the server. The input is the feedback information entered by the user. In concrete terms, the terminal sends this information to the server via the Internet. The output is the feedback information sent to the server.

[1293] Step 11:

[1294] The server stores the feedback and uses it in a machine learning module to improve the next coordination proposal. The input is the feedback information. Specifically, the server stores the feedback information in a database and uses it to update the machine learning model. The output is an improved coordination model.

[1295] Step 12:

[1296] The server's item recommendation module identifies missing items in the user's outfit or the proposed outfit, and generates information on where to purchase them. The input is the proposed outfit and feedback information. Specifically, the server identifies the missing item (e.g., a "gray cardigan") and collects information on online shops and nearby stores. The output is information on where to purchase them.

[1297] Step 13:

[1298] The server sends the generated supplier information to the terminal. The input is the supplier information. In concrete terms, the server sends the supplier information to the terminal via the Internet. The output is the supplier information sent to the terminal.

[1299] Step 14:

[1300] The terminal displays the supplier information to the user. The input is the supplier information sent from the server. As a specific operation, the supplier information is visually displayed on the terminal screen. The output is the supplier information that the user can view.

[1301] (Application example 1)

[1302] 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."

[1303] In modern society, there is a demand for assistance in optimizing the coordination of users' clothing. Efficient and personalized coordination suggestions and purchasing support are essential, especially for users who struggle with daily fashion choices. However, current systems struggle to analyze users' clothing in real time and provide optimal coordination suggestions based on various criteria, as well as information on where to purchase missing items. Furthermore, there is a lack of systems that allow users to virtually try on suggested coordinations. Therefore, a means is needed that allows users to easily receive high-quality fashion advice while also receiving purchasing support.

[1304] 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.

[1305] In this invention, the server includes means for acquiring an image of the user's clothing, means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user, and means for inputting information on the user's destination and weather, thereby enabling the user to receive optimal outfit suggestions.

[1306] The server further includes a means for generating an appropriate outfit based on the analysis results and input information, a means for presenting the generated outfit to the user and enabling virtual try-on, a means for receiving feedback from the user, learning from it, and reflecting it in generating the next outfit, and a means for recommending places to purchase missing clothing items and providing links to online stores. This allows the user to not only receive outfit suggestions in real time, but also personalized suggestions that reflect the user's feedback, and easily purchase missing items.

[1307] "Image acquisition means" refers to a device or function for capturing images of a user's clothing in real time, and includes image capture devices such as smartphones, smart glasses, and head-mounted displays.

[1308] "Video analysis means" refers to software or algorithms that analyze captured video data in real time and identify the type, color, and style of clothing worn by the user.

[1309] "Information input means" refers to a function that provides an interface for users to input destination and weather information, and includes the use of a mobile information terminal or a personal computer.

[1310] "Coordination generation means" refers to an algorithm or module that generates appropriate clothing combinations based on the results of video analysis and information entered by the user.

[1311] The "coordinate presentation means" refers to an interface or device for visually displaying the generated coordinates to the user, and also includes a function that allows virtual try-on.

[1312] "Feedback means" refers to a function that provides an interface for receiving opinions and reactions from users regarding coordination suggestions, learns from them, and reflects them in the next suggestion.

[1313] "Purchase recommendation means" refers to a function for providing information on where to purchase items that are missing from the proposed outfit, and includes providing links to online stores.

[1314] "Internal database" refers to a database that stores analyzed data and user feedback and is used within the system.

[1315] "External database" refers to an external fashion information service that is referenced to obtain the latest fashion trends and seasonal style information.

[1316] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is composed of a user, a server, and a terminal.

[1317] System Configuration

[1318] The system includes the following main measures:

[1319] 1. Image acquisition means: A device or function for capturing images of the user's clothing in real time. This uses an image capture device such as a smartphone, smart glasses, or a head-mounted display.

[1320] 2. Video analysis means: This refers to software and algorithms that analyze captured video data in real time and identify the type, color, and style of clothing worn by the user. Specifically, OpenCV and TensorFlow are used.

[1321] 3. Information input means: This function provides an interface for users to input destination and weather information, and uses the user interface of a smartphone or PC.

[1322] 4. Coordination generation means: Algorithms and modules that generate appropriate clothing combinations based on the results of video analysis and input information, taking into account the user's preferences and the latest fashion database.

[1323] 5. Coordination presentation means: A function for visually displaying the generated coordination to the user, including an interface that allows virtual try-on.

[1324] 6. Feedback means: This function provides an interface for receiving opinions and reactions from users regarding coordination suggestions, and learns from that feedback and reflects it in future suggestions.

[1325] 7. Purchasing recommendation tool: This function provides information on where to purchase items that are missing from the suggested outfit, including links to online stores.

[1326] System Operation

[1327] 1. Image acquisition:

[1328] Users take photos of their outfits in real time using the camera on their smartphone or smart glasses.

[1329] The captured video data is immediately sent to a server for analysis.

[1330] 2. Video analysis:

[1331] The server uses OpenCV and TensorFlow to analyze the transmitted video data and identify the type of clothing (e.g., shirt, pants, dress, etc.), color, and style the user is wearing.

[1332] 3. Enter your information:

[1333] The user inputs destination and weather information through the terminal interface, which is then sent to the server.

[1334] Example prompt statement:

[1335] user_info = {

[1336] 'location': 'Tokyo',

[1337] 'event': 'Lunch with a friend'

[1338] }

[1339] 4. Coordinate generation:

[1340] Based on the video analysis results and the input information, the server refers to the latest fashion database and the user's past feedback information to generate the optimal outfit.

[1341] The generated coordinates are saved as information and sent to the user's terminal.

[1342] 5. Coordination presentation and virtual try-on:

[1343] The terminal visually displays the generated outfits to the user, allowing the user to virtually try on the suggested outfits.

[1344] 6. Feedback:

[1345] The user inputs their opinions and reactions to the proposed coordination through the terminal, which are then sent to the server.

[1346] The server learns from the feedback it receives and understands the user's preferences and patterns.

[1347] 7. Purchase recommendation:

[1348] The server's item recommendation module identifies items missing from the proposed outfit and generates purchasing information and links to online shops.

[1349] The terminal displays the recommended vendor information to the user.

[1350] Specific examples

[1351] For example, if a user is going out to lunch with a friend this morning and is wearing a white shirt and jeans, and the weather forecast predicts cloudy skies with rain, the system will operate as follows:

[1352] 1. The user uses the smartphone camera to take a picture of a white shirt and jeans.

[1353] 2. The captured video data is sent to the server.

[1354] 3. The server analyzes the video and identifies the white shirt and jeans.

[1355] 4. The user inputs the destination (lunch with a friend) and the weather (cloudy with rain) into the terminal.

[1356] 5. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[1357] 6. The server sends the proposal to the device.

[1358] 7. The device displays the suggestions to the user, who then virtually tries them on.

[1359] 8. The user provides feedback that they do not own a cardigan.

[1360] 9. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[1361] 10. The terminal displays the purchasing information to the user, and the user can purchase the cardigan from the online shop.

[1362] By following this process, users can easily purchase any missing items while receiving suggestions for optimal outfits.

[1363] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1364] Step 1: The user takes a picture of their outfit in real time using the camera on their smartphone or smart glasses. The captured video data is immediately sent to the server.

[1365] Input: Video data of the clothes worn by the user.

[1366] Output: Sending video data to the server.

[1367] How it works: The user turns on the camera on their smartphone and takes a full-body video of themselves. This video data is then uploaded to a cloud server in real time.

[1368] Step 2: The server uses OpenCV and TensorFlow to analyze the transmitted video data and identify the type, color, and style of clothing the user is wearing.

[1369] Input: Video data sent to the server.

[1370] Output: Analyzed data about clothing type, color, and style.

[1371] How it works: Image recognition algorithms running on the server identify the type of clothing (shirt, pants, etc.) as well as their color and style from the video data. The resulting analysis data is stored in an internal database.

[1372] Step 3: The user inputs destination and weather information through the terminal interface, which is then sent to the server.

[1373] Input: Destination and weather information.

[1374] Output: Sending information to the server.

[1375] Specific operation: The user uses a smartphone app to enter the location they plan to go to that day and weather forecast information, and then submits the form.

[1376] Step 4: The server's coordinate generation means generates an optimal coordinate based on the video analysis results and the information input by the user, by referring to the latest fashion database and the user's past feedback information.

[1377] Input: Analysis data, user destination and weather information.

[1378] Output: Optimal outfit ideas.

[1379] Specific operation: The server searches a fashion database for the latest trends and weather-appropriate combinations, and generates optimal outfit suggestions for shirts, pants, and accessories.

[1380] Step 5: The terminal visually displays the generated outfit to the user, allowing the user to virtually try on the suggested outfit.

[1381] Input: Generated coordinate plan.

[1382] Output: Visual presentation of outfits and virtual try-on.

[1383] Specific operation: The device displays outfit ideas on the application interface, and the user tries them on in a virtual environment.

[1384] Step 6: The user inputs their opinions and reactions to the proposed coordination through the terminal, which are then sent to the server.

[1385] Input: User feedback.

[1386] Output: Sending feedback to the server.

[1387] Specific operation: The user enters their thoughts and opinions about the outfit into the feedback form within the application and presses the submit button.

[1388] Step 7: The server learns from the received feedback and understands the user's preferences and patterns. It uses the generative AI model to reflect this in the next outfit suggestions.

[1389] Input: User feedback data.

[1390] Output: Improved outfit suggestions.

[1391] How it works: The server stores the feedback information in a database, and the generative AI model uses this information to learn user preferences and patterns.

[1392] Step 8: The server's item recommendation module identifies the missing items and generates purchasing information and links to online shops.

[1393] Input: User's current belongings information and coordination suggestions.

[1394] Output: Purchase information and online shop link.

[1395] Specific operation: The server retrieves purchasing information from an internal database and external shopping sites and sends it to the user's device.

[1396] Step 9: The terminal displays the recommended purchasing information to the user, and the user can purchase the missing items online based on the recommended purchasing information.

[1397] Input: Supplier information and shopping links.

[1398] Output: Providing information to the user and assisting them in making a purchase.

[1399] Specific operation: The device displays the purchasing information and link on the application display screen, and the user can purchase the item from the online shop by clicking the link.

[1400] This flow of processing steps allows the user to efficiently receive suggestions for optimal outfits while easily obtaining the items they need.

[1401] 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.

[1402] This invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. This system is comprised of a user, a server, and a terminal, and also incorporates an emotion engine that recognizes the user's emotions.

[1403] overview

[1404] Users take pictures of their outfits using the camera on their smartphone or computer and send the images to the server. The server analyzes the image data and identifies the type, color, and style of the clothes they are wearing. The user then inputs their destination and weather information for the day using their device, which is then sent to the server. The server then combines the analysis data, the input information, and the user's emotions, as recognized by the emotion engine, to generate an optimal outfit. This generated outfit matches the user's mood. The user provides feedback on the suggested outfit, and the server uses that feedback to improve its next outfit suggestions. The server also recommends places to purchase any clothing items the user is missing.

[1405] Program processing

[1406] Video Analysis

[1407] The server analyzes the received video data and identifies the type of clothing (e.g., shirt, pants, accessories, etc.), color, and style) worn by the user. This analysis is performed using image recognition technology. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the style of the clothing. The resulting analysis data is stored in the server's internal database.

[1408] Emotion analysis

[1409] The device provides a means to acquire the user's facial expressions and voice in real time and transmits the data to a server. An emotion engine installed on the server analyzes the user's emotions based on this data. The emotion engine uses facial expression recognition and voice analysis technology to determine the user's current emotion (e.g., joy, sadness, excitement, fatigue).

[1410] Coordinate generation

[1411] The device provides a means for the user to input information about their destination and weather, and sends that information to the server. Based on this, the server uses a coordination suggestion module to generate optimal outfits. This module generates multiple outfit suggestions based on analytical data, emotional data, and user information, and evaluates each one. It also references an external fashion database, taking into account the latest fashion trends and seasonal styles. It also adjusts the style of the suggested outfits based on the user's emotions, presenting outfits that suit the user's mood.

[1412] Coordination presentation and feedback

[1413] The server selects the optimal outfit suggestions and sends them to the device as a recommendation list. The device displays them to the user. The user then enters feedback on the suggested outfits, which is sent to the server. The server stores the feedback and uses it in a machine learning module to learn about the user's preferences and patterns.

[1414] Purchase recommendation

[1415] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and sends information on where to purchase them to the device. The device displays this information to the user, providing links to online shops and information on nearby stores.

[1416] Specific examples

[1417] scenario

[1418] The user is planning to go out to lunch with a friend this morning and is already dressed in a white shirt and jeans. The weather forecast predicts cloudy skies with rain. The user is feeling a little tired, but is looking forward to a fun lunch.

[1419] flow

[1420] 1. A user takes a picture of a white shirt and jeans using their smartphone camera.

[1421] 2. The device sends the video data to the server.

[1422] 3. The server analyzes the video and identifies the white shirt and jeans.

[1423] 4. The user inputs a destination (lunch with a friend) and weather (cloudy with rain) into the terminal.

[1424] 5. The device sends the input information to the server.

[1425] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[1426] 7. The server sends the proposal to the device.

[1427] 8. The device displays the suggestions to the user.

[1428] 9. The user provides feedback that they do not own a cardigan.

[1429] 10. The device sends the feedback to the server.

[1430] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[1431] 12. The terminal displays the supplier information to the user.

[1432] 13. The user provides facial expression and voice data through the terminal.

[1433] 14. The device sends facial expression and voice data to the server.

[1434] 15. The server's emotion engine analyzes the user's emotions and suggests additional outfits that emphasize a happy mood (e.g., brightly colored accessories).

[1435] This process allows users to receive optimal fashion suggestions and easily obtain purchasing information to supplement any clothing shortages. Furthermore, adjustments are made to match the user's emotions, further increasing satisfaction with everyday coordination.

[1436] The processing flow will be explained below.

[1437] Step 1:

[1438] The user takes a photo of their outfit using the camera on their smartphone or computer.

[1439] Step 2:

[1440] The video data acquired by the terminal is transmitted to the server.

[1441] Step 3:

[1442] The server begins analyzing the received video data.

[1443] Step 4:

[1444] The server's image recognition module identifies the type of clothing the user is wearing (e.g., shirt, pants, accessories, etc.) from the video.

[1445] Step 5:

[1446] The server's color recognition algorithm analyzes the color of each item.

[1447] Step 6:

[1448] The server's style recognition algorithm identifies the clothing style (e.g., casual, formal, etc.).

[1449] Step 7:

[1450] The server stores the analysis results in an internal database.

[1451] Step 8:

[1452] The user uses the terminal to input information about the destination and weather for the day.

[1453] Step 9:

[1454] The terminal sends the entered destination, schedule and weather data to the server.

[1455] Step 10:

[1456] The server combines the received destination and weather data with the analysis data.

[1457] Step 11:

[1458] The user provides emotional data such as facial expressions and voice through the terminal.

[1459] Step 12:

[1460] The device transmits the emotion data to the server.

[1461] Step 13:

[1462] The server's emotion engine uses facial expression recognition and voice analysis technology to analyze the user's emotions (e.g., joy, sadness, excitement, fatigue, etc.).

[1463] Step 14:

[1464] The server's coordination suggestion module generates optimal coordination based on analysis data, emotion data, and user information.

[1465] Step 15:

[1466] The server creates multiple coordination proposals and evaluates each one.

[1467] Step 16:

[1468] The server selects the most suitable coordination plan based on the evaluation results.

[1469] Step 17:

[1470] The server creates a recommendation list and sends it to the device.

[1471] Step 18:

[1472] The device displays the recommendation list to the user.

[1473] Step 19:

[1474] The user inputs feedback on the proposed coordination into the terminal.

[1475] Step 20:

[1476] The terminal transmits the user's feedback data to the server.

[1477] Step 21:

[1478] The server stores the feedback data, and the machine learning module uses it to learn user preferences and patterns.

[1479] Step 22:

[1480] The server's item recommendation module identifies items that are missing from the user's outfit or outfit.

[1481] Step 23:

[1482] The server generates information on where to purchase the missing items and transmits it to the terminal.

[1483] Step 24:

[1484] The terminal displays the supplier information to the user.

[1485] Example 2

[1486] 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."

[1487] Conventional fashion coordination assistant systems can make suggestions based on the user's clothing and style, destination, weather information, etc., but they cannot generate coordinations that take the user's emotions into consideration, so they have the problem of not being able to make suggestions that fully reflect the user's mood.In addition, they lack the function to specifically recommend clothing items that the user is lacking, making it difficult for users to easily purchase the items needed for the suggested coordination.

[1488] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring an image of the user's clothing, means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user, means for inputting information about the user's destination and weather, means for generating an appropriate outfit based on the analysis results and the input information, means for presenting the generated outfit to the user, means for receiving feedback from the user, learning from the feedback, and reflecting it in generating the next outfit, means for analyzing the user's emotions, means for adjusting the outfit based on the emotions, and means for recommending where to purchase missing clothing and accessories. This makes it possible to suggest an optimal outfit based on the user's mood, and by specifically recommending where to purchase missing items, the user can quickly obtain the items they need.

[1489] "User" refers to a person who uses the system to improve or receive suggestions for their own clothing coordination.

[1490] "Outfit image" refers to digital image data that contains visual information about the clothing and accessories worn by a user.

[1491] "Means for acquiring" refers to a device or technology that allows a user to take an image of the outfit and send the image to the system.

[1492] "Means for analyzing" refers to technology for identifying the type, color, and style of clothing worn by a user based on the acquired image data.

[1493] "Means for identifying" refers to technology for identifying specific attributes of the clothing worn by the user based on the analysis results.

[1494] "Input means" refers to the devices and technologies that allow users to input destination and weather information.

[1495] "Means for generating appropriate coordination" refers to technology for proposing optimal clothing combinations to users based on analysis results and input information.

[1496] "Presenting means" refers to a device or technology for showing the generated coordinates to the user.

[1497] "Means for receiving feedback" refers to technology that allows users to input their thoughts and requests regarding the proposed outfits and send that information to the system.

[1498] "Means of learning" refers to technology that uses user feedback to improve the next outfit suggestion.

[1499] "Means for analyzing emotions" refers to technology for identifying emotions based on a user's facial expressions and voice data.

[1500] The term "means for adjusting a coordination based on emotions" refers to a technique for adjusting an optimal coordination for a user in consideration of the analyzed emotions of the user.

[1501] "Means for recommending where to purchase missing clothing items" refers to technology for showing a user where to purchase missing items based on the suggested outfit.

[1502] This invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. This system is comprised of a user, a server, and a terminal, and also incorporates an emotion analysis engine that recognizes the user's emotions.

[1503] Hardware and software used

[1504] The server is equipped with image recognition technology, an emotion analysis engine, a coordination suggestion module, an item recommendation module, and a machine learning algorithm, which utilize the following specific technologies:

[1505] Image recognition technology: color recognition algorithm, style recognition algorithm

[1506] Emotion analysis engine: facial expression recognition technology, voice analysis technology

[1507] Coordination suggestion module: Includes the function to refer to external fashion databases

[1508] Item recommendation module: Online shop link generation function, nearby store information acquisition function

[1509] Machine learning algorithms: Ability to learn from feedback data

[1510] The device includes a camera that captures images of the user's outfit, an interface for inputting destination and weather information, and a display that shows suggested outfits and shopping information.

[1511] Users can use these functions using smartphones or computers.

[1512] Coordination proposal process

[1513] Users use their smartphone or PC camera to take a picture of their outfit and send the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothes they are wearing. The user then inputs their destination and weather information for the day via their device, which is then sent to the server. The server then combines the analysis data, the input information, and the user's emotional data recognized by an emotion analysis engine to generate the optimal outfit. The generated outfit matches the user's mood.

[1514] For example, suppose a user is planning to go out to lunch with a friend this morning and is wearing a white shirt and jeans. The weather forecast predicts cloudy skies with rain, and the user is feeling a little tired but is looking forward to a pleasant lunch. In this situation, the flow of using the system is as follows:

[1515] 1. A user takes a picture of a white shirt and jeans using their smartphone camera.

[1516] 2. The device sends the video data to the server.

[1517] 3. The server analyzes the video and identifies the white shirt and jeans.

[1518] 4. The user inputs a destination (lunch with a friend) and weather (cloudy with rain) into the terminal.

[1519] 5. The device sends the input information to the server.

[1520] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots.

[1521] 7. The server sends the proposal to the terminal, which displays it to the user.

[1522] 8. The user provides feedback that they do not own a cardigan.

[1523] 9. The device sends the feedback to the server.

[1524] 10. The server stores the feedback and generates and sends information about where to buy the cardigan to the device.

[1525] 11. The device displays the retailer information to the user.

[1526] 12. The user provides facial expression and voice data through the terminal.

[1527] 13. The device sends facial expression and voice data to the server.

[1528] 14. The server's emotion analysis engine analyzes the user's emotions and suggests additional accessories that emphasize a happy mood (e.g., a brightly colored scarf).

[1529] 15. The server sends the additional suggestions to the terminal, which displays them to the user.

[1530] This process not only allows users to receive optimal fashion suggestions, but also provides information on purchasing clothing items that they are lacking, and improves their satisfaction with their everyday outfits.

[1531] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1532] Step 1:

[1533] Users take a photo of their outfit using the camera on their smartphone or computer. Specifically, the user stands in front of a mirror and takes a photo that captures their entire body. The captured image is then saved as digital data on the device.

[1534] Input: Image of the user's outfit

[1535] Output: Digital image data

[1536] Step 2:

[1537] The terminal transmits the captured digital image data to a server via the Internet.

[1538] Input: Digital image data

[1539] Output: Image data sent to the server

[1540] Step 3:

[1541] The server analyzes the received digital image data. It uses image recognition technology to identify the type of clothing (e.g., shirt, pants), color, and style the user is wearing. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the type of clothing. The analysis results are stored in an internal database.

[1542] Input: Digital image data

[1543] Data processing and calculation: Color recognition algorithm, style recognition algorithm

[1544] Output: Analysis results (clothing type, color, style)

[1545] Step 4:

[1546] The user inputs information about the destination and weather for the day through the terminal, and the input information is sent from the terminal to the server.

[1547] Input: Destination information, weather information

[1548] Output: Destination information and weather information sent to the server

[1549] Step 5:

[1550] The server uses the outfit suggestion module to generate optimal outfits based on the analysis results and the destination and weather information entered by the user. During this process, it references an external fashion database to consider the latest trends and seasonal styles. It also uses the user's emotional data to consider outfits that suit their mood.

[1551] Input: Analysis results, destination information, weather information, emotion data

[1552] Data processing and calculation: External fashion database reference, coordinate generation algorithm

[1553] Output: Generated coordinate plan

[1554] Step 6:

[1555] The server selects one of the generated coordination plans and sends it to the terminal, which displays it to the user.

[1556] Input: Generated coordination plan

[1557] Output: Coordination ideas displayed to the user

[1558] Step 7:

[1559] The user inputs feedback about the proposed outfit. For example, the user inputs feedback such as "I don't own a cardigan" into the terminal. The feedback is sent from the terminal to the server.

[1560] Input: User feedback

[1561] Output: Feedback sent to the server

[1562] Step 8:

[1563] The server uses machine learning algorithms to learn from user feedback and suggests outfits, storing the feedback to improve future suggestions.

[1564] Input: Feedback data

[1565] Data processing and calculation: Machine learning algorithms

[1566] Output: Improved outfit suggestion data

[1567] Step 9:

[1568] The server's item recommendation module generates purchasing information for missing items (e.g., cardigans) based on the suggested outfits, including online shop links and nearby store locations.

[1569] Input: Feedback data

[1570] Data processing and calculation: Item recommendation algorithm

[1571] Output: Generated supplier information

[1572] Step 10:

[1573] The server transmits the generated supplier information to the terminal, which displays it to the user.

[1574] Input: Generated supplier information

[1575] Output: Supplier information displayed to the user

[1576] Step 11:

[1577] The user provides facial expression and voice data through the device, which is collected in real time and sent to the server.

[1578] Input: facial expression data, voice data

[1579] Output: Emotion data sent to the server

[1580] Step 12:

[1581] The server's emotion analysis engine analyzes the user's emotions from their facial expressions and voice. For example, it can use facial recognition technology to determine if the user is slightly tired. The results of this emotion analysis are also reflected in the outfit suggestions.

[1582] Input: facial expression data, voice data

[1583] Data processing and calculation: Emotion analysis algorithm

[1584] Output: Emotion analysis results

[1585] Step 13:

[1586] Based on the results of the emotion analysis, the server adjusts the outfit to suit the user's mood and generates additional suggestions, such as an accessory (such as a brightly colored scarf) that emphasizes a happy mood.

[1587] Input: Sentiment analysis results

[1588] Data processing and calculation: Coordinate adjustment algorithm

[1589] Output: Additional suggested coordinates

[1590] Step 14:

[1591] The server sends the additional suggestions to the terminal, which displays them to the user.

[1592] Input:Add suggested coordinates

[1593] Output: Additional outfit suggestions displayed to the user

[1594] In this way, users can not only receive optimal fashion suggestions through the system, but also obtain purchasing information for items they are lacking, and can receive coordination suggestions that correspond to their emotions.

[1595] (Application example 2)

[1596] 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."

[1597] Conventional outfit suggestion systems only consider the user's clothing and preferences, but do not consider emotions or real-time environmental changes. As a result, suggestions may be made that do not match the user's mood or the weather, resulting in low satisfaction. Also, if a suggested outfit is missing an item, there is insufficient means to supplement it. These issues need to be resolved.

[1598] 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.

[1599] In this invention, the server includes means for acquiring images of the user's clothing, means for analyzing the acquired images and identifying the type, color, and style of the clothing worn by the user, means for inputting information about the user's destination and weather conditions, means for acquiring the user's facial expressions and voice in real time and analyzing their emotions, means for adjusting and presenting the generated outfit in accordance with the user's emotions, means for receiving feedback from the user, learning from it, and reflecting it in generating the next outfit, and means for recommending where to purchase missing clothing accessories. This makes it possible to propose optimal outfits that take into account the user's emotions and real-time environmental changes.

[1600] The "means for acquiring an image of the user's clothing" refers to a device or technology for photographing the clothing currently being worn by the user.

[1601] "Means for analyzing the captured image and identifying the type, color, and style of clothing worn by the user" refers to technology that processes captured image data and identifies detailed characteristics of the clothing worn by the user.

[1602] The "means for inputting information on the user's destination and weather conditions" refers to a device or method for inputting the user's planned location and weather information for the day into the system.

[1603] "Means for acquiring a user's facial expressions and voice in real time and analyzing their emotions" refers to technology that acquires a user's facial expressions and tone of voice in real time and determines the user's emotional state based on that data.

[1604] "Means for adjusting and presenting the generated coordination in accordance with the user's emotions" refers to a device or method for optimizing the generated coordination to reflect the user's current emotional state and presenting it to the user.

[1605] "Means for receiving feedback from the user, learning from it, and reflecting it in the next coordination generation" refers to a learning technology that records the user's reactions and opinions and uses them to help generate the next coordination.

[1606] The "means for recommending where to purchase missing clothing accessories" is a technology that detects items that are missing from a proposed outfit and provides the user with information on where to purchase those items.

[1607] This invention is a system that acquires images of a user's clothing, analyzes them, and suggests outfits that suit the user's outfit. The system consists of a terminal, a server, and a user's device. Using smart glasses, a smartphone, a PC, or other devices, users can easily try on clothes virtually and receive fashion advice from the comfort of their own home.

[1608] 1. How to obtain images of the user's clothing

[1609] The user uses the camera in the smart glasses to take a picture of their own clothes in real time and captures the image. The smart glasses device collects the image data and sends it to the server.

[1610] 2. A means of analyzing the captured image and identifying the type, color, and style of clothing worn by the user.

[1611] The server analyzes the received image data to identify the type, color, and style of the user's clothing. This analysis is performed using algorithms from image recognition technologies (e.g., OpenCV and TensorFlow). For example, a color recognition algorithm determines the color, and a style recognition algorithm identifies the style of the clothing.

[1612] 3. A means of inputting information about the user's destination and weather conditions

[1613] Users can input their destination and weather information for the day through the smart glasses' voice assistant, which is then sent to the server and integrated with analytical data.

[1614] 4. A means of capturing the user's facial expressions and voice in real time and analyzing their emotions

[1615] The image data sent to the server is used to analyze the user's facial expressions and voice. Facial expression recognition technology (e.g., face_recognition) and voice analysis technology (e.g., emotion_recognition) are used to detect the user's current emotion (happiness, sadness, excitement, fatigue, etc.).

[1616] 5. A method for adjusting and presenting the generated outfits according to the user's emotions

[1617] Based on the analysis results, input information, and emotional data, the outfit suggestion module generates the optimal outfit. This module uses a generative AI model (e.g., a TensorFlow model) to evaluate multiple outfit suggestions. It also references an external fashion database to consider the latest fashion trends and seasonal styles. It adjusts the suggestions based on the user's emotions and presents outfits that suit the user's mood.

[1618] 6. A means to receive feedback from users, learn from it, and reflect it in the next coordinate generation

[1619] Users can provide feedback on the suggested outfits through the smart glasses, which is then sent to the server, where the machine learning module learns the user's preferences and patterns and reflects them in the next outfit suggestions.

[1620] 7. Recommendations for purchasing clothing items in short supply

[1621] The server's item recommendation module identifies missing items in an outfit and provides the user with information on where to purchase them. The suggested outfits and item information are displayed on the smart glasses, allowing the user to easily access links to online shops and nearby store locations.

[1622] Examples of concrete examples and prompts

[1623] Specific examples

[1624] For example, a user uses smart glasses to wear a white shirt and jeans at home. The user plans to go on a picnic in the park with friends the next day, and the weather forecast predicts sunny skies. The system also determines that the user is feeling a little tired. The system then suggests a bright-colored cardigan or colorful scarf to go with the white shirt and jeans, providing an outfit that will lift the user's spirits.

[1625] Prompt Sentence Examples

[1626] "Tomorrow I'm going to have a picnic in the park with a friend. The weather is sunny. I'm a little tired. Can you suggest some outfits that will make me feel energized?"

[1627] In this way, the present invention provides a system that takes into consideration the user's emotions and real-time environmental changes and proposes optimal outfits.

[1628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1629] Step 1:

[1630] The user uses the camera in the smart glasses to take a picture of their clothing.

[1631] Specific operation: The user wears the smart glasses and captures an image of their entire outfit with the camera to obtain image data.

[1632] Input: Real-time clothing image

[1633] Output: Acquired clothing image data

[1634] Step 2:

[1635] The terminal transmits the acquired image data to the server.

[1636] Specific operation: The smart glasses are connected via Wi-Fi or Bluetooth and transmit the acquired image data to the server.

[1637] Input: Clothing image data

[1638] Output: Image data sent to the server

[1639] Step 3:

[1640] The server analyzes the transmitted image data and identifies the type, color, and style of clothing the user is wearing.

[1641] How it works: An image recognition algorithm running on the server extracts clothing features (type, color, style) from image data. It uses an image recognition model such as TensorFlow.

[1642] Input: Clothing image data

[1643] Output: Analysis results for clothing type, color, and style

[1644] Step 4:

[1645] The user inputs information about their destination and weather conditions through the voice assistant in the smart glasses.

[1646] Specific Actions: A user uses voice input to provide information about the destination for the day (e.g., going to the park) and weather conditions (sunny).

[1647] Input: Voice input information (destination, weather conditions)

[1648] Output: Destination and weather information in text format

[1649] Step 5:

[1650] The terminal transmits the voice input information to the server.

[1651] Specific operation: The analyzed destination and weather condition information is sent from the terminal to the server.

[1652] Input: Destination and weather information in text format

[1653] Output: Destination and weather information sent to the server

[1654] Step 6:

[1655] The server captures the user's facial expressions and voice in real time and analyzes their emotions.

[1656] Specific operation: The server captures the user's facial expressions and voice through the camera and microphone of the smart glasses, and analyzes emotions using facial expression recognition technology (face_recognition) and voice analysis technology (emotion_recognition).

[1657] Input: Real-time facial expression and voice data

[1658] Output: User's emotional state (e.g., happy, sad, excited, tired)

[1659] Step 7:

[1660] The server generates an appropriate outfit based on the analysis results (type, color, and style of clothing), destination, and weather condition information.

[1661] How it works: Using a generative AI model (TensorFlow model), the analysis results are integrated with the input information to generate multiple outfit ideas. It also references an external fashion database.

[1662] Input: Clothing analysis results, destination information, weather condition information, emotional state

[1663] Output: Coordination proposal

[1664] Step 8:

[1665] The server adjusts the generated coordinates according to the user's emotions and displays them on the smart glasses.

[1666] Specific operation: Based on the user's emotional state, the suggested outfits are adjusted and displayed on the smart glasses display. For example, if the user is tired, cheerful and uplifting outfits will be displayed first.

[1667] Input: Coordination proposal, emotional state

[1668] Output: Coordinate suggestions presented to the user

[1669] Step 9:

[1670] The user inputs feedback on the coordination proposal.

[1671] Specific operation: Using the voice input function or touch interface of the smart glasses, the user provides feedback on their opinions and thoughts about the suggested outfits.

[1672] Input: User feedback (e.g., I don't own a cardigan)

[1673] Output: Feedback information

[1674] Step 10:

[1675] The terminal sends feedback information to the server.

[1676] Specific operation: The terminal transmits the feedback information obtained from the user to the server.

[1677] Input: Feedback information

[1678] Output: Feedback information sent to the server

[1679] Step 11:

[1680] The server will reflect the feedback information in the next coordinate generation.

[1681] How it works: The machine learning module learns from the feedback information and improves the next outfit suggestions by reflecting the user's preferences and patterns.

[1682] Input: Feedback information

[1683] Output: Improved coordinate generation algorithm

[1684] Step 12:

[1685] The server recommends where to buy clothing items that are in short supply.

[1686] Specific operation: The item recommendation module identifies missing items in the proposed outfit and generates purchasing information. The smart glasses display online shop links and nearby store information.

[1687] Input: Proposed outfit ideas, missing item information

[1688] Output: Purchase information (links and store information)

[1689] 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.

[1690] 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.

[1691] 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.

[1692] [Fourth embodiment]

[1693] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1694] 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.

[1695] 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).

[1696] 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.

[1697] 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.

[1698] 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).

[1699] 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.

[1700] 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.

[1701] 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.

[1702] 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.

[1703] 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.

[1704] 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.

[1705] 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."

[1706] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is composed of a user, a server, and a terminal.

[1707] overview

[1708] Users take a photo of their outfit using the camera on their smartphone or computer and send the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothing they are wearing. The user then uses their device to input information about their destination and weather for the day, which is then sent to the server. The server combines the analysis data with the input information, generates an optimal outfit, and presents it to the user. The user provides feedback, and the server uses that feedback to improve its next outfit suggestions. It also recommends places to purchase any clothing items the user is missing.

[1709] Program processing

[1710] Video Analysis

[1711] The server analyzes the received video data to identify the type of clothing (shirt, pants, accessories, etc.), color, and style the user is wearing. This analysis is performed using image recognition technology. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the style of the clothing. The resulting analysis data is stored in the server's internal database.

[1712] Coordinate generation

[1713] The device provides a means for the user to input information about their destination and weather, and sends that information to the server. Based on this information, the server uses a coordination suggestion module to generate optimal outfits. This module generates multiple coordination suggestions and evaluates each one. It also references an external fashion database, taking into account the latest fashion trends and seasonal styles.

[1714] Coordination presentation and feedback

[1715] The server selects the optimal outfit suggestions and sends them to the device as a recommendation list. The device displays them to the user. The user then enters feedback on the suggested outfits, which is sent to the server. The server stores the feedback and uses it in a machine learning module to learn about the user's preferences and patterns.

[1716] Purchase recommendation

[1717] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and sends information on where to purchase them to the device. The device displays this information to the user, providing links to online shops and information on nearby stores.

[1718] Specific examples

[1719] scenario

[1720] The user is going out to lunch with a friend this morning and is already dressed in a white shirt and jeans. The weather forecast predicts cloudy skies with rain.

[1721] flow

[1722] 1. The user takes a picture of a white shirt and jeans using the smartphone camera.

[1723] 2. The device sends the video data to the server.

[1724] 3. The server analyzes the video and identifies the white shirt and jeans.

[1725] 4. The user inputs the destination (lunch with a friend) and the weather (cloudy with rain) into the terminal.

[1726] 5. The device sends the input information to the server.

[1727] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[1728] 7. The server sends the proposal to the device.

[1729] 8. The device displays the suggestions to the user.

[1730] 9. The user provides feedback that they do not own a cardigan.

[1731] 10. The device sends the feedback to the server.

[1732] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[1733] 12. The terminal displays the supplier information to the user.

[1734] This process allows users to receive optimal fashion suggestions and easily obtain purchasing information to supplement any clothing shortages, thereby improving their fashion sense and giving them confidence in their everyday coordination.

[1735] The processing flow will be explained below.

[1736] Step 1:

[1737] The user takes a photo of their outfit using the camera on their smartphone or computer.

[1738] Step 2:

[1739] The video data acquired by the terminal is transmitted to the server.

[1740] Step 3:

[1741] The server begins analyzing the received video data.

[1742] Step 4:

[1743] The server's image recognition module identifies the type of clothing the user is wearing (e.g., shirt, pants, accessories, etc.) from the video.

[1744] Step 5:

[1745] The server's color recognition algorithm analyzes the color of each item.

[1746] Step 6:

[1747] The server's style recognition algorithm identifies the clothing style (e.g., casual, formal, etc.).

[1748] Step 7:

[1749] The server stores the analysis results in an internal database.

[1750] Step 8:

[1751] The user uses the terminal to input information about the destination and weather for the day.

[1752] Step 9:

[1753] The terminal sends the entered destination, schedule and weather data to the server.

[1754] Step 10:

[1755] The server combines the received destination and weather data with the analysis data.

[1756] Step 11:

[1757] The server's coordination suggestion module generates optimal coordination based on the analysis data and user information.

[1758] Step 12:

[1759] The server creates multiple coordination proposals and evaluates each one.

[1760] Step 13:

[1761] The server selects the most suitable coordination plan based on the evaluation results.

[1762] Step 14:

[1763] The server creates a recommendation list and sends it to the device.

[1764] Step 15:

[1765] The device displays the recommendation list to the user.

[1766] Step 16:

[1767] The user inputs feedback on the coordination into the terminal.

[1768] Step 17:

[1769] The terminal transmits the user's feedback data to the server.

[1770] Step 18:

[1771] The server stores the feedback data, and the machine learning module uses it to learn user preferences and patterns.

[1772] Step 19:

[1773] The server's item recommendation module identifies items that are missing from the user's outfit or outfit.

[1774] Step 20:

[1775] The server generates supplier information for the missing items.

[1776] Step 21:

[1777] The server sends the supplier information to the terminal.

[1778] Step 22:

[1779] The terminal displays the supplier information to the user.

[1780] Example 1

[1781] 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."

[1782] Conventional fashion coordination suggestion systems have problems such as difficulty in suggesting outfits that reflect the user's appropriate destination or weather information, or when the user does not accurately understand their own outfit. Furthermore, if the user is not satisfied with the suggested outfit, there is no mechanism to reflect that feedback in the next suggestion. Furthermore, there is also a lack of a way to quickly provide information on where to purchase missing items.

[1783] 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.

[1784] In this invention, the server includes: means for acquiring an image of the user's clothing; means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user; means for inputting information about the user's destination and weather; means for generating an appropriate outfit based on the analysis results and the input information; means for presenting the generated outfit to the user; means for receiving feedback from the user, learning from the feedback, and incorporating it into the next outfit generation; means for recommending where to purchase missing clothing accessories; means for identifying the color and style of clothing using image recognition technology; means for learning the user's preferences and patterns using a machine learning module; means for referencing an external fashion database to generate outfits; means for evaluating outfit suggestions based on the user's destination and weather information; and means for providing links to online shops and nearby store information. This allows the server to accurately analyze the user's current fashion situation and propose optimal outfits based on the weather and destination. Furthermore, the server can reflect the user's feedback in the next outfit proposal and quickly provide information on where to purchase missing items.

[1785] "User" refers to an individual who uses the system to photograph, input, and provide feedback about their outfit.

[1786] "Server" refers to a central processing unit that receives data sent by users, analyzes, stores, learns from, and reflects coordination suggestions and feedback.

[1787] A "terminal" is a device used by a user, such as a smartphone or PC, and refers to an interface means for taking images, inputting information, displaying outfit suggestions, etc.

[1788] "Image recognition technology" is a technology that automatically identifies objects, shapes, colors, etc. from acquired image data, and primarily utilizes deep learning models and algorithms.

[1789] "Machine learning module" refers to artificial intelligence (AI) technology or software programs that learn from user feedback data and improve the accuracy of future outfit suggestions.

[1790] The "coordination suggestion module" refers to a software program that generates optimal outfit combinations by referencing a fashion database based on the user's clothing analysis data and input information.

[1791] A "fashion database" refers to a database that contains the latest fashion trends, style information according to the season, brand information, etc.

[1792] "Feedback" refers to input information such as evaluations, opinions, and comments made by users regarding the proposed coordination.

[1793] "Purchaser information" refers to links to online shops and information on physical stores provided as places to purchase new clothing items that the user needs.

[1794] "Destination information" refers to information about places and events that the user plans to go to.

[1795] "Weather information" refers to information about the weather conditions at the user's location or the location where the user plans to go.

[1796] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is mainly composed of a user, a server, and a terminal.

[1797] System Overview

[1798] The user uses the camera on their smartphone or computer to take a picture of their current outfit and sends the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothes the user is wearing. The user then uses their device to input information such as their destination and weather, which is then sent to the server. The server then combines the analysis data with the input information to generate an optimal outfit and present it to the user. It receives feedback from the user and reflects it in generating the next outfit. It also provides information on where to purchase any clothing items the user does not own.

[1799] System configuration and processing

[1800] Video Analysis

[1801] The server analyzes the received video data. This analysis uses image recognition technologies such as TensorFlow and OpenCV. Specifically, it extracts contours from the transmitted image data, identifies the color of the clothing using a color recognition algorithm, and determines the type of clothing and silhouette using a style recognition algorithm. The resulting data is stored in the server's internal database.

[1802] Coordinate generation

[1803] The device provides a means for users to input destination and weather information, and sends that information to the server. The server then uses a coordination suggestion module to combine the user's clothing analysis data with the input information to generate optimal outfits. This module references an external fashion database (e.g., Polyvore API) and takes into account the latest fashion trends and seasonal styles.

[1804] Coordination presentation and feedback

[1805] The server sends the generated outfits to the device, which displays them to the user. The user can then enter feedback about the outfit suggestions, which is then sent back to the server. The server stores the feedback and uses a machine learning module to improve the accuracy of the next outfit suggestions.

[1806] Purchase recommendation

[1807] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and generates information on where to purchase them. The generated information is sent to the user's device and provided to them. Specifically, it includes links to online shops and information on nearby stores.

[1808] Specific examples

[1809] Consider a scenario where a user is going out to lunch with a friend on the following date and is wearing a white shirt and jeans. The weather forecast is cloudy with rain.

[1810] flow

[1811] 1. A user takes a picture of a white shirt and jeans using the smartphone camera.

[1812] 2. The device sends the video data to the server.

[1813] 3. The server analyzes the video and identifies the white shirt and jeans.

[1814] 4. The user inputs the destination ("lunch with a friend") and the weather ("cloudy with rain") into the terminal.

[1815] 5. The device sends the input information to the server.

[1816] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[1817] 7. The server sends the proposal to the device.

[1818] 8. The device displays the suggestions to the user.

[1819] 9. The user provides feedback that they do not own a cardigan.

[1820] 10. The device sends the feedback to the server.

[1821] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[1822] 12. The terminal displays the supplier information to the user.

[1823] Prompt Sentence Examples

[1824] User outfit image: [image file]

[1825] Destination: Lunch with a friend

[1826] Weather: Cloudy with rain

[1827] Please suggest the best outfit to go with my current outfit. Also, please let me know where to buy any items that are missing from the suggested outfit.

[1828] This system not only allows users to receive suggestions for the perfect outfit for the day, but also makes it easy to find out how to purchase any missing items. Through this process, users can improve their fashion sense and gain confidence.

[1829] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1830] Step 1:

[1831] The user takes a photo of their own outfit using the camera on their smartphone or computer. The input is image data of the outfit. Specifically, the user launches the camera app and presses the capture button to take a full-body shot of the outfit they are currently wearing. The output is the captured image data.

[1832] Step 2:

[1833] The device sends the captured image data to the server. The input is the image data captured by the user. Specifically, the device uploads this image data to the specified server URL via the Internet. The output is the image data sent to the server.

[1834] Step 3:

[1835] The server analyzes the received image data and identifies the type, color, and style of clothing worn by the user. The input is image data sent from the device. Specifically, the server first preprocesses the image (e.g., noise removal), then uses TensorFlow or OpenCV to identify the color of the clothing using k-means clustering, and uses a deep learning model (e.g., ResNet or YOLO) to determine the type of clothing and silhouette. The output is analytical data related to the type, color, and style of clothing.

[1836] Step 4:

[1837] The user uses the device to input destination and weather information. The input includes clothing data after video analysis, the destination (e.g., "lunch with friends"), and the weather (e.g., "cloudy with rain"). Specifically, the user enters the destination and weather information into the app's input form and presses the send button. The output is the destination and weather information entered into the device.

[1838] Step 5:

[1839] The terminal transmits the destination and weather information input by the user to the server. The input is the destination and weather information input by the user to the terminal. In concrete terms, the terminal transmits this information to the server via the Internet. The output is the destination and weather information transmitted to the server.

[1840] Step 6:

[1841] The server integrates the analysis data with the information entered by the user and generates the optimal outfit using the outfit suggestion module. The input is the clothing analysis data, destination, and weather information. Specifically, the server queries an external fashion database, generates multiple outfit suggestions that meet the conditions, and selects the optimal suggestion based on the destination and weather conditions. The output is the outfit suggestion presented to the user.

[1842] Step 7:

[1843] The server transmits the generated coordination plan to the terminal. The input is the optimal coordination plan. In concrete terms, the server transmits the selected coordination plan to the terminal via the Internet. The output is the coordination plan transmitted to the terminal.

[1844] Step 8:

[1845] The terminal displays the outfit suggestions received from the server to the user. The input is the outfit suggestions sent from the server. As a specific operation, the outfit suggestions are visually displayed on the screen of the terminal. The output is the outfit suggestions that the user can view.

[1846] Step 9:

[1847] The user inputs feedback on the proposed outfit. The input is the proposed outfit. Specifically, the user enters comments and ratings into the app's feedback form and presses the send button. The output is the feedback information entered into the device.

[1848] Step 10:

[1849] The terminal sends the feedback information to the server. The input is the feedback information entered by the user. In concrete terms, the terminal sends this information to the server via the Internet. The output is the feedback information sent to the server.

[1850] Step 11:

[1851] The server stores the feedback and uses it in a machine learning module to improve the next coordination proposal. The input is the feedback information. Specifically, the server stores the feedback information in a database and uses it to update the machine learning model. The output is an improved coordination model.

[1852] Step 12:

[1853] The server's item recommendation module identifies missing items in the user's outfit or the proposed outfit, and generates information on where to purchase them. The input is the proposed outfit and feedback information. Specifically, the server identifies the missing item (e.g., a "gray cardigan") and collects information on online shops and nearby stores. The output is information on where to purchase them.

[1854] Step 13:

[1855] The server sends the generated supplier information to the terminal. The input is the supplier information. In concrete terms, the server sends the supplier information to the terminal via the Internet. The output is the supplier information sent to the terminal.

[1856] Step 14:

[1857] The terminal displays the supplier information to the user. The input is the supplier information sent from the server. As a specific operation, the supplier information is visually displayed on the terminal screen. The output is the supplier information that the user can view.

[1858] (Application example 1)

[1859] 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."

[1860] In modern society, there is a demand for assistance in optimizing the coordination of users' clothing. Efficient and personalized coordination suggestions and purchasing support are essential, especially for users who struggle with daily fashion choices. However, current systems struggle to analyze users' clothing in real time and provide optimal coordination suggestions based on various criteria, as well as information on where to purchase missing items. Furthermore, there is a lack of systems that allow users to virtually try on suggested coordinations. Therefore, a means is needed that allows users to easily receive high-quality fashion advice while also receiving purchasing support.

[1861] 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.

[1862] In this invention, the server includes means for acquiring an image of the user's clothing, means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user, and means for inputting information on the user's destination and weather, thereby enabling the user to receive optimal outfit suggestions.

[1863] The server further includes a means for generating an appropriate outfit based on the analysis results and input information, a means for presenting the generated outfit to the user and enabling virtual try-on, a means for receiving feedback from the user, learning from it, and reflecting it in generating the next outfit, and a means for recommending places to purchase missing clothing items and providing links to online stores. This allows the user to not only receive outfit suggestions in real time, but also personalized suggestions that reflect the user's feedback, and easily purchase missing items.

[1864] "Image acquisition means" refers to a device or function for capturing images of a user's clothing in real time, and includes image capture devices such as smartphones, smart glasses, and head-mounted displays.

[1865] "Video analysis means" refers to software or algorithms that analyze captured video data in real time and identify the type, color, and style of clothing worn by the user.

[1866] "Information input means" refers to a function that provides an interface for users to input destination and weather information, and includes the use of a mobile information terminal or a personal computer.

[1867] "Coordination generation means" refers to an algorithm or module that generates appropriate clothing combinations based on the results of video analysis and information entered by the user.

[1868] The "coordinate presentation means" refers to an interface or device for visually displaying the generated coordinates to the user, and also includes a function that allows virtual try-on.

[1869] "Feedback means" refers to a function that provides an interface for receiving opinions and reactions from users regarding coordination suggestions, learns from them, and reflects them in the next suggestion.

[1870] "Purchase recommendation means" refers to a function for providing information on where to purchase items that are missing from the proposed outfit, and includes providing links to online stores.

[1871] "Internal database" refers to a database that stores analyzed data and user feedback and is used within the system.

[1872] "External database" refers to an external fashion information service that is referenced to obtain the latest fashion trends and seasonal style information.

[1873] The present invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. The system is composed of a user, a server, and a terminal.

[1874] System Configuration

[1875] The system includes the following main measures:

[1876] 1. Image acquisition means: A device or function for capturing images of the user's clothing in real time. This uses an image capture device such as a smartphone, smart glasses, or a head-mounted display.

[1877] 2. Video analysis means: This refers to software and algorithms that analyze captured video data in real time and identify the type, color, and style of clothing worn by the user. Specifically, OpenCV and TensorFlow are used.

[1878] 3. Information input means: This function provides an interface for users to input destination and weather information, and uses the user interface of a smartphone or PC.

[1879] 4. Coordination generation means: Algorithms and modules that generate appropriate clothing combinations based on the results of video analysis and input information, taking into account the user's preferences and the latest fashion database.

[1880] 5. Coordination presentation means: A function for visually displaying the generated coordination to the user, including an interface that allows virtual try-on.

[1881] 6. Feedback means: This function provides an interface for receiving opinions and reactions from users regarding coordination suggestions, and learns from that feedback and reflects it in future suggestions.

[1882] 7. Purchasing recommendation tool: This function provides information on where to purchase items that are missing from the suggested outfit, including links to online stores.

[1883] System Operation

[1884] 1. Image acquisition:

[1885] Users take photos of their outfits in real time using the camera on their smartphone or smart glasses.

[1886] The captured video data is immediately sent to a server for analysis.

[1887] 2. Video analysis:

[1888] The server uses OpenCV and TensorFlow to analyze the transmitted video data and identify the type of clothing (e.g., shirt, pants, dress, etc.), color, and style the user is wearing.

[1889] 3. Enter your information:

[1890] The user inputs destination and weather information through the terminal interface, which is then sent to the server.

[1891] Example prompt statement:

[1892] user_info = {

[1893] 'location': 'Tokyo',

[1894] 'event': 'Lunch with a friend'

[1895] }

[1896] 4. Coordinate generation:

[1897] Based on the video analysis results and the input information, the server refers to the latest fashion database and the user's past feedback information to generate the optimal outfit.

[1898] The generated coordinates are saved as information and sent to the user's terminal.

[1899] 5. Coordination presentation and virtual try-on:

[1900] The terminal visually displays the generated outfits to the user, allowing the user to virtually try on the suggested outfits.

[1901] 6. Feedback:

[1902] The user inputs their opinions and reactions to the proposed coordination through the terminal, which are then sent to the server.

[1903] The server learns from the feedback it receives and understands the user's preferences and patterns.

[1904] 7. Purchase recommendation:

[1905] The server's item recommendation module identifies items missing from the proposed outfit and generates purchasing information and links to online shops.

[1906] The terminal displays the recommended vendor information to the user.

[1907] Specific examples

[1908] For example, if a user is going out to lunch with a friend this morning and is wearing a white shirt and jeans, and the weather forecast predicts cloudy skies with rain, the system will operate as follows:

[1909] 1. The user uses the smartphone camera to take a picture of a white shirt and jeans.

[1910] 2. The captured video data is sent to the server.

[1911] 3. The server analyzes the video and identifies the white shirt and jeans.

[1912] 4. The user inputs the destination (lunch with a friend) and the weather (cloudy with rain) into the terminal.

[1913] 5. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[1914] 6. The server sends the proposal to the device.

[1915] 7. The device displays the suggestions to the user, who then virtually tries them on.

[1916] 8. The user provides feedback that they do not own a cardigan.

[1917] 9. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[1918] 10. The terminal displays the purchasing information to the user, and the user can purchase the cardigan from the online shop.

[1919] By following this process, users can easily purchase any missing items while receiving suggestions for optimal outfits.

[1920] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1921] Step 1: The user takes a picture of their outfit in real time using the camera on their smartphone or smart glasses. The captured video data is immediately sent to the server.

[1922] Input: Video data of the clothes worn by the user.

[1923] Output: Sending video data to the server.

[1924] How it works: The user turns on the camera on their smartphone and takes a full-body video of themselves. This video data is then uploaded to a cloud server in real time.

[1925] Step 2: The server uses OpenCV and TensorFlow to analyze the transmitted video data and identify the type, color, and style of clothing the user is wearing.

[1926] Input: Video data sent to the server.

[1927] Output: Analyzed data about clothing type, color, and style.

[1928] How it works: Image recognition algorithms running on the server identify the type of clothing (shirt, pants, etc.) as well as their color and style from the video data. The resulting analysis data is stored in an internal database.

[1929] Step 3: The user inputs destination and weather information through the terminal interface, which is then sent to the server.

[1930] Input: Destination and weather information.

[1931] Output: Sending information to the server.

[1932] Specific operation: The user uses a smartphone app to enter the location they plan to go to that day and weather forecast information, and then submits the form.

[1933] Step 4: The server's coordinate generation means generates an optimal coordinate based on the video analysis results and the information input by the user, by referring to the latest fashion database and the user's past feedback information.

[1934] Input: Analysis data, user destination and weather information.

[1935] Output: Optimal outfit ideas.

[1936] Specific operation: The server searches a fashion database for the latest trends and weather-appropriate combinations, and generates optimal outfit suggestions for shirts, pants, and accessories.

[1937] Step 5: The terminal visually displays the generated outfit to the user, allowing the user to virtually try on the suggested outfit.

[1938] Input: Generated coordinate plan.

[1939] Output: Visual presentation of outfits and virtual try-on.

[1940] Specific operation: The device displays outfit ideas on the application interface, and the user tries them on in a virtual environment.

[1941] Step 6: The user inputs their opinions and reactions to the proposed coordination through the terminal, which are then sent to the server.

[1942] Input: User feedback.

[1943] Output: Sending feedback to the server.

[1944] Specific operation: The user enters their thoughts and opinions about the outfit into the feedback form within the application and presses the submit button.

[1945] Step 7: The server learns from the received feedback and understands the user's preferences and patterns. It uses the generative AI model to reflect this in the next outfit suggestions.

[1946] Input: User feedback data.

[1947] Output: Improved outfit suggestions.

[1948] How it works: The server stores the feedback information in a database, and the generative AI model uses this information to learn user preferences and patterns.

[1949] Step 8: The server's item recommendation module identifies the missing items and generates purchasing information and links to online shops.

[1950] Input: User's current belongings information and coordination suggestions.

[1951] Output: Purchase information and online shop link.

[1952] Specific operation: The server retrieves purchasing information from an internal database and external shopping sites and sends it to the user's device.

[1953] Step 9: The terminal displays the recommended purchasing information to the user, and the user can purchase the missing items online based on the recommended purchasing information.

[1954] Input: Supplier information and shopping links.

[1955] Output: Providing information to the user and assisting them in making a purchase.

[1956] Specific operation: The device displays the purchasing information and link on the application display screen, and the user can purchase the item from the online shop by clicking the link.

[1957] This flow of processing steps allows the user to efficiently receive suggestions for optimal outfits while easily obtaining the items they need.

[1958] 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.

[1959] This invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. This system is comprised of a user, a server, and a terminal, and also incorporates an emotion engine that recognizes the user's emotions.

[1960] overview

[1961] Users take pictures of their outfits using the camera on their smartphone or computer and send the images to the server. The server analyzes the image data and identifies the type, color, and style of the clothes they are wearing. The user then inputs their destination and weather information for the day using their device, which is then sent to the server. The server then combines the analysis data, the input information, and the user's emotions, as recognized by the emotion engine, to generate an optimal outfit. This generated outfit matches the user's mood. The user provides feedback on the suggested outfit, and the server uses that feedback to improve its next outfit suggestions. The server also recommends places to purchase any clothing items the user is missing.

[1962] Program processing

[1963] Video Analysis

[1964] The server analyzes the received video data and identifies the type of clothing (e.g., shirt, pants, accessories, etc.), color, and style) worn by the user. This analysis is performed using image recognition technology. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the style of the clothing. The resulting analysis data is stored in the server's internal database.

[1965] Emotion analysis

[1966] The device provides a means to acquire the user's facial expressions and voice in real time and transmits the data to a server. An emotion engine installed on the server analyzes the user's emotions based on this data. The emotion engine uses facial expression recognition and voice analysis technology to determine the user's current emotion (e.g., joy, sadness, excitement, fatigue).

[1967] Coordinate generation

[1968] The device provides a means for the user to input information about their destination and weather, and sends that information to the server. Based on this, the server uses a coordination suggestion module to generate optimal outfits. This module generates multiple outfit suggestions based on analytical data, emotional data, and user information, and evaluates each one. It also references an external fashion database, taking into account the latest fashion trends and seasonal styles. It also adjusts the style of the suggested outfits based on the user's emotions, presenting outfits that suit the user's mood.

[1969] Coordination presentation and feedback

[1970] The server selects the optimal outfit suggestions and sends them to the device as a recommendation list. The device displays them to the user. The user then enters feedback on the suggested outfits, which is sent to the server. The server stores the feedback and uses it in a machine learning module to learn about the user's preferences and patterns.

[1971] Purchase recommendation

[1972] The server's item recommendation module identifies items missing from the user's current outfit and the proposed outfit, and sends information on where to purchase them to the device. The device displays this information to the user, providing links to online shops and information on nearby stores.

[1973] Specific examples

[1974] scenario

[1975] The user is planning to go out to lunch with a friend this morning and is already dressed in a white shirt and jeans. The weather forecast predicts cloudy skies with rain. The user is feeling a little tired, but is looking forward to a fun lunch.

[1976] flow

[1977] 1. A user takes a picture of a white shirt and jeans using their smartphone camera.

[1978] 2. The device sends the video data to the server.

[1979] 3. The server analyzes the video and identifies the white shirt and jeans.

[1980] 4. The user inputs a destination (lunch with a friend) and weather (cloudy with rain) into the terminal.

[1981] 5. The device sends the input information to the server.

[1982] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots based on the analysis data and input information.

[1983] 7. The server sends the proposal to the device.

[1984] 8. The device displays the suggestions to the user.

[1985] 9. The user provides feedback that they do not own a cardigan.

[1986] 10. The device sends the feedback to the server.

[1987] 11. The server stores the feedback and generates and sends to the device information on where to buy the cardigan.

[1988] 12. The terminal displays the supplier information to the user.

[1989] 13. The user provides facial expression and voice data through the terminal.

[1990] 14. The device sends facial expression and voice data to the server.

[1991] 15. The server's emotion engine analyzes the user's emotions and suggests additional outfits that emphasize a happy mood (e.g., brightly colored accessories).

[1992] This process allows users to receive optimal fashion suggestions and easily obtain purchasing information to supplement any clothing shortages. Furthermore, adjustments are made to match the user's emotions, further increasing satisfaction with everyday coordination.

[1993] The processing flow will be explained below.

[1994] Step 1:

[1995] The user takes a photo of their outfit using the camera on their smartphone or computer.

[1996] Step 2:

[1997] The video data acquired by the terminal is transmitted to the server.

[1998] Step 3:

[1999] The server begins analyzing the received video data.

[2000] Step 4:

[2001] The server's image recognition module identifies the type of clothing the user is wearing (e.g., shirt, pants, accessories, etc.) from the video.

[2002] Step 5:

[2003] The server's color recognition algorithm analyzes the color of each item.

[2004] Step 6:

[2005] The server's style recognition algorithm identifies the clothing style (e.g., casual, formal, etc.).

[2006] Step 7:

[2007] The server stores the analysis results in an internal database.

[2008] Step 8:

[2009] The user uses the terminal to input information about the destination and weather for the day.

[2010] Step 9:

[2011] The terminal sends the entered destination, schedule and weather data to the server.

[2012] Step 10:

[2013] The server combines the received destination and weather data with the analysis data.

[2014] Step 11:

[2015] The user provides emotional data such as facial expressions and voice through the terminal.

[2016] Step 12:

[2017] The device transmits the emotion data to the server.

[2018] Step 13:

[2019] The server's emotion engine uses facial expression recognition and voice analysis technology to analyze the user's emotions (e.g., joy, sadness, excitement, fatigue, etc.).

[2020] Step 14:

[2021] The server's coordination suggestion module generates optimal coordination based on analysis data, emotion data, and user information.

[2022] Step 15:

[2023] The server creates multiple coordination proposals and evaluates each one.

[2024] Step 16:

[2025] The server selects the most suitable coordination plan based on the evaluation results.

[2026] Step 17:

[2027] The server creates a recommendation list and sends it to the device.

[2028] Step 18:

[2029] The device displays the recommendation list to the user.

[2030] Step 19:

[2031] The user inputs feedback on the proposed coordination into the terminal.

[2032] Step 20:

[2033] The terminal transmits the user's feedback data to the server.

[2034] Step 21:

[2035] The server stores the feedback data, and the machine learning module uses it to learn user preferences and patterns.

[2036] Step 22:

[2037] The server's item recommendation module identifies items that are missing from the user's outfit or outfit.

[2038] Step 23:

[2039] The server generates information on where to purchase the missing items and transmits it to the terminal.

[2040] Step 24:

[2041] The terminal displays the supplier information to the user.

[2042] Example 2

[2043] 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."

[2044] Conventional fashion coordination assistant systems can make suggestions based on the user's clothing and style, destination, weather information, etc., but they cannot generate coordinations that take the user's emotions into consideration, so they have the problem of not being able to make suggestions that fully reflect the user's mood.In addition, they lack the function to specifically recommend clothing items that the user is lacking, making it difficult for users to easily purchase the items needed for the suggested coordination.

[2045] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring an image of the user's clothing, means for analyzing the acquired image and identifying the type, color, and style of the clothing worn by the user, means for inputting information about the user's destination and weather, means for generating an appropriate outfit based on the analysis results and the input information, means for presenting the generated outfit to the user, means for receiving feedback from the user, learning from the feedback, and reflecting it in generating the next outfit, means for analyzing the user's emotions, means for adjusting the outfit based on the emotions, and means for recommending where to purchase missing clothing and accessories. This makes it possible to suggest an optimal outfit based on the user's mood, and by specifically recommending where to purchase missing items, the user can quickly obtain the items they need.

[2046] "User" refers to a person who uses the system to improve or receive suggestions for their own clothing coordination.

[2047] "Outfit image" refers to digital image data that contains visual information about the clothing and accessories worn by a user.

[2048] "Means for acquiring" refers to a device or technology that allows a user to take an image of the outfit and send the image to the system.

[2049] "Means for analyzing" refers to technology for identifying the type, color, and style of clothing worn by a user based on the acquired image data.

[2050] "Means for identifying" refers to technology for identifying specific attributes of the clothing worn by the user based on the analysis results.

[2051] "Input means" refers to the devices and technologies that allow users to input destination and weather information.

[2052] "Means for generating appropriate coordination" refers to technology for proposing optimal clothing combinations to users based on analysis results and input information.

[2053] "Presenting means" refers to a device or technology for showing the generated coordinates to the user.

[2054] "Means for receiving feedback" refers to technology that allows users to input their thoughts and requests regarding the proposed outfits and send that information to the system.

[2055] "Means of learning" refers to technology that uses user feedback to improve the next outfit suggestion.

[2056] "Means for analyzing emotions" refers to technology for identifying emotions based on a user's facial expressions and voice data.

[2057] The term "means for adjusting a coordination based on emotions" refers to a technique for adjusting an optimal coordination for a user in consideration of the analyzed emotions of the user.

[2058] "Means for recommending where to purchase missing clothing items" refers to technology for showing a user where to purchase missing items based on the suggested outfit.

[2059] This invention is a system that analyzes a user's clothing in real time and provides feedback on the day's outfit suggestions and improvements. This system is comprised of a user, a server, and a terminal, and also incorporates an emotion analysis engine that recognizes the user's emotions.

[2060] Hardware and software used

[2061] The server is equipped with image recognition technology, an emotion analysis engine, a coordination suggestion module, an item recommendation module, and a machine learning algorithm, which utilize the following specific technologies:

[2062] Image recognition technology: color recognition algorithm, style recognition algorithm

[2063] Emotion analysis engine: facial expression recognition technology, voice analysis technology

[2064] Coordination suggestion module: Includes the function to refer to external fashion databases

[2065] Item recommendation module: Online shop link generation function, nearby store information acquisition function

[2066] Machine learning algorithms: Ability to learn from feedback data

[2067] The device includes a camera that captures images of the user's outfit, an interface for inputting destination and weather information, and a display that shows suggested outfits and shopping information.

[2068] Users can use these functions using smartphones or computers.

[2069] Coordination proposal process

[2070] Users use their smartphone or PC camera to take a picture of their outfit and send the video to the server. The server analyzes the video data and identifies the type, color, and style of the clothes they are wearing. The user then inputs their destination and weather information for the day via their device, which is then sent to the server. The server then combines the analysis data, the input information, and the user's emotional data recognized by an emotion analysis engine to generate the optimal outfit. The generated outfit matches the user's mood.

[2071] For example, suppose a user is planning to go out to lunch with a friend this morning and is wearing a white shirt and jeans. The weather forecast predicts cloudy skies with rain, and the user is feeling a little tired but is looking forward to a pleasant lunch. In this situation, the flow of using the system is as follows:

[2072] 1. A user takes a picture of a white shirt and jeans using their smartphone camera.

[2073] 2. The device sends the video data to the server.

[2074] 3. The server analyzes the video and identifies the white shirt and jeans.

[2075] 4. The user inputs a destination (lunch with a friend) and weather (cloudy with rain) into the terminal.

[2076] 5. The device sends the input information to the server.

[2077] 6. The server's outfit suggestion module generates an outfit that combines a white shirt and jeans with a gray cardigan and black rain boots.

[2078] 7. The server sends the proposal to the terminal, which displays it to the user.

[2079] 8. The user provides feedback that they do not own a cardigan.

[2080] 9. The device sends the feedback to the server.

[2081] 10. The server stores the feedback and generates and sends information about where to buy the cardigan to the device.

[2082] 11. The device displays the retailer information to the user.

[2083] 12. The user provides facial expression and voice data through the terminal.

[2084] 13. The device sends facial expression and voice data to the server.

[2085] 14. The server's emotion analysis engine analyzes the user's emotions and suggests additional accessories that emphasize a happy mood (e.g., a brightly colored scarf).

[2086] 15. The server sends the additional suggestions to the terminal, which displays them to the user.

[2087] This process not only allows users to receive optimal fashion suggestions, but also provides information on purchasing clothing items that they are lacking, and improves their satisfaction with their everyday outfits.

[2088] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2089] Step 1:

[2090] Users take a photo of their outfit using the camera on their smartphone or computer. Specifically, the user stands in front of a mirror and takes a photo that captures their entire body. The captured image is then saved as digital data on the device.

[2091] Input: Image of the user's outfit

[2092] Output: Digital image data

[2093] Step 2:

[2094] The terminal transmits the captured digital image data to a server via the Internet.

[2095] Input: Digital image data

[2096] Output: Image data sent to the server

[2097] Step 3:

[2098] The server analyzes the received digital image data. It uses image recognition technology to identify the type of clothing (e.g., shirt, pants), color, and style the user is wearing. For example, a color recognition algorithm determines the color of the clothing, and a style recognition algorithm identifies the type of clothing. The analysis results are stored in an internal database.

[2099] Input: Digital image data

[2100] Data processing and calculation: Color recognition algorithm, style recognition algorithm

[2101] Output: Analysis results (clothing type, color, style)

[2102] Step 4:

[2103] The user inputs information about the destination and weather for the day through the terminal, and the input information is sent from the terminal to the server.

[2104] Input: Destination information, weather information

[2105] Output: Destination information and weather information sent to the server

[2106] Step 5:

[2107] The server uses the outfit suggestion module to generate optimal outfits based on the analysis results and the destination and weather information entered by the user. During this process, it references an external fashion database to consider the latest trends and seasonal styles. It also uses the user's emotional data to consider outfits that suit their mood.

[2108] Input: Analysis results, destination information, weather information, emotion data

[2109] Data processing and calculation: External fashion database reference, coordinate generation algorithm

[2110] Output: Generated coordinate plan

[2111] Step 6:

[2112] The server selects one of the generated coordination plans and sends it to the terminal, which displays it to the user.

[2113] Input: Generated coordination plan

[2114] Output: Coordination ideas displayed to the user

[2115] Step 7:

[2116] The user inputs feedback about the proposed outfit. For example, the user inputs feedback such as "I don't own a cardigan" into the terminal. The feedback is sent from the terminal to the server.

[2117] Input: User feedback

[2118] Output: Feedback sent to the server

[2119] Step 8:

[2120] The server uses machine learning algorithms to learn from user feedback and suggests outfits, storing the feedback to improve future suggestions.

[2121] Input: Feedback data

[2122] Data processing and calculation: Machine learning algorithms

[2123] Output: Improved outfit suggestion data

[2124] Step 9:

[2125] The server's item recommendation module generates purchasing information for missing items (e.g., cardigans) based on the suggested outfits, including online shop links and nearby store locations.

[2126] Input: Feedback data

[2127] Data processing and calculation: Item recommendation algorithm

[2128] Output: Generated supplier information

[2129] Step 10:

[2130] The server transmits the generated supplier information to the terminal, which displays it to the user.

[2131] Input: Generated supplier information

[2132] Output: Supplier information displayed to the user

[2133] Step 11:

[2134] The user provides facial expression and voice data through the device, which is collected in real time and sent to the server.

[2135] Input: facial expression data, voice data

[2136] Output: Emotion data sent to the server

[2137] Step 12:

[2138] The server's emotion analysis engine analyzes the user's emotions from their facial expressions and voice. For example, it can use facial recognition technology to determine if the user is slightly tired. The results of this emotion analysis are also reflected in the outfit suggestions.

[2139] Input: facial expression data, voice data

[2140] Data processing and calculation: Emotion analysis algorithm ...

Claims

1. means for acquiring an image of a user's clothing; means for analyzing the acquired image to identify the type, color, and style of clothing worn by the user; a means for inputting user destination and weather information; A means for generating an appropriate coordinate based on the analysis result and input information; means for presenting the generated coordinates to a user; A means for receiving feedback from users, learning from it, and reflecting it in the next coordinate generation; A system that includes a means for recommending where to purchase clothing items that are in short supply.

2. The system according to claim 1, wherein the means for acquiring an image of the user's clothing uses a camera of a smartphone or a personal computer.

3. 2. The system according to claim 1, further comprising means for storing the analyzed data in an internal database and for also referencing an external fashion database.

Images