System

Abstract

To provide a system.SOLUTION: A system includes: means for proposing a fashion coordination on the basis of situation information and weather information inputted by a user; means for learning a feedback from the user with respect to the proposed fashion coordination; means for purchasing commodities similar to the proposed fashion coordination; means for transmitting a prompt sentence to receive the proposal of the fashion coordination to a learnt generative AI model; and means for receiving a fashion coordination proposed by the generative AI model with respect to the prompt sentence.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] There are challenges to reduce the time spent worrying about fashion coordination, as well as the challenge of proposing outfits that suit the individual user's tastes and preferences. [Means for solving the problem]

[0005] We provide a means to suggest fashion coordination based on situational and weather information entered by the user. We also provide a means to learn from user feedback and suggest coordination that suits the individual user's physical sensations and preferences. We also provide a means to purchase products similar to the suggested coordination and a means to order custom-made items based on the suggested coordination. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, when a user inputs information about the situation, such as "date," and weather information, such as "sunny," into the app, a casual yet stylish outfit is suggested based on this information. A suggested outfit might be, for example, a white blouse, a denim skirt, and red pumps. Furthermore, if the user inputs feedback such as "it was hot," the app learns to suggest cooler outfits next time.

[0029] "Example 2"

[0030] Furthermore, the app offers a feature that allows users to purchase items similar to the suggested outfits directly within the app. For example, multiple items similar to the suggested white blouse will be displayed, allowing users to select and purchase the item they like.

[0031] "Example 3"

[0032] There is also a way to order custom items based on the suggested outfit. For example, if a user likes the red pumps included in the suggested outfit, they can order custom pumps of the same design but in a different size and color.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The user enters the situation information "date" and the weather information "sunny" into the app.

[0036] Step 2: Based on this information, the system suggests a casual yet stylish outfit, such as a white blouse with a denim skirt and red pumps.

[0037] Step 3: The user enters feedback such as "It was hot."

[0038] Step 4: The system learns from this feedback and will suggest cooler outfits next time.

[0039] "Example 2"

[0040] Step 1: The system displays products similar to the outfits it suggests.

[0041] Step 2: The user selects the product they want from the displayed products.

[0042] Step 3: The user purchases the selected item directly within the app.

[0043] "Example 3"

[0044] Step 1: Provide a way to order custom-made items based on the outfits suggested by the system.

[0045] Step 2: If the user likes an item included in the suggested outfit, they can order a custom-made item based on the design of that item.

[0046] Step 3: The user customizes the size and color of the made-to-order item and confirms the order.

[0047] Example 1

[0048] Next, a description will be given of Example 1 of Form 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."

[0049] Conventional fashion coordination suggestion systems have difficulty proposing appropriate outfits based on the user's situation and weather information, and it is also difficult to effectively learn from user feedback and reflect it in future suggestions. Furthermore, there is a lack of a way to purchase products based on the suggested outfits, and a lack of advanced outfit generation using generative AI models.

[0050] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for sending a prompt message to the generative AI model, and a means for receiving coordination from the generative AI model. This makes it possible to suggest appropriate coordination according to the user's situation and weather, improve the suggestions based on user feedback, and generate advanced coordination using the generative AI model.

[0051] "User" refers to an individual who uses the system to receive fashion coordination suggestions.

[0052] "Situation information" refers to information about a specific situation entered by the user, such as "date" or "work."

[0053] "Weather information" refers to information about the current weather that is input by the user, such as "sunny" or "rainy."

[0054] "Fashion coordination" refers to a combination of clothing and accessories suggested based on the user's situational and weather information.

[0055] "Feedback" refers to the evaluations and impressions provided by users regarding the suggested outfits.

[0056] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate outfits based on user input.

[0057] "Prompt sentence" refers to an instruction sentence sent to a generative AI model to generate a coordinate.

[0058] "Server" refers to the computer system that receives user input, sends prompts to the generative AI model, and provides the generated coordinates to the user.

[0059] "Terminal" refers to the device used by a User to enter information and review suggested outfits.

[0060] "Product" refers to items such as clothing and accessories included in the proposed outfit.

[0061] "Made-to-order items" refer to clothing and accessories that are made specifically to a user's request.

[0062] MODE FOR CARRYING OUT THE INVENTION

[0063] This invention is a system that proposes fashion coordination based on situation information and weather information input by a user, learns feedback from the user, and reflects it in future proposals. A specific embodiment of this system will be described below.

[0064] Hardware and software used

[0065] This system is implemented using the following hardware and software:

[0066] Server: Receives user input, sends prompts to the generative AI model, and provides the generated coordinates to the user. The server is developed using Python and uses TENSORFLOW (registered trademark) as the machine learning model.

[0067] Device: The device used by the user to enter information and view suggested outfits, such as a smartphone or tablet.

[0068] Generative AI model: An algorithm that generates coordinates based on user input. For example, OpenAI's GPT-3 (registered trademark) is used.

[0069] Program processing

[0070] The user opens the app and enters the situation information "date" and the weather information "sunny." The device sends the information entered by the user to the server. Specifically, it sends the data using an HTTP POST request.

[0071] The server generates a prompt to send to the generative AI model based on the received situational and weather information. For example, it generates the following prompt:

[0072] Based on the situation information "date" and the weather information "sunny," please suggest a casual yet stylish outfit.

[0073] The server sends this prompt to the generative AI model, which then generates an outfit based on the prompt. For example, it might generate a white blouse, denim skirt, and red pumps.

[0074] The server sends the outfit information received from the generative AI model to the device. Specifically, it returns the outfit information as an HTTP response. The user checks the outfit displayed on the device and enters feedback such as "it was hot." The device then sends the feedback entered by the user to the server. Specifically, it sends the feedback data using an HTTP POST request.

[0075] The server retrains the generative AI model based on the received feedback, so that from the next time onwards, it will suggest outfits that reflect the user's feedback.

[0076] Specific examples

[0077] For example, if a user inputs "date" and "sunny" and the suggested outfit is "white blouse, denim skirt, red pumps," if the user provides feedback that "it was hot," the next time the system will suggest a cooler outfit such as "white blouse, linen shorts, sandals."

[0078] In this way, it becomes possible to suggest appropriate outfits based on the user's situation and weather, improve suggestions based on user feedback, and generate advanced outfits using generative AI models.

[0079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0080] Step 1:

[0081] The user enters the situation information and weather information. The user opens the app and enters the situation information "date" and the weather information "sunny." The entered information is saved on the device.

[0082] Step 2:

[0083] The device sends the input information to the server. The device sends the situation information and weather information entered by the user to the server using an HTTP POST request. The input data is sent in JSON format.

[0084] Step 3:

[0085] The server sends a prompt to the generative AI model. Based on the received situational and weather information, the server generates a prompt to send to the generative AI model. For example, it generates the following prompt:

[0086] Based on the situation information "date" and the weather information "sunny," please suggest a casual yet stylish outfit.

[0087] The generated prompt sentence is sent to a generative AI model.

[0088] Step 4:

[0089] The generative AI model generates an outfit based on the received prompt. For example, it might generate an outfit such as a white blouse, denim skirt, and red pumps. The generated outfit is returned to the server.

[0090] Step 5:

[0091] The server sends the generated coordinates to the device. The server sends the coordinates received from the generative AI model to the device as an HTTP response. The output data is sent in JSON format.

[0092] Step 6:

[0093] The user checks the outfit and inputs feedback. The user checks the outfit displayed on the device and inputs feedback such as "it was hot." The input feedback is saved on the device.

[0094] Step 7:

[0095] The device sends the feedback to the server. The device sends the feedback entered by the user to the server using an HTTP POST request. The input data is sent in JSON format.

[0096] Step 8:

[0097] The server trains the model based on the feedback. The server then retrains the generative AI model based on the received feedback. This allows the server to suggest outfits that reflect the user's feedback from the next time.

[0098] (Application example 1)

[0099] Next, a description will be given of Application Example 1 of Embodiment 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."

[0100] Conventional fashion coordination suggestion systems have difficulty proposing appropriate outfits based on the user's situation and weather information, and are unable to effectively learn from the user's feedback and reflect it in future suggestions. Furthermore, there is a lack of means for users to purchase items based on the suggested outfits, resulting in low user convenience.

[0101] 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.

[0102] In this invention, the server includes a means for suggesting fashion coordination based on situational information and weather information input by the user, a means for learning user feedback, a means for purchasing products similar to the suggested coordination, a means for suggesting coordination using a generative AI model, and a means for generating prompt sentences. This makes it possible to suggest optimal coordination based on the user's situation and weather, and to learn user feedback and reflect it in future suggestions. Furthermore, by providing a means for purchasing products based on the suggested coordination, user convenience can be improved.

[0103] A "user" is an individual who uses the system to receive fashion coordination suggestions.

[0104] "Context information" is information entered by a user about a particular situation or event.

[0105] "Weather information" is information about the current weather and weather conditions entered by the user.

[0106] "Fashion coordination" is the combination of clothing and accessories appropriate for a particular situation or weather.

[0107] "Feedback" refers to the impressions and opinions that users provide regarding the proposed outfits.

[0108] "Learners" are methods and techniques for improving the next offering based on user feedback.

[0109] A "generative AI model" is an algorithm that uses artificial intelligence to generate outfits based on user input.

[0110] A "prompt sentence" is an instruction sentence input to a generative AI model.

[0111] The "means for purchasing products" refers to a method or system for purchasing related products based on the proposed coordination.

[0112] The system for implementing this invention proposes fashion coordination based on situational and weather information entered by the user, learns from the user's feedback and reflects it in future proposals, and also provides a means for purchasing products based on the proposed coordination.

[0113] Hardware and software used

[0114] Hardware: Smartphones, servers

[0115] Software: Python, Requests library, Scikit-learn, OpenAI API

[0116] System configuration

[0117] 1. User device: The user uses a smartphone to input situation information (e.g., "date") and weather information (e.g., "sunny").

[0118] 2. Server: The server receives the information sent by the user and uses a generative AI model to suggest appropriate fashion coordination.

[0119] 3. Generative AI model: The server inputs a prompt statement into the generative AI model to generate coordination suggestions.

[0120] 4. Feedback learning: When a user provides feedback on a suggested outfit (e.g., "It was hot"), the server learns this feedback and reflects it in the next suggestion.

[0121] 5. Product Purchasing Method: Allows users to purchase related products based on the suggested outfits.

[0122] Data processing and calculation

[0123] 1. Data acquisition: The server acquires situational information and weather information from the user's device.

[0124] 2. Prompt generation: The server generates a prompt to be input into the generative AI model based on the acquired information.

[0125] Example: "Situation: Date, Weather: Please suggest an outfit suitable for sunny weather."

[0126] 3. Coordination proposal: The generative AI model generates a coordination proposal based on the prompt sentence and returns it to the server.

[0127] 4. Feedback learning: The server receives feedback from the user and uses Scikit-learn to update the model to improve the next suggestion.

[0128] 5. Product Purchase: The server generates a purchase link for related products based on the suggested coordination and provides it to the user.

[0129] Specific examples

[0130] Situation: Dating

[0131] Weather: Sunny

[0132] Suggested outfit: White blouse, denim skirt, red pumps

[0133] Feedback: It was hot

[0134] In this way, the system can suggest the best outfits for the user's situation and weather, learn from the user's feedback, and reflect it in future suggestions. Also, by providing a means to purchase products based on the suggested outfits, the system can improve user convenience.

[0135] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0136] Step 1:

[0137] The user uses a smartphone device to input situation information (e.g., "date") and weather information (e.g., "sunny"). The input information is sent from the device to the server. The input data is situation information and weather information.

[0138] Step 2:

[0139] The server receives the situational information and weather information sent by the user. Based on the received data, it generates a prompt sentence to input into the generative AI model. Specifically, it combines the situational information and weather information to create the following prompt sentence:

[0140] Example: "Situation: Date, Weather: Please suggest an outfit suitable for sunny weather."

[0141] Step 3:

[0142] The server sends the generated prompt to the generative AI model, which generates a fashion outfit based on the prompt. The output of the generative AI model is a suggested outfit.

[0143] Step 4:

[0144] The server receives the coordinates returned by the generative AI model and sends them to the user's device. The user's device displays the received coordinates to the user. The displayed data is the suggested coordinates.

[0145] Step 5:

[0146] The user inputs feedback for the proposed coordinates. The feedback is sent from the terminal to the server. The input data is the user's feedback.

[0147] Step 6:

[0148] The server receives the feedback sent by the user and uses Scikit-learn to update the model to improve the next suggestion. Specifically, the feedback data is used as training data to update the linear regression model. The updated model is reflected in the next suggestion.

[0149] Step 7:

[0150] The server generates a purchase link for the related product based on the proposed coordination. The generated purchase link is sent to the user terminal and displayed to the user. The displayed data is the purchase link for the related product.

[0151] In this way, the system can suggest the best outfits for the user's situation and weather, learn from the user's feedback, and reflect it in future suggestions. Also, by providing a means to purchase products based on the suggested outfits, the system can improve user convenience.

[0152] Example 2

[0153] Next, a description will be given of Example 2 of Form 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."

[0154] Conventional fashion coordination systems have difficulty in proposing items that fully reflect the user's preferences and past purchase history, which has prevented them from increasing user satisfaction. Furthermore, there is a lack of easy ways to purchase items similar to the suggested outfits, which has prevented them from effectively stimulating users' purchasing desire.

[0155] 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 a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for inputting a prompt sentence to the generative AI model based on the user's past purchase history and preferences, a means for the generative AI model to generate a coordination, a means for transmitting the generated coordination to the user's terminal, and a means for the user to select and purchase products. This makes it possible to suggest optimal coordination that reflects the user's preferences and past purchase history, and allows the user to easily purchase the suggested products.

[0156] "User" refers to an individual who uses the system to receive fashion coordination suggestions.

[0157] "Situation information" refers to information about the current situation or event entered by the user.

[0158] "Weather information" refers to information about the weather at the user's current location or a specified location.

[0159] "Fashion coordination" refers to the combination of clothing and accessories suggested based on the user's situation and weather information.

[0160] "Feedback" refers to the evaluations and opinions that users give about the suggested outfits.

[0161] A "generative AI model" refers to an artificial intelligence model that generates optimal outfits based on user data.

[0162] A "prompt sentence" refers to an instruction sentence input to a generative AI model.

[0163] "Purchase history" refers to a record of products a user has purchased in the past.

[0164] "Preferences" refers to personal preferences such as a user's favorite styles, brands, or colors.

[0165] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a user uses to access the system.

[0166] "Product" refers to items such as clothing and accessories included in the suggested outfit.

[0167] "Purchase Method" means the method by which a User can purchase a suggested Product directly within the App.

[0168] This invention is a system for suggesting fashion coordination based on situational information and weather information input by a user, learning from the user's feedback, and purchasing products similar to the suggested coordination. Specific embodiments of this system are described below.

[0169] First, a user launches the app on a device such as a smartphone or tablet. The app displays the initial screen and confirms the user's login information. Once the user logs in, the server retrieves the user's past purchase history and preference data from a database. This data includes the type, color, size, and brand of the products purchased.

[0170] Next, the server inputs a prompt to the generative AI model based on the acquired user data. For example, the server sends a prompt such as, "Please suggest products similar to the white blouse based on the user's past purchase history and preferences." The generative AI model then generates the optimal outfit for the user based on this prompt. The generated outfit includes products similar to the white blouse.

[0171] The generated outfit is sent from the server to the user's device. The device displays the outfit to the user. The user can then review the suggested items and view detailed information. The user selects the preferred item from the suggested items and completes the purchase. Payment information and delivery address are entered to complete the purchase directly within the app.

[0172] As a concrete example, consider the case where a user is offered a "white blouse." The server displays multiple products similar to the white blouse based on the user's past purchase history and preferences. The user can then select and purchase a "white blouse with lace" or a "simple white blouse," etc.

[0173] Examples of prompts to be input to a generative AI model include:

[0174] Example prompt sentence:

[0175] Suggest products similar to white blouses based on the user's past purchase history and preferences.

[0176] By inputting this prompt into a generative AI model, the most suitable product is suggested to the user.

[0177] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0178] Step 1:

[0179] A user launches an app. The user launches the app on a device such as a smartphone or tablet, and the login screen appears. The user enters their login information, and if authentication is successful, the app's home screen appears. The input is the user's login information, and the output is the authenticated user information.

[0180] Step 2:

[0181] The server retrieves user data. Based on the authenticated user information, the server retrieves the user's past purchase history and preference data from a database. This data includes the type, color, size, and brand of purchased products. The input is authenticated user information, and the output is the user's past purchase history and preference data.

[0182] Step 3:

[0183] The server inputs a prompt to the generative AI model. The server inputs the prompt to the generative AI model based on the acquired user data. For example, a prompt such as "Please suggest products similar to the white blouse based on the user's past purchase history and preferences" is sent to the generative AI model. The input is the user's past purchase history and preference data, and the output is a prompt to the generative AI model.

[0184] Step 4:

[0185] The generative AI model generates an outfit. The generative AI model generates the optimal outfit for the user based on the input prompt. The generated outfit includes items similar to the white blouse. The input is the prompt, and the output is the generated outfit.

[0186] Step 5:

[0187] The server sends the generated outfit to the device. The server then sends the outfit received from the generative AI model to the user's device. The sent data includes product images, prices, detailed information, etc. The input is the generated outfit, and the output is the outfit data sent to the user's device.

[0188] Step 6:

[0189] The terminal displays the coordinated outfits to the user. The terminal displays the received coordinated outfits to the user. The user can check the suggested items and view detailed information. The input is the coordinated outfit data sent from the server, and the output is the coordinated outfit information displayed to the user.

[0190] Step 7:

[0191] The user selects and purchases a product. The user selects the preferred product from the suggested products and completes the purchase. Payment information and delivery address are entered to complete the purchase directly within the app. The input is the user's selected product information and payment information, and the output is confirmation of purchase completion.

[0192] (Application example 2)

[0193] Next, a description will be given of Application Example 2 of Form 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."

[0194] Conventional fashion coordination suggestion systems can suggest outfits based on the user's situation and weather information, but they lack the ability to suggest similar fashion items based on images taken by the user. They also lack the ability to display multiple products similar to the suggested items so the user can select and purchase them, or the ability to display detailed product information and reviews. This makes it difficult for users to easily find and purchase products that match their preferences.

[0195] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for suggesting fashion coordination based on situation information and weather information input by the user, means for learning feedback from the user, means for purchasing products similar to the suggested coordination, means for suggesting similar fashion items based on images taken by the user, means for displaying multiple products similar to the suggested items so that the user can select and purchase them, and means for displaying detailed product information and reviews. This allows the user to easily find and purchase products that suit their preferences.

[0196] "User-entered contextual information" refers to information provided by the user, such as current activities, events, and locations.

[0197] "Weather information" refers to meteorological data such as the current weather, temperature, and humidity.

[0198] "Means for suggesting fashion coordination" is a function that suggests appropriate clothing combinations based on the user's situational information and weather information.

[0199] "Means for learning from user feedback" is a function that collects opinions and evaluations provided by users and uses them to improve the accuracy of the system's suggestions.

[0200] "Means for purchasing products similar to the suggested coordination" is a function that displays products similar to the suggested fashion coordination and allows the user to purchase them.

[0201] "A means for suggesting similar fashion items based on images taken by the user" is a function that analyzes photos taken by the user and suggests similar fashion items.

[0202] "A means of displaying multiple products similar to the suggested item and allowing the user to select and purchase" is a function that displays multiple products similar to the suggested item and allows the user to select and purchase from among them.

[0203] "Means for displaying detailed product information and reviews" refers to a function that displays detailed product information and ratings and reviews from other users.

[0204] The system for implementing this invention has the functions of suggesting fashion coordination based on situational and weather information entered by the user and learning from user feedback. It also provides a means for purchasing products similar to the suggested coordination and has the functions of suggesting similar fashion items based on images taken by the user. It also has the functions of displaying multiple products similar to the suggested items so that the user can select and purchase them, and displaying detailed product information and reviews.

[0205] System program and processing description

[0206] Hardware

[0207] Smartphone (iOS or ANDROID (registered trademark))

[0208] server

[0209] software

[0210] Python

[0211] TensorFlow

[0212] Keras

[0213] VGG16 model (pre-trained)

[0214] Data processing and calculation

[0215] The server receives situational and weather information entered by the user on their smartphone and suggests fashion coordination based on that information. When the user uploads a photo they have taken to the server, the server analyzes the image and suggests similar fashion items. Specifically, it uses the VGG16 model to extract features from the image and predict similar items.

[0216] The server displays multiple products similar to the suggested item and allows the user to select and purchase from them. It also displays detailed product information and reviews from other users, allowing users to easily find and purchase products that suit their preferences.

[0217] Specific examples

[0218] Users take a photo of a white blouse with their smartphone and upload it to the server via the app. The server analyzes the image using the VGG16 model and suggests several similar white blouses. Users can then choose their favorite from the suggested blouses and purchase them after checking detailed information and reviews.

[0219] Prompt Sentence Examples

[0220] "Upload a photo of a white blouse and let our AI suggest similar products."

[0221] In this way, users can easily find and purchase products that suit their tastes.

[0222] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0223] Step 1:

[0224] The user inputs situational and weather information using a smartphone. The input information is sent to the server, which receives the information and stores it in a database. The input data includes the user's current activities and events, location, weather, temperature, humidity, etc.

[0225] Step 2:

[0226] The server then proposes fashion coordination based on the saved situational and weather information. The server then generates appropriate outfit combinations using a pre-trained model. The coordinated outfits are then sent to the user's smartphone and displayed.

[0227] Step 3:

[0228] The user provides feedback on the suggested outfits. The feedback is based on the user's preferences and experience. The server receives this feedback and stores it in a database. The feedback data is used to improve the accuracy of the next suggestion.

[0229] Step 4:

[0230] Users take images with their smartphones and upload them to the server via the app. The server receives the uploaded images and performs image analysis. Specifically, it uses the VGG16 model to extract features from the images.

[0231] Step 5:

[0232] The server then suggests similar fashion items based on the extracted features. The suggested items are sent to the user's smartphone and displayed. The user can then confirm the suggested items.

[0233] Step 6:

[0234] The server displays multiple products similar to the suggested item, including searching for similar products in a database and sending them to the user's smartphone. The user can then select the product they like best.

[0235] Step 7:

[0236] The server displays detailed information and reviews from other users about the product selected by the user. Detailed information includes the product's material, size, price, etc. Reviews include ratings and comments from other users. The user uses this information to purchase the product.

[0237] Step 8:

[0238] If the user decides to make a purchase, the server processes the purchase, which includes verifying payment information, entering shipping details, etc. Once the purchase is complete, the server sends a confirmation message to the user.

[0239] In this way, users can easily find and purchase products that suit their preferences.

[0240] Example 3

[0241] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0242] Conventional fashion coordination systems have difficulty making suggestions that match a user's preferences and physical experience, and lack the functionality to customize and order suggested items. As a result, they are unable to provide coordination that satisfies users, and the user experience is not improved.

[0243] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0244] In this invention, the server includes means for proposing fashion coordination based on situational information and weather information input by the user, means for learning feedback from the user, means for purchasing products similar to the proposed coordination, means for receiving a prompt input by the user and generating a coordination using a generative AI model, means for the user to customize and order items based on the proposed coordination, and means for sending instructions to a manufacturing system based on the customization information. This makes it possible to propose coordination that suits the user's preferences and physical sensations, and to order further customized items.

[0245] "User" refers to an individual who uses the system to receive fashion coordination suggestions.

[0246] "Status information" refers to information about an event or situation that is entered by the user.

[0247] "Weather Information" means information regarding weather conditions at a User's location or a specified location.

[0248] "Fashion coordination" refers to a style proposed by combining multiple fashion items.

[0249] "Feedback" refers to the evaluations and opinions that users give about the suggested outfits.

[0250] A "generative AI model" refers to an algorithm that uses artificial intelligence to generate outfits based on user input.

[0251] "Prompt" refers to a textual request that a user enters into a generative AI model.

[0252] "Customization" refers to the act of a user changing the size, color, etc. of a suggested item.

[0253] "Manufacturing system" refers to the machines and processes that produce made-to-order items based on customization information.

[0254] "Means of suggestion" refers to the function of generating optimal fashion coordination based on information input by the user.

[0255] "Means of learning" refers to the function of collecting feedback from users and reflecting it in future suggestions.

[0256] "Means for purchasing" refers to the function for purchasing the items included in the proposed coordination.

[0257] "Means for ordering" refers to the functionality that allows users to order customised items on a made-to-order basis.

[0258] The "means for transmitting instructions" refers to a function for transmitting customization information to the manufacturing system.

[0259] This invention is a system that proposes fashion coordination based on situational information and weather information entered by a user, learns feedback from the user, and orders custom-made items based on the proposed coordination. Specific embodiments of this system are described below.

[0260] First, the user inputs a prompt using the device. An example of a prompt is, "Please suggest an outfit suitable for a casual date." The device then sends this prompt to the server. The server uses a generative AI model (e.g., OpenAI's GPT-4 (registered trademark)) to generate an outfit that takes into account the user's preferences and past purchase history.

[0261] The generated outfit is sent from the server to the device, and the user can review the suggested outfit. For example, a white T-shirt, denim jacket, black skinny jeans, and red pumps are suggested. The user can select their favorite items and further customize them. For example, they can change the size of the red pumps to 24cm and the color to blue.

[0262] Once the user has completed the customization, the terminal sends the customization information to the server, which then sends instructions to the manufacturing system to create the custom-made item. The manufacturing system then produces the customized item and delivers it to the address specified by the user upon completion.

[0263] This system suggests outfits that suit the user's tastes and preferences, and also allows the user to order customized items, providing a more satisfying fashion experience for the user.

[0264] Specific hardware includes user devices (such as smartphones and tablets), servers, and manufacturing systems, while software includes generative AI models (such as OpenAI's GPT-4), communication protocols (HTTPS), and applications that provide user interfaces.

[0265] This system allows users to easily find fashion items that suit their tastes, customize them, and place an order. The flow of the specification process in the third embodiment will be described with reference to FIG.

[0266] Step 1:

[0267] The user enters a prompt statement.

[0268] The user uses the device interface to input a prompt about the desired outfit. For example, the user might input, "Please suggest an outfit suitable for a casual date." The input prompt becomes the input data for the device.

[0269] Step 2:

[0270] The terminal sends the prompt to the server.

[0271] The terminal sends the prompt text entered by the user to the server using the HTTPS protocol. The input data is the prompt text, and the output data is the prompt text sent to the server.

[0272] Step 3:

[0273] The server generates coordinates using a generative AI model.

[0274] The server inputs the received prompt into a generative AI model (e.g., OpenAI's GPT-4) to generate an outfit that takes into account the user's preferences and past purchase history. The input data is the prompt and the user's history data, and the output data is the generated outfit.

[0275] Step 4:

[0276] The server transmits the generated coordinates to the terminal.

[0277] The server sends the generated coordinates to the terminal in JSON format. The input data is the generated coordinates, and the output data is the coordinates sent to the terminal.

[0278] Step 5:

[0279] The user checks the suggested outfits and selects items.

[0280] The user checks the outfits displayed on the device screen and selects the items they like. For example, they tap red pumps to select them. The input data is the suggested outfit, and the output data is the selected items.

[0281] Step 6:

[0282] Customize and order the items the user selects.

[0283] The user customizes the size and color of the selected item. For example, they change the size of a pair of red pumps to 24cm and the color to blue, and then tap the "Order" button. The input data are the selected item and customization information, and the output data is the customized order information.

[0284] Step 7:

[0285] The terminal transmits the customization information to the server.

[0286] The terminal sends the user-customized information to the server in JSON format, where the input data is the customized order information and the output data is the customized information sent to the server.

[0287] Step 8:

[0288] The server sends instructions to the manufacturing system.

[0289] The server sends instructions to the manufacturing system to manufacture the custom-made item based on the received customization information. The input data is the customization information, and the output data is the instructions sent to the manufacturing system.

[0290] Step 9:

[0291] A manufacturing system produces and delivers custom-made items to users.

[0292] The manufacturing system follows instructions from the server to manufacture customized items. Once manufacturing is complete, the items are delivered to an address specified by the user. The input data are manufacturing instructions, and the output data are the manufactured items.

[0293] (Application example 3)

[0294] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0295] Conventional fashion coordination systems have problems in that they do not adequately provide suggestions based on the user's preferences, and users cannot actually try on the suggested outfits, resulting in low user satisfaction. Furthermore, when ordering custom-made items, it is difficult for users to customize them to suit their preferences.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0297] In this invention, the server includes means for suggesting fashion coordination based on situational information and weather information input by the user, means for learning from user feedback, means for purchasing products similar to the suggested coordination, means for suggesting coordination based on the user's preferences using a generative AI model, means for providing a virtual try-on function that overlays items on the user's image, and means for ordering custom-made items. This allows for coordination suggestions based on the user's preferences, allows the user to actually try on the outfits through the virtual try-on function, and further allows the user to easily customize and order custom-made items.

[0298] "User-inputted situation information" refers to information about the current situation or environment that the user provides to the system, such as the type of event, location, and time of day.

[0299] "Weather information" refers to information about current weather conditions such as temperature, humidity, etc. This information can be used to suggest appropriate fashion coordination.

[0300] "Means for suggesting fashion coordination" is a function that suggests appropriate combinations of clothing and accessories based on situational and weather information entered by the user.

[0301] "Means for learning from user feedback" is a function that collects opinions and evaluations provided by users and uses them to improve the accuracy of the system's suggestions.

[0302] "Means for purchasing products similar to the suggested coordination" is a function that provides products that the user can actually purchase based on the fashion coordination suggested by the system.

[0303] A "generative AI model" is an algorithm that uses artificial intelligence to learn a user's preferences and tendencies and then generates optimal outfits based on that information.

[0304] The "virtual try-on feature" overlays suggested items onto the user's image, making it appear as if the user is actually trying them on.

[0305] "Means for ordering custom-made items" refers to a feature that allows users to customize suggested items and order them by specifying size, color, etc.

[0306] A system for implementing this invention includes means for suggesting fashion coordination based on situational and weather information input by a user, learning from user feedback, purchasing products similar to the suggested coordination, using a generative AI model to suggest coordination based on the user's preferences, providing a virtual try-on function that overlays items on the user's image, and ordering custom-made items.

[0307] Hardware and software used

[0308] Hardware: Smartphone, head-mounted display

[0309] Software: OpenAI API, OpenCV

[0310] Data processing and calculation

[0311] Coordination suggestions using generative AI models

[0312] The server uses a generative AI model to suggest outfits based on the user's preferences. The user's preferences and past feedback are input as prompts, and the AI ​​model generates the optimal outfit.

[0313] Example prompt sentence:

[0314] Suggest outfits based on the user's preferences: casual and simple style

[0315] Virtual try-on feature

[0316] The device uses OpenCV to overlay suggested items onto the user's image, synthesizing the image the user took with the suggested items, enabling a virtual try-on experience.

[0317] Order custom-made items

[0318] The user customizes the suggested items and places a custom order by specifying the size and color. The server receives the user's customization information and processes the order.

[0319] Specific examples

[0320] If a user prefers a "casual and simple style," the generative AI model will suggest a "white T-shirt, denim pants, and red pumps." The user can then take a photo of themselves with their smartphone and try on the suggested outfit using the virtual try-on feature. They can then select their favorite pair of red pumps, specify the size "M" and the color "red," and place a custom order.

[0321] In this way, users can receive outfit suggestions based on their preferences, try them on, and easily order customised, made-to-order items.

[0322] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0323] Step 1:

[0324] The user inputs situation and weather information.

[0325] Input: User situation information (e.g., event type, location, time), weather information (e.g., weather, temperature, humidity)

[0326] Processing: The terminal sends this information to the server.

[0327] Output: Situation and weather information sent to the server

[0328] Step 2:

[0329] The server uses a generative AI model to suggest outfits.

[0330] Input: User situation information, weather information, user preferences and past feedback

[0331] Processing: The server inputs the prompt sentence into the generative AI model and generates the optimal coordinates.

[0332] Output: Proposed coordinates

[0333] Specific operation: The server inputs the following prompt sentence into the generative AI model:

[0334] Suggest outfits based on the user's preferences: casual and simple style

[0335] The generative AI model generates a coordinate based on this prompt and returns it to the server.

[0336] Step 3:

[0337] The user checks the suggested outfits.

[0338] Input: Proposed coordinates

[0339] Processing: The terminal displays the suggested coordination to the user.

[0340] Output: Coordination confirmed by the user

[0341] Step 4:

[0342] Users can try on the clothes virtually.

[0343] Input: User image, suggested item image

[0344] Processing: The device uses OpenCV to overlay the item on the user's image.

[0345] Output: Virtual try-on image

[0346] Specific operation: The device combines the image taken by the user with the image of the suggested item to generate a virtual try-on image.

[0347] Step 5:

[0348] Users customize and order made-to-order items.

[0349] Input: Suggested items, user customization information (e.g. size, color)

[0350] Processing: The server receives the user's customization information and processes the order.

[0351] Output: Custom order confirmation

[0352] Specific behavior: The server receives the size and color of the item selected by the user and confirms the order.

[0353] Step 6:

[0354] The server learns from user feedback.

[0355] Input: User feedback (e.g., satisfaction, areas for improvement)

[0356] Processing: The server collects the feedback and uses it as training data for the generative AI model.

[0357] Output: An updated generative AI model

[0358] Specific operation: The server stores the user's feedback in a database and reflects it in the next outfit suggestions.

[0359] 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.

[0360] "Example 1"

[0361] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes the user's emotions and suggests fashion coordination based on those emotions. Specifically, when a user inputs emotional information such as "I'm tired" into the app, the emotion engine analyzes this information and suggests a relaxed, casual outfit. For example, it suggests a combination of loose-fitting sweatshirts and pants made of soft material.

[0362] "Example 2"

[0363] The emotion engine also provides a way for users to order custom-made items based on their emotions. Specifically, when a user inputs emotional information such as "special occasion," the emotion engine analyzes this information and suggests custom-made items suitable for the special occasion. For example, it could suggest a custom-made dress or suit tailored to the user's preferences and the occasion of the special occasion.

[0364] "Example 3"

[0365] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes the user's emotions and suggests fashion coordination based on those emotions. Specifically, when a user inputs emotional information such as "I'm tired" into the app, the emotion engine analyzes this information and suggests a relaxed, casual outfit. For example, it suggests a combination of loose-fitting sweatshirts and pants made of soft material.

[0366] The processing flow of each embodiment will be described below.

[0367] "Example 1"

[0368] Step 1: The user inputs emotional information into the app. For example, they input "I'm tired."

[0369] Step 2: The emotion engine analyzes the information input by the user, which determines the user's current emotional state.

[0370] Step 3: The emotion engine suggests fashion coordination based on the analysis results. For example, if the user feels tired, it will suggest a casual outfit that will help them relax.

[0371] "Example 2"

[0372] Step 1: The user inputs emotional information into the app, for example, "special day."

[0373] Step 2: The emotion engine analyzes the information input by the user, which determines the user's current emotional state.

[0374] Step 3: The emotion engine will suggest custom-made items based on the analysis results. For example, if the user feels that a special day is coming up, it will suggest custom-made items suitable for that day.

[0375] Example 1

[0376] Next, a description will be given of Example 1 of Form 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."

[0377] Conventional fashion coordination suggestion systems were limited in the suggestions they could make based on the user's situation and weather information, and were unable to fully reflect the user's emotions and feedback. Furthermore, they lacked a way to purchase products based on the suggested outfits or to order custom-made items, making it difficult to increase user satisfaction.

[0378] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for analyzing emotional information of the user and suggesting a fashion coordination based on the emotion, and a means for generating a fashion coordination using a generative AI model. This makes it possible to suggest appropriate fashion coordination according to the user's situation, weather, and emotion, and to make suggestions that reflect the user's feedback, as well as to purchase products and order custom-made items.

[0379] A "user" is an individual who uses the system to receive fashion coordination suggestions.

[0380] "Context information" is information entered by a user about a particular event or situation.

[0381] "Weather information" is information about the weather for that day entered by the user.

[0382] "Fashion coordination" refers to the combination of clothing and accessories worn by a user.

[0383] "Feedback" refers to the evaluation or comments that a user provides regarding the proposed outfit.

[0384] "Means to learn" refers to how the system uses user feedback to improve its next suggestions.

[0385] "Means for purchasing products" refers to a method for purchasing items included in the proposed coordination.

[0386] "Emotion information" is information about the user's own emotions and moods that is input by the user.

[0387] "Means for suggesting fashion coordination based on emotions" refers to a method for analyzing a user's emotional information and suggesting appropriate coordination based on the results.

[0388] A "generative AI model" is an artificial intelligence model that generates fashion coordination based on user input information.

[0389] A "means for ordering a custom-made item" is a method for ordering a customized item based on a suggested outfit.

[0390] This invention is a system that suggests appropriate fashion coordination based on situational information, weather information, and emotional information input by the user. The system has the function of learning from the user's feedback and reflecting it in the next suggestion. It also includes a means for purchasing products based on the suggested coordination, or a means for ordering custom-made items.

[0391] Hardware and software used

[0392] Hardware: Servers, user devices (smartphones and tablets)

[0393] Software: Applications, emotion engines, generative AI models

[0394] Specific operation of the system

[0395] 1. The user enters information

[0396] The user enters the situation information "date" and the weather information "sunny" into the app's input fields.

[0397] Specific behavior: The user opens the app on their smartphone, enters "date" and "sunny" in the text boxes, and presses the send button.

[0398] 2. The server receives and analyzes the information

[0399] The server receives the status information and weather information sent by the user.

[0400] Specific operation: The server receives the HTTP request and extracts the "date" and "sunny" information from the request body.

[0401] 3. The server generates the coordinates

[0402] The server uses a generative AI model to generate a fashion coordination based on the received information.

[0403] Specific operation: The server inputs the information "date" and "sunny" into the generated AI model, and the model outputs an outfit such as a white blouse, denim skirt, and red pumps.

[0404] 4. The server sends the coordinates to the user device.

[0405] The server transmits the generated coordinates to the user terminal.

[0406] Specific operation: The server constructs the generated coordinates in JSON format and sends them to the user's device as an HTTP response.

[0407] 5. User enters feedback

[0408] The user inputs feedback on the proposed outfit.

[0409] Specific behavior: The user enters "It was hot" in the app's feedback field and presses the submit button.

[0410] 6. The server learns from the feedback

[0411] The server receives user feedback and trains the generative AI model.

[0412] Specific operation: The server receives the feedback information, adds it to the training dataset of the generative AI model, and reflects this feedback in the next coordinate generation.

[0413] 7. The server uses the emotion engine

[0414] When a user inputs emotional information such as "I'm tired," the server analyzes this information using an emotional engine.

[0415] How it works: The user enters "I'm tired" into the app, and the server sends this information to the emotion engine. The emotion engine generates a relaxing outfit, which the server then sends to the user's device.

[0416] Examples and prompts

[0417] Example: If a user inputs "date" and "sunny," a white blouse, denim skirt, and red pumps are suggested. If the user then inputs feedback that "it was hot," a cooler outfit will be suggested for next time.

[0418] Example prompt: "I have a date and the weather is sunny. What outfit would be good?"

[0419] The system aims to increase user satisfaction by suggesting more appropriate fashion coordination based on the user's input information and feedback.

[0420] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0421] Step 1:

[0422] The user enters information.

[0423] The user enters the situation information "date" and the weather information "sunny" into the app's input fields and presses the send button. The entered information is sent from the user's device to the server. Specifically, the user opens the app on their smartphone, enters "date" and "sunny" into the text boxes, and presses the send button.

[0424] Step 2:

[0425] The server receives and analyzes the information.

[0426] The server receives the status information and weather information sent by the user. The received information is sent to the server as an HTTP request, and the "date" and "sunny" information is extracted from the request body. Specifically, the server analyzes the HTTP request and extracts the necessary information.

[0427] Step 3:

[0428] The server generates the coordinates.

[0429] The server uses a generative AI model to generate a fashion coordination based on the received information. The input information of "date" and "sunny" is input into the generative AI model, and the model outputs an outfit such as a white blouse, denim skirt, and red pumps. In concrete terms, the server inputs information into the generative AI model, and the model generates the outfit.

[0430] Step 4:

[0431] The server sends the coordinates to the user terminal.

[0432] The server sends the generated coordinates to the user's device. The generated coordinates are constructed in JSON format and sent to the user's device as an HTTP response. Specifically, the server converts the generated coordinates into JSON format and sends them as an HTTP response.

[0433] Step 5:

[0434] The user enters feedback.

[0435] The user enters feedback on the suggested outfit. The user enters "It was hot" in the feedback field of the app and presses the send button. The entered feedback is sent from the user's device to the server. Specifically, the user enters text in the feedback field of the app and presses the send button.

[0436] Step 6:

[0437] The server learns the feedback.

[0438] The server receives user feedback and trains the generative AI model. The received feedback information is added to the training dataset of the generative AI model and is reflected in the next coordinate generation. Specifically, the server receives feedback information and adds it to the training dataset of the generative AI model.

[0439] Step 7:

[0440] The server uses the emotion engine.

[0441] When a user inputs emotional information such as "I'm tired," the server analyzes this information using an emotion engine. The emotion engine generates a relaxing outfit, which the server then sends to the user's device. Specifically, the user inputs "I'm tired" into the app, the server sends the information to the emotion engine, and the generated outfit is sent to the user's device.

[0442] (Application example 1)

[0443] Next, a description will be given of Application Example 1 of Embodiment 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."

[0444] While conventional fashion coordination suggestion systems make suggestions based on the user's situation and weather information, they have not been able to fully utilize the user's emotional information and feedback, making it difficult to increase user satisfaction.In addition, in virtual stores, there is a lack of a way to suggest optimal fashion coordination based on the user's input information, making it difficult to improve the user's shopping experience.

[0445] 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.

[0446] In this invention, the server includes means for proposing fashion coordination based on situation information and weather information input by the user, means for learning feedback from the user, means for purchasing products similar to the proposed coordination, means for analyzing emotional information of the user and proposing fashion coordination based on the emotions, and means for proposing optimal fashion coordination in a virtual store based on the information input by the user. This makes it possible to propose fashion coordination that reflects the user's emotions and feedback and provides a higher level of satisfaction.

[0447] "User-entered context information" refers to information that a user inputs into an application about a particular situation or event.

[0448] "Weather information" refers to information about current weather and weather conditions.

[0449] The "means for suggesting fashion coordination" is a system that has the function of suggesting appropriate clothing combinations based on information input by the user.

[0450] "Means for learning from user feedback" refers to a system that has the ability to collect opinions and feedback provided by users and improve the system based on that.

[0451] "Means for purchasing products similar to the proposed fashion coordination" refers to a system that has the functionality to enable the purchase of similar products online or in a physical store based on the proposed fashion coordination.

[0452] The "means for analyzing the user's emotional information" is a system that has the function of analyzing the emotional information entered by the user and suggesting appropriate fashion coordination based on the results.

[0453] A "virtual store" refers to a virtual shopping space operated on the Internet.

[0454] "Means for suggesting optimal fashion coordination based on information input by the user" refers to a system that has the function of suggesting optimal clothing combinations based on situational information, weather information, emotional information, etc. provided by the user.

[0455] As an embodiment of the present invention, the following system can be constructed.

[0456] First, the server receives information about the situation, weather, and emotions entered by the user via a device such as a smartphone or tablet. The server analyzes this information and refers to a database to suggest appropriate fashion coordination.

[0457] The server then collects user feedback and uses machine learning algorithms to learn from it. For example, when a user provides feedback such as "it was hot" or "it was comfortable," the server analyzes it and uses it to improve its next recommendation. This learning process can be achieved using machine learning libraries such as Python and TensorFlow.

[0458] Furthermore, the server generates a link to enable the user to purchase products similar to the suggested outfits at online stores or physical stores, making it easy for the user to purchase the products.

[0459] The system also uses a sentiment analysis engine to analyze the user's emotional information. For example, if a user inputs "I'm tired," the server analyzes this information and suggests relaxing fashion coordination. This process uses natural language processing (NLP) technology.

[0460] In the virtual store, the server suggests optimal fashion coordination based on the user's input information. For example, if a user inputs the information "date" and "sunny" and adds the emotion information "tired," the server will suggest "loose sweatshirts" and "pants made of soft material." This suggestion will be useful when the user goes shopping in the virtual store.

[0461] As a concrete example, by inputting the following prompt sentence into the generative AI model, ideas for suggesting appropriate outfits can be obtained.

[0462] Example prompt sentence:

[0463] If a user inputs the information "date" and "sunny" and adds the emotion information "tired," what kind of fashion coordination will be suggested?

[0464] In this way, it becomes possible to propose fashion coordination that reflects the user's emotions and feedback and provides greater satisfaction.

[0465] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0466] Step 1:

[0467] A user inputs situation information, weather information, and emotion information using a device such as a smartphone or tablet.

[0468] Input: situation information (e.g., "date"), weather information (e.g., "sunny"), emotion information (e.g., "tired")

[0469] Output: The entered information is sent to the server.

[0470] Step 2:

[0471] The server analyzes the received situation information, weather information, and emotion information.

[0472] Input: Situation information, weather information, and emotion information sent by the user

[0473] Data processing: Analyze input information using natural language processing (NLP) techniques.

[0474] Output: Analysis results (e.g. "date", "sunny", "tired")

[0475] Step 3:

[0476] The server will suggest appropriate fashion coordination based on the analysis results.

[0477] Input: Analysis results

[0478] Data calculation: Refer to the database and search for the optimal coordination based on the analysis results.

[0479] Output: Suggested outfits (e.g., "loose-fitting sweatshirts," "soft pants")

[0480] Step 4:

[0481] The server generates a link that allows products similar to the suggested coordination to be purchased at an online store or a physical store.

[0482] Input: Suggested fashion coordination

[0483] Data processing: Refer to the product database and generate links to similar products.

[0484] Output: Purchase link (e.g. "Online store link")

[0485] Step 5:

[0486] Users can review suggested outfits and purchase links and enter feedback.

[0487] Input: User feedback (e.g. "It was hot" or "It was comfortable")

[0488] Output: Feedback is sent to the server.

[0489] Step 6:

[0490] The server collects user feedback and learns using machine learning algorithms.

[0491] Input: User feedback

[0492] Data computation: Using machine learning algorithms (e.g., Python, TensorFlow), we analyze the feedback and incorporate it into our next proposal.

[0493] Output: Updated proposed model

[0494] Step 7:

[0495] In a virtual store, we propose optimal fashion coordination based on the information entered by the user.

[0496] Input: User situation information, weather information, emotional information

[0497] Data calculation: Based on the analysis results, we propose optimal coordination in a virtual store.

[0498] Output: Suggested fashion coordination in a virtual store (e.g., "loose-fitting sweatshirt," "soft pants")

[0499] In this way, it becomes possible to propose fashion coordination that reflects the user's emotions and feedback and provides greater satisfaction.

[0500] Example 2

[0501] Next, a description will be given of Example 2 of Form 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."

[0502] Conventional fashion coordination systems not only suggest outfits based on the situation and weather information entered by the user, but also lack the ability to suggest custom-made items based on the user's emotions and preferences, or a means to easily purchase items similar to the suggested outfits. Furthermore, there is a need for systems that can effectively learn from user feedback and make more accurate suggestions.

[0503] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for analyzing the user's input using a generative AI model and searching for similar products, and a means for analyzing the user's emotion information using an emotion engine and suggesting custom-made items. This allows the user to not only receive coordination suggestions based on the situation and weather, but also to easily purchase custom-made item suggestions and suggested products based on their emotions.

[0504] "User-entered context information" is information about a particular situation or event that a user provides through an application.

[0505] "Weather information" is data about current weather, temperature, humidity, and other meteorological conditions.

[0506] "Means for suggesting fashion coordination" is a function that suggests appropriate combinations of clothing and accessories based on situational and weather information entered by the user.

[0507] "Means for learning from user feedback" is a function that collects ratings and comments provided by users and uses them to improve the accuracy of the system's suggestions.

[0508] "Means for purchasing products similar to the suggested coordination" is a function that allows the system to search for products similar to the suggested fashion coordination and enable the user to purchase them.

[0509] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze user input and generate appropriate products and outfits.

[0510] An "emotion engine" is a system that analyzes a user's emotional information and makes appropriate suggestions based on the results.

[0511] "Means for suggesting custom-made items" is a function that suggests specially customized products based on the user's emotional information and preferences.

[0512] This invention is a system that proposes fashion coordination based on situational and weather information entered by the user, learns from user feedback, and provides a means for purchasing products similar to the proposed coordination. It also includes functions that analyze user input using a generative AI model, analyze the user's emotional information using an emotion engine, and propose custom-made items.

[0513] Hardware and software used

[0514] Hardware: Servers, user devices (smartphones, tablets, PCs)

[0515] Software: Generative AI model, emotion engine, application (iOS / Android)

[0516] Specific operation of the system

[0517] Product suggestion function

[0518] 1. User Input

[0519] Within the app, users input information about a particular outfit, such as a prompt such as "Suggest products similar to this white blouse."

[0520] 2. Server search process

[0521] The server uses a generative AI model to analyze the user's input and search a database for similar products.

[0522] The server generates search results in list form and sends them to the user terminal.

[0523] 3. Terminal display processing

[0524] The user's device displays the product list received from the server within the app.

[0525] The user selects the product of their choice from the displayed product list.

[0526] 4. User purchase process

[0527] The user adds the selected items to the cart and completes the purchase.

[0528] The server receives the purchase information and processes the payment.

[0529] Emotion-based personalized recommendations

[0530] 1. User emotion input

[0531] The user inputs emotional information within the app, for example, "special day."

[0532] 2. Server Emotion Analysis

[0533] The server analyzes the user's emotional information using an emotion engine.

[0534] Based on the analysis results, the server uses a generative AI model to suggest custom-made items suitable for special occasions.

[0535] 3. Device suggestions

[0536] The user's device displays the custom-made item suggestions received from the server within the app.

[0537] Users can choose their favorite items from the suggested items.

[0538] 4. User's custom orders

[0539] The user confirms the selected items as a custom order.

[0540] The server receives the order information and processes the production and delivery.

[0541] Specific examples

[0542] Example prompt: "Suggest products similar to the white blouse."

[0543] Example prompt: "Suggest a custom-made item for a special occasion."

[0544] This system not only allows users to receive outfit suggestions based on the situation and weather, but also makes it possible for them to receive custom-made item suggestions based on their emotions and easily purchase the suggested products.

[0545] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0546] Step 1:

[0547] User Input

[0548] Within the app, users input information about a particular outfit, such as a prompt such as "Suggest products similar to this white blouse."

[0549] Input: The prompt text entered by the user.

[0550] Output: The prompt text sent to the server.

[0551] Step 2:

[0552] Server search process

[0553] The server uses a generative AI model to analyze the user's input, specifically by analyzing the prompt sentence using natural language processing technology to extract keywords and features.

[0554] Input: The prompt text sent by the user.

[0555] Data processing: Parsing prompts using a generative AI model.

[0556] Output: Extracted keywords and features.

[0557] Step 3:

[0558] Server database search

[0559] The server searches a database for similar products based on the extracted keywords and characteristics, applying filters such as color, design, and price range.

[0560] Input: Extracted keywords or features.

[0561] Data calculation: Product search using database search algorithms.

[0562] Output: A list of similar products.

[0563] Step 4:

[0564] Server result transmission

[0565] The server generates search results in list form and sends them to the user terminal.

[0566] Input: A list of similar products.

[0567] Data processing: Convert to list format.

[0568] Output: Product list sent to user device.

[0569] Step 5:

[0570] Terminal display processing

[0571] The user's device displays the product list received from the server within the app, including product images, prices, reviews, and other information.

[0572] Input: Product list sent from the server.

[0573] Data processing: Converting product list into display format.

[0574] Output: The product list displayed to the user.

[0575] Step 6:

[0576] User checkout process

[0577] The user selects the desired product from the displayed product list, adds it to the cart, checks the items in the cart, and presses the purchase button.

[0578] Input: The product selected by the user.

[0579] Data processing: Adding to cart and checkout processing.

[0580] Output: Purchase information.

[0581] Step 7:

[0582] Server payment processing

[0583] The server receives the purchase information and processes the payment, including verifying credit card information and communicating with a payment gateway.

[0584] Input: User's purchase information.

[0585] Data calculation: Settlement by payment processing algorithm.

[0586] Output: Payment completion notification.

[0587] Step 8:

[0588] User emotion input

[0589] The user inputs emotional information within the app, for example, "special day."

[0590] Input: Emotion information entered by the user.

[0591] Output: Emotion information sent to the server.

[0592] Step 9:

[0593] Server sentiment analysis

[0594] The server uses an emotion engine to analyze the user's emotional information. Specifically, it analyzes the emotional information using natural language processing technology and extracts data to make appropriate suggestions.

[0595] Input: Emotion information sent by the user.

[0596] Data processing: Analysis of emotional information using an emotion engine.

[0597] Output: Extracted emotion data.

[0598] Step 10:

[0599] Custom-made server proposals

[0600] The server uses a generative AI model to suggest custom-made items for special occasions based on the analysis results, taking into account the user's past purchase history and preferences, for example.

[0601] Input: Extracted emotion data.

[0602] Data computation: Generative AI models generate custom items.

[0603] Output: A list of suggested custom-made items.

[0604] Step 11:

[0605] Device suggestions

[0606] The user's device displays the custom-made item suggestions received from the server within the app, such as design images and detailed information for a custom-made dress or suit.

[0607] Input: A list of custom-made items sent from the server.

[0608] Data processing: Converting proposed items into a display format.

[0609] Output: A list of custom items that will be displayed to the user.

[0610] Step 12:

[0611] User's custom orders

[0612] The user confirms the selected items as a custom order, for example by selecting customization options for size and color.

[0613] Input: The custom item selected by the user.

[0614] Data processing: Processing custom orders.

[0615] Output: Order information.

[0616] Step 13:

[0617] Server production and delivery procedures

[0618] The server receives the order information and handles the manufacturing and delivery procedures, such as placing an order with the manufacturing factory and coordinating with the delivery company.

[0619] Input: User's order information.

[0620] Data calculation: Processing of production and delivery procedures.

[0621] Output: Notification of completion of production and delivery.

[0622] (Application example 2)

[0623] Next, a description will be given of Application Example 2 of Form 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."

[0624] Conventional fashion coordination systems lacked suggestions tailored to the user's emotions and the situation of special occasions, and were unable to fully increase user satisfaction. Furthermore, the lack of a function to directly purchase suggested items within the application fragmented the user's purchasing experience. Furthermore, the inability to suggest custom-made items for special occasions or events made it difficult to meet the diverse needs of users.

[0625] 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.

[0626] In this invention, the server includes means for suggesting fashion coordination based on situation information and weather information input by the user, means for learning user feedback, means for purchasing products similar to the suggested coordination, means for analyzing the user's emotional information, means for suggesting products based on the analyzed emotional information, means for purchasing the suggested products directly within the application, and means for suggesting custom-made items for special occasions or events. This enables suggestions based on the user's emotions and the situation of the special occasion, thereby increasing user satisfaction. Furthermore, the suggested products can be purchased directly within the application, improving the user's purchasing experience. Furthermore, it is possible to suggest custom-made items for special occasions or events, thereby meeting the diverse needs of users.

[0627] "User-entered context information" refers to information about the current situation or environment provided by the user through the application.

[0628] "Weather information" is information about weather conditions such as the current weather and temperature.

[0629] "Means for suggesting fashion coordination" is a function that suggests appropriate combinations of clothing and accessories based on the user's situation and weather information.

[0630] "Means for learning from user feedback" is a function that collects opinions and evaluations provided by users and uses them to improve the accuracy of the system's suggestions.

[0631] "Means for purchasing products similar to the suggested coordination" is a function that allows the user to purchase products similar to the fashion coordination suggested by the system.

[0632] "Means for analyzing user emotional information" refers to a function that analyzes emotions from the text and options entered by the user and identifies those emotions.

[0633] "Means for suggesting products based on analyzed emotional information" is a function that suggests appropriate products based on the user's emotional information.

[0634] "Means for purchasing suggested products directly within the application" refers to a function that allows users to purchase suggested products directly within the application.

[0635] "A means of suggesting custom-made items for special occasions and events" is a function that suggests custom-made items suitable for the user's special occasions and events.

[0636] The system for implementing this invention has the function of suggesting fashion coordination based on situational information and weather information entered by the user, and suggesting products by analyzing the user's emotional information. It also includes the function of allowing suggested products to be purchased directly within the application, and suggesting custom-made items for special occasions or events.

[0637] Hardware and software used

[0638] Hardware: Smartphone

[0639] Software: Python, sentiment analysis library (e.g., TextBlob), product recommendation engine, custom order generation engine, HTTP request library (e.g., requests)

[0640] System configuration

[0641] 1. A method to suggest fashion coordination based on the situation and weather information entered by the user:

[0642] The user enters situational information (e.g., location, type of event) and weather information into the application.

[0643] The server generates an appropriate fashion coordination based on this information.

[0644] 2. Learning from user feedback:

[0645] The user provides feedback on the proposed outfits.

[0646] The server collects this feedback and uses machine learning algorithms to improve the accuracy of its next suggestions.

[0647] 3. How to purchase items similar to the suggested outfit:

[0648] Based on the suggested outfit, a list of similar products is created.

[0649] Users can select products from this list and purchase them directly within the application.

[0650] 4. How to analyze user sentiment:

[0651] Analyze the text entered by the user (e.g., "Today is a special day, so I want a nice dress") using a sentiment analysis library.

[0652] The server determines the user's emotions based on the analysis results.

[0653] 5. Means for suggesting products based on analyzed sentiment information:

[0654] The server then suggests appropriate products based on the identified emotional information.

[0655] For example, if a user types, "I'm feeling a bit down today," the app will suggest relaxing items.

[0656] 6. How to purchase the proposed products directly within the application:

[0657] The user selects the suggested product and completes the purchase within the application.

[0658] The server processes the purchase request and notifies you of the purchase completion.

[0659] 7. How to offer custom-made items for special occasions and events:

[0660] When a user inputs the emotional information "special day," the server analyzes this information and suggests custom-made items suitable for that special day.

[0661] For example, it suggests custom-made dresses and suits tailored to the user's preferences and the occasion of the special occasion.

[0662] Specific examples

[0663] When a user types, "Today is a special day, so I want a beautiful dress," the emotion engine interprets it as a "special day" and suggests a custom-made dress.

[0664] If a user types "I'm feeling a little down today," the emotion engine will interpret this as "depressed" and suggest relaxing items to lift their mood.

[0665] Prompt Sentence Examples

[0666] "How are you feeling today?"

[0667] Please suggest items suitable for special occasions.

[0668] "What products would you recommend for when you're feeling down?"

[0669] In this way, we have created a system that can make suggestions based on the user's emotions and the situation of the special day, thereby increasing user satisfaction.

[0670] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0671] Step 1:

[0672] The user inputs situation information and weather information into the application. The input situation information (e.g., location, type of event) and weather information (e.g., temperature, weather) are sent from the device to the server. The server receives this information and stores it in a database.

[0673] Step 2:

[0674] The server generates a fashion coordination based on the received situational and weather information. Using a generative AI model, it suggests appropriate combinations of clothing and accessories. The generated coordination is sent from the server to the device and displayed to the user.

[0675] Step 3:

[0676] The user provides feedback on the proposed outfits. The feedback is sent from the device to the server, which then stores it in a database to use machine learning algorithms to improve the accuracy of the next suggestions.

[0677] Step 4:

[0678] The server creates a list of similar products based on the proposed outfit. It uses a product recommendation engine to search for similar products in a database and generate the list. The created list is sent from the server to the terminal and displayed to the user.

[0679] Step 5:

[0680] The user selects a product from the list and completes the purchase. The selected product information is sent from the device to the server. The server processes the purchase request and notifies the user that the purchase is complete. A purchase completion notification is sent from the server to the device and displayed to the user.

[0681] Step 6:

[0682] The user inputs emotional information. The input emotional information (e.g., "Today is a special day, so I want a nice dress") is sent from the device to the server. The server uses an emotion analysis library to analyze the emotional information and extract specific emotions.

[0683] Step 7:

[0684] The server then suggests products based on the analyzed emotional information. Using a generative AI model, it suggests appropriate products. The suggested products are then sent from the server to the device and displayed to the user.

[0685] Step 8:

[0686] When a user inputs the emotional information "special day," the server suggests custom-made items suitable for that special day. Using a custom order generation engine, custom-made items are generated that match the user's preferences and the situation of the special day. The generated items are sent from the server to the device and displayed to the user.

[0687] Example 3

[0688] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0689] Conventional fashion coordination systems make suggestions based solely on weather and situational information, without taking the user's emotional state into account, making it difficult to provide coordination that meets the user's psychological needs. Furthermore, they lack a means to effectively learn from user feedback and provide optimal suggestions for each individual user. Furthermore, there are limited ways to order custom-made items based on the suggested coordination.

[0690] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes means for receiving emotional information input by the user, means for analyzing the received emotional information, means for generating a fashion coordination based on the analysis results, means for presenting the generated coordination to the user, means for learning feedback from the user, and means for purchasing products similar to the suggested coordination. This makes it possible to provide appropriate fashion coordination according to the user's emotional state, effectively learn user feedback, and make optimal suggestions for each user. It also makes it easy to order custom-made items based on the suggested coordination.

[0691] "Emotional information entered by the user" is data entered by the user in text format that describes their emotional state.

[0692] "Means for receiving" is a function that allows the server to receive emotion information sent by the user.

[0693] The "analysis means" is a function for analyzing received emotional information and identifying the emotional state of the user.

[0694] The "means for generating fashion coordinates" is a function for creating appropriate fashion coordinates based on the analysis results.

[0695] The "presentation means" is a function for displaying the generated fashion coordination to the user.

[0696] "Means for learning feedback" is a function that collects feedback from users and uses it to improve the accuracy of the system's suggestions.

[0697] "Means for purchasing products" is a function that allows users to purchase products similar to the suggested outfits.

[0698] "Means for ordering custom-made items" is a function that allows users to order items with customized sizes and colors based on suggested outfits.

[0699] This invention is a system that proposes fashion coordination based on a user's emotional information and orders custom-made items. This system includes a series of processes that receive and analyze the user's emotional information and generate fashion coordination based on the results.

[0700] First, the user inputs emotional information into the application using a device such as a smartphone or tablet. For example, they input "I'm tired." This emotional information is sent to the server as text data.

[0701] The server receives the emotional information sent by the user. The received emotional information is then sent to the emotion engine. The emotion engine uses a "natural language understanding engine" that uses natural language processing technology. This engine analyzes the emotional information and identifies the user's emotional state. For example, based on the information that the user is "tired," it can determine that the user needs to relax.

[0702] Next, the server receives the analysis results from the emotion engine. Based on this analysis result, the server sends a prompt sentence to the generative AI model. The generative AI model used is the "generative AI engine." An example of a prompt sentence is, "The user feels tired. Please suggest a casual outfit that will help them relax."

[0703] The generative AI model analyzes the prompt and generates an appropriate fashion coordination, such as suggesting a combination of loose-fitting sweatshirts and soft pants. This coordinated coordination is then sent to the user's device via the server.

[0704] Users can check the suggested outfits on the app. If they find an item they like, they can customize the size and color to order it as a custom order. For example, if a pair of red pumps is suggested, the user can order the same design in size 24cm and in blue.

[0705] This system provides appropriate fashion coordination according to the user's emotional state and can effectively learn from user feedback to make optimal suggestions for each individual user. It also makes it easy to order custom-made items based on the suggested coordination. The flow of the identification process in Example 3 will be described with reference to FIG. 21.

[0706] Step 1:

[0707] The user inputs emotion information. The user opens the application on their smartphone or tablet and inputs "tired" on the emotion input screen. This input is sent to the server as text data.

[0708] Step 2:

[0709] The server receives the emotion information. The server receives the user's input in real time and stores it in a database. The input data is text data such as "I'm tired."

[0710] Step 3:

[0711] The server sends emotion information to the emotion engine. The server sends the emotion information "tired" to the emotion engine via API. A "natural language understanding engine" is used as the emotion engine.

[0712] Step 4:

[0713] The emotion engine analyzes the emotion information. Using natural language processing technology, the emotion engine analyzes the emotion "tired" and determines that the user needs to relax. The analysis result is the data "Needs relaxation."

[0714] Step 5:

[0715] The server receives the analysis result. The server receives the analysis result from the emotion engine and proceeds to the next step. The received data is the analysis result that "you need to relax."

[0716] Step 6:

[0717] The server sends a prompt to the generative AI model. The server generates a prompt based on the analysis results and sends it to the generative AI model. An example of a prompt is, "The user feels tired. Please suggest a casual outfit that will help them relax."

[0718] Step 7:

[0719] The generative AI model generates an outfit. The generative AI model uses a "generative AI engine" to analyze the prompt and generate an appropriate fashion outfit. The generated outfit is a combination of loose-fitting sweatshirts and pants made of soft material.

[0720] Step 8:

[0721] The server receives the generated outfit. The server receives the outfit from the generative AI model and stores it in a database. The received data is an outfit that combines a loose sweatshirt with pants made of soft material.

[0722] Step 9:

[0723] The server sends the outfit to the user's device. The server then sends the created outfit to the user's device and notifies the user through the app's notification function. The sent data is an outfit consisting of a "combination of loose-fitting sweatshirts and pants made of soft material."

[0724] Step 10:

[0725] The user checks the outfits and orders custom-made items. The user opens the app and checks the suggested outfits. If they find an item they like, they can customize the size and color and order it as a custom-made item. For example, they can select red pumps, change the size to 24cm, and change the color to blue.

[0726] (Application example 3)

[0727] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0728] Conventional fashion coordination systems make suggestions based on the user's situation and weather information, but they cannot take into account the user's emotional state, making it difficult to increase the user's psychological satisfaction. Furthermore, there are limited ways to order custom-made items based on the suggested outfits, which makes it difficult to fully meet the individual needs of users.

[0729] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the proposed coordination, a means for inputting the user's emotional information, a means for analyzing the user's emotions using an emotion engine, and a means for suggesting a fashion coordination based on the emotions using a generative AI model. This makes it possible to suggest a fashion coordination that takes the user's emotional state into consideration, thereby increasing the user's psychological satisfaction. In addition, by providing a means for ordering custom-made items based on the suggested coordination, the individual needs of the user can be met.

[0730] "User-inputted situation information" refers to information about the current situation or environment that the user inputs.

[0731] "Weather information" is information about weather conditions such as the current weather and temperature.

[0732] The "means for suggesting fashion coordination" is a function that suggests appropriate fashion combinations based on input information.

[0733] "Means for learning from user feedback" is a function that analyzes feedback provided by users and improves the accuracy of the system's suggestions.

[0734] The "means for purchasing products similar to the suggested coordination" is a function that allows the user to purchase products similar to the suggested fashion coordination.

[0735] "Means for inputting user's emotional information" is a function that allows the user to input their own emotional state into the system.

[0736] The "means for analyzing a user's emotions using an emotion engine" is a function for analyzing input emotion information and identifying the user's emotional state.

[0737] "Means for proposing emotion-based fashion coordination using a generative AI model" is a function for generating appropriate fashion coordination based on analyzed emotional information.

[0738] "Means for ordering custom-made items" is a function that allows users to order customized items based on suggested fashion coordination.

[0739] The system for implementing this invention proposes fashion coordination based on situation information, weather information, and emotional information input by the user, and also allows the user to order custom-made items. A specific embodiment of this system will be described below.

[0740] System Configuration

[0741] The system includes a user device, a server, an emotion engine, and a generative AI model. The user device is a device such as a smartphone or tablet, and the server is located on the cloud.

[0742] Hardware and software used

[0743] User devices: smartphones, tablets

[0744] Server: Cloud server

[0745] Emotion Engine: Emotion Analysis API

[0746] Generative AI model: OpenAI API

[0747] Data processing and calculation

[0748] 1. User input:

[0749] Users use their smartphones or tablets to input situational information, weather information, and emotional information, such as "It's raining today, and I'm a little tired."

[0750] 2. Emotion analysis:

[0751] The server analyzes the user's emotional information using an emotion engine, which identifies the user's emotional state from the input text.

[0752] 3. Fashion Coordination Generation:

[0753] The server uses a generative AI model to suggest fashion coordination based on emotions. The generative AI model is input with the following prompt:

[0754] "The user is feeling fatigued. Please suggest a casual fashion coordination that will help them relax."

[0755] 4. Show suggestions:

[0756] The suggested fashion coordinations are displayed on the user's device, and the user can check the suggested coordinations and select the items they like.

[0757] 5. Custom Orders:

[0758] The user can customize the size and color of the selected item to place a custom order. The server receives the user's customization information and processes the order.

[0759] Specific examples

[0760] For example, if a user inputs "It's raining today and I'm a little tired," the emotion engine will analyze "fatigue" as the dominant emotion. The generative AI model will then be prompted with the following prompt: "The user is feeling tired. Please suggest a casual fashion outfit that will help them relax." The generated outfits will then be displayed to the user. The user can then select their favorite items from the suggested outfits and customize the size and color to place a custom order.

[0761] In this way, it becomes possible to suggest fashion coordination that takes into account the user's emotional state and to order custom-made items.

[0762] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0763] Step 1:

[0764] Users input situational information, weather information, and emotional information using a smartphone or tablet. For example, they input information such as, "It's raining today, and I'm a little tired." The input information is then sent from the user device to the server.

[0765] Step 2:

[0766] The server sends the received emotion information to the emotion engine, which analyzes the user's emotional state from the input text and identifies the dominant emotion. For example, the emotion "fatigue" may be identified. The analysis results are then sent back to the server.

[0767] Step 3:

[0768] The server inputs a prompt sentence into the generative AI model. The prompt sentence is generated based on the analyzed emotional information. For example, a prompt sentence such as "The user is feeling tired. Please suggest a relaxing casual fashion coordination" is input into the generative AI model.

[0769] Step 4:

[0770] The generative AI model generates a fashion coordination based on the prompt sentence. The generated coordination is sent back to the server. For example, it might suggest "a combination of loose-fitting sweatshirts and pants made of soft material."

[0771] Step 5:

[0772] The server transmits the generated fashion coordinates to the user terminal, which displays the proposed coordinates to the user. The user can then review the proposed coordinates and select items that they like.

[0773] Step 6:

[0774] The user can customize the size and color of the selected item to place a custom order. The customization information is sent from the user terminal to the server.

[0775] Step 7:

[0776] The server processes the custom order based on the received customization information. Once the order processing is complete, a confirmation is sent to the user's terminal. The user can confirm that the order has been successfully received.

[0777] 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.

[0778] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0779] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0780] 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.

[0781] [Second embodiment]

[0782] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0783] 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.

[0784] 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).

[0785] 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.

[0786] 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.

[0787] 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).

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] In the smart glasses 214, 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.

[0793] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0794] "Example 1"

[0795] In one embodiment of the present invention, when a user inputs information about the situation, such as "date," and weather information, such as "sunny," into the app, a casual yet stylish outfit is suggested based on this information. A suggested outfit might be, for example, a white blouse, a denim skirt, and red pumps. Furthermore, if the user inputs feedback such as "it was hot," the app learns to suggest cooler outfits next time.

[0796] "Example 2"

[0797] Furthermore, the app offers a feature that allows users to purchase items similar to the suggested outfits directly within the app. For example, multiple items similar to the suggested white blouse will be displayed, allowing users to select and purchase the item they like.

[0798] "Example 3"

[0799] There is also a way to order custom items based on the suggested outfit. For example, if a user likes the red pumps included in the suggested outfit, they can order custom pumps of the same design but in a different size and color.

[0800] The processing flow of each embodiment will be described below.

[0801] "Example 1"

[0802] Step 1: The user enters the situation information "date" and the weather information "sunny" into the app.

[0803] Step 2: Based on this information, the system suggests a casual yet stylish outfit, such as a white blouse with a denim skirt and red pumps.

[0804] Step 3: The user enters feedback such as "It was hot."

[0805] Step 4: The system learns from this feedback and will suggest cooler outfits next time.

[0806] "Example 2"

[0807] Step 1: The system displays products similar to the outfits it suggests.

[0808] Step 2: The user selects the product they want from the displayed products.

[0809] Step 3: The user purchases the selected item directly within the app.

[0810] "Example 3"

[0811] Step 1: Provide a way to order custom-made items based on the outfits suggested by the system.

[0812] Step 2: If the user likes an item included in the suggested outfit, they can order a custom-made item based on the design of that item.

[0813] Step 3: The user customizes the size and color of the made-to-order item and confirms the order.

[0814] Example 1

[0815] Next, a description will be given of Example 1 of Form 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."

[0816] Conventional fashion coordination suggestion systems have difficulty proposing appropriate outfits based on the user's situation and weather information, and it is also difficult to effectively learn from user feedback and reflect it in future suggestions. Furthermore, there is a lack of a way to purchase products based on the suggested outfits, and a lack of advanced outfit generation using generative AI models.

[0817] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for sending a prompt message to the generative AI model, and a means for receiving coordination from the generative AI model. This makes it possible to suggest appropriate coordination according to the user's situation and weather, improve the suggestions based on user feedback, and generate advanced coordination using the generative AI model.

[0818] "User" refers to an individual who uses the system to receive fashion coordination suggestions.

[0819] "Situation information" refers to information about a specific situation entered by the user, such as "date" or "work."

[0820] "Weather information" refers to information about the current weather that is input by the user, such as "sunny" or "rainy."

[0821] "Fashion coordination" refers to a combination of clothing and accessories suggested based on the user's situational and weather information.

[0822] "Feedback" refers to the evaluations and impressions provided by users regarding the suggested outfits.

[0823] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate outfits based on user input.

[0824] "Prompt sentence" refers to an instruction sentence sent to a generative AI model to generate a coordinate.

[0825] "Server" refers to the computer system that receives user input, sends prompts to the generative AI model, and provides the generated coordinates to the user.

[0826] "Terminal" refers to the device used by a User to enter information and review suggested outfits.

[0827] "Product" refers to items such as clothing and accessories included in the proposed outfit.

[0828] "Made-to-order items" refer to clothing and accessories that are made specifically to a user's request.

[0829] MODE FOR CARRYING OUT THE INVENTION

[0830] This invention is a system that proposes fashion coordination based on situation information and weather information input by a user, learns feedback from the user, and reflects it in future proposals. A specific embodiment of this system will be described below.

[0831] Hardware and software used

[0832] This system is implemented using the following hardware and software:

[0833] Server: Receives user input, sends prompts to the generative AI model, and provides the generated coordinates to the user. The server is developed using Python and TensorFlow as the machine learning model.

[0834] Device: The device used by the user to enter information and view suggested outfits, such as a smartphone or tablet.

[0835] Generative AI model: An algorithm that generates outfits based on user input. For example, OpenAI's GPT-3.

[0836] Program processing

[0837] The user opens the app and enters the situation information "date" and the weather information "sunny." The device sends the information entered by the user to the server. Specifically, it sends the data using an HTTP POST request.

[0838] The server generates a prompt to send to the generative AI model based on the received situational and weather information. For example, it generates the following prompt:

[0839] Based on the situation information "date" and the weather information "sunny," please suggest a casual yet stylish outfit.

[0840] The server sends this prompt to the generative AI model, which then generates an outfit based on the prompt. For example, it might generate a white blouse, denim skirt, and red pumps.

[0841] The server sends the outfit information received from the generative AI model to the device. Specifically, it returns the outfit information as an HTTP response. The user checks the outfit displayed on the device and enters feedback such as "it was hot." The device then sends the feedback entered by the user to the server. Specifically, it sends the feedback data using an HTTP POST request.

[0842] The server retrains the generative AI model based on the received feedback, so that from the next time onwards, it will suggest outfits that reflect the user's feedback.

[0843] Specific examples

[0844] For example, if a user inputs "date" and "sunny" and the suggested outfit is "white blouse, denim skirt, red pumps," if the user provides feedback that "it was hot," the next time the system will suggest a cooler outfit such as "white blouse, linen shorts, sandals."

[0845] In this way, it becomes possible to suggest appropriate outfits based on the user's situation and weather, improve suggestions based on user feedback, and generate advanced outfits using generative AI models.

[0846] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0847] Step 1:

[0848] The user enters the situation information and weather information. The user opens the app and enters the situation information "date" and the weather information "sunny." The entered information is saved on the device.

[0849] Step 2:

[0850] The device sends the input information to the server. The device sends the situation information and weather information entered by the user to the server using an HTTP POST request. The input data is sent in JSON format.

[0851] Step 3:

[0852] The server sends a prompt to the generative AI model. Based on the received situational and weather information, the server generates a prompt to send to the generative AI model. For example, it generates the following prompt:

[0853] Based on the situation information "date" and the weather information "sunny," please suggest a casual yet stylish outfit.

[0854] The generated prompt sentence is sent to a generative AI model.

[0855] Step 4:

[0856] The generative AI model generates an outfit based on the received prompt. For example, it might generate an outfit such as a white blouse, denim skirt, and red pumps. The generated outfit is returned to the server.

[0857] Step 5:

[0858] The server sends the generated coordinates to the device. The server sends the coordinates received from the generative AI model to the device as an HTTP response. The output data is sent in JSON format.

[0859] Step 6:

[0860] The user checks the outfit and inputs feedback. The user checks the outfit displayed on the device and inputs feedback such as "it was hot." The input feedback is saved on the device.

[0861] Step 7:

[0862] The device sends the feedback to the server. The device sends the feedback entered by the user to the server using an HTTP POST request. The input data is sent in JSON format.

[0863] Step 8:

[0864] The server trains the model based on the feedback. The server then retrains the generative AI model based on the received feedback. This allows the server to suggest outfits that reflect the user's feedback from the next time.

[0865] (Application example 1)

[0866] Next, a description will be given of Application Example 1 of Form 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."

[0867] Conventional fashion coordination suggestion systems have difficulty proposing appropriate outfits based on the user's situation and weather information, and are unable to effectively learn from the user's feedback and reflect it in future suggestions. Furthermore, there is a lack of means for users to purchase items based on the suggested outfits, resulting in low user convenience.

[0868] 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.

[0869] In this invention, the server includes a means for suggesting fashion coordination based on situational information and weather information input by the user, a means for learning user feedback, a means for purchasing products similar to the suggested coordination, a means for suggesting coordination using a generative AI model, and a means for generating prompt sentences. This makes it possible to suggest optimal coordination based on the user's situation and weather, and to learn user feedback and reflect it in future suggestions. Furthermore, by providing a means for purchasing products based on the suggested coordination, user convenience can be improved.

[0870] A "user" is an individual who uses the system to receive fashion coordination suggestions.

[0871] "Context information" is information entered by a user about a particular situation or event.

[0872] "Weather information" is information about the current weather and weather conditions entered by the user.

[0873] "Fashion coordination" is the combination of clothing and accessories appropriate for a particular situation or weather.

[0874] "Feedback" refers to the impressions and opinions that users provide regarding the proposed outfits.

[0875] "Learners" are methods and techniques for improving the next offering based on user feedback.

[0876] A "generative AI model" is an algorithm that uses artificial intelligence to generate outfits based on user input.

[0877] A "prompt sentence" is an instruction sentence input to a generative AI model.

[0878] The "means for purchasing products" refers to a method or system for purchasing related products based on the proposed coordination.

[0879] The system for implementing this invention proposes fashion coordination based on situational and weather information entered by the user, learns from the user's feedback and reflects it in future proposals, and also provides a means for purchasing products based on the proposed coordination.

[0880] Hardware and software used

[0881] Hardware: Smartphones, servers

[0882] Software: Python, Requests library, Scikit-learn, OpenAI API

[0883] System configuration

[0884] 1. User device: The user uses a smartphone to input situation information (e.g., "date") and weather information (e.g., "sunny").

[0885] 2. Server: The server receives the information sent by the user and uses a generative AI model to suggest appropriate fashion coordination.

[0886] 3. Generative AI model: The server inputs a prompt statement into the generative AI model to generate coordination suggestions.

[0887] 4. Feedback learning: When a user provides feedback on a suggested outfit (e.g., "It was hot"), the server learns this feedback and reflects it in the next suggestion.

[0888] 5. Product Purchasing Method: Allows users to purchase related products based on the suggested outfits.

[0889] Data processing and calculation

[0890] 1. Data acquisition: The server acquires situational information and weather information from the user's device.

[0891] 2. Prompt generation: The server generates a prompt to be input into the generative AI model based on the acquired information.

[0892] Example: "Situation: Date, Weather: Please suggest an outfit suitable for sunny weather."

[0893] 3. Coordination proposal: The generative AI model generates a coordination proposal based on the prompt sentence and returns it to the server.

[0894] 4. Feedback learning: The server receives feedback from the user and uses Scikit-learn to update the model to improve the next suggestion.

[0895] 5. Product Purchase: The server generates a purchase link for related products based on the suggested coordination and provides it to the user.

[0896] Specific examples

[0897] Situation: Dating

[0898] Weather: Sunny

[0899] Suggested outfit: White blouse, denim skirt, red pumps

[0900] Feedback: It was hot

[0901] In this way, the system can suggest the best outfits for the user's situation and weather, learn from the user's feedback, and reflect it in future suggestions. Also, by providing a means to purchase products based on the suggested outfits, the system can improve user convenience.

[0902] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0903] Step 1:

[0904] The user uses a smartphone device to input situation information (e.g., "date") and weather information (e.g., "sunny"). The input information is sent from the device to the server. The input data is situation information and weather information.

[0905] Step 2:

[0906] The server receives the situational information and weather information sent by the user. Based on the received data, it generates a prompt sentence to input into the generative AI model. Specifically, it combines the situational information and weather information to create the following prompt sentence:

[0907] Example: "Situation: Date, Weather: Please suggest an outfit suitable for sunny weather."

[0908] Step 3:

[0909] The server sends the generated prompt to the generative AI model, which generates a fashion outfit based on the prompt. The output of the generative AI model is a suggested outfit.

[0910] Step 4:

[0911] The server receives the coordinates returned by the generative AI model and sends them to the user's device. The user's device displays the received coordinates to the user. The displayed data is the suggested coordinates.

[0912] Step 5:

[0913] The user inputs feedback for the proposed coordinates. The feedback is sent from the terminal to the server. The input data is the user's feedback.

[0914] Step 6:

[0915] The server receives the feedback sent by the user and uses Scikit-learn to update the model to improve the next suggestion. Specifically, the feedback data is used as training data to update the linear regression model. The updated model is reflected in the next suggestion.

[0916] Step 7:

[0917] The server generates a purchase link for the related product based on the proposed coordination. The generated purchase link is sent to the user terminal and displayed to the user. The displayed data is the purchase link for the related product.

[0918] In this way, the system can suggest the best outfits for the user's situation and weather, learn from the user's feedback, and reflect it in future suggestions. Also, by providing a means to purchase products based on the suggested outfits, the system can improve user convenience.

[0919] Example 2

[0920] Next, a description will be given of Example 2 of Form 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."

[0921] Conventional fashion coordination systems have difficulty in proposing items that fully reflect the user's preferences and past purchase history, which has prevented them from increasing user satisfaction. Furthermore, there is a lack of easy ways to purchase items similar to the suggested outfits, which has prevented them from effectively stimulating users' purchasing desire.

[0922] 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 a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for inputting a prompt sentence to the generative AI model based on the user's past purchase history and preferences, a means for the generative AI model to generate a coordination, a means for transmitting the generated coordination to the user's terminal, and a means for the user to select and purchase products. This makes it possible to suggest optimal coordination that reflects the user's preferences and past purchase history, and allows the user to easily purchase the suggested products.

[0923] "User" refers to an individual who uses the system to receive fashion coordination suggestions.

[0924] "Situation information" refers to information about the current situation or event entered by the user.

[0925] "Weather information" refers to information about the weather at the user's current location or a specified location.

[0926] "Fashion coordination" refers to the combination of clothing and accessories suggested based on the user's situation and weather information.

[0927] "Feedback" refers to the evaluations and opinions that users give about the suggested outfits.

[0928] A "generative AI model" refers to an artificial intelligence model that generates optimal outfits based on user data.

[0929] A "prompt sentence" refers to an instruction sentence input to a generative AI model.

[0930] "Purchase history" refers to a record of products a user has purchased in the past.

[0931] "Preferences" refers to personal preferences such as a user's favorite styles, brands, or colors.

[0932] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a user uses to access the system.

[0933] "Product" refers to items such as clothing and accessories included in the suggested outfit.

[0934] "Purchase Method" means the method by which a User can purchase a suggested Product directly within the App.

[0935] This invention is a system for suggesting fashion coordination based on situational information and weather information input by a user, learning from the user's feedback, and purchasing products similar to the suggested coordination. Specific embodiments of this system are described below.

[0936] First, a user launches the app on a device such as a smartphone or tablet. The app displays the initial screen and confirms the user's login information. Once the user logs in, the server retrieves the user's past purchase history and preference data from a database. This data includes the type, color, size, and brand of the products purchased.

[0937] Next, the server inputs a prompt to the generative AI model based on the acquired user data. For example, the server sends a prompt such as, "Please suggest products similar to the white blouse based on the user's past purchase history and preferences." The generative AI model then generates the optimal outfit for the user based on this prompt. The generated outfit includes products similar to the white blouse.

[0938] The generated outfit is sent from the server to the user's device. The device displays the outfit to the user. The user can then review the suggested items and view detailed information. The user selects the preferred item from the suggested items and completes the purchase. Payment information and delivery address are entered to complete the purchase directly within the app.

[0939] As a concrete example, consider the case where a user is offered a "white blouse." The server displays multiple products similar to the white blouse based on the user's past purchase history and preferences. The user can then select and purchase a "white blouse with lace" or a "simple white blouse," etc.

[0940] Examples of prompts to be input to a generative AI model include:

[0941] Example prompt sentence:

[0942] Suggest products similar to white blouses based on the user's past purchase history and preferences.

[0943] By inputting this prompt into a generative AI model, the most suitable product is suggested to the user.

[0944] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0945] Step 1:

[0946] A user launches an app. The user launches the app on a device such as a smartphone or tablet, and the login screen appears. The user enters their login information, and if authentication is successful, the app's home screen appears. The input is the user's login information, and the output is the authenticated user information.

[0947] Step 2:

[0948] The server retrieves user data. Based on the authenticated user information, the server retrieves the user's past purchase history and preference data from a database. This data includes the type, color, size, and brand of purchased products. The input is authenticated user information, and the output is the user's past purchase history and preference data.

[0949] Step 3:

[0950] The server inputs a prompt to the generative AI model. The server inputs the prompt to the generative AI model based on the acquired user data. For example, a prompt such as "Please suggest products similar to the white blouse based on the user's past purchase history and preferences" is sent to the generative AI model. The input is the user's past purchase history and preference data, and the output is a prompt to the generative AI model.

[0951] Step 4:

[0952] The generative AI model generates an outfit. The generative AI model generates the optimal outfit for the user based on the input prompt. The generated outfit includes items similar to the white blouse. The input is the prompt, and the output is the generated outfit.

[0953] Step 5:

[0954] The server sends the generated outfit to the device. The server then sends the outfit received from the generative AI model to the user's device. The sent data includes product images, prices, detailed information, etc. The input is the generated outfit, and the output is the outfit data sent to the user's device.

[0955] Step 6:

[0956] The terminal displays the coordinated outfits to the user. The terminal displays the received coordinated outfits to the user. The user can check the suggested items and view detailed information. The input is the coordinated outfit data sent from the server, and the output is the coordinated outfit information displayed to the user.

[0957] Step 7:

[0958] The user selects and purchases a product. The user selects the preferred product from the suggested products and completes the purchase. Payment information and delivery address are entered to complete the purchase directly within the app. The input is the user's selected product information and payment information, and the output is confirmation of purchase completion.

[0959] (Application example 2)

[0960] Next, a description will be given of Application Example 2 of Form 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."

[0961] Conventional fashion coordination suggestion systems can suggest outfits based on the user's situation and weather information, but they lack the ability to suggest similar fashion items based on images taken by the user. They also lack the ability to display multiple products similar to the suggested items so the user can select and purchase them, or the ability to display detailed product information and reviews. This makes it difficult for users to easily find and purchase products that match their preferences.

[0962] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for suggesting fashion coordination based on situation information and weather information input by the user, means for learning feedback from the user, means for purchasing products similar to the suggested coordination, means for suggesting similar fashion items based on images taken by the user, means for displaying multiple products similar to the suggested items so that the user can select and purchase them, and means for displaying detailed product information and reviews. This allows the user to easily find and purchase products that suit their preferences.

[0963] "User-entered contextual information" refers to information provided by the user, such as current activities, events, and locations.

[0964] "Weather information" refers to meteorological data such as the current weather, temperature, and humidity.

[0965] "Means for suggesting fashion coordination" is a function that suggests appropriate clothing combinations based on the user's situational information and weather information.

[0966] "Means for learning from user feedback" is a function that collects opinions and evaluations provided by users and uses them to improve the accuracy of the system's suggestions.

[0967] "Means for purchasing products similar to the suggested coordination" is a function that displays products similar to the suggested fashion coordination and allows the user to purchase them.

[0968] "A means for suggesting similar fashion items based on images taken by the user" is a function that analyzes photos taken by the user and suggests similar fashion items.

[0969] "A means of displaying multiple products similar to the suggested item and allowing the user to select and purchase" is a function that displays multiple products similar to the suggested item and allows the user to select and purchase from among them.

[0970] "Means for displaying detailed product information and reviews" refers to a function that displays detailed product information and ratings and reviews from other users.

[0971] The system for implementing this invention has the functions of suggesting fashion coordination based on situational and weather information entered by the user and learning from user feedback. It also provides a means for purchasing products similar to the suggested coordination and has the functions of suggesting similar fashion items based on images taken by the user. It also has the functions of displaying multiple products similar to the suggested items so that the user can select and purchase them, and displaying detailed product information and reviews.

[0972] System program and processing description

[0973] Hardware

[0974] Smartphone (iOS or Android)

[0975] server

[0976] software

[0977] Python

[0978] TensorFlow

[0979] Keras

[0980] VGG16 model (pre-trained)

[0981] Data processing and calculation

[0982] The server receives situational and weather information entered by the user on their smartphone and suggests fashion coordination based on that information. When the user uploads a photo they have taken to the server, the server analyzes the image and suggests similar fashion items. Specifically, it uses the VGG16 model to extract features from the image and predict similar items.

[0983] The server displays multiple products similar to the suggested item and allows the user to select and purchase from them. It also displays detailed product information and reviews from other users, allowing users to easily find and purchase products that suit their preferences.

[0984] Specific examples

[0985] Users take a photo of a white blouse with their smartphone and upload it to the server via the app. The server analyzes the image using the VGG16 model and suggests several similar white blouses. Users can then choose their favorite from the suggested blouses and purchase them after checking detailed information and reviews.

[0986] Prompt Sentence Examples

[0987] "Upload a photo of a white blouse and let our AI suggest similar products."

[0988] In this way, users can easily find and purchase products that suit their tastes.

[0989] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0990] Step 1:

[0991] The user inputs situational and weather information using a smartphone. The input information is sent to the server, which receives the information and stores it in a database. The input data includes the user's current activities and events, location, weather, temperature, humidity, etc.

[0992] Step 2:

[0993] The server then proposes fashion coordination based on the saved situational and weather information. The server then generates appropriate outfit combinations using a pre-trained model. The coordinated outfits are then sent to the user's smartphone and displayed.

[0994] Step 3:

[0995] The user provides feedback on the suggested outfits. The feedback is based on the user's preferences and experience. The server receives this feedback and stores it in a database. The feedback data is used to improve the accuracy of the next suggestion.

[0996] Step 4:

[0997] Users take images with their smartphones and upload them to the server via the app. The server receives the uploaded images and performs image analysis. Specifically, it uses the VGG16 model to extract features from the images.

[0998] Step 5:

[0999] The server then suggests similar fashion items based on the extracted features. The suggested items are sent to the user's smartphone and displayed. The user can then confirm the suggested items.

[1000] Step 6:

[1001] The server displays multiple products similar to the suggested item, including searching for similar products in a database and sending them to the user's smartphone. The user can then select the product they like best.

[1002] Step 7:

[1003] The server displays detailed information and reviews from other users about the product selected by the user. Detailed information includes the product's material, size, price, etc. Reviews include ratings and comments from other users. The user uses this information to purchase the product.

[1004] Step 8:

[1005] If the user decides to make a purchase, the server processes the purchase, which includes verifying payment information, entering shipping details, etc. Once the purchase is complete, the server sends a confirmation message to the user.

[1006] In this way, users can easily find and purchase products that suit their preferences.

[1007] Example 3

[1008] Next, a description will be given of Example 3 of Form Example 3. 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."

[1009] Conventional fashion coordination systems have difficulty making suggestions that match a user's preferences and physical experience, and lack the functionality to customize and order suggested items. As a result, they are unable to provide coordination that satisfies users, and the user experience is not improved.

[1010] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1011] In this invention, the server includes means for proposing fashion coordination based on situational information and weather information input by the user, means for learning feedback from the user, means for purchasing products similar to the proposed coordination, means for receiving a prompt input by the user and generating a coordination using a generative AI model, means for the user to customize and order items based on the proposed coordination, and means for sending instructions to a manufacturing system based on the customization information. This makes it possible to propose coordination that suits the user's preferences and physical sensations, and to order further customized items.

[1012] "User" refers to an individual who uses the system to receive fashion coordination suggestions.

[1013] "Status information" refers to information about an event or situation that is entered by the user.

[1014] "Weather Information" means information regarding weather conditions at a User's location or a specified location.

[1015] "Fashion coordination" refers to a style proposed by combining multiple fashion items.

[1016] "Feedback" refers to the evaluations and opinions that users give about the suggested outfits.

[1017] A "generative AI model" refers to an algorithm that uses artificial intelligence to generate outfits based on user input.

[1018] "Prompt" refers to a textual request that a user enters into a generative AI model.

[1019] "Customization" refers to the act of a user changing the size, color, etc. of a suggested item.

[1020] "Manufacturing system" refers to the machines and processes that produce made-to-order items based on customization information.

[1021] "Means of suggestion" refers to the function of generating optimal fashion coordination based on information input by the user.

[1022] "Means of learning" refers to the function of collecting feedback from users and reflecting it in future suggestions.

[1023] "Means for purchasing" refers to the function for purchasing the items included in the proposed coordination.

[1024] "Means for ordering" refers to the functionality that allows users to order customised items on a made-to-order basis.

[1025] The "means for transmitting instructions" refers to a function for transmitting customization information to the manufacturing system.

[1026] This invention is a system that proposes fashion coordination based on situational information and weather information entered by a user, learns feedback from the user, and orders custom-made items based on the proposed coordination. Specific embodiments of this system are described below.

[1027] First, the user inputs a prompt using the device. For example, the prompt might be, "Please suggest an outfit suitable for a casual date." The device then sends this prompt to the server. The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate an outfit that takes into account the user's preferences and past purchase history.

[1028] The generated outfit is sent from the server to the device, and the user can review the suggested outfit. For example, a white T-shirt, denim jacket, black skinny jeans, and red pumps are suggested. The user can select their favorite items and further customize them. For example, they can change the size of the red pumps to 24cm and the color to blue.

[1029] Once the user has completed the customization, the terminal sends the customization information to the server, which then sends instructions to the manufacturing system to create the custom-made item. The manufacturing system then produces the customized item and delivers it to the address specified by the user upon completion.

[1030] This system suggests outfits that suit the user's tastes and preferences, and also allows the user to order customized items, providing a more satisfying fashion experience for the user.

[1031] Specific hardware includes user devices (such as smartphones and tablets), servers, and manufacturing systems, while software includes generative AI models (such as OpenAI's GPT-4), communication protocols (HTTPS), and applications that provide user interfaces.

[1032] This system allows users to easily find fashion items that suit their tastes, customize them, and place an order. The flow of the specification process in the third embodiment will be described with reference to FIG.

[1033] Step 1:

[1034] The user enters a prompt statement.

[1035] The user uses the device interface to input a prompt about the desired outfit. For example, the user might input, "Please suggest an outfit suitable for a casual date." The input prompt becomes the input data for the device.

[1036] Step 2:

[1037] The terminal sends the prompt to the server.

[1038] The terminal sends the prompt text entered by the user to the server using the HTTPS protocol. The input data is the prompt text, and the output data is the prompt text sent to the server.

[1039] Step 3:

[1040] The server generates coordinates using a generative AI model.

[1041] The server inputs the received prompt into a generative AI model (e.g., OpenAI's GPT-4) to generate an outfit that takes into account the user's preferences and past purchase history. The input data is the prompt and the user's history data, and the output data is the generated outfit.

[1042] Step 4:

[1043] The server transmits the generated coordinates to the terminal.

[1044] The server sends the generated coordinates to the terminal in JSON format. The input data is the generated coordinates, and the output data is the coordinates sent to the terminal.

[1045] Step 5:

[1046] The user checks the suggested outfits and selects items.

[1047] The user checks the outfits displayed on the device screen and selects the items they like. For example, they tap red pumps to select them. The input data is the suggested outfit, and the output data is the selected items.

[1048] Step 6:

[1049] Customize and order the items the user selects.

[1050] The user customizes the size and color of the selected item. For example, they change the size of a pair of red pumps to 24cm and the color to blue, and then tap the "Order" button. The input data are the selected item and customization information, and the output data is the customized order information.

[1051] Step 7:

[1052] The terminal transmits the customization information to the server.

[1053] The terminal sends the user-customized information to the server in JSON format, where the input data is the customized order information and the output data is the customized information sent to the server.

[1054] Step 8:

[1055] The server sends instructions to the manufacturing system.

[1056] The server sends instructions to the manufacturing system to manufacture the custom-made item based on the received customization information. The input data is the customization information, and the output data is the instructions sent to the manufacturing system.

[1057] Step 9:

[1058] A manufacturing system produces and delivers custom-made items to users.

[1059] The manufacturing system follows instructions from the server to manufacture customized items. Once manufacturing is complete, the items are delivered to an address specified by the user. The input data are manufacturing instructions, and the output data are the manufactured items.

[1060] (Application example 3)

[1061] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1062] Conventional fashion coordination systems have problems in that they do not adequately provide suggestions based on the user's preferences, and users cannot actually try on the suggested outfits, resulting in low user satisfaction. Furthermore, when ordering custom-made items, it is difficult for users to customize them to suit their preferences.

[1063] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1064] In this invention, the server includes means for suggesting fashion coordination based on situational information and weather information input by the user, means for learning from user feedback, means for purchasing products similar to the suggested coordination, means for suggesting coordination based on the user's preferences using a generative AI model, means for providing a virtual try-on function that overlays items on the user's image, and means for ordering custom-made items. This allows for coordination suggestions based on the user's preferences, allows the user to actually try on the outfits through the virtual try-on function, and further allows the user to easily customize and order custom-made items.

[1065] "User-inputted situation information" refers to information about the current situation or environment that the user provides to the system, such as the type of event, location, and time of day.

[1066] "Weather information" refers to information about current weather conditions such as temperature, humidity, etc. This information can be used to suggest appropriate fashion coordination.

[1067] "Means for suggesting fashion coordination" is a function that suggests appropriate combinations of clothing and accessories based on situational and weather information entered by the user.

[1068] "Means for learning from user feedback" is a function that collects opinions and evaluations provided by users and uses them to improve the accuracy of the system's suggestions.

[1069] "Means for purchasing products similar to the suggested coordination" is a function that provides products that the user can actually purchase based on the fashion coordination suggested by the system.

[1070] A "generative AI model" is an algorithm that uses artificial intelligence to learn a user's preferences and tendencies and then generates optimal outfits based on that information.

[1071] The "virtual try-on feature" overlays suggested items onto the user's image, making it appear as if the user is actually trying them on.

[1072] "Means for ordering custom-made items" refers to a feature that allows users to customize suggested items and order them by specifying size, color, etc.

[1073] A system for implementing this invention includes means for suggesting fashion coordination based on situational and weather information input by a user, learning from user feedback, purchasing products similar to the suggested coordination, using a generative AI model to suggest coordination based on the user's preferences, providing a virtual try-on function that overlays items on the user's image, and ordering custom-made items.

[1074] Hardware and software used

[1075] Hardware: Smartphone, head-mounted display

[1076] Software: OpenAI API, OpenCV

[1077] Data processing and calculation

[1078] Coordination suggestions using generative AI models

[1079] The server uses a generative AI model to suggest outfits based on the user's preferences. The user's preferences and past feedback are input as prompts, and the AI ​​model generates the optimal outfit.

[1080] Example prompt sentence:

[1081] Suggest outfits based on the user's preferences: casual and simple style

[1082] Virtual try-on feature

[1083] The device uses OpenCV to overlay suggested items onto the user's image, synthesizing the image the user took with the suggested items, enabling a virtual try-on experience.

[1084] Order custom-made items

[1085] The user customizes the suggested items and places a custom order by specifying the size and color. The server receives the user's customization information and processes the order.

[1086] Specific examples

[1087] If a user prefers a "casual and simple style," the generative AI model will suggest a "white T-shirt, denim pants, and red pumps." The user can then take a photo of themselves with their smartphone and try on the suggested outfit using the virtual try-on feature. They can then select their favorite pair of red pumps, specify the size "M" and the color "red," and place a custom order.

[1088] In this way, users can receive outfit suggestions based on their preferences, try them on, and easily order customised, made-to-order items.

[1089] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1090] Step 1:

[1091] The user inputs situation and weather information.

[1092] Input: User situation information (e.g., event type, location, time), weather information (e.g., weather, temperature, humidity)

[1093] Processing: The terminal sends this information to the server.

[1094] Output: Situation and weather information sent to the server

[1095] Step 2:

[1096] The server uses a generative AI model to suggest outfits.

[1097] Input: User situation information, weather information, user preferences and past feedback

[1098] Processing: The server inputs the prompt sentence into the generative AI model and generates the optimal coordinates.

[1099] Output: Proposed coordinates

[1100] Specific operation: The server inputs the following prompt sentence into the generative AI model:

[1101] Suggest outfits based on the user's preferences: casual and simple style

[1102] The generative AI model generates a coordinate based on this prompt and returns it to the server.

[1103] Step 3:

[1104] The user checks the suggested outfits.

[1105] Input: Proposed coordinates

[1106] Processing: The terminal displays the suggested coordination to the user.

[1107] Output: Coordination confirmed by the user

[1108] Step 4:

[1109] Users can try on the clothes virtually.

[1110] Input: User image, suggested item image

[1111] Processing: The device uses OpenCV to overlay the item on the user's image.

[1112] Output: Virtual try-on image

[1113] Specific operation: The device combines the image taken by the user with the image of the suggested item to generate a virtual try-on image.

[1114] Step 5:

[1115] Users customize and order made-to-order items.

[1116] Input: Suggested items, user customization information (e.g. size, color)

[1117] Processing: The server receives the user's customization information and processes the order.

[1118] Output: Custom order confirmation

[1119] Specific behavior: The server receives the size and color of the item selected by the user and confirms the order.

[1120] Step 6:

[1121] The server learns from user feedback.

[1122] Input: User feedback (e.g., satisfaction, areas for improvement)

[1123] Processing: The server collects the feedback and uses it as training data for the generative AI model.

[1124] Output: An updated generative AI model

[1125] Specific operation: The server stores the user's feedback in a database and reflects it in the next outfit suggestions.

[1126] 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.

[1127] "Example 1"

[1128] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes the user's emotions and suggests fashion coordination based on those emotions. Specifically, when a user inputs emotional information such as "I'm tired" into the app, the emotion engine analyzes this information and suggests a relaxed, casual outfit. For example, it suggests a combination of loose-fitting sweatshirts and pants made of soft material.

[1129] "Example 2"

[1130] The emotion engine also provides a way for users to order custom-made items based on their emotions. Specifically, when a user inputs emotional information such as "special occasion," the emotion engine analyzes this information and suggests custom-made items suitable for the special occasion. For example, it could suggest a custom-made dress or suit tailored to the user's preferences and the occasion of the special occasion.

[1131] "Example 3"

[1132] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes the user's emotions and suggests fashion coordination based on those emotions. Specifically, when a user inputs emotional information such as "I'm tired" into the app, the emotion engine analyzes this information and suggests a relaxed, casual outfit. For example, it suggests a combination of loose-fitting sweatshirts and pants made of soft material.

[1133] The processing flow of each embodiment will be described below.

[1134] "Example 1"

[1135] Step 1: The user inputs emotional information into the app. For example, they input "I'm tired."

[1136] Step 2: The emotion engine analyzes the information input by the user, which determines the user's current emotional state.

[1137] Step 3: The emotion engine suggests fashion coordination based on the analysis results. For example, if the user feels tired, it will suggest a casual outfit that will help them relax.

[1138] "Example 2"

[1139] Step 1: The user inputs emotional information into the app, for example, "special day."

[1140] Step 2: The emotion engine analyzes the information input by the user, which determines the user's current emotional state.

[1141] Step 3: The emotion engine will suggest custom-made items based on the analysis results. For example, if the user feels that a special day is coming up, it will suggest custom-made items suitable for that day.

[1142] Example 1

[1143] Next, a description will be given of Example 1 of Form 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."

[1144] Conventional fashion coordination suggestion systems were limited in the suggestions they could make based on the user's situation and weather information, and were unable to fully reflect the user's emotions and feedback. Furthermore, they lacked a way to purchase products based on the suggested outfits or to order custom-made items, making it difficult to increase user satisfaction.

[1145] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for analyzing emotional information of the user and suggesting a fashion coordination based on the emotion, and a means for generating a fashion coordination using a generative AI model. This makes it possible to suggest appropriate fashion coordination according to the user's situation, weather, and emotion, and to make suggestions that reflect the user's feedback, as well as to purchase products and order custom-made items.

[1146] A "user" is an individual who uses the system to receive fashion coordination suggestions.

[1147] "Context information" is information entered by a user about a particular event or situation.

[1148] "Weather information" is information about the weather for that day entered by the user.

[1149] "Fashion coordination" refers to the combination of clothing and accessories worn by a user.

[1150] "Feedback" refers to the evaluation or comments that a user provides regarding the proposed outfit.

[1151] "Means to learn" refers to how the system uses user feedback to improve its next suggestions.

[1152] "Means for purchasing products" refers to a method for purchasing items included in the proposed coordination.

[1153] "Emotion information" is information about the user's own emotions and moods that is input by the user.

[1154] "Means for suggesting fashion coordination based on emotions" refers to a method for analyzing a user's emotional information and suggesting appropriate coordination based on the results.

[1155] A "generative AI model" is an artificial intelligence model that generates fashion coordination based on user input information.

[1156] A "means for ordering a custom-made item" is a method for ordering a customized item based on a suggested outfit.

[1157] This invention is a system that suggests appropriate fashion coordination based on situational information, weather information, and emotional information input by the user. The system has the function of learning from the user's feedback and reflecting it in the next suggestion. It also includes a means for purchasing products based on the suggested coordination, or a means for ordering custom-made items.

[1158] Hardware and software used

[1159] Hardware: Servers, user devices (smartphones and tablets)

[1160] Software: Applications, emotion engines, generative AI models

[1161] Specific operation of the system

[1162] 1. The user enters information

[1163] The user enters the situation information "date" and the weather information "sunny" into the app's input fields.

[1164] Specific behavior: The user opens the app on their smartphone, enters "date" and "sunny" in the text boxes, and presses the send button.

[1165] 2. The server receives and analyzes the information

[1166] The server receives the status information and weather information sent by the user.

[1167] Specific operation: The server receives the HTTP request and extracts the "date" and "sunny" information from the request body.

[1168] 3. The server generates the coordinates

[1169] The server uses a generative AI model to generate a fashion coordination based on the received information.

[1170] Specific operation: The server inputs the information "date" and "sunny" into the generated AI model, and the model outputs an outfit such as a white blouse, denim skirt, and red pumps.

[1171] 4. The server sends the coordinates to the user device.

[1172] The server transmits the generated coordinates to the user terminal.

[1173] Specific operation: The server constructs the generated coordinates in JSON format and sends them to the user's device as an HTTP response.

[1174] 5. User enters feedback

[1175] The user inputs feedback on the proposed outfit.

[1176] Specific behavior: The user enters "It was hot" in the app's feedback field and presses the submit button.

[1177] 6. The server learns from the feedback

[1178] The server receives user feedback and trains the generative AI model.

[1179] Specific operation: The server receives the feedback information, adds it to the training dataset of the generative AI model, and reflects this feedback in the next coordinate generation.

[1180] 7. The server uses the emotion engine

[1181] When a user inputs emotional information such as "I'm tired," the server analyzes this information using an emotional engine.

[1182] How it works: The user enters "I'm tired" into the app, and the server sends this information to the emotion engine. The emotion engine generates a relaxing outfit, which the server then sends to the user's device.

[1183] Examples and prompts

[1184] Example: If a user inputs "date" and "sunny," a white blouse, denim skirt, and red pumps are suggested. If the user then inputs feedback that "it was hot," a cooler outfit will be suggested for next time.

[1185] Example prompt: "I have a date and the weather is sunny. What outfit would be good?"

[1186] The system aims to increase user satisfaction by suggesting more appropriate fashion coordination based on the user's input information and feedback.

[1187] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1188] Step 1:

[1189] The user enters information.

[1190] The user enters the situation information "date" and the weather information "sunny" into the app's input fields and presses the send button. The entered information is sent from the user's device to the server. Specifically, the user opens the app on their smartphone, enters "date" and "sunny" into the text boxes, and presses the send button.

[1191] Step 2:

[1192] The server receives and analyzes the information.

[1193] The server receives the status information and weather information sent by the user. The received information is sent to the server as an HTTP request, and the "date" and "sunny" information is extracted from the request body. Specifically, the server analyzes the HTTP request and extracts the necessary information.

[1194] Step 3:

[1195] The server generates the coordinates.

[1196] The server uses a generative AI model to generate a fashion coordination based on the received information. The input information of "date" and "sunny" is input into the generative AI model, and the model outputs an outfit such as a white blouse, denim skirt, and red pumps. In concrete terms, the server inputs information into the generative AI model, and the model generates the outfit.

[1197] Step 4:

[1198] The server sends the coordinates to the user terminal.

[1199] The server sends the generated coordinates to the user's device. The generated coordinates are constructed in JSON format and sent to the user's device as an HTTP response. Specifically, the server converts the generated coordinates into JSON format and sends them as an HTTP response.

[1200] Step 5:

[1201] The user enters feedback.

[1202] The user enters feedback on the suggested outfit. The user enters "It was hot" in the feedback field of the app and presses the send button. The entered feedback is sent from the user's device to the server. Specifically, the user enters text in the feedback field of the app and presses the send button.

[1203] Step 6:

[1204] The server learns the feedback.

[1205] The server receives user feedback and trains the generative AI model. The received feedback information is added to the training dataset of the generative AI model and is reflected in the next coordinate generation. Specifically, the server receives feedback information and adds it to the training dataset of the generative AI model.

[1206] Step 7:

[1207] The server uses the emotion engine.

[1208] When a user inputs emotional information such as "I'm tired," the server analyzes this information using an emotion engine. The emotion engine generates a relaxing outfit, which the server then sends to the user's device. Specifically, the user inputs "I'm tired" into the app, the server sends the information to the emotion engine, and the generated outfit is sent to the user's device.

[1209] (Application example 1)

[1210] Next, a description will be given of Application Example 1 of Form 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."

[1211] While conventional fashion coordination suggestion systems make suggestions based on the user's situation and weather information, they have not been able to fully utilize the user's emotional information and feedback, making it difficult to increase user satisfaction.In addition, in virtual stores, there is a lack of a way to suggest optimal fashion coordination based on the user's input information, making it difficult to improve the user's shopping experience.

[1212] 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.

[1213] In this invention, the server includes means for proposing fashion coordination based on situation information and weather information input by the user, means for learning feedback from the user, means for purchasing products similar to the proposed coordination, means for analyzing emotional information of the user and proposing fashion coordination based on the emotions, and means for proposing optimal fashion coordination in a virtual store based on the information input by the user. This makes it possible to propose fashion coordination that reflects the user's emotions and feedback and provides a higher level of satisfaction.

[1214] "User-entered context information" refers to information that a user inputs into an application about a particular situation or event.

[1215] "Weather information" refers to information about current weather and weather conditions.

[1216] The "means for suggesting fashion coordination" is a system that has the function of suggesting appropriate clothing combinations based on information input by the user.

[1217] "Means for learning from user feedback" refers to a system that has the ability to collect opinions and feedback provided by users and improve the system based on that.

[1218] "Means for purchasing products similar to the proposed fashion coordination" refers to a system that has the functionality to enable the purchase of similar products online or in a physical store based on the proposed fashion coordination.

[1219] The "means for analyzing the user's emotional information" is a system that has the function of analyzing the emotional information entered by the user and suggesting appropriate fashion coordination based on the results.

[1220] A "virtual store" refers to a virtual shopping space operated on the Internet.

[1221] "Means for suggesting optimal fashion coordination based on information input by the user" refers to a system that has the function of suggesting optimal clothing combinations based on situational information, weather information, emotional information, etc. provided by the user.

[1222] As an embodiment of the present invention, the following system can be constructed.

[1223] First, the server receives information about the situation, weather, and emotions entered by the user via a device such as a smartphone or tablet. The server analyzes this information and refers to a database to suggest appropriate fashion coordination.

[1224] The server then collects user feedback and uses machine learning algorithms to learn from it. For example, when a user provides feedback such as "it was hot" or "it was comfortable," the server analyzes it and uses it to improve its next recommendation. This learning process can be achieved using machine learning libraries such as Python and TensorFlow.

[1225] Furthermore, the server generates a link to enable the user to purchase products similar to the suggested outfits at online stores or physical stores, making it easy for the user to purchase the products.

[1226] The system also uses a sentiment analysis engine to analyze the user's emotional information. For example, if a user inputs "I'm tired," the server analyzes this information and suggests relaxing fashion coordination. This process uses natural language processing (NLP) technology.

[1227] In the virtual store, the server suggests optimal fashion coordination based on the user's input information. For example, if a user inputs the information "date" and "sunny" and adds the emotion information "tired," the server will suggest "loose sweatshirts" and "pants made of soft material." This suggestion will be useful when the user goes shopping in the virtual store.

[1228] As a concrete example, by inputting the following prompt sentence into the generative AI model, ideas for suggesting appropriate outfits can be obtained.

[1229] Example prompt sentence:

[1230] If a user inputs the information "date" and "sunny" and adds the emotion information "tired," what kind of fashion coordination will be suggested?

[1231] In this way, it becomes possible to propose fashion coordination that reflects the user's emotions and feedback and provides greater satisfaction.

[1232] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1233] Step 1:

[1234] A user inputs situation information, weather information, and emotion information using a device such as a smartphone or tablet.

[1235] Input: situation information (e.g., "date"), weather information (e.g., "sunny"), emotion information (e.g., "tired")

[1236] Output: The entered information is sent to the server.

[1237] Step 2:

[1238] The server analyzes the received situation information, weather information, and emotion information.

[1239] Input: Situation information, weather information, and emotion information sent by the user

[1240] Data processing: Analyze input information using natural language processing (NLP) techniques.

[1241] Output: Analysis results (e.g. "date", "sunny", "tired")

[1242] Step 3:

[1243] The server will suggest appropriate fashion coordination based on the analysis results.

[1244] Input: Analysis results

[1245] Data calculation: Refer to the database and search for the optimal coordination based on the analysis results.

[1246] Output: Suggested outfits (e.g., "loose-fitting sweatshirts," "soft pants")

[1247] Step 4:

[1248] The server generates a link that allows products similar to the suggested coordination to be purchased at an online store or a physical store.

[1249] Input: Suggested fashion coordination

[1250] Data processing: Refer to the product database and generate links to similar products.

[1251] Output: Purchase link (e.g. "Online store link")

[1252] Step 5:

[1253] Users can review suggested outfits and purchase links and enter feedback.

[1254] Input: User feedback (e.g. "It was hot" or "It was comfortable")

[1255] Output: Feedback is sent to the server.

[1256] Step 6:

[1257] The server collects user feedback and learns using machine learning algorithms.

[1258] Input: User feedback

[1259] Data computation: Using machine learning algorithms (e.g., Python, TensorFlow), we analyze the feedback and incorporate it into our next proposal.

[1260] Output: Updated proposed model

[1261] Step 7:

[1262] In a virtual store, we propose optimal fashion coordination based on the information entered by the user.

[1263] Input: User situation information, weather information, emotional information

[1264] Data calculation: Based on the analysis results, we propose optimal coordination in a virtual store.

[1265] Output: Suggested fashion coordination in a virtual store (e.g., "loose-fitting sweatshirt," "soft pants")

[1266] In this way, it becomes possible to propose fashion coordination that reflects the user's emotions and feedback and provides greater satisfaction.

[1267] Example 2

[1268] Next, a description will be given of Example 2 of Form 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."

[1269] Conventional fashion coordination systems not only suggest outfits based on the situation and weather information entered by the user, but also lack the ability to suggest custom-made items based on the user's emotions and preferences, or a means to easily purchase items similar to the suggested outfits. Furthermore, there is a need for systems that can effectively learn from user feedback and make more accurate suggestions.

[1270] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for analyzing the user's input using a generative AI model and searching for similar products, and a means for analyzing the user's emotion information using an emotion engine and suggesting custom-made items. This allows the user to not only receive coordination suggestions based on the situation and weather, but also to easily purchase custom-made item suggestions and suggested products based on their emotions.

[1271] "User-entered context information" is information about a particular situation or event that a user provides through an application.

[1272] "Weather information" is data about current weather, temperature, humidity, and other meteorological conditions.

[1273] "Means for suggesting fashion coordination" is a function that suggests appropriate combinations of clothing and accessories based on situational and weather information entered by the user.

[1274] "Means for learning from user feedback" is a function that collects ratings and comments provided by users and uses them to improve the accuracy of the system's suggestions.

[1275] "Means for purchasing products similar to the suggested coordination" is a function that allows the system to search for products similar to the suggested fashion coordination and enable the user to purchase them.

[1276] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze user input and generate appropriate products and outfits.

[1277] An "emotion engine" is a system that analyzes a user's emotional information and makes appropriate suggestions based on the results.

[1278] "Means for suggesting custom-made items" is a function that suggests specially customized products based on the user's emotional information and preferences.

[1279] This invention is a system that proposes fashion coordination based on situational and weather information entered by the user, learns from user feedback, and provides a means for purchasing products similar to the proposed coordination. It also includes functions that analyze user input using a generative AI model, analyze the user's emotional information using an emotion engine, and propose custom-made items.

[1280] Hardware and software used

[1281] Hardware: Servers, user devices (smartphones, tablets, PCs)

[1282] Software: Generative AI model, emotion engine, application (iOS / Android)

[1283] Specific operation of the system

[1284] Product suggestion function

[1285] 1. User Input

[1286] Within the app, users input information about a particular outfit, such as a prompt such as "Suggest products similar to this white blouse."

[1287] 2. Server search process

[1288] The server uses a generative AI model to analyze the user's input and search a database for similar products.

[1289] The server generates search results in list form and sends them to the user terminal.

[1290] 3. Terminal display processing

[1291] The user's device displays the product list received from the server within the app.

[1292] The user selects the product of their choice from the displayed product list.

[1293] 4. User purchase process

[1294] The user adds the selected items to the cart and completes the purchase.

[1295] The server receives the purchase information and processes the payment.

[1296] Emotion-based personalized recommendations

[1297] 1. User emotion input

[1298] The user inputs emotional information within the app, for example, "special day."

[1299] 2. Server Emotion Analysis

[1300] The server analyzes the user's emotional information using an emotion engine.

[1301] Based on the analysis results, the server uses a generative AI model to suggest custom-made items suitable for special occasions.

[1302] 3. Device suggestions

[1303] The user's device displays the custom-made item suggestions received from the server within the app.

[1304] Users can choose their favorite items from the suggested items.

[1305] 4. User's custom orders

[1306] The user confirms the selected items as a custom order.

[1307] The server receives the order information and processes the production and delivery.

[1308] Specific examples

[1309] Example prompt: "Suggest products similar to the white blouse."

[1310] Example prompt: "Suggest a custom-made item for a special occasion."

[1311] This system not only allows users to receive outfit suggestions based on the situation and weather, but also makes it possible for them to receive custom-made item suggestions based on their emotions and easily purchase the suggested products.

[1312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1313] Step 1:

[1314] User Input

[1315] Within the app, users input information about a particular outfit, such as a prompt such as "Suggest products similar to this white blouse."

[1316] Input: The prompt text entered by the user.

[1317] Output: The prompt text sent to the server.

[1318] Step 2:

[1319] Server search process

[1320] The server uses a generative AI model to analyze the user's input, specifically by analyzing the prompt sentence using natural language processing technology to extract keywords and features.

[1321] Input: The prompt text sent by the user.

[1322] Data processing: Parsing prompts using a generative AI model.

[1323] Output: Extracted keywords and features.

[1324] Step 3:

[1325] Server database search

[1326] The server searches a database for similar products based on the extracted keywords and characteristics, applying filters such as color, design, and price range.

[1327] Input: Extracted keywords or features.

[1328] Data calculation: Product search using database search algorithms.

[1329] Output: A list of similar products.

[1330] Step 4:

[1331] Server result transmission

[1332] The server generates search results in list form and sends them to the user terminal.

[1333] Input: A list of similar products.

[1334] Data processing: Convert to list format.

[1335] Output: Product list sent to user device.

[1336] Step 5:

[1337] Terminal display processing

[1338] The user's device displays the product list received from the server within the app, including product images, prices, reviews, and other information.

[1339] Input: Product list sent from the server.

[1340] Data processing: Converting product list into display format.

[1341] Output: The product list displayed to the user.

[1342] Step 6:

[1343] User checkout process

[1344] The user selects the desired product from the displayed product list, adds it to the cart, checks the items in the cart, and presses the purchase button.

[1345] Input: The product selected by the user.

[1346] Data processing: Adding to cart and checkout processing.

[1347] Output: Purchase information.

[1348] Step 7:

[1349] Server payment processing

[1350] The server receives the purchase information and processes the payment, including verifying credit card information and communicating with a payment gateway.

[1351] Input: User's purchase information.

[1352] Data calculation: Settlement by payment processing algorithm.

[1353] Output: Payment completion notification.

[1354] Step 8:

[1355] User emotion input

[1356] The user inputs emotional information within the app, for example, "special day."

[1357] Input: Emotion information entered by the user.

[1358] Output: Emotion information sent to the server.

[1359] Step 9:

[1360] Server sentiment analysis

[1361] The server uses an emotion engine to analyze the user's emotional information. Specifically, it analyzes the emotional information using natural language processing technology and extracts data to make appropriate suggestions.

[1362] Input: Emotion information sent by the user.

[1363] Data processing: Analysis of emotional information using an emotion engine.

[1364] Output: Extracted emotion data.

[1365] Step 10:

[1366] Custom-made server proposals

[1367] The server uses a generative AI model to suggest custom-made items for special occasions based on the analysis results, taking into account the user's past purchase history and preferences, for example.

[1368] Input: Extracted emotion data.

[1369] Data computation: Generative AI models generate custom items.

[1370] Output: A list of suggested custom-made items.

[1371] Step 11:

[1372] Device suggestions

[1373] The user's device displays the custom-made item suggestions received from the server within the app, such as design images and detailed information for a custom-made dress or suit.

[1374] Input: A list of custom-made items sent from the server.

[1375] Data processing: Converting proposed items into a display format.

[1376] Output: A list of custom items that will be displayed to the user.

[1377] Step 12:

[1378] User's custom orders

[1379] The user confirms the selected items as a custom order, for example by selecting customization options for size and color.

[1380] Input: The custom item selected by the user.

[1381] Data processing: Processing custom orders.

[1382] Output: Order information.

[1383] Step 13:

[1384] Server production and delivery procedures

[1385] The server receives the order information and handles the manufacturing and delivery procedures, such as placing an order with the manufacturing factory and coordinating with the delivery company.

[1386] Input: User's order information.

[1387] Data calculation: Processing of production and delivery procedures.

[1388] Output: Notification of completion of production and delivery.

[1389] (Application example 2)

[1390] Next, a description will be given of Application Example 2 of Form 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."

[1391] Conventional fashion coordination systems lacked suggestions tailored to the user's emotions and the situation of special occasions, and were unable to fully increase user satisfaction. Furthermore, the lack of a function to directly purchase suggested items within the application fragmented the user's purchasing experience. Furthermore, the inability to suggest custom-made items for special occasions or events made it difficult to meet the diverse needs of users.

[1392] 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.

[1393] In this invention, the server includes means for suggesting fashion coordination based on situation information and weather information input by the user, means for learning user feedback, means for purchasing products similar to the suggested coordination, means for analyzing the user's emotional information, means for suggesting products based on the analyzed emotional information, means for purchasing the suggested products directly within the application, and means for suggesting custom-made items for special occasions or events. This enables suggestions based on the user's emotions and the situation of the special occasion, thereby increasing user satisfaction. Furthermore, the suggested products can be purchased directly within the application, improving the user's purchasing experience. Furthermore, it is possible to suggest custom-made items for special occasions or events, thereby meeting the diverse needs of users.

[1394] "User-entered context information" refers to information about the current situation or environment provided by the user through the application.

[1395] "Weather information" is information about weather conditions such as the current weather and temperature.

[1396] "Means for suggesting fashion coordination" is a function that suggests appropriate combinations of clothing and accessories based on the user's situation and weather information.

[1397] "Means for learning from user feedback" is a function that collects opinions and evaluations provided by users and uses them to improve the accuracy of the system's suggestions.

[1398] "Means for purchasing products similar to the suggested coordination" is a function that allows the user to purchase products similar to the fashion coordination suggested by the system.

[1399] "Means for analyzing user emotional information" refers to a function that analyzes emotions from the text and options entered by the user and identifies those emotions.

[1400] "Means for suggesting products based on analyzed emotional information" is a function that suggests appropriate products based on the user's emotional information.

[1401] "Means for purchasing suggested products directly within the application" refers to a function that allows users to purchase suggested products directly within the application.

[1402] "A means of suggesting custom-made items for special occasions and events" is a function that suggests custom-made items suitable for the user's special occasions and events.

[1403] The system for implementing this invention has the function of suggesting fashion coordination based on situational information and weather information entered by the user, and suggesting products by analyzing the user's emotional information. It also includes the function of allowing suggested products to be purchased directly within the application, and suggesting custom-made items for special occasions or events.

[1404] Hardware and software used

[1405] Hardware: Smartphone

[1406] Software: Python, sentiment analysis library (e.g., TextBlob), product recommendation engine, custom order generation engine, HTTP request library (e.g., requests)

[1407] System configuration

[1408] 1. A method to suggest fashion coordination based on the situation and weather information entered by the user:

[1409] The user enters situational information (e.g., location, type of event) and weather information into the application.

[1410] The server generates an appropriate fashion coordination based on this information.

[1411] 2. Learning from user feedback:

[1412] The user provides feedback on the proposed outfits.

[1413] The server collects this feedback and uses machine learning algorithms to improve the accuracy of its next suggestions.

[1414] 3. How to purchase items similar to the suggested outfit:

[1415] Based on the suggested outfit, a list of similar products is created.

[1416] Users can select products from this list and purchase them directly within the application.

[1417] 4. How to analyze user sentiment:

[1418] Analyze the text entered by the user (e.g., "Today is a special day, so I want a nice dress") using a sentiment analysis library.

[1419] The server determines the user's emotions based on the analysis results.

[1420] 5. Means for suggesting products based on analyzed sentiment information:

[1421] The server then suggests appropriate products based on the identified emotional information.

[1422] For example, if a user types, "I'm feeling a bit down today," the app will suggest relaxing items.

[1423] 6. How to purchase the proposed products directly within the application:

[1424] The user selects the suggested product and completes the purchase within the application.

[1425] The server processes the purchase request and notifies you of the purchase completion.

[1426] 7. How to offer custom-made items for special occasions and events:

[1427] When a user inputs the emotional information "special day," the server analyzes this information and suggests custom-made items suitable for that special day.

[1428] For example, it suggests custom-made dresses and suits tailored to the user's preferences and the occasion of the special occasion.

[1429] Specific examples

[1430] When a user types, "Today is a special day, so I want a beautiful dress," the emotion engine interprets it as a "special day" and suggests a custom-made dress.

[1431] If a user types "I'm feeling a little down today," the emotion engine will interpret this as "depressed" and suggest relaxing items to lift their mood.

[1432] Prompt Sentence Examples

[1433] "How are you feeling today?"

[1434] Please suggest items suitable for special occasions.

[1435] "What products would you recommend for when you're feeling down?"

[1436] In this way, we have created a system that can make suggestions based on the user's emotions and the situation of the special day, thereby increasing user satisfaction.

[1437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1438] Step 1:

[1439] The user inputs situation information and weather information into the application. The input situation information (e.g., location, type of event) and weather information (e.g., temperature, weather) are sent from the device to the server. The server receives this information and stores it in a database.

[1440] Step 2:

[1441] The server generates a fashion coordination based on the received situational and weather information. Using a generative AI model, it suggests appropriate combinations of clothing and accessories. The generated coordination is sent from the server to the device and displayed to the user.

[1442] Step 3:

[1443] The user provides feedback on the proposed outfits. The feedback is sent from the device to the server, which then stores it in a database to use machine learning algorithms to improve the accuracy of the next suggestions.

[1444] Step 4:

[1445] The server creates a list of similar products based on the proposed outfit. It uses a product recommendation engine to search for similar products in a database and generate the list. The created list is sent from the server to the terminal and displayed to the user.

[1446] Step 5:

[1447] The user selects a product from the list and completes the purchase. The selected product information is sent from the device to the server. The server processes the purchase request and notifies the user that the purchase is complete. A purchase completion notification is sent from the server to the device and displayed to the user.

[1448] Step 6:

[1449] The user inputs emotional information. The input emotional information (e.g., "Today is a special day, so I want a nice dress") is sent from the device to the server. The server uses an emotion analysis library to analyze the emotional information and extract specific emotions.

[1450] Step 7:

[1451] The server then suggests products based on the analyzed emotional information. Using a generative AI model, it suggests appropriate products. The suggested products are then sent from the server to the device and displayed to the user.

[1452] Step 8:

[1453] When a user inputs the emotional information "special day," the server suggests custom-made items suitable for that special day. Using a custom order generation engine, custom-made items are generated that match the user's preferences and the situation of the special day. The generated items are sent from the server to the device and displayed to the user.

[1454] Example 3

[1455] Next, a description will be given of Example 3 of Form Example 3. 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."

[1456] Conventional fashion coordination systems make suggestions based solely on weather and situational information, without taking the user's emotional state into account, making it difficult to provide coordination that meets the user's psychological needs. Furthermore, they lack a means to effectively learn from user feedback and provide optimal suggestions for each individual user. Furthermore, there are limited ways to order custom-made items based on the suggested coordination.

[1457] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes means for receiving emotional information input by the user, means for analyzing the received emotional information, means for generating a fashion coordination based on the analysis results, means for presenting the generated coordination to the user, means for learning feedback from the user, and means for purchasing products similar to the suggested coordination. This makes it possible to provide appropriate fashion coordination according to the user's emotional state, effectively learn user feedback, and make optimal suggestions for each user. It also makes it easy to order custom-made items based on the suggested coordination.

[1458] "Emotional information entered by the user" is data entered by the user in text format that describes their emotional state.

[1459] "Means for receiving" is a function that allows the server to receive emotion information sent by the user.

[1460] The "analysis means" is a function for analyzing received emotional information and identifying the emotional state of the user.

[1461] The "means for generating fashion coordinates" is a function for creating appropriate fashion coordinates based on the analysis results.

[1462] The "presentation means" is a function for displaying the generated fashion coordination to the user.

[1463] "Means for learning feedback" is a function that collects feedback from users and uses it to improve the accuracy of the system's suggestions.

[1464] "Means for purchasing products" is a function that allows users to purchase products similar to the suggested outfits.

[1465] "Means for ordering custom-made items" is a function that allows users to order items with customized sizes and colors based on suggested outfits.

[1466] This invention is a system that proposes fashion coordination based on a user's emotional information and orders custom-made items. This system includes a series of processes that receive and analyze the user's emotional information and generate fashion coordination based on the results.

[1467] First, the user inputs emotional information into the application using a device such as a smartphone or tablet. For example, they input "I'm tired." This emotional information is sent to the server as text data.

[1468] The server receives the emotional information sent by the user. The received emotional information is then sent to the emotion engine. The emotion engine uses a "natural language understanding engine" that uses natural language processing technology. This engine analyzes the emotional information and identifies the user's emotional state. For example, based on the information that the user is "tired," it can determine that the user needs to relax.

[1469] Next, the server receives the analysis results from the emotion engine. Based on this analysis result, the server sends a prompt sentence to the generative AI model. The generative AI model used is the "generative AI engine." An example of a prompt sentence is, "The user feels tired. Please suggest a casual outfit that will help them relax."

[1470] The generative AI model analyzes the prompt and generates an appropriate fashion coordination, such as suggesting a combination of loose-fitting sweatshirts and soft pants. This coordinated coordination is then sent to the user's device via the server.

[1471] Users can check the suggested outfits on the app. If they find an item they like, they can customize the size and color to order it as a custom order. For example, if a pair of red pumps is suggested, the user can order the same design in size 24cm and in blue.

[1472] This system provides appropriate fashion coordination according to the user's emotional state and can effectively learn from user feedback to make optimal suggestions for each individual user. It also makes it easy to order custom-made items based on the suggested coordination. The flow of the identification process in Example 3 will be described with reference to FIG. 21.

[1473] Step 1:

[1474] The user inputs emotion information. The user opens the application on their smartphone or tablet and inputs "tired" on the emotion input screen. This input is sent to the server as text data.

[1475] Step 2:

[1476] The server receives the emotion information. The server receives the user's input in real time and stores it in a database. The input data is text data such as "I'm tired."

[1477] Step 3:

[1478] The server sends emotion information to the emotion engine. The server sends the emotion information "tired" to the emotion engine via API. A "natural language understanding engine" is used as the emotion engine.

[1479] Step 4:

[1480] The emotion engine analyzes the emotion information. Using natural language processing technology, the emotion engine analyzes the emotion "tired" and determines that the user needs to relax. The analysis result is the data "Needs relaxation."

[1481] Step 5:

[1482] The server receives the analysis result. The server receives the analysis result from the emotion engine and proceeds to the next step. The received data is the analysis result that "you need to relax."

[1483] Step 6:

[1484] The server sends a prompt to the generative AI model. The server generates a prompt based on the analysis results and sends it to the generative AI model. An example of a prompt is, "The user feels tired. Please suggest a casual outfit that will help them relax."

[1485] Step 7:

[1486] The generative AI model generates an outfit. The generative AI model uses a "generative AI engine" to analyze the prompt and generate an appropriate fashion outfit. The generated outfit is a combination of loose-fitting sweatshirts and pants made of soft material.

[1487] Step 8:

[1488] The server receives the generated outfit. The server receives the outfit from the generative AI model and stores it in a database. The received data is an outfit that combines a loose sweatshirt with pants made of soft material.

[1489] Step 9:

[1490] The server sends the outfit to the user's device. The server then sends the created outfit to the user's device and notifies the user through the app's notification function. The sent data is an outfit consisting of a "combination of loose-fitting sweatshirts and pants made of soft material."

[1491] Step 10:

[1492] The user checks the outfits and orders custom-made items. The user opens the app and checks the suggested outfits. If they find an item they like, they can customize the size and color and order it as a custom-made item. For example, they can select red pumps, change the size to 24cm, and change the color to blue.

[1493] (Application example 3)

[1494] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1495] Conventional fashion coordination systems make suggestions based on the user's situation and weather information, but they cannot take into account the user's emotional state, making it difficult to increase the user's psychological satisfaction. Furthermore, there are limited ways to order custom-made items based on the suggested outfits, which makes it difficult to fully meet the individual needs of users.

[1496] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the proposed coordination, a means for inputting the user's emotional information, a means for analyzing the user's emotions using an emotion engine, and a means for suggesting a fashion coordination based on the emotions using a generative AI model. This makes it possible to suggest a fashion coordination that takes the user's emotional state into consideration, thereby increasing the user's psychological satisfaction. In addition, by providing a means for ordering custom-made items based on the suggested coordination, the individual needs of the user can be met.

[1497] "User-inputted situation information" refers to information about the current situation or environment that the user inputs.

[1498] "Weather information" is information about weather conditions such as the current weather and temperature.

[1499] The "means for suggesting fashion coordination" is a function that suggests appropriate fashion combinations based on input information.

[1500] "Means for learning from user feedback" is a function that analyzes feedback provided by users and improves the accuracy of the system's suggestions.

[1501] The "means for purchasing products similar to the suggested coordination" is a function that allows the user to purchase products similar to the suggested fashion coordination.

[1502] "Means for inputting user's emotional information" is a function that allows the user to input their own emotional state into the system.

[1503] The "means for analyzing a user's emotions using an emotion engine" is a function for analyzing input emotion information and identifying the user's emotional state.

[1504] "Means for proposing emotion-based fashion coordination using a generative AI model" is a function for generating appropriate fashion coordination based on analyzed emotional information.

[1505] "Means for ordering custom-made items" is a function that allows users to order customized items based on suggested fashion coordination.

[1506] The system for implementing this invention proposes fashion coordination based on situation information, weather information, and emotional information input by the user, and also allows the user to order custom-made items. A specific embodiment of this system will be described below.

[1507] System Configuration

[1508] The system includes a user device, a server, an emotion engine, and a generative AI model. The user device is a device such as a smartphone or tablet, and the server is located on the cloud.

[1509] Hardware and software used

[1510] User devices: smartphones, tablets

[1511] Server: Cloud server

[1512] Emotion Engine: Emotion Analysis API

[1513] Generative AI model: OpenAI API

[1514] Data processing and calculation

[1515] 1. User input:

[1516] Users use their smartphones or tablets to input situational information, weather information, and emotional information, such as "It's raining today, and I'm a little tired."

[1517] 2. Emotion analysis:

[1518] The server analyzes the user's emotional information using an emotion engine, which identifies the user's emotional state from the input text.

[1519] 3. Fashion Coordination Generation:

[1520] The server uses a generative AI model to suggest fashion coordination based on emotions. The generative AI model is input with the following prompt:

[1521] "The user is feeling fatigued. Please suggest a casual fashion coordination that will help them relax."

[1522] 4. Show suggestions:

[1523] The suggested fashion coordinations are displayed on the user's device, and the user can check the suggested coordinations and select the items they like.

[1524] 5. Custom Orders:

[1525] The user can customize the size and color of the selected item to place a custom order. The server receives the user's customization information and processes the order.

[1526] Specific examples

[1527] For example, if a user inputs "It's raining today and I'm a little tired," the emotion engine will analyze "fatigue" as the dominant emotion. The generative AI model will then be prompted with the following prompt: "The user is feeling tired. Please suggest a casual fashion outfit that will help them relax." The generated outfits will then be displayed to the user. The user can then select their favorite items from the suggested outfits and customize the size and color to place a custom order.

[1528] In this way, it becomes possible to suggest fashion coordination that takes into account the user's emotional state and to order custom-made items.

[1529] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1530] Step 1:

[1531] Users input situational information, weather information, and emotional information using a smartphone or tablet. For example, they input information such as, "It's raining today, and I'm a little tired." The input information is then sent from the user device to the server.

[1532] Step 2:

[1533] The server sends the received emotion information to the emotion engine, which analyzes the user's emotional state from the input text and identifies the dominant emotion. For example, the emotion "fatigue" may be identified. The analysis results are then sent back to the server.

[1534] Step 3:

[1535] The server inputs a prompt sentence into the generative AI model. The prompt sentence is generated based on the analyzed emotional information. For example, a prompt sentence such as "The user is feeling tired. Please suggest a relaxing casual fashion coordination" is input into the generative AI model.

[1536] Step 4:

[1537] The generative AI model generates a fashion coordination based on the prompt sentence. The generated coordination is sent back to the server. For example, it might suggest "a combination of loose-fitting sweatshirts and pants made of soft material."

[1538] Step 5:

[1539] The server transmits the generated fashion coordinates to the user terminal, which displays the proposed coordinates to the user. The user can then review the proposed coordinates and select items that they like.

[1540] Step 6:

[1541] The user can customize the size and color of the selected item to place a custom order. The customization information is sent from the user terminal to the server.

[1542] Step 7:

[1543] The server processes the custom order based on the received customization information. Once the order processing is complete, a confirmation is sent to the user's terminal. The user can confirm that the order has been successfully received.

[1544] 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.

[1545] 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> ) 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.

[1546] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1547] 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.

[1548] [Third embodiment]

[1549] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1550] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1551] 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).

[1552] 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.

[1553] 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.

[1554] 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).

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1561] "Example 1"

[1562] In one embodiment of the present invention, when a user inputs information about the situation, such as "date," and weather information, such as "sunny," into the app, a casual yet stylish outfit is suggested based on this information. A suggested outfit might be, for example, a white blouse, a denim skirt, and red pumps. Furthermore, if the user inputs feedback such as "it was hot," the app learns to suggest cooler outfits next time.

[1563] "Example 2"

[1564] Furthermore, the app offers a feature that allows users to purchase items similar to the suggested outfits directly within the app. For example, multiple items similar to the suggested white blouse will be displayed, allowing users to select and purchase the item they like.

[1565] "Example 3"

[1566] There is also a way to order custom items based on the suggested outfit. For example, if a user likes the red pumps included in the suggested outfit, they can order custom pumps of the same design but in a different size and color.

[1567] The processing flow of each embodiment will be described below.

[1568] "Example 1"

[1569] Step 1: The user enters the situation information "date" and the weather information "sunny" into the app.

[1570] Step 2: Based on this information, the system suggests a casual yet stylish outfit, such as a white blouse with a denim skirt and red pumps.

[1571] Step 3: The user enters feedback such as "It was hot."

[1572] Step 4: The system learns from this feedback and will suggest cooler outfits next time.

[1573] "Example 2"

[1574] Step 1: The system displays products similar to the outfits it suggests.

[1575] Step 2: The user selects the product they want from the displayed products.

[1576] Step 3: The user purchases the selected item directly within the app.

[1577] "Example 3"

[1578] Step 1: Provide a way to order custom-made items based on the outfits suggested by the system.

[1579] Step 2: If the user likes an item included in the suggested outfit, they can order a custom-made item based on the design of that item.

[1580] Step 3: The user customizes the size and color of the made-to-order item and confirms the order.

[1581] Example 1

[1582] Next, a description will be given of Example 1 of Form 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."

[1583] Conventional fashion coordination suggestion systems have difficulty proposing appropriate outfits based on the user's situation and weather information, and it is also difficult to effectively learn from user feedback and reflect it in future suggestions. Furthermore, there is a lack of a way to purchase products based on the suggested outfits, and a lack of advanced outfit generation using generative AI models.

[1584] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for sending a prompt message to the generative AI model, and a means for receiving coordination from the generative AI model. This makes it possible to suggest appropriate coordination according to the user's situation and weather, improve the suggestions based on user feedback, and generate advanced coordination using the generative AI model.

[1585] "User" refers to an individual who uses the system to receive fashion coordination suggestions.

[1586] "Situation information" refers to information about a specific situation entered by the user, such as "date" or "work."

[1587] "Weather information" refers to information about the current weather that is input by the user, such as "sunny" or "rainy."

[1588] "Fashion coordination" refers to a combination of clothing and accessories suggested based on the user's situational and weather information.

[1589] "Feedback" refers to the evaluations and impressions provided by users regarding the suggested outfits.

[1590] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate outfits based on user input.

[1591] "Prompt sentence" refers to an instruction sentence sent to a generative AI model to generate a coordinate.

[1592] "Server" refers to the computer system that receives user input, sends prompts to the generative AI model, and provides the generated coordinates to the user.

[1593] "Terminal" refers to the device used by a User to enter information and review suggested outfits.

[1594] "Product" refers to items such as clothing and accessories included in the proposed outfit.

[1595] "Made-to-order items" refer to clothing and accessories that are made specifically to a user's request.

[1596] MODE FOR CARRYING OUT THE INVENTION

[1597] This invention is a system that proposes fashion coordination based on situation information and weather information input by a user, learns feedback from the user, and reflects it in future proposals. A specific embodiment of this system will be described below.

[1598] Hardware and software used

[1599] This system is implemented using the following hardware and software:

[1600] Server: Receives user input, sends prompts to the generative AI model, and provides the generated coordinates to the user. The server is developed using Python and TensorFlow as the machine learning model.

[1601] Device: The device used by the user to enter information and view suggested outfits, such as a smartphone or tablet.

[1602] Generative AI model: An algorithm that generates outfits based on user input. For example, OpenAI's GPT-3.

[1603] Program processing

[1604] The user opens the app and enters the situation information "date" and the weather information "sunny." The device sends the information entered by the user to the server. Specifically, it sends the data using an HTTP POST request.

[1605] The server generates a prompt to send to the generative AI model based on the received situational and weather information. For example, it generates the following prompt:

[1606] Based on the situation information "date" and the weather information "sunny," please suggest a casual yet stylish outfit.

[1607] The server sends this prompt to the generative AI model, which then generates an outfit based on the prompt. For example, it might generate a white blouse, denim skirt, and red pumps.

[1608] The server sends the outfit information received from the generative AI model to the device. Specifically, it returns the outfit information as an HTTP response. The user checks the outfit displayed on the device and enters feedback such as "it was hot." The device then sends the feedback entered by the user to the server. Specifically, it sends the feedback data using an HTTP POST request.

[1609] The server retrains the generative AI model based on the received feedback, so that from the next time onwards, it will suggest outfits that reflect the user's feedback.

[1610] Specific examples

[1611] For example, if a user inputs "date" and "sunny" and the suggested outfit is "white blouse, denim skirt, red pumps," if the user provides feedback that "it was hot," the next time the system will suggest a cooler outfit such as "white blouse, linen shorts, sandals."

[1612] In this way, it becomes possible to suggest appropriate outfits based on the user's situation and weather, improve suggestions based on user feedback, and generate advanced outfits using generative AI models.

[1613] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1614] Step 1:

[1615] The user enters the situation information and weather information. The user opens the app and enters the situation information "date" and the weather information "sunny." The entered information is saved on the device.

[1616] Step 2:

[1617] The device sends the input information to the server. The device sends the situation information and weather information entered by the user to the server using an HTTP POST request. The input data is sent in JSON format.

[1618] Step 3:

[1619] The server sends a prompt to the generative AI model. Based on the received situational and weather information, the server generates a prompt to send to the generative AI model. For example, it generates the following prompt:

[1620] Based on the situation information "date" and the weather information "sunny," please suggest a casual yet stylish outfit.

[1621] The generated prompt sentence is sent to a generative AI model.

[1622] Step 4:

[1623] The generative AI model generates an outfit based on the received prompt. For example, it might generate an outfit such as a white blouse, denim skirt, and red pumps. The generated outfit is returned to the server.

[1624] Step 5:

[1625] The server sends the generated coordinates to the device. The server sends the coordinates received from the generative AI model to the device as an HTTP response. The output data is sent in JSON format.

[1626] Step 6:

[1627] The user checks the outfit and inputs feedback. The user checks the outfit displayed on the device and inputs feedback such as "it was hot." The input feedback is saved on the device.

[1628] Step 7:

[1629] The device sends the feedback to the server. The device sends the feedback entered by the user to the server using an HTTP POST request. The input data is sent in JSON format.

[1630] Step 8:

[1631] The server trains the model based on the feedback. The server then retrains the generative AI model based on the received feedback. This allows the server to suggest outfits that reflect the user's feedback from the next time.

[1632] (Application example 1)

[1633] Next, a description will be given of Application Example 1 of Form 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."

[1634] Conventional fashion coordination suggestion systems have difficulty proposing appropriate outfits based on the user's situation and weather information, and are unable to effectively learn from the user's feedback and reflect it in future suggestions. Furthermore, there is a lack of means for users to purchase items based on the suggested outfits, resulting in low user convenience.

[1635] 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.

[1636] In this invention, the server includes a means for suggesting fashion coordination based on situational information and weather information input by the user, a means for learning user feedback, a means for purchasing products similar to the suggested coordination, a means for suggesting coordination using a generative AI model, and a means for generating prompt sentences. This makes it possible to suggest optimal coordination based on the user's situation and weather, and to learn user feedback and reflect it in future suggestions. Furthermore, by providing a means for purchasing products based on the suggested coordination, user convenience can be improved.

[1637] A "user" is an individual who uses the system to receive fashion coordination suggestions.

[1638] "Context information" is information entered by a user about a particular situation or event.

[1639] "Weather information" is information about the current weather and weather conditions entered by the user.

[1640] "Fashion coordination" is the combination of clothing and accessories appropriate for a particular situation or weather.

[1641] "Feedback" refers to the impressions and opinions that users provide regarding the proposed outfits.

[1642] "Learners" are methods and techniques for improving the next offering based on user feedback.

[1643] A "generative AI model" is an algorithm that uses artificial intelligence to generate outfits based on user input.

[1644] A "prompt sentence" is an instruction sentence input to a generative AI model.

[1645] The "means for purchasing products" refers to a method or system for purchasing related products based on the proposed coordination.

[1646] The system for implementing this invention proposes fashion coordination based on situational and weather information entered by the user, learns from the user's feedback and reflects it in future proposals, and also provides a means for purchasing products based on the proposed coordination.

[1647] Hardware and software used

[1648] Hardware: Smartphones, servers

[1649] Software: Python, Requests library, Scikit-learn, OpenAI API

[1650] System configuration

[1651] 1. User device: The user uses a smartphone to input situation information (e.g., "date") and weather information (e.g., "sunny").

[1652] 2. Server: The server receives the information sent by the user and uses a generative AI model to suggest appropriate fashion coordination.

[1653] 3. Generative AI model: The server inputs a prompt statement into the generative AI model to generate coordination suggestions.

[1654] 4. Feedback learning: When a user provides feedback on a suggested outfit (e.g., "It was hot"), the server learns this feedback and reflects it in the next suggestion.

[1655] 5. Product Purchasing Method: Allows users to purchase related products based on the suggested outfits.

[1656] Data processing and calculation

[1657] 1. Data acquisition: The server acquires situational information and weather information from the user's device.

[1658] 2. Prompt generation: The server generates a prompt to be input into the generative AI model based on the acquired information.

[1659] Example: "Situation: Date, Weather: Please suggest an outfit suitable for sunny weather."

[1660] 3. Coordination proposal: The generative AI model generates a coordination proposal based on the prompt sentence and returns it to the server.

[1661] 4. Feedback learning: The server receives feedback from the user and uses Scikit-learn to update the model to improve the next suggestion.

[1662] 5. Product Purchase: The server generates a purchase link for related products based on the suggested coordination and provides it to the user.

[1663] Specific examples

[1664] Situation: Dating

[1665] Weather: Sunny

[1666] Suggested outfit: White blouse, denim skirt, red pumps

[1667] Feedback: It was hot

[1668] In this way, the system can suggest the best outfits for the user's situation and weather, learn from the user's feedback, and reflect it in future suggestions. Also, by providing a means to purchase products based on the suggested outfits, the system can improve user convenience.

[1669] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1670] Step 1:

[1671] The user uses a smartphone device to input situation information (e.g., "date") and weather information (e.g., "sunny"). The input information is sent from the device to the server. The input data is situation information and weather information.

[1672] Step 2:

[1673] The server receives the situational information and weather information sent by the user. Based on the received data, it generates a prompt sentence to input into the generative AI model. Specifically, it combines the situational information and weather information to create the following prompt sentence:

[1674] Example: "Situation: Date, Weather: Please suggest an outfit suitable for sunny weather."

[1675] Step 3:

[1676] The server sends the generated prompt to the generative AI model, which generates a fashion outfit based on the prompt. The output of the generative AI model is a suggested outfit.

[1677] Step 4:

[1678] The server receives the coordinates returned by the generative AI model and sends them to the user's device. The user's device displays the received coordinates to the user. The displayed data is the suggested coordinates.

[1679] Step 5:

[1680] The user inputs feedback for the proposed coordinates. The feedback is sent from the terminal to the server. The input data is the user's feedback.

[1681] Step 6:

[1682] The server receives the feedback sent by the user and uses Scikit-learn to update the model to improve the next suggestion. Specifically, the feedback data is used as training data to update the linear regression model. The updated model is reflected in the next suggestion.

[1683] Step 7:

[1684] The server generates a purchase link for the related product based on the proposed coordination. The generated purchase link is sent to the user terminal and displayed to the user. The displayed data is the purchase link for the related product.

[1685] In this way, the system can suggest the best outfits for the user's situation and weather, learn from the user's feedback, and reflect it in future suggestions. Also, by providing a means to purchase products based on the suggested outfits, the system can improve user convenience.

[1686] Example 2

[1687] Next, a description will be given of Example 2 of Form 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."

[1688] Conventional fashion coordination systems have difficulty in proposing items that fully reflect the user's preferences and past purchase history, which has prevented them from increasing user satisfaction. Furthermore, there is a lack of easy ways to purchase items similar to the suggested outfits, which has prevented them from effectively stimulating users' purchasing desire.

[1689] 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 a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for inputting a prompt sentence to the generative AI model based on the user's past purchase history and preferences, a means for the generative AI model to generate a coordination, a means for transmitting the generated coordination to the user's terminal, and a means for the user to select and purchase products. This makes it possible to suggest optimal coordination that reflects the user's preferences and past purchase history, and allows the user to easily purchase the suggested products.

[1690] "User" refers to an individual who uses the system to receive fashion coordination suggestions.

[1691] "Situation information" refers to information about the current situation or event entered by the user.

[1692] "Weather information" refers to information about the weather at the user's current location or a specified location.

[1693] "Fashion coordination" refers to the combination of clothing and accessories suggested based on the user's situation and weather information.

[1694] "Feedback" refers to the evaluations and opinions that users give about the suggested outfits.

[1695] A "generative AI model" refers to an artificial intelligence model that generates optimal outfits based on user data.

[1696] A "prompt sentence" refers to an instruction sentence input to a generative AI model.

[1697] "Purchase history" refers to a record of products a user has purchased in the past.

[1698] "Preferences" refers to personal preferences such as a user's favorite styles, brands, or colors.

[1699] "Terminal" refers to the device (smartphone, tablet, PC, etc.) that a user uses to access the system.

[1700] "Product" refers to items such as clothing and accessories included in the suggested outfit.

[1701] "Purchase Method" means the method by which a User can purchase a suggested Product directly within the App.

[1702] This invention is a system for suggesting fashion coordination based on situational information and weather information input by a user, learning from the user's feedback, and purchasing products similar to the suggested coordination. Specific embodiments of this system are described below.

[1703] First, a user launches the app on a device such as a smartphone or tablet. The app displays the initial screen and confirms the user's login information. Once the user logs in, the server retrieves the user's past purchase history and preference data from a database. This data includes the type, color, size, and brand of the products purchased.

[1704] Next, the server inputs a prompt to the generative AI model based on the acquired user data. For example, the server sends a prompt such as, "Please suggest products similar to the white blouse based on the user's past purchase history and preferences." The generative AI model then generates the optimal outfit for the user based on this prompt. The generated outfit includes products similar to the white blouse.

[1705] The generated outfit is sent from the server to the user's device. The device displays the outfit to the user. The user can then review the suggested items and view detailed information. The user selects the preferred item from the suggested items and completes the purchase. Payment information and delivery address are entered to complete the purchase directly within the app.

[1706] As a concrete example, consider the case where a user is offered a "white blouse." The server displays multiple products similar to the white blouse based on the user's past purchase history and preferences. The user can then select and purchase a "white blouse with lace" or a "simple white blouse," etc.

[1707] Examples of prompts to be input to a generative AI model include:

[1708] Example prompt sentence:

[1709] Suggest products similar to white blouses based on the user's past purchase history and preferences.

[1710] By inputting this prompt into a generative AI model, the most suitable product is suggested to the user.

[1711] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1712] Step 1:

[1713] A user launches an app. The user launches the app on a device such as a smartphone or tablet, and the login screen appears. The user enters their login information, and if authentication is successful, the app's home screen appears. The input is the user's login information, and the output is the authenticated user information.

[1714] Step 2:

[1715] The server retrieves user data. Based on the authenticated user information, the server retrieves the user's past purchase history and preference data from a database. This data includes the type, color, size, and brand of purchased products. The input is authenticated user information, and the output is the user's past purchase history and preference data.

[1716] Step 3:

[1717] The server inputs a prompt to the generative AI model. The server inputs the prompt to the generative AI model based on the acquired user data. For example, a prompt such as "Please suggest products similar to the white blouse based on the user's past purchase history and preferences" is sent to the generative AI model. The input is the user's past purchase history and preference data, and the output is a prompt to the generative AI model.

[1718] Step 4:

[1719] The generative AI model generates an outfit. The generative AI model generates the optimal outfit for the user based on the input prompt. The generated outfit includes items similar to the white blouse. The input is the prompt, and the output is the generated outfit.

[1720] Step 5:

[1721] The server sends the generated outfit to the device. The server then sends the outfit received from the generative AI model to the user's device. The sent data includes product images, prices, detailed information, etc. The input is the generated outfit, and the output is the outfit data sent to the user's device.

[1722] Step 6:

[1723] The terminal displays the coordinated outfits to the user. The terminal displays the received coordinated outfits to the user. The user can check the suggested items and view detailed information. The input is the coordinated outfit data sent from the server, and the output is the coordinated outfit information displayed to the user.

[1724] Step 7:

[1725] The user selects and purchases a product. The user selects the preferred product from the suggested products and completes the purchase. Payment information and delivery address are entered to complete the purchase directly within the app. The input is the user's selected product information and payment information, and the output is confirmation of purchase completion.

[1726] (Application example 2)

[1727] Next, a description will be given of Application Example 2 of Form 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."

[1728] Conventional fashion coordination suggestion systems can suggest outfits based on the user's situation and weather information, but they lack the ability to suggest similar fashion items based on images taken by the user. They also lack the ability to display multiple products similar to the suggested items so the user can select and purchase them, or the ability to display detailed product information and reviews. This makes it difficult for users to easily find and purchase products that match their preferences.

[1729] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for suggesting fashion coordination based on situation information and weather information input by the user, means for learning feedback from the user, means for purchasing products similar to the suggested coordination, means for suggesting similar fashion items based on images taken by the user, means for displaying multiple products similar to the suggested items so that the user can select and purchase them, and means for displaying detailed product information and reviews. This allows the user to easily find and purchase products that suit their preferences.

[1730] "User-entered contextual information" refers to information provided by the user, such as current activities, events, and locations.

[1731] "Weather information" refers to meteorological data such as the current weather, temperature, and humidity.

[1732] "Means for suggesting fashion coordination" is a function that suggests appropriate clothing combinations based on the user's situational information and weather information.

[1733] "Means for learning from user feedback" is a function that collects opinions and evaluations provided by users and uses them to improve the accuracy of the system's suggestions.

[1734] "Means for purchasing products similar to the suggested coordination" is a function that displays products similar to the suggested fashion coordination and allows the user to purchase them.

[1735] "A means for suggesting similar fashion items based on images taken by the user" is a function that analyzes photos taken by the user and suggests similar fashion items.

[1736] "A means of displaying multiple products similar to the suggested item and allowing the user to select and purchase" is a function that displays multiple products similar to the suggested item and allows the user to select and purchase from among them.

[1737] "Means for displaying detailed product information and reviews" refers to a function that displays detailed product information and ratings and reviews from other users.

[1738] The system for implementing this invention has the functions of suggesting fashion coordination based on situational and weather information entered by the user and learning from user feedback. It also provides a means for purchasing products similar to the suggested coordination and has the functions of suggesting similar fashion items based on images taken by the user. It also has the functions of displaying multiple products similar to the suggested items so that the user can select and purchase them, and displaying detailed product information and reviews.

[1739] System program and processing description

[1740] Hardware

[1741] Smartphone (iOS or Android)

[1742] server

[1743] software

[1744] Python

[1745] TensorFlow

[1746] Keras

[1747] VGG16 model (pre-trained)

[1748] Data processing and calculation

[1749] The server receives situational and weather information entered by the user on their smartphone and suggests fashion coordination based on that information. When the user uploads a photo they have taken to the server, the server analyzes the image and suggests similar fashion items. Specifically, it uses the VGG16 model to extract features from the image and predict similar items.

[1750] The server displays multiple products similar to the suggested item and allows the user to select and purchase from them. It also displays detailed product information and reviews from other users, allowing users to easily find and purchase products that suit their preferences.

[1751] Specific examples

[1752] Users take a photo of a white blouse with their smartphone and upload it to the server via the app. The server analyzes the image using the VGG16 model and suggests several similar white blouses. Users can then choose their favorite from the suggested blouses and purchase them after checking detailed information and reviews.

[1753] Prompt Sentence Examples

[1754] "Upload a photo of a white blouse and let our AI suggest similar products."

[1755] In this way, users can easily find and purchase products that suit their tastes.

[1756] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1757] Step 1:

[1758] The user inputs situational and weather information using a smartphone. The input information is sent to the server, which receives the information and stores it in a database. The input data includes the user's current activities and events, location, weather, temperature, humidity, etc.

[1759] Step 2:

[1760] The server then proposes fashion coordination based on the saved situational and weather information. The server then generates appropriate outfit combinations using a pre-trained model. The coordinated outfits are then sent to the user's smartphone and displayed.

[1761] Step 3:

[1762] The user provides feedback on the suggested outfits. The feedback is based on the user's preferences and experience. The server receives this feedback and stores it in a database. The feedback data is used to improve the accuracy of the next suggestion.

[1763] Step 4:

[1764] Users take images with their smartphones and upload them to the server via the app. The server receives the uploaded images and performs image analysis. Specifically, it uses the VGG16 model to extract features from the images.

[1765] Step 5:

[1766] The server then suggests similar fashion items based on the extracted features. The suggested items are sent to the user's smartphone and displayed. The user can then confirm the suggested items.

[1767] Step 6:

[1768] The server displays multiple products similar to the suggested item, including searching for similar products in a database and sending them to the user's smartphone. The user can then select the product they like best.

[1769] Step 7:

[1770] The server displays detailed information and reviews from other users about the product selected by the user. Detailed information includes the product's material, size, price, etc. Reviews include ratings and comments from other users. The user uses this information to purchase the product.

[1771] Step 8:

[1772] If the user decides to make a purchase, the server processes the purchase, which includes verifying payment information, entering shipping details, etc. Once the purchase is complete, the server sends a confirmation message to the user.

[1773] In this way, users can easily find and purchase products that suit their preferences.

[1774] Example 3

[1775] Next, a third embodiment of the third embodiment will be described. 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."

[1776] Conventional fashion coordination systems have difficulty making suggestions that match a user's preferences and physical experience, and lack the functionality to customize and order suggested items. As a result, they are unable to provide coordination that satisfies users, and the user experience is not improved.

[1777] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1778] In this invention, the server includes means for proposing fashion coordination based on situational information and weather information input by the user, means for learning feedback from the user, means for purchasing products similar to the proposed coordination, means for receiving a prompt input by the user and generating a coordination using a generative AI model, means for the user to customize and order items based on the proposed coordination, and means for sending instructions to a manufacturing system based on the customization information. This makes it possible to propose coordination that suits the user's preferences and physical sensations, and to order further customized items.

[1779] "User" refers to an individual who uses the system to receive fashion coordination suggestions.

[1780] "Status information" refers to information about an event or situation that is entered by the user.

[1781] "Weather Information" means information regarding weather conditions at a User's location or a specified location.

[1782] "Fashion coordination" refers to a style proposed by combining multiple fashion items.

[1783] "Feedback" refers to the evaluations and opinions that users give about the suggested outfits.

[1784] A "generative AI model" refers to an algorithm that uses artificial intelligence to generate outfits based on user input.

[1785] "Prompt" refers to a textual request that a user enters into a generative AI model.

[1786] "Customization" refers to the act of a user changing the size, color, etc. of a suggested item.

[1787] "Manufacturing system" refers to the machines and processes that produce made-to-order items based on customization information.

[1788] "Means of suggestion" refers to the function of generating optimal fashion coordination based on information input by the user.

[1789] "Means of learning" refers to the function of collecting feedback from users and reflecting it in future suggestions.

[1790] "Means for purchasing" refers to the function for purchasing the items included in the proposed coordination.

[1791] "Means for ordering" refers to the functionality that allows users to order customised items on a made-to-order basis.

[1792] The "means for transmitting instructions" refers to a function for transmitting customization information to the manufacturing system.

[1793] This invention is a system that proposes fashion coordination based on situational information and weather information entered by a user, learns feedback from the user, and orders custom-made items based on the proposed coordination. Specific embodiments of this system are described below.

[1794] First, the user inputs a prompt using the device. For example, the prompt might be, "Please suggest an outfit suitable for a casual date." The device then sends this prompt to the server. The server uses a generative AI model (e.g., OpenAI's GPT-4) to generate an outfit that takes into account the user's preferences and past purchase history.

[1795] The generated outfit is sent from the server to the device, and the user can review the suggested outfit. For example, a white T-shirt, denim jacket, black skinny jeans, and red pumps are suggested. The user can select their favorite items and further customize them. For example, they can change the size of the red pumps to 24cm and the color to blue.

[1796] Once the user has completed the customization, the terminal sends the customization information to the server, which then sends instructions to the manufacturing system to create the custom-made item. The manufacturing system then produces the customized item and delivers it to the address specified by the user upon completion.

[1797] This system suggests outfits that suit the user's tastes and preferences, and also allows the user to order customized items, providing a more satisfying fashion experience for the user.

[1798] Specific hardware includes user devices (such as smartphones and tablets), servers, and manufacturing systems, while software includes generative AI models (such as OpenAI's GPT-4), communication protocols (HTTPS), and applications that provide user interfaces.

[1799] This system allows users to easily find fashion items that suit their tastes, customize them, and place an order. The flow of the specification process in the third embodiment will be described with reference to FIG.

[1800] Step 1:

[1801] The user enters a prompt statement.

[1802] The user uses the device interface to input a prompt about the desired outfit. For example, the user might input, "Please suggest an outfit suitable for a casual date." The input prompt becomes the input data for the device.

[1803] Step 2:

[1804] The terminal sends the prompt to the server.

[1805] The terminal sends the prompt text entered by the user to the server using the HTTPS protocol. The input data is the prompt text, and the output data is the prompt text sent to the server.

[1806] Step 3:

[1807] The server generates coordinates using a generative AI model.

[1808] The server inputs the received prompt into a generative AI model (e.g., OpenAI's GPT-4) to generate an outfit that takes into account the user's preferences and past purchase history. The input data is the prompt and the user's history data, and the output data is the generated outfit.

[1809] Step 4:

[1810] The server transmits the generated coordinates to the terminal.

[1811] The server sends the generated coordinates to the terminal in JSON format. The input data is the generated coordinates, and the output data is the coordinates sent to the terminal.

[1812] Step 5:

[1813] The user checks the suggested outfits and selects items.

[1814] The user checks the outfits displayed on the device screen and selects the items they like. For example, they tap red pumps to select them. The input data is the suggested outfit, and the output data is the selected items.

[1815] Step 6:

[1816] Customize and order the items the user selects.

[1817] The user customizes the size and color of the selected item. For example, they change the size of a pair of red pumps to 24cm and the color to blue, and then tap the "Order" button. The input data are the selected item and customization information, and the output data is the customized order information.

[1818] Step 7:

[1819] The terminal transmits the customization information to the server.

[1820] The terminal sends the user-customized information to the server in JSON format, where the input data is the customized order information and the output data is the customized information sent to the server.

[1821] Step 8:

[1822] The server sends instructions to the manufacturing system.

[1823] The server sends instructions to the manufacturing system to manufacture the custom-made item based on the received customization information. The input data is the customization information, and the output data is the instructions sent to the manufacturing system.

[1824] Step 9:

[1825] A manufacturing system produces and delivers custom-made items to users.

[1826] The manufacturing system follows instructions from the server to manufacture customized items. Once manufacturing is complete, the items are delivered to an address specified by the user. The input data are manufacturing instructions, and the output data are the manufactured items.

[1827] (Application example 3)

[1828] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1829] Conventional fashion coordination systems have problems in that they do not adequately provide suggestions based on the user's preferences, and users cannot actually try on the suggested outfits, resulting in low user satisfaction. Furthermore, when ordering custom-made items, it is difficult for users to customize them to suit their preferences.

[1830] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1831] In this invention, the server includes means for suggesting fashion coordination based on situational information and weather information input by the user, means for learning from user feedback, means for purchasing products similar to the suggested coordination, means for suggesting coordination based on the user's preferences using a generative AI model, means for providing a virtual try-on function that overlays items on the user's image, and means for ordering custom-made items. This allows for coordination suggestions based on the user's preferences, allows the user to actually try on the outfits through the virtual try-on function, and further allows the user to easily customize and order custom-made items.

[1832] "User-inputted situation information" refers to information about the current situation or environment that the user provides to the system, such as the type of event, location, and time of day.

[1833] "Weather information" refers to information about current weather conditions such as temperature, humidity, etc. This information can be used to suggest appropriate fashion coordination.

[1834] "Means for suggesting fashion coordination" is a function that suggests appropriate combinations of clothing and accessories based on situational and weather information entered by the user.

[1835] "Means for learning from user feedback" is a function that collects opinions and evaluations provided by users and uses them to improve the accuracy of the system's suggestions.

[1836] "Means for purchasing products similar to the suggested coordination" is a function that provides products that the user can actually purchase based on the fashion coordination suggested by the system.

[1837] A "generative AI model" is an algorithm that uses artificial intelligence to learn a user's preferences and tendencies and then generates optimal outfits based on that information.

[1838] The "virtual try-on feature" overlays suggested items onto the user's image, making it appear as if the user is actually trying them on.

[1839] "Means for ordering custom-made items" refers to a feature that allows users to customize suggested items and order them by specifying size, color, etc.

[1840] A system for implementing this invention includes means for suggesting fashion coordination based on situational and weather information input by a user, learning from user feedback, purchasing products similar to the suggested coordination, using a generative AI model to suggest coordination based on the user's preferences, providing a virtual try-on function that overlays items on the user's image, and ordering custom-made items.

[1841] Hardware and software used

[1842] Hardware: Smartphone, head-mounted display

[1843] Software: OpenAI API, OpenCV

[1844] Data processing and calculation

[1845] Coordination suggestions using generative AI models

[1846] The server uses a generative AI model to suggest outfits based on the user's preferences. The user's preferences and past feedback are input as prompts, and the AI ​​model generates the optimal outfit.

[1847] Example prompt sentence:

[1848] Suggest outfits based on the user's preferences: casual and simple style

[1849] Virtual try-on feature

[1850] The device uses OpenCV to overlay suggested items onto the user's image, synthesizing the image the user took with the suggested items, enabling a virtual try-on experience.

[1851] Order custom-made items

[1852] The user customizes the suggested items and places a custom order by specifying the size and color. The server receives the user's customization information and processes the order.

[1853] Specific examples

[1854] If a user prefers a "casual and simple style," the generative AI model will suggest a "white T-shirt, denim pants, and red pumps." The user can then take a photo of themselves with their smartphone and try on the suggested outfit using the virtual try-on feature. They can then select their favorite pair of red pumps, specify the size "M" and the color "red," and place a custom order.

[1855] In this way, users can receive outfit suggestions based on their preferences, try them on, and easily order customised, made-to-order items.

[1856] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1857] Step 1:

[1858] The user inputs situation and weather information.

[1859] Input: User situation information (e.g., event type, location, time), weather information (e.g., weather, temperature, humidity)

[1860] Processing: The terminal sends this information to the server.

[1861] Output: Situation and weather information sent to the server

[1862] Step 2:

[1863] The server uses a generative AI model to suggest outfits.

[1864] Input: User situation information, weather information, user preferences and past feedback

[1865] Processing: The server inputs the prompt sentence into the generative AI model and generates the optimal coordinates.

[1866] Output: Proposed coordinates

[1867] Specific operation: The server inputs the following prompt sentence into the generative AI model:

[1868] Suggest outfits based on the user's preferences: casual and simple style

[1869] The generative AI model generates a coordinate based on this prompt and returns it to the server.

[1870] Step 3:

[1871] The user checks the suggested outfits.

[1872] Input: Proposed coordinates

[1873] Processing: The terminal displays the suggested coordination to the user.

[1874] Output: Coordination confirmed by the user

[1875] Step 4:

[1876] Users can try on the clothes virtually.

[1877] Input: User image, suggested item image

[1878] Processing: The device uses OpenCV to overlay the item on the user's image.

[1879] Output: Virtual try-on image

[1880] Specific operation: The device combines the image taken by the user with the image of the suggested item to generate a virtual try-on image.

[1881] Step 5:

[1882] Users customize and order made-to-order items.

[1883] Input: Suggested items, user customization information (e.g. size, color)

[1884] Processing: The server receives the user's customization information and processes the order.

[1885] Output: Custom order confirmation

[1886] Specific behavior: The server receives the size and color of the item selected by the user and confirms the order.

[1887] Step 6:

[1888] The server learns from user feedback.

[1889] Input: User feedback (e.g., satisfaction, areas for improvement)

[1890] Processing: The server collects the feedback and uses it as training data for the generative AI model.

[1891] Output: An updated generative AI model

[1892] Specific operation: The server stores the user's feedback in a database and reflects it in the next outfit suggestions.

[1893] 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.

[1894] "Example 1"

[1895] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes the user's emotions and suggests fashion coordination based on those emotions. Specifically, when a user inputs emotional information such as "I'm tired" into the app, the emotion engine analyzes this information and suggests a relaxed, casual outfit. For example, it suggests a combination of loose-fitting sweatshirts and pants made of soft material.

[1896] "Example 2"

[1897] The emotion engine also provides a way for users to order custom-made items based on their emotions. Specifically, when a user inputs emotional information such as "special occasion," the emotion engine analyzes this information and suggests custom-made items suitable for the special occasion. For example, it could suggest a custom-made dress or suit tailored to the user's preferences and the occasion of the special occasion.

[1898] "Example 3"

[1899] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes the user's emotions and suggests fashion coordination based on those emotions. Specifically, when a user inputs emotional information such as "I'm tired" into the app, the emotion engine analyzes this information and suggests a relaxed, casual outfit. For example, it suggests a combination of loose-fitting sweatshirts and pants made of soft material.

[1900] The processing flow of each embodiment will be described below.

[1901] "Example 1"

[1902] Step 1: The user inputs emotional information into the app. For example, they input "I'm tired."

[1903] Step 2: The emotion engine analyzes the information input by the user, which determines the user's current emotional state.

[1904] Step 3: The emotion engine suggests fashion coordination based on the analysis results. For example, if the user feels tired, it will suggest a casual outfit that will help them relax.

[1905] "Example 2"

[1906] Step 1: The user inputs emotional information into the app, for example, "special day."

[1907] Step 2: The emotion engine analyzes the information input by the user, which determines the user's current emotional state.

[1908] Step 3: The emotion engine will suggest custom-made items based on the analysis results. For example, if the user feels that a special day is coming up, it will suggest custom-made items suitable for that day.

[1909] Example 1

[1910] Next, a description will be given of Example 1 of Form 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."

[1911] Conventional fashion coordination suggestion systems were limited in the suggestions they could make based on the user's situation and weather information, and were unable to fully reflect the user's emotions and feedback. Furthermore, they lacked a way to purchase products based on the suggested outfits or to order custom-made items, making it difficult to increase user satisfaction.

[1912] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for suggesting a fashion coordination based on situation information and weather information input by the user, a means for learning feedback from the user, a means for purchasing products similar to the suggested coordination, a means for analyzing emotional information of the user and suggesting a fashion coordination based on the emotion, and a means for generating a fashion coordination using a generative AI model. This makes it possible to suggest appropriate fashion coordination according to the user's situation, weather, and emotion, and to make suggestions that reflect the user's feedback, as well as to purchase products and order custom-made items.

[1913] A "user" is an individual who uses the system to receive fashion coordination suggestions.

[1914] "Context information" is information entered by a user about a particular event or situation.

[1915] "Weather information" is information about the weather for that day entered by the user.

[1916] "Fashion coordination" refers to the combination of clothing and accessories worn by a user.

[1917] "Feedback" refers to the evaluation or comments that a user provides regarding the proposed outfit.

[1918] "Means to learn" refers to how the system uses user feedback to improve its next suggestions.

[1919] "Means for purchasing products" refers to a method for purchasing items included in the proposed coordination.

[1920] "Emotion information" is information about the user's own emotions and moods that is input by the user.

[1921] "Means for suggesting fashion coordination based on emotions" refers to a method for analyzing a user's emotional information and suggesting appropriate coordination based on the results.

[1922] A "generative AI model" is an artificial intelligence model that generates fashion coordination based on user input information.

[1923] A "means for ordering a custom-made item" is a method for ordering a customized item based on a suggested outfit.

[1924] This invention is a system that suggests appropriate fashion coordination based on situational information, weather information, and emotional information input by the user. The system has the function of learning from the user's feedback and reflecting it in the next suggestion. It also includes a means for purchasing products based on the suggested coordination, or a means for ordering custom-made items.

[1925] Hardware and software used

[1926] Hardware: Servers, user devices (smartphones and tablets)

[1927] Software: Applications, emotion engines, generative AI models

[1928] Specific operation of the system

[1929] 1. The user enters information

[1930] The user enters the situation information "date" and the weather information "sunny" into the app's input fields.

[1931] Specific behavior: The user opens the app on their smartphone, enters "date" and "sunny" in the text boxes, and presses the send button.

[1932] 2. The server receives and analyzes the information

[1933] The server receives the status information and weather information sent by the user.

[1934] Specific operation: The server receives the HTTP request and extracts the "date" and "sunny" information from the request body.

[1935] 3. The server generates the coordinates

[1936] The server uses a generative AI model to generate a fashion coordination based on the received information.

[1937] Specific operation: The server inputs the information "date" and "sunny" into the generated AI model, and the model outputs an outfit such as a white blouse, denim skirt, and red pumps.

[1938] 4. The server sends the coordinates to the user device.

[1939] The server transmits the generated coordinates to the user terminal.

[1940] Specific operation: The server constructs the generated coordinates in JSON format and sends them to the user's device as an HTTP response.

[1941] 5. User enters feedback

[1942] The user inputs feedback on the proposed outfit.

[1943] Specific behavior: The user enters "It was hot" in the app's feedback field and presses the submit button.

[1944] 6. The server learns from the feedback

[1945] The server receives user feedback and trains the generative AI model.

[1946] Specific operation: The server receives the feedback information, adds it to the training dataset of the generative AI model, and reflects this feedback in the next coordinate generation.

[1947] 7. The server uses the emotion engine

[1948] When a user inputs emotional information such as "I'm tired," the server analyzes this information using an emotional engine.

[1949] How it works: The user enters "I'm tired" into the app, and the server sends this information to the emotion engine. The emotion engine generates a relaxing outfit, which the server then sends to the user's device.

[1950] Examples and prompts

[1951] Example: If a user inputs "date" and "sunny," a white blouse, denim skirt, and red pumps are suggested. If the user then inputs feedback that "it was hot," a cooler outfit will be suggested for next time.

[1952] Example prompt: "I have a date and the weather is sunny. What outfit would be good?"

[1953] The system aims to increase user satisfaction by suggesting more appropriate fashion coordination based on the user's input information and feedback.

[1954] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1955] Step 1:

[1956] The user enters information.

[1957] The user enters the situation information "date" and the weather information "sunny" into the app's input fields and presses the send button. The entered information is sent from the user's device to the server. Specifically, the user opens the app on their smartphone, enters "date" and "sunny" into the text boxes, and presses the send button.

[1958] Step 2:

[1959] The server receives and analyzes the information.

[1960] The server receives the status information and weather information sent by the user. The received information is sent to the server as an HTTP request, and the "date" and "sunny" information is extracted from the request body. Specifically, the server analyzes the HTTP request and extracts the necessary information.

[1961] Step 3:

[1962] The server generates the coordinates.

[1963] The server uses a generative AI model to generate a fashion coordination based on the received information. The input information of "date" and "sunny" is input into the generative AI model, and the model outputs an outfit such as a white blouse, denim skirt, and red pumps. In concrete terms, the server inputs information into the generative AI model, and the model generates the outfit.

[1964] Step 4:

[1965] The server sends the coordinates to the user terminal.

[1966] The server sends the generated coordinates to the user's device. The generated coordinates are constructed in JSON format and sent to the user's device as an HTTP response. Specifically, the server converts the generated coordinates into JSON format and sends them as an HTTP response.

[1967] Step 5:

[1968] The user enters feedback.

[1969] The user enters feedback on the suggested outfit. The user enters "It was hot" in the feedback field of the app and presses the send button. The entered feedback is sent from the user's device to the server. Specifically, the user enters text in the feedback field of the app and presses the send button.

[1970] Step 6:

[1971] The server learns the feedback.

[1972] The server receives user feedback and trains the generative AI model. The received feedback information is added to the training dataset of the generative AI model and is reflected in the next ...

Claims

1. A means for suggesting fashion coordination based on situation information and weather information input by a user; A means for learning user feedback on the proposed fashion coordination; and A means for purchasing products similar to the proposed fashion coordination; A means for transmitting a prompt sentence to the learned generative AI model to receive a fashion coordination suggestion; A means for receiving a fashion coordination suggested by the generative AI model in response to the prompt sentence; A system including:

2. The system of claim 1 , further comprising means for ordering a custom-made item based on the suggested fashion outfit.

3. The system of claim 1 , wherein the means for learning user feedback further comprises means for generating suggestions that match a user's experience and preferences.

Images