system

Abstract

Provide a system. [Solution] means for accepting user-input design requirements; means for transmitting the design requirement data to a server; a means for analyzing the received design requirements; means for generating design proposals based on the analyzed design requirements; A means of analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to a terminal; A means for users to check the design proposals displayed on their devices; A system including:

Description

[Technical Field]

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

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

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

[0004] The modern fashion industry is required to respond quickly and effectively to market trends and provide customized designs that meet the needs of individual customers. However, traditional methods separate design proposals and trend forecasts, making it difficult to achieve an efficient design process. Furthermore, it is difficult to simultaneously optimize color, shape, and material when generating designs, which can lead to a decline in design quality. Technologically innovative methods are needed to solve these problems. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a means for accepting design requirements input by a user is provided. After receiving this requirement data, a means for transmitting it from the terminal to a server is provided. Next, a means for analyzing the accepted design requirements at the server is provided, and a means for generating design proposals based on the analyzed design requirements is provided. This includes a means for proposing appropriate color combinations using color theory and trend data, and a means for proposing shapes and silhouettes based on specified uses and seasons. Furthermore, the server analyzes the latest market trends and uses a means for predicting future trends to reflect trend elements in the generated design proposals. Finally, a means for transmitting the generated design proposals and trend prediction results to the terminal is provided, and a means for the user to confirm the design proposals on the terminal is provided. This series of processes makes it possible to quickly and efficiently provide high-quality designs that meet market demands.

[0006] "User" refers to the person who uses the system to input design requirements and review the final design proposal.

[0007] "Design Requirements" refers to the specific conditions or specifications for clothing or accessories desired by a user, such as color, shape, material, season, etc.

[0008] "Device" refers to an electronic device, such as a computer or smartphone, that a user uses to input and submit design requirements and receive and review the final design.

[0009] "Server" refers to a computer system that receives design requirements sent by a user, analyzes and processes them to generate design proposals, and transmits the design proposals to a terminal.

[0010] "Means of acceptance" refers to the functions and interfaces that collect design requirements from users in input format.

[0011] "Means for transmitting" refers to a function for transmitting design requirement data from a terminal to a server.

[0012] "Means for analysis" refers to the function of analyzing received design requirement data using techniques such as natural language processing and extracting the necessary information.

[0013] "Means of generation" refers to the function of generating optimal design proposals using AI models, etc., based on the analyzed design requirements.

[0014] "Trend forecasting means" refers to the function of analyzing the latest market trends and predicting future fashion trends based on the results.

[0015] "Color suggestion tool" refers to a function that suggests the best color combinations for a design based on color theory and trend data.

[0016] "Shape suggestion means" refers to the function of suggesting appropriate shapes and silhouettes depending on the design's purpose and season.

[0017] "Material suggestion means" refers to the function of suggesting suitable materials based on the functionality and trends of the design.

[0018] The "transmission means" refers to a function for transmitting the generated design proposals and trend prediction results to a terminal.

[0019] "Display means" refers to a function that displays the design proposal received from the server to the user on the terminal. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0028] [First embodiment]

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

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

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

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

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

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

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

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

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

[0041] This invention relates to a system in which a server analyzes design requirements input by a user, generates optimal design proposals, and makes proposals that reflect trend predictions.

[0042] System Overview

[0043] This system works in conjunction with the terminal and server to generate design proposals based on the design requirements entered by the user, and makes proposals that take trend elements into account. Below are specific processing and examples of the program.

[0044] Explanation of program processing

[0045] Step 1: User enters design requirements

[0046] The user uses the device interface to input design requirements, such as specific requirements like "a casual summer dress," "bright color," and "breathable material." This information is structured as data on the device and then passed on to the next processing step.

[0047] Step 2: The device sends the input data to the server

[0048] The terminal sends the design requirement data entered by the user to the server, which transfers the data via the Internet using an HTTP POST request.

[0049] Step 3: The server analyzes the requirements

[0050] The server analyzes the received data using natural language processing (NLP) technology to extract and structure the necessary information from the user's requirements. For example, it extracts specific keywords such as "summer," "casual," "bright colors," and "breathable materials."

[0051] Step 4: The server generates a design proposal

[0052] The server generates design proposals from the requirements data analyzed using the AI ​​model, taking into account the following factors:

[0053] Color Suggestion: Based on color theory and the latest trend data, it suggests the best color combinations. For example, it suggests bright colors such as yellow and light blue for summer dresses.

[0054] Shape suggestions: We suggest shapes and silhouettes that are suitable for different occasions and seasons. For example, A-line dresses and midi lengths are suggested for casual wear.

[0055] Material suggestions: Select the appropriate material based on functionality and trends. For example, breathable linen or cotton is suggested.

[0056] Step 5: The server makes a trend prediction

[0057] The server analyzes the latest market trends and applies algorithms to predict future trends. Here, data is collected from online sources such as fashion blogs, social media, and shopping sites, and analyzed using AI.

[0058] Step 6: Send the final design to your device

[0059] The generated design proposals and trend forecast results are sent from the server to the device, which receives them and displays them to the user, such as visual images, color palettes, and material lists.

[0060] Step 7: User reviews the design

[0061] The user can review the proposed design on their device, provide feedback if necessary, and request revisions to the design by resubmitting it to the server.

[0062] Specific examples

[0063] Example 1: Summer casual dress design

[0064] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[0065] 2. The device sends the input data to the server.

[0066] 3. Server analyzes: extracts keywords (summer, casual, bright colors, breathable)

[0067] 4. Server generated:

[0068] Color suggestions: Yellow, light blue, white

[0069] Suggested styles: A-line dress, midi length

[0070] Material suggestions: linen, cotton

[0071] 5. Server predicts trend: Minimalist design is in vogue

[0072] 6. The server sends the design proposal and trend prediction results to the device.

[0073] 7. User confirms: Check the visual image and material details and finalize the design

[0074] Example 2: Winter accessories for the office

[0075] 1. User types: "winter office accessories," "elegant design," "silver"

[0076] 2. The device sends the input data to the server.

[0077] 3. Server analyzes: Keywords (winter, office, elegant, silver) are extracted

[0078] 4. Server generated:

[0079] Color suggestions: Silver, black, navy

[0080] Shape suggestion: simple lines, modern design

[0081] Material suggestions: Silver, stainless steel

[0082] 5. Server predicts trend: Minimalist jewelry is trending

[0083] 6. The server sends the design proposal and trend prediction results to the device.

[0084] 7. User review: Check the visual image and material details and request fine-tuning if necessary

[0085] As shown in these examples, the system can provide efficient and high-quality designs based on the user's requirements.

[0086] The processing flow will be explained below.

[0087] Step 1:

[0088] The user inputs design requirements using the device interface, for example, specific requirements such as "casual summer dress," "bright color," and "breathable material."

[0089] Step 2:

[0090] The terminal sends the input design requirement data to the server. Specifically, the user input data is passed to the server via an HTTP POST request.

[0091] Step 3:

[0092] The server analyzes the received data and uses natural language processing (NLP) technology to extract and structure the necessary information from the user's requirements, organizing keywords such as "summer," "casual," "bright colors," and "breathable."

[0093] Step 4:

[0094] The server makes color suggestions based on design requirements. It references color theory and trend data to select the optimal color combination. For example, suggestions such as "yellow," "light blue," and "white" are made.

[0095] Step 5:

[0096] The server will suggest shapes and silhouettes that are best suited to the user's purpose and the season, such as "A-line dress" or "midi length."

[0097] Step 6:

[0098] The server will suggest materials based on functionality, user requests, and trends. For example, "linen" or "cotton" may be suggested.

[0099] Step 7:

[0100] The server applies trend prediction algorithms, analyzes current market trends, and collects and analyzes data to predict future trends, for example, by utilizing information from online fashion blogs and social media.

[0101] Step 8:

[0102] The server synthesizes the final design proposals. Design proposals are synthesized based on color, shape, and material, and a final proposal is created that reflects the trend forecast results.

[0103] Step 9:

[0104] The server sends the final design proposal to the device using an HTTP POST request, along with the generated design proposal and trend prediction results.

[0105] Step 10:

[0106] The terminal displays the received design proposal, providing detailed information such as visual images, color palettes, and material lists to the user.

[0107] Step 11:

[0108] The user checks the design proposal and provides feedback as needed. If corrections are needed, the requirements are entered again and the process is repeated.

[0109] Example 1

[0110] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0111] In modern design, it is difficult for users to efficiently find designs that meet their requirements, which consumes a lot of time and effort. It is also difficult to quickly incorporate market trends and reflect them in designs. In conventional systems, even if users provide specific feedback, it takes time for it to be reflected, resulting in a decrease in satisfaction.

[0112] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0113] In this invention, the server includes: means for accepting design requirements input by a user; means for transmitting the design requirement data to the server; means for analyzing the accepted design requirements; means for generating a design proposal based on the analyzed design requirements; means for analyzing the latest market trends and predicting future trends; means for transmitting the generated design proposal and the trend prediction results to a terminal; means for the user to confirm the design proposal displayed on the terminal; and means for the user to input feedback on the confirmed design proposal and retransmit it to the server to request a revision. This enables the generation of appropriate and efficient design proposals that meet user requirements and reflect trends in the proposals. Furthermore, by quickly reflecting user feedback, improved user satisfaction can be expected.

[0114] "User" refers to the end-user who inputs design requirements and reviews and modifies proposed designs.

[0115] "Terminal" refers to a computer or mobile device used by a user to input design requirements and review proposed designs.

[0116] "Server" refers to the central computing system that analyzes design requirements, generates and proposes designs, and analyzes market trends and forecasts trends.

[0117] "Design requirements" refers to specific design requests and conditions entered by the user, such as information on use, color, material, shape, etc.

[0118] "Design Proposal" refers to a specific design or proposal generated by the server based on the user's design requirements.

[0119] "Market Trends" refers to data regarding current and recent market trends and trends.

[0120] "Trend forecasting" refers to the use of AI technology to predict future trends based on market trend data.

[0121] "Analysis" refers to the process of extracting necessary information using natural language processing technology, etc., based on the design requirements received by the server.

[0122] A "request for revision" refers to a user providing feedback on a proposed design and requesting further revisions.

[0123] "Theory" refers to academic foundations such as color theory and design theory that are referenced when generating design proposals.

[0124] "Data" refers to information used to generate design proposals and forecast trends, such as trend data, user data, and market data.

[0125] This invention relates to a system in which a server analyzes design requirements entered by a user, generates optimal design proposals, and makes proposals that reflect the latest market trends.

[0126] System Overview

[0127] This system works by linking terminals and a server to generate design proposals based on design requirements entered by users and make proposals that take market trends into account. Specifically, it uses the following hardware and software:

[0128] Hardware

[0129] Device: A device such as a computer or smartphone operated by a user.

[0130] Server: A central computing system that performs data analysis, design generation, and trend forecasting.

[0131] software

[0132] Natural Language Processing (NLP) engine: Software for analyzing user-entered design requirements.

[0133] Generative AI model: AI for generating design proposals from analyzed requirements data.

[0134] Trend Forecasting Algorithms: Algorithms for analyzing the latest market trends and predicting future trends.

[0135] Program processing explanation

[0136] The user uses the device interface to input design requirements, such as specific requirements like "summer casual dress," "bright color," and "breathable material." The device then structures this information as data and sends it to the server using an HTTP POST request.

[0137] The server first stores the received data in a database, then analyzes the input data using a natural language processing (NLP) engine, extracting specific keywords such as "summer," "casual," "bright colors," and "breathable materials."

[0138] Based on the analyzed requirements data, the server uses a generative AI model to generate design proposals, taking into account the following factors:

[0139] Color suggestions: The server refers to color theory and the latest trend data and suggests bright colors such as yellow or light blue for a "casual summer dress," for example.

[0140] Style suggestions: The server will suggest styles such as A-line dresses or midi dresses depending on the season and purpose.

[0141] Material suggestions: The server will suggest breathable materials such as linen and cotton.

[0142] The server then uses trend prediction algorithms to gather data from fashion blogs, social media, and shopping sites to analyze the latest market trends. For example, if minimalist design is predicted to be popular, the server generates design proposals based on that.

[0143] The generated design proposals and trend forecast results are sent from the server to the terminal, which receives them and displays visual images, color palettes, material lists, etc. to the user. The user can check the proposed design proposals on the terminal, enter feedback if necessary, and resubmit them to the server to request design revisions.

[0144] Specific examples

[0145] Example 1: Designing a casual summer dress

[0146] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[0147] 2. The device sends the input data to the server.

[0148] 3. Server analyzes: extracts keywords (summer, casual, bright colors, breathable)

[0149] 4. Server generated:

[0150] Color suggestions: Yellow, light blue, white

[0151] Suggested styles: A-line dress, midi length

[0152] Material suggestions: linen, cotton

[0153] 5. Server predicts trend: Minimalist design is in vogue

[0154] 6. The server sends the design proposal and trend prediction results to the terminal.

[0155] 7. User confirms: Check the visual image and material details and finalize the design

[0156] Example 2: Winter office accessories

[0157] 1. User types: "winter office accessories," "elegant design," "silver"

[0158] 2. The device sends the input data to the server.

[0159] 3. Server analyzes: Keywords (winter, office, elegant, silver) are extracted

[0160] 4. Server generated:

[0161] Color suggestions: Silver, black, navy

[0162] Shape suggestion: simple lines, modern design

[0163] Material suggestions: Silver, stainless steel

[0164] 5. Server predicts trend: Minimalist jewelry is trending

[0165] 6. The server sends the design proposal and trend prediction results to the terminal.

[0166] 7. User review: Check the visual image and material details and request fine-tuning if necessary

[0167] Prompt Sentence Examples

[0168] "Casual summer dress," "bright color," "breathable material"

[0169] "Winter office accessories," "elegant design," "silver"

[0170] This makes it possible to generate and propose appropriate and efficient design proposals that meet the user's requirements.

[0171] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0172] Step 1:

[0173] The user uses the device interface to input design requirements, such as "a casual summer dress," "bright color," and "breathable material." This input data is structured on the device and prepared for the next processing step.

[0174] Input: User-entered design requirements (e.g., "casual summer dress," "bright color," "breathable material").

[0175] Output: Structured design requirements data.

[0176] Step 2:

[0177] The device sends structured design requirement data to the server via an HTTP POST request, using the HTTPS protocol to keep the data secure.

[0178] Input: Structured design requirements data.

[0179] Output: The data sent as an HTTP POST request.

[0180] Step 3:

[0181] The server first stores the received data in a database. It then analyzes the data using a natural language processing (NLP) engine to extract important keywords and concepts from the user's requirements. For example, keywords such as "summer," "casual," "light colors," and "breathable" are extracted.

[0182] Input: The data sent as an HTTP POST request.

[0183] Output: Extracted keywords and concepts (e.g., "summer," "casual," "light colors," "breathable").

[0184] Step 4:

[0185] The server uses a generative AI model to generate design proposals from the analyzed requirements data, taking into account the following factors:

[0186] Color suggestions: Based on color theory and the latest trend data, colors such as "yellow," "light blue," and "white" are suggested.

[0187] Shape suggestions: Depending on the purpose and season, we will suggest shapes such as "A-line dress" or "midi length."

[0188] Material suggestions: We suggest "linen" and "cotton" as breathable materials.

[0189] Input: Extracted keywords and concepts.

[0190] Output: Design proposals with suggested colors, shapes, and materials.

[0191] Step 5:

[0192] The server uses trend prediction algorithms to collect data from fashion blogs, social media, and shopping sites on the Internet and analyze the latest market trends. For example, it predicts that minimalist design is trending.

[0193] Input: Market trend data from the internet.

[0194] Output: Future trend prediction results (e.g. minimalist design will be popular).

[0195] Step 6:

[0196] The server sends the generated design proposals and trend forecast results as an HTTP response to the terminal, which receives them and displays them visually to the user. The displayed content includes visual images, color palettes, material lists, etc.

[0197] Input: Design proposals and trend forecast results.

[0198] Output: The data sent as the HTTP response.

[0199] Step 7:

[0200] The user checks the proposed design on the terminal, and if the user is satisfied, confirms it as is, enters feedback as necessary, and resubmits it to the server to request corrections.

[0201] Input: Design proposals and trend forecast results.

[0202] Output: User feedback or design confirmation.

[0203] (Application example 1)

[0204] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0205] Conventional design systems have difficulty quickly generating design proposals that accurately reflect user requirements, and it is even more difficult to reflect market trends. As a result, user satisfaction is low and design quality is inconsistent. In addition, there is a lack of ways for users to specifically check and edit proposed design proposals, which means that they are unable to see the actual product when selling online.

[0206] 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.

[0207] In this invention, the server includes means for accepting design requirements input by a user, means for transmitting the design requirement data to the server, means for analyzing the accepted design requirements, means for generating design proposals based on the analyzed design requirements, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to a terminal, means for the user to check the design proposals displayed on the terminal, means for the user to check the design proposals and provide feedback or edit them, and means for providing the generated design proposals to the user and allowing them to check them online in a form close to the real thing. This enables the rapid generation of high-quality design proposals based on user requirements and proposals that reflect market trends, as well as the user to specifically check and edit the design proposals online.

[0208] "Means for accepting design requirements input by a user" refers to an interface through which a user inputs requirements regarding a desired design and the system receives them.

[0209] "Means for transmitting design requirement data to a server" refers to the process or technology for transmitting design requirement data entered at a terminal to a server via a network.

[0210] The "means for analyzing received design requirements" refers to a technology for analyzing the design requirement data sent to the server and extracting and structuring the necessary information.

[0211] "Means for generating design proposals based on analyzed design requirements" refers to a system that uses AI and other technologies to generate actual design proposals based on analyzed design requirement data.

[0212] "Means of analyzing the latest market trends and predicting future trends" refers to algorithms and technologies that collect the latest market trends as data and analyze it to predict future trends.

[0213] "Means for transmitting the generated design proposals and trend prediction results to the terminal" refers to the process or technology for transmitting the design proposals and trend prediction results generated by the server to the terminal being used by the user.

[0214] "Means for users to check the design proposals displayed on their devices" refers to the function that allows users to view and check the sent design proposals on the screen of their devices.

[0215] "A means for users to review design proposals and provide feedback or edits" refers to a function that allows users to view design proposals and provide feedback, or modify the design as needed.

[0216] "A means of providing the generated design proposal to the user and allowing them to check it online in a manner close to the actual product" refers to technology that allows the user to see the generated design proposal and check it in an online environment in a manner close to the actual product.

[0217] This invention relates to a system in which a server analyzes design requirements entered by a user, generates optimal design proposals, and makes proposals that reflect trend forecasts. A specific method for realizing this system is described below.

[0218] System program generation and implementation method

[0219] This system operates in cooperation with the server and the terminal used by the user. The main processing steps are as follows:

[0220] Hardware and Software

[0221] Devices: Smartphones, tablets, computers, and other devices

[0222] Server: Cloud server or on-premise server

[0223] Network: Internet connection

[0224] Languages ​​and libraries used: Python, NLP libraries (e.g., NLTK, spaCy), machine learning libraries (e.g., TENSORFLOW (registered trademark), PyTorch), HTTP communication libraries (e.g., Requests)

[0225] Processing description

[0226] User inputs design requirements

[0227] Users input design requirements using a smartphone or PC interface, for example, by typing specific requirements such as "casual jacket for spring," "pastel color," and "waterproof material" into text boxes.

[0228] The device sends the input data to the server

[0229] The entered design requirement data is sent to the server via the Internet by an HTTP POST request.

[0230] The server analyzes the requirements

[0231] The server analyzes the received design requirements data and uses natural language processing (NLP) technology to extract and structure specific keywords (such as "spring," "casual," "pastel colors," and "waterproof") from the input text.

[0232] The server generates design proposals

[0233] The AI ​​model installed on the server generates design proposals based on the analyzed requirements data, using color theory and the latest trend data to suggest appropriate color combinations, shapes, silhouettes, materials, etc.

[0234] The server makes trend predictions

[0235] The server analyzes the latest market trends and applies algorithms to predict future trends, analysing data collected from online sources such as fashion blogs, social media, and shopping sites.

[0236] Send the final design to your device

[0237] The generated design proposals and trend forecast results are sent from the server to the user's device, where they can be viewed. Visual images, color palettes, material lists, and more are displayed.

[0238] Users can review the design proposal and provide feedback or edits

[0239] After reviewing the proposed design on their device, users can provide feedback and make any necessary revisions to the design. Once the final design is confirmed, they will also be given the option to purchase it online.

[0240] Examples of specific examples and prompts

[0241] For example, if a user enters "casual spring jacket," "pastel color," and "waterproof material," the system will do the following:

[0242] Input prompt statement:

[0243] Casual jacket for spring

[0244] "Pastel colors"

[0245] Waterproof material

[0246] This system allows users to quickly obtain high-quality design proposals that meet their requirements and also allows them to receive proposals that reflect market trends. Furthermore, users can confirm and edit the proposed design proposals in detail, improving the online purchasing experience.

[0247] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0248] Step 1:

[0249] User inputs design requirements

[0250] The user uses the terminal interface to input design requirements. Examples of input requirements include "casual jacket for spring," "pastel color," and "waterproof material." The terminal structures this as text data and prepares it for the next processing step. The input data is the design requirements in text format. The output is structured design requirement data.

[0251] Step 2:

[0252] The device sends the input data to the server

[0253] The structured design requirement data is sent from the terminal to the server. Here, the data is transferred via the Internet by an HTTP POST request. The input data is the structured design requirement data, and the output is the design requirement data sent to the server.

[0254] Step 3:

[0255] The server analyzes the requirements

[0256] The server analyzes the received design requirements data and uses natural language processing (NLP) technology to extract and structure specific keywords (such as "spring," "casual," "pastel colors," and "waterproof") from the user's requirements. Here, the input data is the design requirements data received by the server, and the output is the identified keywords and their understanding.

[0257] Step 4:

[0258] The server generates design proposals

[0259] A generative AI model installed on the server generates design proposals based on the analyzed requirement data. Based on color theory and the latest trend data, it suggests appropriate color combinations, shapes, silhouettes, materials, etc. The input data are identified requirement keywords, and the output is the generated design proposals.

[0260] Step 5:

[0261] The server makes trend predictions

[0262] The server collects the latest market trend data from online sources such as fashion blogs, social media, and shopping sites, and applies a trend prediction algorithm to predict future trends. The input data is the collected market trend data, and the output is the trend prediction results.

[0263] Step 6:

[0264] The server sends design proposals and trend forecast results to the terminal.

[0265] The generated design proposals and trend prediction results are sent from the server to the terminal, where the user can check them. The input data are the generated design proposals and trend prediction results, and the output is the design proposals and trend prediction results displayed on the terminal.

[0266] Step 7:

[0267] Users can review the design proposal and provide feedback or edits

[0268] The user checks the design proposal displayed on the terminal. The user can provide feedback on the design proposal or edit the design as needed. The input data is the displayed design proposal, and the output is the feedback or edited design proposal.

[0269] Step 8:

[0270] Users can check the actual product online

[0271] The system provides the generated design proposal to the user and allows them to check it online in a form close to the real thing. This allows the user to check the design in detail. The input data is the generated design proposal, and the output is a design proposal displayed in a form close to the real thing.

[0272] 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.

[0273] This invention relates to a system in which a server analyzes and generates optimal design proposals based on design requirements and emotional information input by a user, and makes proposals that reflect trend predictions.

[0274] System Overview

[0275] This system consists of a terminal, a server, and an emotion engine. Its unique feature is that it recognizes the user's emotional information in addition to the design requirements input by the user, and reflects this information in the design proposal.

[0276] Explanation of program processing

[0277] Step 1: User enters design requirements

[0278] The user uses the device interface to input design requirements, such as "a casual summer dress," "bright color," and "breathable material," for each specific item.

[0279] Step 2: The emotion engine recognizes the user's emotion

[0280] The emotion engine analyzes the user's facial expressions, voice, text, etc. to recognize the user's emotional state, for example, determining whether the user is happy, excited, calm, etc.

[0281] Step 3: The device sends the input data and emotion data to the server.

[0282] The device sends the design requirement data and emotion data entered by the user to the server via an HTTP POST request.

[0283] Step 4: The server parses the data

[0284] The server analyzes the received design requirements and emotion data. It uses natural language processing (NLP) technology to extract necessary information from the design requirements and combines it with the emotion information obtained from the emotion engine for analysis. For example, it organizes information such as "summer," "casual," "bright color," "breathable," "happy," and "calm."

[0285] Step 5: The server generates a design proposal

[0286] The server uses the AI ​​model to generate design proposals from the analyzed requirements and sentiment data, taking into account the following factors:

[0287] Color suggestions: Select the optimal color combination based on color theory and the latest trend data. For example, if the emotion is "happiness," suggest "yellow" or "light blue."

[0288] Shape suggestions: We suggest the best shape and silhouette for each occasion and season, such as "A-line dress" or "midi length."

[0289] Material suggestions: Materials are selected based on functionality, user requests, and trends. For example, "linen" and "cotton" are suggested.

[0290] Step 6: The server makes a trend prediction

[0291] The server analyzes the latest market trends and applies algorithms to predict future trends. It collects data from online fashion blogs, social media, shopping sites, and other sources and uses AI to analyze it.

[0292] Step 7: Send the final design to your device

[0293] The generated design proposals and trend forecast results are sent from the server to the device, which receives them and displays them to the user, such as visual images, color palettes, and material lists.

[0294] Step 8: User reviews the design

[0295] The user can review the proposed design on their device, provide feedback if necessary, and request revisions to the design by resubmitting it to the server.

[0296] Specific examples

[0297] Example 1: Emotion-based casual summer dress design

[0298] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[0299] 2. Emotion engine recognizes: User's emotions are "happy" and "excited"

[0300] 3. The device sends input data and emotion data to the server.

[0301] 4. Server analyzes: extracts keywords (summer, casual, bright colors, breathable, happy, excited)

[0302] 5. Server generated:

[0303] Color suggestions: Yellow, light blue

[0304] Suggested styles: A-line dress, midi length

[0305] Material suggestions: linen, cotton

[0306] 6. Server predicts trend: Minimalist design is in vogue

[0307] 7. The server sends the design proposal and trend prediction results to the device.

[0308] 8. User confirms: Check the visual image and material details and finalize the design

[0309] Example 2: Emotion-based winter accessories for the office

[0310] 1. User types: "winter office accessories," "elegant design," "silver"

[0311] 2. Emotion engine recognizes: User's emotions are "calm" and "confident"

[0312] 3. The device sends input data and emotion data to the server.

[0313] 4. Server analyzes: extracts keywords (winter, office, elegant, silver, calm, confident)

[0314] 5. Server generated:

[0315] Color suggestions: Silver, black, navy

[0316] Shape suggestion: simple lines, modern design

[0317] Material suggestions: Silver, stainless steel

[0318] 6. Server predicts trend: Minimalist jewelry is trending

[0319] 7. The server sends the design proposal and trend prediction results to the device.

[0320] 8. User review: Check the visual image and material details and request fine-tuning if necessary

[0321] The system takes into account the user's design requirements and emotional state to deliver more personalized and high-quality design suggestions.

[0322] The processing flow will be explained below.

[0323] Step 1:

[0324] The user inputs design requirements using the device interface, for example, specific requirements such as "casual summer dress," "bright color," and "breathable material."

[0325] Step 2:

[0326] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions, voice, text, etc. to recognize the user's emotional state. For example, it analyzes facial expressions through a camera and identifies emotions such as "happiness" or "excitement."

[0327] Step 3:

[0328] The device sends the input data and emotion data to the server. The device sends the design requirement data entered by the user and the emotion data recognized by the emotion engine to the server. Here, an HTTP POST request is used.

[0329] Step 4:

[0330] The server analyzes the received design requirement data and sentiment data. Using natural language processing (NLP) techniques, it extracts keywords (summer, casual, bright colors, breathable, happy, excited) and organizes them as structured data.

[0331] Step 5:

[0332] The server generates design proposals. Using AI models, the server generates design proposals based on the analyzed design requirements and emotional data. It makes suggestions based on the following factors:

[0333] Color Suggestion: Selects the optimal color combination based on color theory and the latest trend data. For example, if the user is "happy," it will suggest bright colors such as "yellow" and "light blue."

[0334] Shape suggestions: The system suggests the best shape and silhouette for each occasion and season. For example, for "casual dresses," it suggests "A-line dresses" and "midi length."

[0335] Material suggestions: Select materials based on functionality, user requests, and trends. For example, suggest "linen" or "cotton" as "materials with good breathability."

[0336] Step 6:

[0337] The server performs trend prediction. The server analyzes the latest market trends and applies algorithms to predict future trends. For example, it collects data from online fashion blogs, social media, shopping sites, etc. and analyzes it using AI.

[0338] Step 7:

[0339] The server integrates the final design proposal. It integrates design proposals based on color, shape, and material, and incorporates trend forecast results to create the final design proposal.

[0340] Step 8:

[0341] The server sends the final design proposal to the terminal. The server sends the generated design proposal and trend prediction results to the terminal using an HTTP POST request.

[0342] Step 9:

[0343] The terminal displays the received design proposal, providing detailed information such as visual images, color palettes, and material lists to the user.

[0344] Step 10:

[0345] The user checks the proposed design. The user checks the proposed design on the terminal and enters feedback as necessary. If corrections are necessary, the requirements are entered again and the process is repeated.

[0346] Example 2

[0347] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0348] Conventional design generation systems did not consider the user's emotional information when proposing designs, making it difficult to provide designs that satisfied the user. It was also difficult to integrate trend forecasts that reflected the latest market trends into the design. For this reason, there was a need for a system that could provide personalized design proposals that met the user's needs.

[0349] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting design requirements input by the user, means for transmitting the design requirement data and user emotion data to the server, means for analyzing the accepted design requirements and emotion information, means for generating design proposals based on the analyzed design requirements and emotion information, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to the terminal, and means for the user to check the design proposals displayed on the terminal and input feedback. This makes it possible to provide personalized design proposals that reflect the user's emotional state and incorporate trend predictions that reflect the latest market trends into the design.

[0350] "Design requirements" are information entered by a user regarding their wishes and conditions regarding a particular design.

[0351] "Emotional data" is information that represents the user's emotional state, and is data collected from facial expressions, voice, and text.

[0352] The "server" is a computer system that generates design proposals, analyzes design requirements and emotional data, and predicts trends.

[0353] "Means for analysis" refers to a method for understanding the input design requirements and emotional data and extracting the necessary information.

[0354] A "generative AI model" is an artificial intelligence algorithm that generates optimal design proposals based on design requirements and emotional data.

[0355] "Trend forecasting" is a method of analyzing the latest market trends and predicting future design trends.

[0356] "Feedback" refers to the act of a user inputting comments or requests for corrections to a design proposal.

[0357] "Color theory" is a theory that studies the impressions and psychological effects that specific colors give to people.

[0358] "Shape and silhouette" are design elements that indicate the appearance and placement of an object.

[0359] A "terminal" is a device to which a user can send input data and view generated design proposals.

[0360] This invention relates to a system in which a server analyzes design requirements and emotional information input by a user, generates optimal design proposals, and makes proposals that reflect trend predictions. The system is composed of a terminal, a server, and an emotion engine.

[0361] Hardware and software used

[0362] 1. Terminal: A device on which users input design requirements and review proposed designs, such as a PC, tablet, or smartphone.

[0363] 2. Server: A computer system for analyzing design requirements and emotion data, generating design proposals, and forecasting trends.

[0364] 3. Emotion engine: Software for collecting and analyzing emotional data from users' facial expressions, voice, and text.

[0365] Data processing and calculation

[0366] 1. Enter your design requirements:

[0367] Users input design requirements through the device interface, such as "casual summer dress," "bright color," and "breathable material," using text fields and drop-down menus.

[0368] 2. Emotional data collection and analysis:

[0369] The device activates an emotion engine, collects facial expressions and voice data from the user via a webcam and microphone, and analyzes input text data and history data to recognize the user's emotional state.

[0370] The emotion engine identifies emotions such as "happy," "excited," and "calm" based on the collected data.

[0371] 3. Sending design and emotion data:

[0372] The device converts the input design requirements and analyzed emotion data into JSON format and sends it to the server via an HTTP POST request.

[0373] 4. Data Analysis:

[0374] The server analyzes the received design requirement data and emotion data. It uses natural language processing (NLP) technology to extract necessary information from the design requirements, and combines it with the emotion information obtained from the emotion engine for analysis. For example, it organizes information such as "summer," "casual," "bright color," "breathable," "happy," and "calm."

[0375] 5. Generate design proposals:

[0376] The server generates design proposals from the analyzed requirements and emotional data using a generative AI model. For example, it suggests colors like "yellow" or "light blue" based on color theory and trend data, shapes like "A-line dress" or "midi length" based on the purpose and season, and materials like "linen" or "cotton" based on functionality and trend data.

[0377] 6. Trend Forecasting:

[0378] The server collects data from fashion blogs, social media, and shopping sites, and uses machine learning algorithms to predict future design trends, such as the popularity of minimalist design.

[0379] 7. Submission of design proposals and trend forecast results:

[0380] The server sends the generated design proposals and trend prediction results via HTTPS to the terminal, which receives them and displays them visually to the user.

[0381] 8. User Acknowledgment and Feedback:

[0382] The user checks the proposed design on the device and, if necessary, sends feedback or correction requests to the server via the device's input interface. The server then generates a new design based on the received feedback and presents it to the device again.

[0383] Specific examples

[0384] Emotion-based summer casual dress design

[0385] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[0386] 2. Emotion engine recognizes: User's emotions are "happy" and "excited"

[0387] 3. The device sends input data and emotion data to the server.

[0388] 4. Server analyzes: extracts keywords (summer, casual, bright colors, breathable, happy, excited)

[0389] 5. Server generated:

[0390] Color suggestions: Yellow, light blue

[0391] Suggested styles: A-line dress, midi length

[0392] Material suggestions: linen, cotton

[0393] 6. Server predicts trend: Minimalist design is in vogue

[0394] 7. The server sends the design proposal and trend prediction results to the device.

[0395] 8. User confirms: Check the visual image and material details and finalize the design

[0396] Prompt Sentence Examples

[0397] "Imagine a design for a casual summer dress. The color should be bright and the material should be breathable. The user's emotions should be happy and excited."

[0398] "Imagine designing winter office accessories. The design is elegant and the color is silver. The user emotions are calm and confident."

[0399] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0400] Step 1:

[0401] The user inputs the design requirements using the terminal interface.

[0402] Specifically, users use text fields and drop-down menus to input requirements such as "casual summer dress," "light color," and "breathable material."

[0403] Input: Design requirements (text format)

[0404] Output: Input design requirements (internal data of the device)

[0405] Step 2:

[0406] The terminal starts the emotion engine and starts collecting the user's emotion data.

[0407] Specifically, the emotion engine collects facial and voice data from the user via a webcam and microphone, and also analyzes the input text data, allowing it to classify the user's emotional state into categories such as "happy," "excited," or "calm."

[0408] Input: User's facial expression data, voice data, text data

[0409] Output: Analyzed emotion information (categorical data)

[0410] Step 3:

[0411] The terminal transmits the input design requirement data and the analyzed emotion data to the server.

[0412] Specifically, this data is converted into JSON format and sent to the server as an HTTP POST request.

[0413] Input: Design requirements data, emotion data (JSON format)

[0414] Output: HTTP POST request to the server

[0415] Step 4:

[0416] The server analyzes the received design requirement data and emotion data.

[0417] Specifically, it uses natural language processing (NLP) technology to extract important information from design requirements and process it in combination with emotional information, for example, extracting keywords such as "summer," "casual," "bright colors," "breathable," "happy," and "excited" from the input data.

[0418] Input: Design requirement data (text format), emotion data (categorical data)

[0419] Output: Extracted keywords and analysis information

[0420] Step 5:

[0421] The server uses a generative AI model to generate design proposals.

[0422] Specifically, it generates design proposals based on analyzed requirements and emotional data, as well as color theory and trend data. For example, it suggests colors like "yellow" and "light blue," suggests styles like "A-line dress" and "midi length," and selects materials like "linen" and "cotton."

[0423] Input: Extracted keywords and analysis information

[0424] Output: Generated design proposals (color, shape, material suggestions)

[0425] Step 6:

[0426] The server analyzes the latest market trends and predicts future trends.

[0427] Specifically, the project collects data from online fashion blogs, social media, shopping sites, etc., and uses machine learning algorithms to predict future design trends, such as the trend toward minimalist design.

[0428] Input: Market trend data (web data, social media data, etc.)

[0429] Output: Trend prediction results (future fashion information)

[0430] Step 7:

[0431] The server transmits the generated design proposals and trend prediction results to the terminal.

[0432] This information is sent to the device via HTTPS.

[0433] The device receives this and displays visual images, color palettes, material lists, etc. on a dashboard or preview screen.

[0434] Input: Generated design proposals, trend prediction results

[0435] Output: Design proposals and trend information displayed to the user

[0436] Step 8:

[0437] The user checks the proposed design on the device.

[0438] If necessary, feedback or correction requests can be resubmitted to the server via the input interface of the device, and the server will generate new design proposals based on the received feedback and present them to the device again.

[0439] Input: Feedback information (user comments, correction requests, etc.)

[0440] Output: Revised design proposal (design proposal resent from server)

[0441] (Application example 2)

[0442] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0443] Conventional design generation systems generate design proposals based solely on user input data. This makes it difficult to propose designs that reflect the user's emotions and psychological state, and fails to sufficiently improve user satisfaction. Furthermore, it is difficult to accurately reflect the latest market trends and future trends, making it an inappropriate solution for virtual stores, which must always incorporate the latest trends.

[0444] The specification processing by the specification 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 accepting design requirements input by a user, means for transmitting the design requirement data to the server, means for analyzing the accepted design requirements, means for generating design proposals based on the analyzed design requirements and the user's emotional state, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to the terminal, means for the user to confirm the design proposals displayed on the terminal, and means for recognizing the user's emotional state using facial recognition and voice recognition. This enables personalized design proposals that take the user's emotional state into consideration, thereby increasing user satisfaction. Furthermore, design proposals that reflect the latest market trends and future trends can be made.

[0445] "Design requirements" refer to the design features and conditions desired by the user.

[0446] A "server" is a computer system that provides services and information to other devices on a network.

[0447] "Analysis" means examining data or information in detail to clarify its structure and meaning.

[0448] "Emotional state" refers to the user's psychological state or mood, and is information that can be inferred from facial expressions and voice.

[0449] A "design proposal" is a specific design proposal generated based on the analyzed data and requirements.

[0450] "Market trends" refers to current market trends and consumer preferences.

[0451] "Trend forecasting" is analysis to predict future consumer preferences and market changes.

[0452] A "terminal" is an electronic device that allows a user to input information and check the display.

[0453] "Facial recognition" is a technology that uses a camera to identify an individual's face and analyze its features.

[0454] "Speech recognition" is a technology that uses a microphone to convert voice data into text data.

[0455] "Personalization" refers to customization according to the needs and preferences of individual users.

[0456] A "visual image" is a picture or figure that is displayed in a visual form.

[0457] This invention is a system in which a server generates optimal design proposals based on the user's design requirements and emotional information, and makes proposals that reflect the latest market trends. Specifically, the system allows the user to input design requirements using a terminal and recognize emotional information, enabling personalized design proposals.

[0458] Hardware and Software Use

[0459] Device:

[0460] Smartphone (using an application that implements React Native)

[0461] Smartphone camera (using OpenCV for facial recognition)

[0462] Smartphone microphone (voice recognition is performed using the Google (registered trademark) Cloud Speech-to-Text API)

[0463] server:

[0464] Server system (built using Python Flask)

[0465] Natural language processing library (using SpaCy and GPT-4 (registered trademark))

[0466] AI models (using TensorFlow or PyTorch)

[0467] Data processing and calculation

[0468] 1. Design requirements and receiving emotional information:

[0469] The user inputs design requirements, such as "autumn jacket," "warm material," and "modern design," through the smartphone interface. At the same time, the smartphone's camera and microphone are used for facial and voice recognition to capture the user's emotional state (e.g., "relaxed" or "satisfied").

[0470] 2. Data transmission:

[0471] The device sends the user's design requirement data and emotion data to the server via an HTTP POST request.

[0472] 3. Data analysis and design generation:

[0473] The server analyzes the received design requirement data using a natural language processing library (such as SpaCy) to extract keywords. At the same time, it also analyzes sentiment data. Based on this data, it uses an AI model (a generative AI model using TensorFlow or PyTorch) to generate optimal design proposals.

[0474] 4. Trend Forecasting:

[0475] The server collects data from online fashion blogs, social media, shopping sites, and other sources, and uses AI to analyze market trends and predict future trends. These trend predictions are also reflected in design proposals.

[0476] 5. Design proposal submission:

[0477] The final design proposals and trend forecast results are sent from the server to the user's device and displayed for review, allowing the user to check the visual image, color palette, material list, and other details.

[0478] Specific examples

[0479] If a user is looking for a fall jacket:

[0480] The user types "autumn jacket," "warm material," and "modern design" into their smartphone, and the camera and microphone are used to recognize the emotional states of "relaxed" and "satisfied."

[0481] The server analyzes this data and suggests the most suitable color (e.g., "olive green" or "brown"), shape (e.g., "slim fit"), material (e.g., "wool"), etc.

[0482] The server analyzes the latest market trends and sends the generated design proposals and trend forecast results to the smartphone.

[0483] The user checks visual images and detailed design proposals and makes the final selection.

[0484] Prompt Sentence Examples

[0485] "Generate detailed design proposals for a fall jacket made of warm material with a modern design that is perfect for customers with a relaxed feel."

[0486] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0487] Step 1:

[0488] The user inputs the design requirements. Using the smartphone interface, the user inputs design requirements such as "autumn jacket," "warm material," and "modern design" in text. This input serves as the basis for data processing in each subsequent step.

[0489] Step 2:

[0490] The device recognizes emotional information. It uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and then performs facial recognition (using OpenCV) and voice recognition (using Google Cloud Speech-to-Text API). Through this process, the device identifies the user's emotional state as "relaxed" or "satisfied," for example. Emotional information is extracted from the user's facial expression and voice data using an emotion recognition algorithm.

[0491] Step 3:

[0492] The terminal sends the design requirement data and emotion data to the server. The terminal sends the design requirement data and emotion data entered by the user to the server via an HTTP POST request. The sent data includes text (design requirement) and emotion state (relaxed, satisfied, etc.).

[0493] Step 4:

[0494] The server analyzes the data. The server uses natural language processing (SpaCy or GPT-4) to analyze the received design requirement data and extract keywords. At the same time, it also analyzes the emotional data. As a result of this analysis, keywords such as "autumn," "jacket," "warm," and "modern" and emotional states such as "relaxed" and "satisfied" are obtained.

[0495] Step 5:

[0496] The server generates design proposals using a generative AI model (using TensorFlow or PyTorch) based on the analyzed requirements and sentiment data. The server suggests optimal colors ("olive green" or "brown"), shapes ("slim fit"), and materials ("wool"), for example. The AI ​​model is trained on a large amount of design data and generates design proposals by referencing related data.

[0497] Step 6:

[0498] The server analyzes the latest market trends and makes trend predictions. The server collects data from online fashion blogs, social media, shopping sites, etc. and uses AI to analyze market trends. Based on these results, future trends are predicted and incorporated into design proposals.

[0499] Step 7:

[0500] The server sends the generated design proposal and trend prediction results to the terminal. The server then sends the final generated design proposal and trend prediction results to the terminal as an HTTP response, which includes detailed information such as visual images, color palettes, and material lists.

[0501] Step 8:

[0502] The user checks the proposed design on their device. The user can check the design proposals and trend prediction results sent to the device on their smartphone screen and make corrections or feedback as necessary. For example, they can input a request for correction, such as "I want the color to be a little darker," and send it back to the server to fine-tune the design.

[0503] The above is the flow of specific processing steps, which enables personalized design proposals based on the user's needs and emotions.

[0504] 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.

[0505] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0506] 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.

[0507] [Second embodiment]

[0508] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0509] 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.

[0510] 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).

[0511] 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.

[0512] 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.

[0513] 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).

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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.

[0518] 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.

[0519] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0520] This invention relates to a system in which a server analyzes design requirements input by a user, generates optimal design proposals, and makes proposals that reflect trend predictions.

[0521] System Overview

[0522] This system works in conjunction with the terminal and server to generate design proposals based on the design requirements entered by the user, and makes proposals that take trend elements into account. Below are specific processing and examples of the program.

[0523] Explanation of program processing

[0524] Step 1: User enters design requirements

[0525] The user uses the device interface to input design requirements, such as specific requirements like "a casual summer dress," "bright color," and "breathable material." This information is structured as data on the device and then passed on to the next processing step.

[0526] Step 2: The device sends the input data to the server

[0527] The terminal sends the design requirement data entered by the user to the server, which transfers the data via the Internet using an HTTP POST request.

[0528] Step 3: The server analyzes the requirements

[0529] The server analyzes the received data using natural language processing (NLP) technology to extract and structure the necessary information from the user's requirements. For example, it extracts specific keywords such as "summer," "casual," "bright colors," and "breathable materials."

[0530] Step 4: The server generates a design proposal

[0531] The server generates design proposals from the requirements data analyzed using the AI ​​model, taking into account the following factors:

[0532] Color Suggestion: Based on color theory and the latest trend data, it suggests the best color combinations. For example, it suggests bright colors such as yellow and light blue for summer dresses.

[0533] Shape suggestions: We suggest shapes and silhouettes that are suitable for different occasions and seasons. For example, A-line dresses and midi lengths are suggested for casual wear.

[0534] Material suggestions: Select the appropriate material based on functionality and trends. For example, breathable linen or cotton is suggested.

[0535] Step 5: The server makes a trend prediction

[0536] The server analyzes the latest market trends and applies algorithms to predict future trends. Here, data is collected from online sources such as fashion blogs, social media, and shopping sites, and analyzed using AI.

[0537] Step 6: Send the final design to your device

[0538] The generated design proposals and trend forecast results are sent from the server to the device, which receives them and displays them to the user, such as visual images, color palettes, and material lists.

[0539] Step 7: User reviews the design

[0540] The user can review the proposed design on their device, provide feedback if necessary, and request revisions to the design by resubmitting it to the server.

[0541] Specific examples

[0542] Example 1: Summer casual dress design

[0543] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[0544] 2. The device sends the input data to the server.

[0545] 3. Server analyzes: extracts keywords (summer, casual, bright colors, breathable)

[0546] 4. Server generated:

[0547] Color suggestions: Yellow, light blue, white

[0548] Suggested styles: A-line dress, midi length

[0549] Material suggestions: linen, cotton

[0550] 5. Server predicts trend: Minimalist design is in vogue

[0551] 6. The server sends the design proposal and trend prediction results to the device.

[0552] 7. User confirms: Check the visual image and material details and finalize the design

[0553] Example 2: Winter accessories for the office

[0554] 1. User types: "winter office accessories," "elegant design," "silver"

[0555] 2. The device sends the input data to the server.

[0556] 3. Server analyzes: Keywords (winter, office, elegant, silver) are extracted

[0557] 4. Server generated:

[0558] Color suggestions: Silver, black, navy

[0559] Shape suggestion: simple lines, modern design

[0560] Material suggestions: Silver, stainless steel

[0561] 5. Server predicts trend: Minimalist jewelry is trending

[0562] 6. The server sends the design proposal and trend prediction results to the device.

[0563] 7. User review: Check the visual image and material details and request fine-tuning if necessary

[0564] As shown in these examples, the system can provide efficient and high-quality designs based on the user's requirements.

[0565] The processing flow will be explained below.

[0566] Step 1:

[0567] The user inputs design requirements using the device interface, for example, specific requirements such as "casual summer dress," "bright color," and "breathable material."

[0568] Step 2:

[0569] The terminal sends the input design requirement data to the server. Specifically, the user input data is passed to the server via an HTTP POST request.

[0570] Step 3:

[0571] The server analyzes the received data and uses natural language processing (NLP) technology to extract and structure the necessary information from the user's requirements, organizing keywords such as "summer," "casual," "bright colors," and "breathable."

[0572] Step 4:

[0573] The server makes color suggestions based on design requirements. It references color theory and trend data to select the optimal color combination. For example, suggestions such as "yellow," "light blue," and "white" are made.

[0574] Step 5:

[0575] The server will suggest shapes and silhouettes that are best suited to the user's purpose and the season, such as "A-line dress" or "midi length."

[0576] Step 6:

[0577] The server will suggest materials based on functionality, user requests, and trends. For example, "linen" or "cotton" may be suggested.

[0578] Step 7:

[0579] The server applies trend prediction algorithms, analyzes current market trends, and collects and analyzes data to predict future trends, for example, by utilizing information from online fashion blogs and social media.

[0580] Step 8:

[0581] The server synthesizes the final design proposals. Design proposals are synthesized based on color, shape, and material, and a final proposal is created that reflects the trend forecast results.

[0582] Step 9:

[0583] The server sends the final design proposal to the device using an HTTP POST request, along with the generated design proposal and trend prediction results.

[0584] Step 10:

[0585] The terminal displays the received design proposal, providing detailed information such as visual images, color palettes, and material lists to the user.

[0586] Step 11:

[0587] The user checks the design proposal and provides feedback as needed. If corrections are needed, the requirements are entered again and the process is repeated.

[0588] Example 1

[0589] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0590] In modern design, it is difficult for users to efficiently find designs that meet their requirements, which consumes a lot of time and effort. It is also difficult to quickly incorporate market trends and reflect them in designs. In conventional systems, even if users provide specific feedback, it takes time for it to be reflected, resulting in a decrease in satisfaction.

[0591] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0592] In this invention, the server includes: means for accepting design requirements input by a user; means for transmitting the design requirement data to the server; means for analyzing the accepted design requirements; means for generating a design proposal based on the analyzed design requirements; means for analyzing the latest market trends and predicting future trends; means for transmitting the generated design proposal and the trend prediction results to a terminal; means for the user to confirm the design proposal displayed on the terminal; and means for the user to input feedback on the confirmed design proposal and retransmit it to the server to request a revision. This enables the generation of appropriate and efficient design proposals that meet user requirements and reflect trends in the proposals. Furthermore, by quickly reflecting user feedback, improved user satisfaction can be expected.

[0593] "User" refers to the end-user who inputs design requirements and reviews and modifies proposed designs.

[0594] "Terminal" refers to a computer or mobile device used by a user to input design requirements and review proposed designs.

[0595] "Server" refers to the central computing system that analyzes design requirements, generates and proposes designs, and analyzes market trends and forecasts trends.

[0596] "Design requirements" refers to specific design requests and conditions entered by the user, such as information on use, color, material, shape, etc.

[0597] "Design Proposal" refers to a specific design or proposal generated by the server based on the user's design requirements.

[0598] "Market Trends" refers to data regarding current and recent market trends and trends.

[0599] "Trend forecasting" refers to the use of AI technology to predict future trends based on market trend data.

[0600] "Analysis" refers to the process of extracting necessary information using natural language processing technology, etc., based on the design requirements received by the server.

[0601] A "request for revision" refers to a user providing feedback on a proposed design and requesting further revisions.

[0602] "Theory" refers to academic foundations such as color theory and design theory that are referenced when generating design proposals.

[0603] "Data" refers to information used to generate design proposals and forecast trends, such as trend data, user data, and market data.

[0604] This invention relates to a system in which a server analyzes design requirements entered by a user, generates optimal design proposals, and makes proposals that reflect the latest market trends.

[0605] System Overview

[0606] This system works by linking terminals and a server to generate design proposals based on design requirements entered by users and make proposals that take market trends into account. Specifically, it uses the following hardware and software:

[0607] Hardware

[0608] Device: A device such as a computer or smartphone operated by a user.

[0609] Server: A central computing system that performs data analysis, design generation, and trend forecasting.

[0610] software

[0611] Natural Language Processing (NLP) engine: Software for analyzing user-entered design requirements.

[0612] Generative AI model: AI for generating design proposals from analyzed requirements data.

[0613] Trend Forecasting Algorithms: Algorithms for analyzing the latest market trends and predicting future trends.

[0614] Program processing explanation

[0615] The user uses the device interface to input design requirements, such as specific requirements like "summer casual dress," "bright color," and "breathable material." The device then structures this information as data and sends it to the server using an HTTP POST request.

[0616] The server first stores the received data in a database, then analyzes the input data using a natural language processing (NLP) engine, extracting specific keywords such as "summer," "casual," "bright colors," and "breathable materials."

[0617] Based on the analyzed requirements data, the server uses a generative AI model to generate design proposals, taking into account the following factors:

[0618] Color suggestions: The server refers to color theory and the latest trend data and suggests bright colors such as yellow or light blue for a "casual summer dress," for example.

[0619] Style suggestions: The server will suggest styles such as A-line dresses or midi dresses depending on the season and purpose.

[0620] Material suggestions: The server will suggest breathable materials such as linen and cotton.

[0621] The server then uses trend prediction algorithms to gather data from fashion blogs, social media, and shopping sites to analyze the latest market trends. For example, if minimalist design is predicted to be popular, the server generates design proposals based on that.

[0622] The generated design proposals and trend forecast results are sent from the server to the terminal, which receives them and displays visual images, color palettes, material lists, etc. to the user. The user can check the proposed design proposals on the terminal, enter feedback if necessary, and resubmit them to the server to request design revisions.

[0623] Specific examples

[0624] Example 1: Designing a casual summer dress

[0625] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[0626] 2. The device sends the input data to the server.

[0627] 3. Server analyzes: extracts keywords (summer, casual, bright colors, breathable)

[0628] 4. Server generated:

[0629] Color suggestions: Yellow, light blue, white

[0630] Suggested styles: A-line dress, midi length

[0631] Material suggestions: linen, cotton

[0632] 5. Server predicts trend: Minimalist design is in vogue

[0633] 6. The server sends the design proposal and trend prediction results to the terminal.

[0634] 7. User confirms: Check the visual image and material details and finalize the design

[0635] Example 2: Winter office accessories

[0636] 1. User types: "winter office accessories," "elegant design," "silver"

[0637] 2. The device sends the input data to the server.

[0638] 3. Server analyzes: Keywords (winter, office, elegant, silver) are extracted

[0639] 4. Server generated:

[0640] Color suggestions: Silver, black, navy

[0641] Shape suggestion: simple lines, modern design

[0642] Material suggestions: Silver, stainless steel

[0643] 5. Server predicts trend: Minimalist jewelry is trending

[0644] 6. The server sends the design proposal and trend prediction results to the terminal.

[0645] 7. User review: Check the visual image and material details and request fine-tuning if necessary

[0646] Prompt Sentence Examples

[0647] "Casual summer dress," "bright color," "breathable material"

[0648] "Winter office accessories," "elegant design," "silver"

[0649] This makes it possible to generate and propose appropriate and efficient design proposals that meet the user's requirements.

[0650] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0651] Step 1:

[0652] The user uses the device interface to input design requirements, such as "a casual summer dress," "bright color," and "breathable material." This input data is structured on the device and prepared for the next processing step.

[0653] Input: User-entered design requirements (e.g., "casual summer dress," "bright color," "breathable material").

[0654] Output: Structured design requirements data.

[0655] Step 2:

[0656] The device sends structured design requirement data to the server via an HTTP POST request, using the HTTPS protocol to keep the data secure.

[0657] Input: Structured design requirements data.

[0658] Output: The data sent as an HTTP POST request.

[0659] Step 3:

[0660] The server first stores the received data in a database. It then analyzes the data using a natural language processing (NLP) engine to extract important keywords and concepts from the user's requirements. For example, keywords such as "summer," "casual," "light colors," and "breathable" are extracted.

[0661] Input: The data sent as an HTTP POST request.

[0662] Output: Extracted keywords and concepts (e.g., "summer," "casual," "light colors," "breathable").

[0663] Step 4:

[0664] The server uses a generative AI model to generate design proposals from the analyzed requirements data, taking into account the following factors:

[0665] Color suggestions: Based on color theory and the latest trend data, colors such as "yellow," "light blue," and "white" are suggested.

[0666] Shape suggestions: Depending on the purpose and season, we will suggest shapes such as "A-line dress" or "midi length."

[0667] Material suggestions: We suggest "linen" and "cotton" as breathable materials.

[0668] Input: Extracted keywords and concepts.

[0669] Output: Design proposals with suggested colors, shapes, and materials.

[0670] Step 5:

[0671] The server uses trend prediction algorithms to collect data from fashion blogs, social media, and shopping sites on the Internet and analyze the latest market trends. For example, it predicts that minimalist design is trending.

[0672] Input: Market trend data from the internet.

[0673] Output: Future trend prediction results (e.g. minimalist design will be popular).

[0674] Step 6:

[0675] The server sends the generated design proposals and trend forecast results as an HTTP response to the terminal, which receives them and displays them visually to the user. The displayed content includes visual images, color palettes, material lists, etc.

[0676] Input: Design proposals and trend forecast results.

[0677] Output: The data sent as the HTTP response.

[0678] Step 7:

[0679] The user checks the proposed design on the terminal, and if the user is satisfied, confirms it as is, enters feedback as necessary, and resubmits it to the server to request corrections.

[0680] Input: Design proposals and trend forecast results.

[0681] Output: User feedback or design confirmation.

[0682] (Application example 1)

[0683] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0684] Conventional design systems have difficulty quickly generating design proposals that accurately reflect user requirements, and it is even more difficult to reflect market trends. As a result, user satisfaction is low and design quality is inconsistent. In addition, there is a lack of ways for users to specifically check and edit proposed design proposals, which means that they are unable to see the actual product when selling online.

[0685] 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.

[0686] In this invention, the server includes means for accepting design requirements input by a user, means for transmitting the design requirement data to the server, means for analyzing the accepted design requirements, means for generating design proposals based on the analyzed design requirements, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to a terminal, means for the user to check the design proposals displayed on the terminal, means for the user to check the design proposals and provide feedback or edit them, and means for providing the generated design proposals to the user and allowing them to check them online in a form close to the real thing. This enables the rapid generation of high-quality design proposals based on user requirements and proposals that reflect market trends, as well as the user to specifically check and edit the design proposals online.

[0687] "Means for accepting design requirements input by a user" refers to an interface through which a user inputs requirements regarding a desired design and the system receives them.

[0688] "Means for transmitting design requirement data to a server" refers to the process or technology for transmitting design requirement data entered at a terminal to a server via a network.

[0689] The "means for analyzing received design requirements" refers to a technology for analyzing the design requirement data sent to the server and extracting and structuring the necessary information.

[0690] "Means for generating design proposals based on analyzed design requirements" refers to a system that uses AI and other technologies to generate actual design proposals based on analyzed design requirement data.

[0691] "Means of analyzing the latest market trends and predicting future trends" refers to algorithms and technologies that collect the latest market trends as data and analyze it to predict future trends.

[0692] "Means for transmitting the generated design proposals and trend prediction results to the terminal" refers to the process or technology for transmitting the design proposals and trend prediction results generated by the server to the terminal being used by the user.

[0693] "Means for users to check the design proposals displayed on their devices" refers to the function that allows users to view and check the sent design proposals on the screen of their devices.

[0694] "A means for users to review design proposals and provide feedback or edits" refers to a function that allows users to view design proposals and provide feedback, or modify the design as needed.

[0695] "A means of providing the generated design proposal to the user and allowing them to check it online in a manner close to the actual product" refers to technology that allows the user to see the generated design proposal and check it in an online environment in a manner close to the actual product.

[0696] This invention relates to a system in which a server analyzes design requirements entered by a user, generates optimal design proposals, and makes proposals that reflect trend forecasts. A specific method for realizing this system is described below.

[0697] System program generation and implementation method

[0698] This system operates in cooperation with the server and the terminal used by the user. The main processing steps are as follows:

[0699] Hardware and Software

[0700] Devices: Smartphones, tablets, computers, and other devices

[0701] Server: Cloud server or on-premise server

[0702] Network: Internet connection

[0703] Languages ​​and libraries used: Python, NLP libraries (e.g., NLTK, spaCy), machine learning libraries (e.g., TensorFlow, PyTorch), HTTP communication libraries (e.g., Requests)

[0704] Processing description

[0705] User inputs design requirements

[0706] Users input design requirements using a smartphone or PC interface, for example, by typing specific requirements such as "casual jacket for spring," "pastel color," and "waterproof material" into text boxes.

[0707] The device sends the input data to the server

[0708] The entered design requirement data is sent to the server via the Internet by an HTTP POST request.

[0709] The server analyzes the requirements

[0710] The server analyzes the received design requirements data and uses natural language processing (NLP) technology to extract and structure specific keywords (such as "spring," "casual," "pastel colors," and "waterproof") from the input text.

[0711] The server generates design proposals

[0712] The AI ​​model installed on the server generates design proposals based on the analyzed requirements data, using color theory and the latest trend data to suggest appropriate color combinations, shapes, silhouettes, materials, etc.

[0713] The server makes trend predictions

[0714] The server analyzes the latest market trends and applies algorithms to predict future trends, analysing data collected from online sources such as fashion blogs, social media, and shopping sites.

[0715] Send the final design to your device

[0716] The generated design proposals and trend forecast results are sent from the server to the user's device, where they can be viewed. Visual images, color palettes, material lists, and more are displayed.

[0717] Users can review the design proposal and provide feedback or edits

[0718] After reviewing the proposed design on their device, users can provide feedback and make any necessary revisions to the design. Once the final design is confirmed, they will also be given the option to purchase it online.

[0719] Examples of specific examples and prompts

[0720] For example, if a user enters "casual spring jacket," "pastel color," and "waterproof material," the system will do the following:

[0721] Input prompt statement:

[0722] Casual jacket for spring

[0723] "Pastel colors"

[0724] Waterproof material

[0725] This system allows users to quickly obtain high-quality design proposals that meet their requirements and also allows them to receive proposals that reflect market trends. Furthermore, users can confirm and edit the proposed design proposals in detail, improving the online purchasing experience.

[0726] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0727] Step 1:

[0728] User inputs design requirements

[0729] The user uses the terminal interface to input design requirements. Examples of input requirements include "casual jacket for spring," "pastel color," and "waterproof material." The terminal structures this as text data and prepares it for the next processing step. The input data is the design requirements in text format. The output is structured design requirement data.

[0730] Step 2:

[0731] The device sends the input data to the server

[0732] The structured design requirement data is sent from the terminal to the server. Here, the data is transferred via the Internet by an HTTP POST request. The input data is the structured design requirement data, and the output is the design requirement data sent to the server.

[0733] Step 3:

[0734] The server analyzes the requirements

[0735] The server analyzes the received design requirements data and uses natural language processing (NLP) technology to extract and structure specific keywords (such as "spring," "casual," "pastel colors," and "waterproof") from the user's requirements. Here, the input data is the design requirements data received by the server, and the output is the identified keywords and their understanding.

[0736] Step 4:

[0737] The server generates design proposals

[0738] A generative AI model installed on the server generates design proposals based on the analyzed requirement data. Based on color theory and the latest trend data, it suggests appropriate color combinations, shapes, silhouettes, materials, etc. The input data are identified requirement keywords, and the output is the generated design proposals.

[0739] Step 5:

[0740] The server makes trend predictions

[0741] The server collects the latest market trend data from online sources such as fashion blogs, social media, and shopping sites, and applies a trend prediction algorithm to predict future trends. The input data is the collected market trend data, and the output is the trend prediction results.

[0742] Step 6:

[0743] The server sends design proposals and trend forecast results to the terminal.

[0744] The generated design proposals and trend prediction results are sent from the server to the terminal, where the user can check them. The input data are the generated design proposals and trend prediction results, and the output is the design proposals and trend prediction results displayed on the terminal.

[0745] Step 7:

[0746] Users can review the design proposal and provide feedback or edits

[0747] The user checks the design proposal displayed on the terminal. The user can provide feedback on the design proposal or edit the design as needed. The input data is the displayed design proposal, and the output is the feedback or edited design proposal.

[0748] Step 8:

[0749] Users can check the actual product online

[0750] The system provides the generated design proposal to the user and allows them to check it online in a form close to the real thing. This allows the user to check the design in detail. The input data is the generated design proposal, and the output is a design proposal displayed in a form close to the real thing.

[0751] 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.

[0752] This invention relates to a system in which a server analyzes and generates optimal design proposals based on design requirements and emotional information input by a user, and makes proposals that reflect trend predictions.

[0753] System Overview

[0754] This system consists of a terminal, a server, and an emotion engine. Its unique feature is that it recognizes the user's emotional information in addition to the design requirements input by the user, and reflects this information in the design proposal.

[0755] Explanation of program processing

[0756] Step 1: User enters design requirements

[0757] The user uses the device interface to input design requirements, such as "a casual summer dress," "bright color," and "breathable material," for each specific item.

[0758] Step 2: The emotion engine recognizes the user's emotion

[0759] The emotion engine analyzes the user's facial expressions, voice, text, etc. to recognize the user's emotional state, for example, determining whether the user is happy, excited, calm, etc.

[0760] Step 3: The device sends the input data and emotion data to the server.

[0761] The device sends the design requirement data and emotion data entered by the user to the server via an HTTP POST request.

[0762] Step 4: The server parses the data

[0763] The server analyzes the received design requirements and emotion data. It uses natural language processing (NLP) technology to extract necessary information from the design requirements and combines it with the emotion information obtained from the emotion engine for analysis. For example, it organizes information such as "summer," "casual," "bright color," "breathable," "happy," and "calm."

[0764] Step 5: The server generates a design proposal

[0765] The server uses the AI ​​model to generate design proposals from the analyzed requirements and sentiment data, taking into account the following factors:

[0766] Color suggestions: Select the optimal color combination based on color theory and the latest trend data. For example, if the emotion is "happiness," suggest "yellow" or "light blue."

[0767] Shape suggestions: We suggest the best shape and silhouette for each occasion and season, such as "A-line dress" or "midi length."

[0768] Material suggestions: Materials are selected based on functionality, user requests, and trends. For example, "linen" and "cotton" are suggested.

[0769] Step 6: The server makes a trend prediction

[0770] The server analyzes the latest market trends and applies algorithms to predict future trends. It collects data from online fashion blogs, social media, shopping sites, and other sources and uses AI to analyze it.

[0771] Step 7: Send the final design to your device

[0772] The generated design proposals and trend forecast results are sent from the server to the device, which receives them and displays them to the user, such as visual images, color palettes, and material lists.

[0773] Step 8: User reviews the design

[0774] The user can review the proposed design on their device, provide feedback if necessary, and request revisions to the design by resubmitting it to the server.

[0775] Specific examples

[0776] Example 1: Emotion-based casual summer dress design

[0777] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[0778] 2. Emotion engine recognizes: User's emotions are "happy" and "excited"

[0779] 3. The device sends input data and emotion data to the server.

[0780] 4. Server analyzes: extracts keywords (summer, casual, bright colors, breathable, happy, excited)

[0781] 5. Server generated:

[0782] Color suggestions: Yellow, light blue

[0783] Suggested styles: A-line dress, midi length

[0784] Material suggestions: linen, cotton

[0785] 6. Server predicts trend: Minimalist design is in vogue

[0786] 7. The server sends the design proposal and trend prediction results to the device.

[0787] 8. User confirms: Check the visual image and material details and finalize the design

[0788] Example 2: Emotion-based winter accessories for the office

[0789] 1. User types: "winter office accessories," "elegant design," "silver"

[0790] 2. Emotion engine recognizes: User's emotions are "calm" and "confident"

[0791] 3. The device sends input data and emotion data to the server.

[0792] 4. Server analyzes: extracts keywords (winter, office, elegant, silver, calm, confident)

[0793] 5. Server generated:

[0794] Color suggestions: Silver, black, navy

[0795] Shape suggestion: simple lines, modern design

[0796] Material suggestions: Silver, stainless steel

[0797] 6. Server predicts trend: Minimalist jewelry is trending

[0798] 7. The server sends the design proposal and trend prediction results to the device.

[0799] 8. User review: Check the visual image and material details and request fine-tuning if necessary

[0800] The system takes into account the user's design requirements and emotional state to deliver more personalized and high-quality design suggestions.

[0801] The processing flow will be explained below.

[0802] Step 1:

[0803] The user inputs design requirements using the device interface, for example, specific requirements such as "casual summer dress," "bright color," and "breathable material."

[0804] Step 2:

[0805] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions, voice, text, etc. to recognize the user's emotional state. For example, it analyzes facial expressions through a camera and identifies emotions such as "happiness" or "excitement."

[0806] Step 3:

[0807] The device sends the input data and emotion data to the server. The device sends the design requirement data entered by the user and the emotion data recognized by the emotion engine to the server. Here, an HTTP POST request is used.

[0808] Step 4:

[0809] The server analyzes the received design requirement data and sentiment data. Using natural language processing (NLP) techniques, it extracts keywords (summer, casual, bright colors, breathable, happy, excited) and organizes them as structured data.

[0810] Step 5:

[0811] The server generates design proposals. Using AI models, the server generates design proposals based on the analyzed design requirements and emotional data. It makes suggestions based on the following factors:

[0812] Color Suggestion: Selects the optimal color combination based on color theory and the latest trend data. For example, if the user is "happy," it will suggest bright colors such as "yellow" and "light blue."

[0813] Shape suggestions: The system suggests the best shape and silhouette for each occasion and season. For example, for "casual dresses," it suggests "A-line dresses" and "midi length."

[0814] Material suggestions: Select materials based on functionality, user requests, and trends. For example, suggest "linen" or "cotton" as "materials with good breathability."

[0815] Step 6:

[0816] The server performs trend prediction. The server analyzes the latest market trends and applies algorithms to predict future trends. For example, it collects data from online fashion blogs, social media, shopping sites, etc. and analyzes it using AI.

[0817] Step 7:

[0818] The server integrates the final design proposal. It integrates design proposals based on color, shape, and material, and incorporates trend forecast results to create the final design proposal.

[0819] Step 8:

[0820] The server sends the final design proposal to the terminal. The server sends the generated design proposal and trend prediction results to the terminal using an HTTP POST request.

[0821] Step 9:

[0822] The terminal displays the received design proposal, providing detailed information such as visual images, color palettes, and material lists to the user.

[0823] Step 10:

[0824] The user checks the proposed design. The user checks the proposed design on the terminal and enters feedback as necessary. If corrections are necessary, the requirements are entered again and the process is repeated.

[0825] Example 2

[0826] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0827] Conventional design generation systems did not consider the user's emotional information when proposing designs, making it difficult to provide designs that satisfied the user. It was also difficult to integrate trend forecasts that reflected the latest market trends into the design. For this reason, there was a need for a system that could provide personalized design proposals that met the user's needs.

[0828] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting design requirements input by the user, means for transmitting the design requirement data and user emotion data to the server, means for analyzing the accepted design requirements and emotion information, means for generating design proposals based on the analyzed design requirements and emotion information, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to the terminal, and means for the user to check the design proposals displayed on the terminal and input feedback. This makes it possible to provide personalized design proposals that reflect the user's emotional state and incorporate trend predictions that reflect the latest market trends into the design.

[0829] "Design requirements" are information entered by a user regarding their wishes and conditions regarding a particular design.

[0830] "Emotional data" is information that represents the user's emotional state, and is data collected from facial expressions, voice, and text.

[0831] The "server" is a computer system that generates design proposals, analyzes design requirements and emotional data, and predicts trends.

[0832] "Means for analysis" refers to a method for understanding the input design requirements and emotional data and extracting the necessary information.

[0833] A "generative AI model" is an artificial intelligence algorithm that generates optimal design proposals based on design requirements and emotional data.

[0834] "Trend forecasting" is a method of analyzing the latest market trends and predicting future design trends.

[0835] "Feedback" refers to the act of a user inputting comments or requests for corrections to a design proposal.

[0836] "Color theory" is a theory that studies the impressions and psychological effects that specific colors give to people.

[0837] "Shape and silhouette" are design elements that indicate the appearance and placement of an object.

[0838] A "terminal" is a device to which a user can send input data and view generated design proposals.

[0839] This invention relates to a system in which a server analyzes design requirements and emotional information input by a user, generates optimal design proposals, and makes proposals that reflect trend predictions. The system is composed of a terminal, a server, and an emotion engine.

[0840] Hardware and software used

[0841] 1. Terminal: A device on which users input design requirements and review proposed designs, such as a PC, tablet, or smartphone.

[0842] 2. Server: A computer system for analyzing design requirements and emotion data, generating design proposals, and forecasting trends.

[0843] 3. Emotion engine: Software for collecting and analyzing emotional data from users' facial expressions, voice, and text.

[0844] Data processing and calculation

[0845] 1. Enter your design requirements:

[0846] Users input design requirements through the device interface, such as "casual summer dress," "bright color," and "breathable material," using text fields and drop-down menus.

[0847] 2. Emotional data collection and analysis:

[0848] The device activates an emotion engine, collects facial expressions and voice data from the user via a webcam and microphone, and analyzes input text data and history data to recognize the user's emotional state.

[0849] The emotion engine identifies emotions such as "happy," "excited," and "calm" based on the collected data.

[0850] 3. Sending design and emotion data:

[0851] The device converts the input design requirements and analyzed emotion data into JSON format and sends it to the server via an HTTP POST request.

[0852] 4. Data Analysis:

[0853] The server analyzes the received design requirement data and emotion data. It uses natural language processing (NLP) technology to extract necessary information from the design requirements, and combines it with the emotion information obtained from the emotion engine for analysis. For example, it organizes information such as "summer," "casual," "bright color," "breathable," "happy," and "calm."

[0854] 5. Generate design proposals:

[0855] The server generates design proposals from the analyzed requirements and emotional data using a generative AI model. For example, it suggests colors like "yellow" or "light blue" based on color theory and trend data, shapes like "A-line dress" or "midi length" based on the purpose and season, and materials like "linen" or "cotton" based on functionality and trend data.

[0856] 6. Trend Forecasting:

[0857] The server collects data from fashion blogs, social media, and shopping sites, and uses machine learning algorithms to predict future design trends, such as the popularity of minimalist design.

[0858] 7. Submission of design proposals and trend forecast results:

[0859] The server sends the generated design proposals and trend prediction results via HTTPS to the terminal, which receives them and displays them visually to the user.

[0860] 8. User Acknowledgment and Feedback:

[0861] The user checks the proposed design on the device and, if necessary, sends feedback or correction requests to the server via the device's input interface. The server then generates a new design based on the received feedback and presents it to the device again.

[0862] Specific examples

[0863] Emotion-based summer casual dress design

[0864] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[0865] 2. Emotion engine recognizes: User's emotions are "happy" and "excited"

[0866] 3. The device sends input data and emotion data to the server.

[0867] 4. Server analyzes: extracts keywords (summer, casual, bright colors, breathable, happy, excited)

[0868] 5. Server generated:

[0869] Color suggestions: Yellow, light blue

[0870] Suggested styles: A-line dress, midi length

[0871] Material suggestions: linen, cotton

[0872] 6. Server predicts trend: Minimalist design is in vogue

[0873] 7. The server sends the design proposal and trend prediction results to the device.

[0874] 8. User confirms: Check the visual image and material details and finalize the design

[0875] Prompt Sentence Examples

[0876] "Imagine a design for a casual summer dress. The color should be bright and the material should be breathable. The user's emotions should be happy and excited."

[0877] "Imagine designing winter office accessories. The design is elegant and the color is silver. The user emotions are calm and confident."

[0878] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0879] Step 1:

[0880] The user inputs the design requirements using the terminal interface.

[0881] Specifically, users use text fields and drop-down menus to input requirements such as "casual summer dress," "light color," and "breathable material."

[0882] Input: Design requirements (text format)

[0883] Output: Input design requirements (internal data of the device)

[0884] Step 2:

[0885] The terminal starts the emotion engine and starts collecting the user's emotion data.

[0886] Specifically, the emotion engine collects facial and voice data from the user via a webcam and microphone, and also analyzes the input text data, allowing it to classify the user's emotional state into categories such as "happy," "excited," or "calm."

[0887] Input: User's facial expression data, voice data, text data

[0888] Output: Analyzed emotion information (categorical data)

[0889] Step 3:

[0890] The terminal transmits the input design requirement data and the analyzed emotion data to the server.

[0891] Specifically, this data is converted into JSON format and sent to the server as an HTTP POST request.

[0892] Input: Design requirements data, emotion data (JSON format)

[0893] Output: HTTP POST request to the server

[0894] Step 4:

[0895] The server analyzes the received design requirement data and emotion data.

[0896] Specifically, it uses natural language processing (NLP) technology to extract important information from design requirements and process it in combination with emotional information, for example, extracting keywords such as "summer," "casual," "bright colors," "breathable," "happy," and "excited" from the input data.

[0897] Input: Design requirement data (text format), emotion data (categorical data)

[0898] Output: Extracted keywords and analysis information

[0899] Step 5:

[0900] The server uses a generative AI model to generate design proposals.

[0901] Specifically, it generates design proposals based on analyzed requirements and emotional data, as well as color theory and trend data. For example, it suggests colors like "yellow" and "light blue," suggests styles like "A-line dress" and "midi length," and selects materials like "linen" and "cotton."

[0902] Input: Extracted keywords and analysis information

[0903] Output: Generated design proposals (color, shape, material suggestions)

[0904] Step 6:

[0905] The server analyzes the latest market trends and predicts future trends.

[0906] Specifically, the project collects data from online fashion blogs, social media, shopping sites, etc., and uses machine learning algorithms to predict future design trends, such as the trend toward minimalist design.

[0907] Input: Market trend data (web data, social media data, etc.)

[0908] Output: Trend prediction results (future fashion information)

[0909] Step 7:

[0910] The server transmits the generated design proposals and trend prediction results to the terminal.

[0911] This information is sent to the device via HTTPS.

[0912] The device receives this and displays visual images, color palettes, material lists, etc. on a dashboard or preview screen.

[0913] Input: Generated design proposals, trend prediction results

[0914] Output: Design proposals and trend information displayed to the user

[0915] Step 8:

[0916] The user checks the proposed design on the device.

[0917] If necessary, feedback or correction requests can be resubmitted to the server via the input interface of the device, and the server will generate new design proposals based on the received feedback and present them to the device again.

[0918] Input: Feedback information (user comments, correction requests, etc.)

[0919] Output: Revised design proposal (design proposal resent from server)

[0920] (Application example 2)

[0921] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0922] Conventional design generation systems generate design proposals based solely on user input data. This makes it difficult to propose designs that reflect the user's emotions and psychological state, and fails to sufficiently improve user satisfaction. Furthermore, it is difficult to accurately reflect the latest market trends and future trends, making it an inappropriate solution for virtual stores, which must always incorporate the latest trends.

[0923] The specification processing by the specification 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 accepting design requirements input by a user, means for transmitting the design requirement data to the server, means for analyzing the accepted design requirements, means for generating design proposals based on the analyzed design requirements and the user's emotional state, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to the terminal, means for the user to confirm the design proposals displayed on the terminal, and means for recognizing the user's emotional state using facial recognition and voice recognition. This enables personalized design proposals that take the user's emotional state into consideration, thereby increasing user satisfaction. Furthermore, design proposals that reflect the latest market trends and future trends can be made.

[0924] "Design requirements" refer to the design features and conditions desired by the user.

[0925] A "server" is a computer system that provides services and information to other devices on a network.

[0926] "Analysis" means examining data or information in detail to clarify its structure and meaning.

[0927] "Emotional state" refers to the user's psychological state or mood, and is information that can be inferred from facial expressions and voice.

[0928] A "design proposal" is a specific design proposal generated based on the analyzed data and requirements.

[0929] "Market trends" refers to current market trends and consumer preferences.

[0930] "Trend forecasting" is analysis to predict future consumer preferences and market changes.

[0931] A "terminal" is an electronic device that allows a user to input information and check the display.

[0932] "Facial recognition" is a technology that uses a camera to identify an individual's face and analyze its features.

[0933] "Speech recognition" is a technology that uses a microphone to convert voice data into text data.

[0934] "Personalization" refers to customization according to the needs and preferences of individual users.

[0935] A "visual image" is a picture or figure that is displayed in a visual form.

[0936] This invention is a system in which a server generates optimal design proposals based on the user's design requirements and emotional information, and makes proposals that reflect the latest market trends. Specifically, the system allows the user to input design requirements using a terminal and recognize emotional information, enabling personalized design proposals.

[0937] Hardware and Software Use

[0938] Device:

[0939] Smartphone (using an application that implements React Native)

[0940] Smartphone camera (using OpenCV for facial recognition)

[0941] Smartphone microphone (voice recognition is performed using the Google Cloud Speech-to-Text API)

[0942] server:

[0943] Server system (built using Python Flask)

[0944] Natural language processing libraries (using SpaCy and GPT-4)

[0945] AI models (using TensorFlow or PyTorch)

[0946] Data processing and calculation

[0947] 1. Design requirements and receiving emotional information:

[0948] The user inputs design requirements, such as "autumn jacket," "warm material," and "modern design," through the smartphone interface. At the same time, the smartphone's camera and microphone are used for facial and voice recognition to capture the user's emotional state (e.g., "relaxed" or "satisfied").

[0949] 2. Data transmission:

[0950] The device sends the user's design requirement data and emotion data to the server via an HTTP POST request.

[0951] 3. Data analysis and design generation:

[0952] The server analyzes the received design requirement data using a natural language processing library (such as SpaCy) to extract keywords. At the same time, it also analyzes sentiment data. Based on this data, it uses an AI model (a generative AI model using TensorFlow or PyTorch) to generate optimal design proposals.

[0953] 4. Trend Forecasting:

[0954] The server collects data from online fashion blogs, social media, shopping sites, and other sources, and uses AI to analyze market trends and predict future trends. These trend predictions are also reflected in design proposals.

[0955] 5. Design proposal submission:

[0956] The final design proposals and trend forecast results are sent from the server to the user's device and displayed for review, allowing the user to check the visual image, color palette, material list, and other details.

[0957] Specific examples

[0958] If a user is looking for a fall jacket:

[0959] The user types "autumn jacket," "warm material," and "modern design" into their smartphone, and the camera and microphone are used to recognize the emotional states of "relaxed" and "satisfied."

[0960] The server analyzes this data and suggests the most suitable color (e.g., "olive green" or "brown"), shape (e.g., "slim fit"), material (e.g., "wool"), etc.

[0961] The server analyzes the latest market trends and sends the generated design proposals and trend forecast results to the smartphone.

[0962] The user checks visual images and detailed design proposals and makes the final selection.

[0963] Prompt Sentence Examples

[0964] "Generate detailed design proposals for a fall jacket made of warm material with a modern design that is perfect for customers with a relaxed feel."

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

[0966] Step 1:

[0967] The user inputs the design requirements. Using the smartphone interface, the user inputs design requirements such as "autumn jacket," "warm material," and "modern design" in text. This input serves as the basis for data processing in each subsequent step.

[0968] Step 2:

[0969] The device recognizes emotional information. It uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and then performs facial recognition (using OpenCV) and voice recognition (using Google Cloud Speech-to-Text API). Through this process, the device identifies the user's emotional state as "relaxed" or "satisfied," for example. Emotional information is extracted from the user's facial expression and voice data using an emotion recognition algorithm.

[0970] Step 3:

[0971] The terminal sends the design requirement data and emotion data to the server. The terminal sends the design requirement data and emotion data entered by the user to the server via an HTTP POST request. The sent data includes text (design requirement) and emotion state (relaxed, satisfied, etc.).

[0972] Step 4:

[0973] The server analyzes the data. The server uses natural language processing (SpaCy or GPT-4) to analyze the received design requirement data and extract keywords. At the same time, it also analyzes the emotional data. As a result of this analysis, keywords such as "autumn," "jacket," "warm," and "modern" and emotional states such as "relaxed" and "satisfied" are obtained.

[0974] Step 5:

[0975] The server generates design proposals using a generative AI model (using TensorFlow or PyTorch) based on the analyzed requirements and sentiment data. The server suggests optimal colors ("olive green" or "brown"), shapes ("slim fit"), and materials ("wool"), for example. The AI ​​model is trained on a large amount of design data and generates design proposals by referencing related data.

[0976] Step 6:

[0977] The server analyzes the latest market trends and makes trend predictions. The server collects data from online fashion blogs, social media, shopping sites, etc. and uses AI to analyze market trends. Based on these results, future trends are predicted and incorporated into design proposals.

[0978] Step 7:

[0979] The server sends the generated design proposal and trend prediction results to the terminal. The server then sends the final generated design proposal and trend prediction results to the terminal as an HTTP response, which includes detailed information such as visual images, color palettes, and material lists.

[0980] Step 8:

[0981] The user checks the proposed design on their device. The user can check the design proposals and trend prediction results sent to the device on their smartphone screen and make corrections or feedback as necessary. For example, they can input a request for correction, such as "I want the color to be a little darker," and send it back to the server to fine-tune the design.

[0982] The above is the flow of specific processing steps, which enables personalized design proposals based on the user's needs and emotions.

[0983] 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.

[0984] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0985] 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.

[0986] [Third embodiment]

[0987] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0988] 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.

[0989] 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).

[0990] 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.

[0991] 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.

[0992] 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).

[0993] 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.

[0994] 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.

[0995] 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.

[0996] 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.

[0997] 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.

[0998] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0999] This invention relates to a system in which a server analyzes design requirements input by a user, generates optimal design proposals, and makes proposals that reflect trend predictions.

[1000] System Overview

[1001] This system works in conjunction with the terminal and server to generate design proposals based on the design requirements entered by the user, and makes proposals that take trend elements into account. Below are specific processing and examples of the program.

[1002] Explanation of program processing

[1003] Step 1: User enters design requirements

[1004] The user uses the device interface to input design requirements, such as specific requirements like "a casual summer dress," "bright color," and "breathable material." This information is structured as data on the device and then passed on to the next processing step.

[1005] Step 2: The device sends the input data to the server

[1006] The terminal sends the design requirement data entered by the user to the server, which transfers the data via the Internet using an HTTP POST request.

[1007] Step 3: The server analyzes the requirements

[1008] The server analyzes the received data using natural language processing (NLP) technology to extract and structure the necessary information from the user's requirements. For example, it extracts specific keywords such as "summer," "casual," "bright colors," and "breathable materials."

[1009] Step 4: The server generates a design proposal

[1010] The server generates design proposals from the requirements data analyzed using the AI ​​model, taking into account the following factors:

[1011] Color Suggestion: Based on color theory and the latest trend data, it suggests the best color combinations. For example, it suggests bright colors such as yellow and light blue for summer dresses.

[1012] Shape suggestions: We suggest shapes and silhouettes that are suitable for different occasions and seasons. For example, A-line dresses and midi lengths are suggested for casual wear.

[1013] Material suggestions: Select the appropriate material based on functionality and trends. For example, breathable linen or cotton is suggested.

[1014] Step 5: The server makes a trend prediction

[1015] The server analyzes the latest market trends and applies algorithms to predict future trends. Here, data is collected from online sources such as fashion blogs, social media, and shopping sites, and analyzed using AI.

[1016] Step 6: Send the final design to your device

[1017] The generated design proposals and trend forecast results are sent from the server to the device, which receives them and displays them to the user, such as visual images, color palettes, and material lists.

[1018] Step 7: User reviews the design

[1019] The user can review the proposed design on their device, provide feedback if necessary, and request revisions to the design by resubmitting it to the server.

[1020] Specific examples

[1021] Example 1: Summer casual dress design

[1022] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[1023] 2. The device sends the input data to the server.

[1024] 3. Server analyzes: extracts keywords (summer, casual, bright colors, breathable)

[1025] 4. Server generated:

[1026] Color suggestions: Yellow, light blue, white

[1027] Suggested styles: A-line dress, midi length

[1028] Material suggestions: linen, cotton

[1029] 5. Server predicts trend: Minimalist design is in vogue

[1030] 6. The server sends the design proposal and trend prediction results to the device.

[1031] 7. User confirms: Check the visual image and material details and finalize the design

[1032] Example 2: Winter accessories for the office

[1033] 1. User types: "winter office accessories," "elegant design," "silver"

[1034] 2. The device sends the input data to the server.

[1035] 3. Server analyzes: Keywords (winter, office, elegant, silver) are extracted

[1036] 4. Server generated:

[1037] Color suggestions: Silver, black, navy

[1038] Shape suggestion: simple lines, modern design

[1039] Material suggestions: Silver, stainless steel

[1040] 5. Server predicts trend: Minimalist jewelry is trending

[1041] 6. The server sends the design proposal and trend prediction results to the device.

[1042] 7. User review: Check the visual image and material details and request fine-tuning if necessary

[1043] As shown in these examples, the system can provide efficient and high-quality designs based on the user's requirements.

[1044] The processing flow will be explained below.

[1045] Step 1:

[1046] The user inputs design requirements using the device interface, for example, specific requirements such as "casual summer dress," "bright color," and "breathable material."

[1047] Step 2:

[1048] The terminal sends the input design requirement data to the server. Specifically, the user input data is passed to the server via an HTTP POST request.

[1049] Step 3:

[1050] The server analyzes the received data and uses natural language processing (NLP) technology to extract and structure the necessary information from the user's requirements, organizing keywords such as "summer," "casual," "bright colors," and "breathable."

[1051] Step 4:

[1052] The server makes color suggestions based on the design requirements. It selects the optimal color combination by referring to color theory and trend data. For example, suggestions such as "yellow," "light blue," and "white" are made.

[1053] Step 5:

[1054] The server will suggest shapes and silhouettes that are best suited to the user's purpose and the season, such as "A-line dress" or "midi length."

[1055] Step 6:

[1056] The server will suggest materials based on functionality, user requests, and trends. For example, "linen" or "cotton" may be suggested.

[1057] Step 7:

[1058] The server applies trend prediction algorithms, analyzes current market trends, and collects and analyzes data to predict future trends, for example, by utilizing information from online fashion blogs and social media.

[1059] Step 8:

[1060] The server synthesizes the final design proposals. Design proposals are synthesized based on color, shape, and material, and a final proposal is created that reflects the trend forecast results.

[1061] Step 9:

[1062] The server sends the final design proposal to the device using an HTTP POST request, along with the generated design proposal and trend prediction results.

[1063] Step 10:

[1064] The terminal displays the received design proposal, providing detailed information such as visual images, color palettes, and material lists to the user.

[1065] Step 11:

[1066] The user checks the design proposal and provides feedback as needed. If corrections are needed, the requirements are entered again and the process is repeated.

[1067] Example 1

[1068] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1069] In modern design, it is difficult for users to efficiently find designs that meet their requirements, which consumes a lot of time and effort. It is also difficult to quickly incorporate market trends and reflect them in designs. In conventional systems, even if users provide specific feedback, it takes time for it to be reflected, resulting in a decrease in satisfaction.

[1070] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1071] In this invention, the server includes: means for accepting design requirements input by a user; means for transmitting the design requirement data to the server; means for analyzing the accepted design requirements; means for generating a design proposal based on the analyzed design requirements; means for analyzing the latest market trends and predicting future trends; means for transmitting the generated design proposal and the trend prediction results to a terminal; means for the user to confirm the design proposal displayed on the terminal; and means for the user to input feedback on the confirmed design proposal and retransmit it to the server to request a revision. This enables the generation of appropriate and efficient design proposals that meet user requirements and reflect trends in the proposals. Furthermore, by quickly reflecting user feedback, improved user satisfaction can be expected.

[1072] "User" refers to the end-user who inputs design requirements and reviews and modifies proposed designs.

[1073] "Terminal" refers to a computer or mobile device used by a user to input design requirements and review proposed designs.

[1074] "Server" refers to the central computing system that analyzes design requirements, generates and proposes designs, and analyzes market trends and forecasts trends.

[1075] "Design requirements" refers to specific design requests and conditions entered by the user, such as information on use, color, material, shape, etc.

[1076] "Design Proposal" refers to a specific design or proposal generated by the server based on the user's design requirements.

[1077] "Market Trends" refers to data regarding current and recent market trends and trends.

[1078] "Trend forecasting" refers to the use of AI technology to predict future trends based on market trend data.

[1079] "Analysis" refers to the process of extracting necessary information using natural language processing technology, etc., based on the design requirements received by the server.

[1080] A "request for revision" refers to a user providing feedback on a proposed design and requesting further revisions.

[1081] "Theory" refers to academic foundations such as color theory and design theory that are referenced when generating design proposals.

[1082] "Data" refers to information used to generate design proposals and forecast trends, such as trend data, user data, and market data.

[1083] This invention relates to a system in which a server analyzes design requirements entered by a user, generates optimal design proposals, and makes proposals that reflect the latest market trends.

[1084] System Overview

[1085] This system works by linking terminals and a server to generate design proposals based on design requirements entered by users and make proposals that take market trends into account. Specifically, it uses the following hardware and software:

[1086] Hardware

[1087] Device: A device such as a computer or smartphone operated by a user.

[1088] Server: A central computing system that performs data analysis, design generation, and trend forecasting.

[1089] software

[1090] Natural Language Processing (NLP) engine: Software for analyzing user-entered design requirements.

[1091] Generative AI model: AI for generating design proposals from analyzed requirements data.

[1092] Trend Forecasting Algorithms: Algorithms for analyzing the latest market trends and predicting future trends.

[1093] Program processing explanation

[1094] The user uses the device interface to input design requirements, such as specific requirements like "summer casual dress," "bright color," and "breathable material." The device then structures this information as data and sends it to the server using an HTTP POST request.

[1095] The server first stores the received data in a database, then analyzes the input data using a natural language processing (NLP) engine, extracting specific keywords such as "summer," "casual," "bright colors," and "breathable materials."

[1096] Based on the analyzed requirements data, the server uses a generative AI model to generate design proposals, taking into account the following factors:

[1097] Color suggestions: The server refers to color theory and the latest trend data and suggests bright colors such as yellow or light blue for a "casual summer dress," for example.

[1098] Style suggestions: The server will suggest styles such as A-line dresses or midi dresses depending on the season and purpose.

[1099] Material suggestions: The server will suggest breathable materials such as linen and cotton.

[1100] The server then uses trend prediction algorithms to gather data from fashion blogs, social media, and shopping sites to analyze the latest market trends. For example, if minimalist design is predicted to be popular, the server generates design proposals based on that.

[1101] The generated design proposals and trend forecast results are sent from the server to the terminal, which receives them and displays visual images, color palettes, material lists, etc. to the user. The user can check the proposed design proposals on the terminal, enter feedback if necessary, and resubmit them to the server to request design revisions.

[1102] Specific examples

[1103] Example 1: Designing a casual summer dress

[1104] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[1105] 2. The device sends the input data to the server.

[1106] 3. Server analyzes: extracts keywords (summer, casual, bright colors, breathable)

[1107] 4. Server generated:

[1108] Color suggestions: Yellow, light blue, white

[1109] Suggested styles: A-line dress, midi length

[1110] Material suggestions: linen, cotton

[1111] 5. Server predicts trend: Minimalist design is in vogue

[1112] 6. The server sends the design proposal and trend prediction results to the terminal.

[1113] 7. User confirms: Check the visual image and material details and finalize the design

[1114] Example 2: Winter office accessories

[1115] 1. User types: "winter office accessories," "elegant design," "silver"

[1116] 2. The device sends the input data to the server.

[1117] 3. Server analyzes: Keywords (winter, office, elegant, silver) are extracted

[1118] 4. Server generated:

[1119] Color suggestions: Silver, black, navy

[1120] Shape suggestion: simple lines, modern design

[1121] Material suggestions: Silver, stainless steel

[1122] 5. Server predicts trend: Minimalist jewelry is trending

[1123] 6. The server sends the design proposal and trend prediction results to the terminal.

[1124] 7. User review: Check the visual image and material details and request fine-tuning if necessary

[1125] Prompt Sentence Examples

[1126] "Casual summer dress," "bright color," "breathable material"

[1127] "Winter office accessories," "elegant design," "silver"

[1128] This makes it possible to generate and propose appropriate and efficient design proposals that meet the user's requirements.

[1129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1130] Step 1:

[1131] The user uses the device interface to input design requirements, such as "a casual summer dress," "bright color," and "breathable material." This input data is structured on the device and prepared for the next processing step.

[1132] Input: User-entered design requirements (e.g., "casual summer dress," "bright color," "breathable material").

[1133] Output: Structured design requirements data.

[1134] Step 2:

[1135] The device sends structured design requirement data to the server via an HTTP POST request, using the HTTPS protocol to keep the data secure.

[1136] Input: Structured design requirements data.

[1137] Output: The data sent as an HTTP POST request.

[1138] Step 3:

[1139] The server first stores the received data in a database. It then analyzes the data using a natural language processing (NLP) engine to extract important keywords and concepts from the user's requirements. For example, keywords such as "summer," "casual," "light colors," and "breathable" are extracted.

[1140] Input: The data sent as an HTTP POST request.

[1141] Output: Extracted keywords and concepts (e.g., "summer," "casual," "light colors," "breathable").

[1142] Step 4:

[1143] The server uses a generative AI model to generate design proposals from the analyzed requirements data, taking into account the following factors:

[1144] Color suggestions: Based on color theory and the latest trend data, colors such as "yellow," "light blue," and "white" are suggested.

[1145] Shape suggestions: Depending on the purpose and season, we will suggest shapes such as "A-line dress" or "midi length."

[1146] Material suggestions: We suggest "linen" and "cotton" as breathable materials.

[1147] Input: Extracted keywords and concepts.

[1148] Output: Design proposals with suggested colors, shapes, and materials.

[1149] Step 5:

[1150] The server uses trend prediction algorithms to collect data from fashion blogs, social media, and shopping sites on the Internet and analyze the latest market trends. For example, it predicts that minimalist design is trending.

[1151] Input: Market trend data from the internet.

[1152] Output: Future trend prediction results (e.g. minimalist design will be popular).

[1153] Step 6:

[1154] The server sends the generated design proposals and trend forecast results as an HTTP response to the terminal, which receives them and displays them visually to the user. The displayed content includes visual images, color palettes, material lists, etc.

[1155] Input: Design proposals and trend forecast results.

[1156] Output: The data sent as the HTTP response.

[1157] Step 7:

[1158] The user checks the proposed design on the terminal, and if the user is satisfied, confirms it as is, enters feedback as necessary, and resubmits it to the server to request corrections.

[1159] Input: Design proposals and trend forecast results.

[1160] Output: User feedback or design confirmation.

[1161] (Application example 1)

[1162] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1163] Conventional design systems have difficulty quickly generating design proposals that accurately reflect user requirements, and it is even more difficult to reflect market trends. As a result, user satisfaction is low and design quality is inconsistent. In addition, there is a lack of ways for users to specifically check and edit proposed design proposals, which means that they are unable to see the actual product when selling online.

[1164] 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.

[1165] In this invention, the server includes means for accepting design requirements input by a user, means for transmitting the design requirement data to the server, means for analyzing the accepted design requirements, means for generating design proposals based on the analyzed design requirements, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to a terminal, means for the user to check the design proposals displayed on the terminal, means for the user to check the design proposals and provide feedback or edit them, and means for providing the generated design proposals to the user and allowing them to check them online in a form close to the real thing. This enables the rapid generation of high-quality design proposals based on user requirements and proposals that reflect market trends, as well as the user to specifically check and edit the design proposals online.

[1166] "Means for accepting design requirements input by a user" refers to an interface through which a user inputs requirements regarding a desired design and the system receives them.

[1167] "Means for transmitting design requirement data to a server" refers to the process or technology for transmitting design requirement data entered at a terminal to a server via a network.

[1168] The "means for analyzing received design requirements" refers to a technology for analyzing the design requirement data sent to the server and extracting and structuring the necessary information.

[1169] "Means for generating design proposals based on analyzed design requirements" refers to a system that uses AI and other technologies to generate actual design proposals based on analyzed design requirement data.

[1170] "Means of analyzing the latest market trends and predicting future trends" refers to algorithms and technologies that collect the latest market trends as data and analyze it to predict future trends.

[1171] "Means for transmitting the generated design proposals and trend prediction results to the terminal" refers to the process or technology for transmitting the design proposals and trend prediction results generated by the server to the terminal being used by the user.

[1172] "Means for users to check the design proposals displayed on their devices" refers to the function that allows users to view and check the sent design proposals on the screen of their devices.

[1173] "A means for users to review design proposals and provide feedback or edits" refers to a function that allows users to view design proposals and provide feedback, or modify the design as needed.

[1174] "A means of providing the generated design proposal to the user and allowing them to check it online in a manner close to the actual product" refers to technology that allows the user to see the generated design proposal and check it in an online environment in a manner close to the actual product.

[1175] This invention relates to a system in which a server analyzes design requirements entered by a user, generates optimal design proposals, and makes proposals that reflect trend forecasts. A specific method for realizing this system is described below.

[1176] System program generation and implementation method

[1177] This system operates in cooperation with the server and the terminal used by the user. The main processing steps are as follows:

[1178] Hardware and Software

[1179] Devices: Smartphones, tablets, computers, and other devices

[1180] Server: Cloud server or on-premise server

[1181] Network: Internet connection

[1182] Languages ​​and libraries used: Python, NLP libraries (e.g., NLTK, spaCy), machine learning libraries (e.g., TensorFlow, PyTorch), HTTP communication libraries (e.g., Requests)

[1183] Processing description

[1184] User inputs design requirements

[1185] Users input design requirements using a smartphone or PC interface, for example, by typing specific requirements such as "casual jacket for spring," "pastel color," and "waterproof material" into text boxes.

[1186] The device sends the input data to the server

[1187] The entered design requirement data is sent to the server via the Internet by an HTTP POST request.

[1188] The server analyzes the requirements

[1189] The server analyzes the received design requirements data and uses natural language processing (NLP) technology to extract and structure specific keywords (such as "spring," "casual," "pastel colors," and "waterproof") from the input text.

[1190] The server generates design proposals

[1191] The AI ​​model installed on the server generates design proposals based on the analyzed requirements data, using color theory and the latest trend data to suggest appropriate color combinations, shapes, silhouettes, materials, etc.

[1192] The server makes trend predictions

[1193] The server analyzes the latest market trends and applies algorithms to predict future trends, analysing data collected from online sources such as fashion blogs, social media, and shopping sites.

[1194] Send the final design to your device

[1195] The generated design proposals and trend forecast results are sent from the server to the user's device, where they can be viewed. Visual images, color palettes, material lists, and more are displayed.

[1196] Users can review the design proposal and provide feedback or edits

[1197] After reviewing the proposed design on their device, users can provide feedback and make any necessary revisions to the design. Once the final design is confirmed, they will also be given the option to purchase it online.

[1198] Examples of concrete examples and prompts

[1199] For example, if a user enters "casual spring jacket," "pastel color," and "waterproof material," the system will do the following:

[1200] Input prompt statement:

[1201] Casual jacket for spring

[1202] "Pastel colors"

[1203] Waterproof material

[1204] This system allows users to quickly obtain high-quality design proposals that meet their requirements and also allows them to receive proposals that reflect market trends. Furthermore, users can confirm and edit the proposed design proposals in detail, improving the online purchasing experience.

[1205] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1206] Step 1:

[1207] User inputs design requirements

[1208] The user uses the terminal interface to input design requirements. Examples of input requirements include "casual jacket for spring," "pastel color," and "waterproof material." The terminal structures this as text data and prepares it for the next processing step. The input data is the design requirements in text format. The output is structured design requirement data.

[1209] Step 2:

[1210] The device sends the input data to the server

[1211] The structured design requirement data is sent from the terminal to the server. Here, the data is transferred via the Internet by an HTTP POST request. The input data is the structured design requirement data, and the output is the design requirement data sent to the server.

[1212] Step 3:

[1213] The server analyzes the requirements

[1214] The server analyzes the received design requirements data and uses natural language processing (NLP) technology to extract and structure specific keywords (such as "spring," "casual," "pastel colors," and "waterproof") from the user's requirements. Here, the input data is the design requirements data received by the server, and the output is the identified keywords and their understanding.

[1215] Step 4:

[1216] The server generates design proposals

[1217] A generative AI model installed on the server generates design proposals based on the analyzed requirement data. Based on color theory and the latest trend data, it suggests appropriate color combinations, shapes, silhouettes, materials, etc. The input data are identified requirement keywords, and the output is the generated design proposals.

[1218] Step 5:

[1219] The server makes trend predictions

[1220] The server collects the latest market trend data from online sources such as fashion blogs, social media, and shopping sites, and applies a trend prediction algorithm to predict future trends. The input data is the collected market trend data, and the output is the trend prediction results.

[1221] Step 6:

[1222] The server sends design proposals and trend forecast results to the terminal.

[1223] The generated design proposals and trend prediction results are sent from the server to the terminal, where the user can check them. The input data are the generated design proposals and trend prediction results, and the output is the design proposals and trend prediction results displayed on the terminal.

[1224] Step 7:

[1225] Users can review the design proposal and provide feedback or edits

[1226] The user checks the design proposal displayed on the terminal. The user can provide feedback on the design proposal or edit the design as needed. The input data is the displayed design proposal, and the output is the feedback or edited design proposal.

[1227] Step 8:

[1228] Users can check the actual product online

[1229] The system provides the generated design proposal to the user and allows them to check it online in a form close to the real thing. This allows the user to check the design in detail. The input data is the generated design proposal, and the output is a design proposal displayed in a form close to the real thing.

[1230] 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.

[1231] This invention relates to a system in which a server analyzes and generates optimal design proposals based on design requirements and emotional information input by a user, and makes proposals that reflect trend predictions.

[1232] System Overview

[1233] This system consists of a terminal, a server, and an emotion engine. Its unique feature is that it recognizes the user's emotional information in addition to the design requirements input by the user, and reflects this information in the design proposal.

[1234] Explanation of program processing

[1235] Step 1: User enters design requirements

[1236] The user uses the device interface to input design requirements, such as "a casual summer dress," "bright color," and "breathable material," for each specific item.

[1237] Step 2: The emotion engine recognizes the user's emotion

[1238] The emotion engine analyzes the user's facial expressions, voice, text, etc. to recognize the user's emotional state, for example, determining whether the user is happy, excited, calm, etc.

[1239] Step 3: The device sends the input data and emotion data to the server.

[1240] The device sends the design requirement data and emotion data entered by the user to the server via an HTTP POST request.

[1241] Step 4: The server parses the data

[1242] The server analyzes the received design requirements and emotion data. It uses natural language processing (NLP) technology to extract necessary information from the design requirements and combines it with the emotion information obtained from the emotion engine for analysis. For example, it organizes information such as "summer," "casual," "bright color," "breathable," "happy," and "calm."

[1243] Step 5: The server generates a design proposal

[1244] The server uses the AI ​​model to generate design proposals from the analyzed requirements and sentiment data, taking into account the following factors:

[1245] Color suggestions: Select the optimal color combination based on color theory and the latest trend data. For example, if the emotion is "happiness," suggest "yellow" or "light blue."

[1246] Shape suggestions: We suggest the best shape and silhouette for each occasion and season, such as "A-line dress" or "midi length."

[1247] Material suggestions: Materials are selected based on functionality, user requests, and trends. For example, "linen" and "cotton" are suggested.

[1248] Step 6: The server makes a trend prediction

[1249] The server analyzes the latest market trends and applies algorithms to predict future trends. It collects data from online fashion blogs, social media, shopping sites, and other sources and uses AI to analyze it.

[1250] Step 7: Send the final design to your device

[1251] The generated design proposals and trend forecast results are sent from the server to the device, which receives them and displays them to the user, such as visual images, color palettes, and material lists.

[1252] Step 8: User reviews the design

[1253] The user can review the proposed design on their device, provide feedback if necessary, and request revisions to the design by resubmitting it to the server.

[1254] Specific examples

[1255] Example 1: Emotion-based casual summer dress design

[1256] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[1257] 2. Emotion engine recognizes: User's emotions are "happy" and "excited"

[1258] 3. The device sends input data and emotion data to the server.

[1259] 4. Server analyzes: extracts keywords (summer, casual, bright colors, breathable, happy, excited)

[1260] 5. Server generated:

[1261] Color suggestions: Yellow, light blue

[1262] Suggested styles: A-line dress, midi length

[1263] Material suggestions: linen, cotton

[1264] 6. Server predicts trend: Minimalist design is in vogue

[1265] 7. The server sends the design proposal and trend prediction results to the device.

[1266] 8. User confirms: Check the visual image and material details and finalize the design

[1267] Example 2: Emotion-based winter accessories for the office

[1268] 1. User types: "winter office accessories," "elegant design," "silver"

[1269] 2. Emotion engine recognizes: User's emotions are "calm" and "confident"

[1270] 3. The device sends input data and emotion data to the server.

[1271] 4. Server analyzes: extracts keywords (winter, office, elegant, silver, calm, confident)

[1272] 5. Server generated:

[1273] Color suggestions: Silver, black, navy

[1274] Shape suggestion: simple lines, modern design

[1275] Material suggestions: Silver, stainless steel

[1276] 6. Server predicts trend: Minimalist jewelry is trending

[1277] 7. The server sends the design proposal and trend prediction results to the device.

[1278] 8. User review: Check the visual image and material details and request fine-tuning if necessary

[1279] The system takes into account the user's design requirements and emotional state to deliver more personalized and high-quality design suggestions.

[1280] The processing flow will be explained below.

[1281] Step 1:

[1282] The user inputs design requirements using the device interface, for example, specific requirements such as "casual summer dress," "bright color," and "breathable material."

[1283] Step 2:

[1284] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions, voice, text, etc. to recognize the user's emotional state. For example, it analyzes facial expressions through a camera and identifies emotions such as "happiness" or "excitement."

[1285] Step 3:

[1286] The device sends the input data and emotion data to the server. The device sends the design requirement data entered by the user and the emotion data recognized by the emotion engine to the server. Here, an HTTP POST request is used.

[1287] Step 4:

[1288] The server analyzes the received design requirement data and sentiment data. Using natural language processing (NLP) techniques, it extracts keywords (summer, casual, bright colors, breathable, happy, excited) and organizes them as structured data.

[1289] Step 5:

[1290] The server generates design proposals. Using AI models, the server generates design proposals based on the analyzed design requirements and emotional data. It makes suggestions based on the following factors:

[1291] Color Suggestion: Selects the optimal color combination based on color theory and the latest trend data. For example, if the user is "happy," it will suggest bright colors such as "yellow" and "light blue."

[1292] Shape suggestions: The system suggests the best shape and silhouette for each occasion and season. For example, for "casual dresses," it suggests "A-line dresses" and "midi length."

[1293] Material suggestions: Select materials based on functionality, user requests, and trends. For example, suggest "linen" or "cotton" as "materials with good breathability."

[1294] Step 6:

[1295] The server performs trend prediction. The server analyzes the latest market trends and applies algorithms to predict future trends. For example, it collects data from online fashion blogs, social media, shopping sites, etc. and analyzes it using AI.

[1296] Step 7:

[1297] The server integrates the final design proposal. It integrates design proposals based on color, shape, and material, and incorporates trend forecast results to create the final design proposal.

[1298] Step 8:

[1299] The server sends the final design proposal to the terminal. The server sends the generated design proposal and trend prediction results to the terminal using an HTTP POST request.

[1300] Step 9:

[1301] The terminal displays the received design proposal, providing detailed information such as visual images, color palettes, and material lists to the user.

[1302] Step 10:

[1303] The user checks the proposed design. The user checks the proposed design on the terminal and enters feedback as necessary. If corrections are necessary, the requirements are entered again and the process is repeated.

[1304] Example 2

[1305] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1306] Conventional design generation systems did not consider the user's emotional information when proposing designs, making it difficult to provide designs that satisfied the user. It was also difficult to integrate trend forecasts that reflected the latest market trends into the design. For this reason, there was a need for a system that could provide personalized design proposals that met the user's needs.

[1307] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting design requirements input by the user, means for transmitting the design requirement data and user emotion data to the server, means for analyzing the accepted design requirements and emotion information, means for generating design proposals based on the analyzed design requirements and emotion information, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to the terminal, and means for the user to check the design proposals displayed on the terminal and input feedback. This makes it possible to provide personalized design proposals that reflect the user's emotional state and incorporate trend predictions that reflect the latest market trends into the design.

[1308] "Design requirements" are information entered by a user regarding their wishes and conditions regarding a particular design.

[1309] "Emotional data" is information that represents the user's emotional state, and is data collected from facial expressions, voice, and text.

[1310] The "server" is a computer system that generates design proposals, analyzes design requirements and emotional data, and predicts trends.

[1311] "Means for analysis" refers to a method for understanding the input design requirements and emotional data and extracting the necessary information.

[1312] A "generative AI model" is an artificial intelligence algorithm that generates optimal design proposals based on design requirements and emotional data.

[1313] "Trend forecasting" is a method of analyzing the latest market trends and predicting future design trends.

[1314] "Feedback" refers to the act of a user inputting comments or requests for corrections to a design proposal.

[1315] "Color theory" is a theory that studies the impressions and psychological effects that specific colors give to people.

[1316] "Shape and silhouette" are design elements that indicate the appearance and placement of an object.

[1317] A "terminal" is a device to which a user can send input data and view generated design proposals.

[1318] This invention relates to a system in which a server analyzes design requirements and emotional information input by a user, generates optimal design proposals, and makes proposals that reflect trend predictions. The system is composed of a terminal, a server, and an emotion engine.

[1319] Hardware and software used

[1320] 1. Terminal: A device on which users input design requirements and review proposed designs, such as a PC, tablet, or smartphone.

[1321] 2. Server: A computer system for analyzing design requirements and emotion data, generating design proposals, and forecasting trends.

[1322] 3. Emotion engine: Software for collecting and analyzing emotional data from users' facial expressions, voice, and text.

[1323] Data processing and calculation

[1324] 1. Enter your design requirements:

[1325] Users input design requirements through the device interface, such as "casual summer dress," "bright color," and "breathable material," using text fields and drop-down menus.

[1326] 2. Emotional data collection and analysis:

[1327] The device activates an emotion engine, collects facial expressions and voice data from the user via a webcam and microphone, and analyzes input text data and history data to recognize the user's emotional state.

[1328] The emotion engine identifies emotions such as "happy," "excited," and "calm" based on the collected data.

[1329] 3. Sending design and emotion data:

[1330] The device converts the input design requirements and analyzed emotion data into JSON format and sends it to the server via an HTTP POST request.

[1331] 4. Data Analysis:

[1332] The server analyzes the received design requirement data and emotion data. It uses natural language processing (NLP) technology to extract necessary information from the design requirements, and combines it with the emotion information obtained from the emotion engine for analysis. For example, it organizes information such as "summer," "casual," "bright color," "breathable," "happy," and "calm."

[1333] 5. Generate design proposals:

[1334] The server generates design proposals from the analyzed requirements and emotional data using a generative AI model. For example, it suggests colors like "yellow" or "light blue" based on color theory and trend data, shapes like "A-line dress" or "midi length" based on the purpose and season, and materials like "linen" or "cotton" based on functionality and trend data.

[1335] 6. Trend Forecasting:

[1336] The server collects data from fashion blogs, social media, and shopping sites, and uses machine learning algorithms to predict future design trends, such as the popularity of minimalist design.

[1337] 7. Submission of design proposals and trend forecast results:

[1338] The server sends the generated design proposals and trend prediction results via HTTPS to the terminal, which receives them and displays them visually to the user.

[1339] 8. User Acknowledgment and Feedback:

[1340] The user checks the proposed design on the device and, if necessary, sends feedback or correction requests to the server via the device's input interface. The server then generates a new design based on the received feedback and presents it to the device again.

[1341] Specific examples

[1342] Emotion-based summer casual dress design

[1343] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[1344] 2. Emotion engine recognizes: User's emotions are "happy" and "excited"

[1345] 3. The device sends input data and emotion data to the server.

[1346] 4. Server analyzes: extracts keywords (summer, casual, bright colors, breathable, happy, excited)

[1347] 5. Server generated:

[1348] Color suggestions: Yellow, light blue

[1349] Suggested styles: A-line dress, midi length

[1350] Material suggestions: linen, cotton

[1351] 6. Server predicts trend: Minimalist design is in vogue

[1352] 7. The server sends the design proposal and trend prediction results to the device.

[1353] 8. User confirms: Check the visual image and material details and finalize the design

[1354] Prompt Sentence Examples

[1355] "I'd like you to design a casual summer dress. The color should be bright and the material should be breathable. The user's emotions should be happy and excited."

[1356] "Imagine designing winter office accessories. The design is elegant and the color is silver. The user emotions are calm and confident."

[1357] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1358] Step 1:

[1359] The user inputs the design requirements using the terminal interface.

[1360] Specifically, users use text fields and drop-down menus to input requirements such as "casual summer dress," "light color," and "breathable material."

[1361] Input: Design requirements (text format)

[1362] Output: Input design requirements (internal data of the device)

[1363] Step 2:

[1364] The terminal starts the emotion engine and starts collecting the user's emotion data.

[1365] Specifically, the emotion engine collects facial and voice data from the user via a webcam and microphone, and also analyzes the input text data, allowing it to classify the user's emotional state into categories such as "happy," "excited," or "calm."

[1366] Input: User's facial expression data, voice data, text data

[1367] Output: Analyzed emotion information (categorical data)

[1368] Step 3:

[1369] The terminal transmits the input design requirement data and the analyzed emotion data to the server.

[1370] Specifically, this data is converted into JSON format and sent to the server as an HTTP POST request.

[1371] Input: Design requirements data, emotion data (JSON format)

[1372] Output: HTTP POST request to the server

[1373] Step 4:

[1374] The server analyzes the received design requirement data and emotion data.

[1375] Specifically, it uses natural language processing (NLP) technology to extract important information from design requirements and process it in combination with emotional information, for example, extracting keywords such as "summer," "casual," "bright colors," "breathable," "happy," and "excited" from the input data.

[1376] Input: Design requirement data (text format), emotion data (categorical data)

[1377] Output: Extracted keywords and analysis information

[1378] Step 5:

[1379] The server uses a generative AI model to generate design proposals.

[1380] Specifically, it generates design proposals based on analyzed requirements and emotional data, as well as color theory and trend data. For example, it suggests colors like "yellow" and "light blue," suggests styles like "A-line dress" and "midi length," and selects materials like "linen" and "cotton."

[1381] Input: Extracted keywords and analysis information

[1382] Output: Generated design proposals (color, shape, material suggestions)

[1383] Step 6:

[1384] The server analyzes the latest market trends and predicts future trends.

[1385] Specifically, the project collects data from online fashion blogs, social media, shopping sites, etc., and uses machine learning algorithms to predict future design trends, such as the trend toward minimalist design.

[1386] Input: Market trend data (web data, social media data, etc.)

[1387] Output: Trend prediction results (future fashion information)

[1388] Step 7:

[1389] The server transmits the generated design proposals and trend prediction results to the terminal.

[1390] This information is sent to the device via HTTPS.

[1391] The device receives this and displays visual images, color palettes, material lists, etc. on a dashboard or preview screen.

[1392] Input: Generated design proposals, trend prediction results

[1393] Output: Design proposals and trend information displayed to the user

[1394] Step 8:

[1395] The user checks the proposed design on the device.

[1396] If necessary, feedback or correction requests can be resubmitted to the server via the input interface of the device, and the server will generate new design proposals based on the received feedback and present them to the device again.

[1397] Input: Feedback information (user comments, correction requests, etc.)

[1398] Output: Revised design proposal (design proposal resent from server)

[1399] (Application example 2)

[1400] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1401] Conventional design generation systems generate design proposals based solely on user input data. This makes it difficult to propose designs that reflect the user's emotions and psychological state, and fails to sufficiently improve user satisfaction. Furthermore, it is difficult to accurately reflect the latest market trends and future trends, making it an inappropriate solution for virtual stores, which must always incorporate the latest trends.

[1402] The specification processing by the specification 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 accepting design requirements input by a user, means for transmitting the design requirement data to the server, means for analyzing the accepted design requirements, means for generating design proposals based on the analyzed design requirements and the user's emotional state, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to the terminal, means for the user to confirm the design proposals displayed on the terminal, and means for recognizing the user's emotional state using facial recognition and voice recognition. This enables personalized design proposals that take the user's emotional state into consideration, thereby increasing user satisfaction. Furthermore, design proposals that reflect the latest market trends and future trends can be made.

[1403] "Design requirements" refer to the design features and conditions desired by the user.

[1404] A "server" is a computer system that provides services and information to other devices on a network.

[1405] "Analysis" means examining data or information in detail to clarify its structure and meaning.

[1406] "Emotional state" refers to the user's psychological state or mood, and is information that can be inferred from facial expressions and voice.

[1407] A "design proposal" is a specific design proposal generated based on the analyzed data and requirements.

[1408] "Market trends" refers to current market trends and consumer preferences.

[1409] "Trend forecasting" is analysis to predict future consumer preferences and market changes.

[1410] A "terminal" is an electronic device that allows a user to input information and check the display.

[1411] "Facial recognition" is a technology that uses a camera to identify an individual's face and analyze its features.

[1412] "Speech recognition" is a technology that uses a microphone to convert voice data into text data.

[1413] "Personalization" refers to customization according to the needs and preferences of individual users.

[1414] A "visual image" is a picture or figure that is displayed in a visual form.

[1415] This invention is a system in which a server generates optimal design proposals based on the user's design requirements and emotional information, and makes proposals that reflect the latest market trends. Specifically, the system allows the user to input design requirements using a terminal and recognize emotional information, enabling personalized design proposals.

[1416] Hardware and Software Use

[1417] Device:

[1418] Smartphone (using an application that implements React Native)

[1419] Smartphone camera (using OpenCV for facial recognition)

[1420] Smartphone microphone (voice recognition is performed using the Google Cloud Speech-to-Text API)

[1421] server:

[1422] Server system (built using Python Flask)

[1423] Natural language processing libraries (using SpaCy and GPT-4)

[1424] AI models (using TensorFlow or PyTorch)

[1425] Data processing and calculation

[1426] 1. Design requirements and receiving emotional information:

[1427] The user inputs design requirements, such as "autumn jacket," "warm material," and "modern design," through the smartphone interface. At the same time, the smartphone's camera and microphone are used for facial and voice recognition to capture the user's emotional state (e.g., "relaxed" or "satisfied").

[1428] 2. Data transmission:

[1429] The device sends the user's design requirement data and emotion data to the server via an HTTP POST request.

[1430] 3. Data analysis and design generation:

[1431] The server analyzes the received design requirement data using a natural language processing library (such as SpaCy) to extract keywords. At the same time, it also analyzes sentiment data. Based on this data, it uses an AI model (a generative AI model using TensorFlow or PyTorch) to generate optimal design proposals.

[1432] 4. Trend Forecasting:

[1433] The server collects data from online fashion blogs, social media, shopping sites, and other sources, and uses AI to analyze market trends and predict future trends. These trend predictions are also reflected in design proposals.

[1434] 5. Design proposal submission:

[1435] The final design proposals and trend forecast results are sent from the server to the user's device and displayed for review, allowing the user to check the visual image, color palette, material list, and other details.

[1436] Specific examples

[1437] If a user is looking for a fall jacket:

[1438] The user types "autumn jacket," "warm material," and "modern design" into their smartphone, and the camera and microphone are used to recognize the emotional states of "relaxed" and "satisfied."

[1439] The server analyzes this data and suggests the most suitable color (e.g., "olive green" or "brown"), shape (e.g., "slim fit"), material (e.g., "wool"), etc.

[1440] The server analyzes the latest market trends and sends the generated design proposals and trend forecast results to the smartphone.

[1441] The user checks visual images and detailed design proposals and makes the final selection.

[1442] Prompt Sentence Examples

[1443] "Generate detailed design proposals for a fall jacket made of warm material with a modern design that is perfect for customers with a relaxed feel."

[1444] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1445] Step 1:

[1446] The user inputs the design requirements. Using the smartphone interface, the user inputs design requirements such as "autumn jacket," "warm material," and "modern design" in text. This input serves as the basis for data processing in each subsequent step.

[1447] Step 2:

[1448] The device recognizes emotional information. It uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and then performs facial recognition (using OpenCV) and voice recognition (using Google Cloud Speech-to-Text API). Through this process, the device identifies the user's emotional state as "relaxed" or "satisfied," for example. Emotional information is extracted from the user's facial expression and voice data using an emotion recognition algorithm.

[1449] Step 3:

[1450] The terminal sends the design requirement data and emotion data to the server. The terminal sends the design requirement data and emotion data entered by the user to the server via an HTTP POST request. The sent data includes text (design requirement) and emotion state (relaxed, satisfied, etc.).

[1451] Step 4:

[1452] The server analyzes the data. The server uses natural language processing (SpaCy or GPT-4) to analyze the received design requirement data and extract keywords. At the same time, it also analyzes the emotional data. As a result of this analysis, keywords such as "autumn," "jacket," "warm," and "modern" and emotional states such as "relaxed" and "satisfied" are obtained.

[1453] Step 5:

[1454] The server generates design proposals using a generative AI model (using TensorFlow or PyTorch) based on the analyzed requirements and sentiment data. The server suggests optimal colors ("olive green" or "brown"), shapes ("slim fit"), and materials ("wool"), for example. The AI ​​model is trained on a large amount of design data and generates design proposals by referencing related data.

[1455] Step 6:

[1456] The server analyzes the latest market trends and makes trend predictions. The server collects data from online fashion blogs, social media, shopping sites, etc. and uses AI to analyze market trends. Based on these results, future trends are predicted and incorporated into design proposals.

[1457] Step 7:

[1458] The server sends the generated design proposal and trend prediction results to the terminal. The server then sends the final generated design proposal and trend prediction results to the terminal as an HTTP response, which includes detailed information such as visual images, color palettes, and material lists.

[1459] Step 8:

[1460] The user checks the proposed design on their device. The user can check the design proposals and trend prediction results sent to the device on their smartphone screen and make corrections or feedback as necessary. For example, they can input a request for correction, such as "I want the color to be a little darker," and send it back to the server to fine-tune the design.

[1461] The above is the flow of specific processing steps, which enables personalized design proposals based on the user's needs and emotions.

[1462] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1463] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1464] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1465] [Fourth embodiment]

[1466] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1467] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1468] 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).

[1469] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1470] 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.

[1471] 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).

[1472] 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.

[1473] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1474] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1475] 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.

[1476] 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.

[1477] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1478] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1479] This invention relates to a system in which a server analyzes design requirements input by a user, generates optimal design proposals, and makes proposals that reflect trend predictions.

[1480] System Overview

[1481] This system works in conjunction with the terminal and server to generate design proposals based on the design requirements entered by the user, and makes proposals that take trend elements into account. Below are specific processing and examples of the program.

[1482] Explanation of program processing

[1483] Step 1: User enters design requirements

[1484] The user uses the device interface to input design requirements, such as specific requirements like "a casual summer dress," "bright color," and "breathable material." This information is structured as data on the device and then passed on to the next processing step.

[1485] Step 2: The device sends the input data to the server

[1486] The terminal sends the design requirement data entered by the user to the server, which transfers the data via the Internet using an HTTP POST request.

[1487] Step 3: The server analyzes the requirements

[1488] The server analyzes the received data using natural language processing (NLP) technology to extract and structure the necessary information from the user's requirements. For example, it extracts specific keywords such as "summer," "casual," "bright colors," and "breathable materials."

[1489] Step 4: The server generates a design proposal

[1490] The server generates design proposals from the requirements data analyzed using the AI ​​model, taking into account the following factors:

[1491] Color Suggestion: Based on color theory and the latest trend data, it suggests the best color combinations. For example, it suggests bright colors such as yellow and light blue for summer dresses.

[1492] Shape suggestions: We suggest shapes and silhouettes that are suitable for different occasions and seasons. For example, A-line dresses and midi lengths are suggested for casual wear.

[1493] Material suggestions: Select the appropriate material based on functionality and trends. For example, breathable linen or cotton is suggested.

[1494] Step 5: The server makes a trend prediction

[1495] The server analyzes the latest market trends and applies algorithms to predict future trends. Here, data is collected from online sources such as fashion blogs, social media, and shopping sites, and analyzed using AI.

[1496] Step 6: Send the final design to your device

[1497] The generated design proposals and trend forecast results are sent from the server to the device, which receives them and displays them to the user, such as visual images, color palettes, and material lists.

[1498] Step 7: User reviews the design

[1499] The user can review the proposed design on their device, provide feedback if necessary, and request revisions to the design by resubmitting it to the server.

[1500] Specific examples

[1501] Example 1: Summer casual dress design

[1502] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[1503] 2. The device sends the input data to the server.

[1504] 3. Server analyzes: extracts keywords (summer, casual, bright colors, breathable)

[1505] 4. Server generated:

[1506] Color suggestions: Yellow, light blue, white

[1507] Suggested styles: A-line dress, midi length

[1508] Material suggestions: linen, cotton

[1509] 5. Server predicts trend: Minimalist design is in vogue

[1510] 6. The server sends the design proposal and trend prediction results to the device.

[1511] 7. User confirms: Check the visual image and material details and finalize the design

[1512] Example 2: Winter accessories for the office

[1513] 1. User types: "winter office accessories," "elegant design," "silver"

[1514] 2. The device sends the input data to the server.

[1515] 3. Server analyzes: Keywords (winter, office, elegant, silver) are extracted

[1516] 4. Server generated:

[1517] Color suggestions: Silver, black, navy

[1518] Shape suggestion: simple lines, modern design

[1519] Material suggestions: Silver, stainless steel

[1520] 5. Server predicts trend: Minimalist jewelry is trending

[1521] 6. The server sends the design proposal and trend prediction results to the device.

[1522] 7. User review: Check the visual image and material details and request fine-tuning if necessary

[1523] As shown in these examples, the system can provide efficient and high-quality designs based on the user's requirements.

[1524] The processing flow will be explained below.

[1525] Step 1:

[1526] The user inputs design requirements using the device interface, for example, specific requirements such as "casual summer dress," "bright color," and "breathable material."

[1527] Step 2:

[1528] The terminal sends the input design requirement data to the server. Specifically, the user input data is passed to the server via an HTTP POST request.

[1529] Step 3:

[1530] The server analyzes the received data and uses natural language processing (NLP) technology to extract and structure the necessary information from the user's requirements, organizing keywords such as "summer," "casual," "bright colors," and "breathable."

[1531] Step 4:

[1532] The server makes color suggestions based on design requirements. It references color theory and trend data to select the optimal color combination. For example, suggestions such as "yellow," "light blue," and "white" are made.

[1533] Step 5:

[1534] The server will suggest shapes and silhouettes that are best suited to the user's purpose and the season, such as "A-line dress" or "midi length."

[1535] Step 6:

[1536] The server will suggest materials based on functionality, user requests, and trends. For example, "linen" or "cotton" may be suggested.

[1537] Step 7:

[1538] The server applies trend prediction algorithms, analyzes current market trends, and collects and analyzes data to predict future trends, for example, by utilizing information from online fashion blogs and social media.

[1539] Step 8:

[1540] The server synthesizes the final design proposals. Design proposals are synthesized based on color, shape, and material, and a final proposal is created that reflects the trend forecast results.

[1541] Step 9:

[1542] The server sends the final design proposal to the device using an HTTP POST request, along with the generated design proposal and trend prediction results.

[1543] Step 10:

[1544] The terminal displays the received design proposal, providing detailed information such as visual images, color palettes, and material lists to the user.

[1545] Step 11:

[1546] The user checks the design proposal and provides feedback as needed. If corrections are needed, the requirements are entered again and the process is repeated.

[1547] Example 1

[1548] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1549] In modern design, it is difficult for users to efficiently find designs that meet their requirements, which consumes a lot of time and effort. It is also difficult to quickly incorporate market trends and reflect them in designs. In conventional systems, even if users provide specific feedback, it takes time for it to be reflected, resulting in a decrease in satisfaction.

[1550] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1551] In this invention, the server includes: means for accepting design requirements input by a user; means for transmitting the design requirement data to the server; means for analyzing the accepted design requirements; means for generating a design proposal based on the analyzed design requirements; means for analyzing the latest market trends and predicting future trends; means for transmitting the generated design proposal and the trend prediction results to a terminal; means for the user to confirm the design proposal displayed on the terminal; and means for the user to input feedback on the confirmed design proposal and retransmit it to the server to request a revision. This enables the generation of appropriate and efficient design proposals that meet user requirements and reflect trends in the proposals. Furthermore, by quickly reflecting user feedback, improved user satisfaction can be expected.

[1552] "User" refers to the end-user who inputs design requirements and reviews and modifies proposed designs.

[1553] "Terminal" refers to a computer or mobile device used by a user to input design requirements and review proposed designs.

[1554] "Server" refers to the central computing system that analyzes design requirements, generates and proposes designs, and analyzes market trends and forecasts trends.

[1555] "Design requirements" refers to specific design requests and conditions entered by the user, such as information on use, color, material, shape, etc.

[1556] "Design Proposal" refers to a specific design or proposal generated by the server based on the user's design requirements.

[1557] "Market Trends" refers to data regarding current and recent market trends and trends.

[1558] "Trend forecasting" refers to the use of AI technology to predict future trends based on market trend data.

[1559] "Analysis" refers to the process of extracting necessary information using natural language processing technology, etc., based on the design requirements received by the server.

[1560] A "request for revision" refers to a user providing feedback on a proposed design and requesting further revisions.

[1561] "Theory" refers to academic foundations such as color theory and design theory that are referenced when generating design proposals.

[1562] "Data" refers to information used to generate design proposals and forecast trends, such as trend data, user data, and market data.

[1563] This invention relates to a system in which a server analyzes design requirements entered by a user, generates optimal design proposals, and makes proposals that reflect the latest market trends.

[1564] System Overview

[1565] This system works by linking terminals and a server to generate design proposals based on design requirements entered by users and make proposals that take market trends into account. Specifically, it uses the following hardware and software:

[1566] Hardware

[1567] Device: A device such as a computer or smartphone operated by a user.

[1568] Server: A central computing system that performs data analysis, design generation, and trend forecasting.

[1569] software

[1570] Natural Language Processing (NLP) engine: Software for analyzing user-entered design requirements.

[1571] Generative AI model: AI for generating design proposals from analyzed requirements data.

[1572] Trend Forecasting Algorithms: Algorithms for analyzing the latest market trends and predicting future trends.

[1573] Program processing explanation

[1574] The user uses the device interface to input design requirements, such as specific requirements like "summer casual dress," "bright color," and "breathable material." The device then structures this information as data and sends it to the server using an HTTP POST request.

[1575] The server first stores the received data in a database, then analyzes the input data using a natural language processing (NLP) engine, extracting specific keywords such as "summer," "casual," "bright colors," and "breathable materials."

[1576] Based on the analyzed requirements data, the server uses a generative AI model to generate design proposals, taking into account the following factors:

[1577] Color suggestions: The server refers to color theory and the latest trend data and suggests bright colors such as yellow or light blue for a "casual summer dress," for example.

[1578] Style suggestions: The server will suggest styles such as A-line dresses or midi dresses depending on the season and purpose.

[1579] Material suggestions: The server will suggest breathable materials such as linen and cotton.

[1580] The server then uses trend prediction algorithms to gather data from fashion blogs, social media, and shopping sites to analyze the latest market trends. For example, if minimalist design is predicted to be popular, the server generates design proposals based on that.

[1581] The generated design proposals and trend forecast results are sent from the server to the terminal, which receives them and displays visual images, color palettes, material lists, etc. to the user. The user can check the proposed design proposals on the terminal, enter feedback if necessary, and resubmit them to the server to request design revisions.

[1582] Specific examples

[1583] Example 1: Designing a casual summer dress

[1584] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[1585] 2. The device sends the input data to the server.

[1586] 3. Server analyzes: extracts keywords (summer, casual, bright colors, breathable)

[1587] 4. Server generated:

[1588] Color suggestions: Yellow, light blue, white

[1589] Suggested styles: A-line dress, midi length

[1590] Material suggestions: linen, cotton

[1591] 5. Server predicts trend: Minimalist design is in vogue

[1592] 6. The server sends the design proposal and trend prediction results to the terminal.

[1593] 7. User confirms: Check the visual image and material details and finalize the design

[1594] Example 2: Winter office accessories

[1595] 1. User types: "winter office accessories," "elegant design," "silver"

[1596] 2. The device sends the input data to the server.

[1597] 3. Server analyzes: Keywords (winter, office, elegant, silver) are extracted

[1598] 4. Server generated:

[1599] Color suggestions: Silver, black, navy

[1600] Shape suggestion: simple lines, modern design

[1601] Material suggestions: Silver, stainless steel

[1602] 5. Server predicts trend: Minimalist jewelry is trending

[1603] 6. The server sends the design proposal and trend prediction results to the terminal.

[1604] 7. User review: Check the visual image and material details and request fine-tuning if necessary

[1605] Prompt Sentence Examples

[1606] "Casual summer dress," "bright color," "breathable material"

[1607] "Winter office accessories," "elegant design," "silver"

[1608] This makes it possible to generate and propose appropriate and efficient design proposals that meet the user's requirements.

[1609] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1610] Step 1:

[1611] The user uses the device interface to input design requirements, such as "a casual summer dress," "bright color," and "breathable material." This input data is structured on the device and prepared for the next processing step.

[1612] Input: User-entered design requirements (e.g., "casual summer dress," "bright color," "breathable material").

[1613] Output: Structured design requirements data.

[1614] Step 2:

[1615] The device sends structured design requirement data to the server via an HTTP POST request, using the HTTPS protocol to keep the data secure.

[1616] Input: Structured design requirements data.

[1617] Output: The data sent as an HTTP POST request.

[1618] Step 3:

[1619] The server first stores the received data in a database. It then analyzes the data using a natural language processing (NLP) engine to extract important keywords and concepts from the user's requirements. For example, keywords such as "summer," "casual," "light colors," and "breathable" are extracted.

[1620] Input: The data sent as an HTTP POST request.

[1621] Output: Extracted keywords and concepts (e.g., "summer," "casual," "light colors," "breathable").

[1622] Step 4:

[1623] The server uses a generative AI model to generate design proposals from the analyzed requirements data, taking into account the following factors:

[1624] Color suggestions: Based on color theory and the latest trend data, colors such as "yellow," "light blue," and "white" are suggested.

[1625] Shape suggestions: Depending on the purpose and season, we will suggest shapes such as "A-line dress" or "midi length."

[1626] Material suggestions: We suggest "linen" and "cotton" as breathable materials.

[1627] Input: Extracted keywords and concepts.

[1628] Output: Design proposals with suggested colors, shapes, and materials.

[1629] Step 5:

[1630] The server uses trend prediction algorithms to collect data from fashion blogs, social media, and shopping sites on the Internet and analyze the latest market trends. For example, it predicts that minimalist design is trending.

[1631] Input: Market trend data from the internet.

[1632] Output: Future trend prediction results (e.g. minimalist design will be popular).

[1633] Step 6:

[1634] The server sends the generated design proposals and trend forecast results as an HTTP response to the terminal, which receives them and displays them visually to the user. The displayed content includes visual images, color palettes, material lists, etc.

[1635] Input: Design proposals and trend forecast results.

[1636] Output: The data sent as the HTTP response.

[1637] Step 7:

[1638] The user checks the proposed design on the terminal, and if the user is satisfied, confirms it as is, enters feedback as necessary, and resubmits it to the server to request corrections.

[1639] Input: Design proposals and trend forecast results.

[1640] Output: User feedback or design confirmation.

[1641] (Application example 1)

[1642] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1643] Conventional design systems have difficulty quickly generating design proposals that accurately reflect user requirements, and it is even more difficult to reflect market trends. As a result, user satisfaction is low and design quality is inconsistent. In addition, there is a lack of ways for users to specifically check and edit proposed design proposals, which means that they are unable to see the actual product when selling online.

[1644] 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.

[1645] In this invention, the server includes means for accepting design requirements input by a user, means for transmitting the design requirement data to the server, means for analyzing the accepted design requirements, means for generating design proposals based on the analyzed design requirements, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to a terminal, means for the user to check the design proposals displayed on the terminal, means for the user to check the design proposals and provide feedback or edit them, and means for providing the generated design proposals to the user and allowing them to check them online in a form close to the real thing. This enables the rapid generation of high-quality design proposals based on user requirements and proposals that reflect market trends, as well as the user to specifically check and edit the design proposals online.

[1646] "Means for accepting design requirements input by a user" refers to an interface through which a user inputs requirements regarding a desired design and the system receives them.

[1647] "Means for transmitting design requirement data to a server" refers to the process or technology for transmitting design requirement data entered at a terminal to a server via a network.

[1648] The "means for analyzing received design requirements" refers to a technology for analyzing the design requirement data sent to the server and extracting and structuring the necessary information.

[1649] "Means for generating design proposals based on analyzed design requirements" refers to a system that uses AI and other technologies to generate actual design proposals based on analyzed design requirement data.

[1650] "Means of analyzing the latest market trends and predicting future trends" refers to algorithms and technologies that collect the latest market trends as data and analyze it to predict future trends.

[1651] "Means for transmitting the generated design proposals and trend prediction results to the terminal" refers to the process or technology for transmitting the design proposals and trend prediction results generated by the server to the terminal being used by the user.

[1652] "Means for users to check the design proposals displayed on their devices" refers to the function that allows users to view and check the sent design proposals on the screen of their devices.

[1653] "A means for users to review design proposals and provide feedback or edits" refers to a function that allows users to view design proposals and provide feedback, or modify the design as needed.

[1654] "A means of providing the generated design proposal to the user and allowing them to check it online in a manner close to the actual product" refers to technology that allows the user to see the generated design proposal and check it in an online environment in a manner close to the actual product.

[1655] This invention relates to a system in which a server analyzes design requirements entered by a user, generates optimal design proposals, and makes proposals that reflect trend forecasts. A specific method for realizing this system is described below.

[1656] System program generation and implementation method

[1657] This system operates in cooperation with the server and the terminal used by the user. The main processing steps are as follows:

[1658] Hardware and Software

[1659] Devices: Smartphones, tablets, computers, and other devices

[1660] Server: Cloud server or on-premise server

[1661] Network: Internet connection

[1662] Languages ​​and libraries used: Python, NLP libraries (e.g., NLTK, spaCy), machine learning libraries (e.g., TensorFlow, PyTorch), HTTP communication libraries (e.g., Requests)

[1663] Processing description

[1664] User inputs design requirements

[1665] Users input design requirements using a smartphone or PC interface, for example, by typing specific requirements such as "casual jacket for spring," "pastel color," and "waterproof material" into text boxes.

[1666] The device sends the input data to the server

[1667] The entered design requirement data is sent to the server via the Internet by an HTTP POST request.

[1668] The server analyzes the requirements

[1669] The server analyzes the received design requirements data and uses natural language processing (NLP) technology to extract and structure specific keywords (such as "spring," "casual," "pastel colors," and "waterproof") from the input text.

[1670] The server generates design proposals

[1671] The AI ​​model installed on the server generates design proposals based on the analyzed requirements data, using color theory and the latest trend data to suggest appropriate color combinations, shapes, silhouettes, materials, etc.

[1672] The server makes trend predictions

[1673] The server analyzes the latest market trends and applies algorithms to predict future trends, analysing data collected from online sources such as fashion blogs, social media, and shopping sites.

[1674] Send the final design to your device

[1675] The generated design proposals and trend forecast results are sent from the server to the user's device, where they can be viewed. Visual images, color palettes, material lists, and more are displayed.

[1676] Users can review the design proposal and provide feedback or edits

[1677] After reviewing the proposed design on their device, users can provide feedback and make any necessary revisions to the design. Once the final design is confirmed, they will also be given the option to purchase it online.

[1678] Examples of specific examples and prompts

[1679] For example, if a user enters "casual spring jacket," "pastel color," and "waterproof material," the system will do the following:

[1680] Input prompt statement:

[1681] Casual jacket for spring

[1682] "Pastel colors"

[1683] Waterproof material

[1684] This system allows users to quickly obtain high-quality design proposals that meet their requirements and also allows them to receive proposals that reflect market trends. Furthermore, users can confirm and edit the proposed design proposals in detail, improving the online purchasing experience.

[1685] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1686] Step 1:

[1687] User inputs design requirements

[1688] The user uses the terminal interface to input design requirements. Examples of input requirements include "casual jacket for spring," "pastel color," and "waterproof material." The terminal structures this as text data and prepares it for the next processing step. The input data is the design requirements in text format. The output is structured design requirement data.

[1689] Step 2:

[1690] The device sends the input data to the server

[1691] The structured design requirement data is sent from the terminal to the server. Here, the data is transferred via the Internet by an HTTP POST request. The input data is the structured design requirement data, and the output is the design requirement data sent to the server.

[1692] Step 3:

[1693] The server analyzes the requirements

[1694] The server analyzes the received design requirements data and uses natural language processing (NLP) technology to extract and structure specific keywords (such as "spring," "casual," "pastel colors," and "waterproof") from the user's requirements. Here, the input data is the design requirements data received by the server, and the output is the identified keywords and their understanding.

[1695] Step 4:

[1696] The server generates design proposals

[1697] A generative AI model installed on the server generates design proposals based on the analyzed requirement data. Based on color theory and the latest trend data, it suggests appropriate color combinations, shapes, silhouettes, materials, etc. The input data are identified requirement keywords, and the output is the generated design proposals.

[1698] Step 5:

[1699] The server makes trend predictions

[1700] The server collects the latest market trend data from online sources such as fashion blogs, social media, and shopping sites, and applies a trend prediction algorithm to predict future trends. The input data is the collected market trend data, and the output is the trend prediction results.

[1701] Step 6:

[1702] The server sends design proposals and trend forecast results to the terminal.

[1703] The generated design proposals and trend prediction results are sent from the server to the terminal, where the user can check them. The input data are the generated design proposals and trend prediction results, and the output is the design proposals and trend prediction results displayed on the terminal.

[1704] Step 7:

[1705] Users can review the design proposal and provide feedback or edits

[1706] The user checks the design proposal displayed on the terminal. The user can provide feedback on the design proposal or edit the design as needed. The input data is the displayed design proposal, and the output is the feedback or edited design proposal.

[1707] Step 8:

[1708] Users can check the actual product online

[1709] The system provides the generated design proposal to the user and allows them to check it online in a form close to the real thing. This allows the user to check the design in detail. The input data is the generated design proposal, and the output is a design proposal displayed in a form close to the real thing.

[1710] 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.

[1711] This invention relates to a system in which a server analyzes and generates optimal design proposals based on design requirements and emotional information input by a user, and makes proposals that reflect trend predictions.

[1712] System Overview

[1713] This system consists of a terminal, a server, and an emotion engine. Its unique feature is that it recognizes the user's emotional information in addition to the design requirements input by the user, and reflects this information in the design proposal.

[1714] Explanation of program processing

[1715] Step 1: User enters design requirements

[1716] The user uses the device interface to input design requirements, such as "a casual summer dress," "bright color," and "breathable material," for each specific item.

[1717] Step 2: The emotion engine recognizes the user's emotion

[1718] The emotion engine analyzes the user's facial expressions, voice, text, etc. to recognize the user's emotional state, for example, determining whether the user is happy, excited, calm, etc.

[1719] Step 3: The device sends the input data and emotion data to the server.

[1720] The device sends the design requirement data and emotion data entered by the user to the server via an HTTP POST request.

[1721] Step 4: The server parses the data

[1722] The server analyzes the received design requirements and emotion data. It uses natural language processing (NLP) technology to extract necessary information from the design requirements and combines it with the emotion information obtained from the emotion engine for analysis. For example, it organizes information such as "summer," "casual," "bright color," "breathable," "happy," and "calm."

[1723] Step 5: The server generates a design proposal

[1724] The server uses the AI ​​model to generate design proposals from the analyzed requirements and sentiment data, taking into account the following factors:

[1725] Color suggestions: Select the optimal color combination based on color theory and the latest trend data. For example, if the emotion is "happiness," suggest "yellow" or "light blue."

[1726] Shape suggestions: We suggest the best shape and silhouette for each occasion and season, such as "A-line dress" or "midi length."

[1727] Material suggestions: Materials are selected based on functionality, user requests, and trends. For example, "linen" and "cotton" are suggested.

[1728] Step 6: The server makes a trend prediction

[1729] The server analyzes the latest market trends and applies algorithms to predict future trends. It collects data from online fashion blogs, social media, shopping sites, and other sources and uses AI to analyze it.

[1730] Step 7: Send the final design to your device

[1731] The generated design proposals and trend forecast results are sent from the server to the device, which receives them and displays them to the user, such as visual images, color palettes, and material lists.

[1732] Step 8: User reviews the design

[1733] The user can review the proposed design on their device, provide feedback if necessary, and request revisions to the design by resubmitting it to the server.

[1734] Specific examples

[1735] Example 1: Emotion-based casual summer dress design

[1736] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[1737] 2. Emotion engine recognizes: User's emotions are "happy" and "excited"

[1738] 3. The device sends input data and emotion data to the server.

[1739] 4. Server analyzes: extracts keywords (summer, casual, bright colors, breathable, happy, excited)

[1740] 5. Server generated:

[1741] Color suggestions: Yellow, light blue

[1742] Suggested styles: A-line dress, midi length

[1743] Material suggestions: linen, cotton

[1744] 6. Server predicts trend: Minimalist design is in vogue

[1745] 7. The server sends the design proposal and trend prediction results to the device.

[1746] 8. User confirms: Check the visual image and material details and finalize the design

[1747] Example 2: Emotion-based winter accessories for the office

[1748] 1. User types: "winter office accessories," "elegant design," "silver"

[1749] 2. Emotion engine recognizes: User's emotions are "calm" and "confident"

[1750] 3. The device sends input data and emotion data to the server.

[1751] 4. Server analyzes: extracts keywords (winter, office, elegant, silver, calm, confident)

[1752] 5. Server generated:

[1753] Color suggestions: Silver, black, navy

[1754] Shape suggestion: simple lines, modern design

[1755] Material suggestions: Silver, stainless steel

[1756] 6. Server predicts trend: Minimalist jewelry is trending

[1757] 7. The server sends the design proposal and trend prediction results to the device.

[1758] 8. User review: Check the visual image and material details and request fine-tuning if necessary

[1759] The system takes into account the user's design requirements and emotional state to deliver more personalized and high-quality design suggestions.

[1760] The processing flow will be explained below.

[1761] Step 1:

[1762] The user inputs design requirements using the device interface, for example, specific requirements such as "casual summer dress," "bright color," and "breathable material."

[1763] Step 2:

[1764] The emotion engine recognizes the user's emotions. The emotion engine analyzes the user's facial expressions, voice, text, etc. to recognize the user's emotional state. For example, it analyzes facial expressions through a camera and identifies emotions such as "happiness" or "excitement."

[1765] Step 3:

[1766] The device sends the input data and emotion data to the server. The device sends the design requirement data entered by the user and the emotion data recognized by the emotion engine to the server. Here, an HTTP POST request is used.

[1767] Step 4:

[1768] The server analyzes the received design requirement data and sentiment data. Using natural language processing (NLP) techniques, it extracts keywords (summer, casual, bright colors, breathable, happy, excited) and organizes them as structured data.

[1769] Step 5:

[1770] The server generates design proposals. Using AI models, the server generates design proposals based on the analyzed design requirements and emotional data. It makes suggestions based on the following factors:

[1771] Color Suggestion: Selects the optimal color combination based on color theory and the latest trend data. For example, if the user is "happy," it will suggest bright colors such as "yellow" and "light blue."

[1772] Shape suggestions: The system suggests the best shape and silhouette for each occasion and season. For example, for "casual dresses," it suggests "A-line dresses" and "midi length."

[1773] Material suggestions: Select materials based on functionality, user requests, and trends. For example, suggest "linen" or "cotton" as "materials with good breathability."

[1774] Step 6:

[1775] The server performs trend prediction. The server analyzes the latest market trends and applies algorithms to predict future trends. For example, it collects data from online fashion blogs, social media, shopping sites, etc. and analyzes it using AI.

[1776] Step 7:

[1777] The server integrates the final design proposal. It integrates design proposals based on color, shape, and material, and incorporates trend forecast results to create the final design proposal.

[1778] Step 8:

[1779] The server sends the final design proposal to the terminal. The server sends the generated design proposal and trend prediction results to the terminal using an HTTP POST request.

[1780] Step 9:

[1781] The terminal displays the received design proposal, providing detailed information such as visual images, color palettes, and material lists to the user.

[1782] Step 10:

[1783] The user checks the proposed design. The user checks the proposed design on the terminal and enters feedback as necessary. If corrections are necessary, the requirements are entered again and the process is repeated.

[1784] Example 2

[1785] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1786] Conventional design generation systems did not consider the user's emotional information when proposing designs, making it difficult to provide designs that satisfied the user. It was also difficult to integrate trend forecasts that reflected the latest market trends into the design. For this reason, there was a need for a system that could provide personalized design proposals that met the user's needs.

[1787] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting design requirements input by the user, means for transmitting the design requirement data and user emotion data to the server, means for analyzing the accepted design requirements and emotion information, means for generating design proposals based on the analyzed design requirements and emotion information, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to the terminal, and means for the user to check the design proposals displayed on the terminal and input feedback. This makes it possible to provide personalized design proposals that reflect the user's emotional state and incorporate trend predictions that reflect the latest market trends into the design.

[1788] "Design requirements" are information entered by a user regarding their wishes and conditions regarding a particular design.

[1789] "Emotional data" is information that represents the user's emotional state, and is data collected from facial expressions, voice, and text.

[1790] The "server" is a computer system that generates design proposals, analyzes design requirements and emotional data, and predicts trends.

[1791] "Means for analysis" refers to a method for understanding the input design requirements and emotional data and extracting the necessary information.

[1792] A "generative AI model" is an artificial intelligence algorithm that generates optimal design proposals based on design requirements and emotional data.

[1793] "Trend forecasting" is a method of analyzing the latest market trends and predicting future design trends.

[1794] "Feedback" refers to the act of a user inputting comments or requests for corrections to a design proposal.

[1795] "Color theory" is a theory that studies the impressions and psychological effects that specific colors give to people.

[1796] "Shape and silhouette" are design elements that indicate the appearance and placement of an object.

[1797] A "terminal" is a device to which a user can send input data and view generated design proposals.

[1798] This invention relates to a system in which a server analyzes design requirements and emotional information input by a user, generates optimal design proposals, and makes proposals that reflect trend predictions. The system is composed of a terminal, a server, and an emotion engine.

[1799] Hardware and software used

[1800] 1. Terminal: A device on which users input design requirements and review proposed designs, such as a PC, tablet, or smartphone.

[1801] 2. Server: A computer system for analyzing design requirements and emotion data, generating design proposals, and forecasting trends.

[1802] 3. Emotion engine: Software for collecting and analyzing emotional data from users' facial expressions, voice, and text.

[1803] Data processing and calculation

[1804] 1. Enter your design requirements:

[1805] Users input design requirements through the device interface, such as "casual summer dress," "bright color," and "breathable material," using text fields and drop-down menus.

[1806] 2. Emotional data collection and analysis:

[1807] The device activates an emotion engine, collects facial expressions and voice data from the user via a webcam and microphone, and analyzes input text data and history data to recognize the user's emotional state.

[1808] The emotion engine identifies emotions such as "happy," "excited," and "calm" based on the collected data.

[1809] 3. Sending design and emotion data:

[1810] The device converts the input design requirements and analyzed emotion data into JSON format and sends it to the server via an HTTP POST request.

[1811] 4. Data Analysis:

[1812] The server analyzes the received design requirement data and emotion data. It uses natural language processing (NLP) technology to extract necessary information from the design requirements, and combines it with the emotion information obtained from the emotion engine for analysis. For example, it organizes information such as "summer," "casual," "bright color," "breathable," "happy," and "calm."

[1813] 5. Generate design proposals:

[1814] The server generates design proposals from the analyzed requirements and emotional data using a generative AI model. For example, it suggests colors like "yellow" or "light blue" based on color theory and trend data, shapes like "A-line dress" or "midi length" based on the purpose and season, and materials like "linen" or "cotton" based on functionality and trend data.

[1815] 6. Trend Forecasting:

[1816] The server collects data from fashion blogs, social media, and shopping sites, and uses machine learning algorithms to predict future design trends, such as the popularity of minimalist design.

[1817] 7. Submission of design proposals and trend forecast results:

[1818] The server sends the generated design proposals and trend prediction results via HTTPS to the terminal, which receives them and displays them visually to the user.

[1819] 8. User Acknowledgment and Feedback:

[1820] The user checks the proposed design on the device and, if necessary, sends feedback or correction requests to the server via the device's input interface. The server then generates a new design based on the received feedback and presents it to the device again.

[1821] Specific examples

[1822] Emotion-based summer casual dress design

[1823] 1. User input: "Casual summer dress," "Bright color," "Breathable material."

[1824] 2. Emotion engine recognizes: User's emotions are "happy" and "excited"

[1825] 3. The device sends input data and emotion data to the server.

[1826] 4. Server analyzes: extracts keywords (summer, casual, bright colors, breathable, happy, excited)

[1827] 5. Server generated:

[1828] Color suggestions: Yellow, light blue

[1829] Suggested styles: A-line dress, midi length

[1830] Material suggestions: linen, cotton

[1831] 6. Server predicts trend: Minimalist design is in vogue

[1832] 7. The server sends the design proposal and trend prediction results to the device.

[1833] 8. User confirms: Check the visual image and material details and finalize the design

[1834] Prompt Sentence Examples

[1835] "Imagine a design for a casual summer dress. The color should be bright and the material should be breathable. The user's emotions should be happy and excited."

[1836] "Imagine designing winter office accessories. The design is elegant and the color is silver. The user emotions are calm and confident."

[1837] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1838] Step 1:

[1839] The user inputs the design requirements using the terminal interface.

[1840] Specifically, users use text fields and drop-down menus to input requirements such as "casual summer dress," "light color," and "breathable material."

[1841] Input: Design requirements (text format)

[1842] Output: Input design requirements (internal data of the device)

[1843] Step 2:

[1844] The terminal starts the emotion engine and starts collecting the user's emotion data.

[1845] Specifically, the emotion engine collects facial and voice data from the user via a webcam and microphone, and also analyzes the input text data, allowing it to classify the user's emotional state into categories such as "happy," "excited," or "calm."

[1846] Input: User's facial expression data, voice data, text data

[1847] Output: Analyzed emotion information (categorical data)

[1848] Step 3:

[1849] The terminal transmits the input design requirement data and the analyzed emotion data to the server.

[1850] Specifically, this data is converted into JSON format and sent to the server as an HTTP POST request.

[1851] Input: Design requirements data, emotion data (JSON format)

[1852] Output: HTTP POST request to the server

[1853] Step 4:

[1854] The server analyzes the received design requirement data and emotion data.

[1855] Specifically, it uses natural language processing (NLP) technology to extract important information from design requirements and process it in combination with emotional information, for example, extracting keywords such as "summer," "casual," "bright colors," "breathable," "happy," and "excited" from the input data.

[1856] Input: Design requirement data (text format), emotion data (categorical data)

[1857] Output: Extracted keywords and analysis information

[1858] Step 5:

[1859] The server uses a generative AI model to generate design proposals.

[1860] Specifically, it generates design proposals based on analyzed requirements and emotional data, as well as color theory and trend data. For example, it suggests colors like "yellow" and "light blue," suggests styles like "A-line dress" and "midi length," and selects materials like "linen" and "cotton."

[1861] Input: Extracted keywords and analysis information

[1862] Output: Generated design proposals (color, shape, material suggestions)

[1863] Step 6:

[1864] The server analyzes the latest market trends and predicts future trends.

[1865] Specifically, the project collects data from online fashion blogs, social media, shopping sites, etc., and uses machine learning algorithms to predict future design trends, such as the trend toward minimalist design.

[1866] Input: Market trend data (web data, social media data, etc.)

[1867] Output: Trend prediction results (future fashion information)

[1868] Step 7:

[1869] The server transmits the generated design proposals and trend prediction results to the terminal.

[1870] This information is sent to the device via HTTPS.

[1871] The device receives this and displays visual images, color palettes, material lists, etc. on a dashboard or preview screen.

[1872] Input: Generated design proposals, trend prediction results

[1873] Output: Design proposals and trend information displayed to the user

[1874] Step 8:

[1875] The user checks the proposed design on the device.

[1876] If necessary, feedback or correction requests can be resubmitted to the server via the input interface of the device, and the server will generate new design proposals based on the received feedback and present them to the device again.

[1877] Input: Feedback information (user comments, correction requests, etc.)

[1878] Output: Revised design proposal (design proposal resent from server)

[1879] (Application example 2)

[1880] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1881] Conventional design generation systems generate design proposals based solely on user input data. This makes it difficult to propose designs that reflect the user's emotions and psychological state, and fails to sufficiently improve user satisfaction. Furthermore, it is difficult to accurately reflect the latest market trends and future trends, making it an inappropriate solution for virtual stores, which must always incorporate the latest trends.

[1882] The specification processing by the specification 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 accepting design requirements input by a user, means for transmitting the design requirement data to the server, means for analyzing the accepted design requirements, means for generating design proposals based on the analyzed design requirements and the user's emotional state, means for analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to the terminal, means for the user to confirm the design proposals displayed on the terminal, and means for recognizing the user's emotional state using facial recognition and voice recognition. This enables personalized design proposals that take the user's emotional state into consideration, thereby increasing user satisfaction. Furthermore, design proposals that reflect the latest market trends and future trends can be made.

[1883] "Design requirements" refer to the design features and conditions desired by the user.

[1884] A "server" is a computer system that provides services and information to other devices on a network.

[1885] "Analysis" means examining data or information in detail to clarify its structure and meaning.

[1886] "Emotional state" refers to the user's psychological state or mood, and is information that can be inferred from facial expressions and voice.

[1887] A "design proposal" is a specific design proposal generated based on the analyzed data and requirements.

[1888] "Market trends" refers to current market trends and consumer preferences.

[1889] "Trend forecasting" is analysis to predict future consumer preferences and market changes.

[1890] A "terminal" is an electronic device that allows a user to input information and check the display.

[1891] "Facial recognition" is a technology that uses a camera to identify an individual's face and analyze its features.

[1892] "Speech recognition" is a technology that uses a microphone to convert voice data into text data.

[1893] "Personalization" refers to customization according to the needs and preferences of individual users.

[1894] A "visual image" is a picture or figure that is displayed in a visual form.

[1895] This invention is a system in which a server generates optimal design proposals based on the user's design requirements and emotional information, and makes proposals that reflect the latest market trends. Specifically, the system allows the user to input design requirements using a terminal and recognize emotional information, enabling personalized design proposals.

[1896] Hardware and Software Use

[1897] Device:

[1898] Smartphone (using an application that implements React Native)

[1899] Smartphone camera (using OpenCV for facial recognition)

[1900] Smartphone microphone (voice recognition is performed using the Google Cloud Speech-to-Text API)

[1901] server:

[1902] Server system (built using Python Flask)

[1903] Natural language processing libraries (using SpaCy and GPT-4)

[1904] AI models (using TensorFlow or PyTorch)

[1905] Data processing and calculation

[1906] 1. Design requirements and receiving emotional information:

[1907] The user inputs design requirements, such as "autumn jacket," "warm material," and "modern design," through the smartphone interface. At the same time, the smartphone's camera and microphone are used for facial and voice recognition to capture the user's emotional state (e.g., "relaxed" or "satisfied").

[1908] 2. Data transmission:

[1909] The device sends the user's design requirement data and emotion data to the server via an HTTP POST request.

[1910] 3. Data analysis and design generation:

[1911] The server analyzes the received design requirement data using a natural language processing library (such as SpaCy) to extract keywords. At the same time, it also analyzes sentiment data. Based on this data, it uses an AI model (a generative AI model using TensorFlow or PyTorch) to generate optimal design proposals.

[1912] 4. Trend Forecasting:

[1913] The server collects data from online fashion blogs, social media, shopping sites, and other sources, and uses AI to analyze market trends and predict future trends. These trend predictions are also reflected in design proposals.

[1914] 5. Design proposal submission:

[1915] The final design proposals and trend forecast results are sent from the server to the user's device and displayed for review, allowing the user to check the visual image, color palette, material list, and other details.

[1916] Specific examples

[1917] If a user is looking for a fall jacket:

[1918] The user types "autumn jacket," "warm material," and "modern design" into their smartphone, and the camera and microphone are used to recognize the emotional states of "relaxed" and "satisfied."

[1919] The server analyzes this data and suggests the most suitable color (e.g., "olive green" or "brown"), shape (e.g., "slim fit"), material (e.g., "wool"), etc.

[1920] The server analyzes the latest market trends and sends the generated design proposals and trend forecast results to the smartphone.

[1921] The user checks visual images and detailed design proposals and makes the final selection.

[1922] Prompt Sentence Examples

[1923] "Generate detailed design proposals for a fall jacket made of warm material with a modern design that is perfect for customers with a relaxed feel."

[1924] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1925] Step 1:

[1926] The user inputs the design requirements. Using the smartphone interface, the user inputs design requirements such as "autumn jacket," "warm material," and "modern design" in text. This input serves as the basis for data processing in each subsequent step.

[1927] Step 2:

[1928] The device recognizes emotional information. It uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and then performs facial recognition (using OpenCV) and voice recognition (using Google Cloud Speech-to-Text API). Through this process, the device identifies the user's emotional state as "relaxed" or "satisfied," for example. Emotional information is extracted from the user's facial expression and voice data using an emotion recognition algorithm.

[1929] Step 3:

[1930] The terminal sends the design requirement data and emotion data to the server. The terminal sends the design requirement data and emotion data entered by the user to the server via an HTTP POST request. The sent data includes text (design requirement) and emotion state (relaxed, satisfied, etc.).

[1931] Step 4:

[1932] The server analyzes the data. The server uses natural language processing (SpaCy or GPT-4) to analyze the received design requirement data and extract keywords. At the same time, it also analyzes the emotional data. As a result of this analysis, keywords such as "autumn," "jacket," "warm," and "modern" and emotional states such as "relaxed" and "satisfied" are obtained.

[1933] Step 5:

[1934] The server generates design proposals using a generative AI model (using TensorFlow or PyTorch) based on the analyzed requirements and sentiment data. The server suggests optimal colors ("olive green" or "brown"), shapes ("slim fit"), and materials ("wool"), for example. The AI ​​model is trained on a large amount of design data and generates design proposals by referencing related data.

[1935] Step 6:

[1936] The server analyzes the latest market trends and makes trend predictions. The server collects data from online fashion blogs, social media, shopping sites, etc. and uses AI to analyze market trends. Based on these results, future trends are predicted and incorporated into design proposals.

[1937] Step 7:

[1938] The server sends the generated design proposal and trend prediction results to the terminal. The server then sends the final generated design proposal and trend prediction results to the terminal as an HTTP response, which includes detailed information such as visual images, color palettes, and material lists.

[1939] Step 8:

[1940] The user checks the proposed design on their device. The user can check the design proposals and trend prediction results sent to the device on their smartphone screen and make corrections or feedback as necessary. For example, they can input a request for correction, such as "I want the color to be a little darker," and send it back to the server to fine-tune the design.

[1941] The above is the flow of specific processing steps, which enables personalized design proposals based on the user's needs and emotions.

[1942] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1943] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1944] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1945] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1946] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1947] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1948] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1949] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1950] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1951] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1952] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1953] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1954] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1955] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1956] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1957] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1958] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1959] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1960] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1961] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1962] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1963] The following is further disclosed regarding the above embodiment.

[1964] (Claim 1)

[1965] means for accepting user-input design requirements;

[1966] means for transmitting the design requirement data to a server;

[1967] a means for analyzing the received design requirements;

[1968] means for generating design proposals based on the analyzed design requirements;

[1969] A means of analyzing the latest market trends and predicting future trends,

[1970] means for transmitting the generated design proposals and trend prediction results to a terminal;

[1971] A means for users to check the design proposals displayed on their devices;

[1972] A system including:

[1973] (Claim 2)

[1974] 2. The system according to claim 1, further comprising means for suggesting suitable color combinations using color theory and trend data when generating design proposals.

[1975] (Claim 3)

[1976] The system according to claim 1, further comprising means for suggesting shapes and silhouettes based on a specified use and season when generating design proposals.

[1977] "Example 1"

[1978] (Claim 1)

[1979] means for accepting design requirements input by a user;

[1980] means for transmitting the design requirement data to a server;

[1981] means for analyzing the received design requirements;

[1982] means for generating a design proposal based on the analyzed design requirements;

[1983] A means of analyzing the latest market trends and predicting future trends;

[1984] means for transmitting the generated design proposal and trend prediction result to a terminal;

[1985] A means for the user to confirm the design proposal displayed on the terminal;

[1986] a means for inputting feedback on the design plan confirmed by the user and retransmitting the feedback to the server to request a modification;

[1987] A system including:

[1988] (Claim 2)

[1989] 2. The system according to claim 1, further comprising means for proposing suitable color combinations using theory and data when generating design proposals.

[1990] (Claim 3)

[1991] The system according to claim 1, further comprising means for proposing shapes and silhouettes based on designated uses and seasons when generating design proposals.

[1992] "Application Example 1"

[1993] (Claim 1)

[1994] means for accepting user-input design requirements;

[1995] means for transmitting the design requirement data to a server;

[1996] a means for analyzing the received design requirements;

[1997] means for generating design proposals based on the analyzed design requirements;

[1998] A means of analyzing the latest market trends and predicting future trends,

[1999] means for transmitting the generated design proposals and trend prediction results to a terminal;

[2000] A means for users to check the design proposals displayed on their devices;

[2001] A means for users to review the design proposal and provide feedback or edits;

[2002] A system including:

[2003] (Claim 2)

[2004] 2. The system according to claim 1, further comprising means for suggesting suitable color combinations using color theory and trend data when generating design proposals.

[2005] (Claim 3)

[2006] The system according to claim 1, further comprising means for suggesting shapes and silhouettes based on a specified use and season when generating design proposals.

[2007] (Claim 4)

[2008] 2. The system according to claim 1, further comprising means for providing the generated design proposal to the user and enabling the user to check the proposal online in a manner close to the actual product.

[2009] "Example 2: Combining Emotion Engines"

[2010] (Claim 1)

[2011] means for accepting user-input design requirements;

[2012] means for transmitting the design requirement data and the user's emotion data to a server;

[2013] means for analyzing the received design requirements and sentiment information;

[2014] means for generating design proposals based on the analyzed design requirements and emotion information;

[2015] A means of analyzing the latest market trends and predicting future trends,

[2016] means for transmitting the generated design proposals and trend prediction results to a terminal;

[2017] A means for users to check the design proposals displayed on the device and enter feedback;

[2018] A system including:

[2019] (Claim 2)

[2020] 2. The system according to claim 1, further comprising means for suggesting suitable color combinations using color theory and trend data when generating design proposals.

[2021] (Claim 3)

[2022] The system according to claim 1, further comprising means for suggesting shapes and silhouettes based on a specified use and season when generating design proposals.

[2023] "Application example 2 when combining emotion engines"

[2024] (Claim 1)

[2025] means for accepting user-input design requirements;

[2026] means for transmitting the design requirement data to a server;

[2027] a means for analyzing the received design requirements;

[2028] a means for generating a design proposal based on the analyzed design requirements and the user's emotional state;

[2029] A means of analyzing the latest market trends and predicting future trends,

[2030] means for transmitting the generated design proposals and trend prediction results to a terminal;

[2031] A means for users to check the design proposals displayed on their devices;

[2032] means for recognizing the emotional state of a user using facial and voice recognition;

[2033] A system including:

[2034] (Claim 2)

[2035] 2. The system according to claim 1, further comprising means for suggesting suitable color combinations using color theory and trend data when generating design proposals.

[2036] (Claim 3)

[2037] The system according to claim 1, further comprising means for suggesting shapes and silhouettes based on a specified use and season when generating design proposals. [Explanation of symbols]

[2038] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for accepting user-input design requirements; means for transmitting the design requirement data to a server; a means for analyzing the received design requirements; means for generating design proposals based on the analyzed design requirements; A means of analyzing the latest market trends and predicting future trends, means for transmitting the generated design proposals and trend prediction results to a terminal; A means for users to check the design proposals displayed on their devices; A system including:

2. 2. The system according to claim 1, further comprising means for proposing suitable color combinations using color theory and trend data when generating design proposals.

3. The system according to claim 1, further comprising means for proposing shapes and silhouettes based on designated uses and seasons when generating design proposals.

Images