System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving user input; means for analyzing the received user input; means for generating a plurality of proposed designs based on the analysis; means for evaluating and optimizing the generated proposed designs; and means for providing the optimized proposed designs to a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The goal is to solve the problems faced by design agencies, small businesses, independent artists, and others, such as a lack of creative design ideas, difficulty in creating effective marketing materials, and a lack of ways to increase efficiency while maintaining creativity. [Means for solving the problem]

[0005] The present invention provides a system including a means for receiving user input, a means for analyzing the received user input, a means for generating a plurality of design proposals based on the analysis results, a means for evaluating and optimizing the generated design proposals, and a means for providing the optimized design proposals to a user terminal, thereby enabling a user to quickly obtain innovative and feasible design proposals and increasing efficiency while improving creativity.

[0006] "User input" is initial data such as text, sketches, or images provided by the user.

[0007] "Means for receiving" refers to the function by which a server or terminal receives user input.

[0008] An "analyzing means" is an algorithm or software that processes received user input to understand and break down its content.

[0009] "Design proposals" refer to original visual concepts and graphic designs proposed by the generative AI model based on the analysis results.

[0010] "Generative means" refers to the function of the generative AI model that generates design ideas based on user input.

[0011] "Means of evaluation" are criteria or algorithms for determining whether the generated design proposal meets the user's requirements.

[0012] "Optimization means" refers to the processes and techniques used to improve the design proposal based on the evaluation results and to create the optimal form.

[0013] "Means of providing" refers to the function for sending and displaying optimized design proposals on the user's device.

[0014] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0015] "Computer vision algorithms" are techniques for analyzing images and sketches and understanding their content. [Brief explanation of the drawings]

[0016] [Figure 1]1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention is a system in which generative AI generates innovative design concepts based on initial ideas and instructions provided by users. Below, we explain the program processing of this system in natural language and provide concrete examples.

[0038] System configuration

[0039] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit and performs complex data analysis and runs generative AI models. The terminal is a user-operated device that sends user input and receives design proposals.

[0040] Program processing

[0041] 1. The server receives user input

[0042] Users upload and send input data such as text, sketches, and images from their devices, and the server receives and stores the data in the required format.

[0043] 2. Data Analysis

[0044] The server analyzes the received data, using natural language processing (NLP) techniques for text data and computer vision algorithms for sketches and images, to extract important features and keywords from the user's input.

[0045] 3. Generate design proposals

[0046] Based on the analysis results, the server uses a generative AI model to generate multiple design proposals, each of which includes unique elements tailored to the user's requirements.

[0047] 4. Evaluate and optimize design ideas

[0048] The server evaluates the generated design proposals to see how well they meet user expectations, and then optimizes and fine-tunes the design proposals based on the evaluation results.

[0049] 5. Providing design proposals

[0050] The server then sends the optimized design proposals to the device for the user to review, and the user can review these design proposals and, if necessary, send feedback or correction requests to the server.

[0051] Specific examples

[0052] For example, if a user needs a packaging design for a new product, the system works like this:

[0053] 1. Providing User Input

[0054] Users upload text such as "I want a simple packaging design with a nature theme," along with a sketch of a plant and an image of a specific color scheme from their device to the server.

[0055] 2. Data Analysis

[0056] The server uses NLP to extract keywords such as "nature," "simple," and "packaging design" from this text, and then uses computer vision to extract plant shapes from sketches and color schemes from images.

[0057] 3. Generate design proposals

[0058] Based on the extracted features, the server uses a generative AI model to generate multiple package design ideas, each of which reflects the image of plants and simplicity.

[0059] 4. Evaluate and optimize design ideas

[0060] The server evaluates each design proposal, selects the one that best meets the user's requirements, and then makes further adjustments, such as adjusting the color and layout.

[0061] 5. Providing design proposals

[0062] The server sends the optimized design to the device and provides it to the user, and if the user is not satisfied, further revisions are made through feedback.

[0063] This series of processes allows users to quickly and efficiently obtain high-quality design proposals, supporting users' creativity and significantly improving the efficiency of their design work.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] The user uses the device to input initial design ideas and instructions, specifically uploading text, sketches, images, etc., and then clicks a send button to send the data to the server.

[0067] Step 2:

[0068] The server receives the data sent by the user. After receiving it, the server validates the data format and ensures that all required data is present. For example, it checks that text is sent correctly and that sketches and images are in the supported formats (JPEG, PNG, etc.).

[0069] Step 3:

[0070] The server analyzes the received text data using natural language processing (NLP) technology, which extracts keywords such as "simple," "modern," and "logo."

[0071] Step 4:

[0072] The server analyzes the received sketches and images using computer vision technology, specifically recognizing the shape of the sketch and extracting features such as the color and pattern of the image.

[0073] Step 5:

[0074] The server then formats the analysis results as input data for generating multiple design proposals, and creates design prompts by integrating the text analysis results with the features of sketches and images.

[0075] Step 6:

[0076] The server uses a generative AI model to generate design proposals. During the generation process, multiple different design proposals are generated based on the interpreted user requirements, such as a simple and modern logo.

[0077] Step 7:

[0078] The server evaluates the generated design proposals and scores them based on the evaluation criteria to determine which design proposal best meets the user's requirements.

[0079] Step 8:

[0080] The server then optimizes the design proposals with the highest scores based on the evaluation results, which includes adjusting color tones and optimizing the layout.

[0081] Step 9:

[0082] The server then formats the optimized design into its final form, and the resulting design, formatted as a high-resolution image, is sent to the user's device.

[0083] Step 10:

[0084] The user can check the design proposal sent to them on their device. They can then enter feedback or corrections they would like to make and send it back to the server. The server will receive this and make any necessary corrections.

[0085] These steps allow users to quickly receive specific, high-quality ideas for the design they want.

[0086] Example 1

[0087] 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."

[0088] In the modern design process, it is difficult and time-consuming to quickly generate high-quality design proposals based on the user's initial ideas and instructions. In particular, there is a need to respond to various user input formats, analyze and evaluate them, and provide optimal design proposals. Furthermore, an efficient method is needed to properly evaluate how well the generated design proposals meet the user's expectations and to further optimize them.

[0089] 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.

[0090] In this invention, the server includes means for receiving user input, means for saving the received user input in a database, means for analyzing the saved user input, means for generating multiple design proposals using a generative AI model based on the analysis results, means for evaluating and optimizing the generated design proposals, and means for providing the optimized design proposals to a user terminal, thereby enabling efficient processing of various user inputs and rapid generation of high-quality design proposals.

[0091] "User input" means instructions or initial data such as text, sketches, or images provided by a user to the system.

[0092] "Database" means a digital storage system for storing received user-entered data and making it available for reference in subsequent analysis or generation processes.

[0093] "Analysis" is the process of processing received and stored user-entered data and extracting important features or keywords.

[0094] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to generate new design ideas based on user input.

[0095] "Design Proposals" are multiple design and layout proposals created by a generative AI model.

[0096] The "evaluation method" is the process of determining how well the generated design proposal meets the user's requirements.

[0097] "Optimization" is the process of adjusting elements of a design proposal based on the evaluation results to create a form that best meets user expectations.

[0098] "User terminal" means a device through which a user accesses the system, sends input data, and receives generated design proposals.

[0099] This invention relates to a system that generates multiple design proposals using a generative AI model based on user input, optimizes them, and provides them to the user. Specific embodiments of the invention are described below.

[0100] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit and executes analysis and generative AI models. The terminal is a device operated by the user, used to send input data and receive design proposals. The user provides initial ideas and specific instructions.

[0101] Hardware and software used

[0102] For server hardware, a server machine equipped with a regular processor and memory is used. For example, an EC2 instance from Amazon Web Services (AWS) can be used. For data storage, a cloud storage service such as Amazon S3 is used. For software to run the generative AI model, a machine learning framework such as TensorFlow or PyTorch is used. For natural language processing (NLP), SpaCy or NLTK is used, and for computer vision, OpenCV or TensorFlow is used.

[0103] The devices used may be personal computers, smartphones, tablets, etc. These devices require an internet connection and communicate with the server via a browser or dedicated application.

[0104] Specific Examples

[0105] 1. Providing User Input

[0106] Users access the system using their own devices. For example, they can provide the text "I want a simple package design with a nature theme," as well as sketches of plants and images with specific color schemes. An example of a prompt sentence could be, "I need a package with a natural and simple design. Please refer to the images and sketches below."

[0107] 2. Data storage and analysis

[0108] The server receives input data sent by users and stores it in a database. The saved text data is then analyzed using natural language processing (NLP) techniques to extract keywords such as "nature," "simple," and "packaging design." For sketches and images, computer vision algorithms are used to identify the shape and color of plants.

[0109] 3. Generate design proposals

[0110] The server generates a specific prompt based on the analysis results and inputs it into the generative AI model. For example, this prompt might be in the form of, "Please generate a package design with the themes of 'nature' and 'simplicity' based on the image and sketch below." The generative AI model then generates multiple design proposals based on this prompt.

[0111] 4. Evaluation and Optimization

[0112] The server evaluates the generated design proposals and selects the one that best meets the user's requirements. Furthermore, it optimizes the design proposals by fine-tuning the color and layout based on the evaluation results. This evaluation can be performed using heuristic evaluation or machine learning algorithms.

[0113] 5. Providing design ideas and feedback

[0114] The server then sends the optimized design proposal to the user's device for review. The user reviews the proposal and provides feedback or corrections as needed. The server then adjusts the design proposal based on this feedback, and the process is repeated until the final design is completed.

[0115] This series of processes allows users to quickly and efficiently obtain high-quality design proposals. The present invention is expected to support users' creativity and significantly improve the efficiency of design work.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1:

[0118] The user sends initial input data from their device to the server. The user uses a personal computer or smartphone to input text, sketches, images, etc. into the system. The input includes the text "I want a simple packaging design with a nature theme," a sketch of a plant, and an image of a specific color scheme. This data is sent to the server via a form or file upload function.

[0119] Input: User text, sketches, and images

[0120] Output: User-entered data sent to the server

[0121] Step 2:

[0122] The server saves the input data received from the user to a database. The specific saving operation uses a cloud storage service (e.g., Amazon S3), and the data is managed in an appropriate folder structure for each user.

[0123] Input: User-entered data sent to the server

[0124] Output: User-entered data stored in a database

[0125] Step 3:

[0126] The server analyzes the stored user-entered data. For text data, natural language processing (NLP) techniques are used to extract keywords such as "nature," "simple," and "packaging design." For sketches and images, computer vision algorithms are used to identify the shape and color of plants and extract their features.

[0127] Input: User-entered data stored in a database

[0128] Output: Extracted features and keywords

[0129] Step 4:

[0130] The server generates a specific prompt based on the analysis results. The generated prompt is input into a generative AI model, which generates multiple design proposals. An example of a prompt is, "Please generate a package design with the themes of 'nature' and 'simplicity' based on the image and sketch below."

[0131] Input: extracted features and keywords

[0132] Output: Generated prompts and design proposals

[0133] Step 5:

[0134] The server evaluates and optimizes the generated design proposals. Using an evaluation algorithm, it determines how well the generated design proposals meet the user's requirements. Based on the evaluation results, the design proposals are optimized by fine-tuning their color and layout.

[0135] Input: Generated design proposal

[0136] Output: Evaluation results and optimized design proposals

[0137] Step 6:

[0138] The server sends the optimized design proposal to the user's device, using the HTTP protocol and WebSocket for communication, allowing the design proposal to be viewed in the user interface.

[0139] Input: Optimized design proposal

[0140] Output: Optimized design proposal sent to user device

[0141] Step 7:

[0142] The user checks the submitted design proposal on their device and sends feedback to the server. If necessary, they can submit correction requests, and the server will then adjust the design proposal accordingly.

[0143] Input: User feedback

[0144] Output: Final, refined design proposal

[0145] This series of processes allows users to obtain high-quality design proposals quickly and efficiently.

[0146] (Application example 1)

[0147] 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."

[0148] In modern design generation, users are expected to quickly obtain high-quality design proposals simply by providing their ideas and instructions. However, conventional systems cannot accurately reflect the user's intentions, and as a result, the generated designs often do not meet the user's expectations. Furthermore, there is no process for reflecting user feedback and re-optimizing the design, making it difficult to efficiently improve design quality.

[0149] 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.

[0150] In this invention, the server includes means for receiving user input, means for analyzing the received user input, means for generating multiple design proposals based on the analysis results, means for evaluating and optimizing the generated design proposals, means for providing the optimized design proposals to the user terminal, and means for re-optimizing the design proposals based on the evaluation results and reflecting user feedback. This makes it possible to quickly provide design proposals that more accurately reflect the user's intentions, and further to improve the quality of the design by reflecting user feedback.

[0151] "Means for receiving user input" refers to devices or software that allow a user to send data, such as text, sketches, or images, to the system and receive it.

[0152] "Means for analyzing received user input" means equipment or software that includes algorithms or techniques for analyzing received text, sketches, images, etc., and extracting key features or keywords.

[0153] "Means for generating multiple design proposals based on analysis results" refers to equipment or software that has the function of automatically generating multiple design proposals using a generative AI model based on analyzed data.

[0154] "Means for evaluating and optimizing the generated design proposals" refers to algorithms or software that evaluate the generated design proposals, check how well they meet the user requirements, and make any necessary optimizations.

[0155] "Means for providing optimized design proposals to a user device" refers to equipment or software that has the function of transmitting optimized design proposals to a user device so that the user can review them.

[0156] "Means of re-optimizing design proposals by reflecting user feedback based on evaluation results" refers to algorithms or software that have the function of re-evaluating and optimizing design proposals based on user feedback.

[0157] This invention is a system in which a user inputs initial ideas and instructions, and a generative AI model generates innovative design concepts based on those ideas.

[0158] System configuration

[0159] The system mainly consists of a server, terminals, and users. The server acts as a central control unit and performs complex data analysis and executes generative AI models. The terminals are devices operated by users and are used to send user input and receive design proposals. Users access the system using terminals such as smartphones and tablets.

[0160] Program processing

[0161] The server performs the following steps:

[0162] 1. Receiving user input: The user uploads data such as text, sketches, and images from their device and sends it to the server, which receives the data and stores it in an appropriate format.

[0163] 2. Data Analysis: The server analyzes the received data, using natural language processing (NLP) techniques for text data and computer vision algorithms for sketches and images, to extract important features and keywords from the user's input.

[0164] 3. Design proposal generation: Based on the analysis results, the server uses a generative AI model to generate multiple design proposals, each of which contains unique elements that meet the user's requirements.

[0165] 4. Evaluate and optimize the design: The server evaluates the generated design to see how well it meets the user's expectations. Based on the evaluation results, it optimizes and fine-tunes the design.

[0166] 5. Providing design proposals: The server sends the optimized design proposals to the device for the user to review. The user reviews these design proposals and provides feedback if necessary.

[0167] 6. Reflecting feedback and re-optimizing: Based on user feedback, the server re-evaluates the design proposal and reflects the feedback to optimize the design proposal.

[0168] Hardware and software used

[0169] Hardware: Smartphones, tablets, servers (cloud-based)

[0170] Software: Python programs, OpenAI API, natural language processing (NLP) techniques, computer vision algorithms

[0171] Specific examples

[0172] For example, if a user needs a packaging design for a new product, the system works as follows:

[0173] 1. Providing user input: The user uploads the text "I want a simple packaging design with a nature theme," along with a sketch of a plant and an image of a specific color scheme, from their device to the server.

[0174] 2. Data analysis: The server uses NLP to extract keywords such as "nature," "simple," and "packaging design" from the text, and uses computer vision to extract plant shapes from sketches and color schemes from images.

[0175] 3. Design proposal generation: Based on the extracted features, the server uses a generative AI model to generate multiple package design proposals, each of which reflects the image of plants and simplicity.

[0176] 4. Evaluating and optimizing design ideas: The server evaluates each design idea, selects the one that best meets the user's requirements, and then performs further fine-tuning, such as adjusting the color and layout.

[0177] 5. Providing design proposals: The server sends the optimized design proposals to the terminal and provides them to the user. If the user is not satisfied, further revisions will be made through feedback.

[0178] 6. Reflecting feedback and re-optimizing: If a user provides feedback such as "Use a brighter green," the server will re-evaluate and optimize the design based on that feedback and serve it again.

[0179] Prompt Sentence Examples

[0180] Text: I want a simple package design with a nature theme.

[0181] Sketch Features: Simple sketches of trees, leaves, and flowers

[0182] Color characteristics: Bright green and pale blue tones

[0183] Based on these prompts, the system generates design proposals using the OpenAI API, and after receiving user feedback, the system re-optimizes the design and delivers it to the user.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The server receives user input. The user uses a terminal to upload text such as "I want a simple package design with a nature theme," a sketch of a plant, and an image of a specific color scheme. The server receives this input data and saves it as text data, sketch image data, and color scheme image data.

[0187] Step 2:

[0188] The server analyzes the received user input. It uses natural language processing (NLP) technology on the text data to extract keywords such as "nature," "simple," and "package design." It uses computer vision algorithms on the sketch image data to extract the shape and characteristics of plants. It also uses computer vision algorithms on the color scheme image data to extract color scheme information such as bright green and light blue. This allows the user's intention to be extracted as specific features and keywords.

[0189] Step 3:

[0190] The server generates multiple design proposals based on the analysis results. Using the analyzed text keywords, sketch features, and color scheme information, it creates prompts for the generative AI model, which then generates design proposals based on those prompts. The generated design proposals include original elements that are in line with the input data. For example, they include elements such as a "simple design with a nature theme," "reflecting the shape of a specific plant," and "using a bright green and light blue color scheme."

[0191] Step 4:

[0192] The server evaluates the generated design proposals. The design proposals output by the generative AI model are analyzed using an evaluation algorithm to check how well they match the user's instructions and input data. The evaluation checks the degree of agreement of keywords, shapes, and color schemes. Based on the evaluation results, if further optimization is required, fine-tuning of colors and layout is performed.

[0193] Step 5:

[0194] The server provides the optimized design proposal to the user's device. The generated and optimized design proposal is sent to the user's device for the user to review. The user reviews the proposed design proposal, and if they are not satisfied, they send feedback from their device to the server.

[0195] Step 6:

[0196] The server receives feedback from the user and re-optimizes the design proposal based on that feedback. It analyzes the feedback provided by the user (e.g., "Please use a brighter green") and uses the generative AI model and optimization algorithm to re-generate and optimize the design proposal. It then provides the re-generated and optimized design proposal to the user again and confirms that the design proposal has been improved based on the feedback.

[0197] 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.

[0198] This invention is a system in which generative AI generates innovative design concepts based on initial ideas and instructions provided by the user. This system is combined with an emotion engine that recognizes the user's emotions, and is able to propose design proposals that reflect the user's emotions. Below, we will explain the program processing of this system in natural language, and provide concrete examples.

[0199] System configuration

[0200] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit, performing complex data analysis and running generative AI models. The terminal is a device operated by the user, used to send user input and receive design proposals. In addition, it is equipped with an emotion engine, which has the built-in ability to recognize and analyze user emotions.

[0201] Program processing

[0202] 1. The server receives user input

[0203] Users upload text, sketches, images, and even emotional data from their devices, and the server receives and stores the data in the required format.

[0204] 2. Data Analysis

[0205] The server analyzes the received text data using natural language processing (NLP) technology to extract keywords such as "simple," "modern," and "logo" from the text, and also analyzes sketches and images using computer vision technology to extract features.

[0206] 3. Emotion Data Analysis

[0207] The emotion engine analyzes the user's emotional data, which includes emotional information derived from the user's voice and facial expressions. The emotion engine identifies emotions such as "happy," "excited," and "calm."

[0208] 4. Generate design proposals

[0209] Based on the analysis results, the server uses a generative AI model to generate multiple design proposals. Emotional data obtained from the emotion engine is also reflected in the design prompts. For example, if the user feels "calm," color schemes and design elements that reflect that emotion will be suggested.

[0210] 5. Evaluate and optimize design ideas

[0211] The server evaluates the generated design proposals and selects the one that best matches the user's needs and emotions. The evaluation criteria also take into account emotional data, and the design proposal that best matches the user's emotions is scored. The server then optimizes the design proposals and adjusts the details based on the evaluation results.

[0212] 6. Providing design proposals

[0213] The server sends the optimized design proposal to the device, where the user can review it and send feedback or correction requests to the server if necessary. The server receives the feedback and makes corrections.

[0214] Specific examples

[0215] For example, if a user needs a logo for a new cafe, the system works like this:

[0216] 1. Providing User Input

[0217] The user uploads the text "I want a nature-themed relaxing logo," along with a simple sketch and a specific color scheme image, to the server from their device, and the emotion engine recognizes that the user is relaxed.

[0218] 2. Data Analysis

[0219] The server uses NLP to extract keywords such as "nature," "relax," and "logo" from the text, and then uses computer vision to analyze the shape of the sketch and the color scheme of the image.

[0220] 3. Emotion Data Analysis

[0221] The emotion engine analyzes the user's emotions and identifies that "relaxation" is the main emotion.

[0222] 4. Generate design proposals

[0223] The server uses a generative AI model to generate multiple logo designs based on these analysis results and emotional data, such as a nature-themed logo using muted shades of green and blue.

[0224] 5. Evaluate and optimize design ideas

[0225] The server evaluates each logo design, selects the one that best matches the user's needs and emotions, and then fine-tunes it, adjusting the color and shape, for example, to create the optimal design.

[0226] 6. Providing design proposals

[0227] The server sends the optimized logo design to the device and provides it to the user, and if the user is not satisfied, further revisions are made through feedback.

[0228] In this way, users can quickly obtain high-quality design proposals that reflect their own emotions, improving the quality and fit of their designs, supporting creativity and streamlining work.

[0229] The processing flow will be explained below.

[0230] Step 1:

[0231] Users use their device to input their initial design ideas and instructions, including uploading text, sketches, and images, providing emotional data, and then clicking a send button to send this data to the server.

[0232] Step 2:

[0233] The server receives the text data, sketches, images, and emotion data sent by the user. After receiving the data, the server verifies the format of each data and ensures that all required data is present. For example, it verifies that the text is sent correctly and that the sketches and images are in the supported formats (JPEG, PNG, etc.).

[0234] Step 3:

[0235] The server analyzes the received text data using natural language processing (NLP) technology, specifically extracting keywords such as "simple," "modern," and "logo" from the text.

[0236] Step 4:

[0237] The server analyzes the received sketches and images using computer vision technology, specifically recognizing the shape of the sketch and extracting features such as the color and pattern of the image.

[0238] Step 5:

[0239] The emotion engine analyzes the emotional data provided by the user, specifically identifying emotions such as "satisfied," "excited," or "calm" based on information gleaned from the user's voice and facial expressions.

[0240] Step 6:

[0241] The server then formats the analysis results as input data for generating multiple design proposals. It creates design prompts by integrating the text analysis results, features of sketches and images, and emotion data.

[0242] Step 7:

[0243] The server uses a generative AI model to generate design proposals. The generation process takes into account the interpreted user request as well as emotional data. For example, if the user is feeling "relaxed," the server will suggest color schemes and design elements that reflect that emotion.

[0244] Step 8:

[0245] The server evaluates the generated design proposals and scores them based on the evaluation criteria to determine which design proposal best suits the user's needs and emotions. Emotional data is also taken into account as an evaluation criterion.

[0246] Step 9:

[0247] The server then optimizes the design proposals with the highest scores based on the evaluation results, which includes adjusting color tones and optimizing the layout.

[0248] Step 10:

[0249] The server then formats the optimized design into its final form, and the resulting design, formatted as a high-resolution image, is sent to the user's device.

[0250] Step 11:

[0251] The user can check the design proposal sent to them on their device. They can then enter feedback or corrections they would like to make and send it back to the server. The server will receive this and make any necessary corrections.

[0252] These steps allow users to quickly receive high-quality design proposals that reflect their emotions, improving the quality and fit of the design, supporting creativity and streamlining work.

[0253] Example 2

[0254] 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."

[0255] Conventional design generation systems lacked a means to provide design proposals that reflected the user's emotions, making it difficult to increase user satisfaction. Furthermore, there was a lack of a system that could accurately analyze the user's needs and emotions and quickly generate and provide optimal design proposals in response. This meant that users could not obtain designs that accurately reflected their requirements, and the process of providing feedback and making corrections was time-consuming.

[0256] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0257] In this invention, the server includes means for receiving user input, means for analyzing the received user input, means for recognizing and analyzing user emotion data, means for generating multiple design proposals based on the analysis results and the emotion data, means for evaluating and optimizing the generated design proposals, and means for providing the optimized design proposals to the user terminal, thereby enabling the rapid provision of high-quality design proposals that reflect the user's emotions.

[0258] "User Input" means text, sketches, images, and other information provided by a user.

[0259] "Means for receiving" refers to the functionality by which the server receives user input.

[0260] "Means of analysis" refers to technology for analyzing the content of user input and extracting keywords and features.

[0261] "Emotional data" refers to emotional information recognized and analyzed from the user's voice, facial expressions, etc.

[0262] "Means for recognizing and analyzing emotional data" refers to the ability to identify a user's emotions using an emotion engine.

[0263] "Design Proposals" refers to multiple design proposals generated based on the analysis results and emotion data.

[0264] "Means for generating" refers to the functionality for generating multiple design alternatives using a generative AI model.

[0265] "Means for evaluation and optimization" refers to the function of evaluating the generated design proposals, selecting the proposal that best suits the user's requirements and emotions, and fine-tuning it.

[0266] "Means of providing" refers to the function for sending optimized design proposals to the user's terminal.

[0267] "User Terminal" means the electronic device used by a User to submit input and receive design suggestions.

[0268] "Natural language processing" refers to the technology of analyzing a user's text input and extracting keywords and meaning.

[0269] "Computer vision algorithms" refers to techniques for analyzing the features of sketches and images.

[0270] "Generative AI model" refers to an artificial intelligence model that generates design ideas based on user input and emotional data.

[0271] A "prompt" refers to an instruction that a generative AI model uses to generate design proposals.

[0272] Program Generation and Explanation

[0273] The system of this invention is designed to generate innovative design concepts based on user input. The system incorporates an emotion engine that recognizes the user's emotions and can propose design proposals that reflect the user's emotional state.

[0274] Hardware and software used

[0275] The system mainly uses the following hardware and software:

[0276] Server: Responsible for receiving data, analyzing it, and running generative AI models. Specifically, it utilizes AWS computing resources.

[0277] Device: The user sends input data and receives the generated design proposals. A standard computer or smartphone is used.

[0278] Natural Language Processing (NLP) techniques: Use TensorFlow to parse text input.

[0279] Computer Vision Techniques: Use OpenCV to analyze sketches and images.

[0280] Emotion Engine: Uses Google Cloud AutoML to analyze the user's voice and facial expressions.

[0281] Generative AI model: We use OpenAI's GPT-3 to generate design ideas.

[0282] Evaluation and optimization: We use scikit-learn and Photoshop APIs to evaluate and optimize the generated design solutions.

[0283] Data processing and calculation

[0284] 1. Receiving User Input

[0285] Users upload text, sketches, images, and emotional data, including voice and facial expressions, from their devices to the server.

[0286] 2. Data storage

[0287] The server stores the received data in AWS S3 or RDS.

[0288] 3. Data Analysis

[0289] The server uses NLP technology (TensorFlow) to analyze text and extract keywords, and computer vision technology (OpenCV) to extract features from sketches and images.

[0290] 4. Emotion Data Analysis

[0291] The emotion engine (Google Cloud AutoML) analyzes user emotion data and recognizes specific emotional states.

[0292] 5. Generate design proposals

[0293] Based on the above analysis results, the server generates multiple design proposals using a generative AI model (OpenAI's GPT-3).

[0294] 6. Evaluate and optimize design ideas

[0295] The server evaluates the generated design proposals, performs scoring using scikit-learn, and then optimizes the proposals using the Photoshop API.

[0296] 7. Providing design proposals

[0297] The optimized design is sent to the user's device, where the user can review it and provide feedback if necessary.

[0298] Examples of specific examples and prompts

[0299] For example, if a user needs a logo for a new cafe, the system might do the following:

[0300] 1. Providing User Input

[0301] Users upload text such as "I want a nature-themed, relaxing logo," a simple sketch, and a specific color scheme image from their device to the server, and the emotion engine recognizes that the user is relaxing.

[0302] 2. Data Analysis

[0303] The server extracts keywords such as "nature," "relaxation," and "logo" from the text and analyzes sketches and color scheme images.

[0304] 3. Emotion Data Analysis

[0305] The emotion engine identifies the user's emotion as "relaxed."

[0306] 4. Generate design proposals

[0307] Based on the analysis results and emotion data, the server uses a generative AI model to generate multiple logo designs, such as a nature-themed logo using muted shades of green and blue.

[0308] 5. Evaluate and optimize design ideas

[0309] The server evaluates each logo design and selects the design that best matches the user's needs and emotions, then adjusts the color and shape.

[0310] 6. Providing design proposals

[0311] The server sends the optimized logo design to the device.

[0312] Prompt Sentence Examples

[0313] "I'd like to create a new logo for my cafe. I'd like the theme to be nature-themed and relaxing. I'd like it to have a green and blue color scheme as the base."

[0314] This system allows users to quickly obtain high-quality design proposals that reflect their own emotions.

[0315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0316] Step 1: Providing User Input

[0317] ----

[0318] The user uses the device to provide text, sketches, images, and emotion data to the server. For example, the user can type, "I want a nature-themed relaxing logo," and upload related sketches and color scheme images. The emotion engine then recognizes that the user is relaxed based on their voice and facial expression.

[0319] Input: Text (e.g., "Relaxing nature-themed logos"), sketches, images, audio, facial expressions

[0320] Output: Data provided to the server

[0321] Step 2: Receiving and storing data

[0322] ----

[0323] The server receives input data sent by the user, saves images and sketches to AWS S3, and saves text data to RDS.

[0324] Input: User-submitted text, sketches, images, voice, and facial expressions

[0325] Output: User input information stored in a database

[0326] Step 3: Analyzing the text data

[0327] ----

[0328] The server uses NLP (Natural Language Processing) technology to analyze the text data with TensorFlow and extract keywords, such as "nature," "relax," and "logo."

[0329] Input: Saved text data

[0330] Output: Extracted keywords (e.g., "nature," "relax," "logo")

[0331] Step 4: Analyzing the image data

[0332] ----

[0333] The server uses computer vision technology to analyze the shape and features of sketches and images using OpenCV, specifically analyzing hue, brightness, shape, etc.

[0334] Input: Saved sketches and image data

[0335] Output: Analyzed image feature information (shape, color, etc.)

[0336] Step 5: Analyze the sentiment data

[0337] ----

[0338] The emotion engine uses Google Cloud AutoML to analyze emotions from the user's voice and facial expressions and identify specific emotional states such as "relaxed."

[0339] Input: Stored voice data and facial expression data

[0340] Output: Analyzed emotion information (e.g., "Relaxed")

[0341] Step 6: Generate design ideas

[0342] ----

[0343] Based on the analysis results and emotion data, the server uses a generative AI model (OpenAI's GPT-3) to generate multiple design proposals. For example, it proposes a logo design based on green and blue tones based on the relaxed emotion.

[0344] Input: extracted keywords, analyzed image feature information, analyzed emotion information

[0345] Output: Multiple design proposals generated

[0346] Step 7: Evaluate and optimize design alternatives

[0347] ----

[0348] The server evaluates the generated design proposals, scores them using scikit-learn, and selects the one that best suits the user's needs and emotions. It then optimizes the design proposals by adjusting color, shape, etc. using the Photoshop API.

[0349] Input: Multiple generated design ideas

[0350] Output: Optimized design proposal

[0351] Step 8: Submit a design proposal

[0352] ----

[0353] The server sends the optimized design proposal to the user's device. The user checks the design proposal on the device and sends feedback to the server if necessary. The server then makes further revisions based on this feedback.

[0354] Input: Optimized design proposal

[0355] Output: Design proposals provided to users, and suggested revisions based on their feedback

[0356] (Application example 2)

[0357] 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."

[0358] Conventional design generation systems were unable to reflect the user's emotions in the design proposal, making it difficult to propose optimal designs that matched the user's psychological state and preferences. Furthermore, there was a lack of a way to visually confirm how the generated design proposal would be applied to the actual space, making it difficult to increase user satisfaction.

[0359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0360] In this invention, the server includes means for receiving user input, means for analyzing the received user input and emotional data, means for generating multiple design proposals based on the analysis results and the user's emotional data, means for evaluating and optimizing the generated design proposals, and means for displaying the optimized design proposals on the user terminal using augmented reality technology. This makes it possible to generate design proposals that reflect the user's emotions and also makes it easy to visually confirm them in real space, thereby improving user satisfaction.

[0361] "User input" refers to information such as text, sketches, or images provided by a user to the system.

[0362] "Emotional data" refers to information about the psychological state analyzed based on voice and facial expressions obtained from the user.

[0363] "Natural language processing" refers to the technology that allows computers to understand and analyze natural human language.

[0364] "Computer vision algorithms" refer to algorithms used to analyze and understand visual data such as images and videos.

[0365] "Augmented reality technology" refers to technology that overlays digital information onto the real world.

[0366] "Design Proposal" refers to a design proposal generated based on user input and emotional data.

[0367] "User terminal" refers to a device operated by a user, such as a smartphone or head-mounted display.

[0368] Overall system configuration

[0369] The system is comprised of three main components: a server, a user device, and the user. The server acts as a central control unit, responsible for complex data analysis and generative AI model execution. The user device is a device used by the user to provide input and receive design proposals, and can include a smartphone or head-mounted display. Furthermore, it incorporates an emotion engine, capable of recognizing and analyzing user emotions.

[0370] Hardware and software used

[0371] Hardware: Smartphone, head-mounted display, camera, microphone

[0372] Software: Natural Language Processing (NLP) algorithms, computer vision algorithms, generative AI models, emotion recognition engines, and augmented reality (AR) display software

[0373] Program processing

[0374] The server receives user input and analyzes it using the emotion engine. The received user input includes text, sketches, and images, and is analyzed using natural language processing and computer vision technologies. The emotion engine also analyzes and recognizes emotional data from the user's voice and facial expressions. This input data and emotional data are integrated and multiple design proposals are generated using a generative AI model.

[0375] The generated design proposals are evaluated on the server, and the proposal that best suits the user's requirements and emotions is selected. Emotional data is also taken into account in the evaluation criteria, and the design proposal that best matches the user's emotions is optimized. The optimized design proposal is displayed on the user's device using augmented reality technology, allowing the user to view and evaluate it.

[0376] Specific examples

[0377] For example, here's how the system works if a brick-and-mortar cafe owner wants a new interior design.

[0378] 1. Providing user input:

[0379] A cafe owner launches the smartphone app and uploads text information such as "I want a natural cafe atmosphere," along with hand-drawn sketches and images of examples of cafe interiors with plenty of greenery. The emotion engine then recognizes that the cafe owner is relaxed.

[0380] 2. Data Analysis:

[0381] The server uses NLP to extract keywords such as "nature," "cafe," and "relaxation" from the text information, and analyzes the shape of the sketch and the color scheme of the image using computer vision technology.

[0382] 3. Emotional Data Analysis:

[0383] Emotional data is derived using a camera and microphone to identify the user's sense of relaxation.

[0384] 4. Design generation and evaluation:

[0385] The generative AI model generates multiple design proposals based on this data, and the server selects and optimizes the most suitable design proposal, taking into account emotional data. For example, it generates a design for a nature-themed cafe interior using calming colors such as green and blue.

[0386] 5. Submit design proposal:

[0387] Using augmented reality technology, the optimized design proposals are displayed to the user in real time through a head-mounted display, allowing the owner to see what the proposed design will look like while walking through the store.

[0388] Prompt Sentence Examples

[0389] "Please propose a new layout that evokes a natural cafe atmosphere in a chalk art style. Users will feel relaxed."

[0390] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0391] Step 1:

[0392] Providing User Input

[0393] Users access the system using a smartphone or head-mounted display to upload text, sketches, and images, while the emotion engine reads the user's voice and facial expressions through a camera and microphone to collect emotional data.

[0394] Input: Text (e.g., a natural cafe atmosphere is desired), sketch image, interior image, emotional data (voice, facial expression)

[0395] Output: User input and emotion data sent to the server

[0396] Step 2:

[0397] Data analysis

[0398] The server analyzes the received user input, using natural language processing (NLP) techniques to extract keywords from the text and computer vision algorithms to extract features from sketches and images.

[0399] Input: Text received from the user, sketch image, interior image

[0400] Output: Text analysis results (keywords), image analysis results (shape and color features)

[0401] Step 3:

[0402] Emotional Data Analysis

[0403] The emotion engine analyzes the user's voice and facial expressions to identify the user's emotions, for example, determining that the user is relaxed.

[0404] Input: User's voice data, facial expression data

[0405] Output: User's emotional state (e.g., relaxed)

[0406] Step 4:

[0407] Generate design ideas

[0408] The server uses a generative AI model to generate multiple design proposals based on the analysis results and user emotion data. The system generates designs based on design prompts that reflect the user's emotions and keywords.

[0409] Input: Text analysis results (keywords), image analysis results (shape and color features), emotional state (relaxed)

[0410] Output: Multiple design ideas

[0411] Step 5:

[0412] Evaluating and optimizing design alternatives

[0413] The server evaluates the generated design proposals and selects the one that best suits the user's emotions and requests. Since the evaluation criteria also include emotional data, design proposals that match the user's emotions are highly rated. The optimal design proposal is selected and fine-tuned.

[0414] Input: Multiple design options, user emotional state

[0415] Output: Optimized design proposal

[0416] Step 6:

[0417] Displaying design ideas

[0418] The optimized design proposals are displayed on the user's device using augmented reality technology, allowing the user to view the proposed design in real time via a head-mounted display or smartphone.

[0419] Input: Optimized design proposal

[0420] Output: Design proposal displayed using augmented reality technology

[0421] 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.

[0422] 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.

[0423] 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.

[0424] [Second embodiment]

[0425] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0436] 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."

[0437] This invention is a system in which generative AI generates innovative design concepts based on initial ideas and instructions provided by users. Below, we explain the program processing of this system in natural language and provide concrete examples.

[0438] System configuration

[0439] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit and performs complex data analysis and runs generative AI models. The terminal is a user-operated device that sends user input and receives design proposals.

[0440] Program processing

[0441] 1. The server receives user input

[0442] Users upload and send input data such as text, sketches, and images from their devices, and the server receives and stores the data in the required format.

[0443] 2. Data Analysis

[0444] The server analyzes the received data, using natural language processing (NLP) techniques for text data and computer vision algorithms for sketches and images, to extract important features and keywords from the user's input.

[0445] 3. Generate design proposals

[0446] Based on the analysis results, the server uses a generative AI model to generate multiple design proposals, each of which includes unique elements tailored to the user's requirements.

[0447] 4. Evaluate and optimize design ideas

[0448] The server evaluates the generated design proposals to see how well they meet user expectations, and then optimizes and fine-tunes the design proposals based on the evaluation results.

[0449] 5. Providing design proposals

[0450] The server then sends the optimized design proposals to the device for the user to review, and the user can review these design proposals and, if necessary, send feedback or correction requests to the server.

[0451] Specific examples

[0452] For example, if a user needs a packaging design for a new product, the system works like this:

[0453] 1. Providing User Input

[0454] Users upload text such as "I want a simple packaging design with a nature theme," along with a sketch of a plant and an image of a specific color scheme from their device to the server.

[0455] 2. Data Analysis

[0456] The server uses NLP to extract keywords such as "nature," "simple," and "packaging design" from this text, and then uses computer vision to extract plant shapes from sketches and color schemes from images.

[0457] 3. Generate design proposals

[0458] Based on the extracted features, the server uses a generative AI model to generate multiple package design ideas, each of which reflects the image of plants and simplicity.

[0459] 4. Evaluate and optimize design ideas

[0460] The server evaluates each design proposal, selects the one that best meets the user's requirements, and then makes further adjustments, such as adjusting the color and layout.

[0461] 5. Providing design proposals

[0462] The server sends the optimized design to the device and provides it to the user, and if the user is not satisfied, further revisions are made through feedback.

[0463] This series of processes allows users to quickly and efficiently obtain high-quality design proposals, supporting users' creativity and significantly improving the efficiency of their design work.

[0464] The processing flow will be explained below.

[0465] Step 1:

[0466] The user uses the device to input initial design ideas and instructions, specifically uploading text, sketches, images, etc., and then clicks a send button to send the data to the server.

[0467] Step 2:

[0468] The server receives the data sent by the user. After receiving it, the server validates the data format and ensures that all required data is present. For example, it checks that text is sent correctly and that sketches and images are in the supported formats (JPEG, PNG, etc.).

[0469] Step 3:

[0470] The server analyzes the received text data using natural language processing (NLP) technology, which extracts keywords such as "simple," "modern," and "logo."

[0471] Step 4:

[0472] The server analyzes the received sketches and images using computer vision technology, specifically recognizing the shape of the sketch and extracting features such as the color and pattern of the image.

[0473] Step 5:

[0474] The server then formats the analysis results as input data for generating multiple design proposals, and creates design prompts by integrating the text analysis results with the features of sketches and images.

[0475] Step 6:

[0476] The server uses a generative AI model to generate design proposals. During the generation process, multiple different design proposals are generated based on the interpreted user requirements, such as a simple and modern logo.

[0477] Step 7:

[0478] The server evaluates the generated design proposals and scores them based on the evaluation criteria to determine which design proposal best meets the user's requirements.

[0479] Step 8:

[0480] The server then optimizes the design proposals with the highest scores based on the evaluation results, which includes adjusting color tones and optimizing the layout.

[0481] Step 9:

[0482] The server then formats the optimized design into its final form, and the resulting design, formatted as a high-resolution image, is sent to the user's device.

[0483] Step 10:

[0484] The user can check the design proposal sent to them on their device. They can then enter feedback or corrections they would like to make and send it back to the server. The server will receive this and make any necessary corrections.

[0485] These steps allow users to quickly receive specific, high-quality ideas for the design they want.

[0486] Example 1

[0487] 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."

[0488] In the modern design process, it is difficult and time-consuming to quickly generate high-quality design proposals based on the user's initial ideas and instructions. In particular, there is a need to respond to various user input formats, analyze and evaluate them, and provide optimal design proposals. Furthermore, an efficient method is needed to properly evaluate how well the generated design proposals meet the user's expectations and to further optimize them.

[0489] 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.

[0490] In this invention, the server includes means for receiving user input, means for saving the received user input in a database, means for analyzing the saved user input, means for generating multiple design proposals using a generative AI model based on the analysis results, means for evaluating and optimizing the generated design proposals, and means for providing the optimized design proposals to a user terminal, thereby enabling efficient processing of various user inputs and rapid generation of high-quality design proposals.

[0491] "User input" means instructions or initial data such as text, sketches, or images provided by a user to the system.

[0492] "Database" means a digital storage system for storing received user-entered data and making it available for reference in subsequent analysis or generation processes.

[0493] "Analysis" is the process of processing received and stored user-entered data and extracting important features or keywords.

[0494] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to generate new design ideas based on user input.

[0495] "Design Proposals" are multiple design and layout proposals created by a generative AI model.

[0496] The "evaluation method" is the process of determining how well the generated design proposal meets the user's requirements.

[0497] "Optimization" is the process of adjusting elements of a design proposal based on the evaluation results to create a form that best meets user expectations.

[0498] "User terminal" means a device through which a user accesses the system, sends input data, and receives generated design proposals.

[0499] This invention relates to a system that generates multiple design proposals using a generative AI model based on user input, optimizes them, and provides them to the user. Specific embodiments of the invention are described below.

[0500] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit and executes analysis and generative AI models. The terminal is a device operated by the user, used to send input data and receive design proposals. The user provides initial ideas and specific instructions.

[0501] Hardware and software used

[0502] For server hardware, a server machine equipped with a regular processor and memory is used. For example, an EC2 instance from Amazon Web Services (AWS) can be used. For data storage, a cloud storage service such as Amazon S3 is used. For software to run the generative AI model, a machine learning framework such as TensorFlow or PyTorch is used. For natural language processing (NLP), SpaCy or NLTK is used, and for computer vision, OpenCV or TensorFlow is used.

[0503] The devices used may be personal computers, smartphones, tablets, etc. These devices require an internet connection and communicate with the server via a browser or dedicated application.

[0504] Specific Examples

[0505] 1. Providing User Input

[0506] Users access the system using their own devices. For example, they can provide the text "I want a simple package design with a nature theme," as well as sketches of plants and images with specific color schemes. An example of a prompt sentence could be, "I need a package with a natural and simple design. Please refer to the images and sketches below."

[0507] 2. Data storage and analysis

[0508] The server receives input data sent by users and stores it in a database. The saved text data is then analyzed using natural language processing (NLP) techniques to extract keywords such as "nature," "simple," and "packaging design." For sketches and images, computer vision algorithms are used to identify the shape and color of plants.

[0509] 3. Generate design proposals

[0510] The server generates a specific prompt based on the analysis results and inputs it into the generative AI model. For example, this prompt might be in the form of, "Please generate a package design with the themes of 'nature' and 'simplicity' based on the image and sketch below." The generative AI model then generates multiple design proposals based on this prompt.

[0511] 4. Evaluation and Optimization

[0512] The server evaluates the generated design proposals and selects the one that best meets the user's requirements. Furthermore, it optimizes the design proposals by fine-tuning the color and layout based on the evaluation results. This evaluation can be performed using heuristic evaluation or machine learning algorithms.

[0513] 5. Providing design ideas and feedback

[0514] The server then sends the optimized design proposal to the user's device for review. The user reviews the proposal and provides feedback or corrections as needed. The server then adjusts the design proposal based on this feedback, and the process is repeated until the final design is completed.

[0515] This series of processes allows users to quickly and efficiently obtain high-quality design proposals. The present invention is expected to support users' creativity and significantly improve the efficiency of design work.

[0516] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0517] Step 1:

[0518] The user sends initial input data from their device to the server. The user uses a personal computer or smartphone to input text, sketches, images, etc. into the system. The input includes the text "I want a simple packaging design with a nature theme," a sketch of a plant, and an image of a specific color scheme. This data is sent to the server via a form or file upload function.

[0519] Input: User text, sketches, and images

[0520] Output: User-entered data sent to the server

[0521] Step 2:

[0522] The server saves the input data received from the user to a database. The specific saving operation uses a cloud storage service (e.g., Amazon S3), and the data is managed in an appropriate folder structure for each user.

[0523] Input: User-entered data sent to the server

[0524] Output: User-entered data stored in a database

[0525] Step 3:

[0526] The server analyzes the stored user-entered data. For text data, natural language processing (NLP) techniques are used to extract keywords such as "nature," "simple," and "packaging design." For sketches and images, computer vision algorithms are used to identify the shape and color of plants and extract their features.

[0527] Input: User-entered data stored in a database

[0528] Output: Extracted features and keywords

[0529] Step 4:

[0530] The server generates a specific prompt based on the analysis results. The generated prompt is input into a generative AI model, which generates multiple design proposals. An example of a prompt is, "Please generate a package design with the themes of 'nature' and 'simplicity' based on the image and sketch below."

[0531] Input: extracted features and keywords

[0532] Output: Generated prompts and design proposals

[0533] Step 5:

[0534] The server evaluates and optimizes the generated design proposals. Using an evaluation algorithm, it determines how well the generated design proposals meet the user's requirements. Based on the evaluation results, the design proposals are optimized by fine-tuning their color and layout.

[0535] Input: Generated design proposal

[0536] Output: Evaluation results and optimized design proposals

[0537] Step 6:

[0538] The server sends the optimized design proposal to the user's device, using the HTTP protocol and WebSocket for communication, allowing the design proposal to be viewed in the user interface.

[0539] Input: Optimized design proposal

[0540] Output: Optimized design proposal sent to user device

[0541] Step 7:

[0542] The user checks the submitted design proposal on their device and sends feedback to the server. If necessary, they can submit correction requests, and the server will then adjust the design proposal accordingly.

[0543] Input: User feedback

[0544] Output: Final, refined design proposal

[0545] This series of processes allows users to obtain high-quality design proposals quickly and efficiently.

[0546] (Application example 1)

[0547] 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."

[0548] In modern design generation, users are expected to quickly obtain high-quality design proposals simply by providing their ideas and instructions. However, conventional systems cannot accurately reflect the user's intentions, and as a result, the generated designs often do not meet the user's expectations. Furthermore, there is no process for reflecting user feedback and re-optimizing the design, making it difficult to efficiently improve design quality.

[0549] 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.

[0550] In this invention, the server includes means for receiving user input, means for analyzing the received user input, means for generating multiple design proposals based on the analysis results, means for evaluating and optimizing the generated design proposals, means for providing the optimized design proposals to the user terminal, and means for re-optimizing the design proposals based on the evaluation results and reflecting user feedback. This makes it possible to quickly provide design proposals that more accurately reflect the user's intentions, and further to improve the quality of the design by reflecting user feedback.

[0551] "Means for receiving user input" refers to devices or software that allow a user to send data, such as text, sketches, or images, to the system and receive it.

[0552] "Means for analyzing received user input" means equipment or software that includes algorithms or techniques for analyzing received text, sketches, images, etc., and extracting key features or keywords.

[0553] "Means for generating multiple design proposals based on analysis results" refers to equipment or software that has the function of automatically generating multiple design proposals using a generative AI model based on analyzed data.

[0554] "Means for evaluating and optimizing the generated design proposals" refers to algorithms or software that evaluate the generated design proposals, check how well they meet the user requirements, and make any necessary optimizations.

[0555] "Means for providing optimized design proposals to a user device" refers to equipment or software that has the function of transmitting optimized design proposals to a user device so that the user can review them.

[0556] "Means of re-optimizing design proposals by reflecting user feedback based on evaluation results" refers to algorithms or software that have the function of re-evaluating and optimizing design proposals based on user feedback.

[0557] This invention is a system in which a user inputs initial ideas and instructions, and a generative AI model generates innovative design concepts based on those ideas.

[0558] System configuration

[0559] The system mainly consists of a server, terminals, and users. The server acts as a central control unit and performs complex data analysis and executes generative AI models. The terminals are devices operated by users and are used to send user input and receive design proposals. Users access the system using terminals such as smartphones and tablets.

[0560] Program processing

[0561] The server performs the following steps:

[0562] 1. Receiving user input: The user uploads data such as text, sketches, and images from their device and sends it to the server, which receives the data and stores it in an appropriate format.

[0563] 2. Data Analysis: The server analyzes the received data, using natural language processing (NLP) techniques for text data and computer vision algorithms for sketches and images, to extract important features and keywords from the user's input.

[0564] 3. Design proposal generation: Based on the analysis results, the server uses a generative AI model to generate multiple design proposals, each of which contains unique elements that meet the user's requirements.

[0565] 4. Evaluate and optimize the design: The server evaluates the generated design to see how well it meets the user's expectations. Based on the evaluation results, it optimizes and fine-tunes the design.

[0566] 5. Providing design proposals: The server sends the optimized design proposals to the device for the user to review. The user reviews these design proposals and provides feedback if necessary.

[0567] 6. Reflecting feedback and re-optimizing: Based on user feedback, the server re-evaluates the design proposal and reflects the feedback to optimize the design proposal.

[0568] Hardware and software used

[0569] Hardware: Smartphones, tablets, servers (cloud-based)

[0570] Software: Python programs, OpenAI API, natural language processing (NLP) techniques, computer vision algorithms

[0571] Specific examples

[0572] For example, if a user needs a packaging design for a new product, the system works as follows:

[0573] 1. Providing user input: The user uploads the text "I want a simple packaging design with a nature theme," along with a sketch of a plant and an image of a specific color scheme, from their device to the server.

[0574] 2. Data analysis: The server uses NLP to extract keywords such as "nature," "simple," and "packaging design" from the text, and uses computer vision to extract plant shapes from sketches and color schemes from images.

[0575] 3. Design proposal generation: Based on the extracted features, the server uses a generative AI model to generate multiple package design proposals, each of which reflects the image of plants and simplicity.

[0576] 4. Evaluating and optimizing design ideas: The server evaluates each design idea, selects the one that best meets the user's requirements, and then performs further fine-tuning, such as adjusting the color and layout.

[0577] 5. Providing design proposals: The server sends the optimized design proposals to the terminal and provides them to the user. If the user is not satisfied, further revisions will be made through feedback.

[0578] 6. Reflecting feedback and re-optimizing: If a user provides feedback such as "Use a brighter green," the server will re-evaluate and optimize the design based on that feedback and serve it again.

[0579] Prompt Sentence Examples

[0580] Text: I want a simple package design with a nature theme.

[0581] Sketch Features: Simple sketches of trees, leaves, and flowers

[0582] Color characteristics: Bright green and pale blue tones

[0583] Based on these prompts, the system generates design proposals using the OpenAI API, and after receiving user feedback, the system re-optimizes the design and delivers it to the user.

[0584] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0585] Step 1:

[0586] The server receives user input. The user uses a terminal to upload text such as "I want a simple package design with a nature theme," a sketch of a plant, and an image of a specific color scheme. The server receives this input data and saves it as text data, sketch image data, and color scheme image data.

[0587] Step 2:

[0588] The server analyzes the received user input. It uses natural language processing (NLP) technology on the text data to extract keywords such as "nature," "simple," and "package design." It uses computer vision algorithms on the sketch image data to extract the shape and characteristics of plants. It also uses computer vision algorithms on the color scheme image data to extract color scheme information such as bright green and light blue. This allows the user's intention to be extracted as specific features and keywords.

[0589] Step 3:

[0590] The server generates multiple design proposals based on the analysis results. Using the analyzed text keywords, sketch features, and color scheme information, it creates prompts for the generative AI model, which then generates design proposals based on those prompts. The generated design proposals include original elements that are in line with the input data. For example, they include elements such as a "simple design with a nature theme," "reflecting the shape of a specific plant," and "using a bright green and light blue color scheme."

[0591] Step 4:

[0592] The server evaluates the generated design proposals. The design proposals output by the generative AI model are analyzed using an evaluation algorithm to check how well they match the user's instructions and input data. The evaluation checks the degree of agreement of keywords, shapes, and color schemes. Based on the evaluation results, if further optimization is required, fine-tuning of colors and layout is performed.

[0593] Step 5:

[0594] The server provides the optimized design proposal to the user's device. The generated and optimized design proposal is sent to the user's device for the user to review. The user reviews the proposed design proposal, and if they are not satisfied, they send feedback from their device to the server.

[0595] Step 6:

[0596] The server receives feedback from the user and re-optimizes the design proposal based on that feedback. It analyzes the feedback provided by the user (e.g., "Please use a brighter green") and uses the generative AI model and optimization algorithm to re-generate and optimize the design proposal. It then provides the re-generated and optimized design proposal to the user again and confirms that the design proposal has been improved based on the feedback.

[0597] 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.

[0598] This invention is a system in which generative AI generates innovative design concepts based on initial ideas and instructions provided by the user. This system is combined with an emotion engine that recognizes the user's emotions, and is able to propose design proposals that reflect the user's emotions. Below, we will explain the program processing of this system in natural language, and provide concrete examples.

[0599] System configuration

[0600] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit, performing complex data analysis and running generative AI models. The terminal is a device operated by the user, used to send user input and receive design proposals. In addition, it is equipped with an emotion engine, which has the built-in ability to recognize and analyze user emotions.

[0601] Program processing

[0602] 1. The server receives user input

[0603] Users upload text, sketches, images, and even emotional data from their devices, and the server receives and stores the data in the required format.

[0604] 2. Data Analysis

[0605] The server analyzes the received text data using natural language processing (NLP) technology to extract keywords such as "simple," "modern," and "logo" from the text, and also analyzes sketches and images using computer vision technology to extract features.

[0606] 3. Emotion Data Analysis

[0607] The emotion engine analyzes the user's emotional data, which includes emotional information derived from the user's voice and facial expressions. The emotion engine identifies emotions such as "happy," "excited," and "calm."

[0608] 4. Generate design proposals

[0609] Based on the analysis results, the server uses a generative AI model to generate multiple design proposals. Emotional data obtained from the emotion engine is also reflected in the design prompts. For example, if the user feels "calm," color schemes and design elements that reflect that emotion will be suggested.

[0610] 5. Evaluate and optimize design ideas

[0611] The server evaluates the generated design proposals and selects the one that best matches the user's needs and emotions. The evaluation criteria also take into account emotional data, and the design proposal that best matches the user's emotions is scored. The server then optimizes the design proposals and adjusts the details based on the evaluation results.

[0612] 6. Providing design proposals

[0613] The server sends the optimized design proposal to the device, where the user can review it and send feedback or correction requests to the server if necessary. The server receives the feedback and makes corrections.

[0614] Specific examples

[0615] For example, if a user needs a logo for a new cafe, the system works like this:

[0616] 1. Providing User Input

[0617] The user uploads the text "I want a nature-themed relaxing logo," along with a simple sketch and a specific color scheme image, to the server from their device, and the emotion engine recognizes that the user is relaxed.

[0618] 2. Data Analysis

[0619] The server uses NLP to extract keywords such as "nature," "relax," and "logo" from the text, and then uses computer vision to analyze the shape of the sketch and the color scheme of the image.

[0620] 3. Emotion Data Analysis

[0621] The emotion engine analyzes the user's emotions and identifies that "relaxation" is the main emotion.

[0622] 4. Generate design proposals

[0623] The server uses a generative AI model to generate multiple logo designs based on these analysis results and emotional data, such as a nature-themed logo using muted shades of green and blue.

[0624] 5. Evaluate and optimize design ideas

[0625] The server evaluates each logo design, selects the one that best matches the user's needs and emotions, and then fine-tunes it, adjusting the color and shape, for example, to create the optimal design.

[0626] 6. Providing design proposals

[0627] The server sends the optimized logo design to the device and provides it to the user, and if the user is not satisfied, further revisions are made through feedback.

[0628] In this way, users can quickly obtain high-quality design proposals that reflect their own emotions, improving the quality and fit of their designs, supporting creativity and streamlining work.

[0629] The processing flow will be explained below.

[0630] Step 1:

[0631] Users use their device to input their initial design ideas and instructions, including uploading text, sketches, and images, providing emotional data, and then clicking a send button to send this data to the server.

[0632] Step 2:

[0633] The server receives the text data, sketches, images, and emotion data sent by the user. After receiving the data, the server verifies the format of each data and ensures that all required data is present. For example, it verifies that the text is sent correctly and that the sketches and images are in the supported formats (JPEG, PNG, etc.).

[0634] Step 3:

[0635] The server analyzes the received text data using natural language processing (NLP) technology, specifically extracting keywords such as "simple," "modern," and "logo" from the text.

[0636] Step 4:

[0637] The server analyzes the received sketches and images using computer vision technology, specifically recognizing the shape of the sketch and extracting features such as the color and pattern of the image.

[0638] Step 5:

[0639] The emotion engine analyzes the emotional data provided by the user, specifically identifying emotions such as "satisfied," "excited," or "calm" based on information gleaned from the user's voice and facial expressions.

[0640] Step 6:

[0641] The server then formats the analysis results as input data for generating multiple design proposals. It creates design prompts by integrating the text analysis results, features of sketches and images, and emotion data.

[0642] Step 7:

[0643] The server uses a generative AI model to generate design proposals. The generation process takes into account the interpreted user request as well as emotional data. For example, if the user is feeling "relaxed," the server will suggest color schemes and design elements that reflect that emotion.

[0644] Step 8:

[0645] The server evaluates the generated design proposals and scores them based on the evaluation criteria to determine which design proposal best suits the user's needs and emotions. Emotional data is also taken into account as an evaluation criterion.

[0646] Step 9:

[0647] The server then optimizes the design proposals with the highest scores based on the evaluation results, which includes adjusting color tones and optimizing the layout.

[0648] Step 10:

[0649] The server then formats the optimized design into its final form, and the resulting design, formatted as a high-resolution image, is sent to the user's device.

[0650] Step 11:

[0651] The user can check the design proposal sent to them on their device. They can then enter feedback or corrections they would like to make and send it back to the server. The server will receive this and make any necessary corrections.

[0652] These steps allow users to quickly receive high-quality design proposals that reflect their emotions, improving the quality and fit of the design, supporting creativity and streamlining work.

[0653] Example 2

[0654] 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."

[0655] Conventional design generation systems lacked a means to provide design proposals that reflected the user's emotions, making it difficult to increase user satisfaction. Furthermore, there was a lack of a system that could accurately analyze the user's needs and emotions and quickly generate and provide optimal design proposals in response. This meant that users could not obtain designs that accurately reflected their requirements, and the process of providing feedback and making corrections was time-consuming.

[0656] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0657] In this invention, the server includes means for receiving user input, means for analyzing the received user input, means for recognizing and analyzing user emotion data, means for generating multiple design proposals based on the analysis results and the emotion data, means for evaluating and optimizing the generated design proposals, and means for providing the optimized design proposals to the user terminal, thereby enabling the rapid provision of high-quality design proposals that reflect the user's emotions.

[0658] "User Input" means text, sketches, images, and other information provided by a user.

[0659] "Means for receiving" refers to the functionality by which the server receives user input.

[0660] "Means of analysis" refers to technology for analyzing the content of user input and extracting keywords and features.

[0661] "Emotional data" refers to emotional information recognized and analyzed from the user's voice, facial expressions, etc.

[0662] "Means for recognizing and analyzing emotional data" refers to the ability to identify a user's emotions using an emotion engine.

[0663] "Design Proposals" refers to multiple design proposals generated based on the analysis results and emotion data.

[0664] "Means for generating" refers to the functionality for generating multiple design alternatives using a generative AI model.

[0665] "Means for evaluation and optimization" refers to the function of evaluating the generated design proposals, selecting the proposal that best suits the user's requirements and emotions, and fine-tuning it.

[0666] "Means of providing" refers to the function for sending optimized design proposals to the user's terminal.

[0667] "User Terminal" means the electronic device used by a User to submit input and receive design suggestions.

[0668] "Natural language processing" refers to the technology of analyzing a user's text input and extracting keywords and meaning.

[0669] "Computer vision algorithms" refers to techniques for analyzing the features of sketches and images.

[0670] "Generative AI model" refers to an artificial intelligence model that generates design ideas based on user input and emotional data.

[0671] A "prompt" refers to an instruction that a generative AI model uses to generate design proposals.

[0672] Program Generation and Explanation

[0673] The system of this invention is designed to generate innovative design concepts based on user input. The system incorporates an emotion engine that recognizes the user's emotions and can propose design proposals that reflect the user's emotional state.

[0674] Hardware and software used

[0675] The system mainly uses the following hardware and software:

[0676] Server: Responsible for receiving data, analyzing it, and running generative AI models. Specifically, it utilizes AWS computing resources.

[0677] Device: The user sends input data and receives the generated design proposals. A standard computer or smartphone is used.

[0678] Natural Language Processing (NLP) techniques: Use TensorFlow to parse text input.

[0679] Computer Vision Techniques: Use OpenCV to analyze sketches and images.

[0680] Emotion Engine: Uses Google Cloud AutoML to analyze the user's voice and facial expressions.

[0681] Generative AI model: We use OpenAI's GPT-3 to generate design ideas.

[0682] Evaluation and optimization: We use scikit-learn and Photoshop APIs to evaluate and optimize the generated design solutions.

[0683] Data processing and calculation

[0684] 1. Receiving User Input

[0685] Users upload text, sketches, images, and emotional data, including voice and facial expressions, from their devices to the server.

[0686] 2. Data storage

[0687] The server stores the received data in AWS S3 or RDS.

[0688] 3. Data Analysis

[0689] The server uses NLP technology (TensorFlow) to analyze text and extract keywords, and computer vision technology (OpenCV) to extract features from sketches and images.

[0690] 4. Emotion Data Analysis

[0691] The emotion engine (Google Cloud AutoML) analyzes user emotion data and recognizes specific emotional states.

[0692] 5. Generate design proposals

[0693] Based on the above analysis results, the server generates multiple design proposals using a generative AI model (OpenAI's GPT-3).

[0694] 6. Evaluate and optimize design ideas

[0695] The server evaluates the generated design proposals, performs scoring using scikit-learn, and then optimizes the proposals using the Photoshop API.

[0696] 7. Providing design proposals

[0697] The optimized design is sent to the user's device, where the user can review it and provide feedback if necessary.

[0698] Examples of specific examples and prompts

[0699] For example, if a user needs a logo for a new cafe, the system might do the following:

[0700] 1. Providing User Input

[0701] Users upload text such as "I want a nature-themed, relaxing logo," a simple sketch, and a specific color scheme image from their device to the server, and the emotion engine recognizes that the user is relaxing.

[0702] 2. Data Analysis

[0703] The server extracts keywords such as "nature," "relaxation," and "logo" from the text and analyzes sketches and color scheme images.

[0704] 3. Emotion Data Analysis

[0705] The emotion engine identifies the user's emotion as "relaxed."

[0706] 4. Generate design proposals

[0707] Based on the analysis results and emotion data, the server uses a generative AI model to generate multiple logo designs, such as a nature-themed logo using muted shades of green and blue.

[0708] 5. Evaluate and optimize design ideas

[0709] The server evaluates each logo design and selects the design that best matches the user's needs and emotions, then adjusts the color and shape.

[0710] 6. Providing design proposals

[0711] The server sends the optimized logo design to the device.

[0712] Prompt Sentence Examples

[0713] "I'd like to create a new logo for my cafe. I'd like the theme to be nature-themed and relaxing. I'd like it to have a green and blue color scheme as the base."

[0714] This system allows users to quickly obtain high-quality design proposals that reflect their own emotions.

[0715] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0716] Step 1: Providing User Input

[0717] ----

[0718] The user uses the device to provide text, sketches, images, and emotion data to the server. For example, the user can type, "I want a nature-themed relaxing logo," and upload related sketches and color scheme images. The emotion engine then recognizes that the user is relaxed based on their voice and facial expression.

[0719] Input: Text (e.g., "Relaxing nature-themed logos"), sketches, images, audio, facial expressions

[0720] Output: Data provided to the server

[0721] Step 2: Receiving and storing data

[0722] ----

[0723] The server receives input data sent by the user, saves images and sketches to AWS S3, and saves text data to RDS.

[0724] Input: User-submitted text, sketches, images, voice, and facial expressions

[0725] Output: User input information stored in a database

[0726] Step 3: Analyzing the text data

[0727] ----

[0728] The server uses NLP (Natural Language Processing) technology to analyze the text data with TensorFlow and extract keywords, such as "nature," "relax," and "logo."

[0729] Input: Saved text data

[0730] Output: Extracted keywords (e.g., "nature," "relax," "logo")

[0731] Step 4: Analyzing the image data

[0732] ----

[0733] The server uses computer vision technology to analyze the shape and features of sketches and images using OpenCV, specifically analyzing hue, brightness, shape, etc.

[0734] Input: Saved sketches and image data

[0735] Output: Analyzed image feature information (shape, color, etc.)

[0736] Step 5: Analyze the sentiment data

[0737] ----

[0738] The emotion engine uses Google Cloud AutoML to analyze emotions from the user's voice and facial expressions and identify specific emotional states such as "relaxed."

[0739] Input: Stored voice data and facial expression data

[0740] Output: Analyzed emotion information (e.g., "Relaxed")

[0741] Step 6: Generate design ideas

[0742] ----

[0743] Based on the analysis results and emotion data, the server uses a generative AI model (OpenAI's GPT-3) to generate multiple design proposals. For example, it proposes a logo design based on green and blue tones based on the relaxed emotion.

[0744] Input: extracted keywords, analyzed image feature information, analyzed emotion information

[0745] Output: Multiple design proposals generated

[0746] Step 7: Evaluate and optimize design alternatives

[0747] ----

[0748] The server evaluates the generated design proposals, scores them using scikit-learn, and selects the one that best suits the user's needs and emotions. It then optimizes the design proposals by adjusting color, shape, etc. using the Photoshop API.

[0749] Input: Multiple generated design ideas

[0750] Output: Optimized design proposal

[0751] Step 8: Submit a design proposal

[0752] ----

[0753] The server sends the optimized design proposal to the user's device. The user checks the design proposal on the device and sends feedback to the server if necessary. The server then makes further revisions based on this feedback.

[0754] Input: Optimized design proposal

[0755] Output: Design proposals provided to users, and suggested revisions based on their feedback

[0756] (Application example 2)

[0757] 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."

[0758] Conventional design generation systems were unable to reflect the user's emotions in the design proposal, making it difficult to propose optimal designs that matched the user's psychological state and preferences. Furthermore, there was a lack of a way to visually confirm how the generated design proposal would be applied to the actual space, making it difficult to increase user satisfaction.

[0759] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0760] In this invention, the server includes means for receiving user input, means for analyzing the received user input and emotional data, means for generating multiple design proposals based on the analysis results and the user's emotional data, means for evaluating and optimizing the generated design proposals, and means for displaying the optimized design proposals on the user terminal using augmented reality technology. This makes it possible to generate design proposals that reflect the user's emotions and also makes it easy to visually confirm them in real space, thereby improving user satisfaction.

[0761] "User input" refers to information such as text, sketches, or images provided by a user to the system.

[0762] "Emotional data" refers to information about the psychological state analyzed based on voice and facial expressions obtained from the user.

[0763] "Natural language processing" refers to the technology that allows computers to understand and analyze natural human language.

[0764] "Computer vision algorithms" refer to algorithms used to analyze and understand visual data such as images and videos.

[0765] "Augmented reality technology" refers to technology that overlays digital information onto the real world.

[0766] "Design Proposal" refers to a design proposal generated based on user input and emotional data.

[0767] "User terminal" refers to a device operated by a user, such as a smartphone or head-mounted display.

[0768] Overall system configuration

[0769] The system is comprised of three main components: a server, a user device, and the user. The server acts as a central control unit, responsible for complex data analysis and generative AI model execution. The user device is a device used by the user to provide input and receive design proposals, and can include a smartphone or head-mounted display. Furthermore, it incorporates an emotion engine, capable of recognizing and analyzing user emotions.

[0770] Hardware and software used

[0771] Hardware: Smartphone, head-mounted display, camera, microphone

[0772] Software: Natural Language Processing (NLP) algorithms, computer vision algorithms, generative AI models, emotion recognition engines, and augmented reality (AR) display software

[0773] Program processing

[0774] The server receives user input and analyzes it using the emotion engine. The received user input includes text, sketches, and images, and is analyzed using natural language processing and computer vision technologies. The emotion engine also analyzes and recognizes emotional data from the user's voice and facial expressions. This input data and emotional data are integrated and multiple design proposals are generated using a generative AI model.

[0775] The generated design proposals are evaluated on the server, and the proposal that best suits the user's requirements and emotions is selected. Emotional data is also taken into account in the evaluation criteria, and the design proposal that best matches the user's emotions is optimized. The optimized design proposal is displayed on the user's device using augmented reality technology, allowing the user to view and evaluate it.

[0776] Specific examples

[0777] For example, here's how the system works if a brick-and-mortar cafe owner wants a new interior design.

[0778] 1. Providing user input:

[0779] A cafe owner launches the smartphone app and uploads text information such as "I want a natural cafe atmosphere," along with hand-drawn sketches and images of examples of cafe interiors with plenty of greenery. The emotion engine then recognizes that the cafe owner is relaxed.

[0780] 2. Data Analysis:

[0781] The server uses NLP to extract keywords such as "nature," "cafe," and "relaxation" from the text information, and analyzes the shape of the sketch and the color scheme of the image using computer vision technology.

[0782] 3. Emotional Data Analysis:

[0783] Emotional data is derived using a camera and microphone to identify the user's sense of relaxation.

[0784] 4. Design generation and evaluation:

[0785] The generative AI model generates multiple design proposals based on this data, and the server selects and optimizes the most suitable design proposal, taking into account emotional data. For example, it generates a design for a nature-themed cafe interior using calming colors such as green and blue.

[0786] 5. Submit design proposal:

[0787] Using augmented reality technology, the optimized design proposals are displayed to the user in real time through a head-mounted display, allowing the owner to see what the proposed design will look like while walking through the store.

[0788] Prompt Sentence Examples

[0789] "Please propose a new layout that evokes a natural cafe atmosphere in a chalk art style. Users will feel relaxed."

[0790] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0791] Step 1:

[0792] Providing User Input

[0793] Users access the system using a smartphone or head-mounted display to upload text, sketches, and images, while the emotion engine reads the user's voice and facial expressions through a camera and microphone to collect emotional data.

[0794] Input: Text (e.g., a natural cafe atmosphere is desired), sketch image, interior image, emotional data (voice, facial expression)

[0795] Output: User input and emotion data sent to the server

[0796] Step 2:

[0797] Data analysis

[0798] The server analyzes the received user input, using natural language processing (NLP) techniques to extract keywords from the text and computer vision algorithms to extract features from sketches and images.

[0799] Input: Text received from the user, sketch image, interior image

[0800] Output: Text analysis results (keywords), image analysis results (shape and color features)

[0801] Step 3:

[0802] Emotional Data Analysis

[0803] The emotion engine analyzes the user's voice and facial expressions to identify the user's emotions, for example, determining that the user is relaxed.

[0804] Input: User's voice data, facial expression data

[0805] Output: User's emotional state (e.g., relaxed)

[0806] Step 4:

[0807] Generate design ideas

[0808] The server uses a generative AI model to generate multiple design proposals based on the analysis results and user emotion data. The system generates designs based on design prompts that reflect the user's emotions and keywords.

[0809] Input: Text analysis results (keywords), image analysis results (shape and color features), emotional state (relaxed)

[0810] Output: Multiple design ideas

[0811] Step 5:

[0812] Evaluating and optimizing design alternatives

[0813] The server evaluates the generated design proposals and selects the one that best suits the user's emotions and requests. Since the evaluation criteria also include emotional data, design proposals that match the user's emotions are highly rated. The optimal design proposal is selected and fine-tuned.

[0814] Input: Multiple design options, user emotional state

[0815] Output: Optimized design proposal

[0816] Step 6:

[0817] Displaying design ideas

[0818] The optimized design proposals are displayed on the user's device using augmented reality technology, allowing the user to view the proposed design in real time via a head-mounted display or smartphone.

[0819] Input: Optimized design proposal

[0820] Output: Design proposal displayed using augmented reality technology

[0821] 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.

[0822] 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.

[0823] 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.

[0824] [Third embodiment]

[0825] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0826] 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.

[0827] 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).

[0828] 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.

[0829] 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.

[0830] 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).

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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."

[0837] This invention is a system in which generative AI generates innovative design concepts based on initial ideas and instructions provided by users. Below, we explain the program processing of this system in natural language and provide concrete examples.

[0838] System configuration

[0839] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit and performs complex data analysis and runs generative AI models. The terminal is a user-operated device that sends user input and receives design proposals.

[0840] Program processing

[0841] 1. The server receives user input

[0842] Users upload and send input data such as text, sketches, and images from their devices, and the server receives and stores the data in the required format.

[0843] 2. Data Analysis

[0844] The server analyzes the received data, using natural language processing (NLP) techniques for text data and computer vision algorithms for sketches and images, to extract important features and keywords from the user's input.

[0845] 3. Generate design proposals

[0846] Based on the analysis results, the server uses a generative AI model to generate multiple design proposals, each of which includes unique elements tailored to the user's requirements.

[0847] 4. Evaluate and optimize design ideas

[0848] The server evaluates the generated design proposals to see how well they meet user expectations, and then optimizes and fine-tunes the design proposals based on the evaluation results.

[0849] 5. Providing design proposals

[0850] The server then sends the optimized design proposals to the device for the user to review, and the user can review these design proposals and, if necessary, send feedback or correction requests to the server.

[0851] Specific examples

[0852] For example, if a user needs a packaging design for a new product, the system works like this:

[0853] 1. Providing User Input

[0854] Users upload text such as "I want a simple packaging design with a nature theme," along with a sketch of a plant and an image of a specific color scheme from their device to the server.

[0855] 2. Data Analysis

[0856] The server uses NLP to extract keywords such as "nature," "simple," and "packaging design" from this text, and then uses computer vision to extract plant shapes from sketches and color schemes from images.

[0857] 3. Generate design proposals

[0858] Based on the extracted features, the server uses a generative AI model to generate multiple package design ideas, each of which reflects the image of plants and simplicity.

[0859] 4. Evaluate and optimize design ideas

[0860] The server evaluates each design proposal, selects the one that best meets the user's requirements, and then makes further adjustments, such as adjusting the color and layout.

[0861] 5. Providing design proposals

[0862] The server sends the optimized design to the device and provides it to the user, and if the user is not satisfied, further revisions are made through feedback.

[0863] This series of processes allows users to quickly and efficiently obtain high-quality design proposals, supporting users' creativity and significantly improving the efficiency of their design work.

[0864] The processing flow will be explained below.

[0865] Step 1:

[0866] The user uses the device to input initial design ideas and instructions, specifically uploading text, sketches, images, etc., and then clicks a send button to send the data to the server.

[0867] Step 2:

[0868] The server receives the data sent by the user. After receiving it, the server validates the data format and ensures that all required data is present. For example, it checks that text is sent correctly and that sketches and images are in the supported formats (JPEG, PNG, etc.).

[0869] Step 3:

[0870] The server analyzes the received text data using natural language processing (NLP) technology, which extracts keywords such as "simple," "modern," and "logo."

[0871] Step 4:

[0872] The server analyzes the received sketches and images using computer vision technology, specifically recognizing the shape of the sketch and extracting features such as the color and pattern of the image.

[0873] Step 5:

[0874] The server then formats the analysis results as input data for generating multiple design proposals, and creates design prompts by integrating the text analysis results with the features of sketches and images.

[0875] Step 6:

[0876] The server uses a generative AI model to generate design proposals. During the generation process, multiple different design proposals are generated based on the interpreted user requirements, such as a simple and modern logo.

[0877] Step 7:

[0878] The server evaluates the generated design proposals and scores them based on the evaluation criteria to determine which design proposal best meets the user's requirements.

[0879] Step 8:

[0880] The server then optimizes the design proposals with the highest scores based on the evaluation results, which includes adjusting color tones and optimizing the layout.

[0881] Step 9:

[0882] The server then formats the optimized design into its final form, and the resulting design, formatted as a high-resolution image, is sent to the user's device.

[0883] Step 10:

[0884] The user can check the design proposal sent to them on their device. They can then enter feedback or corrections they would like to make and send it back to the server. The server will receive this and make any necessary corrections.

[0885] These steps allow users to quickly receive specific, high-quality ideas for the design they want.

[0886] Example 1

[0887] 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."

[0888] In the modern design process, it is difficult and time-consuming to quickly generate high-quality design proposals based on the user's initial ideas and instructions. In particular, there is a need to respond to various user input formats, analyze and evaluate them, and provide optimal design proposals. Furthermore, an efficient method is needed to properly evaluate how well the generated design proposals meet the user's expectations and to further optimize them.

[0889] 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.

[0890] In this invention, the server includes means for receiving user input, means for saving the received user input in a database, means for analyzing the saved user input, means for generating multiple design proposals using a generative AI model based on the analysis results, means for evaluating and optimizing the generated design proposals, and means for providing the optimized design proposals to a user terminal, thereby enabling efficient processing of various user inputs and rapid generation of high-quality design proposals.

[0891] "User input" means instructions or initial data such as text, sketches, or images provided by a user to the system.

[0892] "Database" means a digital storage system for storing received user-entered data and making it available for reference in subsequent analysis or generation processes.

[0893] "Analysis" is the process of processing received and stored user-entered data and extracting important features or keywords.

[0894] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to generate new design ideas based on user input.

[0895] "Design Proposals" are multiple design and layout proposals created by a generative AI model.

[0896] The "evaluation method" is the process of determining how well the generated design proposal meets the user's requirements.

[0897] "Optimization" is the process of adjusting elements of a design proposal based on the evaluation results to create a form that best meets user expectations.

[0898] "User terminal" means a device through which a user accesses the system, sends input data, and receives generated design proposals.

[0899] This invention relates to a system that generates multiple design proposals using a generative AI model based on user input, optimizes them, and provides them to the user. Specific embodiments of the invention are described below.

[0900] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit and executes analysis and generative AI models. The terminal is a device operated by the user, used to send input data and receive design proposals. The user provides initial ideas and specific instructions.

[0901] Hardware and software used

[0902] For server hardware, a server machine equipped with a regular processor and memory is used. For example, an EC2 instance from Amazon Web Services (AWS) can be used. For data storage, a cloud storage service such as Amazon S3 is used. For software to run the generative AI model, a machine learning framework such as TensorFlow or PyTorch is used. For natural language processing (NLP), SpaCy or NLTK is used, and for computer vision, OpenCV or TensorFlow is used.

[0903] The devices used may be personal computers, smartphones, tablets, etc. These devices require an internet connection and communicate with the server via a browser or dedicated application.

[0904] Specific Examples

[0905] 1. Providing User Input

[0906] Users access the system using their own devices. For example, they can provide the text "I want a simple package design with a nature theme," as well as sketches of plants and images with specific color schemes. An example of a prompt sentence could be, "I need a package with a natural and simple design. Please refer to the images and sketches below."

[0907] 2. Data storage and analysis

[0908] The server receives input data sent by users and stores it in a database. The saved text data is then analyzed using natural language processing (NLP) techniques to extract keywords such as "nature," "simple," and "packaging design." For sketches and images, computer vision algorithms are used to identify the shape and color of plants.

[0909] 3. Generate design proposals

[0910] The server generates a specific prompt based on the analysis results and inputs it into the generative AI model. For example, this prompt might be in the form of, "Please generate a package design with the themes of 'nature' and 'simplicity' based on the image and sketch below." The generative AI model then generates multiple design proposals based on this prompt.

[0911] 4. Evaluation and Optimization

[0912] The server evaluates the generated design proposals and selects the one that best meets the user's requirements. Furthermore, it optimizes the design proposals by fine-tuning the color and layout based on the evaluation results. This evaluation can be performed using heuristic evaluation or machine learning algorithms.

[0913] 5. Providing design ideas and feedback

[0914] The server then sends the optimized design proposal to the user's device for review. The user reviews the proposal and provides feedback or corrections as needed. The server then adjusts the design proposal based on this feedback, and the process is repeated until the final design is completed.

[0915] This series of processes allows users to quickly and efficiently obtain high-quality design proposals. The present invention is expected to support users' creativity and significantly improve the efficiency of design work.

[0916] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0917] Step 1:

[0918] The user sends initial input data from their device to the server. The user uses a personal computer or smartphone to input text, sketches, images, etc. into the system. The input includes the text "I want a simple packaging design with a nature theme," a sketch of a plant, and an image of a specific color scheme. This data is sent to the server via a form or file upload function.

[0919] Input: User text, sketches, and images

[0920] Output: User-entered data sent to the server

[0921] Step 2:

[0922] The server saves the input data received from the user to a database. The specific saving operation uses a cloud storage service (e.g., Amazon S3), and the data is managed in an appropriate folder structure for each user.

[0923] Input: User-entered data sent to the server

[0924] Output: User-entered data stored in a database

[0925] Step 3:

[0926] The server analyzes the stored user-entered data. For text data, natural language processing (NLP) techniques are used to extract keywords such as "nature," "simple," and "packaging design." For sketches and images, computer vision algorithms are used to identify the shape and color of plants and extract their features.

[0927] Input: User-entered data stored in a database

[0928] Output: Extracted features and keywords

[0929] Step 4:

[0930] The server generates a specific prompt based on the analysis results. The generated prompt is input into a generative AI model, which generates multiple design proposals. An example of a prompt is, "Please generate a package design with the themes of 'nature' and 'simplicity' based on the image and sketch below."

[0931] Input: extracted features and keywords

[0932] Output: Generated prompts and design proposals

[0933] Step 5:

[0934] The server evaluates and optimizes the generated design proposals. Using an evaluation algorithm, it determines how well the generated design proposals meet the user's requirements. Based on the evaluation results, the design proposals are optimized by fine-tuning their color and layout.

[0935] Input: Generated design proposal

[0936] Output: Evaluation results and optimized design proposals

[0937] Step 6:

[0938] The server sends the optimized design proposal to the user's device, using the HTTP protocol and WebSocket for communication, allowing the design proposal to be viewed in the user interface.

[0939] Input: Optimized design proposal

[0940] Output: Optimized design proposal sent to user device

[0941] Step 7:

[0942] The user checks the submitted design proposal on their device and sends feedback to the server. If necessary, they can submit correction requests, and the server will then adjust the design proposal accordingly.

[0943] Input: User feedback

[0944] Output: Final, refined design proposal

[0945] This series of processes allows users to obtain high-quality design proposals quickly and efficiently.

[0946] (Application example 1)

[0947] 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."

[0948] In modern design generation, users are expected to quickly obtain high-quality design proposals simply by providing their ideas and instructions. However, conventional systems cannot accurately reflect the user's intentions, and as a result, the generated designs often do not meet the user's expectations. Furthermore, there is no process for reflecting user feedback and re-optimizing the design, making it difficult to efficiently improve design quality.

[0949] 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.

[0950] In this invention, the server includes means for receiving user input, means for analyzing the received user input, means for generating multiple design proposals based on the analysis results, means for evaluating and optimizing the generated design proposals, means for providing the optimized design proposals to the user terminal, and means for re-optimizing the design proposals based on the evaluation results and reflecting user feedback. This makes it possible to quickly provide design proposals that more accurately reflect the user's intentions, and further to improve the quality of the design by reflecting user feedback.

[0951] "Means for receiving user input" refers to devices or software that allow a user to send data, such as text, sketches, or images, to the system and receive it.

[0952] "Means for analyzing received user input" means equipment or software that includes algorithms or techniques for analyzing received text, sketches, images, etc., and extracting key features or keywords.

[0953] "Means for generating multiple design proposals based on analysis results" refers to equipment or software that has the function of automatically generating multiple design proposals using a generative AI model based on analyzed data.

[0954] "Means for evaluating and optimizing the generated design proposals" refers to algorithms or software that evaluate the generated design proposals, check how well they meet the user requirements, and make any necessary optimizations.

[0955] "Means for providing optimized design proposals to a user device" refers to equipment or software that has the function of transmitting optimized design proposals to a user device so that the user can review them.

[0956] "Means of re-optimizing design proposals by reflecting user feedback based on evaluation results" refers to algorithms or software that have the function of re-evaluating and optimizing design proposals based on user feedback.

[0957] This invention is a system in which a user inputs initial ideas and instructions, and a generative AI model generates innovative design concepts based on those ideas.

[0958] System configuration

[0959] The system mainly consists of a server, terminals, and users. The server acts as a central control unit and performs complex data analysis and executes generative AI models. The terminals are devices operated by users and are used to send user input and receive design proposals. Users access the system using terminals such as smartphones and tablets.

[0960] Program processing

[0961] The server performs the following steps:

[0962] 1. Receiving user input: The user uploads data such as text, sketches, and images from their device and sends it to the server, which receives the data and stores it in an appropriate format.

[0963] 2. Data Analysis: The server analyzes the received data, using natural language processing (NLP) techniques for text data and computer vision algorithms for sketches and images, to extract important features and keywords from the user's input.

[0964] 3. Design proposal generation: Based on the analysis results, the server uses a generative AI model to generate multiple design proposals, each of which contains unique elements that meet the user's requirements.

[0965] 4. Evaluate and optimize the design: The server evaluates the generated design to see how well it meets the user's expectations. Based on the evaluation results, it optimizes and fine-tunes the design.

[0966] 5. Providing design proposals: The server sends the optimized design proposals to the device for the user to review. The user reviews these design proposals and provides feedback if necessary.

[0967] 6. Reflecting feedback and re-optimizing: Based on user feedback, the server re-evaluates the design proposal and reflects the feedback to optimize the design proposal.

[0968] Hardware and software used

[0969] Hardware: Smartphones, tablets, servers (cloud-based)

[0970] Software: Python programs, OpenAI API, natural language processing (NLP) techniques, computer vision algorithms

[0971] Specific examples

[0972] For example, if a user needs a packaging design for a new product, the system works as follows:

[0973] 1. Providing user input: The user uploads the text "I want a simple packaging design with a nature theme," along with a sketch of a plant and an image of a specific color scheme, from their device to the server.

[0974] 2. Data analysis: The server uses NLP to extract keywords such as "nature," "simple," and "packaging design" from the text, and uses computer vision to extract plant shapes from sketches and color schemes from images.

[0975] 3. Design proposal generation: Based on the extracted features, the server uses a generative AI model to generate multiple package design proposals, each of which reflects the image of plants and simplicity.

[0976] 4. Evaluating and optimizing design ideas: The server evaluates each design idea, selects the one that best meets the user's requirements, and then performs further fine-tuning, such as adjusting the color and layout.

[0977] 5. Providing design proposals: The server sends the optimized design proposals to the terminal and provides them to the user. If the user is not satisfied, further revisions will be made through feedback.

[0978] 6. Reflecting feedback and re-optimizing: If a user provides feedback such as "Use a brighter green," the server will re-evaluate and optimize the design based on that feedback and serve it again.

[0979] Prompt Sentence Examples

[0980] Text: I want a simple package design with a nature theme.

[0981] Sketch Features: Simple sketches of trees, leaves, and flowers

[0982] Color characteristics: Bright green and pale blue tones

[0983] Based on these prompts, the system generates design proposals using the OpenAI API, and after receiving user feedback, the system re-optimizes the design and delivers it to the user.

[0984] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0985] Step 1:

[0986] The server receives user input. The user uses a terminal to upload text such as "I want a simple package design with a nature theme," a sketch of a plant, and an image of a specific color scheme. The server receives this input data and saves it as text data, sketch image data, and color scheme image data.

[0987] Step 2:

[0988] The server analyzes the received user input. It uses natural language processing (NLP) technology on the text data to extract keywords such as "nature," "simple," and "package design." It uses computer vision algorithms on the sketch image data to extract the shape and characteristics of plants. It also uses computer vision algorithms on the color scheme image data to extract color scheme information such as bright green and light blue. This allows the user's intention to be extracted as specific features and keywords.

[0989] Step 3:

[0990] The server generates multiple design proposals based on the analysis results. Using the analyzed text keywords, sketch features, and color scheme information, it creates prompts for the generative AI model, which then generates design proposals based on those prompts. The generated design proposals include original elements that are in line with the input data. For example, they include elements such as a "simple design with a nature theme," "reflecting the shape of a specific plant," and "using a bright green and light blue color scheme."

[0991] Step 4:

[0992] The server evaluates the generated design proposals. The design proposals output by the generative AI model are analyzed using an evaluation algorithm to check how well they match the user's instructions and input data. The evaluation checks the degree of agreement of keywords, shapes, and color schemes. Based on the evaluation results, if further optimization is required, fine-tuning of colors and layout is performed.

[0993] Step 5:

[0994] The server provides the optimized design proposal to the user's device. The generated and optimized design proposal is sent to the user's device for the user to review. The user reviews the proposed design proposal, and if they are not satisfied, they send feedback from their device to the server.

[0995] Step 6:

[0996] The server receives feedback from the user and re-optimizes the design proposal based on that feedback. It analyzes the feedback provided by the user (e.g., "Please use a brighter green") and uses the generative AI model and optimization algorithm to re-generate and optimize the design proposal. It then provides the re-generated and optimized design proposal to the user again and confirms that the design proposal has been improved based on the feedback.

[0997] 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.

[0998] This invention is a system in which generative AI generates innovative design concepts based on initial ideas and instructions provided by the user. This system is combined with an emotion engine that recognizes the user's emotions, and is able to propose design proposals that reflect the user's emotions. Below, we will explain the program processing of this system in natural language, and provide concrete examples.

[0999] System configuration

[1000] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit, performing complex data analysis and running generative AI models. The terminal is a device operated by the user, used to send user input and receive design proposals. In addition, it is equipped with an emotion engine, which has the built-in ability to recognize and analyze user emotions.

[1001] Program processing

[1002] 1. The server receives user input

[1003] Users upload text, sketches, images, and even emotional data from their devices, and the server receives and stores the data in the required format.

[1004] 2. Data Analysis

[1005] The server analyzes the received text data using natural language processing (NLP) technology to extract keywords such as "simple," "modern," and "logo" from the text, and also analyzes sketches and images using computer vision technology to extract features.

[1006] 3. Emotion Data Analysis

[1007] The emotion engine analyzes the user's emotional data, which includes emotional information derived from the user's voice and facial expressions. The emotion engine identifies emotions such as "happy," "excited," and "calm."

[1008] 4. Generate design proposals

[1009] Based on the analysis results, the server uses a generative AI model to generate multiple design proposals. Emotional data obtained from the emotion engine is also reflected in the design prompts. For example, if the user feels "calm," color schemes and design elements that reflect that emotion will be suggested.

[1010] 5. Evaluate and optimize design ideas

[1011] The server evaluates the generated design proposals and selects the one that best matches the user's needs and emotions. The evaluation criteria also take into account emotional data, and the design proposal that best matches the user's emotions is scored. The server then optimizes the design proposals and adjusts the details based on the evaluation results.

[1012] 6. Providing design proposals

[1013] The server sends the optimized design proposal to the device, where the user can review it and send feedback or correction requests to the server if necessary. The server receives the feedback and makes corrections.

[1014] Specific examples

[1015] For example, if a user needs a logo for a new cafe, the system works like this:

[1016] 1. Providing User Input

[1017] The user uploads the text "I want a nature-themed relaxing logo," along with a simple sketch and a specific color scheme image, to the server from their device, and the emotion engine recognizes that the user is relaxed.

[1018] 2. Data Analysis

[1019] The server uses NLP to extract keywords such as "nature," "relax," and "logo" from the text, and then uses computer vision to analyze the shape of the sketch and the color scheme of the image.

[1020] 3. Emotion Data Analysis

[1021] The emotion engine analyzes the user's emotions and identifies that "relaxation" is the main emotion.

[1022] 4. Generate design proposals

[1023] The server uses a generative AI model to generate multiple logo designs based on these analysis results and emotional data, such as a nature-themed logo using muted shades of green and blue.

[1024] 5. Evaluate and optimize design ideas

[1025] The server evaluates each logo design, selects the one that best matches the user's needs and emotions, and then fine-tunes it, adjusting the color and shape, for example, to create the optimal design.

[1026] 6. Providing design proposals

[1027] The server sends the optimized logo design to the device and provides it to the user, and if the user is not satisfied, further revisions are made through feedback.

[1028] In this way, users can quickly obtain high-quality design proposals that reflect their own emotions, improving the quality and fit of their designs, supporting creativity and streamlining work.

[1029] The processing flow will be explained below.

[1030] Step 1:

[1031] Users use their device to input their initial design ideas and instructions, including uploading text, sketches, and images, providing emotional data, and then clicking a send button to send this data to the server.

[1032] Step 2:

[1033] The server receives the text data, sketches, images, and emotion data sent by the user. After receiving the data, the server verifies the format of each data and ensures that all required data is present. For example, it verifies that the text is sent correctly and that the sketches and images are in the supported formats (JPEG, PNG, etc.).

[1034] Step 3:

[1035] The server analyzes the received text data using natural language processing (NLP) technology, specifically extracting keywords such as "simple," "modern," and "logo" from the text.

[1036] Step 4:

[1037] The server analyzes the received sketches and images using computer vision technology, specifically recognizing the shape of the sketch and extracting features such as the color and pattern of the image.

[1038] Step 5:

[1039] The emotion engine analyzes the emotional data provided by the user, specifically identifying emotions such as "satisfied," "excited," or "calm" based on information gleaned from the user's voice and facial expressions.

[1040] Step 6:

[1041] The server then formats the analysis results as input data for generating multiple design proposals. It creates design prompts by integrating the text analysis results, features of sketches and images, and emotion data.

[1042] Step 7:

[1043] The server uses a generative AI model to generate design proposals. The generation process takes into account the interpreted user request as well as emotional data. For example, if the user is feeling "relaxed," the server will suggest color schemes and design elements that reflect that emotion.

[1044] Step 8:

[1045] The server evaluates the generated design proposals and scores them based on the evaluation criteria to determine which design proposal best suits the user's needs and emotions. Emotional data is also taken into account as an evaluation criterion.

[1046] Step 9:

[1047] The server then optimizes the design proposals with the highest scores based on the evaluation results, which includes adjusting color tones and optimizing the layout.

[1048] Step 10:

[1049] The server then formats the optimized design into its final form, and the resulting design, formatted as a high-resolution image, is sent to the user's device.

[1050] Step 11:

[1051] The user can check the design proposal sent to them on their device. They can then enter feedback or corrections they would like to make and send it back to the server. The server will receive this and make any necessary corrections.

[1052] These steps allow users to quickly receive high-quality design proposals that reflect their emotions, improving the quality and fit of the design, supporting creativity and streamlining work.

[1053] Example 2

[1054] 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."

[1055] Conventional design generation systems lacked a means to provide design proposals that reflected the user's emotions, making it difficult to increase user satisfaction. Furthermore, there was a lack of a system that could accurately analyze the user's needs and emotions and quickly generate and provide optimal design proposals in response. This meant that users could not obtain designs that accurately reflected their requirements, and the process of providing feedback and making corrections was time-consuming.

[1056] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1057] In this invention, the server includes means for receiving user input, means for analyzing the received user input, means for recognizing and analyzing user emotion data, means for generating multiple design proposals based on the analysis results and the emotion data, means for evaluating and optimizing the generated design proposals, and means for providing the optimized design proposals to the user terminal, thereby enabling the rapid provision of high-quality design proposals that reflect the user's emotions.

[1058] "User Input" means text, sketches, images, and other information provided by a user.

[1059] "Means for receiving" refers to the functionality by which the server receives user input.

[1060] "Means of analysis" refers to technology for analyzing the content of user input and extracting keywords and features.

[1061] "Emotional data" refers to emotional information recognized and analyzed from the user's voice, facial expressions, etc.

[1062] "Means for recognizing and analyzing emotional data" refers to the ability to identify a user's emotions using an emotion engine.

[1063] "Design Proposals" refers to multiple design proposals generated based on the analysis results and emotion data.

[1064] "Means for generating" refers to the functionality for generating multiple design alternatives using a generative AI model.

[1065] "Means for evaluation and optimization" refers to the function of evaluating the generated design proposals, selecting the proposal that best suits the user's requirements and emotions, and fine-tuning it.

[1066] "Means of providing" refers to the function for sending optimized design proposals to the user's terminal.

[1067] "User Terminal" means the electronic device used by a User to submit input and receive design suggestions.

[1068] "Natural language processing" refers to the technology of analyzing a user's text input and extracting keywords and meaning.

[1069] "Computer vision algorithms" refers to techniques for analyzing the features of sketches and images.

[1070] "Generative AI model" refers to an artificial intelligence model that generates design ideas based on user input and emotional data.

[1071] A "prompt" refers to an instruction that a generative AI model uses to generate design proposals.

[1072] Program Generation and Explanation

[1073] The system of this invention is designed to generate innovative design concepts based on user input. The system incorporates an emotion engine that recognizes the user's emotions and can propose design proposals that reflect the user's emotional state.

[1074] Hardware and software used

[1075] The system mainly uses the following hardware and software:

[1076] Server: Responsible for receiving data, analyzing it, and running generative AI models. Specifically, it utilizes AWS computing resources.

[1077] Device: The user sends input data and receives the generated design proposals. A standard computer or smartphone is used.

[1078] Natural Language Processing (NLP) techniques: Use TensorFlow to parse text input.

[1079] Computer Vision Techniques: Use OpenCV to analyze sketches and images.

[1080] Emotion Engine: Uses Google Cloud AutoML to analyze the user's voice and facial expressions.

[1081] Generative AI model: We use OpenAI's GPT-3 to generate design ideas.

[1082] Evaluation and optimization: We use scikit-learn and Photoshop APIs to evaluate and optimize the generated design solutions.

[1083] Data processing and calculation

[1084] 1. Receiving User Input

[1085] Users upload text, sketches, images, and emotional data, including voice and facial expressions, from their devices to the server.

[1086] 2. Data storage

[1087] The server stores the received data in AWS S3 or RDS.

[1088] 3. Data Analysis

[1089] The server uses NLP technology (TensorFlow) to analyze text and extract keywords, and computer vision technology (OpenCV) to extract features from sketches and images.

[1090] 4. Emotion Data Analysis

[1091] The emotion engine (Google Cloud AutoML) analyzes user emotion data and recognizes specific emotional states.

[1092] 5. Generate design proposals

[1093] Based on the above analysis results, the server generates multiple design proposals using a generative AI model (OpenAI's GPT-3).

[1094] 6. Evaluate and optimize design ideas

[1095] The server evaluates the generated design proposals, performs scoring using scikit-learn, and then optimizes the proposals using the Photoshop API.

[1096] 7. Providing design proposals

[1097] The optimized design is sent to the user's device, where the user can review it and provide feedback if necessary.

[1098] Examples of specific examples and prompts

[1099] For example, if a user needs a logo for a new cafe, the system might do the following:

[1100] 1. Providing User Input

[1101] Users upload text such as "I want a nature-themed, relaxing logo," a simple sketch, and a specific color scheme image from their device to the server, and the emotion engine recognizes that the user is relaxing.

[1102] 2. Data Analysis

[1103] The server extracts keywords such as "nature," "relaxation," and "logo" from the text and analyzes sketches and color scheme images.

[1104] 3. Emotion Data Analysis

[1105] The emotion engine identifies the user's emotion as "relaxed."

[1106] 4. Generate design proposals

[1107] Based on the analysis results and emotion data, the server uses a generative AI model to generate multiple logo designs, such as a nature-themed logo using muted shades of green and blue.

[1108] 5. Evaluate and optimize design ideas

[1109] The server evaluates each logo design and selects the design that best matches the user's needs and emotions, then adjusts the color and shape.

[1110] 6. Providing design proposals

[1111] The server sends the optimized logo design to the device.

[1112] Prompt Sentence Examples

[1113] "I'd like to create a new logo for my cafe. I'd like the theme to be nature-themed and relaxing. I'd like it to have a green and blue color scheme as the base."

[1114] This system allows users to quickly obtain high-quality design proposals that reflect their own emotions.

[1115] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1116] Step 1: Providing User Input

[1117] ----

[1118] The user uses the device to provide text, sketches, images, and emotion data to the server. For example, the user can type, "I want a nature-themed relaxing logo," and upload related sketches and color scheme images. The emotion engine then recognizes that the user is relaxed based on their voice and facial expression.

[1119] Input: Text (e.g., "Relaxing nature-themed logos"), sketches, images, audio, facial expressions

[1120] Output: Data provided to the server

[1121] Step 2: Receiving and storing data

[1122] ----

[1123] The server receives input data sent by the user, saves images and sketches to AWS S3, and saves text data to RDS.

[1124] Input: User-submitted text, sketches, images, voice, and facial expressions

[1125] Output: User input information stored in a database

[1126] Step 3: Analyzing the text data

[1127] ----

[1128] The server uses NLP (Natural Language Processing) technology to analyze the text data with TensorFlow and extract keywords, such as "nature," "relax," and "logo."

[1129] Input: Saved text data

[1130] Output: Extracted keywords (e.g., "nature," "relax," "logo")

[1131] Step 4: Analyzing the image data

[1132] ----

[1133] The server uses computer vision technology to analyze the shape and features of sketches and images using OpenCV, specifically analyzing hue, brightness, shape, etc.

[1134] Input: Saved sketches and image data

[1135] Output: Analyzed image feature information (shape, color, etc.)

[1136] Step 5: Analyze the sentiment data

[1137] ----

[1138] The emotion engine uses Google Cloud AutoML to analyze emotions from the user's voice and facial expressions and identify specific emotional states such as "relaxed."

[1139] Input: Stored voice data and facial expression data

[1140] Output: Analyzed emotion information (e.g., "Relaxed")

[1141] Step 6: Generate design ideas

[1142] ----

[1143] Based on the analysis results and emotion data, the server uses a generative AI model (OpenAI's GPT-3) to generate multiple design proposals. For example, it proposes a logo design based on green and blue tones based on the relaxed emotion.

[1144] Input: extracted keywords, analyzed image feature information, analyzed emotion information

[1145] Output: Multiple design proposals generated

[1146] Step 7: Evaluate and optimize design alternatives

[1147] ----

[1148] The server evaluates the generated design proposals, scores them using scikit-learn, and selects the one that best suits the user's needs and emotions. It then optimizes the design proposals by adjusting color, shape, etc. using the Photoshop API.

[1149] Input: Multiple generated design ideas

[1150] Output: Optimized design proposal

[1151] Step 8: Submit a design proposal

[1152] ----

[1153] The server sends the optimized design proposal to the user's device. The user checks the design proposal on the device and sends feedback to the server if necessary. The server then makes further revisions based on this feedback.

[1154] Input: Optimized design proposal

[1155] Output: Design proposals provided to users, and suggested revisions based on their feedback

[1156] (Application example 2)

[1157] 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."

[1158] Conventional design generation systems were unable to reflect the user's emotions in the design proposal, making it difficult to propose optimal designs that matched the user's psychological state and preferences. Furthermore, there was a lack of a way to visually confirm how the generated design proposal would be applied to the actual space, making it difficult to increase user satisfaction.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1160] In this invention, the server includes means for receiving user input, means for analyzing the received user input and emotional data, means for generating multiple design proposals based on the analysis results and the user's emotional data, means for evaluating and optimizing the generated design proposals, and means for displaying the optimized design proposals on the user terminal using augmented reality technology. This makes it possible to generate design proposals that reflect the user's emotions and also makes it easy to visually confirm them in real space, thereby improving user satisfaction.

[1161] "User input" refers to information such as text, sketches, or images provided by a user to the system.

[1162] "Emotional data" refers to information about the psychological state analyzed based on voice and facial expressions obtained from the user.

[1163] "Natural language processing" refers to the technology that allows computers to understand and analyze natural human language.

[1164] "Computer vision algorithms" refer to algorithms used to analyze and understand visual data such as images and videos.

[1165] "Augmented reality technology" refers to technology that overlays digital information onto the real world.

[1166] "Design Proposal" refers to a design proposal generated based on user input and emotional data.

[1167] "User terminal" refers to a device operated by a user, such as a smartphone or head-mounted display.

[1168] Overall system configuration

[1169] The system is comprised of three main components: a server, a user device, and the user. The server acts as a central control unit, responsible for complex data analysis and generative AI model execution. The user device is a device used by the user to provide input and receive design proposals, and can include a smartphone or head-mounted display. Furthermore, it incorporates an emotion engine, capable of recognizing and analyzing user emotions.

[1170] Hardware and software used

[1171] Hardware: Smartphone, head-mounted display, camera, microphone

[1172] Software: Natural Language Processing (NLP) algorithms, computer vision algorithms, generative AI models, emotion recognition engines, and augmented reality (AR) display software

[1173] Program processing

[1174] The server receives user input and analyzes it using the emotion engine. The received user input includes text, sketches, and images, and is analyzed using natural language processing and computer vision technologies. The emotion engine also analyzes and recognizes emotional data from the user's voice and facial expressions. This input data and emotional data are integrated and multiple design proposals are generated using a generative AI model.

[1175] The generated design proposals are evaluated on the server, and the proposal that best suits the user's requirements and emotions is selected. Emotional data is also taken into account in the evaluation criteria, and the design proposal that best matches the user's emotions is optimized. The optimized design proposal is displayed on the user's device using augmented reality technology, allowing the user to view and evaluate it.

[1176] Specific examples

[1177] For example, here's how the system works if a brick-and-mortar cafe owner wants a new interior design.

[1178] 1. Providing user input:

[1179] A cafe owner launches the smartphone app and uploads text information such as "I want a natural cafe atmosphere," along with hand-drawn sketches and images of examples of cafe interiors with plenty of greenery. The emotion engine then recognizes that the cafe owner is relaxed.

[1180] 2. Data Analysis:

[1181] The server uses NLP to extract keywords such as "nature," "cafe," and "relaxation" from the text information, and analyzes the shape of the sketch and the color scheme of the image using computer vision technology.

[1182] 3. Emotional Data Analysis:

[1183] Emotional data is derived using a camera and microphone to identify the user's sense of relaxation.

[1184] 4. Design generation and evaluation:

[1185] The generative AI model generates multiple design proposals based on this data, and the server selects and optimizes the most suitable design proposal, taking into account emotional data. For example, it generates a design for a nature-themed cafe interior using calming colors such as green and blue.

[1186] 5. Submit design proposal:

[1187] Using augmented reality technology, the optimized design proposals are displayed to the user in real time through a head-mounted display, allowing the owner to see what the proposed design will look like while walking through the store.

[1188] Prompt Sentence Examples

[1189] "Please propose a new layout that evokes a natural cafe atmosphere in a chalk art style. Users will feel relaxed."

[1190] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1191] Step 1:

[1192] Providing User Input

[1193] Users access the system using a smartphone or head-mounted display to upload text, sketches, and images, while the emotion engine reads the user's voice and facial expressions through a camera and microphone to collect emotional data.

[1194] Input: Text (e.g., a natural cafe atmosphere is desired), sketch image, interior image, emotional data (voice, facial expression)

[1195] Output: User input and emotion data sent to the server

[1196] Step 2:

[1197] Data analysis

[1198] The server analyzes the received user input, using natural language processing (NLP) techniques to extract keywords from the text and computer vision algorithms to extract features from sketches and images.

[1199] Input: Text received from the user, sketch image, interior image

[1200] Output: Text analysis results (keywords), image analysis results (shape and color features)

[1201] Step 3:

[1202] Emotional Data Analysis

[1203] The emotion engine analyzes the user's voice and facial expressions to identify the user's emotions, for example, determining that the user is relaxed.

[1204] Input: User's voice data, facial expression data

[1205] Output: User's emotional state (e.g., relaxed)

[1206] Step 4:

[1207] Generate design ideas

[1208] The server uses a generative AI model to generate multiple design proposals based on the analysis results and user emotion data. The system generates designs based on design prompts that reflect the user's emotions and keywords.

[1209] Input: Text analysis results (keywords), image analysis results (shape and color features), emotional state (relaxed)

[1210] Output: Multiple design ideas

[1211] Step 5:

[1212] Evaluating and optimizing design alternatives

[1213] The server evaluates the generated design proposals and selects the one that best suits the user's emotions and requests. Since the evaluation criteria also include emotional data, design proposals that match the user's emotions are highly rated. The optimal design proposal is selected and fine-tuned.

[1214] Input: Multiple design options, user emotional state

[1215] Output: Optimized design proposal

[1216] Step 6:

[1217] Displaying design ideas

[1218] The optimized design proposals are displayed on the user's device using augmented reality technology, allowing the user to view the proposed design in real time via a head-mounted display or smartphone.

[1219] Input: Optimized design proposal

[1220] Output: Design proposal displayed using augmented reality technology

[1221] 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.

[1222] 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.

[1223] 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.

[1224] [Fourth embodiment]

[1225] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1226] 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.

[1227] 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).

[1228] 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.

[1229] 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.

[1230] 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).

[1231] 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.

[1232] 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.

[1233] 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.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] 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."

[1238] This invention is a system in which generative AI generates innovative design concepts based on initial ideas and instructions provided by users. Below, we explain the program processing of this system in natural language and provide concrete examples.

[1239] System configuration

[1240] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit and performs complex data analysis and runs generative AI models. The terminal is a user-operated device that sends user input and receives design proposals.

[1241] Program processing

[1242] 1. The server receives user input

[1243] Users upload and send input data such as text, sketches, and images from their devices, and the server receives and stores the data in the required format.

[1244] 2. Data Analysis

[1245] The server analyzes the received data, using natural language processing (NLP) techniques for text data and computer vision algorithms for sketches and images, to extract important features and keywords from the user's input.

[1246] 3. Generate design proposals

[1247] Based on the analysis results, the server uses a generative AI model to generate multiple design proposals, each of which includes unique elements tailored to the user's requirements.

[1248] 4. Evaluate and optimize design ideas

[1249] The server evaluates the generated design proposals to see how well they meet user expectations, and then optimizes and fine-tunes the design proposals based on the evaluation results.

[1250] 5. Providing design proposals

[1251] The server then sends the optimized design proposals to the device for the user to review, and the user can review these design proposals and, if necessary, send feedback or correction requests to the server.

[1252] Specific examples

[1253] For example, if a user needs a packaging design for a new product, the system works like this:

[1254] 1. Providing User Input

[1255] Users upload text such as "I want a simple packaging design with a nature theme," along with a sketch of a plant and an image of a specific color scheme from their device to the server.

[1256] 2. Data Analysis

[1257] The server uses NLP to extract keywords such as "nature," "simple," and "packaging design" from this text, and then uses computer vision to extract plant shapes from sketches and color schemes from images.

[1258] 3. Generate design proposals

[1259] Based on the extracted features, the server uses a generative AI model to generate multiple package design ideas, each of which reflects the image of plants and simplicity.

[1260] 4. Evaluate and optimize design ideas

[1261] The server evaluates each design proposal, selects the one that best meets the user's requirements, and then makes further adjustments, such as adjusting the color and layout.

[1262] 5. Providing design proposals

[1263] The server sends the optimized design to the device and provides it to the user, and if the user is not satisfied, further revisions are made through feedback.

[1264] This series of processes allows users to quickly and efficiently obtain high-quality design proposals, supporting users' creativity and significantly improving the efficiency of their design work.

[1265] The processing flow will be explained below.

[1266] Step 1:

[1267] The user uses the device to input initial design ideas and instructions, specifically uploading text, sketches, images, etc., and then clicks a send button to send the data to the server.

[1268] Step 2:

[1269] The server receives the data sent by the user. After receiving it, the server validates the data format and ensures that all required data is present. For example, it checks that text is sent correctly and that sketches and images are in the supported formats (JPEG, PNG, etc.).

[1270] Step 3:

[1271] The server analyzes the received text data using natural language processing (NLP) technology, which extracts keywords such as "simple," "modern," and "logo."

[1272] Step 4:

[1273] The server analyzes the received sketches and images using computer vision technology, specifically recognizing the shape of the sketch and extracting features such as the color and pattern of the image.

[1274] Step 5:

[1275] The server then formats the analysis results as input data for generating multiple design proposals, and creates design prompts by integrating the text analysis results with the features of sketches and images.

[1276] Step 6:

[1277] The server uses a generative AI model to generate design proposals. During the generation process, multiple different design proposals are generated based on the interpreted user requirements, such as a simple and modern logo.

[1278] Step 7:

[1279] The server evaluates the generated design proposals and scores them based on the evaluation criteria to determine which design proposal best meets the user's requirements.

[1280] Step 8:

[1281] The server then optimizes the design proposals with the highest scores based on the evaluation results, which includes adjusting color tones and optimizing the layout.

[1282] Step 9:

[1283] The server then formats the optimized design into its final form, and the resulting design, formatted as a high-resolution image, is sent to the user's device.

[1284] Step 10:

[1285] The user can check the design proposal sent to them on their device. They can then enter feedback or corrections they would like to make and send it back to the server. The server will receive this and make any necessary corrections.

[1286] These steps allow users to quickly receive specific, high-quality ideas for the design they want.

[1287] Example 1

[1288] 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."

[1289] In the modern design process, it is difficult and time-consuming to quickly generate high-quality design proposals based on the user's initial ideas and instructions. In particular, there is a need to respond to various user input formats, analyze and evaluate them, and provide optimal design proposals. Furthermore, an efficient method is needed to properly evaluate how well the generated design proposals meet the user's expectations and to further optimize them.

[1290] 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.

[1291] In this invention, the server includes means for receiving user input, means for saving the received user input in a database, means for analyzing the saved user input, means for generating multiple design proposals using a generative AI model based on the analysis results, means for evaluating and optimizing the generated design proposals, and means for providing the optimized design proposals to a user terminal, thereby enabling efficient processing of various user inputs and rapid generation of high-quality design proposals.

[1292] "User input" means instructions or initial data such as text, sketches, or images provided by a user to the system.

[1293] "Database" means a digital storage system for storing received user-entered data and making it available for reference in subsequent analysis or generation processes.

[1294] "Analysis" is the process of processing received and stored user-entered data and extracting important features or keywords.

[1295] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to generate new design ideas based on user input.

[1296] "Design Proposals" are multiple design and layout proposals created by a generative AI model.

[1297] The "evaluation method" is the process of determining how well the generated design proposal meets the user's requirements.

[1298] "Optimization" is the process of adjusting elements of a design proposal based on the evaluation results to create a form that best meets user expectations.

[1299] "User terminal" means a device through which a user accesses the system, sends input data, and receives generated design proposals.

[1300] This invention relates to a system that generates multiple design proposals using a generative AI model based on user input, optimizes them, and provides them to the user. Specific embodiments of the invention are described below.

[1301] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit and executes analysis and generative AI models. The terminal is a device operated by the user, used to send input data and receive design proposals. The user provides initial ideas and specific instructions.

[1302] Hardware and software used

[1303] For server hardware, a server machine equipped with a regular processor and memory is used. For example, an EC2 instance from Amazon Web Services (AWS) can be used. For data storage, a cloud storage service such as Amazon S3 is used. For software to run the generative AI model, a machine learning framework such as TensorFlow or PyTorch is used. For natural language processing (NLP), SpaCy or NLTK is used, and for computer vision, OpenCV or TensorFlow is used.

[1304] The devices used may be personal computers, smartphones, tablets, etc. These devices require an internet connection and communicate with the server via a browser or dedicated application.

[1305] Specific Examples

[1306] 1. Providing User Input

[1307] Users access the system using their own devices. For example, they can provide the text "I want a simple package design with a nature theme," as well as sketches of plants and images with specific color schemes. An example of a prompt sentence could be, "I need a package with a natural and simple design. Please refer to the images and sketches below."

[1308] 2. Data storage and analysis

[1309] The server receives input data sent by users and stores it in a database. The saved text data is then analyzed using natural language processing (NLP) techniques to extract keywords such as "nature," "simple," and "packaging design." For sketches and images, computer vision algorithms are used to identify the shape and color of plants.

[1310] 3. Generate design proposals

[1311] The server generates a specific prompt based on the analysis results and inputs it into the generative AI model. For example, this prompt might be in the form of, "Please generate a package design with the themes of 'nature' and 'simplicity' based on the image and sketch below." The generative AI model then generates multiple design proposals based on this prompt.

[1312] 4. Evaluation and Optimization

[1313] The server evaluates the generated design proposals and selects the one that best meets the user's requirements. Furthermore, it optimizes the design proposals by fine-tuning the color and layout based on the evaluation results. This evaluation can be performed using heuristic evaluation or machine learning algorithms.

[1314] 5. Providing design ideas and feedback

[1315] The server then sends the optimized design proposal to the user's device for review. The user reviews the proposal and provides feedback or corrections as needed. The server then adjusts the design proposal based on this feedback, and the process is repeated until the final design is completed.

[1316] This series of processes allows users to quickly and efficiently obtain high-quality design proposals. The present invention is expected to support users' creativity and significantly improve the efficiency of design work.

[1317] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] The user sends initial input data from their device to the server. The user uses a personal computer or smartphone to input text, sketches, images, etc. into the system. The input includes the text "I want a simple packaging design with a nature theme," a sketch of a plant, and an image of a specific color scheme. This data is sent to the server via a form or file upload function.

[1320] Input: User text, sketches, and images

[1321] Output: User-entered data sent to the server

[1322] Step 2:

[1323] The server saves the input data received from the user to a database. The specific saving operation uses a cloud storage service (e.g., Amazon S3), and the data is managed in an appropriate folder structure for each user.

[1324] Input: User-entered data sent to the server

[1325] Output: User-entered data stored in a database

[1326] Step 3:

[1327] The server analyzes the stored user-entered data. For text data, natural language processing (NLP) techniques are used to extract keywords such as "nature," "simple," and "packaging design." For sketches and images, computer vision algorithms are used to identify the shape and color of plants and extract their features.

[1328] Input: User-entered data stored in a database

[1329] Output: Extracted features and keywords

[1330] Step 4:

[1331] The server generates a specific prompt based on the analysis results. The generated prompt is input into a generative AI model, which generates multiple design proposals. An example of a prompt is, "Please generate a package design with the themes of 'nature' and 'simplicity' based on the image and sketch below."

[1332] Input: extracted features and keywords

[1333] Output: Generated prompts and design proposals

[1334] Step 5:

[1335] The server evaluates and optimizes the generated design proposals. Using an evaluation algorithm, it determines how well the generated design proposals meet the user's requirements. Based on the evaluation results, the design proposals are optimized by fine-tuning their color and layout.

[1336] Input: Generated design proposal

[1337] Output: Evaluation results and optimized design proposals

[1338] Step 6:

[1339] The server sends the optimized design proposal to the user's device, using the HTTP protocol and WebSocket for communication, allowing the design proposal to be viewed in the user interface.

[1340] Input: Optimized design proposal

[1341] Output: Optimized design proposal sent to user device

[1342] Step 7:

[1343] The user checks the submitted design proposal on their device and sends feedback to the server. If necessary, they can submit correction requests, and the server will then adjust the design proposal accordingly.

[1344] Input: User feedback

[1345] Output: Final, refined design proposal

[1346] This series of processes allows users to obtain high-quality design proposals quickly and efficiently.

[1347] (Application example 1)

[1348] 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."

[1349] In modern design generation, users are expected to quickly obtain high-quality design proposals simply by providing their ideas and instructions. However, conventional systems cannot accurately reflect the user's intentions, and as a result, the generated designs often do not meet the user's expectations. Furthermore, there is no process for reflecting user feedback and re-optimizing the design, making it difficult to efficiently improve design quality.

[1350] 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.

[1351] In this invention, the server includes means for receiving user input, means for analyzing the received user input, means for generating multiple design proposals based on the analysis results, means for evaluating and optimizing the generated design proposals, means for providing the optimized design proposals to the user terminal, and means for re-optimizing the design proposals based on the evaluation results and reflecting user feedback. This makes it possible to quickly provide design proposals that more accurately reflect the user's intentions, and further to improve the quality of the design by reflecting user feedback.

[1352] "Means for receiving user input" refers to devices or software that allow a user to send data, such as text, sketches, or images, to the system and receive it.

[1353] "Means for analyzing received user input" means equipment or software that includes algorithms or techniques for analyzing received text, sketches, images, etc., and extracting key features or keywords.

[1354] "Means for generating multiple design proposals based on analysis results" refers to equipment or software that has the function of automatically generating multiple design proposals using a generative AI model based on analyzed data.

[1355] "Means for evaluating and optimizing the generated design proposals" refers to algorithms or software that evaluate the generated design proposals, check how well they meet the user requirements, and make any necessary optimizations.

[1356] "Means for providing optimized design proposals to a user device" refers to equipment or software that has the function of transmitting optimized design proposals to a user device so that the user can review them.

[1357] "Means of re-optimizing design proposals by reflecting user feedback based on evaluation results" refers to algorithms or software that have the function of re-evaluating and optimizing design proposals based on user feedback.

[1358] This invention is a system in which a user inputs initial ideas and instructions, and a generative AI model generates innovative design concepts based on those ideas.

[1359] System configuration

[1360] The system mainly consists of a server, terminals, and users. The server acts as a central control unit and performs complex data analysis and executes generative AI models. The terminals are devices operated by users and are used to send user input and receive design proposals. Users access the system using terminals such as smartphones and tablets.

[1361] Program processing

[1362] The server performs the following steps:

[1363] 1. Receiving user input: The user uploads data such as text, sketches, and images from their device and sends it to the server, which receives the data and stores it in an appropriate format.

[1364] 2. Data Analysis: The server analyzes the received data, using natural language processing (NLP) techniques for text data and computer vision algorithms for sketches and images, to extract important features and keywords from the user's input.

[1365] 3. Design proposal generation: Based on the analysis results, the server uses a generative AI model to generate multiple design proposals, each of which contains unique elements that meet the user's requirements.

[1366] 4. Evaluate and optimize the design: The server evaluates the generated design to see how well it meets the user's expectations. Based on the evaluation results, it optimizes and fine-tunes the design.

[1367] 5. Providing design proposals: The server sends the optimized design proposals to the device for the user to review. The user reviews these design proposals and provides feedback if necessary.

[1368] 6. Reflecting feedback and re-optimizing: Based on user feedback, the server re-evaluates the design proposal and reflects the feedback to optimize the design proposal.

[1369] Hardware and software used

[1370] Hardware: Smartphones, tablets, servers (cloud-based)

[1371] Software: Python programs, OpenAI API, natural language processing (NLP) techniques, computer vision algorithms

[1372] Specific examples

[1373] For example, if a user needs a packaging design for a new product, the system works as follows:

[1374] 1. Providing user input: The user uploads the text "I want a simple packaging design with a nature theme," along with a sketch of a plant and an image of a specific color scheme, from their device to the server.

[1375] 2. Data analysis: The server uses NLP to extract keywords such as "nature," "simple," and "packaging design" from the text, and uses computer vision to extract plant shapes from sketches and color schemes from images.

[1376] 3. Design proposal generation: Based on the extracted features, the server uses a generative AI model to generate multiple package design proposals, each of which reflects the image of plants and simplicity.

[1377] 4. Evaluating and optimizing design ideas: The server evaluates each design idea, selects the one that best meets the user's requirements, and then performs further fine-tuning, such as adjusting the color and layout.

[1378] 5. Providing design proposals: The server sends the optimized design proposals to the terminal and provides them to the user. If the user is not satisfied, further revisions will be made through feedback.

[1379] 6. Reflecting feedback and re-optimizing: If a user provides feedback such as "Use a brighter green," the server will re-evaluate and optimize the design based on that feedback and serve it again.

[1380] Prompt Sentence Examples

[1381] Text: I want a simple package design with a nature theme.

[1382] Sketch Features: Simple sketches of trees, leaves, and flowers

[1383] Color characteristics: Bright green and pale blue tones

[1384] Based on these prompts, the system generates design proposals using the OpenAI API, and after receiving user feedback, the system re-optimizes the design and delivers it to the user.

[1385] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1386] Step 1:

[1387] The server receives user input. The user uses a terminal to upload text such as "I want a simple package design with a nature theme," a sketch of a plant, and an image of a specific color scheme. The server receives this input data and saves it as text data, sketch image data, and color scheme image data.

[1388] Step 2:

[1389] The server analyzes the received user input. It uses natural language processing (NLP) technology on the text data to extract keywords such as "nature," "simple," and "package design." It uses computer vision algorithms on the sketch image data to extract the shape and characteristics of plants. It also uses computer vision algorithms on the color scheme image data to extract color scheme information such as bright green and light blue. This allows the user's intention to be extracted as specific features and keywords.

[1390] Step 3:

[1391] The server generates multiple design proposals based on the analysis results. Using the analyzed text keywords, sketch features, and color scheme information, it creates prompts for the generative AI model, which then generates design proposals based on those prompts. The generated design proposals include original elements that are in line with the input data. For example, they include elements such as a "simple design with a nature theme," "reflecting the shape of a specific plant," and "using a bright green and light blue color scheme."

[1392] Step 4:

[1393] The server evaluates the generated design proposals. The design proposals output by the generative AI model are analyzed using an evaluation algorithm to check how well they match the user's instructions and input data. The evaluation checks the degree of agreement of keywords, shapes, and color schemes. Based on the evaluation results, if further optimization is required, fine-tuning of colors and layout is performed.

[1394] Step 5:

[1395] The server provides the optimized design proposal to the user's device. The generated and optimized design proposal is sent to the user's device for the user to review. The user reviews the proposed design proposal, and if they are not satisfied, they send feedback from their device to the server.

[1396] Step 6:

[1397] The server receives feedback from the user and re-optimizes the design proposal based on that feedback. It analyzes the feedback provided by the user (e.g., "Please use a brighter green") and uses the generative AI model and optimization algorithm to re-generate and optimize the design proposal. It then provides the re-generated and optimized design proposal to the user again and confirms that the design proposal has been improved based on the feedback.

[1398] 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.

[1399] This invention is a system in which generative AI generates innovative design concepts based on initial ideas and instructions provided by the user. This system is combined with an emotion engine that recognizes the user's emotions, and is able to propose design proposals that reflect the user's emotions. Below, we will explain the program processing of this system in natural language, and provide concrete examples.

[1400] System configuration

[1401] The system mainly consists of a server, a terminal, and a user. The server acts as a central control unit, performing complex data analysis and running generative AI models. The terminal is a device operated by the user, used to send user input and receive design proposals. In addition, it is equipped with an emotion engine, which has the built-in ability to recognize and analyze user emotions.

[1402] Program processing

[1403] 1. The server receives user input

[1404] Users upload text, sketches, images, and even emotional data from their devices, and the server receives and stores the data in the required format.

[1405] 2. Data Analysis

[1406] The server analyzes the received text data using natural language processing (NLP) technology to extract keywords such as "simple," "modern," and "logo" from the text, and also analyzes sketches and images using computer vision technology to extract features.

[1407] 3. Emotion Data Analysis

[1408] The emotion engine analyzes the user's emotional data, which includes emotional information derived from the user's voice and facial expressions. The emotion engine identifies emotions such as "happy," "excited," and "calm."

[1409] 4. Generate design proposals

[1410] Based on the analysis results, the server uses a generative AI model to generate multiple design proposals. Emotional data obtained from the emotion engine is also reflected in the design prompts. For example, if the user feels "calm," color schemes and design elements that reflect that emotion will be suggested.

[1411] 5. Evaluate and optimize design ideas

[1412] The server evaluates the generated design proposals and selects the one that best matches the user's needs and emotions. The evaluation criteria also take into account emotional data, and the design proposal that best matches the user's emotions is scored. The server then optimizes the design proposals and adjusts the details based on the evaluation results.

[1413] 6. Providing design proposals

[1414] The server sends the optimized design proposal to the device, where the user can review it and send feedback or correction requests to the server if necessary. The server receives the feedback and makes corrections.

[1415] Specific examples

[1416] For example, if a user needs a logo for a new cafe, the system works like this:

[1417] 1. Providing User Input

[1418] The user uploads the text "I want a nature-themed relaxing logo," along with a simple sketch and a specific color scheme image, to the server from their device, and the emotion engine recognizes that the user is relaxed.

[1419] 2. Data Analysis

[1420] The server uses NLP to extract keywords such as "nature," "relax," and "logo" from the text, and then uses computer vision to analyze the shape of the sketch and the color scheme of the image.

[1421] 3. Emotion Data Analysis

[1422] The emotion engine analyzes the user's emotions and identifies that "relaxation" is the main emotion.

[1423] 4. Generate design proposals

[1424] The server uses a generative AI model to generate multiple logo designs based on these analysis results and emotional data, such as a nature-themed logo using muted shades of green and blue.

[1425] 5. Evaluate and optimize design ideas

[1426] The server evaluates each logo design, selects the one that best matches the user's needs and emotions, and then fine-tunes it, adjusting the color and shape, for example, to create the optimal design.

[1427] 6. Providing design proposals

[1428] The server sends the optimized logo design to the device and provides it to the user, and if the user is not satisfied, further revisions are made through feedback.

[1429] In this way, users can quickly obtain high-quality design proposals that reflect their own emotions, improving the quality and fit of their designs, supporting creativity and streamlining work.

[1430] The processing flow will be explained below.

[1431] Step 1:

[1432] Users use their device to input their initial design ideas and instructions, including uploading text, sketches, and images, providing emotional data, and then clicking a send button to send this data to the server.

[1433] Step 2:

[1434] The server receives the text data, sketches, images, and emotion data sent by the user. After receiving the data, the server verifies the format of each data and ensures that all required data is present. For example, it verifies that the text is sent correctly and that the sketches and images are in the supported formats (JPEG, PNG, etc.).

[1435] Step 3:

[1436] The server analyzes the received text data using natural language processing (NLP) technology, specifically extracting keywords such as "simple," "modern," and "logo" from the text.

[1437] Step 4:

[1438] The server analyzes the received sketches and images using computer vision technology, specifically recognizing the shape of the sketch and extracting features such as the color and pattern of the image.

[1439] Step 5:

[1440] The emotion engine analyzes the emotional data provided by the user, specifically identifying emotions such as "satisfied," "excited," or "calm" based on information gleaned from the user's voice and facial expressions.

[1441] Step 6:

[1442] The server then formats the analysis results as input data for generating multiple design proposals. It creates design prompts by integrating the text analysis results, features of sketches and images, and emotion data.

[1443] Step 7:

[1444] The server uses a generative AI model to generate design proposals. The generation process takes into account the interpreted user request as well as emotional data. For example, if the user is feeling "relaxed," the server will suggest color schemes and design elements that reflect that emotion.

[1445] Step 8:

[1446] The server evaluates the generated design proposals and scores them based on the evaluation criteria to determine which design proposal best suits the user's needs and emotions. Emotional data is also taken into account as an evaluation criterion.

[1447] Step 9:

[1448] The server then optimizes the design proposals with the highest scores based on the evaluation results, which includes adjusting color tones and optimizing the layout.

[1449] Step 10:

[1450] The server then formats the optimized design into its final form, and the resulting design, formatted as a high-resolution image, is sent to the user's device.

[1451] Step 11:

[1452] The user can check the design proposal sent to them on their device. They can then enter feedback or corrections they would like to make and send it back to the server. The server will receive this and make any necessary corrections.

[1453] These steps allow users to quickly receive high-quality design proposals that reflect their emotions, improving the quality and fit of the design, supporting creativity and streamlining work.

[1454] Example 2

[1455] 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."

[1456] Conventional design generation systems lacked a means to provide design proposals that reflected the user's emotions, making it difficult to increase user satisfaction. Furthermore, there was a lack of a system that could accurately analyze the user's needs and emotions and quickly generate and provide optimal design proposals in response. This meant that users could not obtain designs that accurately reflected their requirements, and the process of providing feedback and making corrections was time-consuming.

[1457] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1458] In this invention, the server includes means for receiving user input, means for analyzing the received user input, means for recognizing and analyzing user emotion data, means for generating multiple design proposals based on the analysis results and the emotion data, means for evaluating and optimizing the generated design proposals, and means for providing the optimized design proposals to the user terminal, thereby enabling the rapid provision of high-quality design proposals that reflect the user's emotions.

[1459] "User Input" means text, sketches, images, and other information provided by a user.

[1460] "Means for receiving" refers to the functionality by which the server receives user input.

[1461] "Means of analysis" refers to technology for analyzing the content of user input and extracting keywords and features.

[1462] "Emotional data" refers to emotional information recognized and analyzed from the user's voice, facial expressions, etc.

[1463] "Means for recognizing and analyzing emotional data" refers to the ability to identify a user's emotions using an emotion engine.

[1464] "Design Proposals" refers to multiple design proposals generated based on the analysis results and emotion data.

[1465] "Means for generating" refers to the functionality for generating multiple design alternatives using a generative AI model.

[1466] "Means for evaluation and optimization" refers to the function of evaluating the generated design proposals, selecting the proposal that best suits the user's requirements and emotions, and fine-tuning it.

[1467] "Means of providing" refers to the function for sending optimized design proposals to the user's terminal.

[1468] "User Terminal" means the electronic device used by a User to submit input and receive design suggestions.

[1469] "Natural language processing" refers to the technology of analyzing a user's text input and extracting keywords and meaning.

[1470] "Computer vision algorithms" refers to techniques for analyzing the features of sketches and images.

[1471] "Generative AI model" refers to an artificial intelligence model that generates design ideas based on user input and emotional data.

[1472] A "prompt" refers to an instruction that a generative AI model uses to generate design proposals.

[1473] Program Generation and Explanation

[1474] The system of this invention is designed to generate innovative design concepts based on user input. The system incorporates an emotion engine that recognizes the user's emotions and can propose design proposals that reflect the user's emotional state.

[1475] Hardware and software used

[1476] The system mainly uses the following hardware and software:

[1477] Server: Responsible for receiving data, analyzing it, and running generative AI models. Specifically, it utilizes AWS computing resources.

[1478] Device: The user sends input data and receives the generated design proposals. A standard computer or smartphone is used.

[1479] Natural Language Processing (NLP) techniques: Use TensorFlow to parse text input.

[1480] Computer Vision Techniques: Use OpenCV to analyze sketches and images.

[1481] Emotion Engine: Uses Google Cloud AutoML to analyze the user's voice and facial expressions.

[1482] Generative AI model: We use OpenAI's GPT-3 to generate design ideas.

[1483] Evaluation and optimization: We use scikit-learn and Photoshop APIs to evaluate and optimize the generated design solutions.

[1484] Data processing and calculation

[1485] 1. Receiving User Input

[1486] Users upload text, sketches, images, and emotional data, including voice and facial expressions, from their devices to the server.

[1487] 2. Data storage

[1488] The server stores the received data in AWS S3 or RDS.

[1489] 3. Data Analysis

[1490] The server uses NLP technology (TensorFlow) to analyze text and extract keywords, and computer vision technology (OpenCV) to extract features from sketches and images.

[1491] 4. Emotion Data Analysis

[1492] The emotion engine (Google Cloud AutoML) analyzes user emotion data and recognizes specific emotional states.

[1493] 5. Generate design proposals

[1494] Based on the above analysis results, the server generates multiple design proposals using a generative AI model (OpenAI's GPT-3).

[1495] 6. Evaluate and optimize design ideas

[1496] The server evaluates the generated design proposals, performs scoring using scikit-learn, and then optimizes the proposals using the Photoshop API.

[1497] 7. Providing design proposals

[1498] The optimized design is sent to the user's device, where the user can review it and provide feedback if necessary.

[1499] Examples of specific examples and prompts

[1500] For example, if a user needs a logo for a new cafe, the system might do the following:

[1501] 1. Providing User Input

[1502] Users upload text such as "I want a nature-themed, relaxing logo," a simple sketch, and a specific color scheme image from their device to the server, and the emotion engine recognizes that the user is relaxing.

[1503] 2. Data Analysis

[1504] The server extracts keywords such as "nature," "relaxation," and "logo" from the text and analyzes sketches and color scheme images.

[1505] 3. Emotion Data Analysis

[1506] The emotion engine identifies the user's emotion as "relaxed."

[1507] 4. Generate design proposals

[1508] Based on the analysis results and emotion data, the server uses a generative AI model to generate multiple logo designs, such as a nature-themed logo using muted shades of green and blue.

[1509] 5. Evaluate and optimize design ideas

[1510] The server evaluates each logo design and selects the design that best matches the user's needs and emotions, then adjusts the color and shape.

[1511] 6. Providing design proposals

[1512] The server sends the optimized logo design to the device.

[1513] Prompt Sentence Examples

[1514] "I'd like to create a new logo for my cafe. I'd like the theme to be nature-themed and relaxing. I'd like it to have a green and blue color scheme as the base."

[1515] This system allows users to quickly obtain high-quality design proposals that reflect their own emotions.

[1516] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1517] Step 1: Providing User Input

[1518] ----

[1519] The user uses the device to provide text, sketches, images, and emotion data to the server. For example, the user can type, "I want a nature-themed relaxing logo," and upload related sketches and color scheme images. The emotion engine then recognizes that the user is relaxed based on their voice and facial expression.

[1520] Input: Text (e.g., "Relaxing nature-themed logos"), sketches, images, audio, facial expressions

[1521] Output: Data provided to the server

[1522] Step 2: Receiving and storing data

[1523] ----

[1524] The server receives input data sent by the user, saves images and sketches to AWS S3, and saves text data to RDS.

[1525] Input: User-submitted text, sketches, images, voice, and facial expressions

[1526] Output: User input information stored in a database

[1527] Step 3: Analyzing the text data

[1528] ----

[1529] The server uses NLP (Natural Language Processing) technology to analyze the text data with TensorFlow and extract keywords, such as "nature," "relax," and "logo."

[1530] Input: Saved text data

[1531] Output: Extracted keywords (e.g., "nature," "relax," "logo")

[1532] Step 4: Analyzing the image data

[1533] ----

[1534] The server uses computer vision technology to analyze the shape and features of sketches and images using OpenCV, specifically analyzing hue, brightness, shape, etc.

[1535] Input: Saved sketches and image data

[1536] Output: Analyzed image feature information (shape, color, etc.)

[1537] Step 5: Analyze the sentiment data

[1538] ----

[1539] The emotion engine uses Google Cloud AutoML to analyze emotions from the user's voice and facial expressions and identify specific emotional states such as "relaxed."

[1540] Input: Stored voice data and facial expression data

[1541] Output: Analyzed emotion information (e.g., "Relaxed")

[1542] Step 6: Generate design ideas

[1543] ----

[1544] Based on the analysis results and emotion data, the server uses a generative AI model (OpenAI's GPT-3) to generate multiple design proposals. For example, it proposes a logo design based on green and blue tones based on the relaxed emotion.

[1545] Input: extracted keywords, analyzed image feature information, analyzed emotion information

[1546] Output: Multiple design proposals generated

[1547] Step 7: Evaluate and optimize design alternatives

[1548] ----

[1549] The server evaluates the generated design proposals, scores them using scikit-learn, and selects the one that best suits the user's needs and emotions. It then optimizes the design proposals by adjusting color, shape, etc. using the Photoshop API.

[1550] Input: Multiple generated design ideas

[1551] Output: Optimized design proposal

[1552] Step 8: Submit a design proposal

[1553] ----

[1554] The server sends the optimized design proposal to the user's device. The user checks the design proposal on the device and sends feedback to the server if necessary. The server then makes further revisions based on this feedback.

[1555] Input: Optimized design proposal

[1556] Output: Design proposals provided to users, and suggested revisions based on their feedback

[1557] (Application example 2)

[1558] 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."

[1559] Conventional design generation systems were unable to reflect the user's emotions in the design proposal, making it difficult to propose optimal designs that matched the user's psychological state and preferences. Furthermore, there was a lack of a way to visually confirm how the generated design proposal would be applied to the actual space, making it difficult to increase user satisfaction.

[1560] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1561] In this invention, the server includes means for receiving user input, means for analyzing the received user input and emotional data, means for generating multiple design proposals based on the analysis results and the user's emotional data, means for evaluating and optimizing the generated design proposals, and means for displaying the optimized design proposals on the user terminal using augmented reality technology. This makes it possible to generate design proposals that reflect the user's emotions and also makes it easy to visually confirm them in real space, thereby improving user satisfaction.

[1562] "User input" refers to information such as text, sketches, or images provided by a user to the system.

[1563] "Emotional data" refers to information about the psychological state analyzed based on voice and facial expressions obtained from the user.

[1564] "Natural language processing" refers to the technology that allows computers to understand and analyze natural human language.

[1565] "Computer vision algorithms" refer to algorithms used to analyze and understand visual data such as images and videos.

[1566] "Augmented reality technology" refers to technology that overlays digital information onto the real world.

[1567] "Design Proposal" refers to a design proposal generated based on user input and emotional data.

[1568] "User terminal" refers to a device operated by a user, such as a smartphone or head-mounted display.

[1569] Overall system configuration

[1570] The system is comprised of three main components: a server, a user device, and the user. The server acts as a central control unit, responsible for complex data analysis and generative AI model execution. The user device is a device used by the user to provide input and receive design proposals, and can include a smartphone or head-mounted display. Furthermore, it incorporates an emotion engine, capable of recognizing and analyzing user emotions.

[1571] Hardware and software used

[1572] Hardware: Smartphone, head-mounted display, camera, microphone

[1573] Software: Natural Language Processing (NLP) algorithms, computer vision algorithms, generative AI models, emotion recognition engines, and augmented reality (AR) display software

[1574] Program processing

[1575] The server receives user input and analyzes it using the emotion engine. The received user input includes text, sketches, and images, and is analyzed using natural language processing and computer vision technologies. The emotion engine also analyzes and recognizes emotional data from the user's voice and facial expressions. This input data and emotional data are integrated and multiple design proposals are generated using a generative AI model.

[1576] The generated design proposals are evaluated on the server, and the proposal that best suits the user's requirements and emotions is selected. Emotional data is also taken into account in the evaluation criteria, and the design proposal that best matches the user's emotions is optimized. The optimized design proposal is displayed on the user's device using augmented reality technology, allowing the user to view and evaluate it.

[1577] Specific examples

[1578] For example, here's how the system works if a brick-and-mortar cafe owner wants a new interior design.

[1579] 1. Providing user input:

[1580] A cafe owner launches the smartphone app and uploads text information such as "I want a natural cafe atmosphere," along with hand-drawn sketches and images of examples of cafe interiors with plenty of greenery. The emotion engine then recognizes that the cafe owner is relaxed.

[1581] 2. Data Analysis:

[1582] The server uses NLP to extract keywords such as "nature," "cafe," and "relaxation" from the text information, and analyzes the shape of the sketch and the color scheme of the image using computer vision technology.

[1583] 3. Emotional Data Analysis:

[1584] Emotional data is derived using a camera and microphone to identify the user's sense of relaxation.

[1585] 4. Design generation and evaluation:

[1586] The generative AI model generates multiple design proposals based on this data, and the server selects and optimizes the most suitable design proposal, taking into account emotional data. For example, it generates a design for a nature-themed cafe interior using calming colors such as green and blue.

[1587] 5. Submit design proposal:

[1588] Using augmented reality technology, the optimized design proposals are displayed to the user in real time through a head-mounted display, allowing the owner to see what the proposed design will look like while walking through the store.

[1589] Prompt Sentence Examples

[1590] "Please propose a new layout that evokes a natural cafe atmosphere in a chalk art style. Users will feel relaxed."

[1591] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1592] Step 1:

[1593] Providing User Input

[1594] Users access the system using a smartphone or head-mounted display to upload text, sketches, and images, while the emotion engine reads the user's voice and facial expressions through a camera and microphone to collect emotional data.

[1595] Input: Text (e.g., a natural cafe atmosphere is desired), sketch image, interior image, emotional data (voice, facial expression)

[1596] Output: User input and emotion data sent to the server

[1597] Step 2:

[1598] Data analysis

[1599] The server analyzes the received user input, using natural language processing (NLP) techniques to extract keywords from the text and computer vision algorithms to extract features from sketches and images.

[1600] Input: Text received from the user, sketch image, interior image

[1601] Output: Text analysis results (keywords), image analysis results (shape and color features)

[1602] Step 3:

[1603] Emotional Data Analysis

[1604] The emotion engine analyzes the user's voice and facial expressions to identify the user's emotions, for example, determining that the user is relaxed.

[1605] Input: User's voice data, facial expression data

[1606] Output: User's emotional state (e.g., relaxed)

[1607] Step 4:

[1608] Generate design ideas

[1609] The server uses a generative AI model to generate multiple design proposals based on the analysis results and user emotion data. The system generates designs based on design prompts that reflect the user's emotions and keywords.

[1610] Input: Text analysis results (keywords), image analysis results (shape and color features), emotional state (relaxed)

[1611] Output: Multiple design ideas

[1612] Step 5:

[1613] Evaluating and optimizing design alternatives

[1614] The server evaluates the generated design proposals and selects the one that best suits the user's emotions and requests. Since the evaluation criteria also include emotional data, design proposals that match the user's emotions are highly rated. The optimal design proposal is selected and fine-tuned.

[1615] Input: Multiple design options, user emotional state

[1616] Output: Optimized design proposal

[1617] Step 6:

[1618] Displaying design ideas

[1619] The optimized design proposals are displayed on the user's device using augmented reality technology, allowing the user to view the proposed design in real time via a head-mounted display or smartphone.

[1620] Input: Optimized design proposal

[1621] Output: Design proposal displayed using augmented reality technology

[1622] 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.

[1623] 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.

[1624] 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.

[1625] 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.

[1626] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1627] 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.

[1628] 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).

[1629] 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.

[1630] 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."

[1631] 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.

[1632] 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).

[1633] 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.

[1634] 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.

[1635] 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.

[1636] 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.

[1637] 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.

[1638] 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.

[1639] 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.

[1640] 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.

[1641] 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.

[1642] 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.

[1643] The following is further disclosed regarding the above embodiment.

[1644] (Claim 1)

[1645] means for receiving user input;

[1646] means for parsing received user input;

[1647] a means for generating a plurality of design proposals based on the analysis results;

[1648] A means for evaluating and optimizing the generated design proposals;

[1649] A means for providing optimized design proposals to user devices;

[1650] A system including:

[1651] (Claim 2)

[1652] 10. The system of claim 1, wherein the user input comprises one of text, a sketch, and an image.

[1653] (Claim 3)

[1654] 10. The system of claim 1, wherein the analysis means includes natural language processing and computer vision algorithms.

[1655] "Example 1"

[1656] (Claim 1)

[1657] means for receiving user input;

[1658] a means for storing received user input in a database;

[1659] a means for parsing the stored user input;

[1660] A means for generating multiple design proposals using a generative AI model based on the analysis results;

[1661] A means for evaluating and optimizing the generated design proposals;

[1662] A means for providing optimized design proposals to user devices;

[1663] A system including:

[1664] (Claim 2)

[1665] 10. The system of claim 1, wherein the user input comprises any one of text, a sketch, and an image.

[1666] (Claim 3)

[1667] 10. The system of claim 1, wherein the analysis means includes natural language processing and computer vision algorithms.

[1668] "Application Example 1"

[1669] (Claim 1)

[1670] means for receiving user input;

[1671] means for parsing received user input;

[1672] a means for generating a plurality of design proposals based on the analysis results;

[1673] A means for evaluating and optimizing the generated design proposals;

[1674] A means for providing optimized design proposals to user devices;

[1675] A method to re-optimize the design proposal by reflecting user feedback based on the evaluation results, and

[1676] A system including:

[1677] (Claim 2)

[1678] 10. The system of claim 1, wherein the user input comprises one of text, a sketch, and an image.

[1679] (Claim 3)

[1680] 10. The system of claim 1, wherein the analysis means includes natural language processing and computer vision algorithms.

[1681] "Example 2: Combining Emotion Engines"

[1682] (Claim 1)

[1683] means for receiving user input;

[1684] means for parsing received user input;

[1685] A means for recognizing and analyzing user emotional data;

[1686] A means for generating multiple design proposals based on the analysis results and emotion data;

[1687] A means for evaluating and optimizing the generated design proposals;

[1688] A means for providing optimized design proposals to user devices;

[1689] A system including:

[1690] (Claim 2)

[1691] 10. The system of claim 1, wherein the user input comprises one of text, a sketch, and an image.

[1692] (Claim 3)

[1693] 10. The system of claim 1, wherein the analysis means includes natural language processing and computer vision algorithms.

[1694] "Application example 2 when combining emotion engines"

[1695] (Claim 1)

[1696] means for receiving user input;

[1697] means for analyzing received user input and emotion data;

[1698] A means for generating a plurality of design proposals based on the analysis results and the user's emotion data;

[1699] A means for evaluating and optimizing the generated design proposals;

[1700] a means for displaying the optimized design proposal on a user terminal using augmented reality technology;

[1701] A system including:

[1702] (Claim 2)

[1703] 10. The system of claim 1, wherein the user input comprises one of text, a sketch, and an image.

[1704] (Claim 3)

[1705] 10. The system of claim 1, wherein the analysis means includes natural language processing and computer vision algorithms.

[1706] (Claim 4)

[1707] 10. The system of claim 1, wherein the emotion data is obtained from speech and facial expressions. [Explanation of symbols]

[1708] 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 receiving user input; means for parsing received user input; a means for generating a plurality of design proposals based on the analysis results; A means for evaluating and optimizing the generated design proposals; A means for providing optimized design proposals to user devices; A system including:

2. The system of claim 1 , wherein the user input comprises one of text, a sketch, and an image.

3. 10. The system of claim 1, wherein the analysis means includes natural language processing and computer vision algorithms.

Images