System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving information on a design input from a user terminal; means for analyzing the information on the design and retrieving a related existing design; means for generating a new rough design based on the existing design; and means for transmitting the generated rough design to the 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] When requesting or creating designs for printed materials or promotional materials, creating rough designs is a time-consuming and labor-intensive process. This slows down the design process and often hinders effective marketing activities. Designers, illustrators, and sales professionals in particular face this challenge, creating a need for tools that can efficiently guide new design directions. [Means for solving the problem]

[0005] The present invention is a system that includes a means for receiving design information input from a user terminal, a means for analyzing the design information and searching for related existing designs, a means for generating a new rough design based on the existing design, and a means for transmitting the generated rough design to the user terminal. This allows designers to efficiently obtain new rough designs based on reference designs, significantly shortening the design creation process and enabling more effective design differentiation.

[0006] A "user terminal" is an electronic device used by a user to input and receive information about a design.

[0007] "Design information" is data provided by users in the form of keywords, images, text, etc., to express the concept or intent of a design.

[0008] "Means" refers to a device, equipment, or software for realizing a specific function or role.

[0009] A "means for receiving" is a system component for obtaining data transmitted from a user terminal.

[0010] A "means for analyzing" is a system component that processes received data and converts its contents into an understandable form.

[0011] "Related existing designs" are existing design data that are similar or useful as references and are searched for based on information about the design.

[0012] A "searching means" is a system component that discovers and extracts relevant data from a particular database or storage.

[0013] A "means for generating" is a system component for creating a new rough design based on the received and analyzed design information.

[0014] A "rough design" is a temporary design that expresses the basic design concept and is provided as a preliminary step to the final design.

[0015] The "means for sending" is a system component for sending the newly generated rough design to the user terminal. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is a system for efficiently creating new designs for printed materials and promotional materials, and includes a user terminal, a server, and a means for communicating between them. This system automates the process of inputting design information, generating a new rough design using AI, and providing it to the user again.

[0038] System Overview

[0039] 1. Material input via user terminal

[0040] The user uses a terminal to input information about the design. Specifically, they upload relevant keywords and reference images into an input form. This information is used to communicate the user's desired design concept and theme to the server.

[0041] Example: If a user wants to create a "Flyer for a Summer Beach Festival," they can enter keywords like "beach," "summer," and "festival" and upload a photo of a beach.

[0042] 2. Data transmission

[0043] The information about the design entered by the user is transmitted from the device to the server using a secure protocol (e.g. SSL / TLS) to ensure the data remains confidential.

[0044] 3. Search the design database

[0045] The server analyzes the information about the design it receives and uses that information to search a design database, which stores various past designs, and extracts existing designs that are highly relevant.

[0046] The server analyzes the entered keywords, calculates features from the image, and compares them with designs in the database.

[0047] 4. AI-based rough design generation

[0048] The server uses AI to generate a new rough design based on the related designs it finds. The AI ​​learns the characteristics of the input design and patterns of existing designs, and suggests new design directions.

[0049] Example: Three new flyer designs related to "beach," "summer," and "festival" are generated.

[0050] 5. Rough design proposal

[0051] The server then sends the generated rough design to the user's terminal, again using a secure protocol.

[0052] The user terminal displays the received rough designs, and the user can review them and select the most appropriate design.

[0053] Example: The user can choose the most attractive one from three generated designs.

[0054] In this way, the system efficiently generates and proposes designs, allowing users to receive new design suggestions from AI with almost no effort required, enabling fast and effective design creation.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The user uses the device to input information about the design, specifically by entering keywords into an input form on the device and uploading related images, which are then ready to be sent to the server.

[0058] Step 2:

[0059] The device packages the information about the design entered by the user. The packaged data includes the keywords and images entered by the user. The device then sends this packaged data to the server. A secure communication protocol (e.g., SSL / TLS) is used for transmission.

[0060] Step 3:

[0061] The server receives the design information sent from the device. The received data includes keywords and image files. The server analyzes this information and prepares it for a database search.

[0062] Step 4:

[0063] The server begins analyzing the received data. During the analysis process, keywords are extracted and features are calculated from the image. This allows information about the design to be organized into specific search criteria. Specifically, the frequency of keyword appearance and features such as the color and shape of the image are analyzed.

[0064] Step 5:

[0065] The server searches the design database based on the analyzed information. The design database stores past design data, and the server extracts highly relevant designs. In this process, the similarity of the designs is evaluated based on keywords and feature values.

[0066] Step 6:

[0067] The server collects relevant existing designs as search results and prepares them for input into the AI ​​model, which uses these designs as a means to generate new rough designs.

[0068] Step 7:

[0069] The server runs the generation AI to generate new rough designs. The AI ​​model learns the received keywords and image characteristics and proposes new rough designs incorporating existing design patterns. For example, three flyer designs related to a "summer beach festival" are generated.

[0070] Step 8:

[0071] The server then transmits the generated rough design to the user's terminal, again using a secure communication protocol.

[0072] Step 9:

[0073] The user terminal displays the rough designs received from the server on the user interface, allowing the user to review the multiple rough designs provided and select the most appropriate one.

[0074] Through these steps, the system provides users with efficient and quick design suggestions.

[0075] Example 1

[0076] 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."

[0077] The conventional design creation process required a great deal of time and effort to reflect the user's desired design concept and theme, resulting in inefficiency. Furthermore, when a user inputs design information, there was no established method for securely transmitting this information to a server and automatically generating new designs based on related designs. Therefore, there was a need for a system that would streamline the design creation process and be easy for users to use.

[0078] 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.

[0079] In this invention, the server includes means for receiving design information input from a user terminal, means for transmitting the design information to the server via a secure communication protocol, means for analyzing the design information and searching a design database for related existing designs, means for generating a new rough design based on the existing design using a generative AI model, and means for transmitting the generated rough design to the user terminal. This makes it possible to streamline the design creation process and allows users to obtain their desired design without hassle.

[0080] A "user terminal" is an electronic device used by a user to input information, and includes devices such as personal computers, smartphones, and tablets.

[0081] "Design information" is data that a user inputs to indicate the concept or theme of a desired design, and includes keywords, images, and the like.

[0082] A "secure communication protocol" is a communication method used to maintain the confidentiality and integrity of information when sending and receiving data, and examples include SSL / TLS.

[0083] A "server" is a remote computer system that receives, analyzes, and processes information input from a user terminal, and includes a database and AI model.

[0084] A "design database" is a collection of data that stores various past design information and is used for searching and referencing.

[0085] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning techniques to generate new designs.

[0086] A "rough design" is a preliminary design proposal generated by AI based on the user's requests and themes.

[0087] "Means for receiving" are the hardware and software components necessary to receive information transmitted from a user terminal.

[0088] "Transmitting means" refers to the functionality for sending data to other systems or devices, and the hardware and software components required for this purpose.

[0089] The "analysis means" is a set of algorithms and techniques used to understand the information received and extract relevant data.

[0090] A "search means" is a function for searching information in a database to find related data based on specific conditions.

[0091] The "generating means" is a function that includes various techniques and algorithms used to construct new designs based on received and analyzed data.

[0092] The present invention is a design creation support system including a user terminal, a server, and means for communicating between them. A mode for implementing this system will be described in detail below.

[0093] Material input via user terminal

[0094] Users operate their devices to input design information. Specifically, they upload keywords (e.g., "beach," "summer," "festival") and reference images into a dedicated input form. This information conveys to the server the specific features and theme of the design the user desires.

[0095] Examples:

[0096] If a user wants to create a "flyer for a summer beach festival," they enter keywords such as "beach," "summer," and "festival" and upload a photo of a beach.

[0097] Sending data

[0098] The user device sends information about the input design to the server, encrypting the data using a secure communication protocol (e.g., SSL / TLS) to prevent unauthorized access or data tampering.

[0099] Search the Design Database

[0100] The server analyzes the received design information and searches the design database based on that information. The server first uses a natural language processing (NLP) engine to extract keywords from the text information, and then uses computer vision technology to calculate features from the uploaded image. It then queries the design database based on this information to extract relevant existing designs.

[0101] AI-based rough design generation

[0102] The server uses a generative AI model (e.g., a deep learning algorithm) to generate new rough designs based on existing designs extracted from a design database. This generative AI model then uses pre-trained design patterns and features to propose new design ideas.

[0103] Examples:

[0104] Based on the input keywords "beach," "summer," and "festival," the generative AI model generates three new flyer designs.

[0105] Rough design proposal

[0106] The server then sends the generated rough designs to the user's device, again using a secure communication protocol to send the data securely. The user's device then displays the received rough designs, allowing the user to review them and select the most appropriate design.

[0107] Example prompt sentence:

[0108] Please create a new flyer design related to "beach," "summer," and "festival." Attach the following beach photo as a reference image.

[0109] In this way, the system achieves efficient design generation and proposals, allowing users to quickly and effectively receive new design proposals from the generative AI model with almost no effort required, greatly streamlining design creation.

[0110] Hardware and software used

[0111] User devices: PCs, smartphones, tablets, etc.

[0112] Server: High performance computing system, database server.

[0113] Secure communication protocol: SSL / TLS.

[0114] Analytics engine: Natural language processing (NLP) engine, computer vision technology.

[0115] Generative AI models: Deep learning algorithms and the frameworks they run on (e.g., TensorFlow, PyTorch).

[0116] The present invention can be implemented using such specific configurations and procedures.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1:

[0119] Input via user terminal

[0120] Users operate their devices to input information about the design. Specifically, they upload keywords (e.g., "beach," "summer," "festival") and reference images into an input form. This information represents the concept and theme of the design and becomes input data for the server.

[0121] Input: Keywords and images

[0122] Output: Information about the design sent from the user's device to the server

[0123] Specific operation: The user opens the dedicated application, enters a keyword into the form, clicks the "Upload image" button, and selects an image file.

[0124] Step 2:

[0125] Sending design information

[0126] The user's device sends information about the input design to the server, and the data is encrypted using a secure communication protocol such as SSL / TLS.

[0127] Input: User-entered design information

[0128] Output: Encrypted design information sent to the server

[0129] Specific operation: The terminal converts the input data into JSON format and sends it to the server as an HTTPS request.

[0130] Step 3:

[0131] Design Information Analysis

[0132] The server analyzes the received design information, first using a natural language processing (NLP) engine to extract keywords, and then using computer vision techniques to calculate features from the images.

[0133] Input: Design information sent to the server

[0134] Output: Keywords and image features

[0135] Specific operation: The server analyzes text information using an NLP library and extracts image features using an image analysis API.

[0136] Step 4:

[0137] Search the Design Database

[0138] The server searches a design database based on the analyzed keywords and image features. The database contains various past designs, and the server extracts existing designs that are highly relevant.

[0139] Input: Keywords and image features

[0140] Output: Related existing designs

[0141] Specific operation: The server generates an SQL query and performs a search against the design database.

[0142] Step 5:

[0143] AI-based rough design generation

[0144] The server generates new rough designs based on related designs extracted from a design database using a generative AI model, which uses deep learning to leverage pre-trained design patterns.

[0145] Input: Related existing designs

[0146] Output: New rough design

[0147] Specific operation: The server inputs a prompt into the generative AI model and obtains the generated design images (e.g., three types of flyer designs).

[0148] Step 6:

[0149] Rough design proposal

[0150] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to select the most suitable design.

[0151] Input: Generated rough design

[0152] Output: Rough design displayed on the user's device

[0153] Specific operation: The server sends the design image as an HTTP response, and the device receives it and displays it on the screen.

[0154] (Application example 1)

[0155] 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."

[0156] The traditional advertising design creation process was inefficient, requiring a lot of time and effort for manual design and revision. Furthermore, it was difficult to propose innovative designs that met user needs, limiting the diversity of designs. This resulted in a decrease in advertising effectiveness. Furthermore, there was a need for an advertising design generation system that could be easily used on mobile devices such as smartphones.

[0157] 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.

[0158] In this invention, the server includes a means for receiving design information input from a user terminal, a means for analyzing the design information and searching for related existing designs, a means for generating a new rough design based on the existing design, a means for generating a new advertising design using AI, and a means for transmitting the generated advertising design to the user terminal. This allows a unique advertising design to be efficiently and quickly generated based on keywords and images input by the user, and can be easily viewed on a device such as a smartphone. This significantly reduces the effort required to create advertising designs and increases the diversity of designs.

[0159] A "user terminal" is a device operated by a user, and includes a smartphone, tablet, PC, etc.

[0160] A "server" is a central device for performing processes such as data storage, analysis, generation, and transmission.

[0161] "Design information" refers to information that serves as a guideline for design, such as keywords, images, and concepts that are input by the user from the terminal.

[0162] "Existing designs" are past designs that are already stored in the database.

[0163] A "rough design" is not a final design, but a simple design proposal that comes before it.

[0164] "Means of generating new advertising designs using AI" refers to technology that uses artificial intelligence to create new advertising designs based on user input information and existing designs.

[0165] A "generative AI model" refers to a machine learning model that generates new content based on user input.

[0166] A "prompt" is a text-based instruction given to a generative AI model to guide the AI ​​in generating new content.

[0167] The present invention provides a system that allows users to easily create advertising designs using a user terminal such as a smartphone. This system is configured as follows.

[0168] First, a user inputs information about the design using a user device such as a smartphone. This information includes keywords and reference images that will form the basis of the advertising design. The input information is then sent to the server via a secure protocol (e.g., HTTPS).

[0169] The server first analyzes the information about the design it receives. This analysis includes keyword analysis and image feature calculation. Based on the analysis results, it searches a design database for related existing designs. This design database stores a wide variety of designs that have been accumulated in the past.

[0170] Next, the server uses AI to generate a new rough design based on the existing designs found. A generative AI model is used for this generation. The generative AI model learns the information entered by the user and patterns of existing designs, and suggests new design directions. A prompt is used as input to the generative AI model. An example of a prompt is "Create new design concepts for: 'Summer Beach Festival'. Based on suggestions: ['beach', 'summer', 'festival', 'poster', 'colorful']."

[0171] The newly generated advertising design is then sent to the user's device via a secure protocol. The received advertising design is then displayed on the user's device, allowing the user to confirm the design. This allows the user to quickly obtain a variety of attractive advertising designs.

[0172] The system is built using HTML, CSS, JavaScript, and React.js on the front end, and Python, Node.js, and MongoDB on the back end, and uses OpenAI's GPT-4 as a generative AI model.

[0173] In this way, the present invention allows users to efficiently and quickly generate advertising designs, improving the diversity of designs and enhancing the effectiveness of advertising.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The user inputs design information on a user device such as a smartphone. The user adds specific keywords and reference images to the input form. This input is primarily basic information for deciding on the ad design. For example, if a user wants to create an ad for the "Summer Beach Festival," they would enter keywords such as "beach," "summer," and "festival" along with a photo of a beach. Once this information is entered, the input data is temporarily stored on the device.

[0177] Step 2:

[0178] The user's device sends information about the entered design to the server. This transmission is performed using a secure protocol such as HTTPS (SSL / TLS). The device converts the keywords and image data into an appropriate format (e.g., JSON format) and sends it to the server. The input data is then transferred to the server in a secure manner.

[0179] Step 3:

[0180] The server analyzes the received design information. First, it performs text analysis to extract keywords, and then it performs image analysis to calculate image features. For example, it extracts keywords using a Python natural language processing library (such as NLTK), and calculates image features using a computer vision library such as OpenCV. The results of this analysis are used in the subsequent design search and generation process.

[0181] Step 4:

[0182] The server searches an existing design database based on the analysis results. A database management system such as MongoDB is used for the search. Highly relevant existing designs are extracted from the database. For example, existing design samples that match keywords such as "beach," "summer," and "festival" are output as search results.

[0183] Step 5:

[0184] The server uses a generative AI model to generate a rough draft of a new advertising design based on the existing designs found in the search. For example, OpenAI's GPT-4 is used as the generative AI model. The server generates a prompt based on the analysis results and existing design information and inputs it into the AI ​​model. An example of a prompt is, "Create new design concepts for: 'Summer Beach Festival'. Based on suggestions: ['beach', 'summer', 'festival', 'poster', 'colorful']." The AI ​​model creates a new design proposal based on this prompt.

[0185] Step 6:

[0186] The server sends the new rough design to the user's device, again using a secure protocol (e.g., HTTPS). The rough design is sent as image data or text data. After sending, the user's device receives it and displays it to the user.

[0187] Step 7:

[0188] Users can check the rough designs generated on their device and select the most suitable design. They can then select the most attractive one from the multiple design proposals displayed, and then request further revisions or make a final decision. This allows users to efficiently and quickly obtain high-quality advertising designs.

[0189] 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.

[0190] This invention is a system that analyzes design information entered by the user, uses AI to generate new rough designs, and proposes them to the user. Furthermore, this invention aims to combine it with an emotion engine that recognizes the user's emotions, and propose the optimal rough design based on the user's emotions.

[0191] System configuration

[0192] 1. Material input via user terminal

[0193] The user uses the device to input information about the design. Specifically, they upload related keywords and reference images into an input form. The system also includes an emotion engine that reads the user's emotions from their facial expressions and voice, and acquires the user's emotional information.

[0194] For example, if a user wants to create a "beach party invitation," they can enter keywords such as "beach," "party," and "invitation," and upload a beach image. Also, if the user has a happy expression, their emotional information will be acquired.

[0195] 2. Analysis of user emotions using an emotion engine

[0196] The emotion engine installed in the device analyzes the user's emotions from their facial expressions, voice, and input actions. For example, if the user has a happy expression, the emotion engine will determine that the emotion is "joy."

[0197] 3. Data transmission

[0198] The design information and emotion information entered by the user are transmitted from the device to the server using a secure communication protocol (e.g., SSL / TLS).

[0199] 4. Search the design database

[0200] The server analyzes the received design information and emotional information. Based on the analyzed information, the server searches the design database and extracts related existing designs. Emotional information is considered an important criterion for design selection.

[0201] Example: Search for existing designs related to "beach" and "party," and prioritize brightly colored designs related to "joy."

[0202] 5. AI-based rough design generation

[0203] The server uses AI to generate a new rough design based on the related designs found and the user's emotional information. The AI ​​takes the emotional information into account and combines design elements that best suit the user's emotions.

[0204] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[0205] 6. Rough design proposal

[0206] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design.

[0207] Example: A user generates bright designs and chooses the one that is most appealing.

[0208] The present invention makes it possible to propose designs that take into account the user's emotions, thereby realizing the provision of more personalized designs, thereby improving the efficiency of design creation and increasing user satisfaction.

[0209] The processing flow will be explained below.

[0210] Step 1:

[0211] The user uses the device to input information about the design, specifically, by entering keywords and uploading related images. The emotion engine also obtains emotional information from the user's facial expressions and voice.

[0212] Example: If a user wants to create a "beach party invitation," they can enter keywords such as "beach," "party," and "invitation" and upload a beach image. If the user has a happy expression, the emotion engine will capture that expression as "joy."

[0213] Step 2:

[0214] The device packages the design information and emotional information entered by the user. The packaged data includes keywords, images, and analyzed emotional information. The device then sends this packaged data to the server. A secure communication protocol (e.g., SSL / TLS) is used for transmission.

[0215] Step 3:

[0216] The server receives the design information and emotion information sent from the device. The received data includes keywords, image files, and emotion information. The server analyzes this information and sets search conditions based on it.

[0217] Step 4:

[0218] The server begins analyzing the received data. During the analysis process, keywords are extracted, features are calculated from the image, and emotional information is processed. This allows design information and emotional information to be organized into specific search criteria. Specifically, the frequency of keyword appearance, the color and shape of the image, and the emotional analysis results are analyzed.

[0219] Step 5:

[0220] The server searches the design database based on the search criteria. The design database contains various design data saved in the past, and the server extracts highly relevant designs from this. In the search process, the similarity of designs is evaluated based on keywords, features, and emotional information.

[0221] Example: Search for existing designs related to "beach" and "party," and prioritize brightly colored designs related to "joy."

[0222] Step 6:

[0223] The server collects related existing designs as search results and prepares them for input into the AI ​​model, which then generates new rough designs based on this design data and emotional information.

[0224] Step 7:

[0225] The server runs the generative AI to generate a new rough design. The AI ​​model learns the received keywords, image features, and the user's emotional information, and then combines appropriate design elements to propose a new rough design.

[0226] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[0227] Step 8:

[0228] The server then transmits the generated rough design to the user's terminal, again using a secure communication protocol.

[0229] Step 9:

[0230] The user terminal displays the rough designs received from the server on the user interface, allowing the user to review the multiple rough designs provided and select the most suitable design from among them.

[0231] Example: A user generates bright designs and chooses the one that is most appealing.

[0232] Through these steps, the system provides users with efficient and emotion-based design suggestions.

[0233] Example 2

[0234] 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."

[0235] Conventional design generation systems propose designs without considering the user's emotions, which limits their ability to provide personalized designs. Furthermore, they often fail to accurately reflect the nuances of the design intended by the user, resulting in a decrease in design satisfaction. The present invention aims to solve these problems and provide a system that provides more optimal designs that reflect the user's emotions.

[0236] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving information about a design input from a user terminal, means for analyzing the information about the design and emotions, means for searching for related existing designs based on the analyzed design information and emotion information, means for generating a new rough design based on the existing design and emotion information, and means for transmitting the generated rough design to the user terminal. This makes it possible to provide a personalized design that reflects the user's emotions.

[0237] "User terminal" refers to a device used by a user to input and transmit information about a design.

[0238] "Design-related information" refers to data related to the design, such as keywords, images, and text input by the user.

[0239] "Emotion" refers to the psychological state expressed by the user when entering a design, and includes information obtained primarily through facial expressions and voice analysis.

[0240] An "emotion engine" refers to software or hardware that analyzes a user's facial expressions, voice, and input actions to extract emotional information.

[0241] "Means for receiving" refers to the mechanism by which the server receives information about design and emotional information sent from the user terminal.

[0242] "Means for analyzing" refers to a mechanism that has the function of analyzing received design-related information and emotion information and identifying related designs and emotions.

[0243] "Existing Design" refers to a previously created design stored in the design database.

[0244] "Searching means" refers to a mechanism that has the function of searching a design database for related existing designs based on the analyzed design information and emotional information.

[0245] "Generative AI model" refers to an artificial intelligence model that generates new rough designs based on received design information and emotional information.

[0246] "Means for generating a rough design" refers to the process of using a generative AI model to create a new rough design.

[0247] "Transmission means" refers to the communication protocol or technology used to transmit the generated rough design to the user terminal.

[0248] "Rough design" refers to an early stage design proposal generated based on the user's input information and emotional information.

[0249] This system analyzes design information entered from a user's device, generates new rough designs using a generative AI model, and proposes them to the user. Furthermore, by combining it with an emotion engine, the system aims to propose optimal rough designs based on the user's emotions.

[0250] System configuration

[0251] 1. Material input via user terminal

[0252] Users use their devices to input information about the design. Specifically, they upload related keywords (e.g., beach, party) and reference images. The system also includes an emotion engine that reads emotions from the user's facial expressions and voice, and emotional information is also acquired. The emotion engine uses facial recognition and voice analysis technology to determine the user's emotions in real time.

[0253] 2. Analysis of user emotions using an emotion engine

[0254] The emotion engine installed in the device analyzes the user's emotions from their facial expressions, voice, and input actions. For example, if the user has a happy expression, the emotion engine will determine this as "joy." The analysis results are sent to the server along with the design information.

[0255] 3. Data transmission

[0256] The design information entered by the user and the analyzed emotional information are sent to the server using a secure communication protocol (e.g., SSL / TLS), which prevents information leakage by third parties during data transmission.

[0257] 4. Search the design database

[0258] The server analyzes the received design information and emotion information. Based on the analyzed information, the server searches its internal design database to extract relevant existing designs. Emotion information is an important factor in this search process, and designs that match the user's emotions are preferentially extracted.

[0259] Example: If a user enters information to create a "beach party invitation," the server searches for existing designs related to "beach" and "party," and prioritizes brightly colored designs related to "joy."

[0260] 5. AI-based rough design generation

[0261] The server uses a generative AI model to generate a new rough design based on the searched related designs and analyzed emotional information. The generative AI model reflects the user's emotions and input data and combines optimal design elements to provide the user with the design they desire.

[0262] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[0263] 6. Rough design proposal

[0264] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design.

[0265] Example: The user can choose the most attractive design from the generated bright designs, and can then save or download the design.

[0266] Prompt Sentence Examples

[0267] To create a beach party invitation, enter the following keywords: beach, party, invitation. Also, upload a beach image. The system will take your emotional information into account to suggest the best design.

[0268] This system will enable the provision of personalized designs that take the user's emotions into consideration, which is expected to improve the efficiency of design creation and increase user satisfaction.

[0269] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0270] Step 1:

[0271] The user uses the device to input information about the design. Specifically, they follow prompts and upload relevant keywords (e.g., beach, party) and reference images. The emotion engine then analyzes the user's emotions from their facial expressions and voice. Inputs include keywords, images, facial expressions, and voice. The output is information about the design and emotional information.

[0272] Step 2:

[0273] The emotion engine installed on the device analyzes emotions from the user's facial expressions, voice, and input actions. The emotion engine uses facial recognition and voice analysis technology to determine the user's emotions in real time. Specifically, if the user has a happy expression or voice, the engine will determine this as "joy." The input includes the user's facial expressions and voice. The output is the analyzed emotional information.

[0274] Step 3:

[0275] The user device combines the input design information and analyzed emotion information into packets and sends them to the server using a secure communication protocol (e.g., SSL / TLS). This prevents information leakage by third parties during data transmission. The input includes design information and emotion information. The output is an encrypted data packet.

[0276] Step 4:

[0277] The server analyzes the received design information and emotion information. Based on the analyzed information, the server searches a design database and extracts related existing designs. Emotion information is an important factor in the search. Specifically, keywords such as "beach" and "party" and the emotion tag "joy" are used to preferentially extract related designs with bright colors. The input includes design information and emotion information. The output generates related existing designs.

[0278] Step 5:

[0279] The server uses a generative AI model to generate new rough designs based on the searched related designs and analyzed emotional information. The generative AI model reflects the user's emotions and input data and combines the optimal design elements. Specifically, for the "beach party invitation," three designs containing many bright colors and fun elements are generated. The input includes related designs and emotional information. The output is three new rough designs.

[0280] Step 6:

[0281] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design. The input includes new rough designs. The output is a rough design displayed on the user's device. Specifically, the user can select the most attractive one from the generated bright designs.

[0282] (Application example 2)

[0283] 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."

[0284] Conventional design generation systems simply generate designs based on input information without considering the user's emotions, making it difficult to propose designs that reflect the user's emotions and subtle nuances. Furthermore, they were unable to generate individually customized product pages or advertising banners to enhance the user's desire to purchase. The goal of this system is to solve these problems and provide optimal designs based on the user's emotions and input information.

[0285] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving design-related information and emotion information input from a user terminal, means for analyzing the design-related information and emotion information and searching for related existing designs, and means for generating a new rough design based on the existing design and taking the emotion information into consideration. This makes it possible to generate a personalized rough design that reflects the user's emotions.

[0286] "User terminal" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[0287] "Design information" refers to all information related to the creation of a design, such as keywords entered by the user and images uploaded by the user.

[0288] "Emotion information" refers to data related to emotions acquired from the user's facial expressions, voice, input actions, etc.

[0289] "Existing Designs" refers to previously created designs or reference designs stored in a design database.

[0290] A "rough design" refers to an early design proposal before a detailed design is created.

[0291] "Analysis" refers to the process of evaluating and making sense of received design information and emotional information.

[0292] "Generation" refers to the process of using AI and other technologies to create new designs.

[0293] "Transmit" refers to the act of sending the generated design to a user terminal.

[0294] The system of the present invention comprises the following means.

[0295] 1. Input of design and emotional information via user terminal

[0296] Users input design information using a user device such as a smartphone, tablet, or PC. Specifically, they upload keywords related to the design they want to create and reference images into an input form. The user device is also equipped with an emotion engine that acquires emotional information from the user's facial expressions and voice. This makes it possible to propose designs that reflect the user's emotions.

[0297] Examples:

[0298] When a user creates a "beach party invitation," they enter keywords such as "beach," "party," and "invitation," and upload a beach image. If the user has a happy expression, their emotional information is acquired.

[0299] 2. Sending data from the user device to the server

[0300] The design information and emotion information entered by the user is transmitted to the server using a secure communication protocol (e.g., SSL / TLS), which ensures data protection.

[0301] 3. Data analysis and design generation by the server

[0302] The server analyzes the received design information and emotion information, including the following:

[0303] Keyword Extraction: Analyzes the keywords you enter and extracts key keywords related to your design.

[0304] Calculating features from images: Calculate features from uploaded images and reflect them in the design.

[0305] Emotion information recognition: Emotions are recognized from facial expressions and voice data acquired using an emotion engine.

[0306] Based on this data analysis, the server searches a design database to extract related existing designs. Next, AI is used to generate a new rough design based on the extracted existing designs and emotional information. The software used on the server includes TensorFlow, OpenCV, transformers (Hugging Face), etc. The Stable Diffusion model is used as the generative AI model.

[0307] Example prompt sentence:

[0308] User emotion: Joy. Keywords: beach, party, invitation. Uploaded image content: user_uploaded_image.jpg.

[0309] 4. Rough design proposal

[0310] The generated rough designs are then sent back to the user's device using a secure communication protocol. The user's device displays the received rough designs, allowing the user to select the most suitable design.

[0311] Examples:

[0312] Users can choose from the bright designs generated that appeal to them the most.

[0313] This system makes it possible to propose personalized designs that reflect the user's emotions, improving the efficiency of design creation and user satisfaction.

[0314] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0315] Step 1:

[0316] Users use a user device such as a smartphone, tablet, or PC to input design information and emotional information. This includes uploading keywords related to the design they want to create and reference images, as well as capturing the user's facial expressions and voice. The emotional information is analyzed by an emotion engine installed on the device. The input data consists of keywords, image files, and emotional information (e.g., "joy," "sadness," etc.).

[0317] Step 2:

[0318] The user device sends the input design information and emotion information to the server using a secure communication protocol (e.g., SSL / TLS). The transmitted content includes a keyword list, image data, and emotion data. This ensures data protection and secure transmission.

[0319] Step 3:

[0320] The server analyzes the received design information and emotion information. First, it extracts keywords and identifies the main related keywords. Then it calculates features from the uploaded image using OpenCV. At the same time, it receives the analysis results of the emotion engine in real time and classifies the user's emotion information. The inputs are a keyword list, image data, and emotion data, and the output is the analyzed keywords, feature data, and emotion labels.

[0321] Step 4:

[0322] The server searches the design database based on the analysis results and extracts related existing designs. It then performs a query search on the design database using the extracted keywords, image features, and emotion labels. The input is the analyzed data, and the output is a list of related existing designs.

[0323] Step 5:

[0324] The server uses AI (e.g., a stable diffusion model) to generate a new rough design based on related existing designs and emotional information. The generation process involves generating a prompt that reflects the emotional information and inputting it into the AI ​​model. An example of a prompt is "User's emotion: joy. Keywords: beach, party, invitation. Uploaded image content: user_uploaded_image.jpg." The input is the prompt and the existing design, and the output is image data of the new rough design.

[0325] Step 6:

[0326] The server then sends the generated rough design back to the user's device using a secure communication protocol. The user's device then displays the received rough design, allowing the user to select the most suitable one from the multiple rough designs generated. The input is image data of the rough design, and the output is the design displayed on the user's device.

[0327] 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.

[0328] 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.

[0329] 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.

[0330] [Second embodiment]

[0331] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0332] 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.

[0333] 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).

[0334] 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.

[0335] 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.

[0336] 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).

[0337] 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.

[0338] 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.

[0339] 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.

[0340] 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.

[0341] 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.

[0342] 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."

[0343] This invention is a system for efficiently creating new designs for printed materials and promotional materials, and includes a user terminal, a server, and a means for communicating between them. This system automates the process of inputting design information, generating a new rough design using AI, and providing it to the user again.

[0344] System Overview

[0345] 1. Material input via user terminal

[0346] The user uses a terminal to input information about the design. Specifically, they upload relevant keywords and reference images into an input form. This information is used to communicate the user's desired design concept and theme to the server.

[0347] Example: If a user wants to create a "Flyer for a Summer Beach Festival," they can enter keywords like "beach," "summer," and "festival" and upload a photo of a beach.

[0348] 2. Data transmission

[0349] The information about the design entered by the user is transmitted from the device to the server using a secure protocol (e.g. SSL / TLS) to ensure the data remains confidential.

[0350] 3. Search the design database

[0351] The server analyzes the information about the design it receives and uses that information to search a design database, which stores various past designs, and extracts existing designs that are highly relevant.

[0352] The server analyzes the entered keywords, calculates features from the image, and compares them with designs in the database.

[0353] 4. AI-based rough design generation

[0354] The server uses AI to generate a new rough design based on the related designs it finds. The AI ​​learns the characteristics of the input design and patterns of existing designs, and suggests new design directions.

[0355] Example: Three new flyer designs related to "beach," "summer," and "festival" are generated.

[0356] 5. Rough design proposal

[0357] The server then sends the generated rough design to the user's terminal, again using a secure protocol.

[0358] The user terminal displays the received rough designs, and the user can review them and select the most appropriate design.

[0359] Example: The user can choose the most attractive one from three generated designs.

[0360] In this way, the system efficiently generates and proposes designs, allowing users to receive new design suggestions from AI with almost no effort required, enabling fast and effective design creation.

[0361] The processing flow will be explained below.

[0362] Step 1:

[0363] The user uses the device to input information about the design, specifically by entering keywords into an input form on the device and uploading related images, which are then ready to be sent to the server.

[0364] Step 2:

[0365] The device packages the information about the design entered by the user. The packaged data includes the keywords and images entered by the user. The device then sends this packaged data to the server. A secure communication protocol (e.g., SSL / TLS) is used for transmission.

[0366] Step 3:

[0367] The server receives the design information sent from the device. The received data includes keywords and image files. The server analyzes this information and prepares it for a database search.

[0368] Step 4:

[0369] The server begins analyzing the received data. During the analysis process, keywords are extracted and features are calculated from the image. This allows information about the design to be organized into specific search criteria. Specifically, the frequency of keyword appearance and features such as the color and shape of the image are analyzed.

[0370] Step 5:

[0371] The server searches the design database based on the analyzed information. The design database stores past design data, and the server extracts highly relevant designs. In this process, the similarity of the designs is evaluated based on keywords and feature values.

[0372] Step 6:

[0373] The server collects relevant existing designs as search results and prepares them for input into the AI ​​model, which uses these designs as a means to generate new rough designs.

[0374] Step 7:

[0375] The server runs the generation AI to generate new rough designs. The AI ​​model learns the received keywords and image characteristics and proposes new rough designs incorporating existing design patterns. For example, three flyer designs related to a "summer beach festival" are generated.

[0376] Step 8:

[0377] The server then transmits the generated rough design to the user's terminal, again using a secure communication protocol.

[0378] Step 9:

[0379] The user terminal displays the rough designs received from the server on the user interface, allowing the user to review the multiple rough designs provided and select the most appropriate one.

[0380] Through these steps, the system provides users with efficient and quick design suggestions.

[0381] Example 1

[0382] 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."

[0383] The conventional design creation process required a great deal of time and effort to reflect the user's desired design concept and theme, resulting in inefficiency. Furthermore, when a user inputs design information, there was no established method for securely transmitting this information to a server and automatically generating new designs based on related designs. Therefore, there was a need for a system that would streamline the design creation process and be easy for users to use.

[0384] 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.

[0385] In this invention, the server includes means for receiving design information input from a user terminal, means for transmitting the design information to the server via a secure communication protocol, means for analyzing the design information and searching a design database for related existing designs, means for generating a new rough design based on the existing design using a generative AI model, and means for transmitting the generated rough design to the user terminal. This makes it possible to streamline the design creation process and allows users to obtain their desired design without hassle.

[0386] A "user terminal" is an electronic device used by a user to input information, and includes devices such as personal computers, smartphones, and tablets.

[0387] "Design information" is data that a user inputs to indicate the concept or theme of a desired design, and includes keywords, images, and the like.

[0388] A "secure communication protocol" is a communication method used to maintain the confidentiality and integrity of information when sending and receiving data, and examples include SSL / TLS.

[0389] A "server" is a remote computer system that receives, analyzes, and processes information input from a user terminal, and includes a database and AI model.

[0390] A "design database" is a collection of data that stores various past design information and is used for searching and referencing.

[0391] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning techniques to generate new designs.

[0392] A "rough design" is a preliminary design proposal generated by AI based on the user's requests and themes.

[0393] "Means for receiving" are the hardware and software components necessary to receive information transmitted from a user terminal.

[0394] "Transmitting means" refers to the functionality for sending data to other systems or devices, and the hardware and software components required for this purpose.

[0395] The "analysis means" is a set of algorithms and techniques used to understand the information received and extract relevant data.

[0396] A "search means" is a function for searching information in a database to find related data based on specific conditions.

[0397] The "generating means" is a function that includes various techniques and algorithms used to construct new designs based on received and analyzed data.

[0398] The present invention is a design creation support system including a user terminal, a server, and means for communicating between them. A mode for implementing this system will be described in detail below.

[0399] Material input via user terminal

[0400] Users operate their devices to input design information. Specifically, they upload keywords (e.g., "beach," "summer," "festival") and reference images into a dedicated input form. This information conveys to the server the specific features and theme of the design the user desires.

[0401] Examples:

[0402] If a user wants to create a "flyer for a summer beach festival," they enter keywords such as "beach," "summer," and "festival" and upload a photo of a beach.

[0403] Sending data

[0404] The user device sends information about the input design to the server, encrypting the data using a secure communication protocol (e.g., SSL / TLS) to prevent unauthorized access or data tampering.

[0405] Search the Design Database

[0406] The server analyzes the received design information and searches the design database based on that information. The server first uses a natural language processing (NLP) engine to extract keywords from the text information, and then uses computer vision technology to calculate features from the uploaded image. It then queries the design database based on this information to extract relevant existing designs.

[0407] AI-based rough design generation

[0408] The server uses a generative AI model (e.g., a deep learning algorithm) to generate new rough designs based on existing designs extracted from a design database. This generative AI model then uses pre-trained design patterns and features to propose new design ideas.

[0409] Examples:

[0410] Based on the input keywords "beach," "summer," and "festival," the generative AI model generates three new flyer designs.

[0411] Rough design proposal

[0412] The server then sends the generated rough designs to the user's device, again using a secure communication protocol to send the data securely. The user's device then displays the received rough designs, allowing the user to review them and select the most appropriate design.

[0413] Example prompt sentence:

[0414] Please create a new flyer design related to "beach," "summer," and "festival." Attach the following beach photo as a reference image.

[0415] In this way, the system achieves efficient design generation and proposals, allowing users to quickly and effectively receive new design proposals from the generative AI model with almost no effort required, greatly streamlining design creation.

[0416] Hardware and software used

[0417] User devices: PCs, smartphones, tablets, etc.

[0418] Server: High performance computing system, database server.

[0419] Secure communication protocol: SSL / TLS.

[0420] Analytics engine: Natural language processing (NLP) engine, computer vision technology.

[0421] Generative AI models: Deep learning algorithms and the frameworks they run on (e.g., TensorFlow, PyTorch).

[0422] The present invention can be implemented using such specific configurations and procedures.

[0423] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0424] Step 1:

[0425] Input via user terminal

[0426] Users operate their devices to input information about the design. Specifically, they upload keywords (e.g., "beach," "summer," "festival") and reference images into an input form. This information represents the concept and theme of the design and becomes input data for the server.

[0427] Input: Keywords and images

[0428] Output: Information about the design sent from the user's device to the server

[0429] Specific operation: The user opens the dedicated application, enters a keyword into the form, clicks the "Upload image" button, and selects an image file.

[0430] Step 2:

[0431] Sending design information

[0432] The user's device sends information about the input design to the server, and the data is encrypted using a secure communication protocol such as SSL / TLS.

[0433] Input: User-entered design information

[0434] Output: Encrypted design information sent to the server

[0435] Specific operation: The terminal converts the input data into JSON format and sends it to the server as an HTTPS request.

[0436] Step 3:

[0437] Design Information Analysis

[0438] The server analyzes the received design information, first using a natural language processing (NLP) engine to extract keywords, and then using computer vision techniques to calculate features from the images.

[0439] Input: Design information sent to the server

[0440] Output: Keywords and image features

[0441] Specific operation: The server analyzes text information using an NLP library and extracts image features using an image analysis API.

[0442] Step 4:

[0443] Search the Design Database

[0444] The server searches a design database based on the analyzed keywords and image features. The database contains various past designs, and the server extracts existing designs that are highly relevant.

[0445] Input: Keywords and image features

[0446] Output: Related existing designs

[0447] Specific operation: The server generates an SQL query and performs a search against the design database.

[0448] Step 5:

[0449] AI-based rough design generation

[0450] The server generates new rough designs based on related designs extracted from a design database using a generative AI model, which uses deep learning to leverage pre-trained design patterns.

[0451] Input: Related existing designs

[0452] Output: New rough design

[0453] Specific operation: The server inputs a prompt into the generative AI model and obtains the generated design images (e.g., three types of flyer designs).

[0454] Step 6:

[0455] Rough design proposal

[0456] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to select the most suitable design.

[0457] Input: Generated rough design

[0458] Output: Rough design displayed on the user's device

[0459] Specific operation: The server sends the design image as an HTTP response, and the device receives it and displays it on the screen.

[0460] (Application example 1)

[0461] 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."

[0462] The traditional advertising design creation process was inefficient, requiring a lot of time and effort for manual design and revision. Furthermore, it was difficult to propose innovative designs that met user needs, limiting the diversity of designs. This resulted in a decrease in advertising effectiveness. Furthermore, there was a need for an advertising design generation system that could be easily used on mobile devices such as smartphones.

[0463] 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.

[0464] In this invention, the server includes a means for receiving design information input from a user terminal, a means for analyzing the design information and searching for related existing designs, a means for generating a new rough design based on the existing design, a means for generating a new advertising design using AI, and a means for transmitting the generated advertising design to the user terminal. This allows a unique advertising design to be efficiently and quickly generated based on keywords and images input by the user, and can be easily viewed on a device such as a smartphone. This significantly reduces the effort required to create advertising designs and increases the diversity of designs.

[0465] A "user terminal" is a device operated by a user, and includes a smartphone, tablet, PC, etc.

[0466] A "server" is a central device for performing processes such as data storage, analysis, generation, and transmission.

[0467] "Design information" refers to information that serves as a guideline for design, such as keywords, images, and concepts that are input by the user from the terminal.

[0468] "Existing designs" are past designs that are already stored in the database.

[0469] A "rough design" is not a final design, but a simple design proposal that comes before it.

[0470] "Means of generating new advertising designs using AI" refers to technology that uses artificial intelligence to create new advertising designs based on user input information and existing designs.

[0471] A "generative AI model" refers to a machine learning model that generates new content based on user input.

[0472] A "prompt" is a text-based instruction given to a generative AI model to guide the AI ​​in generating new content.

[0473] The present invention provides a system that allows users to easily create advertising designs using a user terminal such as a smartphone. This system is configured as follows.

[0474] First, a user inputs information about the design using a user device such as a smartphone. This information includes keywords and reference images that will form the basis of the advertising design. The input information is then sent to the server via a secure protocol (e.g., HTTPS).

[0475] The server first analyzes the information about the design it receives. This analysis includes keyword analysis and image feature calculation. Based on the analysis results, it searches a design database for related existing designs. This design database stores a wide variety of designs that have been accumulated in the past.

[0476] Next, the server uses AI to generate a new rough design based on the existing designs found. A generative AI model is used for this generation. The generative AI model learns the information entered by the user and patterns of existing designs, and suggests new design directions. A prompt is used as input to the generative AI model. An example of a prompt is "Create new design concepts for: 'Summer Beach Festival'. Based on suggestions: ['beach', 'summer', 'festival', 'poster', 'colorful']."

[0477] The newly generated advertising design is then sent to the user's device via a secure protocol. The received advertising design is then displayed on the user's device, allowing the user to confirm the design. This allows the user to quickly obtain a variety of attractive advertising designs.

[0478] The system is built using HTML, CSS, JavaScript, and React.js on the front end, and Python, Node.js, and MongoDB on the back end, and uses OpenAI's GPT-4 as a generative AI model.

[0479] In this way, the present invention allows users to efficiently and quickly generate advertising designs, improving the diversity of designs and enhancing the effectiveness of advertising.

[0480] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0481] Step 1:

[0482] The user inputs design information on a user device such as a smartphone. The user adds specific keywords and reference images to the input form. This input is primarily basic information for deciding on the ad design. For example, if a user wants to create an ad for the "Summer Beach Festival," they would enter keywords such as "beach," "summer," and "festival" along with a photo of a beach. Once this information is entered, the input data is temporarily stored on the device.

[0483] Step 2:

[0484] The user's device sends information about the entered design to the server. This transmission is performed using a secure protocol such as HTTPS (SSL / TLS). The device converts the keywords and image data into an appropriate format (e.g., JSON format) and sends it to the server. The input data is then transferred to the server in a secure manner.

[0485] Step 3:

[0486] The server analyzes the received design information. First, it performs text analysis to extract keywords, and then it performs image analysis to calculate image features. For example, it extracts keywords using a Python natural language processing library (such as NLTK), and calculates image features using a computer vision library such as OpenCV. The results of this analysis are used in the subsequent design search and generation process.

[0487] Step 4:

[0488] The server searches an existing design database based on the analysis results. A database management system such as MongoDB is used for the search. Highly relevant existing designs are extracted from the database. For example, existing design samples that match keywords such as "beach," "summer," and "festival" are output as search results.

[0489] Step 5:

[0490] The server uses a generative AI model to generate a rough draft of a new advertising design based on the existing designs found in the search. For example, OpenAI's GPT-4 is used as the generative AI model. The server generates a prompt based on the analysis results and existing design information and inputs it into the AI ​​model. An example of a prompt is, "Create new design concepts for: 'Summer Beach Festival'. Based on suggestions: ['beach', 'summer', 'festival', 'poster', 'colorful']." The AI ​​model creates a new design proposal based on this prompt.

[0491] Step 6:

[0492] The server sends the new rough design to the user's device, again using a secure protocol (e.g., HTTPS). The rough design is sent as image data or text data. After sending, the user's device receives it and displays it to the user.

[0493] Step 7:

[0494] Users can check the rough designs generated on their device and select the most suitable design. They can then select the most attractive one from the multiple design proposals displayed, and then request further revisions or make a final decision. This allows users to efficiently and quickly obtain high-quality advertising designs.

[0495] 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.

[0496] This invention is a system that analyzes design information entered by the user, uses AI to generate new rough designs, and proposes them to the user. Furthermore, this invention aims to combine it with an emotion engine that recognizes the user's emotions, and propose the optimal rough design based on the user's emotions.

[0497] System configuration

[0498] 1. Material input via user terminal

[0499] The user uses the device to input information about the design. Specifically, they upload related keywords and reference images into an input form. The system also includes an emotion engine that reads the user's emotions from their facial expressions and voice, and acquires the user's emotional information.

[0500] For example, if a user wants to create a "beach party invitation," they can enter keywords such as "beach," "party," and "invitation," and upload a beach image. Also, if the user has a happy expression, their emotional information will be acquired.

[0501] 2. Analysis of user emotions using an emotion engine

[0502] The emotion engine installed in the device analyzes the user's emotions from their facial expressions, voice, and input actions. For example, if the user has a happy expression, the emotion engine will determine that the emotion is "joy."

[0503] 3. Data transmission

[0504] The design information and emotion information entered by the user are transmitted from the device to the server using a secure communication protocol (e.g., SSL / TLS).

[0505] 4. Search the design database

[0506] The server analyzes the received design information and emotional information. Based on the analyzed information, the server searches the design database and extracts related existing designs. Emotional information is considered an important criterion for design selection.

[0507] Example: Search for existing designs related to "beach" and "party," and prioritize brightly colored designs related to "joy."

[0508] 5. AI-based rough design generation

[0509] The server uses AI to generate a new rough design based on the related designs found and the user's emotional information. The AI ​​takes the emotional information into account and combines design elements that best suit the user's emotions.

[0510] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[0511] 6. Rough design proposal

[0512] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design.

[0513] Example: A user generates bright designs and chooses the one that is most appealing.

[0514] The present invention makes it possible to propose designs that take into account the user's emotions, thereby realizing the provision of more personalized designs, thereby improving the efficiency of design creation and increasing user satisfaction.

[0515] The processing flow will be explained below.

[0516] Step 1:

[0517] The user uses the device to input information about the design, specifically, by entering keywords and uploading related images. The emotion engine also obtains emotional information from the user's facial expressions and voice.

[0518] Example: If a user wants to create a "beach party invitation," they can enter keywords such as "beach," "party," and "invitation" and upload a beach image. If the user has a happy expression, the emotion engine will capture that expression as "joy."

[0519] Step 2:

[0520] The device packages the design information and emotional information entered by the user. The packaged data includes keywords, images, and analyzed emotional information. The device then sends this packaged data to the server. A secure communication protocol (e.g., SSL / TLS) is used for transmission.

[0521] Step 3:

[0522] The server receives the design information and emotion information sent from the device. The received data includes keywords, image files, and emotion information. The server analyzes this information and sets search conditions based on it.

[0523] Step 4:

[0524] The server begins analyzing the received data. During the analysis process, keywords are extracted, features are calculated from the image, and emotional information is processed. This allows design information and emotional information to be organized into specific search criteria. Specifically, the frequency of keyword appearance, the color and shape of the image, and the emotional analysis results are analyzed.

[0525] Step 5:

[0526] The server searches the design database based on the search criteria. The design database contains various design data saved in the past, and the server extracts highly relevant designs from this. In the search process, the similarity of designs is evaluated based on keywords, features, and emotional information.

[0527] Example: Search for existing designs related to "beach" and "party," and prioritize brightly colored designs related to "joy."

[0528] Step 6:

[0529] The server collects related existing designs as search results and prepares them for input into the AI ​​model, which then generates new rough designs based on this design data and emotional information.

[0530] Step 7:

[0531] The server runs the generative AI to generate a new rough design. The AI ​​model learns the received keywords, image features, and the user's emotional information, and then combines appropriate design elements to propose a new rough design.

[0532] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[0533] Step 8:

[0534] The server then transmits the generated rough design to the user's terminal, again using a secure communication protocol.

[0535] Step 9:

[0536] The user terminal displays the rough designs received from the server on the user interface, allowing the user to review the multiple rough designs provided and select the most suitable design from among them.

[0537] Example: A user generates bright designs and chooses the one that is most appealing.

[0538] Through these steps, the system provides users with efficient and emotion-based design suggestions.

[0539] Example 2

[0540] 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."

[0541] Conventional design generation systems propose designs without considering the user's emotions, which limits their ability to provide personalized designs. Furthermore, they often fail to accurately reflect the nuances of the design intended by the user, resulting in a decrease in design satisfaction. The present invention aims to solve these problems and provide a system that provides more optimal designs that reflect the user's emotions.

[0542] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving information about a design input from a user terminal, means for analyzing the information about the design and emotions, means for searching for related existing designs based on the analyzed design information and emotion information, means for generating a new rough design based on the existing design and emotion information, and means for transmitting the generated rough design to the user terminal. This makes it possible to provide a personalized design that reflects the user's emotions.

[0543] "User terminal" refers to a device used by a user to input and transmit information about a design.

[0544] "Design-related information" refers to data related to the design, such as keywords, images, and text input by the user.

[0545] "Emotion" refers to the psychological state expressed by the user when entering a design, and includes information obtained primarily through facial expressions and voice analysis.

[0546] An "emotion engine" refers to software or hardware that analyzes a user's facial expressions, voice, and input actions to extract emotional information.

[0547] "Means for receiving" refers to the mechanism by which the server receives information about design and emotional information sent from the user terminal.

[0548] "Means for analyzing" refers to a mechanism that has the function of analyzing received design-related information and emotion information and identifying related designs and emotions.

[0549] "Existing Design" refers to a previously created design stored in the design database.

[0550] "Searching means" refers to a mechanism that has the function of searching a design database for related existing designs based on the analyzed design information and emotional information.

[0551] "Generative AI model" refers to an artificial intelligence model that generates new rough designs based on received design information and emotional information.

[0552] "Means for generating a rough design" refers to the process of using a generative AI model to create a new rough design.

[0553] "Transmission means" refers to the communication protocol or technology used to transmit the generated rough design to the user terminal.

[0554] "Rough design" refers to an early stage design proposal generated based on the user's input information and emotional information.

[0555] This system analyzes design information entered from a user's device, generates new rough designs using a generative AI model, and proposes them to the user. Furthermore, by combining it with an emotion engine, the system aims to propose optimal rough designs based on the user's emotions.

[0556] System configuration

[0557] 1. Material input via user terminal

[0558] Users use their devices to input information about the design. Specifically, they upload related keywords (e.g., beach, party) and reference images. The system also includes an emotion engine that reads emotions from the user's facial expressions and voice, and emotional information is also acquired. The emotion engine uses facial recognition and voice analysis technology to determine the user's emotions in real time.

[0559] 2. Analysis of user emotions using an emotion engine

[0560] The emotion engine installed in the device analyzes the user's emotions from their facial expressions, voice, and input actions. For example, if the user has a happy expression, the emotion engine will determine this as "joy." The analysis results are sent to the server along with the design information.

[0561] 3. Data transmission

[0562] The design information entered by the user and the analyzed emotional information are sent to the server using a secure communication protocol (e.g., SSL / TLS), which prevents information leakage by third parties during data transmission.

[0563] 4. Search the design database

[0564] The server analyzes the received design information and emotion information. Based on the analyzed information, the server searches its internal design database to extract relevant existing designs. Emotion information is an important factor in this search process, and designs that match the user's emotions are preferentially extracted.

[0565] Example: If a user enters information to create a "beach party invitation," the server searches for existing designs related to "beach" and "party," and prioritizes brightly colored designs related to "joy."

[0566] 5. AI-based rough design generation

[0567] The server uses a generative AI model to generate a new rough design based on the searched related designs and analyzed emotional information. The generative AI model reflects the user's emotions and input data and combines optimal design elements to provide the user with the design they desire.

[0568] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[0569] 6. Rough design proposal

[0570] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design.

[0571] Example: The user can choose the most attractive design from the generated bright designs, and can then save or download the design.

[0572] Prompt Sentence Examples

[0573] To create a beach party invitation, enter the following keywords: beach, party, invitation. Also, upload a beach image. The system will take your emotional information into account to suggest the best design.

[0574] This system will enable the provision of personalized designs that take the user's emotions into consideration, which is expected to improve the efficiency of design creation and increase user satisfaction.

[0575] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0576] Step 1:

[0577] The user uses the device to input information about the design. Specifically, they follow prompts and upload relevant keywords (e.g., beach, party) and reference images. The emotion engine then analyzes the user's emotions from their facial expressions and voice. Inputs include keywords, images, facial expressions, and voice. The output is information about the design and emotional information.

[0578] Step 2:

[0579] The emotion engine installed on the device analyzes emotions from the user's facial expressions, voice, and input actions. The emotion engine uses facial recognition and voice analysis technology to determine the user's emotions in real time. Specifically, if the user has a happy expression or voice, the engine will determine this as "joy." The input includes the user's facial expressions and voice. The output is the analyzed emotional information.

[0580] Step 3:

[0581] The user device combines the input design information and analyzed emotion information into packets and sends them to the server using a secure communication protocol (e.g., SSL / TLS). This prevents information leakage by third parties during data transmission. The input includes design information and emotion information. The output is an encrypted data packet.

[0582] Step 4:

[0583] The server analyzes the received design information and emotion information. Based on the analyzed information, the server searches a design database and extracts related existing designs. Emotion information is an important factor in the search. Specifically, keywords such as "beach" and "party" and the emotion tag "joy" are used to preferentially extract related designs with bright colors. The input includes design information and emotion information. The output generates related existing designs.

[0584] Step 5:

[0585] The server uses a generative AI model to generate new rough designs based on the searched related designs and analyzed emotional information. The generative AI model reflects the user's emotions and input data and combines the optimal design elements. Specifically, for the "beach party invitation," three designs containing many bright colors and fun elements are generated. The input includes related designs and emotional information. The output is three new rough designs.

[0586] Step 6:

[0587] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design. The input includes new rough designs. The output is a rough design displayed on the user's device. Specifically, the user can select the most attractive one from the generated bright designs.

[0588] (Application example 2)

[0589] 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."

[0590] Conventional design generation systems simply generate designs based on input information without considering the user's emotions, making it difficult to propose designs that reflect the user's emotions and subtle nuances. Furthermore, they were unable to generate individually customized product pages or advertising banners to enhance the user's desire to purchase. The goal of this system is to solve these problems and provide optimal designs based on the user's emotions and input information.

[0591] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving design-related information and emotion information input from a user terminal, means for analyzing the design-related information and emotion information and searching for related existing designs, and means for generating a new rough design based on the existing design and taking the emotion information into consideration. This makes it possible to generate a personalized rough design that reflects the user's emotions.

[0592] "User terminal" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[0593] "Design information" refers to all information related to the creation of a design, such as keywords entered by the user and images uploaded by the user.

[0594] "Emotion information" refers to data related to emotions acquired from the user's facial expressions, voice, input actions, etc.

[0595] "Existing Designs" refers to previously created designs or reference designs stored in a design database.

[0596] A "rough design" refers to an early design proposal before a detailed design is created.

[0597] "Analysis" refers to the process of evaluating and making sense of received design information and emotional information.

[0598] "Generation" refers to the process of using AI and other technologies to create new designs.

[0599] "Transmit" refers to the act of sending the generated design to a user terminal.

[0600] The system of the present invention comprises the following means.

[0601] 1. Input of design and emotional information via user terminal

[0602] Users input design information using a user device such as a smartphone, tablet, or PC. Specifically, they upload keywords related to the design they want to create and reference images into an input form. The user device is also equipped with an emotion engine that acquires emotional information from the user's facial expressions and voice. This makes it possible to propose designs that reflect the user's emotions.

[0603] Examples:

[0604] When a user creates a "beach party invitation," they enter keywords such as "beach," "party," and "invitation," and upload a beach image. If the user has a happy expression, their emotional information is acquired.

[0605] 2. Sending data from the user device to the server

[0606] The design information and emotion information entered by the user is transmitted to the server using a secure communication protocol (e.g., SSL / TLS), which ensures data protection.

[0607] 3. Data analysis and design generation by the server

[0608] The server analyzes the received design information and emotion information, including the following:

[0609] Keyword Extraction: Analyzes the keywords you enter and extracts key keywords related to your design.

[0610] Calculating features from images: Calculate features from uploaded images and reflect them in the design.

[0611] Emotion information recognition: Emotions are recognized from facial expressions and voice data acquired using an emotion engine.

[0612] Based on this data analysis, the server searches a design database to extract related existing designs. Next, AI is used to generate a new rough design based on the extracted existing designs and emotional information. The software used on the server includes TensorFlow, OpenCV, transformers (Hugging Face), etc. The Stable Diffusion model is used as the generative AI model.

[0613] Example prompt sentence:

[0614] User emotion: Joy. Keywords: beach, party, invitation. Uploaded image content: user_uploaded_image.jpg.

[0615] 4. Rough design proposal

[0616] The generated rough designs are then sent back to the user's device using a secure communication protocol. The user's device displays the received rough designs, allowing the user to select the most suitable design.

[0617] Examples:

[0618] Users can choose from the bright designs generated that appeal to them the most.

[0619] This system makes it possible to propose personalized designs that reflect the user's emotions, improving the efficiency of design creation and user satisfaction.

[0620] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0621] Step 1:

[0622] Users use a user device such as a smartphone, tablet, or PC to input design information and emotional information. This includes uploading keywords related to the design they want to create and reference images, as well as capturing the user's facial expressions and voice. The emotional information is analyzed by an emotion engine installed on the device. The input data consists of keywords, image files, and emotional information (e.g., "joy," "sadness," etc.).

[0623] Step 2:

[0624] The user device sends the input design information and emotion information to the server using a secure communication protocol (e.g., SSL / TLS). The transmitted content includes a keyword list, image data, and emotion data. This ensures data protection and secure transmission.

[0625] Step 3:

[0626] The server analyzes the received design information and emotion information. First, it extracts keywords and identifies the main related keywords. Then it calculates features from the uploaded image using OpenCV. At the same time, it receives the analysis results of the emotion engine in real time and classifies the user's emotion information. The inputs are a keyword list, image data, and emotion data, and the output is the analyzed keywords, feature data, and emotion labels.

[0627] Step 4:

[0628] The server searches the design database based on the analysis results and extracts related existing designs. It then performs a query search on the design database using the extracted keywords, image features, and emotion labels. The input is the analyzed data, and the output is a list of related existing designs.

[0629] Step 5:

[0630] The server uses AI (e.g., a stable diffusion model) to generate a new rough design based on related existing designs and emotional information. The generation process involves generating a prompt that reflects the emotional information and inputting it into the AI ​​model. An example of a prompt is "User's emotion: joy. Keywords: beach, party, invitation. Uploaded image content: user_uploaded_image.jpg." The input is the prompt and the existing design, and the output is image data of the new rough design.

[0631] Step 6:

[0632] The server then sends the generated rough design back to the user's device using a secure communication protocol. The user's device then displays the received rough design, allowing the user to select the most suitable one from the multiple rough designs generated. The input is image data of the rough design, and the output is the design displayed on the user's device.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] [Third embodiment]

[0637] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0638] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0639] 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).

[0640] 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.

[0641] 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.

[0642] 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).

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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."

[0649] This invention is a system for efficiently creating new designs for printed materials and promotional materials, and includes a user terminal, a server, and a means for communicating between them. This system automates the process of inputting design information, generating a new rough design using AI, and providing it to the user again.

[0650] System Overview

[0651] 1. Material input via user terminal

[0652] The user uses a terminal to input information about the design. Specifically, they upload relevant keywords and reference images into an input form. This information is used to communicate the user's desired design concept and theme to the server.

[0653] Example: If a user wants to create a "Flyer for a Summer Beach Festival," they can enter keywords like "beach," "summer," and "festival" and upload a photo of a beach.

[0654] 2. Data transmission

[0655] The information about the design entered by the user is transmitted from the device to the server using a secure protocol (e.g. SSL / TLS) to ensure the data remains confidential.

[0656] 3. Search the design database

[0657] The server analyzes the information about the design it receives and uses that information to search a design database, which stores various past designs, and extracts existing designs that are highly relevant.

[0658] The server analyzes the entered keywords, calculates features from the image, and compares them with designs in the database.

[0659] 4. AI-based rough design generation

[0660] The server uses AI to generate a new rough design based on the related designs it finds. The AI ​​learns the characteristics of the input design and patterns of existing designs, and suggests new design directions.

[0661] Example: Three new flyer designs related to "beach," "summer," and "festival" are generated.

[0662] 5. Rough design proposal

[0663] The server then sends the generated rough design to the user's terminal, again using a secure protocol.

[0664] The user terminal displays the received rough designs, and the user can review them and select the most appropriate design.

[0665] Example: The user can choose the most attractive one from three generated designs.

[0666] In this way, the system efficiently generates and proposes designs, allowing users to receive new design suggestions from AI with almost no effort required, enabling fast and effective design creation.

[0667] The processing flow will be explained below.

[0668] Step 1:

[0669] The user uses the device to input information about the design, specifically by entering keywords into an input form on the device and uploading related images, which are then ready to be sent to the server.

[0670] Step 2:

[0671] The device packages the information about the design entered by the user. The packaged data includes the keywords and images entered by the user. The device then sends this packaged data to the server. A secure communication protocol (e.g., SSL / TLS) is used for transmission.

[0672] Step 3:

[0673] The server receives the design information sent from the device. The received data includes keywords and image files. The server analyzes this information and prepares it for a database search.

[0674] Step 4:

[0675] The server begins analyzing the received data. During the analysis process, keywords are extracted and features are calculated from the image. This allows information about the design to be organized into specific search criteria. Specifically, the frequency of keyword appearance and features such as the color and shape of the image are analyzed.

[0676] Step 5:

[0677] The server searches the design database based on the analyzed information. The design database stores past design data, and the server extracts highly relevant designs. In this process, the similarity of the designs is evaluated based on keywords and feature values.

[0678] Step 6:

[0679] The server collects relevant existing designs as search results and prepares them for input into the AI ​​model, which uses these designs as a means to generate new rough designs.

[0680] Step 7:

[0681] The server runs the generation AI to generate new rough designs. The AI ​​model learns the received keywords and image characteristics and proposes new rough designs incorporating existing design patterns. For example, three flyer designs related to a "summer beach festival" are generated.

[0682] Step 8:

[0683] The server then transmits the generated rough design to the user's terminal, again using a secure communication protocol.

[0684] Step 9:

[0685] The user terminal displays the rough designs received from the server on the user interface, allowing the user to review the multiple rough designs provided and select the most appropriate one.

[0686] Through these steps, the system provides users with efficient and quick design suggestions.

[0687] Example 1

[0688] 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."

[0689] The conventional design creation process required a great deal of time and effort to reflect the user's desired design concept and theme, resulting in inefficiency. Furthermore, when a user inputs design information, there was no established method for securely transmitting this information to a server and automatically generating new designs based on related designs. Therefore, there was a need for a system that would streamline the design creation process and be easy for users to use.

[0690] 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.

[0691] In this invention, the server includes means for receiving design information input from a user terminal, means for transmitting the design information to the server via a secure communication protocol, means for analyzing the design information and searching a design database for related existing designs, means for generating a new rough design based on the existing design using a generative AI model, and means for transmitting the generated rough design to the user terminal. This makes it possible to streamline the design creation process and allows users to obtain their desired design without hassle.

[0692] A "user terminal" is an electronic device used by a user to input information, and includes devices such as personal computers, smartphones, and tablets.

[0693] "Design information" is data that a user inputs to indicate the concept or theme of a desired design, and includes keywords, images, and the like.

[0694] A "secure communication protocol" is a communication method used to maintain the confidentiality and integrity of information when sending and receiving data, and examples include SSL / TLS.

[0695] A "server" is a remote computer system that receives, analyzes, and processes information input from a user terminal, and includes a database and AI model.

[0696] A "design database" is a collection of data that stores various past design information and is used for searching and referencing.

[0697] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning techniques to generate new designs.

[0698] A "rough design" is a preliminary design proposal generated by AI based on the user's requests and themes.

[0699] "Means for receiving" are the hardware and software components necessary to receive information transmitted from a user terminal.

[0700] "Transmitting means" refers to the functionality for sending data to other systems or devices, and the hardware and software components required for this purpose.

[0701] The "analysis means" is a set of algorithms and techniques used to understand the information received and extract relevant data.

[0702] A "search means" is a function for searching information in a database to find related data based on specific conditions.

[0703] The "generating means" is a function that includes various techniques and algorithms used to construct new designs based on received and analyzed data.

[0704] The present invention is a design creation support system including a user terminal, a server, and means for communicating between them. A mode for implementing this system will be described in detail below.

[0705] Material input via user terminal

[0706] Users operate their devices to input design information. Specifically, they upload keywords (e.g., "beach," "summer," "festival") and reference images into a dedicated input form. This information conveys to the server the specific features and theme of the design the user desires.

[0707] Examples:

[0708] If a user wants to create a "flyer for a summer beach festival," they enter keywords such as "beach," "summer," and "festival" and upload a photo of a beach.

[0709] Sending data

[0710] The user device sends information about the input design to the server, encrypting the data using a secure communication protocol (e.g., SSL / TLS) to prevent unauthorized access or data tampering.

[0711] Search the Design Database

[0712] The server analyzes the received design information and searches the design database based on that information. The server first uses a natural language processing (NLP) engine to extract keywords from the text information, and then uses computer vision technology to calculate features from the uploaded image. It then queries the design database based on this information to extract relevant existing designs.

[0713] AI-based rough design generation

[0714] The server uses a generative AI model (e.g., a deep learning algorithm) to generate new rough designs based on existing designs extracted from a design database. This generative AI model then uses pre-trained design patterns and features to propose new design ideas.

[0715] Examples:

[0716] Based on the input keywords "beach," "summer," and "festival," the generative AI model generates three new flyer designs.

[0717] Rough design proposal

[0718] The server then sends the generated rough designs to the user's device, again using a secure communication protocol to send the data securely. The user's device then displays the received rough designs, allowing the user to review them and select the most appropriate design.

[0719] Example prompt sentence:

[0720] Please create a new flyer design related to "beach," "summer," and "festival." Attach the following beach photo as a reference image.

[0721] In this way, the system achieves efficient design generation and proposals, allowing users to quickly and effectively receive new design proposals from the generative AI model with almost no effort required, greatly streamlining design creation.

[0722] Hardware and software used

[0723] User devices: PCs, smartphones, tablets, etc.

[0724] Server: High performance computing system, database server.

[0725] Secure communication protocol: SSL / TLS.

[0726] Analytics engine: Natural language processing (NLP) engine, computer vision technology.

[0727] Generative AI models: Deep learning algorithms and the frameworks they run on (e.g., TensorFlow, PyTorch).

[0728] The present invention can be implemented using such specific configurations and procedures.

[0729] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0730] Step 1:

[0731] Input via user terminal

[0732] Users operate their devices to input information about the design. Specifically, they upload keywords (e.g., "beach," "summer," "festival") and reference images into an input form. This information represents the concept and theme of the design and becomes input data for the server.

[0733] Input: Keywords and images

[0734] Output: Information about the design sent from the user's device to the server

[0735] Specific operation: The user opens the dedicated application, enters a keyword into the form, clicks the "Upload image" button, and selects an image file.

[0736] Step 2:

[0737] Sending design information

[0738] The user's device sends information about the input design to the server, and the data is encrypted using a secure communication protocol such as SSL / TLS.

[0739] Input: User-entered design information

[0740] Output: Encrypted design information sent to the server

[0741] Specific operation: The terminal converts the input data into JSON format and sends it to the server as an HTTPS request.

[0742] Step 3:

[0743] Design Information Analysis

[0744] The server analyzes the received design information, first using a natural language processing (NLP) engine to extract keywords, and then using computer vision techniques to calculate features from the images.

[0745] Input: Design information sent to the server

[0746] Output: Keywords and image features

[0747] Specific operation: The server analyzes text information using an NLP library and extracts image features using an image analysis API.

[0748] Step 4:

[0749] Search the Design Database

[0750] The server searches a design database based on the analyzed keywords and image features. The database contains various past designs, and the server extracts existing designs that are highly relevant.

[0751] Input: Keywords and image features

[0752] Output: Related existing designs

[0753] Specific operation: The server generates an SQL query and performs a search against the design database.

[0754] Step 5:

[0755] AI-based rough design generation

[0756] The server generates new rough designs based on related designs extracted from a design database using a generative AI model, which uses deep learning to leverage pre-trained design patterns.

[0757] Input: Related existing designs

[0758] Output: New rough design

[0759] Specific operation: The server inputs a prompt into the generative AI model and obtains the generated design images (e.g., three types of flyer designs).

[0760] Step 6:

[0761] Rough design proposal

[0762] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to select the most suitable design.

[0763] Input: Generated rough design

[0764] Output: Rough design displayed on the user's device

[0765] Specific operation: The server sends the design image as an HTTP response, and the device receives it and displays it on the screen.

[0766] (Application example 1)

[0767] 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."

[0768] The traditional advertising design creation process was inefficient, requiring a lot of time and effort for manual design and revision. Furthermore, it was difficult to propose innovative designs that met user needs, limiting the diversity of designs. This resulted in a decrease in advertising effectiveness. Furthermore, there was a need for an advertising design generation system that could be easily used on mobile devices such as smartphones.

[0769] 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.

[0770] In this invention, the server includes a means for receiving design information input from a user terminal, a means for analyzing the design information and searching for related existing designs, a means for generating a new rough design based on the existing design, a means for generating a new advertising design using AI, and a means for transmitting the generated advertising design to the user terminal. This allows a unique advertising design to be efficiently and quickly generated based on keywords and images input by the user, and can be easily viewed on a device such as a smartphone. This significantly reduces the effort required to create advertising designs and increases the diversity of designs.

[0771] A "user terminal" is a device operated by a user, and includes a smartphone, tablet, PC, etc.

[0772] A "server" is a central device for performing processes such as data storage, analysis, generation, and transmission.

[0773] "Design information" refers to information that serves as a guideline for design, such as keywords, images, and concepts that are input by the user from the terminal.

[0774] "Existing designs" are past designs that are already stored in the database.

[0775] A "rough design" is not a final design, but a simple design proposal that comes before it.

[0776] "Means of generating new advertising designs using AI" refers to technology that uses artificial intelligence to create new advertising designs based on user input information and existing designs.

[0777] A "generative AI model" refers to a machine learning model that generates new content based on user input.

[0778] A "prompt" is a text-based instruction given to a generative AI model to guide the AI ​​in generating new content.

[0779] The present invention provides a system that allows users to easily create advertising designs using a user terminal such as a smartphone. This system is configured as follows.

[0780] First, a user inputs information about the design using a user device such as a smartphone. This information includes keywords and reference images that will form the basis of the advertising design. The input information is then sent to the server via a secure protocol (e.g., HTTPS).

[0781] The server first analyzes the information about the design it receives. This analysis includes keyword analysis and image feature calculation. Based on the analysis results, it searches a design database for related existing designs. This design database stores a wide variety of designs that have been accumulated in the past.

[0782] Next, the server uses AI to generate a new rough design based on the existing designs found. A generative AI model is used for this generation. The generative AI model learns the information entered by the user and patterns of existing designs, and suggests new design directions. A prompt is used as input to the generative AI model. An example of a prompt is "Create new design concepts for: 'Summer Beach Festival'. Based on suggestions: ['beach', 'summer', 'festival', 'poster', 'colorful']."

[0783] The newly generated advertising design is then sent to the user's device via a secure protocol. The received advertising design is then displayed on the user's device, allowing the user to confirm the design. This allows the user to quickly obtain a variety of attractive advertising designs.

[0784] The system is built using HTML, CSS, JavaScript, and React.js on the front end, and Python, Node.js, and MongoDB on the back end, and uses OpenAI's GPT-4 as a generative AI model.

[0785] In this way, the present invention allows users to efficiently and quickly generate advertising designs, improving the diversity of designs and enhancing the effectiveness of advertising.

[0786] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0787] Step 1:

[0788] The user inputs design information on a user device such as a smartphone. The user adds specific keywords and reference images to the input form. This input is primarily basic information for deciding on the ad design. For example, if a user wants to create an ad for the "Summer Beach Festival," they would enter keywords such as "beach," "summer," and "festival" along with a photo of a beach. Once this information is entered, the input data is temporarily stored on the device.

[0789] Step 2:

[0790] The user's device sends information about the entered design to the server. This transmission is performed using a secure protocol such as HTTPS (SSL / TLS). The device converts the keywords and image data into an appropriate format (e.g., JSON format) and sends it to the server. The input data is then transferred to the server in a secure manner.

[0791] Step 3:

[0792] The server analyzes the received design information. First, it performs text analysis to extract keywords, and then it performs image analysis to calculate image features. For example, it extracts keywords using a Python natural language processing library (such as NLTK), and calculates image features using a computer vision library such as OpenCV. The results of this analysis are used in the subsequent design search and generation process.

[0793] Step 4:

[0794] The server searches an existing design database based on the analysis results. A database management system such as MongoDB is used for the search. Highly relevant existing designs are extracted from the database. For example, existing design samples that match keywords such as "beach," "summer," and "festival" are output as search results.

[0795] Step 5:

[0796] The server uses a generative AI model to generate a rough draft of a new advertising design based on the existing designs found in the search. For example, OpenAI's GPT-4 is used as the generative AI model. The server generates a prompt based on the analysis results and existing design information and inputs it into the AI ​​model. An example of a prompt is, "Create new design concepts for: 'Summer Beach Festival'. Based on suggestions: ['beach', 'summer', 'festival', 'poster', 'colorful']." The AI ​​model creates a new design proposal based on this prompt.

[0797] Step 6:

[0798] The server sends the new rough design to the user's device, again using a secure protocol (e.g., HTTPS). The rough design is sent as image data or text data. After sending, the user's device receives it and displays it to the user.

[0799] Step 7:

[0800] Users can check the rough designs generated on their device and select the most suitable design. They can then select the most attractive one from the multiple design proposals displayed, and then request further revisions or make a final decision. This allows users to efficiently and quickly obtain high-quality advertising designs.

[0801] 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.

[0802] This invention is a system that analyzes design information entered by the user, uses AI to generate new rough designs, and proposes them to the user. Furthermore, this invention aims to combine it with an emotion engine that recognizes the user's emotions, and propose the optimal rough design based on the user's emotions.

[0803] System configuration

[0804] 1. Material input via user terminal

[0805] The user uses the device to input information about the design. Specifically, they upload related keywords and reference images into an input form. The system also includes an emotion engine that reads the user's emotions from their facial expressions and voice, and acquires the user's emotional information.

[0806] For example, if a user wants to create a "beach party invitation," they can enter keywords such as "beach," "party," and "invitation," and upload a beach image. Also, if the user has a happy expression, their emotional information will be acquired.

[0807] 2. Analysis of user emotions using an emotion engine

[0808] The emotion engine installed in the device analyzes the user's emotions from their facial expressions, voice, and input actions. For example, if the user has a happy expression, the emotion engine will determine that the emotion is "joy."

[0809] 3. Data transmission

[0810] The design information and emotion information entered by the user are transmitted from the device to the server using a secure communication protocol (e.g., SSL / TLS).

[0811] 4. Search the design database

[0812] The server analyzes the received design information and emotional information. Based on the analyzed information, the server searches the design database and extracts related existing designs. Emotional information is considered an important criterion for design selection.

[0813] Example: Search for existing designs related to "beach" and "party," and prioritize brightly colored designs related to "joy."

[0814] 5. AI-based rough design generation

[0815] The server uses AI to generate a new rough design based on the related designs found and the user's emotional information. The AI ​​takes the emotional information into account and combines design elements that best suit the user's emotions.

[0816] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[0817] 6. Rough design proposal

[0818] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design.

[0819] Example: A user generates bright designs and chooses the one that is most appealing.

[0820] The present invention makes it possible to propose designs that take into account the user's emotions, thereby realizing the provision of more personalized designs, thereby improving the efficiency of design creation and increasing user satisfaction.

[0821] The processing flow will be explained below.

[0822] Step 1:

[0823] The user uses the device to input information about the design, specifically, by entering keywords and uploading related images. The emotion engine also obtains emotional information from the user's facial expressions and voice.

[0824] Example: If a user wants to create a "beach party invitation," they can enter keywords such as "beach," "party," and "invitation" and upload a beach image. If the user has a happy expression, the emotion engine will capture that expression as "joy."

[0825] Step 2:

[0826] The device packages the design information and emotional information entered by the user. The packaged data includes keywords, images, and analyzed emotional information. The device then sends this packaged data to the server. A secure communication protocol (e.g., SSL / TLS) is used for transmission.

[0827] Step 3:

[0828] The server receives the design information and emotion information sent from the device. The received data includes keywords, image files, and emotion information. The server analyzes this information and sets search conditions based on it.

[0829] Step 4:

[0830] The server begins analyzing the received data. During the analysis process, keywords are extracted, features are calculated from the image, and emotional information is processed. This allows design information and emotional information to be organized into specific search criteria. Specifically, the frequency of keyword appearance, the color and shape of the image, and the emotional analysis results are analyzed.

[0831] Step 5:

[0832] The server searches the design database based on the search criteria. The design database contains various design data saved in the past, and the server extracts highly relevant designs from this. In the search process, the similarity of designs is evaluated based on keywords, features, and emotional information.

[0833] Example: Search for existing designs related to "beach" and "party," and prioritize brightly colored designs related to "joy."

[0834] Step 6:

[0835] The server collects related existing designs as search results and prepares them for input into the AI ​​model, which then generates new rough designs based on this design data and emotional information.

[0836] Step 7:

[0837] The server runs the generative AI to generate a new rough design. The AI ​​model learns the received keywords, image features, and the user's emotional information, and then combines appropriate design elements to propose a new rough design.

[0838] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[0839] Step 8:

[0840] The server then transmits the generated rough design to the user's terminal, again using a secure communication protocol.

[0841] Step 9:

[0842] The user terminal displays the rough designs received from the server on the user interface, allowing the user to review the multiple rough designs provided and select the most suitable design from among them.

[0843] Example: A user generates bright designs and chooses the one that is most appealing.

[0844] Through these steps, the system provides users with efficient and emotion-based design suggestions.

[0845] Example 2

[0846] 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."

[0847] Conventional design generation systems propose designs without considering the user's emotions, which limits their ability to provide personalized designs. Furthermore, they often fail to accurately reflect the nuances of the design intended by the user, resulting in a decrease in design satisfaction. The present invention aims to solve these problems and provide a system that provides more optimal designs that reflect the user's emotions.

[0848] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving information about a design input from a user terminal, means for analyzing the information about the design and emotions, means for searching for related existing designs based on the analyzed design information and emotion information, means for generating a new rough design based on the existing design and emotion information, and means for transmitting the generated rough design to the user terminal. This makes it possible to provide a personalized design that reflects the user's emotions.

[0849] "User terminal" refers to a device used by a user to input and transmit information about a design.

[0850] "Design-related information" refers to data related to the design, such as keywords, images, and text input by the user.

[0851] "Emotion" refers to the psychological state expressed by the user when entering a design, and includes information obtained primarily through facial expressions and voice analysis.

[0852] An "emotion engine" refers to software or hardware that analyzes a user's facial expressions, voice, and input actions to extract emotional information.

[0853] "Means for receiving" refers to the mechanism by which the server receives information about design and emotional information sent from the user terminal.

[0854] "Means for analyzing" refers to a mechanism that has the function of analyzing received design-related information and emotion information and identifying related designs and emotions.

[0855] "Existing Design" refers to a previously created design stored in the design database.

[0856] "Searching means" refers to a mechanism that has the function of searching a design database for related existing designs based on the analyzed design information and emotional information.

[0857] "Generative AI model" refers to an artificial intelligence model that generates new rough designs based on received design information and emotional information.

[0858] "Means for generating a rough design" refers to the process of using a generative AI model to create a new rough design.

[0859] "Transmission means" refers to the communication protocol or technology used to transmit the generated rough design to the user terminal.

[0860] "Rough design" refers to an early stage design proposal generated based on the user's input information and emotional information.

[0861] This system analyzes design information entered from a user's device, generates new rough designs using a generative AI model, and proposes them to the user. Furthermore, by combining it with an emotion engine, the system aims to propose optimal rough designs based on the user's emotions.

[0862] System configuration

[0863] 1. Material input via user terminal

[0864] Users use their devices to input information about the design. Specifically, they upload related keywords (e.g., beach, party) and reference images. The system also includes an emotion engine that reads emotions from the user's facial expressions and voice, and emotional information is also acquired. The emotion engine uses facial recognition and voice analysis technology to determine the user's emotions in real time.

[0865] 2. Analysis of user emotions using an emotion engine

[0866] The emotion engine installed in the device analyzes the user's emotions from their facial expressions, voice, and input actions. For example, if the user has a happy expression, the emotion engine will determine this as "joy." The analysis results are sent to the server along with the design information.

[0867] 3. Data transmission

[0868] The design information entered by the user and the analyzed emotional information are sent to the server using a secure communication protocol (e.g., SSL / TLS), which prevents information leakage by third parties during data transmission.

[0869] 4. Search the design database

[0870] The server analyzes the received design information and emotion information. Based on the analyzed information, the server searches its internal design database to extract relevant existing designs. Emotion information is an important factor in this search process, and designs that match the user's emotions are preferentially extracted.

[0871] Example: If a user enters information to create a "beach party invitation," the server searches for existing designs related to "beach" and "party," and prioritizes brightly colored designs related to "joy."

[0872] 5. AI-based rough design generation

[0873] The server uses a generative AI model to generate a new rough design based on the searched related designs and analyzed emotional information. The generative AI model reflects the user's emotions and input data and combines optimal design elements to provide the user with the design they desire.

[0874] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[0875] 6. Rough design proposal

[0876] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design.

[0877] Example: The user can choose the most attractive design from the generated bright designs, and can then save or download the design.

[0878] Prompt Sentence Examples

[0879] To create a beach party invitation, enter the following keywords: beach, party, invitation. Also, upload a beach image. The system will take your emotional information into account to suggest the best design.

[0880] This system will enable the provision of personalized designs that take the user's emotions into consideration, which is expected to improve the efficiency of design creation and increase user satisfaction.

[0881] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0882] Step 1:

[0883] The user uses the device to input information about the design. Specifically, they follow prompts and upload relevant keywords (e.g., beach, party) and reference images. The emotion engine then analyzes the user's emotions from their facial expressions and voice. Inputs include keywords, images, facial expressions, and voice. The output is information about the design and emotional information.

[0884] Step 2:

[0885] The emotion engine installed on the device analyzes emotions from the user's facial expressions, voice, and input actions. The emotion engine uses facial recognition and voice analysis technology to determine the user's emotions in real time. Specifically, if the user has a happy expression or voice, the engine will determine this as "joy." The input includes the user's facial expressions and voice. The output is the analyzed emotional information.

[0886] Step 3:

[0887] The user device combines the input design information and analyzed emotion information into packets and sends them to the server using a secure communication protocol (e.g., SSL / TLS). This prevents information leakage by third parties during data transmission. The input includes design information and emotion information. The output is an encrypted data packet.

[0888] Step 4:

[0889] The server analyzes the received design information and emotion information. Based on the analyzed information, the server searches a design database and extracts related existing designs. Emotion information is an important factor in the search. Specifically, keywords such as "beach" and "party" and the emotion tag "joy" are used to preferentially extract related designs with bright colors. The input includes design information and emotion information. The output generates related existing designs.

[0890] Step 5:

[0891] The server uses a generative AI model to generate new rough designs based on the searched related designs and analyzed emotional information. The generative AI model reflects the user's emotions and input data and combines the optimal design elements. Specifically, for the "beach party invitation," three designs containing many bright colors and fun elements are generated. The input includes related designs and emotional information. The output is three new rough designs.

[0892] Step 6:

[0893] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design. The input includes new rough designs. The output is a rough design displayed on the user's device. Specifically, the user can select the most attractive one from the generated bright designs.

[0894] (Application example 2)

[0895] 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."

[0896] Conventional design generation systems simply generate designs based on input information without considering the user's emotions, making it difficult to propose designs that reflect the user's emotions and subtle nuances. Furthermore, they were unable to generate individually customized product pages or advertising banners to enhance the user's desire to purchase. The goal of this system is to solve these problems and provide optimal designs based on the user's emotions and input information.

[0897] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving design-related information and emotion information input from a user terminal, means for analyzing the design-related information and emotion information and searching for related existing designs, and means for generating a new rough design based on the existing design and taking the emotion information into consideration. This makes it possible to generate a personalized rough design that reflects the user's emotions.

[0898] "User terminal" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[0899] "Design information" refers to all information related to the creation of a design, such as keywords entered by the user and images uploaded by the user.

[0900] "Emotion information" refers to data related to emotions acquired from the user's facial expressions, voice, input actions, etc.

[0901] "Existing Designs" refers to previously created designs or reference designs stored in a design database.

[0902] A "rough design" refers to an early design proposal before a detailed design is created.

[0903] "Analysis" refers to the process of evaluating and making sense of received design information and emotional information.

[0904] "Generation" refers to the process of using AI and other technologies to create new designs.

[0905] "Transmit" refers to the act of sending the generated design to a user terminal.

[0906] The system of the present invention comprises the following means.

[0907] 1. Input of design and emotional information via user terminal

[0908] Users input design information using a user device such as a smartphone, tablet, or PC. Specifically, they upload keywords related to the design they want to create and reference images into an input form. The user device is also equipped with an emotion engine that acquires emotional information from the user's facial expressions and voice. This makes it possible to propose designs that reflect the user's emotions.

[0909] Examples:

[0910] When a user creates a "beach party invitation," they enter keywords such as "beach," "party," and "invitation," and upload a beach image. If the user has a happy expression, their emotional information is acquired.

[0911] 2. Sending data from the user device to the server

[0912] The design information and emotion information entered by the user is transmitted to the server using a secure communication protocol (e.g., SSL / TLS), which ensures data protection.

[0913] 3. Data analysis and design generation by the server

[0914] The server analyzes the received design information and emotion information, including the following:

[0915] Keyword Extraction: Analyzes the keywords you enter and extracts key keywords related to your design.

[0916] Calculating features from images: Calculate features from uploaded images and reflect them in the design.

[0917] Emotion information recognition: Emotions are recognized from facial expressions and voice data acquired using an emotion engine.

[0918] Based on this data analysis, the server searches a design database to extract related existing designs. Next, AI is used to generate a new rough design based on the extracted existing designs and emotional information. The software used on the server includes TensorFlow, OpenCV, transformers (Hugging Face), etc. The Stable Diffusion model is used as the generative AI model.

[0919] Example prompt sentence:

[0920] User emotion: Joy. Keywords: beach, party, invitation. Uploaded image content: user_uploaded_image.jpg.

[0921] 4. Rough design proposal

[0922] The generated rough designs are then sent back to the user's device using a secure communication protocol. The user's device displays the received rough designs, allowing the user to select the most suitable design.

[0923] Examples:

[0924] Users can choose from the bright designs generated that appeal to them the most.

[0925] This system makes it possible to propose personalized designs that reflect the user's emotions, improving the efficiency of design creation and user satisfaction.

[0926] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0927] Step 1:

[0928] Users use a user device such as a smartphone, tablet, or PC to input design information and emotional information. This includes uploading keywords related to the design they want to create and reference images, as well as capturing the user's facial expressions and voice. The emotional information is analyzed by an emotion engine installed on the device. The input data consists of keywords, image files, and emotional information (e.g., "joy," "sadness," etc.).

[0929] Step 2:

[0930] The user device sends the input design information and emotion information to the server using a secure communication protocol (e.g., SSL / TLS). The transmitted content includes a keyword list, image data, and emotion data. This ensures data protection and secure transmission.

[0931] Step 3:

[0932] The server analyzes the received design information and emotion information. First, it extracts keywords and identifies the main related keywords. Then it calculates features from the uploaded image using OpenCV. At the same time, it receives the analysis results of the emotion engine in real time and classifies the user's emotion information. The inputs are a keyword list, image data, and emotion data, and the output is the analyzed keywords, feature data, and emotion labels.

[0933] Step 4:

[0934] The server searches the design database based on the analysis results and extracts related existing designs. It then performs a query search on the design database using the extracted keywords, image features, and emotion labels. The input is the analyzed data, and the output is a list of related existing designs.

[0935] Step 5:

[0936] The server uses AI (e.g., a stable diffusion model) to generate a new rough design based on related existing designs and emotional information. The generation process involves generating a prompt that reflects the emotional information and inputting it into the AI ​​model. An example of a prompt is "User's emotion: joy. Keywords: beach, party, invitation. Uploaded image content: user_uploaded_image.jpg." The input is the prompt and the existing design, and the output is image data of the new rough design.

[0937] Step 6:

[0938] The server then sends the generated rough design back to the user's device using a secure communication protocol. The user's device then displays the received rough design, allowing the user to select the most suitable one from the multiple rough designs generated. The input is image data of the rough design, and the output is the design displayed on the user's device.

[0939] 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.

[0940] 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.

[0941] 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.

[0942] [Fourth embodiment]

[0943] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0944] 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.

[0945] 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).

[0946] 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.

[0947] 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.

[0948] 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).

[0949] 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.

[0950] 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.

[0951] 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.

[0952] 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.

[0953] 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.

[0954] 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.

[0955] 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."

[0956] This invention is a system for efficiently creating new designs for printed materials and promotional materials, and includes a user terminal, a server, and a means for communicating between them. This system automates the process of inputting design information, generating a new rough design using AI, and providing it to the user again.

[0957] System Overview

[0958] 1. Material input via user terminal

[0959] The user uses a terminal to input information about the design. Specifically, they upload relevant keywords and reference images into an input form. This information is used to communicate the user's desired design concept and theme to the server.

[0960] Example: If a user wants to create a "Flyer for a Summer Beach Festival," they can enter keywords like "beach," "summer," and "festival" and upload a photo of a beach.

[0961] 2. Data transmission

[0962] The information about the design entered by the user is transmitted from the device to the server using a secure protocol (e.g. SSL / TLS) to ensure the data remains confidential.

[0963] 3. Search the design database

[0964] The server analyzes the information about the design it receives and uses that information to search a design database, which stores various past designs, and extracts existing designs that are highly relevant.

[0965] The server analyzes the entered keywords, calculates features from the image, and compares them with designs in the database.

[0966] 4. AI-based rough design generation

[0967] The server uses AI to generate a new rough design based on the related designs it finds. The AI ​​learns the characteristics of the input design and patterns of existing designs, and suggests new design directions.

[0968] Example: Three new flyer designs related to "beach," "summer," and "festival" are generated.

[0969] 5. Rough design proposal

[0970] The server then sends the generated rough design to the user's terminal, again using a secure protocol.

[0971] The user terminal displays the received rough designs, and the user can review them and select the most appropriate design.

[0972] Example: The user can choose the most attractive one from three generated designs.

[0973] In this way, the system efficiently generates and proposes designs, allowing users to receive new design suggestions from AI with almost no effort required, enabling fast and effective design creation.

[0974] The processing flow will be explained below.

[0975] Step 1:

[0976] The user uses the device to input information about the design, specifically by entering keywords into an input form on the device and uploading related images, which are then ready to be sent to the server.

[0977] Step 2:

[0978] The device packages the information about the design entered by the user. The packaged data includes the keywords and images entered by the user. The device then sends this packaged data to the server. A secure communication protocol (e.g., SSL / TLS) is used for transmission.

[0979] Step 3:

[0980] The server receives the design information sent from the device. The received data includes keywords and image files. The server analyzes this information and prepares it for a database search.

[0981] Step 4:

[0982] The server begins analyzing the received data. During the analysis process, keywords are extracted and features are calculated from the image. This allows information about the design to be organized into specific search criteria. Specifically, the frequency of keyword appearance and features such as the color and shape of the image are analyzed.

[0983] Step 5:

[0984] The server searches the design database based on the analyzed information. The design database stores past design data, and the server extracts highly relevant designs. In this process, the similarity of the designs is evaluated based on keywords and feature values.

[0985] Step 6:

[0986] The server collects relevant existing designs as search results and prepares them for input into the AI ​​model, which uses these designs as a means to generate new rough designs.

[0987] Step 7:

[0988] The server runs the generation AI to generate new rough designs. The AI ​​model learns the received keywords and image characteristics and proposes new rough designs incorporating existing design patterns. For example, three flyer designs related to a "summer beach festival" are generated.

[0989] Step 8:

[0990] The server then transmits the generated rough design to the user's terminal, again using a secure communication protocol.

[0991] Step 9:

[0992] The user terminal displays the rough designs received from the server on the user interface, allowing the user to review the multiple rough designs provided and select the most appropriate one.

[0993] Through these steps, the system provides users with efficient and quick design suggestions.

[0994] Example 1

[0995] 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."

[0996] The conventional design creation process required a great deal of time and effort to reflect the user's desired design concept and theme, resulting in inefficiency. Furthermore, when a user inputs design information, there was no established method for securely transmitting this information to a server and automatically generating new designs based on related designs. Therefore, there was a need for a system that would streamline the design creation process and be easy for users to use.

[0997] 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.

[0998] In this invention, the server includes means for receiving design information input from a user terminal, means for transmitting the design information to the server via a secure communication protocol, means for analyzing the design information and searching a design database for related existing designs, means for generating a new rough design based on the existing design using a generative AI model, and means for transmitting the generated rough design to the user terminal. This makes it possible to streamline the design creation process and allows users to obtain their desired design without hassle.

[0999] A "user terminal" is an electronic device used by a user to input information, and includes devices such as personal computers, smartphones, and tablets.

[1000] "Design information" is data that a user inputs to indicate the concept or theme of a desired design, and includes keywords, images, and the like.

[1001] A "secure communication protocol" is a communication method used to maintain the confidentiality and integrity of information when sending and receiving data, and examples include SSL / TLS.

[1002] A "server" is a remote computer system that receives, analyzes, and processes information input from a user terminal, and includes a database and AI model.

[1003] A "design database" is a collection of data that stores various past design information and is used for searching and referencing.

[1004] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning techniques to generate new designs.

[1005] A "rough design" is a preliminary design proposal generated by AI based on the user's requests and themes.

[1006] "Means for receiving" are the hardware and software components necessary to receive information transmitted from a user terminal.

[1007] "Transmitting means" refers to the functionality for sending data to other systems or devices, and the hardware and software components required for this purpose.

[1008] The "analysis means" is a set of algorithms and techniques used to understand the information received and extract relevant data.

[1009] A "search means" is a function for searching information in a database to find related data based on specific conditions.

[1010] The "generating means" is a function that includes various techniques and algorithms used to construct new designs based on received and analyzed data.

[1011] The present invention is a design creation support system including a user terminal, a server, and means for communicating between them. A mode for implementing this system will be described in detail below.

[1012] Material input via user terminal

[1013] Users operate their devices to input design information. Specifically, they upload keywords (e.g., "beach," "summer," "festival") and reference images into a dedicated input form. This information conveys to the server the specific features and theme of the design the user desires.

[1014] Examples:

[1015] If a user wants to create a "flyer for a summer beach festival," they enter keywords such as "beach," "summer," and "festival" and upload a photo of a beach.

[1016] Sending data

[1017] The user device sends information about the input design to the server, encrypting the data using a secure communication protocol (e.g., SSL / TLS) to prevent unauthorized access or data tampering.

[1018] Search the Design Database

[1019] The server analyzes the received design information and searches the design database based on that information. The server first uses a natural language processing (NLP) engine to extract keywords from the text information, and then uses computer vision technology to calculate features from the uploaded image. It then queries the design database based on this information to extract relevant existing designs.

[1020] AI-based rough design generation

[1021] The server uses a generative AI model (e.g., a deep learning algorithm) to generate new rough designs based on existing designs extracted from a design database. This generative AI model then uses pre-trained design patterns and features to propose new design ideas.

[1022] Examples:

[1023] Based on the input keywords "beach," "summer," and "festival," the generative AI model generates three new flyer designs.

[1024] Rough design proposal

[1025] The server then sends the generated rough designs to the user's device, again using a secure communication protocol to send the data securely. The user's device then displays the received rough designs, allowing the user to review them and select the most appropriate design.

[1026] Example prompt sentence:

[1027] Please create a new flyer design related to "beach," "summer," and "festival." Attach the following beach photo as a reference image.

[1028] In this way, the system achieves efficient design generation and proposals, allowing users to quickly and effectively receive new design proposals from the generative AI model with almost no effort required, greatly streamlining design creation.

[1029] Hardware and software used

[1030] User devices: PCs, smartphones, tablets, etc.

[1031] Server: High performance computing system, database server.

[1032] Secure communication protocol: SSL / TLS.

[1033] Analytics engine: Natural language processing (NLP) engine, computer vision technology.

[1034] Generative AI models: Deep learning algorithms and the frameworks they run on (e.g., TensorFlow, PyTorch).

[1035] The present invention can be implemented using such specific configurations and procedures.

[1036] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1037] Step 1:

[1038] Input via user terminal

[1039] Users operate their devices to input information about the design. Specifically, they upload keywords (e.g., "beach," "summer," "festival") and reference images into an input form. This information represents the concept and theme of the design and becomes input data for the server.

[1040] Input: Keywords and images

[1041] Output: Information about the design sent from the user's device to the server

[1042] Specific operation: The user opens the dedicated application, enters a keyword into the form, clicks the "Upload image" button, and selects an image file.

[1043] Step 2:

[1044] Sending design information

[1045] The user's device sends information about the input design to the server, and the data is encrypted using a secure communication protocol such as SSL / TLS.

[1046] Input: User-entered design information

[1047] Output: Encrypted design information sent to the server

[1048] Specific operation: The terminal converts the input data into JSON format and sends it to the server as an HTTPS request.

[1049] Step 3:

[1050] Design Information Analysis

[1051] The server analyzes the received design information, first using a natural language processing (NLP) engine to extract keywords, and then using computer vision techniques to calculate features from the images.

[1052] Input: Design information sent to the server

[1053] Output: Keywords and image features

[1054] Specific operation: The server analyzes text information using an NLP library and extracts image features using an image analysis API.

[1055] Step 4:

[1056] Search the Design Database

[1057] The server searches a design database based on the analyzed keywords and image features. The database contains various past designs, and the server extracts existing designs that are highly relevant.

[1058] Input: Keywords and image features

[1059] Output: Related existing designs

[1060] Specific operation: The server generates an SQL query and performs a search against the design database.

[1061] Step 5:

[1062] AI-based rough design generation

[1063] The server generates new rough designs based on related designs extracted from a design database using a generative AI model, which uses deep learning to leverage pre-trained design patterns.

[1064] Input: Related existing designs

[1065] Output: New rough design

[1066] Specific operation: The server inputs a prompt into the generative AI model and obtains the generated design images (e.g., three types of flyer designs).

[1067] Step 6:

[1068] Rough design proposal

[1069] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to select the most suitable design.

[1070] Input: Generated rough design

[1071] Output: Rough design displayed on the user's device

[1072] Specific operation: The server sends the design image as an HTTP response, and the device receives it and displays it on the screen.

[1073] (Application example 1)

[1074] 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."

[1075] The traditional advertising design creation process was inefficient, requiring a lot of time and effort for manual design and revision. Furthermore, it was difficult to propose innovative designs that met user needs, limiting the diversity of designs. This resulted in a decrease in advertising effectiveness. Furthermore, there was a need for an advertising design generation system that could be easily used on mobile devices such as smartphones.

[1076] 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.

[1077] In this invention, the server includes a means for receiving design information input from a user terminal, a means for analyzing the design information and searching for related existing designs, a means for generating a new rough design based on the existing design, a means for generating a new advertising design using AI, and a means for transmitting the generated advertising design to the user terminal. This allows a unique advertising design to be efficiently and quickly generated based on keywords and images input by the user, and can be easily viewed on a device such as a smartphone. This significantly reduces the effort required to create advertising designs and increases the diversity of designs.

[1078] A "user terminal" is a device operated by a user, and includes a smartphone, tablet, PC, etc.

[1079] A "server" is a central device for performing processes such as data storage, analysis, generation, and transmission.

[1080] "Design information" refers to information that serves as a guideline for design, such as keywords, images, and concepts that are input by the user from the terminal.

[1081] "Existing designs" are past designs that are already stored in the database.

[1082] A "rough design" is not a final design, but a simple design proposal that comes before it.

[1083] "Means of generating new advertising designs using AI" refers to technology that uses artificial intelligence to create new advertising designs based on user input information and existing designs.

[1084] A "generative AI model" refers to a machine learning model that generates new content based on user input.

[1085] A "prompt" is a text-based instruction given to a generative AI model to guide the AI ​​in generating new content.

[1086] The present invention provides a system that allows users to easily create advertising designs using a user terminal such as a smartphone. This system is configured as follows.

[1087] First, a user inputs information about the design using a user device such as a smartphone. This information includes keywords and reference images that will form the basis of the advertising design. The input information is then sent to the server via a secure protocol (e.g., HTTPS).

[1088] The server first analyzes the information about the design it receives. This analysis includes keyword analysis and image feature calculation. Based on the analysis results, it searches a design database for related existing designs. This design database stores a wide variety of designs that have been accumulated in the past.

[1089] Next, the server uses AI to generate a new rough design based on the existing designs found. A generative AI model is used for this generation. The generative AI model learns the information entered by the user and patterns of existing designs, and suggests new design directions. A prompt is used as input to the generative AI model. An example of a prompt is "Create new design concepts for: 'Summer Beach Festival'. Based on suggestions: ['beach', 'summer', 'festival', 'poster', 'colorful']."

[1090] The newly generated advertising design is then sent to the user's device via a secure protocol. The received advertising design is then displayed on the user's device, allowing the user to confirm the design. This allows the user to quickly obtain a variety of attractive advertising designs.

[1091] The system is built using HTML, CSS, JavaScript, and React.js on the front end, and Python, Node.js, and MongoDB on the back end, and uses OpenAI's GPT-4 as a generative AI model.

[1092] In this way, the present invention allows users to efficiently and quickly generate advertising designs, improving the diversity of designs and enhancing the effectiveness of advertising.

[1093] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1094] Step 1:

[1095] The user inputs design information on a user device such as a smartphone. The user adds specific keywords and reference images to the input form. This input is primarily basic information for deciding on the ad design. For example, if a user wants to create an ad for the "Summer Beach Festival," they would enter keywords such as "beach," "summer," and "festival" along with a photo of a beach. Once this information is entered, the input data is temporarily stored on the device.

[1096] Step 2:

[1097] The user's device sends information about the entered design to the server. This transmission is performed using a secure protocol such as HTTPS (SSL / TLS). The device converts the keywords and image data into an appropriate format (e.g., JSON format) and sends it to the server. The input data is then transferred to the server in a secure manner.

[1098] Step 3:

[1099] The server analyzes the received design information. First, it performs text analysis to extract keywords, and then it performs image analysis to calculate image features. For example, it extracts keywords using a Python natural language processing library (such as NLTK), and calculates image features using a computer vision library such as OpenCV. The results of this analysis are used in the subsequent design search and generation process.

[1100] Step 4:

[1101] The server searches an existing design database based on the analysis results. A database management system such as MongoDB is used for the search. Highly relevant existing designs are extracted from the database. For example, existing design samples that match keywords such as "beach," "summer," and "festival" are output as search results.

[1102] Step 5:

[1103] The server uses a generative AI model to generate a rough draft of a new advertising design based on the existing designs found in the search. For example, OpenAI's GPT-4 is used as the generative AI model. The server generates a prompt based on the analysis results and existing design information and inputs it into the AI ​​model. An example of a prompt is, "Create new design concepts for: 'Summer Beach Festival'. Based on suggestions: ['beach', 'summer', 'festival', 'poster', 'colorful']." The AI ​​model creates a new design proposal based on this prompt.

[1104] Step 6:

[1105] The server sends the new rough design to the user's device, again using a secure protocol (e.g., HTTPS). The rough design is sent as image data or text data. After sending, the user's device receives it and displays it to the user.

[1106] Step 7:

[1107] Users can check the rough designs generated on their device and select the most suitable design. They can then select the most attractive one from the multiple design proposals displayed, and then request further revisions or make a final decision. This allows users to efficiently and quickly obtain high-quality advertising designs.

[1108] 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.

[1109] This invention is a system that analyzes design information entered by the user, uses AI to generate new rough designs, and proposes them to the user. Furthermore, this invention aims to combine it with an emotion engine that recognizes the user's emotions, and propose the optimal rough design based on the user's emotions.

[1110] System configuration

[1111] 1. Material input via user terminal

[1112] The user uses the device to input information about the design. Specifically, they upload related keywords and reference images into an input form. The system also includes an emotion engine that reads the user's emotions from their facial expressions and voice, and acquires the user's emotional information.

[1113] For example, if a user wants to create a "beach party invitation," they can enter keywords such as "beach," "party," and "invitation," and upload a beach image. Also, if the user has a happy expression, their emotional information will be acquired.

[1114] 2. Analysis of user emotions using an emotion engine

[1115] The emotion engine installed in the device analyzes the user's emotions from their facial expressions, voice, and input actions. For example, if the user has a happy expression, the emotion engine will determine that the emotion is "joy."

[1116] 3. Data transmission

[1117] The design information and emotion information entered by the user are transmitted from the device to the server using a secure communication protocol (e.g., SSL / TLS).

[1118] 4. Search the design database

[1119] The server analyzes the received design information and emotional information. Based on the analyzed information, the server searches the design database and extracts related existing designs. Emotional information is considered an important criterion for design selection.

[1120] Example: Search for existing designs related to "beach" and "party," and prioritize brightly colored designs related to "joy."

[1121] 5. AI-based rough design generation

[1122] The server uses AI to generate a new rough design based on the related designs found and the user's emotional information. The AI ​​takes the emotional information into account and combines design elements that best suit the user's emotions.

[1123] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[1124] 6. Rough design proposal

[1125] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design.

[1126] Example: A user generates bright designs and chooses the one that is most appealing.

[1127] The present invention makes it possible to propose designs that take into account the user's emotions, thereby realizing the provision of more personalized designs, thereby improving the efficiency of design creation and increasing user satisfaction.

[1128] The processing flow will be explained below.

[1129] Step 1:

[1130] The user uses the device to input information about the design, specifically, by entering keywords and uploading related images. The emotion engine also obtains emotional information from the user's facial expressions and voice.

[1131] Example: If a user wants to create a "beach party invitation," they can enter keywords such as "beach," "party," and "invitation" and upload a beach image. If the user has a happy expression, the emotion engine will capture that expression as "joy."

[1132] Step 2:

[1133] The device packages the design information and emotional information entered by the user. The packaged data includes keywords, images, and analyzed emotional information. The device then sends this packaged data to the server. A secure communication protocol (e.g., SSL / TLS) is used for transmission.

[1134] Step 3:

[1135] The server receives the design information and emotion information sent from the device. The received data includes keywords, image files, and emotion information. The server analyzes this information and sets search conditions based on it.

[1136] Step 4:

[1137] The server begins analyzing the received data. During the analysis process, keywords are extracted, features are calculated from the image, and emotional information is processed. This allows design information and emotional information to be organized into specific search criteria. Specifically, the frequency of keyword appearance, the color and shape of the image, and the emotional analysis results are analyzed.

[1138] Step 5:

[1139] The server searches the design database based on the search criteria. The design database contains various design data saved in the past, and the server extracts highly relevant designs from this. In the search process, the similarity of designs is evaluated based on keywords, features, and emotional information.

[1140] Example: Search for existing designs related to "beach" and "party," and prioritize brightly colored designs related to "joy."

[1141] Step 6:

[1142] The server collects related existing designs as search results and prepares them for input into the AI ​​model, which then generates new rough designs based on this design data and emotional information.

[1143] Step 7:

[1144] The server runs the generative AI to generate a new rough design. The AI ​​model learns the received keywords, image features, and the user's emotional information, and then combines appropriate design elements to propose a new rough design.

[1145] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[1146] Step 8:

[1147] The server then transmits the generated rough design to the user's terminal, again using a secure communication protocol.

[1148] Step 9:

[1149] The user terminal displays the rough designs received from the server on the user interface, allowing the user to review the multiple rough designs provided and select the most suitable design from among them.

[1150] Example: A user generates bright designs and chooses the one that is most appealing.

[1151] Through these steps, the system provides users with efficient and emotion-based design suggestions.

[1152] Example 2

[1153] 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."

[1154] Conventional design generation systems propose designs without considering the user's emotions, which limits their ability to provide personalized designs. Furthermore, they often fail to accurately reflect the nuances of the design intended by the user, resulting in a decrease in design satisfaction. The present invention aims to solve these problems and provide a system that provides more optimal designs that reflect the user's emotions.

[1155] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving information about a design input from a user terminal, means for analyzing the information about the design and emotions, means for searching for related existing designs based on the analyzed design information and emotion information, means for generating a new rough design based on the existing design and emotion information, and means for transmitting the generated rough design to the user terminal. This makes it possible to provide a personalized design that reflects the user's emotions.

[1156] "User terminal" refers to a device used by a user to input and transmit information about a design.

[1157] "Design-related information" refers to data related to the design, such as keywords, images, and text input by the user.

[1158] "Emotion" refers to the psychological state expressed by the user when entering a design, and includes information obtained primarily through facial expressions and voice analysis.

[1159] An "emotion engine" refers to software or hardware that analyzes a user's facial expressions, voice, and input actions to extract emotional information.

[1160] "Means for receiving" refers to the mechanism by which the server receives information about design and emotional information sent from the user terminal.

[1161] "Means for analyzing" refers to a mechanism that has the function of analyzing received design-related information and emotion information and identifying related designs and emotions.

[1162] "Existing Design" refers to a previously created design stored in the design database.

[1163] "Searching means" refers to a mechanism that has the function of searching a design database for related existing designs based on the analyzed design information and emotional information.

[1164] "Generative AI model" refers to an artificial intelligence model that generates new rough designs based on received design information and emotional information.

[1165] "Means for generating a rough design" refers to the process of using a generative AI model to create a new rough design.

[1166] "Transmission means" refers to the communication protocol or technology used to transmit the generated rough design to the user terminal.

[1167] "Rough design" refers to an early stage design proposal generated based on the user's input information and emotional information.

[1168] This system analyzes design information entered from a user's device, generates new rough designs using a generative AI model, and proposes them to the user. Furthermore, by combining it with an emotion engine, the system aims to propose optimal rough designs based on the user's emotions.

[1169] System configuration

[1170] 1. Material input via user terminal

[1171] Users use their devices to input information about the design. Specifically, they upload related keywords (e.g., beach, party) and reference images. The system also includes an emotion engine that reads emotions from the user's facial expressions and voice, and emotional information is also acquired. The emotion engine uses facial recognition and voice analysis technology to determine the user's emotions in real time.

[1172] 2. Analysis of user emotions using an emotion engine

[1173] The emotion engine installed in the device analyzes the user's emotions from their facial expressions, voice, and input actions. For example, if the user has a happy expression, the emotion engine will determine this as "joy." The analysis results are sent to the server along with the design information.

[1174] 3. Data transmission

[1175] The design information entered by the user and the analyzed emotional information are sent to the server using a secure communication protocol (e.g., SSL / TLS), which prevents information leakage by third parties during data transmission.

[1176] 4. Search the design database

[1177] The server analyzes the received design information and emotion information. Based on the analyzed information, the server searches its internal design database to extract relevant existing designs. Emotion information is an important factor in this search process, and designs that match the user's emotions are preferentially extracted.

[1178] Example: If a user enters information to create a "beach party invitation," the server searches for existing designs related to "beach" and "party," and prioritizes brightly colored designs related to "joy."

[1179] 5. AI-based rough design generation

[1180] The server uses a generative AI model to generate a new rough design based on the searched related designs and analyzed emotional information. The generative AI model reflects the user's emotions and input data and combines optimal design elements to provide the user with the design they desire.

[1181] Example: Generate three "beach party invitation" designs that contain lots of bright colors and fun elements.

[1182] 6. Rough design proposal

[1183] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design.

[1184] Example: The user can choose the most attractive design from the generated bright designs, and can then save or download the design.

[1185] Prompt Sentence Examples

[1186] To create a beach party invitation, enter the following keywords: beach, party, invitation. Also, upload a beach image. The system will take your emotional information into account to suggest the best design.

[1187] This system will enable the provision of personalized designs that take the user's emotions into consideration, which is expected to improve the efficiency of design creation and increase user satisfaction.

[1188] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1189] Step 1:

[1190] The user uses the device to input information about the design. Specifically, they follow prompts and upload relevant keywords (e.g., beach, party) and reference images. The emotion engine then analyzes the user's emotions from their facial expressions and voice. Inputs include keywords, images, facial expressions, and voice. The output is information about the design and emotional information.

[1191] Step 2:

[1192] The emotion engine installed on the device analyzes emotions from the user's facial expressions, voice, and input actions. The emotion engine uses facial recognition and voice analysis technology to determine the user's emotions in real time. Specifically, if the user has a happy expression or voice, the engine will determine this as "joy." The input includes the user's facial expressions and voice. The output is the analyzed emotional information.

[1193] Step 3:

[1194] The user device combines the input design information and analyzed emotion information into packets and sends them to the server using a secure communication protocol (e.g., SSL / TLS). This prevents information leakage by third parties during data transmission. The input includes design information and emotion information. The output is an encrypted data packet.

[1195] Step 4:

[1196] The server analyzes the received design information and emotion information. Based on the analyzed information, the server searches a design database and extracts related existing designs. Emotion information is an important factor in the search. Specifically, keywords such as "beach" and "party" and the emotion tag "joy" are used to preferentially extract related designs with bright colors. The input includes design information and emotion information. The output generates related existing designs.

[1197] Step 5:

[1198] The server uses a generative AI model to generate new rough designs based on the searched related designs and analyzed emotional information. The generative AI model reflects the user's emotions and input data and combines the optimal design elements. Specifically, for the "beach party invitation," three designs containing many bright colors and fun elements are generated. The input includes related designs and emotional information. The output is three new rough designs.

[1199] Step 6:

[1200] The server then sends the generated rough designs to the user's device, again using a secure communication protocol. The user's device displays the received rough designs, allowing the user to review them and select the most suitable design. The input includes new rough designs. The output is a rough design displayed on the user's device. Specifically, the user can select the most attractive one from the generated bright designs.

[1201] (Application example 2)

[1202] 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."

[1203] Conventional design generation systems simply generate designs based on input information without considering the user's emotions, making it difficult to propose designs that reflect the user's emotions and subtle nuances. Furthermore, they were unable to generate individually customized product pages or advertising banners to enhance the user's desire to purchase. The goal of this system is to solve these problems and provide optimal designs based on the user's emotions and input information.

[1204] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving design-related information and emotion information input from a user terminal, means for analyzing the design-related information and emotion information and searching for related existing designs, and means for generating a new rough design based on the existing design and taking the emotion information into consideration. This makes it possible to generate a personalized rough design that reflects the user's emotions.

[1205] "User terminal" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[1206] "Design information" refers to all information related to the creation of a design, such as keywords entered by the user and images uploaded by the user.

[1207] "Emotion information" refers to data related to emotions acquired from the user's facial expressions, voice, input actions, etc.

[1208] "Existing Designs" refers to previously created designs or reference designs stored in a design database.

[1209] A "rough design" refers to an early design proposal before a detailed design is created.

[1210] "Analysis" refers to the process of evaluating and making sense of received design information and emotional information.

[1211] "Generation" refers to the process of using AI and other technologies to create new designs.

[1212] "Transmit" refers to the act of sending the generated design to a user terminal.

[1213] The system of the present invention comprises the following means.

[1214] 1. Input of design and emotional information via user terminal

[1215] Users input design information using a user device such as a smartphone, tablet, or PC. Specifically, they upload keywords related to the design they want to create and reference images into an input form. The user device is also equipped with an emotion engine that acquires emotional information from the user's facial expressions and voice. This makes it possible to propose designs that reflect the user's emotions.

[1216] Examples:

[1217] When a user creates a "beach party invitation," they enter keywords such as "beach," "party," and "invitation," and upload a beach image. If the user has a happy expression, their emotional information is acquired.

[1218] 2. Sending data from the user device to the server

[1219] The design information and emotion information entered by the user is transmitted to the server using a secure communication protocol (e.g., SSL / TLS), which ensures data protection.

[1220] 3. Data analysis and design generation by the server

[1221] The server analyzes the received design information and emotion information, including the following:

[1222] Keyword Extraction: Analyzes the keywords you enter and extracts key keywords related to your design.

[1223] Calculating features from images: Calculate features from uploaded images and reflect them in the design.

[1224] Emotion information recognition: Emotions are recognized from facial expressions and voice data acquired using an emotion engine.

[1225] Based on this data analysis, the server searches a design database to extract related existing designs. Next, AI is used to generate a new rough design based on the extracted existing designs and emotional information. The software used on the server includes TensorFlow, OpenCV, transformers (Hugging Face), etc. The Stable Diffusion model is used as the generative AI model.

[1226] Example prompt sentence:

[1227] User emotion: Joy. Keywords: beach, party, invitation. Uploaded image content: user_uploaded_image.jpg.

[1228] 4. Rough design proposal

[1229] The generated rough designs are then sent back to the user's device using a secure communication protocol. The user's device displays the received rough designs, allowing the user to select the most suitable design.

[1230] Examples:

[1231] Users can choose from the bright designs generated that appeal to them the most.

[1232] This system makes it possible to propose personalized designs that reflect the user's emotions, improving the efficiency of design creation and user satisfaction.

[1233] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1234] Step 1:

[1235] Users use a user device such as a smartphone, tablet, or PC to input design information and emotional information. This includes uploading keywords related to the design they want to create and reference images, as well as capturing the user's facial expressions and voice. The emotional information is analyzed by an emotion engine installed on the device. The input data consists of keywords, image files, and emotional information (e.g., "joy," "sadness," etc.).

[1236] Step 2:

[1237] The user device sends the input design information and emotion information to the server using a secure communication protocol (e.g., SSL / TLS). The transmitted content includes a keyword list, image data, and emotion data. This ensures data protection and secure transmission.

[1238] Step 3:

[1239] The server analyzes the received design information and emotion information. First, it extracts keywords and identifies the main related keywords. Then it calculates features from the uploaded image using OpenCV. At the same time, it receives the analysis results of the emotion engine in real time and classifies the user's emotion information. The inputs are a keyword list, image data, and emotion data, and the output is the analyzed keywords, feature data, and emotion labels.

[1240] Step 4:

[1241] The server searches the design database based on the analysis results and extracts related existing designs. It then performs a query search on the design database using the extracted keywords, image features, and emotion labels. The input is the analyzed data, and the output is a list of related existing designs.

[1242] Step 5:

[1243] The server uses AI (e.g., a stable diffusion model) to generate a new rough design based on related existing designs and emotional information. The generation process involves generating a prompt that reflects the emotional information and inputting it into the AI ​​model. An example of a prompt is "User's emotion: joy. Keywords: beach, party, invitation. Uploaded image content: user_uploaded_image.jpg." The input is the prompt and the existing design, and the output is image data of the new rough design.

[1244] Step 6:

[1245] The server then sends the generated rough design back to the user's device using a secure communication protocol. The user's device then displays the received rough design, allowing the user to select the most suitable one from the multiple rough designs generated. The input is image data of the rough design, and the output is the design displayed on the user's device.

[1246] 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.

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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).

[1253] 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.

[1254] 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."

[1255] 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.

[1256] 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).

[1257] 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.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] The following is further disclosed regarding the above embodiment.

[1268] (Claim 1)

[1269] means for receiving information about a design input from a user terminal;

[1270] means for analyzing information about the design and searching for related existing designs;

[1271] means for generating a new rough design based on the existing design;

[1272] means for transmitting the generated rough design to a user terminal;

[1273] A system including:

[1274] (Claim 2)

[1275] 2. The system according to claim 1, wherein keywords and images input from a user terminal are received as information related to the design.

[1276] (Claim 3)

[1277] 2. The system according to claim 1, wherein the system analyzes received information about the design to extract keywords and calculate features from the image.

[1278] "Example 1"

[1279] (Claim 1)

[1280] means for receiving information about a design input from a user terminal;

[1281] means for transmitting information about the design to a server via a secure communication protocol;

[1282] means for analyzing information about the design and searching a design database for related existing designs;

[1283] A means for generating a new rough design using a generative AI model based on the existing design;

[1284] means for transmitting the generated rough design to a user terminal;

[1285] A system including:

[1286] (Claim 2)

[1287] 2. The system according to claim 1, wherein keywords and images input from a user terminal are received as information related to the design.

[1288] (Claim 3)

[1289] 2. The system according to claim 1, wherein the system analyzes received information about the design to extract keywords and calculate features from the image.

[1290] "Application Example 1"

[1291] (Claim 1)

[1292] means for receiving information about a design input from a user terminal;

[1293] means for analyzing information about the design and searching for related existing designs;

[1294] means for generating a new rough design based on the existing design;

[1295] A method for generating new advertising designs using AI,

[1296] means for transmitting the generated advertisement design to a user terminal;

[1297] A system including:

[1298] (Claim 2)

[1299] 2. The system according to claim 1, wherein keywords and images input from a user terminal are received as information related to the design.

[1300] (Claim 3)

[1301] 2. The system according to claim 1, wherein the system analyzes received information about the design to extract keywords and calculate features from the image.

[1302] (Claim 4)

[1303] The system of claim 1, wherein to generate a new advertising design, a prompt sentence is generated using a generative AI model, and a design is generated based on the prompt sentence.

[1304] (Claim 5)

[1305] The system of claim 1, wherein the generated advertising design is displayed on a smartphone.

[1306] "Example 2: Combining Emotion Engines"

[1307] (Claim 1)

[1308] means for receiving information about a design input from a user terminal;

[1309] information about the design and a means for analyzing emotions;

[1310] A means for searching for related existing designs based on the analyzed design information and emotion information;

[1311] means for generating a new rough design based on the existing design and emotion information;

[1312] means for transmitting the generated rough design to a user terminal;

[1313] A system including:

[1314] (Claim 2)

[1315] 2. The system according to claim 1, wherein keywords and images input from a user terminal are received as information relating to the design, and the emotion engine is used to analyze the user's emotions.

[1316] (Claim 3)

[1317] The system according to claim 1, wherein the system analyzes received information about the design, extracts keywords, calculates features from the image, and generates a rough design taking into account the analyzed emotional information.

[1318] "Application example 2 when combining emotion engines"

[1319] (Claim 1)

[1320] means for receiving design information and emotion information input from a user terminal;

[1321] means for analyzing the information and emotion information about the design and searching for related existing designs;

[1322] a means for generating a new rough design based on the existing design and taking emotional information into consideration;

[1323] means for transmitting the generated rough design to a user terminal;

[1324] A system including:

[1325] (Claim 2)

[1326] 2. The system according to claim 1, wherein keywords, images and emotion information input from a user terminal are received as design-related information and emotion information.

[1327] (Claim 3)

[1328] 2. The system according to claim 1, wherein the system analyzes the received design-related information and emotion information to extract keywords, calculates features from the image, and recognizes the emotion information. [Explanation of symbols]

[1329] 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 information about a design input from a user terminal; means for analyzing information about the design and searching for related existing designs; means for generating a new rough design based on the existing design; means for transmitting the generated rough design to a user terminal; A system including:

2. 2. The system according to claim 1, wherein keywords and images input from a user terminal are received as information related to the design.

3. 2. The system according to claim 1, wherein the received information about the design is analyzed to extract keywords and calculate feature quantities from the image.

Images