system

Abstract

We provide the system. [Solution] A means of extracting design and layout features from a collection of information that records past visual materials, A means for training an artificial intelligence model that generates visual materials based on extracted design and layout features, A means for receiving instruction information from a user and generating visual materials using the artificial intelligence model based on said instruction information, Means for providing generated visual materials to users, A means for receiving evaluation information from users and improving the artificial intelligence model based on said evaluation information, A means of acquiring the latest current events information and integrating it into visual materials, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the creation of visual materials, it is difficult to maintain the consistency of the design and layout based on past materials, and users may require a great deal of time and effort when creating new materials. Furthermore, information collection for reflecting the latest current situation information in the materials is also a burden. These problems are particularly hindering efficient material creation in the fields of business and education. The present invention aims to solve such problems and quickly create efficient and high-quality visual materials.

Means for Solving the Problems

[0005] This invention provides a system for automatically generating visual materials by extracting design and layout features from a collection of historical visual materials and training an artificial intelligence model with them. The system includes means for generating visual materials based on user instructions, providing them to the user, improving the artificial intelligence model based on evaluation information, and acquiring and integrating the latest current information. This enables users to generate consistent, high-quality materials in a short time, achieving effective and efficient information transmission.

[0006] "Visual materials" refer to documents, slides, and presentations used to convey information visually.

[0007] An "information collection" refers to a database containing design, layout, and text information related to past visual materials.

[0008] "Design and layout features" refer to the characteristics of the visual elements used in visual materials, such as fonts, color schemes, and graphic arrangements.

[0009] An "artificial intelligence model" refers to a computational model that uses machine learning algorithms to learn design and layout features and generate new visual materials.

[0010] "User" refers to an individual or organization that uses this system to create or modify visual materials.

[0011] "Instruction information" refers to detailed information such as desired topics, styles, and themes that users input into the system when generating visual materials.

[0012] "Evaluation information" refers to the feedback and improvement requests that users provide regarding the generated visual materials.

[0013] "Current events information" refers to information about current social trends and events, such as the latest news and statistical data, which are used to reflect in visual materials. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system for analyzing previously created visual materials and automatically generating new visual materials. This system records past visual materials as an information collection and uses it to extract design and layout features. The extracted features are learned by an artificial intelligence model on a server, and new visual materials are generated based on this learning.

[0036] The server first collects historical visual material data from companies and educational institutions and imports it into a database. During this process, the server analyzes characteristics to maintain consistency in design patterns and layouts. For example, the server identifies specific theme colors, font styles, and graph layout patterns from past materials, abstracts them, and trains the system as features.

[0037] The terminal is used by users to create new visual materials. Through the interface on the terminal, users input the topic and design style of the material they want to create. The terminal sends this information to the server and receives the processed results from the server. Based on the user's desired conditions, the server automatically creates the visual material and sends it to the terminal.

[0038] For example, if a user wants to create a "marketing strategy presentation," they send this request to the server via their device. The server retrieves appropriate design patterns from past marketing-related materials and generates slides that match the user's desired style. The generated slides are returned to the device, and the user can use them immediately.

[0039] Furthermore, the server continuously receives feedback from users and improves the AI ​​model, thereby enhancing the accuracy of the generated visual materials. This feedback allows for the rapid reflection of user preferences and emerging trends. The server can also acquire current events information from external sources and incorporate the latest content into the slides, integrating contemporary and relevant information into the visual materials.

[0040] Thus, the system of the present invention utilizes past document data and efficiently generates visual materials in response to user input, thereby significantly reducing the time and effort required for slide creation and enabling the creation of high-quality, consistent materials.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects historical visual materials from companies and educational institutions into a database. This includes various formats such as slides, documents, and charts, and is stored as a collection of information.

[0044] Step 2:

[0045] The server analyzes the collected data and extracts design and layout features. This includes graphical elements, color schemes, font choices, and slide layout patterns.

[0046] Step 3:

[0047] The server trains an artificial intelligence model based on the extracted features. This process applies machine learning algorithms, enabling the model to recognize visual patterns.

[0048] Step 4:

[0049] The user enters a request to create new visual material using the device. This request includes the topic, design preferences, and intended use.

[0050] Step 5:

[0051] The terminal sends the user's request to the server. Based on the received information, the server uses an artificial intelligence model to generate appropriate visual materials.

[0052] Step 6:

[0053] The server sends the generated visual material to the terminal, allowing the user to review it. The user reviews this material and provides feedback as needed.

[0054] Step 7:

[0055] The server receives feedback from users and uses it to improve the artificial intelligence model. This will improve the accuracy of future generation processes.

[0056] Step 8:

[0057] The server retrieves the latest current events information from external sources and integrates it into visual materials. In this way, the materials always contain the most up-to-date information and are provided to users.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In today's information society, there is a demand for the rapid and efficient creation of visual materials. However, generating high-quality materials while maintaining consistency in visual design and layout requires specialized knowledge and is therefore time-consuming and labor-intensive. Furthermore, automated generation systems using artificial intelligence face challenges in providing flexible designs that meet user needs and incorporating the latest information.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for learning a generative model that generates visual materials based on the extracted design and layout features, and means for receiving instruction information from a user and generating visual materials using the generative model based on said instruction information. This makes it possible to quickly generate high-quality, consistent visual materials even without design expertise.

[0063] An "information aggregate" is a collection of data containing visual materials created in the past, providing a foundation for extracting design and layout characteristics.

[0064] "Design and layout characteristics" refer to the patterns of combination and arrangement of visual elements in visual materials, and include design characteristics such as color, font style, and arrangement of shapes.

[0065] A "generative model" is a computational model that uses artificial intelligence technology to learn the characteristics of past designs and layouts and automatically generate new visual materials.

[0066] "Instructional information" refers to information that expresses the user's desire to create a document, and includes topics, design styles, and other details.

[0067] "Visual materials" refer to digitally presented information media such as presentations, slides, and reports, and are means of conveying information visually.

[0068] "Evaluation information" refers to the feedback that users provide on the generated visual materials, and is used to improve the accuracy of the model.

[0069] "Current events information" refers to data about current events and trends, and is used to integrate the latest information into visual materials.

[0070] In this system, the server's primary role is to collect historical visual materials and store them in a database. The server analyzes design and layout patterns in visual materials such as corporate presentations and educational lecture materials. In this process, the server uses data science techniques to extract theme colors, font styles, and graph placement patterns.

[0071] The extracted design and layout features are learned by a generative AI model on the server. Software such as Python machine learning libraries or deep learning frameworks are used to train the generative AI model. This allows the server to systematically accumulate the design know-how necessary for designing visual materials, which can then be utilized when generating new materials.

[0072] Users access the interface via a terminal and input topics and design styles for new visual materials. The terminal then sends the user's input information to the server. The terminal uses a web browser or dedicated application as its user interface and supports the input of prompts. For example, by entering a prompt such as "I want to create slides for a corporate marketing strategy presentation," users can communicate specific requests to the server.

[0073] The server automatically generates visual materials using a generative AI model based on instructions received from the user. The generated materials are sent back to the terminal, where the user can review and use them. The server also receives feedback from users and continuously improves the AI ​​model. This feedback ensures that the generated materials are always relevant to the times and optimized to the individual user's needs. By acquiring the latest current events information from external sources and integrating it into the visual materials, the server can always provide materials that reflect the latest information.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server collects historical visual materials from companies and educational institutions. The collected data includes presentation slides, reports, and other digital documents. The server receives this data as input and stores it in a database. Within the database, it processes the data to standardize file formats and facilitate searching and classification.

[0077] Step 2:

[0078] The server extracts design and layout features from visual materials stored in the database. Specifically, it uses data analysis algorithms to identify and quantify themes such as theme colors, font styles, and the placement of images and graphs. These characteristics become input and are output as training datasets for the generative AI model.

[0079] Step 3:

[0080] The server trains a generative AI model based on the extracted design and layout features. It receives quantified design characteristics as input, and the generative AI model learns them iteratively. During the learning process, the model builds imitation patterns and accumulates know-how for effectively generating visual materials. This learning result is obtained as output.

[0081] Step 4:

[0082] The user inputs the topic and design style of the document to be created on the interface via their terminal. This prompt text is sent to the server as input data. Specifically, text such as "I want to create slides for a corporate marketing strategy presentation" is used.

[0083] Step 5:

[0084] The server generates visual materials using a generative AI model based on the user's instructions. Here, the prompt text is fed into the model, which outputs a material design that matches the user's request, and then generates it. The final generated result is saved to the server as output.

[0085] Step 6:

[0086] The server sends the generated visual materials to the terminal and provides them to the user. The output slides and presentation files are input and displayed on the terminal. The user can download them and use them in their work.

[0087] Step 7:

[0088] Users provide feedback on the quality and satisfaction level of the generated visual materials. This evaluation information is sent to the server as input. The server uses this feedback to improve the generating AI model and outputs it as data to continuously improve accuracy, which is then used for retraining.

[0089] Step 8:

[0090] The server retrieves the latest current events information from external sources. It references external APIs and feeds as input to obtain the latest news and trend data. This data is then processed and integrated into visual materials, and the output is included in newly generated materials. This ensures that the materials always reflect the most up-to-date information.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Traditionally, creating visual advertising materials required specialized knowledge and skills, making it difficult to generate diverse designs quickly and effectively. Furthermore, reflecting the latest trends and effective advertising patterns required considerable effort and time. These issues made it difficult for small businesses and non-expert users to create competitive advertising.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for extracting structural attributes from a set of information recording past visual materials, means for learning an algorithm for generating visual materials based on the extracted structural attributes, means for acquiring the latest event data and integrating it into visual materials, and means for suggesting automatically generated visual materials based on information related to advertising. This enables users to quickly generate effective and timely visual advertising materials without requiring specialized knowledge.

[0096] "Visual materials" are figures, illustrations, graphs, or other visual content used to convey information visually.

[0097] An "information set" is a collection of data that includes past design and layout information.

[0098] "Structural attributes" refer to characteristics such as design elements and layout patterns in visual materials.

[0099] An "algorithm" is a set of steps or computational processes used to solve a specific problem.

[0100] "Instruction data" refers to information that indicates the requests and conditions that users provide when generating visual materials.

[0101] "Evaluation data" refers to information that includes user feedback and opinions on the generated visual materials.

[0102] "Event data" refers to information that reflects the current situation, such as the latest trends and news.

[0103] "Advertising" refers to information intended to promote products or services and increase their market value.

[0104] The system implementing this invention is built around a server and a terminal. The server takes in a large amount of past visual material and records it as an information set. Then, it identifies design elements from the extracted structural attributes and learns an algorithm for generating new visual material based on a generative AI model. The user inputs instruction data from the terminal and determines the specifications of the generated visual material. The terminal allows the user to easily set design themes and requirements through a user interface.

[0105] The server uses deep learning frameworks such as TENSORFLOW® and PyTorch to analyze design patterns and trends. The server also acquires the latest event data from the internet in real time and integrates it into visual materials, providing materials that reflect current trends and topics.

[0106] As a concrete example, consider a company launching a new advertising campaign using the application. By inputting the product type and target audience on their device, users can receive design suggestions based on an analysis of successful past campaigns. An example of a prompt message might be, "Create advertising visuals to promote a newly launched organic vegetable juice to health-conscious women in their 20s." This allows users without specialized design knowledge to create effective and visually appealing advertisements.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The user inputs instruction data using a terminal. Here, they specify the topic, target audience, and design style of the visual material they want to generate using a user interface. This input data is sent to the server.

[0110] Step 2:

[0111] Based on the received instruction data, the server identifies relevant structural attributes from a collection of historical visual materials. Using database query operations, it extracts design elements corresponding to similar topics and target audiences. This result serves as input for the next step.

[0112] Step 3:

[0113] The server uses the extracted structural attributes to create new visual material design proposals by applying a generative AI model. TensorFlow is used to construct a virtual visual material that reflects the design elements. Experimental design patterns are generated during this process.

[0114] Step 4:

[0115] The server collects real-time information from online sources to integrate the latest event data into the generated design proposals. This includes using news feeds and public APIs from social media. The collected data is incorporated into visual materials, resulting in up-to-date materials that appeal to the target audience.

[0116] Step 5:

[0117] The completed visual materials are sent from the server to the user's device. The user can review and edit the suggested advertising visuals on the device. Based on the displayed materials, the user makes final adjustments. In addition, the user's evaluation feedback is sent to the server and used to train the AI ​​model for future generation.

[0118] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0119] The present invention aims to provide user-adapted visual materials by having an emotion engine recognize the user's emotional state and reflecting that information in the generation and adjustment of the visual materials. This system is operated by combining an artificial intelligence model that learns design and layout based on past visual materials and an emotion engine that senses the user's emotional state.

[0120] The server first collects historical visual materials from companies and educational institutions into a database. This data is used to extract design features and layout characteristics, and serves as foundational information for training an artificial intelligence model. Using this model, the server automatically generates new visual material designs.

[0121] Furthermore, the terminal provides an interface for users to create visual materials and sends user requests to the server, which include new topics and design preferences. The server then uses an artificial intelligence model to generate visual materials based on these requests and sends them back to the terminal.

[0122] The emotion engine analyzes the user's emotional state while they are using the device, utilizing sensors such as the camera and microphone. It recognizes the user's emotional state using their facial expressions, tone of voice, or other biosignals, and sends this information to a server. For example, if a user is feeling stressed, the emotion engine instructs the server to suggest designs and content that evoke feelings of relaxation and friendliness.

[0123] For example, when a user creates a "product introduction presentation," the request entered on the terminal is sent to the server, and an artificial intelligence model is used to generate the initial slides. The emotion engine then senses the user's level of excitement from their facial expressions and voice, and uses this to prompt the server to select energetic designs and visual content.

[0124] Ultimately, feedback from the emotion engine is reflected by the server, and visual materials tailored to the user's current emotions are generated and presented on the device. This process allows the visual materials to adapt to each user's emotional state, increasing their effectiveness and relevance.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The server collects historical visual material data from companies and educational institutions into a database. This data includes slides, reports, graphs, etc., and is used to extract design patterns and layout features.

[0128] Step 2:

[0129] The server extracts design and layout features from the collected visual materials and uses them to train an artificial intelligence model. This is done using machine learning algorithms to recognize and patternize visual features.

[0130] Step 3:

[0131] The user enters a request to create new visual materials using the interface on their device. Here, they specify the topic, design preferences, theme, and other details.

[0132] Step 4:

[0133] The emotion engine detects the user's current emotional state through the device. This involves analyzing the user's facial expressions and voice using the camera and microphone, and obtaining the results as numerical data.

[0134] Step 5:

[0135] The device sends user requests and the results of the emotion engine's analysis to the server. The server receives this information and generates visual materials using an artificial intelligence model. During generation, a design appropriate to the user's emotional state is applied.

[0136] Step 6:

[0137] The server sends the generated visual materials to the user's device. The user can then review, edit, and adjust these materials. By receiving materials that reflect emotion-based design suggestions, the user is provided with the most suitable presentation.

[0138] Step 7:

[0139] Users provide evaluation information about the generated visual materials via their devices, and the server collects this information to improve the artificial intelligence model. This evaluation information is then used in subsequent generation processes.

[0140] Step 8:

[0141] The server retrieves the latest current events information from external sources and integrates it into visual materials as needed. This ensures that the generated visual materials always contain up-to-date content and provide users with more useful information.

[0142] (Example 2)

[0143] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0144] Traditional methods for creating visual materials fail to reflect the emotional state of users, making it difficult to provide materials tailored to the individual needs of each user. Furthermore, the generated visual materials may not align with the user's requirements or mental state, leading to a decrease in their effectiveness and relevance.

[0145] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0146] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for acquiring emotional information using input / output devices to identify the user's emotional state, and means for adjusting visual materials through a generation program based on the emotional information. This makes it possible to generate visual materials adapted to the user's emotions and provide highly effective and relevant content that cannot be obtained by conventional methods.

[0147] An "information collection" is a structured database system for managing diverse forms of data, including historical visual materials.

[0148] "Design and layout characteristics" refer to the characteristics and patterns related to the composition, style, color, and arrangement of visual materials.

[0149] A "generative program" is an artificial intelligence-based algorithm used to create new visual materials based on design and layout characteristics.

[0150] "User instruction information" refers to information regarding the requests and conditions provided by users when creating visual materials.

[0151] "Input / output devices" refer to sensors used to sense the emotional state of a user, specifically devices such as cameras and microphones.

[0152] "Emotional information" refers to data about the user's mental state, analyzed based on facial expressions, voice tone, and other biosignals acquired through input / output devices.

[0153] "Adjusting visual materials through a generation program" means that, based on acquired emotional information, the generation program dynamically changes and optimizes the design and layout of the visual materials.

[0154] "Evaluation information" refers to user feedback and evaluations of the generated visual materials, which are used to improve the generation program.

[0155] "Information sharing means" refers to communication interfaces and protocols for acquiring current events information from external information sources and integrating it into visual materials.

[0156] This invention aims to provide content adapted to the user's emotional state through a system for generating and adjusting visual materials. This system utilizes a server, a terminal, and a technology called an emotion engine.

[0157] The server stores historical visual materials collected from companies, educational institutions, and other sources in a database. These materials are used to extract design and layout features and as foundational data for training generative programs. The server is equipped with a generative AI model that generates customized visual materials based on user prompts. The generated materials are then sent from the server to the terminal.

[0158] The terminal provides the user with an interface for creating visual materials. The user inputs specific requests into the terminal through prompt messages. This information is sent to the server and used for material generation. The terminal is equipped with input / output devices such as a camera and microphone to acquire emotional information, thereby transmitting the user's emotional state to the server in real time.

[0159] The emotion engine uses sensors built into the device to analyze emotional information from the user's facial expressions and tone of voice. This information is then sent to a server, where a generation program dynamically adjusts the design and layout of visual materials.

[0160] As a concrete example, consider a scenario where a user enters a prompt message such as, "Please create a presentation introducing our new product." This prompt message is sent from the terminal to the server, and the generation AI model uses it to construct initial slides. If the emotion engine, which monitors the user's emotional state, detects, for example, excitement, the generated material is adjusted by the server to a more energetic design. Finally, the server sends the adaptive visual material back to the terminal for the user to receive.

[0161] This system makes it possible to provide effective and relevant visual materials that are tailored to the individual user's emotions and needs.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The server collects historical visual materials from companies and educational institutions into a database. This involves accessing external data sources using web crawlers and APIs and periodically downloading data. The input is visual material files, and the output is structured data stored in the database. Design and layout features are extracted and organized as training data required for AI models.

[0165] Step 2:

[0166] The terminal provides an interface for users to create visual materials. The user enters a prompt, for example, "Please create a presentation introducing a new product." This input information is sent to the server as a data packet. The output is the specific request information sent to the server. At this stage, the input fields are checked and their formatting is automatically corrected to ensure accurate processing of the user's request.

[0167] Step 3:

[0168] The server uses a generative AI model to generate visual materials based on the user prompt text it receives. The input consists of the user prompt text and trained data from a database of past materials. The output is the newly generated visual material (e.g., presentation slides). In this step, the AI ​​model automatically selects and edits design patterns to form a consistent layout.

[0169] Step 4:

[0170] The device's emotion engine detects the user's facial expressions and voice tone through the camera and microphone. The input is real-time data from the sensors, and the output is analyzed emotion information (e.g., whether the user is excited or relaxed). The emotion engine generates data packets to send this information to the server.

[0171] Step 5:

[0172] The server adjusts the visual materials generated based on the received emotional information. Input consists of data from the emotion engine and existing visual materials. Output is the final visual material, customized to the user's emotional state. Specifically, this involves changes to color tones, font size adjustments, and resetting of visual emphasis.

[0173] Step 6:

[0174] The terminal presents the user with the final, adjusted visual materials. The input is the final visual material sent from the server, and the output is the material the user views through the interface. The terminal also collects user feedback and additional evaluation information, which is then sent back to the server. This allows for improvements to the entire system.

[0175] (Application Example 2)

[0176] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0177] In generating visual materials, conventional technologies have been insufficient in adjusting designs and content to reflect the emotional state of users, making it difficult to provide materials that are optimal for individual users. Furthermore, the lack of means to change elements of visual materials in real time made it difficult to immediately adapt to users' emotions, thus maximizing advertising effectiveness.

[0178] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0179] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for learning an artificial intelligence model that generates visual materials based on the extracted design and layout features, and means for recognizing the user's emotional state and adjusting the generated visual materials based on that emotional state. This enables real-time adjustment of visual materials according to the user's emotional state, allowing for the provision of more effective advertisements and content.

[0180] An "information set" is a collection of data, including past visual materials, that serves as the basis for extracting design and layout features.

[0181] "Design and layout characteristics" refer to elements that indicate the design style and layout characteristics of visual materials, and are used to train artificial intelligence models.

[0182] An "artificial intelligence model" is a computer program based on algorithms that learn patterns and features from data and generate new visual materials.

[0183] "User emotional state" refers to the user's psychological or physiological responses as perceived through cameras and audio devices, and is reflected in the adjustment of visual materials.

[0184] A "smart device" is an electronic device that can connect to the internet and is equipped with sensors such as cameras and audio devices, and is used to acquire data on emotional states.

[0185] An "interface" is an interface through which a user interacts with a system, and it plays a role in collecting instructional information and emotional information.

[0186] The system used to realize this application has the function of generating visual materials that adapt to the user's emotional state. The server first records past visual materials as an information collection in a database, extracts the design and arrangement features of these materials, and uses them to train an artificial intelligence model. The artificial intelligence model is an algorithm that creates new visual materials from this data.

[0187] When a user inputs instructions from their device, that information is sent to the server. Based on the received instructions, the server uses an artificial intelligence model to generate visual materials and provides them to the device.

[0188] Meanwhile, smart devices recognize the user's emotional state in real time through cameras and audio devices while the user is viewing visual materials. The user obtains information about their emotional state via the smart device and sends it to the server. The server adjusts the visual materials based on this emotional information, specifically changing the colors, layout, and design elements.

[0189] For example, if a user shows signs of excitement while viewing an advertisement, the server can recommend more vibrant color patterns or dynamic designs. Adding stimulating visual effects, for instance, can enhance the persuasiveness of the advertisement. In this way, the effectiveness of visual materials is maximized through real-time adjustments based on emotional states.

[0190] The generative AI model operates according to specific prompts. For example, it might be instructed to "adjust the design of the visual materials to be more impactful if the user's emotional state is 'excited'." This prompt triggers information processing, generating more relevant materials.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The server records past visual data in a database and extracts design and placement features from it. The input is the visual data stored in the database, and the output is the design and placement features. These features are processed by an artificial intelligence model and used as foundational data for generating visual data. Specifically, data analysis algorithms are used to identify patterns in visual elements and construct feature data.

[0194] Step 2:

[0195] The user sends instruction information to the server via their device. The input is the user's instruction information (e.g., a request for a new design), and the output is a prompt message from the generative AI model corresponding to that instruction. The server parses the instruction information as text and generates a prompt message. This prompt message is sent to the generative AI model and serves as guidance for generating visual materials.

[0196] Step 3:

[0197] The server uses the received prompt text to run a generative AI model and construct an initial design for generating visual materials. The input is the prompt text, and the output is the initial visual material. The server combines the design elements using an AI algorithm to form the initial visual material.

[0198] Step 4:

[0199] The user uses the camera and voice equipment of a smart device to recognize their emotional state in real time and send that data to a server. The input is emotional information obtained from the user's facial expressions and tone of voice, and the output is analyzed emotional state data. The smart device acquires sensor data and identifies the user's psychological state by analyzing the emotional information.

[0200] Step 5:

[0201] The server adjusts the visual materials based on the acquired emotional state. The input is the analyzed emotional state data and the initial visual materials, and the output is the final adjusted visual materials. In this process, design elements are optimized according to the emotional state, and the impact of the content is maximized by adjusting the visual effects. Specifically, this involves color changes and the addition of dynamic effects.

[0202] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0203] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0204] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0208] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0209] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0210] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0211] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0212] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0213] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0214] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0215] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0216] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0217] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0218] This invention is a system for analyzing previously created visual materials and automatically generating new visual materials. This system records past visual materials as an information collection and uses it to extract design and layout features. The extracted features are learned by an artificial intelligence model on a server, and new visual materials are generated based on this learning.

[0219] The server first collects historical visual material data from companies and educational institutions and imports it into a database. During this process, the server analyzes characteristics to maintain consistency in design patterns and layouts. For example, the server identifies specific theme colors, font styles, and graph layout patterns from past materials, abstracts them, and trains the system as features.

[0220] The terminal is used by users to create new visual materials. Through the interface on the terminal, users input the topic and design style of the material they want to create. The terminal sends this information to the server and receives the processed results from the server. Based on the user's desired conditions, the server automatically creates the visual material and sends it to the terminal.

[0221] For example, if a user wants to create a "marketing strategy presentation," they send this request to the server via their device. The server retrieves appropriate design patterns from past marketing-related materials and generates slides that match the user's desired style. The generated slides are returned to the device, and the user can use them immediately.

[0222] Furthermore, the server continuously receives feedback from users and improves the AI ​​model, thereby enhancing the accuracy of the generated visual materials. This feedback allows for the rapid reflection of user preferences and emerging trends. The server can also acquire current events information from external sources and incorporate the latest content into the slides, integrating contemporary and relevant information into the visual materials.

[0223] Thus, the system of the present invention utilizes past document data and efficiently generates visual materials in response to user input, thereby significantly reducing the time and effort required for slide creation and enabling the creation of high-quality, consistent materials.

[0224] The following describes the processing flow.

[0225] Step 1:

[0226] The server collects historical visual materials from companies and educational institutions into a database. This includes various formats such as slides, documents, and charts, and is stored as a collection of information.

[0227] Step 2:

[0228] The server analyzes the collected data and extracts design and layout features. This includes graphical elements, color schemes, font choices, and slide layout patterns.

[0229] Step 3:

[0230] The server trains an artificial intelligence model based on the extracted features. This process applies machine learning algorithms, enabling the model to recognize visual patterns.

[0231] Step 4:

[0232] The user enters a request to create new visual material using the device. This request includes the topic, design preferences, and intended use.

[0233] Step 5:

[0234] The terminal sends the user's request to the server. Based on the received information, the server uses an artificial intelligence model to generate appropriate visual materials.

[0235] Step 6:

[0236] The server sends the generated visual material to the terminal, allowing the user to review it. The user reviews this material and provides feedback as needed.

[0237] Step 7:

[0238] The server receives feedback from users and uses it to improve the artificial intelligence model. This will improve the accuracy of future generation processes.

[0239] Step 8:

[0240] The server retrieves the latest current events information from external sources and integrates it into visual materials. In this way, the materials always contain the most up-to-date information and are provided to users.

[0241] (Example 1)

[0242] Next, we will describe Example 1. 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."

[0243] In today's information society, there is a demand for the rapid and efficient creation of visual materials. However, generating high-quality materials while maintaining consistency in visual design and layout requires specialized knowledge and is therefore time-consuming and labor-intensive. Furthermore, automated generation systems using artificial intelligence face challenges in providing flexible designs that meet user needs and incorporating the latest information.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for learning a generative model that generates visual materials based on the extracted design and layout features, and means for receiving instruction information from a user and generating visual materials using the generative model based on said instruction information. This makes it possible to quickly generate high-quality, consistent visual materials even without design expertise.

[0246] An "information aggregate" is a collection of data containing visual materials created in the past, providing a foundation for extracting design and layout characteristics.

[0247] "Design and layout characteristics" refer to the patterns of combination and arrangement of visual elements in visual materials, and include design characteristics such as color, font style, and arrangement of shapes.

[0248] A "generative model" is a computational model that uses artificial intelligence technology to learn the characteristics of past designs and layouts and automatically generate new visual materials.

[0249] "Instructional information" refers to information that expresses the user's desire to create a document, and includes topics, design styles, and other details.

[0250] "Visual materials" refer to digitally presented information media such as presentations, slides, and reports, and are means of conveying information visually.

[0251] "Evaluation information" refers to the feedback that users provide on the generated visual materials, and is used to improve the accuracy of the model.

[0252] "Current events information" refers to data about current events and trends, and is used to integrate the latest information into visual materials.

[0253] In this system, the server's primary role is to collect historical visual materials and store them in a database. The server analyzes design and layout patterns in visual materials such as corporate presentations and educational lecture materials. In this process, the server uses data science techniques to extract theme colors, font styles, and graph placement patterns.

[0254] The extracted design and layout features are learned by a generative AI model on the server. Software such as Python machine learning libraries or deep learning frameworks are used to train the generative AI model. This allows the server to systematically accumulate the design know-how necessary for designing visual materials, which can then be utilized when generating new materials.

[0255] Users access the interface via a terminal and input topics and design styles for new visual materials. The terminal then sends the user's input information to the server. The terminal uses a web browser or dedicated application as its user interface and supports the input of prompts. For example, by entering a prompt such as "I want to create slides for a corporate marketing strategy presentation," users can communicate specific requests to the server.

[0256] The server automatically generates visual materials using a generative AI model based on instructions received from the user. The generated materials are sent back to the terminal, where the user can review and use them. The server also receives feedback from users and continuously improves the AI ​​model. This feedback ensures that the generated materials are always relevant to the times and optimized to the individual user's needs. By acquiring the latest current events information from external sources and integrating it into the visual materials, the server can always provide materials that reflect the latest information.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The server collects historical visual materials from companies and educational institutions. The collected data includes presentation slides, reports, and other digital documents. The server receives this data as input and stores it in a database. Within the database, it processes the data to standardize file formats and facilitate searching and classification.

[0260] Step 2:

[0261] The server extracts design and layout features from visual materials stored in the database. Specifically, it uses data analysis algorithms to identify and quantify themes such as theme colors, font styles, and the placement of images and graphs. These characteristics become input and are output as training datasets for the generative AI model.

[0262] Step 3:

[0263] The server trains a generative AI model based on the extracted design and layout features. It receives quantified design characteristics as input, and the generative AI model learns them iteratively. During the learning process, the model builds imitation patterns and accumulates know-how for effectively generating visual materials. This learning result is obtained as output.

[0264] Step 4:

[0265] The user inputs the topic and design style of the document to be created on the interface via their terminal. This prompt text is sent to the server as input data. Specifically, text such as "I want to create slides for a corporate marketing strategy presentation" is used.

[0266] Step 5:

[0267] The server generates visual materials using a generative AI model based on the user's instructions. Here, the prompt text is fed into the model, which outputs a material design that matches the user's request, and then generates it. The final generated result is saved to the server as output.

[0268] Step 6:

[0269] The server sends the generated visual materials to the terminal and provides them to the user. The output slides and presentation files are input and displayed on the terminal. The user can download them and use them in their work.

[0270] Step 7:

[0271] Users provide feedback on the quality and satisfaction level of the generated visual materials. This evaluation information is sent to the server as input. The server uses this feedback to improve the generating AI model and outputs it as data to continuously improve accuracy, which is then used for retraining.

[0272] Step 8:

[0273] The server retrieves the latest current events information from external sources. It references external APIs and feeds as input to obtain the latest news and trend data. This data is then processed and integrated into visual materials, and the output is included in newly generated materials. This ensures that the materials always reflect the most up-to-date information.

[0274] (Application Example 1)

[0275] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0276] Conventionally, creating visual materials for advertisements has required specialized knowledge and technology, and it has not been easy to generate diverse designs quickly and effectively. Also, there has been a problem that a great deal of labor and time are required to reflect the latest trends and effective advertising patterns. Due to these problems, it has been difficult for small-scale enterprises and non-expert users to create competitive advertisements.

[0277] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0278] In this invention, the server includes means for extracting structural attributes from an information set recording past visual materials, means for learning an algorithm for generating visual materials based on the extracted structural attributes, means for acquiring the latest event data and integrating it into the visual materials, and means for proposing visual materials automatically generated based on information regarding advertisements. Thereby, a user can quickly generate effective and up-to-date visual materials for advertisements without requiring specialized knowledge.

[0279] A "visual material" is a graphic, illustration, graph, or other visual content for visually conveying information.

[0280] An "information set" is a collection of data including past design and layout information.

[0281] "Structural attributes" refer to features such as design elements and arrangement patterns in visual materials.

[0282] An "algorithm" is a series of procedures or computational processes for solving a specific problem.

[0283] "Instruction data" is information indicating the desires and conditions provided by a user when generating visual materials.

[0284] "Evaluation data" is information including feedback and opinions from a user regarding the generated visual materials.

[0285] "Event data" refers to information that reflects the current situation, such as the latest trends and news.

[0286] "Advertisement" refers to information that aims to promote a product or service and enhance its market value.

[0287] The system for implementing this invention is constructed around a server and a terminal. The server captures a large amount of past visual materials and records them as an information collection. Then, it identifies design elements from the extracted structural attributes and learns an algorithm for generating new visual materials based on a generation AI model. The user inputs instruction data from the terminal to determine the specifications of the generated visual materials. The terminal enables the user to easily set design themes and requirements through a user interface.

[0288] The server analyzes design patterns and trends using deep learning frameworks such as TensorFlow and PyTorch. The server also acquires the latest event data from the Internet in real time and integrates it into visual materials to provide materials that reflect the trend and topics of the times.

[0289] As a specific example, consider the case where a company newly launching an advertising campaign uses the application. By inputting the type of product and the target layer on the terminal, the user can receive design proposals that analyze successful cases from past similar campaigns. Examples of prompt sentences include those like "Create an advertising visual to promote the newly released organic vegetable juice for health-conscious women in their 20s." This enables users without specialized design knowledge to create effective and visually appealing advertisements.

[0290] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0291] Step 1:

[0292] The user inputs instruction data using a terminal. Here, they specify the topic, target audience, and design style of the visual material they want to generate using a user interface. This input data is sent to the server.

[0293] Step 2:

[0294] Based on the received instruction data, the server identifies relevant structural attributes from a collection of historical visual materials. Using database query operations, it extracts design elements corresponding to similar topics and target audiences. This result serves as input for the next step.

[0295] Step 3:

[0296] The server uses the extracted structural attributes to create new visual material design proposals by applying a generative AI model. TensorFlow is used to construct a virtual visual material that reflects the design elements. Experimental design patterns are generated during this process.

[0297] Step 4:

[0298] The server collects real-time information from online sources to integrate the latest event data into the generated design proposals. This includes using news feeds and public APIs from social media. The collected data is incorporated into visual materials, resulting in up-to-date materials that appeal to the target audience.

[0299] Step 5:

[0300] The completed visual materials are sent from the server to the user's device. The user can review and edit the suggested advertising visuals on the device. Based on the displayed materials, the user makes final adjustments. In addition, the user's evaluation feedback is sent to the server and used to train the AI ​​model for future generation.

[0301] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0302] The present invention aims to provide user-adapted visual materials by having an emotion engine recognize the user's emotional state and reflecting that information in the generation and adjustment of the visual materials. This system is operated by combining an artificial intelligence model that learns design and layout based on past visual materials and an emotion engine that senses the user's emotional state.

[0303] The server first collects historical visual materials from companies and educational institutions into a database. This data is used to extract design features and layout characteristics, and serves as foundational information for training an artificial intelligence model. Using this model, the server automatically generates new visual material designs.

[0304] Furthermore, the terminal provides an interface for users to create visual materials and sends user requests to the server, which include new topics and design preferences. The server then uses an artificial intelligence model to generate visual materials based on these requests and sends them back to the terminal.

[0305] The emotion engine analyzes the user's emotional state while they are using the device, utilizing sensors such as the camera and microphone. It recognizes the user's emotional state using their facial expressions, tone of voice, or other biosignals, and sends this information to a server. For example, if a user is feeling stressed, the emotion engine instructs the server to suggest designs and content that evoke feelings of relaxation and friendliness.

[0306] As a specific example, when a user creates a "product introduction presentation", the request input on the terminal is sent to the server, and initial slides are generated using an artificial intelligence model. At this time, the emotion engine senses the excitement state from the user's expression and voice, and based on this, prompts the server to select energetic designs and visual contents.

[0307] Finally, the feedback from the emotion engine is reflected by the server, and visual materials adapted to the user's current emotion are generated and presented on the terminal. Through this process, the visual materials can adapt to the emotional state of individual users and enhance their effectiveness and relevance.

[0308] The following describes the processing flow.

[0309] Step 1:

[0310] The server collects past visual material data from companies and educational institutions into the database. This data includes slides, reports, graphs, etc., and is used to extract design patterns and layout features.

[0311] Step 2:

[0312] The server extracts the design and layout features from the collected visual materials and trains the artificial intelligence model. This is done using machine learning algorithms to perform the recognition and patterning of visual features.

[0313] Step 3:

[0314] The user uses the interface on the terminal to input a request for creating new visual materials. Here, specify the topic, design preferences, theme, etc.

[0315] Step 4:

[0316] The emotion engine detects the user's current emotional state through the device. This involves analyzing the user's facial expressions and voice using the camera and microphone, and obtaining the results as numerical data.

[0317] Step 5:

[0318] The device sends user requests and the results of the emotion engine's analysis to the server. The server receives this information and generates visual materials using an artificial intelligence model. During generation, a design appropriate to the user's emotional state is applied.

[0319] Step 6:

[0320] The server sends the generated visual materials to the user's device. The user can then review, edit, and adjust these materials. By receiving materials that reflect emotion-based design suggestions, the user is provided with the most suitable presentation.

[0321] Step 7:

[0322] Users provide evaluation information about the generated visual materials via their devices, and the server collects this information to improve the artificial intelligence model. This evaluation information is then used in subsequent generation processes.

[0323] Step 8:

[0324] The server retrieves the latest current events information from external sources and integrates it into visual materials as needed. This ensures that the generated visual materials always contain up-to-date content and provide users with more useful information.

[0325] (Example 2)

[0326] Next, we will describe Example 2. 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".

[0327] Traditional methods for creating visual materials fail to reflect the emotional state of users, making it difficult to provide materials tailored to the individual needs of each user. Furthermore, the generated visual materials may not align with the user's requirements or mental state, leading to a decrease in their effectiveness and relevance.

[0328] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0329] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for acquiring emotional information using input / output devices to identify the user's emotional state, and means for adjusting visual materials through a generation program based on the emotional information. This makes it possible to generate visual materials adapted to the user's emotions and provide highly effective and relevant content that cannot be obtained by conventional methods.

[0330] An "information collection" is a structured database system for managing diverse forms of data, including historical visual materials.

[0331] "Design and layout characteristics" refer to the characteristics and patterns related to the composition, style, color, and arrangement of visual materials.

[0332] A "generative program" is an artificial intelligence-based algorithm used to create new visual materials based on design and layout characteristics.

[0333] "User instruction information" refers to information regarding the requests and conditions provided by users when creating visual materials.

[0334] "Input / output devices" refer to sensors used to sense the emotional state of a user, specifically devices such as cameras and microphones.

[0335] "Emotional information" refers to data about the user's mental state, analyzed based on facial expressions, voice tone, and other biosignals acquired through input / output devices.

[0336] "Adjusting visual materials through a generation program" means that, based on acquired emotional information, the generation program dynamically changes and optimizes the design and layout of the visual materials.

[0337] "Evaluation information" refers to user feedback and evaluations of the generated visual materials, which are used to improve the generation program.

[0338] "Information sharing means" refers to communication interfaces and protocols for acquiring current events information from external information sources and integrating it into visual materials.

[0339] This invention aims to provide content adapted to the user's emotional state through a system for generating and adjusting visual materials. This system utilizes a server, a terminal, and a technology called an emotion engine.

[0340] The server stores historical visual materials collected from companies, educational institutions, and other sources in a database. These materials are used to extract design and layout features and as foundational data for training generative programs. The server is equipped with a generative AI model that generates customized visual materials based on user prompts. The generated materials are then sent from the server to the terminal.

[0341] The terminal provides the user with an interface for creating visual materials. The user inputs specific requests into the terminal through prompt messages. This information is sent to the server and used for material generation. The terminal is equipped with input / output devices such as a camera and microphone to acquire emotional information, thereby transmitting the user's emotional state to the server in real time.

[0342] The emotion engine uses sensors built into the device to analyze emotional information from the user's facial expressions and tone of voice. This information is then sent to a server, where a generation program dynamically adjusts the design and layout of visual materials.

[0343] As a concrete example, consider a scenario where a user enters a prompt message such as, "Please create a presentation introducing our new product." This prompt message is sent from the terminal to the server, and the generation AI model uses it to construct initial slides. If the emotion engine, which monitors the user's emotional state, detects, for example, excitement, the generated material is adjusted by the server to a more energetic design. Finally, the server sends the adaptive visual material back to the terminal for the user to receive.

[0344] This system makes it possible to provide effective and relevant visual materials that are tailored to the individual user's emotions and needs.

[0345] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0346] Step 1:

[0347] The server collects historical visual materials from companies and educational institutions into a database. This involves accessing external data sources using web crawlers and APIs and periodically downloading data. The input is visual material files, and the output is structured data stored in the database. Design and layout features are extracted and organized as training data required for AI models.

[0348] Step 2:

[0349] The terminal provides an interface for users to create visual materials. The user enters a prompt, for example, "Please create a presentation introducing a new product." This input information is sent to the server as a data packet. The output is the specific request information sent to the server. At this stage, the input fields are checked and their formatting is automatically corrected to ensure accurate processing of the user's request.

[0350] Step 3:

[0351] The server uses a generative AI model to generate visual materials based on the user prompt text it receives. The input consists of the user prompt text and trained data from a database of past materials. The output is the newly generated visual material (e.g., presentation slides). In this step, the AI ​​model automatically selects and edits design patterns to form a consistent layout.

[0352] Step 4:

[0353] The device's emotion engine detects the user's facial expressions and voice tone through the camera and microphone. The input is real-time data from the sensors, and the output is analyzed emotion information (e.g., whether the user is excited or relaxed). The emotion engine generates data packets to send this information to the server.

[0354] Step 5:

[0355] The server adjusts the visual materials generated based on the received emotional information. Input consists of data from the emotion engine and existing visual materials. Output is the final visual material, customized to the user's emotional state. Specifically, this involves changes to color tones, font size adjustments, and resetting of visual emphasis.

[0356] Step 6:

[0357] The terminal presents the user with the final, adjusted visual materials. The input is the final visual material sent from the server, and the output is the material the user views through the interface. The terminal also collects user feedback and additional evaluation information, which is then sent back to the server. This allows for improvements to the entire system.

[0358] (Application Example 2)

[0359] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0360] In generating visual materials, conventional technologies have been insufficient in adjusting designs and content to reflect the emotional state of users, making it difficult to provide materials that are optimal for individual users. Furthermore, the lack of means to change elements of visual materials in real time made it difficult to immediately adapt to users' emotions, thus maximizing advertising effectiveness.

[0361] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0362] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for learning an artificial intelligence model that generates visual materials based on the extracted design and layout features, and means for recognizing the user's emotional state and adjusting the generated visual materials based on that emotional state. This enables real-time adjustment of visual materials according to the user's emotional state, allowing for the provision of more effective advertisements and content.

[0363] An "information set" is a collection of data, including past visual materials, that serves as the basis for extracting design and layout features.

[0364] "Design and layout characteristics" refer to elements that indicate the design style and layout characteristics of visual materials, and are used to train artificial intelligence models.

[0365] An "artificial intelligence model" is a computer program based on algorithms that learn patterns and features from data and generate new visual materials.

[0366] "User emotional state" refers to the user's psychological or physiological responses as perceived through cameras and audio devices, and is reflected in the adjustment of visual materials.

[0367] A "smart device" is an electronic device that can connect to the internet and is equipped with sensors such as cameras and audio devices, and is used to acquire data on emotional states.

[0368] An "interface" is an interface through which a user interacts with a system, and it plays a role in collecting instructional information and emotional information.

[0369] The system used to realize this application has the function of generating visual materials that adapt to the user's emotional state. The server first records past visual materials as an information collection in a database, extracts the design and arrangement features of these materials, and uses them to train an artificial intelligence model. The artificial intelligence model is an algorithm that creates new visual materials from this data.

[0370] When a user inputs instructions from their device, that information is sent to the server. Based on the received instructions, the server uses an artificial intelligence model to generate visual materials and provides them to the device.

[0371] Meanwhile, smart devices recognize the user's emotional state in real time through cameras and audio devices while the user is viewing visual materials. The user obtains information about their emotional state via the smart device and sends it to the server. The server adjusts the visual materials based on this emotional information, specifically changing the colors, layout, and design elements.

[0372] For example, if a user shows signs of excitement while viewing an advertisement, the server can recommend more vibrant color patterns or dynamic designs. Adding stimulating visual effects, for instance, can enhance the persuasiveness of the advertisement. In this way, the effectiveness of visual materials is maximized through real-time adjustments based on emotional states.

[0373] The generative AI model operates according to specific prompts. For example, it might be instructed to "adjust the design of the visual materials to be more impactful if the user's emotional state is 'excited'." This prompt triggers information processing, generating more relevant materials.

[0374] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0375] Step 1:

[0376] The server records past visual data in a database and extracts design and placement features from it. The input is the visual data stored in the database, and the output is the design and placement features. These features are processed by an artificial intelligence model and used as foundational data for generating visual data. Specifically, data analysis algorithms are used to identify patterns in visual elements and construct feature data.

[0377] Step 2:

[0378] The user sends instruction information to the server via their device. The input is the user's instruction information (e.g., a request for a new design), and the output is a prompt message from the generative AI model corresponding to that instruction. The server parses the instruction information as text and generates a prompt message. This prompt message is sent to the generative AI model and serves as guidance for generating visual materials.

[0379] Step 3:

[0380] The server uses the received prompt text to run a generative AI model and construct an initial design for generating visual materials. The input is the prompt text, and the output is the initial visual material. The server combines the design elements using an AI algorithm to form the initial visual material.

[0381] Step 4:

[0382] The user uses the camera and voice equipment of a smart device to recognize their emotional state in real time and send that data to a server. The input is emotional information obtained from the user's facial expressions and tone of voice, and the output is analyzed emotional state data. The smart device acquires sensor data and identifies the user's psychological state by analyzing the emotional information.

[0383] Step 5:

[0384] The server adjusts the visual materials based on the acquired emotional state. The input is the analyzed emotional state data and the initial visual materials, and the output is the final adjusted visual materials. In this process, design elements are optimized according to the emotional state, and the impact of the content is maximized by adjusting the visual effects. Specifically, this involves color changes and the addition of dynamic effects.

[0385] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0386] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0387] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0388] [Third Embodiment]

[0389] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0390] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0391] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0392] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0393] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0394] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0395] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0396] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0397] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0398] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0399] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0400] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0401] This invention is a system for analyzing previously created visual materials and automatically generating new visual materials. This system records past visual materials as an information collection and uses it to extract design and layout features. The extracted features are learned by an artificial intelligence model on a server, and new visual materials are generated based on this learning.

[0402] The server first collects historical visual material data from companies and educational institutions and imports it into a database. During this process, the server analyzes characteristics to maintain consistency in design patterns and layouts. For example, the server identifies specific theme colors, font styles, and graph layout patterns from past materials, abstracts them, and trains the system as features.

[0403] The terminal is used by users to create new visual materials. Through the interface on the terminal, users input the topic and design style of the material they want to create. The terminal sends this information to the server and receives the processed results from the server. Based on the user's desired conditions, the server automatically creates the visual material and sends it to the terminal.

[0404] For example, if a user wants to create a "marketing strategy presentation," they send this request to the server via their device. The server retrieves appropriate design patterns from past marketing-related materials and generates slides that match the user's desired style. The generated slides are returned to the device, and the user can use them immediately.

[0405] Furthermore, the server continuously receives feedback from users and improves the AI ​​model, thereby enhancing the accuracy of the generated visual materials. This feedback allows for the rapid reflection of user preferences and emerging trends. The server can also acquire current events information from external sources and incorporate the latest content into the slides, integrating contemporary and relevant information into the visual materials.

[0406] Thus, the system of the present invention utilizes past document data and efficiently generates visual materials in response to user input, thereby significantly reducing the time and effort required for slide creation and enabling the creation of high-quality, consistent materials.

[0407] The following describes the processing flow.

[0408] Step 1:

[0409] The server collects historical visual materials from companies and educational institutions into a database. This includes various formats such as slides, documents, and charts, and is stored as a collection of information.

[0410] Step 2:

[0411] The server analyzes the collected data and extracts design and layout features. This includes graphical elements, color schemes, font choices, and slide layout patterns.

[0412] Step 3:

[0413] The server trains an artificial intelligence model based on the extracted features. This process applies machine learning algorithms, enabling the model to recognize visual patterns.

[0414] Step 4:

[0415] The user enters a request to create new visual material using the device. This request includes the topic, design preferences, and intended use.

[0416] Step 5:

[0417] The terminal sends the user's request to the server. Based on the received information, the server uses an artificial intelligence model to generate appropriate visual materials.

[0418] Step 6:

[0419] The server sends the generated visual material to the terminal, allowing the user to review it. The user reviews this material and provides feedback as needed.

[0420] Step 7:

[0421] The server receives feedback from users and uses it to improve the artificial intelligence model. This will improve the accuracy of future generation processes.

[0422] Step 8:

[0423] The server retrieves the latest current events information from external sources and integrates it into visual materials. In this way, the materials always contain the most up-to-date information and are provided to users.

[0424] (Example 1)

[0425] Next, we will describe Example 1. 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."

[0426] In today's information society, there is a demand for the rapid and efficient creation of visual materials. However, generating high-quality materials while maintaining consistency in visual design and layout requires specialized knowledge and is therefore time-consuming and labor-intensive. Furthermore, automated generation systems using artificial intelligence face challenges in providing flexible designs that meet user needs and incorporating the latest information.

[0427] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0428] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for learning a generative model that generates visual materials based on the extracted design and layout features, and means for receiving instruction information from a user and generating visual materials using the generative model based on said instruction information. This makes it possible to quickly generate high-quality, consistent visual materials even without design expertise.

[0429] An "information aggregate" is a collection of data containing visual materials created in the past, providing a foundation for extracting design and layout characteristics.

[0430] "Design and layout characteristics" refer to the patterns of combination and arrangement of visual elements in visual materials, and include design characteristics such as color, font style, and arrangement of shapes.

[0431] A "generative model" is a computational model that uses artificial intelligence technology to learn the characteristics of past designs and layouts and automatically generate new visual materials.

[0432] "Instructional information" refers to information that expresses the user's desire to create a document, and includes topics, design styles, and other details.

[0433] "Visual materials" refer to digitally presented information media such as presentations, slides, and reports, and are means of conveying information visually.

[0434] "Evaluation information" refers to the feedback that users provide on the generated visual materials, and is used to improve the accuracy of the model.

[0435] "Current events information" refers to data about current events and trends, and is used to integrate the latest information into visual materials.

[0436] In this system, the server's primary role is to collect historical visual materials and store them in a database. The server analyzes design and layout patterns in visual materials such as corporate presentations and educational lecture materials. In this process, the server uses data science techniques to extract theme colors, font styles, and graph placement patterns.

[0437] The extracted design and layout features are learned by a generative AI model on the server. Software such as Python machine learning libraries or deep learning frameworks are used to train the generative AI model. This allows the server to systematically accumulate the design know-how necessary for designing visual materials, which can then be utilized when generating new materials.

[0438] Users access the interface via a terminal and input topics and design styles for new visual materials. The terminal then sends the user's input information to the server. The terminal uses a web browser or dedicated application as its user interface and supports the input of prompts. For example, by entering a prompt such as "I want to create slides for a corporate marketing strategy presentation," users can communicate specific requests to the server.

[0439] The server automatically generates visual materials using a generative AI model based on instructions received from the user. The generated materials are sent back to the terminal, where the user can review and use them. The server also receives feedback from users and continuously improves the AI ​​model. This feedback ensures that the generated materials are always relevant to the times and optimized to the individual user's needs. By acquiring the latest current events information from external sources and integrating it into the visual materials, the server can always provide materials that reflect the latest information.

[0440] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0441] Step 1:

[0442] The server collects historical visual materials from companies and educational institutions. The collected data includes presentation slides, reports, and other digital documents. The server receives this data as input and stores it in a database. Within the database, it processes the data to standardize file formats and facilitate searching and classification.

[0443] Step 2:

[0444] The server extracts design and layout features from visual materials stored in the database. Specifically, it uses data analysis algorithms to identify and quantify themes such as theme colors, font styles, and the placement of images and graphs. These characteristics become input and are output as training datasets for the generative AI model.

[0445] Step 3:

[0446] The server trains a generative AI model based on the extracted design and layout features. It receives quantified design characteristics as input, and the generative AI model learns them iteratively. During the learning process, the model builds imitation patterns and accumulates know-how for effectively generating visual materials. This learning result is obtained as output.

[0447] Step 4:

[0448] The user inputs the topic and design style of the document to be created on the interface via their terminal. This prompt text is sent to the server as input data. Specifically, text such as "I want to create slides for a corporate marketing strategy presentation" is used.

[0449] Step 5:

[0450] The server generates visual materials using a generative AI model based on the user's instructions. Here, the prompt text is fed into the model, which outputs a material design that matches the user's request, and then generates it. The final generated result is saved to the server as output.

[0451] Step 6:

[0452] The server sends the generated visual materials to the terminal and provides them to the user. The output slides and presentation files are input and displayed on the terminal. The user can download them and use them in their work.

[0453] Step 7:

[0454] Users provide feedback on the quality and satisfaction level of the generated visual materials. This evaluation information is sent to the server as input. The server uses this feedback to improve the generating AI model and outputs it as data to continuously improve accuracy, which is then used for retraining.

[0455] Step 8:

[0456] The server retrieves the latest current events information from external sources. It references external APIs and feeds as input to obtain the latest news and trend data. This data is then processed and integrated into visual materials, and the output is included in newly generated materials. This ensures that the materials always reflect the most up-to-date information.

[0457] (Application Example 1)

[0458] Next, we will explain Application Example 1. In the following explanation, 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."

[0459] Traditionally, creating visual advertising materials required specialized knowledge and skills, making it difficult to generate diverse designs quickly and effectively. Furthermore, reflecting the latest trends and effective advertising patterns required considerable effort and time. These issues made it difficult for small businesses and non-expert users to create competitive advertising.

[0460] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0461] In this invention, the server includes means for extracting structural attributes from a set of information recording past visual materials, means for learning an algorithm for generating visual materials based on the extracted structural attributes, means for acquiring the latest event data and integrating it into visual materials, and means for suggesting automatically generated visual materials based on information related to advertising. This enables users to quickly generate effective and timely visual advertising materials without requiring specialized knowledge.

[0462] "Visual materials" are figures, illustrations, graphs, or other visual content used to convey information visually.

[0463] An "information set" is a collection of data that includes past design and layout information.

[0464] "Structural attributes" refer to characteristics such as design elements and layout patterns in visual materials.

[0465] An "algorithm" is a set of steps or computational processes used to solve a specific problem.

[0466] "Instruction data" refers to information that indicates the requests and conditions that users provide when generating visual materials.

[0467] "Evaluation data" refers to information that includes user feedback and opinions on the generated visual materials.

[0468] "Event data" refers to information that reflects the current situation, such as the latest trends and news.

[0469] "Advertising" refers to information intended to promote products or services and increase their market value.

[0470] The system implementing this invention is built around a server and a terminal. The server takes in a large amount of past visual material and records it as an information set. Then, it identifies design elements from the extracted structural attributes and learns an algorithm for generating new visual material based on a generative AI model. The user inputs instruction data from the terminal and determines the specifications of the generated visual material. The terminal allows the user to easily set design themes and requirements through a user interface.

[0471] The server uses deep learning frameworks such as TensorFlow and PyTorch to analyze design patterns and trends. The server also retrieves the latest event data from the internet in real time and integrates it into visual materials, providing resources that reflect current trends and topics.

[0472] As a concrete example, consider a company launching a new advertising campaign using the application. By inputting the product type and target audience on their device, users can receive design suggestions based on an analysis of successful past campaigns. An example of a prompt message might be, "Create advertising visuals to promote a newly launched organic vegetable juice to health-conscious women in their 20s." This allows users without specialized design knowledge to create effective and visually appealing advertisements.

[0473] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0474] Step 1:

[0475] The user inputs instruction data using a terminal. Here, they specify the topic, target audience, and design style of the visual material they want to generate using a user interface. This input data is sent to the server.

[0476] Step 2:

[0477] Based on the received instruction data, the server identifies relevant structural attributes from a collection of historical visual materials. Using database query operations, it extracts design elements corresponding to similar topics and target audiences. This result serves as input for the next step.

[0478] Step 3:

[0479] The server uses the extracted structural attributes to create new visual material design proposals by applying a generative AI model. TensorFlow is used to construct a virtual visual material that reflects the design elements. Experimental design patterns are generated during this process.

[0480] Step 4:

[0481] The server collects real-time information from online sources to integrate the latest event data into the generated design proposals. This includes using news feeds and public APIs from social media. The collected data is incorporated into visual materials, resulting in up-to-date materials that appeal to the target audience.

[0482] Step 5:

[0483] The completed visual materials are sent from the server to the user's device. The user can review and edit the suggested advertising visuals on the device. Based on the displayed materials, the user makes final adjustments. In addition, the user's evaluation feedback is sent to the server and used to train the AI ​​model for future generation.

[0484] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0485] The present invention aims to provide user-adapted visual materials by having an emotion engine recognize the user's emotional state and reflecting that information in the generation and adjustment of the visual materials. This system is operated by combining an artificial intelligence model that learns design and layout based on past visual materials and an emotion engine that senses the user's emotional state.

[0486] The server first collects historical visual materials from companies and educational institutions into a database. This data is used to extract design features and layout characteristics, and serves as foundational information for training an artificial intelligence model. Using this model, the server automatically generates new visual material designs.

[0487] Furthermore, the terminal provides an interface for users to create visual materials and sends user requests to the server, which include new topics and design preferences. The server then uses an artificial intelligence model to generate visual materials based on these requests and sends them back to the terminal.

[0488] The emotion engine analyzes the user's emotional state while they are using the device, utilizing sensors such as the camera and microphone. It recognizes the user's emotional state using their facial expressions, tone of voice, or other biosignals, and sends this information to a server. For example, if a user is feeling stressed, the emotion engine instructs the server to suggest designs and content that evoke feelings of relaxation and friendliness.

[0489] For example, when a user creates a "product introduction presentation," the request entered on the terminal is sent to the server, and an artificial intelligence model is used to generate the initial slides. The emotion engine then senses the user's level of excitement from their facial expressions and voice, and uses this to prompt the server to select energetic designs and visual content.

[0490] Ultimately, feedback from the emotion engine is reflected by the server, and visual materials tailored to the user's current emotions are generated and presented on the device. This process allows the visual materials to adapt to each user's emotional state, increasing their effectiveness and relevance.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] The server collects historical visual material data from companies and educational institutions into a database. This data includes slides, reports, graphs, etc., and is used to extract design patterns and layout features.

[0494] Step 2:

[0495] The server extracts design and layout features from the collected visual materials and uses them to train an artificial intelligence model. This is done using machine learning algorithms to recognize and patternize visual features.

[0496] Step 3:

[0497] The user enters a request to create new visual materials using the interface on their device. Here, they specify the topic, design preferences, theme, and other details.

[0498] Step 4:

[0499] The emotion engine detects the user's current emotional state through the device. This involves analyzing the user's facial expressions and voice using the camera and microphone, and obtaining the results as numerical data.

[0500] Step 5:

[0501] The device sends user requests and the results of the emotion engine's analysis to the server. The server receives this information and generates visual materials using an artificial intelligence model. During generation, a design appropriate to the user's emotional state is applied.

[0502] Step 6:

[0503] The server sends the generated visual materials to the user's device. The user can then review, edit, and adjust these materials. By receiving materials that reflect emotion-based design suggestions, the user is provided with the most suitable presentation.

[0504] Step 7:

[0505] Users provide evaluation information about the generated visual materials via their devices, and the server collects this information to improve the artificial intelligence model. This evaluation information is then used in subsequent generation processes.

[0506] Step 8:

[0507] The server retrieves the latest current events information from external sources and integrates it into visual materials as needed. This ensures that the generated visual materials always contain up-to-date content and provide users with more useful information.

[0508] (Example 2)

[0509] Next, we will describe Example 2. 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."

[0510] Traditional methods for creating visual materials fail to reflect the emotional state of users, making it difficult to provide materials tailored to the individual needs of each user. Furthermore, the generated visual materials may not align with the user's requirements or mental state, leading to a decrease in their effectiveness and relevance.

[0511] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0512] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for acquiring emotional information using input / output devices to identify the user's emotional state, and means for adjusting visual materials through a generation program based on the emotional information. This makes it possible to generate visual materials adapted to the user's emotions and provide highly effective and relevant content that cannot be obtained by conventional methods.

[0513] An "information collection" is a structured database system for managing diverse forms of data, including historical visual materials.

[0514] "Design and layout characteristics" refer to the characteristics and patterns related to the composition, style, color, and arrangement of visual materials.

[0515] A "generative program" is an artificial intelligence-based algorithm used to create new visual materials based on design and layout characteristics.

[0516] "User instruction information" refers to information regarding the requests and conditions provided by users when creating visual materials.

[0517] "Input / output devices" refer to sensors used to sense the emotional state of a user, specifically devices such as cameras and microphones.

[0518] "Emotional information" refers to data about the user's mental state, analyzed based on facial expressions, voice tone, and other biosignals acquired through input / output devices.

[0519] "Adjusting visual materials through a generation program" means that, based on acquired emotional information, the generation program dynamically changes and optimizes the design and layout of the visual materials.

[0520] "Evaluation information" refers to user feedback and evaluations of the generated visual materials, which are used to improve the generation program.

[0521] "Information sharing means" refers to communication interfaces and protocols for acquiring current events information from external information sources and integrating it into visual materials.

[0522] This invention aims to provide content adapted to the user's emotional state through a system for generating and adjusting visual materials. This system utilizes a server, a terminal, and a technology called an emotion engine.

[0523] The server stores historical visual materials collected from companies, educational institutions, and other sources in a database. These materials are used to extract design and layout features and as foundational data for training generative programs. The server is equipped with a generative AI model that generates customized visual materials based on user prompts. The generated materials are then sent from the server to the terminal.

[0524] The terminal provides the user with an interface for creating visual materials. The user inputs specific requests into the terminal through prompt messages. This information is sent to the server and used for material generation. The terminal is equipped with input / output devices such as a camera and microphone to acquire emotional information, thereby transmitting the user's emotional state to the server in real time.

[0525] The emotion engine uses sensors built into the device to analyze emotional information from the user's facial expressions and tone of voice. This information is then sent to a server, where a generation program dynamically adjusts the design and layout of visual materials.

[0526] As a concrete example, consider a scenario where a user enters a prompt message such as, "Please create a presentation introducing our new product." This prompt message is sent from the terminal to the server, and the generation AI model uses it to construct initial slides. If the emotion engine, which monitors the user's emotional state, detects, for example, excitement, the generated material is adjusted by the server to a more energetic design. Finally, the server sends the adaptive visual material back to the terminal for the user to receive.

[0527] This system makes it possible to provide effective and relevant visual materials that are tailored to the individual user's emotions and needs.

[0528] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0529] Step 1:

[0530] The server collects historical visual materials from companies and educational institutions into a database. This involves accessing external data sources using web crawlers and APIs and periodically downloading data. The input is visual material files, and the output is structured data stored in the database. Design and layout features are extracted and organized as training data required for AI models.

[0531] Step 2:

[0532] The terminal provides an interface for users to create visual materials. The user enters a prompt, for example, "Please create a presentation introducing a new product." This input information is sent to the server as a data packet. The output is the specific request information sent to the server. At this stage, the input fields are checked and their formatting is automatically corrected to ensure accurate processing of the user's request.

[0533] Step 3:

[0534] The server uses a generative AI model to generate visual materials based on the user prompt text it receives. The input consists of the user prompt text and trained data from a database of past materials. The output is the newly generated visual material (e.g., presentation slides). In this step, the AI ​​model automatically selects and edits design patterns to form a consistent layout.

[0535] Step 4:

[0536] The device's emotion engine detects the user's facial expressions and voice tone through the camera and microphone. The input is real-time data from the sensors, and the output is analyzed emotion information (e.g., whether the user is excited or relaxed). The emotion engine generates data packets to send this information to the server.

[0537] Step 5:

[0538] The server adjusts the visual materials generated based on the received emotional information. Input consists of data from the emotion engine and existing visual materials. Output is the final visual material, customized to the user's emotional state. Specifically, this involves changes to color tones, font size adjustments, and resetting of visual emphasis.

[0539] Step 6:

[0540] The terminal presents the user with the final, adjusted visual materials. The input is the final visual material sent from the server, and the output is the material the user views through the interface. The terminal also collects user feedback and additional evaluation information, which is then sent back to the server. This allows for improvements to the entire system.

[0541] (Application Example 2)

[0542] Next, we will explain application example 2. In the following explanation, 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."

[0543] In generating visual materials, conventional technologies have been insufficient in adjusting designs and content to reflect the emotional state of users, making it difficult to provide materials that are optimal for individual users. Furthermore, the lack of means to change elements of visual materials in real time made it difficult to immediately adapt to users' emotions, thus maximizing advertising effectiveness.

[0544] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0545] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for learning an artificial intelligence model that generates visual materials based on the extracted design and layout features, and means for recognizing the user's emotional state and adjusting the generated visual materials based on that emotional state. This enables real-time adjustment of visual materials according to the user's emotional state, allowing for the provision of more effective advertisements and content.

[0546] An "information set" is a collection of data, including past visual materials, that serves as the basis for extracting design and layout features.

[0547] "Design and layout characteristics" refer to elements that indicate the design style and layout characteristics of visual materials, and are used to train artificial intelligence models.

[0548] An "artificial intelligence model" is a computer program based on algorithms that learn patterns and features from data and generate new visual materials.

[0549] "User emotional state" refers to the user's psychological or physiological responses as perceived through cameras and audio devices, and is reflected in the adjustment of visual materials.

[0550] A "smart device" is an electronic device that can connect to the internet and is equipped with sensors such as cameras and audio devices, and is used to acquire data on emotional states.

[0551] An "interface" is an interface through which a user interacts with a system, and it plays a role in collecting instructional information and emotional information.

[0552] The system used to realize this application has the function of generating visual materials that adapt to the user's emotional state. The server first records past visual materials as an information collection in a database, extracts the design and arrangement features of these materials, and uses them to train an artificial intelligence model. The artificial intelligence model is an algorithm that creates new visual materials from this data.

[0553] When a user inputs instructions from their device, that information is sent to the server. Based on the received instructions, the server uses an artificial intelligence model to generate visual materials and provides them to the device.

[0554] Meanwhile, smart devices recognize the user's emotional state in real time through cameras and audio devices while the user is viewing visual materials. The user obtains information about their emotional state via the smart device and sends it to the server. The server adjusts the visual materials based on this emotional information, specifically changing the colors, layout, and design elements.

[0555] For example, if a user shows signs of excitement while viewing an advertisement, the server can recommend more vibrant color patterns or dynamic designs. Adding stimulating visual effects, for instance, can enhance the persuasiveness of the advertisement. In this way, the effectiveness of visual materials is maximized through real-time adjustments based on emotional states.

[0556] The generative AI model operates according to specific prompts. For example, it might be instructed to "adjust the design of the visual materials to be more impactful if the user's emotional state is 'excited'." This prompt triggers information processing, generating more relevant materials.

[0557] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0558] Step 1:

[0559] The server records past visual data in a database and extracts design and placement features from it. The input is the visual data stored in the database, and the output is the design and placement features. These features are processed by an artificial intelligence model and used as foundational data for generating visual data. Specifically, data analysis algorithms are used to identify patterns in visual elements and construct feature data.

[0560] Step 2:

[0561] The user sends instruction information to the server via their device. The input is the user's instruction information (e.g., a request for a new design), and the output is a prompt message from the generative AI model corresponding to that instruction. The server parses the instruction information as text and generates a prompt message. This prompt message is sent to the generative AI model and serves as guidance for generating visual materials.

[0562] Step 3:

[0563] The server uses the received prompt text to run a generative AI model and construct an initial design for generating visual materials. The input is the prompt text, and the output is the initial visual material. The server combines the design elements using an AI algorithm to form the initial visual material.

[0564] Step 4:

[0565] The user uses the camera and voice equipment of a smart device to recognize their emotional state in real time and send that data to a server. The input is emotional information obtained from the user's facial expressions and tone of voice, and the output is analyzed emotional state data. The smart device acquires sensor data and identifies the user's psychological state by analyzing the emotional information.

[0566] Step 5:

[0567] The server adjusts the visual materials based on the acquired emotional state. The input is the analyzed emotional state data and the initial visual materials, and the output is the final adjusted visual materials. In this process, design elements are optimized according to the emotional state, and the impact of the content is maximized by adjusting the visual effects. Specifically, this involves color changes and the addition of dynamic effects.

[0568] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0569] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0570] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0571] [Fourth Embodiment]

[0572] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0573] As shown in Figure 7, the 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.

[0574] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0575] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0576] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0577] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0578] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0579] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0580] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0581] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0582] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0583] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0584] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0585] This invention is a system for analyzing previously created visual materials and automatically generating new visual materials. This system records past visual materials as an information collection and uses it to extract design and layout features. The extracted features are learned by an artificial intelligence model on a server, and new visual materials are generated based on this learning.

[0586] The server first collects historical visual material data from companies and educational institutions and imports it into a database. During this process, the server analyzes characteristics to maintain consistency in design patterns and layouts. For example, the server identifies specific theme colors, font styles, and graph layout patterns from past materials, abstracts them, and trains the system as features.

[0587] The terminal is used by users to create new visual materials. Through the interface on the terminal, users input the topic and design style of the material they want to create. The terminal sends this information to the server and receives the processed results from the server. Based on the user's desired conditions, the server automatically creates the visual material and sends it to the terminal.

[0588] For example, if a user wants to create a "marketing strategy presentation," they send this request to the server via their device. The server retrieves appropriate design patterns from past marketing-related materials and generates slides that match the user's desired style. The generated slides are returned to the device, and the user can use them immediately.

[0589] Furthermore, the server continuously receives feedback from users and improves the AI ​​model, thereby enhancing the accuracy of the generated visual materials. This feedback allows for the rapid reflection of user preferences and emerging trends. The server can also acquire current events information from external sources and incorporate the latest content into the slides, integrating contemporary and relevant information into the visual materials.

[0590] Thus, the system of the present invention utilizes past document data and efficiently generates visual materials in response to user input, thereby significantly reducing the time and effort required for slide creation and enabling the creation of high-quality, consistent materials.

[0591] The following describes the processing flow.

[0592] Step 1:

[0593] The server collects historical visual materials from companies and educational institutions into a database. This includes various formats such as slides, documents, and charts, and is stored as a collection of information.

[0594] Step 2:

[0595] The server analyzes the collected data and extracts design and layout features. This includes graphical elements, color schemes, font choices, and slide layout patterns.

[0596] Step 3:

[0597] The server trains an artificial intelligence model based on the extracted features. This process applies machine learning algorithms, enabling the model to recognize visual patterns.

[0598] Step 4:

[0599] The user enters a request to create new visual material using the device. This request includes the topic, design preferences, and intended use.

[0600] Step 5:

[0601] The terminal sends the user's request to the server. Based on the received information, the server uses an artificial intelligence model to generate appropriate visual materials.

[0602] Step 6:

[0603] The server sends the generated visual material to the terminal, allowing the user to review it. The user reviews this material and provides feedback as needed.

[0604] Step 7:

[0605] The server receives feedback from users and uses it to improve the artificial intelligence model. This will improve the accuracy of future generation processes.

[0606] Step 8:

[0607] The server retrieves the latest current events information from external sources and integrates it into visual materials. In this way, the materials always contain the most up-to-date information and are provided to users.

[0608] (Example 1)

[0609] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0610] In today's information society, there is a demand for the rapid and efficient creation of visual materials. However, generating high-quality materials while maintaining consistency in visual design and layout requires specialized knowledge and is therefore time-consuming and labor-intensive. Furthermore, automated generation systems using artificial intelligence face challenges in providing flexible designs that meet user needs and incorporating the latest information.

[0611] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0612] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for learning a generative model that generates visual materials based on the extracted design and layout features, and means for receiving instruction information from a user and generating visual materials using the generative model based on said instruction information. This makes it possible to quickly generate high-quality, consistent visual materials even without design expertise.

[0613] An "information aggregate" is a collection of data containing visual materials created in the past, providing a foundation for extracting design and layout characteristics.

[0614] "Design and layout characteristics" refer to the patterns of combination and arrangement of visual elements in visual materials, and include design characteristics such as color, font style, and arrangement of shapes.

[0615] A "generative model" is a computational model that uses artificial intelligence technology to learn the characteristics of past designs and layouts and automatically generate new visual materials.

[0616] "Instructional information" refers to information that expresses the user's desire to create a document, and includes topics, design styles, and other details.

[0617] "Visual materials" refer to digitally presented information media such as presentations, slides, and reports, and are means of conveying information visually.

[0618] "Evaluation information" refers to the feedback that users provide on the generated visual materials, and is used to improve the accuracy of the model.

[0619] "Current events information" refers to data about current events and trends, and is used to integrate the latest information into visual materials.

[0620] In this system, the server's primary role is to collect historical visual materials and store them in a database. The server analyzes design and layout patterns in visual materials such as corporate presentations and educational lecture materials. In this process, the server uses data science techniques to extract theme colors, font styles, and graph placement patterns.

[0621] The extracted design and layout features are learned by a generative AI model on the server. Software such as Python machine learning libraries or deep learning frameworks are used to train the generative AI model. This allows the server to systematically accumulate the design know-how necessary for designing visual materials, which can then be utilized when generating new materials.

[0622] Users access the interface via a terminal and input topics and design styles for new visual materials. The terminal then sends the user's input information to the server. The terminal uses a web browser or dedicated application as its user interface and supports the input of prompts. For example, by entering a prompt such as "I want to create slides for a corporate marketing strategy presentation," users can communicate specific requests to the server.

[0623] The server automatically generates visual materials using a generative AI model based on instructions received from the user. The generated materials are sent back to the terminal, where the user can review and use them. The server also receives feedback from users and continuously improves the AI ​​model. This feedback ensures that the generated materials are always relevant to the times and optimized to the individual user's needs. By acquiring the latest current events information from external sources and integrating it into the visual materials, the server can always provide materials that reflect the latest information.

[0624] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0625] Step 1:

[0626] The server collects historical visual materials from companies and educational institutions. The collected data includes presentation slides, reports, and other digital documents. The server receives this data as input and stores it in a database. Within the database, it processes the data to standardize file formats and facilitate searching and classification.

[0627] Step 2:

[0628] The server extracts design and layout features from visual materials stored in the database. Specifically, it uses data analysis algorithms to identify and quantify themes such as theme colors, font styles, and the placement of images and graphs. These characteristics become input and are output as training datasets for the generative AI model.

[0629] Step 3:

[0630] The server trains a generative AI model based on the extracted design and layout features. It receives quantified design characteristics as input, and the generative AI model learns them iteratively. During the learning process, the model builds imitation patterns and accumulates know-how for effectively generating visual materials. This learning result is obtained as output.

[0631] Step 4:

[0632] The user inputs the topic and design style of the document to be created on the interface via their terminal. This prompt text is sent to the server as input data. Specifically, text such as "I want to create slides for a corporate marketing strategy presentation" is used.

[0633] Step 5:

[0634] The server generates visual materials using a generative AI model based on the user's instructions. Here, the prompt text is fed into the model, which outputs a material design that matches the user's request, and then generates it. The final generated result is saved to the server as output.

[0635] Step 6:

[0636] The server sends the generated visual materials to the terminal and provides them to the user. The output slides and presentation files are input and displayed on the terminal. The user can download them and use them in their work.

[0637] Step 7:

[0638] Users provide feedback on the quality and satisfaction level of the generated visual materials. This evaluation information is sent to the server as input. The server uses this feedback to improve the generating AI model and outputs it as data to continuously improve accuracy, which is then used for retraining.

[0639] Step 8:

[0640] The server retrieves the latest current events information from external sources. It references external APIs and feeds as input to obtain the latest news and trend data. This data is then processed and integrated into visual materials, and the output is included in newly generated materials. This ensures that the materials always reflect the most up-to-date information.

[0641] (Application Example 1)

[0642] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] Traditionally, creating visual advertising materials required specialized knowledge and skills, making it difficult to generate diverse designs quickly and effectively. Furthermore, reflecting the latest trends and effective advertising patterns required considerable effort and time. These issues made it difficult for small businesses and non-expert users to create competitive advertising.

[0644] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0645] In this invention, the server includes means for extracting structural attributes from a set of information recording past visual materials, means for learning an algorithm for generating visual materials based on the extracted structural attributes, means for acquiring the latest event data and integrating it into visual materials, and means for suggesting automatically generated visual materials based on information related to advertising. This enables users to quickly generate effective and timely visual advertising materials without requiring specialized knowledge.

[0646] "Visual materials" are figures, illustrations, graphs, or other visual content used to convey information visually.

[0647] An "information set" is a collection of data that includes past design and layout information.

[0648] "Structural attributes" refer to characteristics such as design elements and layout patterns in visual materials.

[0649] An "algorithm" is a set of steps or computational processes used to solve a specific problem.

[0650] "Instruction data" refers to information that indicates the requests and conditions that users provide when generating visual materials.

[0651] "Evaluation data" refers to information that includes user feedback and opinions on the generated visual materials.

[0652] "Event data" refers to information that reflects the current situation, such as the latest trends and news.

[0653] "Advertising" refers to information intended to promote products or services and increase their market value.

[0654] The system implementing this invention is built around a server and a terminal. The server takes in a large amount of past visual material and records it as an information set. Then, it identifies design elements from the extracted structural attributes and learns an algorithm for generating new visual material based on a generative AI model. The user inputs instruction data from the terminal and determines the specifications of the generated visual material. The terminal allows the user to easily set design themes and requirements through a user interface.

[0655] The server uses deep learning frameworks such as TensorFlow and PyTorch to analyze design patterns and trends. The server also retrieves the latest event data from the internet in real time and integrates it into visual materials, providing resources that reflect current trends and topics.

[0656] As a concrete example, consider a company launching a new advertising campaign using the application. By inputting the product type and target audience on their device, users can receive design suggestions based on an analysis of successful past campaigns. An example of a prompt message might be, "Create advertising visuals to promote a newly launched organic vegetable juice to health-conscious women in their 20s." This allows users without specialized design knowledge to create effective and visually appealing advertisements.

[0657] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0658] Step 1:

[0659] The user inputs instruction data using a terminal. Here, they specify the topic, target audience, and design style of the visual material they want to generate using a user interface. This input data is sent to the server.

[0660] Step 2:

[0661] Based on the received instruction data, the server identifies relevant structural attributes from a collection of historical visual materials. Using database query operations, it extracts design elements corresponding to similar topics and target audiences. This result serves as input for the next step.

[0662] Step 3:

[0663] The server uses the extracted structural attributes to create new visual material design proposals by applying a generative AI model. TensorFlow is used to construct a virtual visual material that reflects the design elements. Experimental design patterns are generated during this process.

[0664] Step 4:

[0665] The server collects real-time information from online sources to integrate the latest event data into the generated design proposals. This includes using news feeds and public APIs from social media. The collected data is incorporated into visual materials, resulting in up-to-date materials that appeal to the target audience.

[0666] Step 5:

[0667] The completed visual materials are sent from the server to the user's device. The user can review and edit the suggested advertising visuals on the device. Based on the displayed materials, the user makes final adjustments. In addition, the user's evaluation feedback is sent to the server and used to train the AI ​​model for future generation.

[0668] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0669] The present invention aims to provide user-adapted visual materials by having an emotion engine recognize the user's emotional state and reflecting that information in the generation and adjustment of the visual materials. This system is operated by combining an artificial intelligence model that learns design and layout based on past visual materials and an emotion engine that senses the user's emotional state.

[0670] The server first collects historical visual materials from companies and educational institutions into a database. This data is used to extract design features and layout characteristics, and serves as foundational information for training an artificial intelligence model. Using this model, the server automatically generates new visual material designs.

[0671] Furthermore, the terminal provides an interface for users to create visual materials and sends user requests to the server, which include new topics and design preferences. The server then uses an artificial intelligence model to generate visual materials based on these requests and sends them back to the terminal.

[0672] The emotion engine analyzes the user's emotional state while they are using the device, utilizing sensors such as the camera and microphone. It recognizes the user's emotional state using their facial expressions, tone of voice, or other biosignals, and sends this information to a server. For example, if a user is feeling stressed, the emotion engine instructs the server to suggest designs and content that evoke feelings of relaxation and friendliness.

[0673] For example, when a user creates a "product introduction presentation," the request entered on the terminal is sent to the server, and an artificial intelligence model is used to generate the initial slides. The emotion engine then senses the user's level of excitement from their facial expressions and voice, and uses this to prompt the server to select energetic designs and visual content.

[0674] Ultimately, feedback from the emotion engine is reflected by the server, and visual materials tailored to the user's current emotions are generated and presented on the device. This process allows the visual materials to adapt to each user's emotional state, increasing their effectiveness and relevance.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] The server collects historical visual material data from companies and educational institutions into a database. This data includes slides, reports, graphs, etc., and is used to extract design patterns and layout features.

[0678] Step 2:

[0679] The server extracts design and layout features from the collected visual materials and uses them to train an artificial intelligence model. This is done using machine learning algorithms to recognize and patternize visual features.

[0680] Step 3:

[0681] The user enters a request to create new visual materials using the interface on their device. Here, they specify the topic, design preferences, theme, and other details.

[0682] Step 4:

[0683] The emotion engine detects the user's current emotional state through the device. This involves analyzing the user's facial expressions and voice using the camera and microphone, and obtaining the results as numerical data.

[0684] Step 5:

[0685] The device sends user requests and the results of the emotion engine's analysis to the server. The server receives this information and generates visual materials using an artificial intelligence model. During generation, a design appropriate to the user's emotional state is applied.

[0686] Step 6:

[0687] The server sends the generated visual materials to the user's device. The user can then review, edit, and adjust these materials. By receiving materials that reflect emotion-based design suggestions, the user is provided with the most suitable presentation.

[0688] Step 7:

[0689] Users provide evaluation information about the generated visual materials via their devices, and the server collects this information to improve the artificial intelligence model. This evaluation information is then used in subsequent generation processes.

[0690] Step 8:

[0691] The server retrieves the latest current events information from external sources and integrates it into visual materials as needed. This ensures that the generated visual materials always contain up-to-date content and provide users with more useful information.

[0692] (Example 2)

[0693] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0694] Traditional methods for creating visual materials fail to reflect the emotional state of users, making it difficult to provide materials tailored to the individual needs of each user. Furthermore, the generated visual materials may not align with the user's requirements or mental state, leading to a decrease in their effectiveness and relevance.

[0695] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0696] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for acquiring emotional information using input / output devices to identify the user's emotional state, and means for adjusting visual materials through a generation program based on the emotional information. This makes it possible to generate visual materials adapted to the user's emotions and provide highly effective and relevant content that cannot be obtained by conventional methods.

[0697] An "information collection" is a structured database system for managing diverse forms of data, including historical visual materials.

[0698] "Design and layout characteristics" refer to the characteristics and patterns related to the composition, style, color, and arrangement of visual materials.

[0699] A "generative program" is an artificial intelligence-based algorithm used to create new visual materials based on design and layout characteristics.

[0700] "User instruction information" refers to information regarding the requests and conditions provided by users when creating visual materials.

[0701] "Input / output devices" refer to sensors used to sense the emotional state of a user, specifically devices such as cameras and microphones.

[0702] "Emotional information" refers to data about the user's mental state, analyzed based on facial expressions, voice tone, and other biosignals acquired through input / output devices.

[0703] "Adjusting visual materials through a generation program" means that, based on acquired emotional information, the generation program dynamically changes and optimizes the design and layout of the visual materials.

[0704] "Evaluation information" refers to user feedback and evaluations of the generated visual materials, which are used to improve the generation program.

[0705] "Information sharing means" refers to communication interfaces and protocols for acquiring current events information from external information sources and integrating it into visual materials.

[0706] This invention aims to provide content adapted to the user's emotional state through a system for generating and adjusting visual materials. This system utilizes a server, a terminal, and a technology called an emotion engine.

[0707] The server stores historical visual materials collected from companies, educational institutions, and other sources in a database. These materials are used to extract design and layout features and as foundational data for training generative programs. The server is equipped with a generative AI model that generates customized visual materials based on user prompts. The generated materials are then sent from the server to the terminal.

[0708] The terminal provides the user with an interface for creating visual materials. The user inputs specific requests into the terminal through prompt messages. This information is sent to the server and used for material generation. The terminal is equipped with input / output devices such as a camera and microphone to acquire emotional information, thereby transmitting the user's emotional state to the server in real time.

[0709] The emotion engine uses sensors built into the device to analyze emotional information from the user's facial expressions and tone of voice. This information is then sent to a server, where a generation program dynamically adjusts the design and layout of visual materials.

[0710] As a concrete example, consider a scenario where a user enters a prompt message such as, "Please create a presentation introducing our new product." This prompt message is sent from the terminal to the server, and the generation AI model uses it to construct initial slides. If the emotion engine, which monitors the user's emotional state, detects, for example, excitement, the generated material is adjusted by the server to a more energetic design. Finally, the server sends the adaptive visual material back to the terminal for the user to receive.

[0711] This system makes it possible to provide effective and relevant visual materials that are tailored to the individual user's emotions and needs.

[0712] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0713] Step 1:

[0714] The server collects historical visual materials from companies and educational institutions into a database. This involves accessing external data sources using web crawlers and APIs and periodically downloading data. The input is visual material files, and the output is structured data stored in the database. Design and layout features are extracted and organized as training data required for AI models.

[0715] Step 2:

[0716] The terminal provides an interface for users to create visual materials. The user enters a prompt, for example, "Please create a presentation introducing a new product." This input information is sent to the server as a data packet. The output is the specific request information sent to the server. At this stage, the input fields are checked and their formatting is automatically corrected to ensure accurate processing of the user's request.

[0717] Step 3:

[0718] The server uses a generative AI model to generate visual materials based on the user prompt text it receives. The input consists of the user prompt text and trained data from a database of past materials. The output is the newly generated visual material (e.g., presentation slides). In this step, the AI ​​model automatically selects and edits design patterns to form a consistent layout.

[0719] Step 4:

[0720] The device's emotion engine detects the user's facial expressions and voice tone through the camera and microphone. The input is real-time data from the sensors, and the output is analyzed emotion information (e.g., whether the user is excited or relaxed). The emotion engine generates data packets to send this information to the server.

[0721] Step 5:

[0722] The server adjusts the visual materials generated based on the received emotional information. Input consists of data from the emotion engine and existing visual materials. Output is the final visual material, customized to the user's emotional state. Specifically, this involves changes to color tones, font size adjustments, and resetting of visual emphasis.

[0723] Step 6:

[0724] The terminal presents the user with the final, adjusted visual materials. The input is the final visual material sent from the server, and the output is the material the user views through the interface. The terminal also collects user feedback and additional evaluation information, which is then sent back to the server. This allows for improvements to the entire system.

[0725] (Application Example 2)

[0726] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0727] In generating visual materials, conventional technologies have been insufficient in adjusting designs and content to reflect the emotional state of users, making it difficult to provide materials that are optimal for individual users. Furthermore, the lack of means to change elements of visual materials in real time made it difficult to immediately adapt to users' emotions, thus maximizing advertising effectiveness.

[0728] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0729] In this invention, the server includes means for extracting design and layout features from an information set recording past visual materials, means for learning an artificial intelligence model that generates visual materials based on the extracted design and layout features, and means for recognizing the user's emotional state and adjusting the generated visual materials based on that emotional state. This enables real-time adjustment of visual materials according to the user's emotional state, allowing for the provision of more effective advertisements and content.

[0730] An "information set" is a collection of data, including past visual materials, that serves as the basis for extracting design and layout features.

[0731] "Design and layout characteristics" refer to elements that indicate the design style and layout characteristics of visual materials, and are used to train artificial intelligence models.

[0732] An "artificial intelligence model" is a computer program based on algorithms that learn patterns and features from data and generate new visual materials.

[0733] "User emotional state" refers to the user's psychological or physiological responses as perceived through cameras and audio devices, and is reflected in the adjustment of visual materials.

[0734] A "smart device" is an electronic device that can connect to the internet and is equipped with sensors such as cameras and audio devices, and is used to acquire data on emotional states.

[0735] An "interface" is an interface through which a user interacts with a system, and it plays a role in collecting instructional information and emotional information.

[0736] The system used to realize this application has the function of generating visual materials that adapt to the user's emotional state. The server first records past visual materials as an information collection in a database, extracts the design and arrangement features of these materials, and uses them to train an artificial intelligence model. The artificial intelligence model is an algorithm that creates new visual materials from this data.

[0737] When a user inputs instructions from their device, that information is sent to the server. Based on the received instructions, the server uses an artificial intelligence model to generate visual materials and provides them to the device.

[0738] Meanwhile, smart devices recognize the user's emotional state in real time through cameras and audio devices while the user is viewing visual materials. The user obtains information about their emotional state via the smart device and sends it to the server. The server adjusts the visual materials based on this emotional information, specifically changing the colors, layout, and design elements.

[0739] For example, if a user shows signs of excitement while viewing an advertisement, the server can recommend more vibrant color patterns or dynamic designs. Adding stimulating visual effects, for instance, can enhance the persuasiveness of the advertisement. In this way, the effectiveness of visual materials is maximized through real-time adjustments based on emotional states.

[0740] The generative AI model operates according to specific prompts. For example, it might be instructed to "adjust the design of the visual materials to be more impactful if the user's emotional state is 'excited'." This prompt triggers information processing, generating more relevant materials.

[0741] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0742] Step 1:

[0743] The server records past visual data in a database and extracts design and placement features from it. The input is the visual data stored in the database, and the output is the design and placement features. These features are processed by an artificial intelligence model and used as foundational data for generating visual data. Specifically, data analysis algorithms are used to identify patterns in visual elements and construct feature data.

[0744] Step 2:

[0745] The user sends instruction information to the server via their device. The input is the user's instruction information (e.g., a request for a new design), and the output is a prompt message from the generative AI model corresponding to that instruction. The server parses the instruction information as text and generates a prompt message. This prompt message is sent to the generative AI model and serves as guidance for generating visual materials.

[0746] Step 3:

[0747] The server uses the received prompt text to run a generative AI model and construct an initial design for generating visual materials. The input is the prompt text, and the output is the initial visual material. The server combines the design elements using an AI algorithm to form the initial visual material.

[0748] Step 4:

[0749] The user uses the camera and voice equipment of a smart device to recognize their emotional state in real time and send that data to a server. The input is emotional information obtained from the user's facial expressions and tone of voice, and the output is analyzed emotional state data. The smart device acquires sensor data and identifies the user's psychological state by analyzing the emotional information.

[0750] Step 5:

[0751] The server adjusts the visual materials based on the acquired emotional state. The input is the analyzed emotional state data and the initial visual materials, and the output is the final adjusted visual materials. In this process, design elements are optimized according to the emotional state, and the impact of the content is maximized by adjusting the visual effects. Specifically, this involves color changes and the addition of dynamic effects.

[0752] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0753] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0754] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0755] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0756] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0757] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0758] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0759] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0760] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0761] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0762] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0763] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0764] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0765] 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.

[0766] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0767] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0768] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0769] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0770] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0771] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0772] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0773] The following is further disclosed regarding the embodiments described above.

[0774] (Claim 1)

[0775] A means of extracting design and layout features from a collection of information that records past visual materials,

[0776] A means for training an artificial intelligence model that generates visual materials based on extracted design and layout features,

[0777] A means for receiving instruction information from a user and generating visual materials using the artificial intelligence model based on said instruction information,

[0778] Means for providing generated visual materials to users,

[0779] A means for receiving evaluation information from users and improving the artificial intelligence model based on said evaluation information,

[0780] A means of acquiring the latest current events information and integrating it into visual materials,

[0781] A system that includes this.

[0782] (Claim 2)

[0783] The system according to claim 1, which provides a user interface for generating visual materials and collects instruction information and evaluation information from the user.

[0784] (Claim 3)

[0785] The system according to claim 1, further comprising information sharing means for obtaining the latest current events information from an external information source.

[0786] "Example 1"

[0787] (Claim 1)

[0788] A means of extracting design and layout features from a collection of information that records past visual materials,

[0789] A means for training a generative model that generates visual materials based on extracted design and layout features,

[0790] A means for receiving instruction information from a user and generating visual materials using the generation model based on said instruction information,

[0791] A means of sending the results processed on the server to a terminal and providing the generated visual material to the user,

[0792] A means for receiving evaluation information from users and improving the generation model based on said evaluation information,

[0793] A means of obtaining the latest current events information from external sources and integrating it into visual materials,

[0794] A system that includes this.

[0795] (Claim 2)

[0796] The system according to claim 1, which provides an interface for generating visual materials and collects instruction information and evaluation information from the user.

[0797] (Claim 3)

[0798] The system according to claim 1, further comprising information sharing means for obtaining the latest current events information from external sources.

[0799] "Application Example 1"

[0800] (Claim 1)

[0801] A means of extracting structural attributes from a collection of information that records past visual materials,

[0802] A means of learning an algorithm that generates visual materials based on extracted structural attributes,

[0803] A means for receiving instruction data from a user and generating visual materials using the algorithm based on said instruction data,

[0804] A means of presenting the generated visual materials to the user,

[0805] A means for receiving evaluation data from users and improving the algorithm based on said evaluation data,

[0806] A means of acquiring the latest event data and integrating it into visual materials,

[0807] A means of suggesting automatically generated visual materials based on information related to advertising,

[0808] A mechanism that includes this.

[0809] (Claim 2)

[0810] The mechanism according to claim 1, which provides a user interface for generating visual materials and collects instruction data and evaluation data from the user.

[0811] (Claim 3)

[0812] The mechanism according to claim 1, further comprising information linkage means for obtaining the latest event data from an external information provision medium.

[0813] "Example 2 of combining an emotion engine"

[0814] (Claim 1)

[0815] A means of extracting design and layout features from a collection of information that records past visual materials,

[0816] A means for training a generation program that generates visual materials based on extracted design and layout features,

[0817] A means for receiving user instruction information and generating visual materials using a generation program based on said instruction information,

[0818] Means for providing generated visual materials to users,

[0819] A means of acquiring emotional information using an input / output device to identify the emotional state of a user,

[0820] Means for adjusting visual materials through the generation program based on emotional information,

[0821] A means for receiving user evaluation information and improving the generation program based on said evaluation information,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, which provides a user interface for generating visual materials and collects instruction information, emotional information, and evaluation information from the user.

[0825] (Claim 3)

[0826] The system according to claim 1, further comprising information linking means for acquiring information from external information sources and integrating it into visual materials.

[0827] "Application example 2 when combining with an emotional engine"

[0828] (Claim 1)

[0829] A means for extracting design and layout features from a collection of information recording past visual materials,

[0830] A means for training an artificial intelligence model that generates visual materials based on extracted design and placement features,

[0831] A means for receiving instruction information from a user and generating visual materials using the artificial intelligence model based on said instruction information,

[0832] Means for providing generated visual materials to users,

[0833] A means for recognizing the user's emotional state and adjusting the visual materials generated based on that emotional state,

[0834] A means for acquiring biometric information and analyzing emotional state via the camera and audio equipment of a smart device,

[0835] A means of changing the visual elements of visual materials in real time based on the analyzed emotional state,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, which provides an interface for user involvement in the generation of visual materials and collects instruction information and emotional information from the user.

[0839] (Claim 3)

[0840] The system according to claim 1, wherein the smart device is used as an interface device. [Explanation of Symbols]

[0841] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of extracting design and layout features from a collection of information that records past visual materials, A means for training an artificial intelligence model that generates visual materials based on extracted design and layout features, A means for receiving instruction information from a user and generating visual materials using the artificial intelligence model based on said instruction information, Means for providing generated visual materials to users, A means for receiving evaluation information from users and improving the artificial intelligence model based on said evaluation information, A means of acquiring the latest current events information and integrating it into visual materials, A system that includes this.

2. The system according to claim 1, which provides a user interface for generating visual materials and collects instruction information and evaluation information from the user.

3. The system according to claim 1, further comprising information sharing means for obtaining the latest current events information from an external information source.

Images