System

Abstract

A system is provided.SOLUTION: A system for automatically generating security enlightenment content on the Internet, comprising: means for a user to input generation requirements; means for a server to receive and analyze the input requirements; means for selecting and activating a generative AI model based on the generation requirements; means for generating required text, images, and sounds by the generative AI model to create content; means for verifying and, if necessary, optimizing the generated content; means for sending the optimized content to the user; means for performing regeneration based on user feedback; and means for delivering the generated content.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] A common problem faced by all users and companies using the Internet is a lack of security knowledge. This increases the risk of falling victim to phishing scams and other cyber attacks. However, it is difficult for many users to find time to continually learn about security, and companies also require a significant amount of man-hours to create security awareness content. This invention solves these problems and provides a means to create security awareness content efficiently and effectively. [Means for solving the problem]

[0005] The present invention provides a system that automatically generates security awareness content using generative AI. This system includes the following means: a means for a user to input generation requirements, a means for a server to receive and analyze the input requirements, a means for selecting and activating a generative AI model based on the generation requirements, a means for generating the necessary text, images, and audio using the generative AI model to create content, a means for verifying the quality of the generated content and optimizing it as necessary, a means for sending the optimized content to the user, a means for regenerating the content based on user feedback, and a means for distributing the generated content, thereby efficiently and effectively generating security awareness content, thereby raising the level of security knowledge of users and companies and preventing damage.

[0006] "User" means an individual or organization that utilizes the System to request the generation of security awareness content.

[0007] "Terminal" refers to the device (e.g., PC, smartphone) used by a User to access the System and enter and confirm production requirements.

[0008] "Server" refers to the computing system at the center of the system that receives and analyzes requirements from users and manages and operates generative AI models.

[0009] "Generation requirements" refers to information that indicates the specific characteristics and conditions (e.g., theme, format, length) of the content that a user wants to generate.

[0010] "Generative AI model" refers to an artificial intelligence model that is trained to generate media such as text, images, or audio.

[0011] "Text" refers to sentences and explanations generated as part of security awareness content.

[0012] "Images" refers to visual graphics and illustrations generated as part of security awareness content.

[0013] "Audio" refers to narration and sound effects generated as part of the security awareness content.

[0014] "Content" refers to digital media, such as security awareness videos, images, and audio, created by a generative AI model based on user generation requirements.

[0015] "Quality Verification" refers to the process of evaluating the quality (e.g., sound quality, image quality, length) of generated content and making corrections or optimizations as necessary.

[0016] "Optimization" refers to automatic adjustments and corrections made to improve the quality of the generated content.

[0017] "Feedback" refers to information provided by a user to the system regarding opinions and requests for corrections to generated content.

[0018] "Regeneration" refers to the process of recreating content using a generative AI model based on user feedback. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention relates to a system that automatically generates security awareness content using generative AI. The system is composed of a server, a terminal, a generative AI model, and other components.

[0041] System configuration

[0042] The system includes the following elements:

[0043] Terminal: Provides an interface for users to input production requirements, review, feedback, and finally deliver the generated content.

[0044] Server: A central computing system that receives and analyzes production requirements, selects appropriate generative AI models, and generates, validates, optimizes, and regenerates content.

[0045] Generative AI model: An artificial intelligence model for generating media such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[0046] Program processing explanation

[0047] 1. Enter your content requirements

[0048] Users input the requirements for the content they want to generate through their device, including the purpose, theme, length, and format of the video.

[0049] 2. Submit your requirements

[0050] The device sends the input requirements to the server, which analyzes the received requirements and determines the required generative AI model.

[0051] 3. Launching the Generative AI

[0052] The server selects and activates the appropriate generative AI model based on the analysis results. For example, when creating a short video to combat phishing scams, it activates a text generation AI, an image generation AI, and a voice generation AI.

[0053] 4. Content Generation

[0054] The generative AI model generates content based on user requirements, such as phishing scenarios, warning images, explanatory illustrations, and narration audio.

[0055] 5. Content validation and optimization

[0056] The server verifies the quality of the generated content, checking parameters such as audio quality, video quality, and length, and automatically correcting and optimizing as needed.

[0057] 6. Preparing content for distribution

[0058] The optimized content is sent from the server to the device for the user to review, and if the user is not satisfied, they can enter feedback.

[0059] 7. Feedback and Regeneration

[0060] Once the user submits their feedback, the server re-analyzes it and re-runs the generative AI model, repeating this process until content that satisfies the user is generated.

[0061] 8. Finalize and distribute content

[0062] After the user has final confirmation and is satisfied with the content, they can upload it to social media or their website, allowing the security awareness content to reach a wider audience.

[0063] Specific examples

[0064] Short video generation to combat phishing scams

[0065] 1. Enter your content requirements

[0066] The user uses a device to input the requirements for a "one-minute short video about phishing scams." Input items include "phishing scams," "one minute," and "video format."

[0067] 2. Submit your requirements

[0068] The terminal sends the input requirements to the server, which receives the request and starts requirement analysis.

[0069] 3. Launching the Generative AI

[0070] Based on the analysis results, the server selects and activates an appropriate AI model, such as text generation AI, image generation AI, or voice generation AI.

[0071] 4. Content Generation

[0072] The text generation AI generates phishing scam scenarios and points to watch out for, the image generation AI generates related warning images and explanatory illustrations, and the audio generation AI generates narration audio.These are then combined to create a one-minute short video.

[0073] 5. Content validation and optimization

[0074] The server verifies the quality of the video and optimizes the sound and image quality.

[0075] 6. Preparing content for distribution

[0076] The optimized video is sent from the server to the terminal and viewed by the user.

[0077] 7. Feedback and Regeneration

[0078] The user provides feedback as needed and the server regenerates it.

[0079] 8. Finalize and distribute content

[0080] After the user confirms it, they can upload the generated video to social media or their website.

[0081] As a result, the present invention can efficiently and effectively generate security awareness content, thereby raising the level of security knowledge of users and companies.

[0082] The processing flow will be explained below.

[0083] Step 1:

[0084] The user inputs the requirements for the content they want to generate using their device (e.g., a one-minute short video about phishing scams). Specifically, they input information such as the theme, format, length, and purpose into the device's input form.

[0085] Step 2:

[0086] The terminal transmits the input requirements to the server. Specifically, the terminal transmits the requirement data to the server using an HTTP request.

[0087] Step 3:

[0088] The server receives the input requirements and performs analysis. Specifically, it analyzes the received data and extracts each parameter (e.g., topic, format, length).

[0089] Step 4:

[0090] The server selects and activates the appropriate generative AI model based on the analysis results. Specifically, it selects the text generation AI, image generation AI, and voice generation AI necessary for generating short videos to combat phishing scams.

[0091] Step 5:

[0092] The generative AI model generates content such as text, images, and audio. Specifically, the text generation AI generates the scenario, the image generation AI generates the related images, and the audio generation AI generates the narration audio.

[0093] Step 6:

[0094] The server aggregates the generated content, specifically creating a video file using the generated text, images, and audio.

[0095] Step 7:

[0096] The server verifies the quality of the generated content and optimizes it if necessary, specifically by checking audio and video quality and applying automatic corrections and enhancements.

[0097] Step 8:

[0098] The server sends the optimized content to the device. Specifically, it generates a content URL so that the user can view it and notifies the device.

[0099] Step 9:

[0100] The user views the generated content through their device, specifically by accessing the provided URL and watching the video.

[0101] Step 10:

[0102] The user enters feedback and sends it to the server. Specifically, the user enters feedback in the evaluation form and presses the submit button.

[0103] Step 11:

[0104] The server receives the feedback and initiates the regeneration process if necessary, specifically by analyzing the regeneration points and relaunching the associated generative AI models.

[0105] Step 12:

[0106] The user then performs a final check and uploads the generated content to social media or their website. Specifically, they download the generated video file and post it to each platform.

[0107] Example 1

[0108] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0109] In today's world, security awareness education via the Internet is extremely important. However, manually creating security awareness content requires a significant amount of time and expertise, making it difficult to generate content efficiently. It is also difficult to consistently improve the quality of generated content or quickly improve it based on feedback. For this reason, there is a need for a system that uses generative AI to automatically generate, optimize, and distribute high-quality security awareness content.

[0110] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0111] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the analysis results, means for generating necessary media data using a generative AI model including a text generator, an image generator, and a voice generator to create content, means for verifying the quality of the generated content and automatically correcting or optimizing it as necessary, means for transmitting the optimized content to the user, means for regenerating the content based on user feedback, and means for preparing the generated content after final confirmation for distribution and distributing it to multiple platforms. This enables the automatic generation and rapid correction of high-quality security awareness content based on user requirements.

[0112] "User" means a person or organization that uses the system to generate, review, and distribute security awareness content.

[0113] "Server" is a central computer system that analyzes the generation requirements entered by the user, selects, launches, and executes the appropriate generative AI model, and validates, optimizes, and delivers the generated content.

[0114] The "creation requirements" are information including detailed requests such as the purpose, theme, length, and format of the content the user wants to create.

[0115] A "generative AI model" is an artificial intelligence model used to generate media data such as text, images, and audio, and specifically includes text generators, image generators, and audio generators.

[0116] A "text generator" is a device that generates necessary text data based on user requirements.

[0117] An "image generating device" is a device that generates the necessary image data based on the user's requirements.

[0118] A "voice generating device" is a device that generates necessary voice data based on the user's requirements.

[0119] "Media data" refers to all data that forms content, such as text, images, and audio.

[0120] "Content" refers to a collection of data, including text, images, audio, etc., generated and optimized by a generative AI model for security awareness purposes.

[0121] "Feedback" is information including users' evaluations of the generated content and requests for improvement.

[0122] "Auto-remediation" is the process by which the server verifies the quality of generated content and automatically makes corrections as needed.

[0123] "Optimization" is the process of improving the generated content according to quality and user requirements.

[0124] "Distribution" is the process of publishing the final, verified generated content to multiple platforms.

[0125] "Platform" refers to a website, social networking site, or other online service for distributing Generated Content.

[0126] The present invention relates to a system that automatically generates security awareness content by utilizing a generative AI model. The system is configured by combining a server, a terminal, a generative AI model, etc. The configuration and operation for specifically implementing the present invention are described below.

[0127] System configuration

[0128] The system includes the following elements:

[0129] Terminal: A device through which a user inputs content generation requirements, checks, provides feedback, and finally distributes the generated content.

[0130] Server: A central computing system that receives and analyzes the generation requirements from users, selects and launches appropriate generative AI models, and generates, validates, optimizes, and regenerates content.

[0131] Generative AI model: An artificial intelligence model for generating media data such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[0132] Program processing

[0133] 1. Enter your content requirements

[0134] Users input the requirements for the content they want to generate through their device. Input items include the purpose, theme, length, format, etc. of the video. For example, they input the requirements for a "one-minute short video about phishing scams."

[0135] 2. Submit your requirements

[0136] The device sends the input requirements to the server, which analyzes the received requirements and selects a generative AI model suitable for content generation.

[0137] 3. Launching the Generative AI

[0138] Based on the analysis results, the server selects and activates a generative AI model, including a text generator, an image generator, and a voice generator. For example, when creating a short video to combat phishing scams, these three devices work together.

[0139] 4. Content Generation

[0140] The generative AI model generates the necessary media data based on the user's requirements. For example, it uses a text generator to create a scenario, an image generator to generate warning images and explanatory illustrations, and a voice generator to generate narration. These are then integrated to create content in the form of a one-minute short video.

[0141] 5. Content validation and optimization

[0142] The server verifies the quality of the generated content, checking audio quality, image quality, length, and script consistency, and automatically corrects and optimizes it if necessary.

[0143] 6. Preparing content for distribution

[0144] The optimized content is sent from the server to the device for user confirmation, and the user can preview the generated content through the device and provide feedback as needed.

[0145] 7. Feedback and Regeneration

[0146] When the user submits feedback from their device, the server re-analyzes and re-runs the necessary generative AI models, repeating this process until the user is satisfied.

[0147] 8. Finalize and distribute content

[0148] If the user is satisfied with the content after final confirmation, they can issue a command to upload it to a social networking site or website from their device. The server then formats the content for distribution and distributes it to the specified platform.

[0149] Specific examples

[0150] For example, to generate a one-minute short anti-phishing video, use the following prompt:

[0151] "Create a short 1-minute video about phishing scams. Please include the following:

[0152] Phishing scam method explained

[0153] Examples of fraudulent emails and how to deal with them

[0154] Attention to viewers

[0155] As a result, the present invention can efficiently and effectively generate security awareness content and improve the security knowledge of users and organizations.

[0156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0157] Step 1:

[0158] The user inputs the generation requirements using a terminal.

[0159] Specifically, the user inputs the prompt for a "one-minute short video about phishing scams." The input data includes information such as "phishing scams," "one minute," and "video format." This input information is then saved on the device.

[0160] Step 2:

[0161] The terminal transmits the requirements input by the user to the server.

[0162] Specifically, the device sends input data in JSON format or other appropriate data format to the server. The sent data includes the purpose, theme, length, format, etc. The server receives this data and begins analyzing it. Input data: "Phishing scam," "1 minute," "Video format"

[0163] Output data: Parsed requirements

[0164] Step 3:

[0165] The server analyzes the received requirements and selects the optimal generative AI model.

[0166] The server determines which generative AI models (text generator, image generator, and voice generator) are needed based on the analyzed requirements. For example, a short video to combat phishing requires these three generative AI models. Input data: Analyzed requirements

[0167] Output data: Selected generative AI model

[0168] Step 4:

[0169] The server launches the selected generative AI model.

[0170] The server uses an interface such as a REST API to launch the generative AI model and begin the generation process. For example, it sends instructions such as "Generate a phishing scam scenario" to the text generator and "Convert the generated scenario into audio" to the voice generator. Input data: Selected generative AI model

[0171] Output data: Start command

[0172] Step 5:

[0173] A generative AI model generates content based on user requirements.

[0174] Specifically, the text generator creates a phishing scam scenario, the image generator generates related warning images and explanatory illustrations, and the audio generator generates a narration based on the generated scenario. These are then integrated to create a one-minute short video. Input data: Generation requirements

[0175] Output Data: Generated Content

[0176] Step 6:

[0177] Validate the quality of the server-generated content.

[0178] Specifically, it checks the sound quality, image quality, content length, and consistency of the scenario, and automatically corrects or optimizes it if necessary. For example, if there are any unclear parts of the audio, it issues instructions to the audio generator again. Input data: Generated content

[0179] Output: Optimized content

[0180] Step 7:

[0181] The server sends the optimized content to the device for the user to view.

[0182] Specifically, the server converts the generated content into the appropriate format and sends a preview link or file to the device. The user can preview the generated video using this link. Input data: Optimized content

[0183] Output data: Preview link or file

[0184] Step 8:

[0185] The user inputs feedback through the terminal and transmits it to the server.

[0186] Specifically, users input specific feedback such as "Please make the video a little shorter" or "Please make the illustrations easier to understand." The device then sends this feedback to the server. Input data: User feedback

[0187] Output data: Feedback data

[0188] Step 9:

[0189] The server analyzes the feedback and re-runs any necessary generative AI models.

[0190] For example, based on feedback such as "Please shorten the length of the video," the system issues instructions to the text generator and modifies the scenario. This process is repeated until the user is satisfied. Input data: Feedback data

[0191] Output Data: Regenerated content

[0192] Step 10:

[0193] If the user is satisfied with the generated content after making a final check, they can issue instructions from their device to upload it to a social networking site or their homepage.

[0194] The server formats the content for distribution and distributes it to the specified platform, ensuring that the security awareness content reaches a wide audience. Input data: Final confirmation and distribution instructions

[0195] Output data: Streamed content

[0196] (Application example 1)

[0197] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0198] Despite the growing importance of security on the Internet in recent years, it is difficult to effectively communicate security alerts to users in an easy-to-understand manner. In particular, there is a demand for a system that can automatically and quickly generate content to promote awareness of specific threats such as phishing scams, but current technology is unable to meet this demand. In addition, optimizing the quality of the generated content based on user feedback is also an important issue.

[0199] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0200] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the generation requirements, means for generating the necessary text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means for sending the optimized content to the user, means for regenerating the content based on user feedback, means for the user to make final confirmation, and means for distributing the generated content to a platform on the Internet. This makes it possible to quickly and effectively generate security awareness content and promote user understanding.

[0201] "User" is the entity that inputs requirements for the generation of security awareness content, reviews the generated content, and provides feedback as needed.

[0202] "Generation requirements" are information that indicates the detailed specifications and requests for the security awareness content that a user wants to generate.

[0203] "Server" means a central computing system that analyzes the generation requirements received from the User, selects and launches an appropriate generative AI model, validates and optimizes the generated content, and transmits it to the User.

[0204] A "generative AI model" is an artificial intelligence model that generates media such as text, images, and audio, and performs appropriate generation as needed.

[0205] "Text" refers to sentences or character information generated by a generative AI model.

[0206] "Image" means a visual graphic or illustration generated by a generative AI model.

[0207] "Audio" refers to auditory narration or audio data generated by a generative AI model.

[0208] "Content" means comprehensive security awareness information, including text, images, and audio, generated by a generative AI model.

[0209] "Quality verification" is the process of checking the quality of each element of generated content (text, images, audio) and making corrections or improvements as necessary.

[0210] "Optimization" is the process of automated adjustments and refinements based on quality validation results to improve the quality of the generated content.

[0211] "Feedback" refers to opinions and requests provided by users regarding generated content.

[0212] "Regeneration" is the process of regenerating content by running the generative AI model again based on user feedback.

[0213] "Means of Final Review" means the means by which a user reviews and approves the final version of the generated content.

[0214] "Distribution" is the process of publishing the finalized security awareness content on an internet platform to reach a wide audience.

[0215] The present invention is a system for automatically generating security awareness content, with the aim of providing effective education on security threats on the Internet in particular. The system automates the process of optimizing and distributing the content generated based on user input requirements.

[0216] System Components

[0217] 1. Terminal: A device that allows users to input production requirements, review the generated content, and provide feedback if necessary. Terminals include smartphones, personal computers, tablets, etc.

[0218] 2. Server: The server is a central computing system that analyzes the generation requirements received from users, selects and launches an appropriate generative AI model, validates and optimizes the generated content, and finally sends it to users.

[0219] 3. Generative AI models: These include text generation models, image generation models, and speech synthesis models. For example, natural language processing models (GPT-4) are used for text generation, generative adversarial networks (GANs) are used for image generation, and WaveNet is used for speech synthesis.

[0220] Program processing explanation

[0221] 1. Enter content generation requirements

[0222] The user uses a device to input the requirements for the security awareness content they want to generate. This can be a detailed request, such as "a five-minute video about phishing scams." The input requirements are sent from the device to the server.

[0223] 2. Requirements Analysis

[0224] The server analyzes the generation requirements received from the user and selects the appropriate generative AI model. For example, if the request is for a "5-minute video," a text generation model, an image generation model, and a speech synthesis model will be activated.

[0225] 3. Content Generation

[0226] The generative AI model runs on the server and generates text, images, and audio according to the user's requirements, including phishing scenarios, warning images, explanatory illustrations, and audio narration.

[0227] 4. Quality verification and optimization

[0228] The generated content is verified by the server for quality, checking parameters such as sound quality, image quality, and content length, and optimizing it if necessary.

[0229] 5. Feedback processing and regeneration

[0230] The optimized content is sent to the device for review by the user, who provides feedback, which the server analyzes and regenerates if necessary.

[0231] 6. Finalize and distribute content

[0232] Once the user has given a final review and is satisfied with the generated content, the content is distributed to a platform on the Internet.

[0233] Hardware and software used

[0234] Hardware: Smartphones, personal computers, servers

[0235] Software: Natural language processing model (GPT-4), image generation model (GANs), speech synthesis model (WaveNet)

[0236] Specific examples

[0237] Input prompt example

[0238] A user fills out a form in your app with:

[0239] Content Topic:Phishing

[0240] Content format: 5-minute short videos

[0241] Video length: 5 minutes

[0242] Target audience: general users

[0243] Part of the processing flow

[0244] The prompts entered by the user are sent to the server, which then activates the generative AI model to generate text, images, and audio. The generated content is then sent to the device after quality verification, where it is regenerated after user confirmation and feedback, and finally distributed to the platform after final confirmation.

[0245] This invention makes it possible to generate security awareness content quickly and effectively, and is expected to improve users' security awareness.

[0246] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0247] Step 1:

[0248] The user inputs the generation requirements using a terminal. Input items include the content theme, format, length, and target audience. This input data is sent from the terminal to the server. Input examples include "Content theme: phishing scams," "Content format: 5-minute short video," and "Target audience: general users."

[0249] Step 2:

[0250] The server receives and analyzes the generation requirements sent from the device. Specifically, it uses natural language processing (NLP) to analyze the user's requirements as text data and selects an appropriate generation AI model. For example, if the theme "phishing scam" is detected, it selects a generation AI model specialized in phishing scams.

[0251] Step 3:

[0252] The server selects and launches an appropriate generative AI model based on the analysis results. The selected generative AI models include a text generation model (GPT-4), an image generation model (DALL-E), and a speech synthesis model (WaveNet). For example, these models are launched sequentially according to the requirement of a "5-minute short video."

[0253] Step 4:

[0254] The generative AI model generates content based on user requirements. Specifically, the text generation model generates phishing scam scenarios, the image generation model generates warning images and explanatory illustrations, and the speech synthesis model generates narration. The data generated by each model is integrated to create a single content file.

[0255] Step 5:

[0256] The server verifies the quality of the generated content and optimizes it as necessary. Specifically, it automatically checks parameters such as sound quality, image quality, and length, and makes corrections as necessary. Based on the results of this verification, if the quality of the generated content does not meet certain standards, it will automatically make corrections.

[0257] Step 6:

[0258] The optimized content is sent from the server to the terminal. The user checks the generated content on the terminal and inputs feedback. For example, the user may provide feedback such as "I would like the sound quality of the narration to be improved."

[0259] Step 7:

[0260] User feedback is sent to the server, which analyzes it and, if necessary, re-launches the generative AI model to regenerate new content that reflects the feedback.

[0261] Step 8:

[0262] The server resends the content to the device for the user to check. If the user is satisfied with the content after checking it, the content is distributed to an internet platform. For example, a specific distribution method such as "upload to SNS" is selected.

[0263] Through the above processing steps, users can easily create high-quality security awareness content and deliver it to a wide audience.

[0264] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0265] This invention combines an emotion engine with a system that automatically generates security awareness content using generative AI. This system is composed of a server, a terminal, a generative AI model, an emotion engine, etc.

[0266] System configuration

[0267] The system includes the following elements:

[0268] Terminal: Provides an interface for users to input generation requirements, review the generated content, get feedback, obtain sentiment data, and finally deliver it.

[0269] Server: A central computing system that receives and analyzes generative requirements, and manages and operates the appropriate generative AI models and emotion engines.

[0270] Generative AI model: An artificial intelligence model for generating media such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[0271] Emotion Engine: Recognizes user emotions and provides data to help adjust production requirements, optimize content, and regenerate it.

[0272] Program processing explanation

[0273] 1. Enter your content requirements

[0274] The user inputs the requirements for the content they want to generate through their device. Input items include the purpose, theme, length, and format of the video. The emotion engine reads the user's emotions from their facial expressions and voice and adjusts the generation requirements accordingly.

[0275] 2. Submit your requirements

[0276] The terminal transmits the input requirements and emotion data generated by the emotion engine to the server. Specifically, the terminal transmits the requirements data and emotion data to the server using an HTTP request.

[0277] 3. Receiving and analyzing requirements

[0278] The server receives the input requirements and performs analysis. The received data is analyzed to extract each parameter (e.g., theme, format, length). Emotion data is also analyzed at this time.

[0279] 4. Selecting and starting the generation AI

[0280] The server selects and activates the appropriate generative AI model based on the analysis results. For example, it selects the text generation AI, image generation AI, and voice generation AI needed to generate short videos to combat phishing scams.

[0281] 5. Content Generation

[0282] The generative AI model generates content such as text, images, and audio. For example, a text generation AI generates a scenario, an image generation AI generates related images, and an audio generation AI generates narration audio. Based on data from the emotion engine, content is generated that matches the user's preferences and mood.

[0283] 6. Content validation and optimization

[0284] The server verifies the quality of the generated content, checking parameters such as sound quality, image quality, and length, and automatically correcting or optimizing as necessary. By taking into account data from the emotion engine, the content is more suited to the user's emotions.

[0285] 7. Preparing content for distribution

[0286] The optimized content is sent from the server to the device for the user to review, and data obtained from the emotion engine also helps with the review.

[0287] 8. Feedback and Regeneration

[0288] The user enters feedback and sends it to the server. The server receives the feedback and emotion data, reanalyzes it, and reruns the generative AI model as needed to regenerate the data.

[0289] 9. Finalize and distribute content

[0290] If the user is satisfied with the content after final confirmation, they can upload it to social media or their website. Based on the data obtained by the emotion engine, the content can be delivered in the most appropriate way for the user.

[0291] Specific examples

[0292] Short video generation to combat phishing scams

[0293] 1. Enter content requirements

[0294] The user inputs the requirements for a "one-minute short video about phishing scams" using a terminal. The emotion engine reads emotional data from the user's facial expressions and voice and adjusts the requirements accordingly.

[0295] 2. Submit your requirements

[0296] The terminal transmits the input requirements and emotion data to the server.

[0297] 3. Receiving and analyzing requirements

[0298] The server analyzes the requirements, selects the appropriate generative AI model and emotion engine, and performs the analysis.

[0299] 4. Selecting and starting the generation AI

[0300] The server selects and activates text generation AI, image generation AI, and voice generation AI.

[0301] 5. Content Generation

[0302] The text generation AI generates phishing scam scenarios and points to watch out for, the image generation AI generates related warning images and explanatory illustrations, and the voice generation AI generates narration. Based on data from the emotion engine, content tailored to the user's preferences is generated.

[0303] 6. Content validation and optimization

[0304] The server verifies the quality of the video and optimizes the audio and video quality, taking into account the data from the emotion engine.

[0305] 7. Preparing content for distribution

[0306] The optimized video is sent from the server to the terminal and viewed by the user.

[0307] 8. Feedback and Regeneration

[0308] The user enters feedback and sends it to the server, which then reanalyzes it and reruns the generative AI model to regenerate it.

[0309] 9. Finalize and distribute content

[0310] The user then finalizes the video and uploads it to social media or their website. Based on the data from the emotion engine, the video is distributed in the most appropriate way for the user.

[0311] As a result, the present invention can efficiently and effectively generate security awareness content and raise the level of security knowledge of users and companies. Furthermore, by combining it with an emotion engine, it is possible to provide content that is suited to the user's emotions.

[0312] The processing flow will be explained below.

[0313] Step 1:

[0314] The user inputs the requirements for the content they wish to generate using their device. Specifically, they enter information such as "phishing scam," "1 minute," and "video format" into the device's input form. At this time, the emotion engine analyzes the user's facial expressions and voice in real time to collect emotional data.

[0315] Step 2:

[0316] The terminal transmits the input requirements and emotion data to the server. Specifically, an HTTP request including the requirement information and emotion data is transmitted to the server.

[0317] Step 3:

[0318] The server receives the requirements and emotional data and performs analysis, extracting parameters (e.g., topic, format, length) from the received data, and also analyzes the emotional data to determine the user's current emotional state.

[0319] Step 4:

[0320] The server selects and activates the appropriate generative AI model based on the analysis results, selecting the necessary text generation AI, image generation AI, and voice generation AI, and customizing the generation process based on emotion data.

[0321] Step 5:

[0322] The generative AI model generates content such as text, images, and audio. Specifically, the text generation AI creates a phishing scam scenario, the image generation AI generates related images, and the audio generation AI generates narration audio. Emotional data is used to generate content with a tone and style that matches the user's emotions.

[0323] Step 6:

[0324] The server aggregates the generated content, specifically creating a one-minute short video using the generated text, images, and audio.

[0325] Step 7:

[0326] The server verifies the quality of the generated content and optimizes it. Specifically, it checks the audio and video quality, removes or modifies unnecessary elements, and takes into account emotional data to optimize the content in a way that is likely to be perceived favorably by users.

[0327] Step 8:

[0328] The server sends the optimized content to the device, specifically by generating and notifying the user of the content URL so that the user can view it.

[0329] Step 9:

[0330] The user checks the generated content through their device. Specifically, they access the provided URL and watch the video, and the emotion engine collects the user's reactions again.

[0331] Step 10:

[0332] The user inputs feedback about the content and sends it to the server. Specifically, the user fills out the feedback in the evaluation form and presses the submit button.

[0333] Step 11:

[0334] The server receives the feedback and emotion data and re-analyzes it, identifying points that need to be regenerated based on the emotion data.

[0335] Step 12:

[0336] The server then initiates the regeneration process, reactivating the selected generative AI model to generate new content based on the feedback and emotion data.

[0337] Step 13:

[0338] The user performs a final check on the device and then uploads the generated content to social media or a website. Specifically, the user downloads the generated video file and completes the distribution procedure. It is also possible to adjust the timing and method of distribution based on data obtained from the emotion engine.

[0339] Example 2

[0340] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0341] In order to effectively generate and distribute security awareness content on the Internet, a wide range of processes are required, including adjusting generation requirements, content generation, quality verification, optimization, and feedback re-implementation. However, existing systems do not adequately integrate these processes, making it difficult to automatically generate and provide optimal content that responds to user emotions.

[0342] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0343] In this invention, the server includes means for a user to input generation requirements, means for a terminal to acquire emotion data and adjust the requirements, means for the server to receive and analyze the input requirements and emotion data, means for selecting and activating a generative AI model based on the analysis results, means for generating the necessary text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means for sending the optimized content to the user, means for regenerating the content based on user feedback, and means for delivering the generated content. This makes it possible to automatically generate and efficiently provide high-quality security awareness content that is suited to the user's emotions.

[0344] "User" is a person or organization that uses the system to generate security awareness content, provide input, and provide feedback.

[0345] A "terminal" is a device used by a user that provides an interface for inputting generation requirements, obtaining emotion data, reviewing generated content, and providing feedback.

[0346] "Emotion data" is data that is used to read emotions from the user's facial expressions and voice and to adjust generation requirements and optimize generated content.

[0347] The "server" is a central computing system that receives and analyzes generation requirements and emotion data, selects and launches a generative AI model, verifies and optimizes the quality of the generated content, and finally provides the content to users.

[0348] "Generation requirements" are requirement information such as purpose, theme, length, and format that a user specifies about the content that he or she wants to generate.

[0349] "Analysis" is the process in which the server analyzes the generation requirements and emotion data received and extracts each parameter.

[0350] A "generative AI model" is an artificial intelligence model for generating required media such as text, images, and audio, and includes text generation AI, image generation AI, and audio generation AI.

[0351] "Text generation AI" is an artificial intelligence model that writes appropriate scenarios and explanatory text based on the generation requirements specified by the user.

[0352] "Image generation AI" is an artificial intelligence model that generates relevant images and illustrations based on user-specified generation requirements.

[0353] "Voice generation AI" is an artificial intelligence model that generates narration and voice based on the generation requirements specified by the user.

[0354] "Content" refers to media for security awareness that combines text, images, audio, etc. generated by a generative AI model.

[0355] "Quality verification" is the process by which the server checks the quality of the generated content, such as sound quality, image quality, and length, and automatically corrects or optimizes it as necessary.

[0356] "Optimization" is the process of making necessary adjustments and modifications to improve the quality of the generated content.

[0357] "Feedback" refers to opinions and requests that users provide regarding the generated content, which are reanalyzed by the server and used for regeneration.

[0358] "Distribution" is the process of providing optimized content to users and other platforms.

[0359] This invention combines an emotion engine with a system that uses generative AI to automatically generate security awareness content. This system is configured so that users can input generation requirements, and the emotion engine adjusts those requirements to generate and distribute high-quality content.

[0360] System configuration

[0361] The system includes the following elements:

[0362] Terminal: Provides an interface for users to input generation requirements, review the generated content, receive feedback, obtain emotional data, and finally distribute it. Examples include PCs and smartphones.

[0363] Server: A central computing system that receives and analyzes generative requirements, and manages and operates the appropriate generative AI models and emotion engines.

[0364] Generative AI model: An artificial intelligence model for generating media such as text, images, and audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[0365] Emotion Engine: Recognizes user emotions and provides data to help adjust production requirements, optimize content, and regenerate it.

[0366] Program processing explanation

[0367] Entering content requirements

[0368] Users input the requirements for the content they want to generate through their device. These include the purpose, theme, length, and format of the video. The device then uses an emotion engine to read emotions from the user's facial expressions and voice and adjusts the generation requirements accordingly. For example, if a user wants to create a "one-minute short video about phishing scams," they can input these requirements into their device.

[0369] Submitting requirements

[0370] When the user completes the input and presses the send button, the device uses an HTTP request to send the input requirements and emotion data generated by the emotion engine to the server.

[0371] Receiving and parsing requirements

[0372] The server receives the HTTP request and stores it in a database. The analysis engine then analyzes the data and extracts parameters (e.g., theme, format, length). Sentiment data is also analyzed at this time, and adjustments are made according to requirements.

[0373] Selecting and launching the generation AI

[0374] The server selects the appropriate generative AI model based on the analysis results. For example, GPT-3 is used for text generation, GAN for image generation, and WaveNet for speech generation. It launches each AI model and sends the necessary input data via an API.

[0375] Content generation

[0376] Each generative AI model generates content based on the data it receives. The text generation AI generates a scenario, and the image generation AI generates related images based on that text. The voice generation AI uses the generated scenario and images to generate narration. The emotion engine evaluates the generated content and makes adjustments based on the user's mood and preferences.

[0377] Content validation and optimization

[0378] The server validates the generated content, checking the quality of each output (e.g., sound quality, image quality, text integrity) and automatically correcting or optimizing it. For example, if the voice is not clear, it adjusts the parameters of the voice generation AI and regenerates it.

[0379] Preparing content for distribution

[0380] The optimized content is sent from the server to the device, where the user can check the generated content on the device and also see the feedback provided by the emotion engine.

[0381] Feedback and Regeneration

[0382] The user inputs feedback on the generated content, which is sent via the device to the server, which then re-analyzes it and re-runs each generative AI model to regenerate the content.

[0383] Finalize and distribute content

[0384] If the user is satisfied with the generated content after final confirmation, they can upload it to social media or their website. The server can also suggest the optimal distribution method based on the data from the emotion engine.

[0385] Specific examples

[0386] A user types into their device, "I want to create a one-minute short video about phishing scams." The device uses an emotion engine to collect emotional data from the user's facial expressions and voice, and adjusts the requirements based on this data. The device then sends the requirements and emotional data to the server, which receives and analyzes them. After analyzing, the server selects an appropriate generative AI model (e.g., GPT-3 for text generation, GAN for image generation, WaveNet for voice generation) and activates each AI model to generate content. The generated content is then quality-verified and optimized on the server, and the optimized content is sent to the device. The user reviews the content and provides feedback, and the server reanalyzes and regenerates it. Finally, once the user is satisfied, the content is distributed to social media and the website.

[0387] This system makes it possible to efficiently and automatically generate and effectively deliver high-quality security awareness content that is tailored to the user's emotions.

[0388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0389] System program processing flow

[0390] Step 1:

[0391] The user inputs the content generation requirements using the terminal.

[0392] Input data: purpose of the video, subject, length, format, etc.

[0393] Specific operation: The user inputs into the device's input screen that they would like to create a "one-minute short video about phishing scams." The device uses an emotion engine to collect emotional data from the user's facial expressions and voice. This emotional data is used to adjust the requirements for content generation.

[0394] Step 2:

[0395] The terminal transmits the input requirements and emotion data to the server.

[0396] Input data: User-generated requirements and sentiment data.

[0397] Specific operation: The device sends the generation requirements and emotion data to the server in the form of an HTTP request. The data is packaged in JSON format.

[0398] Step 3:

[0399] The server receives the input requirements and emotion data and analyzes them.

[0400] Input data: Generation requirements and emotion data sent from the device.

[0401] How it works: The server receives an HTTP request and stores the information in a database. The analysis engine then analyzes the generation requirements and sentiment data to extract parameters (e.g., theme, format, length). The sentiment data is also analyzed, and the generation requirements are adjusted as needed.

[0402] Step 4:

[0403] The server selects and launches an appropriate generative AI model based on the analysis results.

[0404] Input data: Parsed generative requirements and sentiment data.

[0405] Specific operation: Based on the analysis results, the server selects and launches an appropriate generative AI model, such as a GPT-3 model for text generation, a GAN model for image generation, or a WaveNet model for voice generation. The necessary input data for each AI model is sent via API.

[0406] Step 5:

[0407] Generative AI models generate content such as text, images, and audio.

[0408] Input data: Input data for each generative AI model (e.g., scenario text, related images, narration script).

[0409] How it works: The text generation AI model generates a scenario, the image generation AI model generates related images, and then the voice generation AI model generates a narration voice. Reflecting data from the emotion engine, content is generated that matches the user's preferences and mood.

[0410] Step 6:

[0411] The server verifies the quality of the generated content and makes optimizations if necessary.

[0412] Input data: Text, images, and audio output by the generative AI model.

[0413] Specific operation: The server verifies the sound quality, image quality, length, etc. of the generated content, and automatically corrects any defects found. For example, if the audio is not clear, the parameters of the audio generation AI are adjusted and the content is generated again.

[0414] Step 7:

[0415] The optimized content is sent from the server to the terminal.

[0416] Input data: optimized text, images, and audio.

[0417] Specific operation: The server sends the optimized content to the device in the form of an HTTP response. The user checks the content on the device and also checks the feedback provided by the emotion engine.

[0418] Step 8:

[0419] The user inputs feedback on the generated content and transmits it to the server via the terminal.

[0420] Input data: User feedback and sentiment data.

[0421] Specific operation: The user enters their opinion or request into the feedback screen on the device and presses the send button. The device then sends the feedback and emotion data to the server.

[0422] Step 9:

[0423] The server re-analyzes the feedback and emotion data and re-runs the generative AI model to re-generate the content.

[0424] Input data: User feedback and sentiment data.

[0425] Specific operation: The server reanalyzes the received feedback and emotion data, reruns each generative AI model, and generates new content including modifications based on the user's requests.

[0426] Step 10:

[0427] The user then makes a final check and uploads the generated content to social media or their website.

[0428] Input data: Final verified content.

[0429] Specific operation: The user checks the content generated on the device and uploads it to social media or a website when satisfied. The server can also suggest the optimal distribution method based on the emotion engine data.

[0430] The above processing steps allow users to efficiently generate and distribute high-quality, emotionally appropriate security awareness content.

[0431] (Application example 2)

[0432] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0433] Conventional ad generation systems struggled to generate personalized content based on user emotions and preferences, and could only provide generic ads. Furthermore, they lacked the ability to regenerate the quality and effectiveness of generated content based on user feedback, making it difficult to maximize advertising effectiveness. This limited the effectiveness of advertising and prevented improvements in user engagement.

[0434] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0435] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the generation requirements, means for generating the required text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means including an emotion engine that acquires user emotion data and adjusts the generation requirements, means for sending the optimized content to the user, means for regenerating content based on user feedback, and means for delivering the generated content. This enables personalized content generation based on emotions and content regeneration based on user feedback.

[0436] A "user" is a person who uses a service or system and makes requests or feedback.

[0437] "Generation requirements" are specific conditions and requirements regarding the content that a user wants to generate.

[0438] A "means" is a method or device by which a system performs a specific function or process.

[0439] A "server" is a computer system that receives input data, analyzes it, and takes appropriate action.

[0440] A "generative AI model" is a model that uses artificial intelligence to automatically generate media such as text, images, and audio.

[0441] "Emotion data" is information about emotions acquired from the user's facial expressions, tone of voice, and the like.

[0442] The "emotion engine" is a system that recognizes user emotional data and provides data useful for adjusting generation requirements and optimizing content.

[0443] "Content" means media consisting of text, images, audio, or a combination thereof created by a generative AI model.

[0444] "Feedback" refers to ratings and opinions provided by users regarding generated content.

[0445] "Personalized" refers to a state that is tailored based on the preferences and feelings of a particular user.

[0446] An "advertisement" is visual or audio content created to promote a product or service.

[0447] "Optimization" is the process of improving the quality of content and making it best suited for a purpose.

[0448] "Distribution" refers to providing the generated content to intended users over the Internet.

[0449] The present invention is a system that uses a generative AI model incorporating an emotion engine to provide personalized advertising content to users. This system is composed of hardware and software such as a user terminal, a server, a generative AI model, and an emotion engine. A specific embodiment of this system will be described.

[0450] This system works as follows: First, the user inputs the requirements for the advertising content they want to generate using a device such as a smartphone. The requirements include the ad's theme, length, format, etc. The emotion engine then obtains emotional data from the user's facial expressions and tone of voice and adjusts the requirements accordingly.

[0451] The device then transmits the acquired generation requirements and emotion data to the server, which analyzes the received data and selects and activates an appropriate generative AI model based on that data. These generative AI models include various models for text generation, image generation, and speech generation.

[0452] Generative AI models generate the necessary media, such as text, images, and audio, to create advertising content. For example, text generation AI creates a scenario, image generation AI generates related visuals, and audio generation AI generates narration. These generation processes take into account user emotional data.

[0453] The generated ad content is verified for quality on the server, with parameters such as sound quality, image quality, length, and overall structure being checked, and optimizations made based on data from the emotion engine as needed.

[0454] The optimized content is then sent back to the user's device from the server, where the user can review it. When the user enters feedback, the device sends it to the server, which analyzes the feedback and regenerates it as necessary.

[0455] Finally, advertising content that users are satisfied with is published on social media, websites, etc. At this time, the content is delivered in the most appropriate way based on the data obtained from the emotion engine.

[0456] The specific hardware and software used includes the following:

[0457] Device: Internet-enabled smartphone

[0458] Server: High-performance cloud computing system

[0459] Generative AI models: Natural language processing models such as OpenAI's GPT-4, image generation models, and speech generation models

[0460] Emotion engine: An emotion recognition system such as Microsoft Azure Face API

[0461] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0462] "Generate a 30-second video ad about a new product introduction. The user emotion is 'joy' and the tone of voice is high-pitched."

[0463] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0464] Step 1:

[0465] The user operates the device to input requirements for generating advertising content, and the emotion engine obtains emotional data from the user's facial expressions and tone of voice. The input data includes the advertisement's theme, length, format, and emotional data, which are then used for subsequent processing.

[0466] Step 2:

[0467] The device sends the input generation requirements and emotion data to the server. Specifically, the data is transferred to the server using an HTTP request. The input data becomes the material for analysis processing on the server.

[0468] Step 3:

[0469] The server receives the data and analyzes the generation requirements and sentiment data. During this process, the data is checked for consistency and parameters are extracted, such as the theme and format of the ad and the user's sentiment information, which are then stored in a database.

[0470] Step 4:

[0471] Based on the analysis results, the server selects and activates the optimal generative AI model. Selection criteria include the application of text generation AI, image generation AI, and voice generation AI appropriate for the theme. Furthermore, emotion data is used to fine-tune the generated content.

[0472] Step 5:

[0473] After the generative AI model is selected, it generates advertising content such as text, images, and audio. Specifically, the generative AI model receives a prompt as input and generates output based on it. For example, a prompt might be, "Generate a 30-second video ad for a new product introduction. The user's emotion is 'joy' and the voice tone is high-pitched."

[0474] Step 6:

[0475] The server receives the generated ad content and verifies its quality. Audio quality, picture quality, and overall composition are checked, and any defects are automatically corrected. This verification uses image and sound quality optimization algorithms.

[0476] Step 7:

[0477] Send the optimized content from the server to the device. Allow the user to view the content for final confirmation. Allow the user to review the ad content and provide feedback if necessary.

[0478] Step 8:

[0479] Users input feedback via their devices and send it to the server. The feedback includes requests for content changes and improvements. This data is used as a reference when the server regenerates the content.

[0480] Step 9:

[0481] The server analyzes the feedback and re-runs the generative AI model if regeneration is necessary, setting new parameters based on the feedback data and generating new ad content.

[0482] Step 10:

[0483] The final regenerated ad content is then resent to the user's device. This loop is repeated until the user is satisfied. The final certified ad content is then delivered to the social networking site or website.

[0484] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0485] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0486] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0487] [Second embodiment]

[0488] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0489] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0490] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0491] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0492] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0493] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0494] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0495] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0496] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0497] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0498] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0499] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0500] This invention relates to a system that automatically generates security awareness content using generative AI. The system is composed of a server, a terminal, a generative AI model, and other components.

[0501] System configuration

[0502] The system includes the following elements:

[0503] Terminal: Provides an interface for users to input production requirements, review, feedback, and finally deliver the generated content.

[0504] Server: A central computing system that receives and analyzes production requirements, selects appropriate generative AI models, and generates, validates, optimizes, and regenerates content.

[0505] Generative AI model: An artificial intelligence model for generating media such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[0506] Program processing explanation

[0507] 1. Enter your content requirements

[0508] Users input the requirements for the content they want to generate through their device, including the purpose, theme, length, and format of the video.

[0509] 2. Submit your requirements

[0510] The device sends the input requirements to the server, which analyzes the received requirements and determines the required generative AI model.

[0511] 3. Launching the Generative AI

[0512] The server selects and activates the appropriate generative AI model based on the analysis results. For example, when creating a short video to combat phishing scams, it activates a text generation AI, an image generation AI, and a voice generation AI.

[0513] 4. Content Generation

[0514] The generative AI model generates content based on user requirements, such as phishing scenarios, warning images, explanatory illustrations, and narration audio.

[0515] 5. Content validation and optimization

[0516] The server verifies the quality of the generated content, checking parameters such as audio quality, video quality, and length, and automatically correcting and optimizing as needed.

[0517] 6. Preparing content for distribution

[0518] The optimized content is sent from the server to the device for the user to review, and if the user is not satisfied, they can enter feedback.

[0519] 7. Feedback and Regeneration

[0520] Once the user submits their feedback, the server re-analyzes it and re-runs the generative AI model, repeating this process until content that satisfies the user is generated.

[0521] 8. Finalize and distribute content

[0522] After the user has final confirmation and is satisfied with the content, they can upload it to social media or their website, allowing the security awareness content to reach a wider audience.

[0523] Specific examples

[0524] Short video generation to combat phishing scams

[0525] 1. Enter your content requirements

[0526] The user uses a device to input the requirements for a "one-minute short video about phishing scams." Input items include "phishing scams," "one minute," and "video format."

[0527] 2. Submit your requirements

[0528] The terminal sends the input requirements to the server, which receives the request and starts requirement analysis.

[0529] 3. Launching the Generative AI

[0530] Based on the analysis results, the server selects and activates an appropriate AI model, such as text generation AI, image generation AI, or voice generation AI.

[0531] 4. Content Generation

[0532] The text generation AI generates phishing scam scenarios and points to watch out for, the image generation AI generates related warning images and explanatory illustrations, and the audio generation AI generates narration audio.These are then combined to create a one-minute short video.

[0533] 5. Content validation and optimization

[0534] The server verifies the quality of the video and optimizes the sound and image quality.

[0535] 6. Preparing content for distribution

[0536] The optimized video is sent from the server to the terminal and viewed by the user.

[0537] 7. Feedback and Regeneration

[0538] The user provides feedback as needed and the server regenerates it.

[0539] 8. Finalize and distribute content

[0540] After the user confirms it, they can upload the generated video to social media or their website.

[0541] As a result, the present invention can efficiently and effectively generate security awareness content, thereby raising the level of security knowledge of users and companies.

[0542] The processing flow will be explained below.

[0543] Step 1:

[0544] The user inputs the requirements for the content they want to generate using their device (e.g., a one-minute short video about phishing scams). Specifically, they input information such as the theme, format, length, and purpose into the device's input form.

[0545] Step 2:

[0546] The terminal transmits the input requirements to the server. Specifically, the terminal transmits the requirement data to the server using an HTTP request.

[0547] Step 3:

[0548] The server receives the input requirements and performs analysis. Specifically, it analyzes the received data and extracts each parameter (e.g., topic, format, length).

[0549] Step 4:

[0550] The server selects and activates the appropriate generative AI model based on the analysis results. Specifically, it selects the text generation AI, image generation AI, and voice generation AI necessary for generating short videos to combat phishing scams.

[0551] Step 5:

[0552] The generative AI model generates content such as text, images, and audio. Specifically, the text generation AI generates the scenario, the image generation AI generates the related images, and the audio generation AI generates the narration audio.

[0553] Step 6:

[0554] The server aggregates the generated content, specifically creating a video file using the generated text, images, and audio.

[0555] Step 7:

[0556] The server verifies the quality of the generated content and optimizes it if necessary, specifically by checking audio and video quality and applying automatic corrections and enhancements.

[0557] Step 8:

[0558] The server sends the optimized content to the device. Specifically, it generates a content URL so that the user can view it and notifies the device.

[0559] Step 9:

[0560] The user views the generated content through their device, specifically by accessing the provided URL and watching the video.

[0561] Step 10:

[0562] The user enters feedback and sends it to the server. Specifically, the user enters feedback in the evaluation form and presses the submit button.

[0563] Step 11:

[0564] The server receives the feedback and initiates the regeneration process if necessary, specifically by analyzing the regeneration points and relaunching the associated generative AI models.

[0565] Step 12:

[0566] The user then performs a final check and uploads the generated content to social media or their website. Specifically, they download the generated video file and post it to each platform.

[0567] Example 1

[0568] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0569] In today's world, security awareness education via the Internet is extremely important. However, manually creating security awareness content requires a significant amount of time and expertise, making it difficult to generate content efficiently. It is also difficult to consistently improve the quality of generated content or quickly improve it based on feedback. For this reason, there is a need for a system that uses generative AI to automatically generate, optimize, and distribute high-quality security awareness content.

[0570] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0571] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the analysis results, means for generating necessary media data using a generative AI model including a text generator, an image generator, and a voice generator to create content, means for verifying the quality of the generated content and automatically correcting or optimizing it as necessary, means for transmitting the optimized content to the user, means for regenerating the content based on user feedback, and means for preparing the generated content after final confirmation for distribution and distributing it to multiple platforms. This enables the automatic generation and rapid correction of high-quality security awareness content based on user requirements.

[0572] "User" means a person or organization that uses the system to generate, review, and distribute security awareness content.

[0573] "Server" is a central computer system that analyzes the generation requirements entered by the user, selects, launches, and executes the appropriate generative AI model, and validates, optimizes, and delivers the generated content.

[0574] The "creation requirements" are information including detailed requests such as the purpose, theme, length, and format of the content the user wants to create.

[0575] A "generative AI model" is an artificial intelligence model used to generate media data such as text, images, and audio, and specifically includes text generators, image generators, and audio generators.

[0576] A "text generator" is a device that generates necessary text data based on user requirements.

[0577] An "image generating device" is a device that generates the necessary image data based on the user's requirements.

[0578] A "voice generating device" is a device that generates necessary voice data based on the user's requirements.

[0579] "Media data" refers to all data that forms content, such as text, images, and audio.

[0580] "Content" refers to a collection of data, including text, images, audio, etc., generated and optimized by a generative AI model for security awareness purposes.

[0581] "Feedback" is information including users' evaluations of the generated content and requests for improvement.

[0582] "Auto-remediation" is the process by which the server verifies the quality of generated content and automatically makes corrections as needed.

[0583] "Optimization" is the process of improving the generated content according to quality and user requirements.

[0584] "Distribution" is the process of publishing the final, verified generated content to multiple platforms.

[0585] "Platform" refers to a website, social networking site, or other online service for distributing Generated Content.

[0586] The present invention relates to a system that automatically generates security awareness content by utilizing a generative AI model. The system is configured by combining a server, a terminal, a generative AI model, etc. The configuration and operation for specifically implementing the present invention are described below.

[0587] System configuration

[0588] The system includes the following elements:

[0589] Terminal: A device through which a user inputs content generation requirements, checks, provides feedback, and finally distributes the generated content.

[0590] Server: A central computing system that receives and analyzes the generation requirements from users, selects and launches appropriate generative AI models, and generates, validates, optimizes, and regenerates content.

[0591] Generative AI model: An artificial intelligence model for generating media data such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[0592] Program processing

[0593] 1. Enter your content requirements

[0594] Users input the requirements for the content they want to generate through their device. Input items include the purpose, theme, length, format, etc. of the video. For example, they input the requirements for a "one-minute short video about phishing scams."

[0595] 2. Submit your requirements

[0596] The device sends the input requirements to the server, which analyzes the received requirements and selects a generative AI model suitable for content generation.

[0597] 3. Launching the Generative AI

[0598] Based on the analysis results, the server selects and activates a generative AI model, including a text generator, an image generator, and a voice generator. For example, when creating a short video to combat phishing scams, these three devices work together.

[0599] 4. Content Generation

[0600] The generative AI model generates the necessary media data based on the user's requirements. For example, it uses a text generator to create a scenario, an image generator to generate warning images and explanatory illustrations, and a voice generator to generate narration. These are then integrated to create content in the form of a one-minute short video.

[0601] 5. Content validation and optimization

[0602] The server verifies the quality of the generated content, checking audio quality, image quality, length, and script consistency, and automatically corrects and optimizes it if necessary.

[0603] 6. Preparing content for distribution

[0604] The server sends the optimized content to the device for user confirmation, and the user can preview the generated content through the device and provide feedback as needed.

[0605] 7. Feedback and Regeneration

[0606] When the user submits feedback from their device, the server re-analyzes and re-runs the necessary generative AI models, repeating this process until the user is satisfied.

[0607] 8. Finalize and distribute content

[0608] If the user is satisfied with the content after final confirmation, they can issue a command to upload it to a social networking site or website from their device. The server then formats the content for distribution and distributes it to the specified platform.

[0609] Specific examples

[0610] For example, to generate a one-minute short anti-phishing video, use the following prompt:

[0611] "Create a short 1-minute video about phishing scams. Please include the following:

[0612] Phishing scam method explained

[0613] Examples of fraudulent emails and how to deal with them

[0614] Attention to viewers

[0615] As a result, the present invention can efficiently and effectively generate security awareness content, thereby improving the security knowledge of users and organizations.

[0616] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0617] Step 1:

[0618] The user inputs the generation requirements using a terminal.

[0619] Specifically, the user inputs the prompt for a "one-minute short video about phishing scams." The input data includes information such as "phishing scams," "one minute," and "video format." This input information is then saved on the device.

[0620] Step 2:

[0621] The terminal transmits the requirements input by the user to the server.

[0622] Specifically, the device sends input data in JSON format or other appropriate data format to the server. The sent data includes the purpose, theme, length, format, etc. The server receives this data and begins analyzing it. Input data: "Phishing scam," "1 minute," "Video format"

[0623] Output data: Parsed requirements

[0624] Step 3:

[0625] The server analyzes the received requirements and selects the optimal generative AI model.

[0626] The server determines which generative AI models (text generator, image generator, and voice generator) are needed based on the analyzed requirements. For example, a short video to combat phishing requires these three generative AI models. Input data: Analyzed requirements

[0627] Output data: Selected generative AI model

[0628] Step 4:

[0629] The server launches the selected generative AI model.

[0630] The server uses an interface such as a REST API to launch the generative AI model and begin the generation process. For example, it sends instructions such as "Generate a phishing scam scenario" to the text generator and "Convert the generated scenario into audio" to the voice generator. Input data: Selected generative AI model

[0631] Output data: Start command

[0632] Step 5:

[0633] A generative AI model generates content based on user requirements.

[0634] Specifically, the text generator creates a phishing scam scenario, the image generator generates related warning images and explanatory illustrations, and the audio generator generates a narration based on the generated scenario. These are then integrated to create a one-minute short video. Input data: Generation requirements

[0635] Output Data: Generated Content

[0636] Step 6:

[0637] Validate the quality of the server-generated content.

[0638] Specifically, it checks the sound quality, image quality, content length, and consistency of the scenario, and automatically corrects or optimizes it if necessary. For example, if there are any unclear parts of the audio, it issues instructions to the audio generator again. Input data: Generated content

[0639] Output: Optimized content

[0640] Step 7:

[0641] The server sends the optimized content to the device for the user to view.

[0642] Specifically, the server converts the generated content into the appropriate format and sends a preview link or file to the device. The user can preview the generated video using this link. Input data: Optimized content

[0643] Output data: Preview link or file

[0644] Step 8:

[0645] The user inputs feedback through the terminal and transmits it to the server.

[0646] Specifically, users input specific feedback such as "Please make the video a little shorter" or "Please make the illustrations easier to understand." The device then sends this feedback to the server. Input data: User feedback

[0647] Output data: Feedback data

[0648] Step 9:

[0649] The server analyzes the feedback and re-runs any necessary generative AI models.

[0650] For example, based on feedback such as "Please shorten the length of the video," the system issues instructions to the text generator and modifies the scenario. This process is repeated until the user is satisfied. Input data: Feedback data

[0651] Output Data: Regenerated content

[0652] Step 10:

[0653] If the user is satisfied with the generated content after making a final check, they can issue instructions from their device to upload it to a social networking site or their homepage.

[0654] The server formats the content for distribution and distributes it to the specified platform, ensuring that the security awareness content reaches a wide audience. Input data: Final confirmation and distribution instructions

[0655] Output data: Streamed content

[0656] (Application example 1)

[0657] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0658] Despite the growing importance of security on the Internet in recent years, it is difficult to effectively communicate security alerts to users in an easy-to-understand manner. In particular, there is a demand for a system that can automatically and quickly generate content to promote awareness of specific threats such as phishing scams, but current technology is unable to meet this demand. In addition, optimizing the quality of the generated content based on user feedback is also an important issue.

[0659] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0660] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the generation requirements, means for generating the necessary text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means for sending the optimized content to the user, means for regenerating the content based on user feedback, means for the user to make final confirmation, and means for distributing the generated content to a platform on the Internet. This makes it possible to quickly and effectively generate security awareness content and promote user understanding.

[0661] "User" is the entity that inputs requirements for the generation of security awareness content, reviews the generated content, and provides feedback as needed.

[0662] "Generation requirements" are information that indicates the detailed specifications and requests for the security awareness content that a user wants to generate.

[0663] "Server" means a central computing system that analyzes the generation requirements received from the User, selects and launches an appropriate generative AI model, validates and optimizes the generated content, and transmits it to the User.

[0664] A "generative AI model" is an artificial intelligence model that generates media such as text, images, and audio, and performs appropriate generation as needed.

[0665] "Text" refers to sentences or character information generated by a generative AI model.

[0666] "Image" means a visual graphic or illustration generated by a generative AI model.

[0667] "Audio" refers to auditory narration or audio data generated by a generative AI model.

[0668] "Content" means comprehensive security awareness information, including text, images, and audio, generated by a generative AI model.

[0669] "Quality verification" is the process of checking the quality of each element of generated content (text, images, audio) and making corrections or improvements as necessary.

[0670] "Optimization" is the process of automated adjustments and refinements based on quality validation results to improve the quality of the generated content.

[0671] "Feedback" refers to opinions and requests provided by users regarding generated content.

[0672] "Regeneration" is the process of regenerating content by running the generative AI model again based on user feedback.

[0673] "Means of Final Review" means the means by which a user reviews and approves the final version of the generated content.

[0674] "Distribution" is the process of publishing the finalized security awareness content on an internet platform to reach a wide audience.

[0675] The present invention is a system for automatically generating security awareness content, with the aim of providing effective education on security threats on the Internet in particular. The system automates the process of optimizing and distributing the content generated based on user input requirements.

[0676] System Components

[0677] 1. Terminal: A device that allows users to input production requirements, review the generated content, and provide feedback if necessary. Terminals include smartphones, personal computers, tablets, etc.

[0678] 2. Server: The server is a central computing system that analyzes the generation requirements received from users, selects and launches an appropriate generative AI model, validates and optimizes the generated content, and finally sends it to users.

[0679] 3. Generative AI models: These include text generation models, image generation models, and speech synthesis models. For example, natural language processing models (GPT-4) are used for text generation, generative adversarial networks (GANs) are used for image generation, and WaveNet is used for speech synthesis.

[0680] Program processing explanation

[0681] 1. Enter content generation requirements

[0682] The user uses a device to input the requirements for the security awareness content they want to generate. This can be a detailed request, such as "a five-minute video about phishing scams." The input requirements are sent from the device to the server.

[0683] 2. Requirements Analysis

[0684] The server analyzes the generation requirements received from the user and selects the appropriate generative AI model. For example, if the request is for a "5-minute video," a text generation model, an image generation model, and a speech synthesis model will be activated.

[0685] 3. Content Generation

[0686] The generative AI model runs on the server and generates text, images, and audio according to the user's requirements, including phishing scenarios, warning images, explanatory illustrations, and audio narration.

[0687] 4. Quality verification and optimization

[0688] The generated content is verified by the server for quality, checking parameters such as sound quality, image quality, and content length, and optimizing it if necessary.

[0689] 5. Feedback processing and regeneration

[0690] The optimized content is sent to the device for review by the user, who provides feedback, which the server analyzes and regenerates if necessary.

[0691] 6. Finalize and distribute content

[0692] Once the user has given a final review and is satisfied with the generated content, the content is distributed to a platform on the Internet.

[0693] Hardware and software used

[0694] Hardware: Smartphones, personal computers, servers

[0695] Software: Natural language processing model (GPT-4), image generation model (GANs), speech synthesis model (WaveNet)

[0696] Specific examples

[0697] Input prompt example

[0698] A user fills out a form in your app with:

[0699] Content Topic:Phishing

[0700] Content format: 5-minute short videos

[0701] Video length: 5 minutes

[0702] Target audience: general users

[0703] Part of the processing flow

[0704] The prompts entered by the user are sent to the server, which then activates the generative AI model to generate text, images, and audio. The generated content is then sent to the device after quality verification, where it is regenerated after user confirmation and feedback, and finally distributed to the platform after final confirmation.

[0705] This invention makes it possible to generate security awareness content quickly and effectively, and is expected to improve users' security awareness.

[0706] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0707] Step 1:

[0708] The user inputs the generation requirements using a terminal. Input items include the content theme, format, length, and target audience. This input data is sent from the terminal to the server. Input examples include "Content theme: phishing scams," "Content format: 5-minute short video," and "Target audience: general users."

[0709] Step 2:

[0710] The server receives and analyzes the generation requirements sent from the device. Specifically, it uses natural language processing (NLP) to analyze the user's requirements as text data and selects an appropriate generation AI model. For example, if the theme "phishing scam" is detected, it selects a generation AI model specialized in phishing scams.

[0711] Step 3:

[0712] The server selects and launches an appropriate generative AI model based on the analysis results. The selected generative AI models include a text generation model (GPT-4), an image generation model (DALL-E), and a speech synthesis model (WaveNet). For example, these models are launched sequentially according to the requirement of a "5-minute short video."

[0713] Step 4:

[0714] The generative AI model generates content based on user requirements. Specifically, the text generation model generates phishing scam scenarios, the image generation model generates warning images and explanatory illustrations, and the speech synthesis model generates narration. The data generated by each model is integrated to create a single content file.

[0715] Step 5:

[0716] The server verifies the quality of the generated content and optimizes it as necessary. Specifically, it automatically checks parameters such as sound quality, image quality, and length, and makes corrections as necessary. Based on the results of this verification, if the quality of the generated content does not meet certain standards, it will automatically make corrections.

[0717] Step 6:

[0718] The optimized content is sent from the server to the terminal. The user checks the generated content on the terminal and inputs feedback. For example, the user may provide feedback such as "I would like the sound quality of the narration to be improved."

[0719] Step 7:

[0720] User feedback is sent to the server, which analyzes it and, if necessary, re-launches the generative AI model to regenerate new content that reflects the feedback.

[0721] Step 8:

[0722] The server resends the content to the device for the user to check. If the user is satisfied with the content after checking it, the content is distributed to an internet platform. For example, a specific distribution method such as "upload to SNS" is selected.

[0723] Through the above processing steps, users can easily create high-quality security awareness content and deliver it to a wide audience.

[0724] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0725] This invention combines an emotion engine with a system that automatically generates security awareness content using generative AI. This system is composed of a server, a terminal, a generative AI model, an emotion engine, etc.

[0726] System configuration

[0727] The system includes the following elements:

[0728] Terminal: Provides an interface for users to input generation requirements, review the generated content, get feedback, obtain sentiment data, and finally deliver it.

[0729] Server: A central computing system that receives and analyzes generative requirements, and manages and operates the appropriate generative AI models and emotion engines.

[0730] Generative AI model: An artificial intelligence model for generating media such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[0731] Emotion Engine: Recognizes user emotions and provides data to help adjust production requirements, optimize content, and regenerate it.

[0732] Program processing explanation

[0733] 1. Enter content requirements

[0734] The user inputs the requirements for the content they want to generate through their device. Input items include the purpose, theme, length, and format of the video. The emotion engine reads the user's emotions from their facial expressions and voice and adjusts the generation requirements accordingly.

[0735] 2. Submit your requirements

[0736] The terminal transmits the input requirements and emotion data generated by the emotion engine to the server. Specifically, the terminal transmits the requirements data and emotion data to the server using an HTTP request.

[0737] 3. Receiving and analyzing requirements

[0738] The server receives the input requirements and performs analysis. The received data is analyzed to extract each parameter (e.g., theme, format, length). Sentiment data is also analyzed at this time.

[0739] 4. Selecting and starting the generation AI

[0740] The server selects and activates the appropriate generative AI model based on the analysis results. For example, it selects the text generation AI, image generation AI, and voice generation AI needed to generate short videos to combat phishing scams.

[0741] 5. Content Generation

[0742] The generative AI model generates content such as text, images, and audio. For example, a text generation AI generates a scenario, an image generation AI generates related images, and an audio generation AI generates narration audio. Based on data from the emotion engine, content is generated that matches the user's preferences and mood.

[0743] 6. Content validation and optimization

[0744] The server verifies the quality of the generated content, checking parameters such as sound quality, image quality, and length, and automatically correcting or optimizing as necessary. By taking into account data from the emotion engine, the content is more suited to the user's emotions.

[0745] 7. Preparing content for distribution

[0746] The optimized content is sent from the server to the device for the user to review, and data obtained from the emotion engine also helps with the review.

[0747] 8. Feedback and Regeneration

[0748] The user enters feedback and sends it to the server. The server receives the feedback and emotion data, reanalyzes it, and reruns the generative AI model as needed to regenerate the data.

[0749] 9. Finalize and distribute content

[0750] If the user is satisfied with the content after final confirmation, they can upload it to social media or their website. Based on the data obtained by the emotion engine, the content can be delivered in the most appropriate way for the user.

[0751] Specific examples

[0752] Short video generation to combat phishing scams

[0753] 1. Enter your content requirements

[0754] The user inputs the requirements for a "one-minute short video about phishing scams" using a terminal. The emotion engine reads emotional data from the user's facial expressions and voice and adjusts the requirements accordingly.

[0755] 2. Submit your requirements

[0756] The terminal transmits the input requirements and emotion data to the server.

[0757] 3. Receiving and analyzing requirements

[0758] The server analyzes the requirements, selects the appropriate generative AI model and emotion engine, and performs the analysis.

[0759] 4. Selecting and starting the generation AI

[0760] The server selects and activates text generation AI, image generation AI, and voice generation AI.

[0761] 5. Content Generation

[0762] The text generation AI generates phishing scam scenarios and points to watch out for, the image generation AI generates related warning images and explanatory illustrations, and the voice generation AI generates narration. Based on data from the emotion engine, content tailored to the user's preferences is generated.

[0763] 6. Content validation and optimization

[0764] The server verifies the quality of the video and optimizes the audio and video quality, taking into account the data from the emotion engine.

[0765] 7. Preparing content for distribution

[0766] The optimized video is sent from the server to the terminal and viewed by the user.

[0767] 8. Feedback and Regeneration

[0768] The user enters feedback and sends it to the server, which then reanalyzes it and reruns the generative AI model to regenerate it.

[0769] 9. Finalize and distribute content

[0770] The user then finalizes the video and uploads it to social media or their website. Based on the data from the emotion engine, the video is distributed in the most appropriate way for the user.

[0771] As a result, the present invention can efficiently and effectively generate security awareness content and raise the level of security knowledge of users and companies. Furthermore, by combining it with an emotion engine, it is possible to provide content that is suited to the user's emotions.

[0772] The processing flow will be explained below.

[0773] Step 1:

[0774] The user inputs the requirements for the content they wish to generate using their device. Specifically, they enter information such as "phishing scam," "1 minute," and "video format" into the device's input form. At this time, the emotion engine analyzes the user's facial expressions and voice in real time to collect emotional data.

[0775] Step 2:

[0776] The terminal transmits the input requirements and emotion data to the server. Specifically, an HTTP request including the requirement information and emotion data is transmitted to the server.

[0777] Step 3:

[0778] The server receives the requirements and emotional data and performs analysis, extracting parameters (e.g., topic, format, length) from the received data, and also analyzes the emotional data to determine the user's current emotional state.

[0779] Step 4:

[0780] The server selects and activates the appropriate generative AI model based on the analysis results, selecting the necessary text generation AI, image generation AI, and voice generation AI, and customizing the generation process based on emotion data.

[0781] Step 5:

[0782] The generative AI model generates content such as text, images, and audio. Specifically, the text generation AI creates a phishing scam scenario, the image generation AI generates related images, and the audio generation AI generates narration audio. Emotional data is used to generate content with a tone and style that matches the user's emotions.

[0783] Step 6:

[0784] The server aggregates the generated content, specifically creating a one-minute short video using the generated text, images, and audio.

[0785] Step 7:

[0786] The server verifies the quality of the generated content and optimizes it. Specifically, it checks the audio and video quality, removes or modifies unnecessary elements, and takes into account emotional data to optimize the content in a way that is likely to be perceived favorably by users.

[0787] Step 8:

[0788] The server sends the optimized content to the device, specifically by generating and notifying the user of the content URL so that the user can view it.

[0789] Step 9:

[0790] The user checks the generated content through their device. Specifically, they access the provided URL and watch the video, and the emotion engine collects the user's reactions again.

[0791] Step 10:

[0792] The user inputs feedback about the content and sends it to the server. Specifically, the user fills out the feedback in the evaluation form and presses the submit button.

[0793] Step 11:

[0794] The server receives the feedback and emotion data and re-analyzes it, identifying points that need to be regenerated based on the emotion data.

[0795] Step 12:

[0796] The server then initiates the regeneration process, reactivating the selected generative AI model to generate new content based on the feedback and emotional data.

[0797] Step 13:

[0798] The user performs a final check on the device and then uploads the generated content to social media or a website. Specifically, the user downloads the generated video file and completes the distribution procedure. It is also possible to adjust the timing and method of distribution based on data obtained from the emotion engine.

[0799] Example 2

[0800] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0801] In order to effectively generate and distribute security awareness content on the Internet, a wide range of processes are required, including adjusting generation requirements, content generation, quality verification, optimization, and feedback re-implementation. However, existing systems do not adequately integrate these processes, making it difficult to automatically generate and provide optimal content that responds to user emotions.

[0802] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0803] In this invention, the server includes means for a user to input generation requirements, means for a terminal to acquire emotion data and adjust the requirements, means for the server to receive and analyze the input requirements and emotion data, means for selecting and activating a generative AI model based on the analysis results, means for generating the necessary text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means for sending the optimized content to the user, means for regenerating the content based on user feedback, and means for delivering the generated content. This makes it possible to automatically generate and efficiently provide high-quality security awareness content that is suited to the user's emotions.

[0804] "User" is a person or organization that uses the system to generate security awareness content, provide input, and provide feedback.

[0805] A "terminal" is a device used by a user that provides an interface for inputting generation requirements, obtaining emotion data, reviewing generated content, and providing feedback.

[0806] "Emotion data" is data that is used to read emotions from the user's facial expressions and voice and to adjust generation requirements and optimize generated content.

[0807] The "server" is a central computing system that receives and analyzes generation requirements and emotion data, selects and launches a generative AI model, verifies and optimizes the quality of the generated content, and finally provides the content to users.

[0808] "Generation requirements" are requirement information such as purpose, theme, length, and format that a user specifies about the content that he or she wants to generate.

[0809] "Analysis" is the process in which the server analyzes the generation requirements and emotion data received and extracts each parameter.

[0810] A "generative AI model" is an artificial intelligence model for generating required media such as text, images, and audio, and includes text generation AI, image generation AI, and audio generation AI.

[0811] "Text generation AI" is an artificial intelligence model that writes appropriate scenarios and explanatory text based on the generation requirements specified by the user.

[0812] "Image generation AI" is an artificial intelligence model that generates relevant images and illustrations based on user-specified generation requirements.

[0813] "Voice generation AI" is an artificial intelligence model that generates narration and voice based on the generation requirements specified by the user.

[0814] "Content" refers to media for security awareness that combines text, images, audio, etc. generated by a generative AI model.

[0815] "Quality verification" is the process by which the server checks the quality of the generated content, such as sound quality, image quality, and length, and automatically corrects or optimizes it as necessary.

[0816] "Optimization" is the process of making necessary adjustments and modifications to improve the quality of the generated content.

[0817] "Feedback" refers to opinions and requests that users provide regarding the generated content, which are reanalyzed by the server and used for regeneration.

[0818] "Distribution" is the process of providing optimized content to users and other platforms.

[0819] This invention combines an emotion engine with a system that uses generative AI to automatically generate security awareness content. This system is configured so that users can input generation requirements, and the emotion engine adjusts those requirements to generate and distribute high-quality content.

[0820] System configuration

[0821] The system includes the following elements:

[0822] Terminal: Provides an interface for users to input generation requirements, review the generated content, receive feedback, obtain emotional data, and finally distribute it. Examples include PCs and smartphones.

[0823] Server: A central computing system that receives and analyzes generative requirements, and manages and operates the appropriate generative AI models and emotion engines.

[0824] Generative AI model: An artificial intelligence model for generating media such as text, images, and audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[0825] Emotion Engine: Recognizes user emotions and provides data to help adjust production requirements, optimize content, and regenerate it.

[0826] Program processing explanation

[0827] Entering content requirements

[0828] Users input the requirements for the content they want to generate through their device. These include the purpose, theme, length, and format of the video. The device then uses an emotion engine to read emotions from the user's facial expressions and voice and adjusts the generation requirements accordingly. For example, if a user wants to create a "one-minute short video about phishing scams," they can input these requirements into their device.

[0829] Submitting requirements

[0830] When the user completes the input and presses the send button, the device uses an HTTP request to send the input requirements and emotion data generated by the emotion engine to the server.

[0831] Receiving and parsing requirements

[0832] The server receives the HTTP request and stores it in a database. The analysis engine then analyzes the data and extracts parameters (e.g., theme, format, length). Sentiment data is also analyzed at this time, and adjustments are made according to requirements.

[0833] Selecting and launching the generation AI

[0834] The server selects the appropriate generative AI model based on the analysis results. For example, GPT-3 is used for text generation, GAN for image generation, and WaveNet for speech generation. It launches each AI model and sends the necessary input data via an API.

[0835] Content generation

[0836] Each generative AI model generates content based on the data it receives. The text generation AI generates a scenario, and the image generation AI generates related images based on that text. The voice generation AI uses the generated scenario and images to generate narration. The emotion engine evaluates the generated content and makes adjustments based on the user's mood and preferences.

[0837] Content validation and optimization

[0838] The server validates the generated content, checking the quality of each output (e.g., sound quality, image quality, text integrity) and automatically correcting or optimizing it. For example, if the voice is not clear, it adjusts the parameters of the voice generation AI and regenerates it.

[0839] Preparing content for distribution

[0840] The optimized content is sent from the server to the device, where the user can check the generated content on the device and also see the feedback provided by the emotion engine.

[0841] Feedback and Regeneration

[0842] The user inputs feedback on the generated content, which is sent via the device to the server, which then re-analyzes it and re-runs each generative AI model to regenerate the content.

[0843] Finalize and distribute content

[0844] If the user is satisfied with the generated content after final confirmation, they can upload it to social media or their website. The server can also suggest the optimal distribution method based on the data from the emotion engine.

[0845] Specific examples

[0846] A user types into their device, "I want to create a one-minute short video about phishing scams." The device uses an emotion engine to collect emotional data from the user's facial expressions and voice, and adjusts the requirements based on this data. The device then sends the requirements and emotional data to the server, which receives and analyzes them. After analyzing, the server selects an appropriate generative AI model (e.g., GPT-3 for text generation, GAN for image generation, WaveNet for voice generation) and activates each AI model to generate content. The generated content is then quality-verified and optimized on the server, and the optimized content is sent to the device. The user reviews the content and provides feedback, and the server reanalyzes and regenerates it. Finally, once the user is satisfied, the content is distributed to social media and the website.

[0847] This system makes it possible to efficiently and automatically generate and effectively deliver high-quality security awareness content that is tailored to the user's emotions.

[0848] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0849] System program processing flow

[0850] Step 1:

[0851] The user inputs the content generation requirements using the terminal.

[0852] Input data: purpose of the video, subject, length, format, etc.

[0853] Specific operation: The user inputs into the device's input screen that they would like to create a "one-minute short video about phishing scams." The device uses an emotion engine to collect emotional data from the user's facial expressions and voice. This emotional data is used to adjust the requirements for content generation.

[0854] Step 2:

[0855] The terminal transmits the input requirements and emotion data to the server.

[0856] Input data: User-generated requirements and sentiment data.

[0857] Specific operation: The device sends the generation requirements and emotion data to the server in the form of an HTTP request. The data is packaged in JSON format.

[0858] Step 3:

[0859] The server receives the input requirements and emotion data and analyzes them.

[0860] Input data: Generation requirements and emotion data sent from the device.

[0861] How it works: The server receives an HTTP request and stores the information in a database. The analysis engine then analyzes the generation requirements and sentiment data to extract parameters (e.g., theme, format, length). The sentiment data is also analyzed, and the generation requirements are adjusted as needed.

[0862] Step 4:

[0863] The server selects and launches an appropriate generative AI model based on the analysis results.

[0864] Input data: Parsed generative requirements and sentiment data.

[0865] Specific operation: Based on the analysis results, the server selects and launches an appropriate generative AI model, such as a GPT-3 model for text generation, a GAN model for image generation, or a WaveNet model for voice generation. The necessary input data for each AI model is sent via API.

[0866] Step 5:

[0867] Generative AI models generate content such as text, images, and audio.

[0868] Input data: Input data for each generative AI model (e.g., scenario text, related images, narration script).

[0869] How it works: The text generation AI model generates a scenario, the image generation AI model generates related images, and then the voice generation AI model generates a narration voice. Reflecting data from the emotion engine, content is generated that matches the user's preferences and mood.

[0870] Step 6:

[0871] The server verifies the quality of the generated content and makes optimizations if necessary.

[0872] Input data: Text, images, and audio output by the generative AI model.

[0873] Specific operation: The server verifies the sound quality, image quality, length, etc. of the generated content, and automatically corrects any defects found. For example, if the audio is not clear, the parameters of the audio generation AI are adjusted and the content is generated again.

[0874] Step 7:

[0875] The optimized content is sent from the server to the terminal.

[0876] Input data: optimized text, images, and audio.

[0877] Specific operation: The server sends the optimized content to the device in the form of an HTTP response. The user checks the content on the device and also checks the feedback provided by the emotion engine.

[0878] Step 8:

[0879] The user inputs feedback on the generated content and transmits it to the server via the terminal.

[0880] Input data: User feedback and sentiment data.

[0881] Specific operation: The user enters their opinion or request into the feedback screen on the device and presses the send button. The device then sends the feedback and emotion data to the server.

[0882] Step 9:

[0883] The server re-analyzes the feedback and emotion data and re-runs the generative AI model to re-generate the content.

[0884] Input data: User feedback and sentiment data.

[0885] Specific operation: The server reanalyzes the received feedback and emotion data, reruns each generative AI model, and generates new content including modifications based on the user's requests.

[0886] Step 10:

[0887] The user then makes a final check and uploads the generated content to social media or their website.

[0888] Input data: Final verified content.

[0889] Specific operation: The user checks the content generated on the device and uploads it to social media or a website when satisfied. The server can also suggest the optimal distribution method based on the emotion engine data.

[0890] The above processing steps allow users to efficiently generate and distribute high-quality, emotionally appropriate security awareness content.

[0891] (Application example 2)

[0892] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0893] Conventional ad generation systems struggled to generate personalized content based on user emotions and preferences, and could only provide generic ads. Furthermore, they lacked the ability to regenerate the quality and effectiveness of generated content based on user feedback, making it difficult to maximize advertising effectiveness. This limited the effectiveness of advertising and prevented improvements in user engagement.

[0894] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0895] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the generation requirements, means for generating the required text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means including an emotion engine that acquires user emotion data and adjusts the generation requirements, means for sending the optimized content to the user, means for regenerating content based on user feedback, and means for delivering the generated content. This enables personalized content generation based on emotions and content regeneration based on user feedback.

[0896] A "user" is a person who uses a service or system and makes requests or feedback.

[0897] "Generation requirements" are specific conditions and requirements regarding the content that a user wants to generate.

[0898] A "means" is a method or device by which a system performs a specific function or process.

[0899] A "server" is a computer system that receives input data, analyzes it, and takes appropriate action.

[0900] A "generative AI model" is a model that uses artificial intelligence to automatically generate media such as text, images, and audio.

[0901] "Emotion data" is information about emotions acquired from the user's facial expressions, tone of voice, and the like.

[0902] The "emotion engine" is a system that recognizes user emotional data and provides data useful for adjusting generation requirements and optimizing content.

[0903] "Content" means media consisting of text, images, audio, or a combination thereof created by a generative AI model.

[0904] "Feedback" refers to ratings and opinions provided by users regarding generated content.

[0905] "Personalized" refers to a state that is tailored based on the preferences and feelings of a particular user.

[0906] An "advertisement" is visual or audio content created to promote a product or service.

[0907] "Optimization" is the process of improving the quality of content and making it best suited for a purpose.

[0908] "Distribution" refers to providing the generated content to intended users over the Internet.

[0909] The present invention is a system that uses a generative AI model incorporating an emotion engine to provide personalized advertising content to users. This system is composed of hardware and software such as a user terminal, a server, a generative AI model, and an emotion engine. A specific embodiment of this system will be described.

[0910] This system works as follows: First, the user inputs the requirements for the advertising content they want to generate using a device such as a smartphone. The requirements include the ad's theme, length, format, etc. The emotion engine then obtains emotional data from the user's facial expressions and tone of voice and adjusts the requirements accordingly.

[0911] The device then transmits the acquired generation requirements and emotion data to the server, which analyzes the received data and selects and activates an appropriate generative AI model based on that data. These generative AI models include various models for text generation, image generation, and speech generation.

[0912] Generative AI models generate the necessary media, such as text, images, and audio, to create advertising content. For example, text generation AI creates a scenario, image generation AI generates related visuals, and audio generation AI generates narration. These generation processes take into account user emotional data.

[0913] The generated ad content is verified for quality on the server, with parameters such as sound quality, image quality, length, and overall structure being checked, and optimizations made as needed based on data from the emotion engine.

[0914] The optimized content is then sent back to the user's device from the server, where it can be viewed by the user. When the user enters feedback, the device sends it to the server, which analyzes the feedback and performs any necessary regeneration.

[0915] Finally, advertising content that users are satisfied with is published on social media, websites, etc. At this time, the content is delivered in the most appropriate way based on the data obtained from the emotion engine.

[0916] The specific hardware and software used includes the following:

[0917] Device: Internet-enabled smartphone

[0918] Server: High-performance cloud computing system

[0919] Generative AI models: Natural language processing models such as OpenAI's GPT-4, image generation models, and speech generation models

[0920] Emotion engine: An emotion recognition system such as Microsoft Azure Face API

[0921] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0922] "Generate a 30-second video ad about a new product introduction. The user emotion is 'joy' and the tone of voice is high-pitched."

[0923] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0924] Step 1:

[0925] The user operates the device to input requirements for generating advertising content, and the emotion engine obtains emotional data from the user's facial expressions and tone of voice. The input data includes the advertisement's theme, length, format, and emotional data, which are then used for subsequent processing.

[0926] Step 2:

[0927] The device sends the input generation requirements and emotion data to the server. Specifically, the data is transferred to the server using an HTTP request. The input data becomes the material for analysis processing on the server.

[0928] Step 3:

[0929] The server receives the data and analyzes the generation requirements and sentiment data. During this process, the data is checked for consistency and parameters are extracted, such as the theme and format of the ad and the user's sentiment information, which are then stored in a database.

[0930] Step 4:

[0931] Based on the analysis results, the server selects and activates the optimal generative AI model. Selection criteria include the application of text generation AI, image generation AI, and voice generation AI appropriate for the theme. Furthermore, emotion data is used to fine-tune the generated content.

[0932] Step 5:

[0933] After the generative AI model is selected, it generates advertising content such as text, images, and audio. Specifically, the generative AI model receives a prompt as input and generates output based on it. For example, a prompt might be, "Generate a 30-second video ad for a new product introduction. The user's emotion is 'joy' and the voice tone is high-pitched."

[0934] Step 6:

[0935] The server receives the generated ad content and verifies its quality. Audio quality, picture quality, and overall composition are checked, and any defects are automatically corrected. This verification uses image and sound quality optimization algorithms.

[0936] Step 7:

[0937] The optimized content is sent from the server to the device. The user is allowed to view the content for final confirmation. The user reviews the ad content and provides feedback if necessary.

[0938] Step 8:

[0939] Users input feedback via their devices and send it to the server. The feedback includes requests for content changes and improvements. This data is used as a reference when the server regenerates the content.

[0940] Step 9:

[0941] The server analyzes the feedback and re-runs the generative AI model if regeneration is necessary, setting new parameters based on the feedback data and generating new ad content.

[0942] Step 10:

[0943] The final regenerated ad content is then resent to the user's device. This loop is repeated until the user is satisfied. The final certified ad content is then delivered to the social networking site or website.

[0944] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0945] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0946] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0947] [Third embodiment]

[0948] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0949] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0950] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0951] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0952] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0953] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0954] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0955] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0956] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0957] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0958] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0959] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0960] This invention relates to a system that automatically generates security awareness content using generative AI. The system is composed of a server, a terminal, a generative AI model, and other components.

[0961] System configuration

[0962] The system includes the following elements:

[0963] Terminal: Provides an interface for users to input production requirements, review, feedback, and finally deliver the generated content.

[0964] Server: A central computing system that receives and analyzes production requirements, selects appropriate generative AI models, and generates, validates, optimizes, and regenerates content.

[0965] Generative AI model: An artificial intelligence model for generating media such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[0966] Program processing explanation

[0967] 1. Enter your content requirements

[0968] Users input the requirements for the content they want to generate through their device, including the purpose, theme, length, and format of the video.

[0969] 2. Submit your requirements

[0970] The device sends the input requirements to the server, which analyzes the received requirements and determines the required generative AI model.

[0971] 3. Launching the Generative AI

[0972] The server selects and activates the appropriate generative AI model based on the analysis results. For example, when creating a short video to combat phishing scams, it activates a text generation AI, an image generation AI, and a voice generation AI.

[0973] 4. Content Generation

[0974] The generative AI model generates content based on user requirements, such as phishing scenarios, warning images, explanatory illustrations, and narration audio.

[0975] 5. Content validation and optimization

[0976] The server verifies the quality of the generated content, checking parameters such as audio quality, video quality, and length, and automatically correcting and optimizing as needed.

[0977] 6. Preparing content for distribution

[0978] The optimized content is sent from the server to the device for the user to review, and if the user is not satisfied, they can enter feedback.

[0979] 7. Feedback and Regeneration

[0980] Once the user submits their feedback, the server re-analyzes it and re-runs the generative AI model, repeating this process until content that satisfies the user is generated.

[0981] 8. Finalize and distribute content

[0982] After the user has final confirmation and is satisfied with the content, they can upload it to social media or their website, allowing the security awareness content to reach a wider audience.

[0983] Specific examples

[0984] Short video generation to combat phishing scams

[0985] 1. Enter your content requirements

[0986] The user uses a device to input the requirements for a "one-minute short video about phishing scams." Input items include "phishing scams," "one minute," and "video format."

[0987] 2. Submit your requirements

[0988] The terminal sends the input requirements to the server, which receives the request and starts requirement analysis.

[0989] 3. Launching the Generative AI

[0990] Based on the analysis results, the server selects and activates an appropriate AI model, such as text generation AI, image generation AI, or voice generation AI.

[0991] 4. Content Generation

[0992] The text generation AI generates phishing scam scenarios and points to watch out for, the image generation AI generates related warning images and explanatory illustrations, and the audio generation AI generates narration audio.These are then combined to create a one-minute short video.

[0993] 5. Content validation and optimization

[0994] The server verifies the quality of the video and optimizes the sound and image quality.

[0995] 6. Preparing content for distribution

[0996] The optimized video is sent from the server to the terminal and viewed by the user.

[0997] 7. Feedback and Regeneration

[0998] The user provides feedback as needed and the server regenerates it.

[0999] 8. Finalize and distribute content

[1000] After the user confirms it, they can upload the generated video to social media or their website.

[1001] As a result, the present invention can efficiently and effectively generate security awareness content, thereby raising the level of security knowledge of users and companies.

[1002] The processing flow will be explained below.

[1003] Step 1:

[1004] The user inputs the requirements for the content they want to generate using their device (e.g., a one-minute short video about phishing scams). Specifically, they input information such as the theme, format, length, and purpose into the device's input form.

[1005] Step 2:

[1006] The terminal transmits the input requirements to the server. Specifically, the terminal transmits the requirement data to the server using an HTTP request.

[1007] Step 3:

[1008] The server receives the input requirements and performs analysis. Specifically, it analyzes the received data and extracts each parameter (e.g., topic, format, length).

[1009] Step 4:

[1010] The server selects and activates the appropriate generative AI model based on the analysis results. Specifically, it selects the text generation AI, image generation AI, and voice generation AI necessary for generating short videos to combat phishing scams.

[1011] Step 5:

[1012] The generative AI model generates content such as text, images, and audio. Specifically, the text generation AI generates the scenario, the image generation AI generates the related images, and the audio generation AI generates the narration audio.

[1013] Step 6:

[1014] The server aggregates the generated content, specifically creating a video file using the generated text, images, and audio.

[1015] Step 7:

[1016] The server verifies the quality of the generated content and optimizes it if necessary, specifically by checking audio and video quality and applying automatic corrections and enhancements.

[1017] Step 8:

[1018] The server sends the optimized content to the device. Specifically, it generates a content URL so that the user can view it and notifies the device.

[1019] Step 9:

[1020] The user views the generated content through their device, specifically by accessing the provided URL and watching the video.

[1021] Step 10:

[1022] The user enters feedback and sends it to the server. Specifically, the user enters feedback in the evaluation form and presses the submit button.

[1023] Step 11:

[1024] The server receives the feedback and initiates the regeneration process if necessary, specifically by analyzing the regeneration points and relaunching the associated generative AI models.

[1025] Step 12:

[1026] The user then performs a final check and uploads the generated content to social media or their website. Specifically, they download the generated video file and post it to each platform.

[1027] Example 1

[1028] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1029] In today's world, security awareness education via the Internet is extremely important. However, manually creating security awareness content requires a significant amount of time and expertise, making it difficult to generate content efficiently. It is also difficult to consistently improve the quality of generated content or quickly improve it based on feedback. For this reason, there is a need for a system that uses generative AI to automatically generate, optimize, and distribute high-quality security awareness content.

[1030] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1031] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the analysis results, means for generating necessary media data using a generative AI model including a text generator, an image generator, and a voice generator to create content, means for verifying the quality of the generated content and automatically correcting or optimizing it as necessary, means for transmitting the optimized content to the user, means for regenerating the content based on user feedback, and means for preparing the generated content after final confirmation for distribution and distributing it to multiple platforms. This enables the automatic generation and rapid correction of high-quality security awareness content based on user requirements.

[1032] "User" means a person or organization that uses the system to generate, review, and distribute security awareness content.

[1033] "Server" is a central computer system that analyzes the generation requirements entered by the user, selects, launches, and executes the appropriate generative AI model, and validates, optimizes, and delivers the generated content.

[1034] The "creation requirements" are information including detailed requests such as the purpose, theme, length, and format of the content the user wants to create.

[1035] A "generative AI model" is an artificial intelligence model used to generate media data such as text, images, and audio, and specifically includes text generators, image generators, and audio generators.

[1036] A "text generator" is a device that generates necessary text data based on user requirements.

[1037] An "image generating device" is a device that generates the necessary image data based on the user's requirements.

[1038] A "voice generating device" is a device that generates necessary voice data based on the user's requirements.

[1039] "Media data" refers to all data that forms content, such as text, images, and audio.

[1040] "Content" refers to a collection of data, including text, images, audio, etc., generated and optimized by a generative AI model for security awareness purposes.

[1041] "Feedback" is information including users' evaluations of the generated content and requests for improvement.

[1042] "Auto-remediation" is the process by which the server verifies the quality of generated content and automatically makes corrections as needed.

[1043] "Optimization" is the process of improving the generated content according to quality and user requirements.

[1044] "Distribution" is the process of publishing the final, verified generated content to multiple platforms.

[1045] "Platform" refers to a website, social networking site, or other online service for distributing Generated Content.

[1046] The present invention relates to a system that automatically generates security awareness content by utilizing a generative AI model. The system is configured by combining a server, a terminal, a generative AI model, etc. The configuration and operation for specifically implementing the present invention are described below.

[1047] System configuration

[1048] The system includes the following elements:

[1049] Terminal: A device through which a user inputs content generation requirements, checks, provides feedback, and finally distributes the generated content.

[1050] Server: A central computing system that receives and analyzes the generation requirements from users, selects and launches appropriate generative AI models, and generates, validates, optimizes, and regenerates content.

[1051] Generative AI model: An artificial intelligence model for generating media data such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[1052] Program processing

[1053] 1. Enter content requirements

[1054] Users input the requirements for the content they want to generate through their device. Input items include the purpose, theme, length, format, etc. of the video. For example, they input the requirements for a "one-minute short video about phishing scams."

[1055] 2. Submit your requirements

[1056] The device sends the input requirements to the server, which analyzes the received requirements and selects a generative AI model suitable for content generation.

[1057] 3. Launching the Generative AI

[1058] Based on the analysis results, the server selects and activates a generative AI model, including a text generator, an image generator, and a voice generator. For example, when creating a short video to combat phishing scams, these three devices work together.

[1059] 4. Content Generation

[1060] The generative AI model generates the necessary media data based on the user's requirements. For example, it uses a text generator to create a scenario, an image generator to generate warning images and explanatory illustrations, and a voice generator to generate narration. These are then integrated to create content in the form of a one-minute short video.

[1061] 5. Content validation and optimization

[1062] The server verifies the quality of the generated content, checking audio quality, image quality, length, and script consistency, and automatically corrects and optimizes it if necessary.

[1063] 6. Preparing content for distribution

[1064] The server sends the optimized content to the device for user confirmation, and the user can preview the generated content through the device and provide feedback as needed.

[1065] 7. Feedback and Regeneration

[1066] When the user submits feedback from their device, the server re-analyzes and re-runs the necessary generative AI models, repeating this process until the user is satisfied.

[1067] 8. Finalize and distribute content

[1068] If the user is satisfied with the content after final confirmation, they can issue a command to upload it to a social networking site or website from their device. The server then formats the content for distribution and distributes it to the specified platform.

[1069] Specific examples

[1070] For example, to generate a one-minute short anti-phishing video, use the following prompt:

[1071] "Create a short 1-minute video about phishing scams. Please include the following:

[1072] Phishing scam method explained

[1073] Examples of fraudulent emails and how to deal with them

[1074] Attention to viewers

[1075] As a result, the present invention can efficiently and effectively generate security awareness content, thereby improving the security knowledge of users and organizations.

[1076] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1077] Step 1:

[1078] The user inputs the generation requirements using a terminal.

[1079] Specifically, the user inputs the prompt for a "one-minute short video about phishing scams." The input data includes information such as "phishing scams," "one minute," and "video format." This input information is then saved on the device.

[1080] Step 2:

[1081] The terminal transmits the requirements input by the user to the server.

[1082] Specifically, the device sends input data in JSON format or other appropriate data format to the server. The sent data includes the purpose, theme, length, format, etc. The server receives this data and begins analyzing it. Input data: "Phishing scam," "1 minute," "Video format"

[1083] Output data: Parsed requirements

[1084] Step 3:

[1085] The server analyzes the received requirements and selects the optimal generative AI model.

[1086] The server determines which generative AI models (text generator, image generator, and voice generator) are needed based on the analyzed requirements. For example, a short video to combat phishing requires these three generative AI models. Input data: Analyzed requirements

[1087] Output data: Selected generative AI model

[1088] Step 4:

[1089] The server launches the selected generative AI model.

[1090] The server uses an interface such as a REST API to launch the generative AI model and begin the generation process. For example, it sends instructions such as "Generate a phishing scam scenario" to the text generator and "Convert the generated scenario into audio" to the voice generator. Input data: Selected generative AI model

[1091] Output data: Start command

[1092] Step 5:

[1093] A generative AI model generates content based on user requirements.

[1094] Specifically, the text generator creates a phishing scam scenario, the image generator generates related warning images and explanatory illustrations, and the audio generator generates a narration based on the generated scenario. These are then integrated to create a one-minute short video. Input data: Generation requirements

[1095] Output Data: Generated Content

[1096] Step 6:

[1097] Validate the quality of the server-generated content.

[1098] Specifically, it checks the sound quality, image quality, content length, and consistency of the scenario, and automatically corrects or optimizes it if necessary. For example, if there are any unclear parts of the audio, it issues instructions to the audio generator again. Input data: Generated content

[1099] Output: Optimized content

[1100] Step 7:

[1101] The server sends the optimized content to the device for the user to view.

[1102] Specifically, the server converts the generated content into the appropriate format and sends a preview link or file to the device. The user can preview the generated video using this link. Input data: Optimized content

[1103] Output data: Preview link or file

[1104] Step 8:

[1105] The user inputs feedback through the terminal and transmits it to the server.

[1106] Specifically, users input specific feedback such as "Please make the video a little shorter" or "Please make the illustrations easier to understand." The device then sends this feedback to the server. Input data: User feedback

[1107] Output data: Feedback data

[1108] Step 9:

[1109] The server analyzes the feedback and re-runs any necessary generative AI models.

[1110] For example, based on feedback such as "Please shorten the length of the video," the system issues instructions to the text generator and modifies the scenario. This process is repeated until the user is satisfied. Input data: Feedback data

[1111] Output Data: Regenerated content

[1112] Step 10:

[1113] If the user is satisfied with the generated content after making a final check, they can issue instructions from their device to upload it to a social networking site or their homepage.

[1114] The server formats the content for distribution and distributes it to the specified platform, ensuring that the security awareness content reaches a wide audience. Input data: Final confirmation and distribution instructions

[1115] Output data: Streamed content

[1116] (Application example 1)

[1117] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1118] Despite the growing importance of security on the Internet in recent years, it is difficult to effectively communicate security alerts to users in an easy-to-understand manner. In particular, there is a demand for a system that can automatically and quickly generate content to promote awareness of specific threats such as phishing scams, but current technology is unable to meet this demand. In addition, optimizing the quality of the generated content based on user feedback is also an important issue.

[1119] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1120] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the generation requirements, means for generating the necessary text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means for sending the optimized content to the user, means for regenerating the content based on user feedback, means for the user to make final confirmation, and means for distributing the generated content to a platform on the Internet. This makes it possible to quickly and effectively generate security awareness content and promote user understanding.

[1121] "User" is the entity that inputs requirements for the generation of security awareness content, reviews the generated content, and provides feedback as needed.

[1122] "Generation requirements" are information that indicates the detailed specifications and requests for the security awareness content that a user wants to generate.

[1123] "Server" means a central computing system that analyzes the generation requirements received from the User, selects and launches an appropriate generative AI model, validates and optimizes the generated content, and transmits it to the User.

[1124] A "generative AI model" is an artificial intelligence model that generates media such as text, images, and audio, and performs appropriate generation as needed.

[1125] "Text" refers to sentences or character information generated by a generative AI model.

[1126] "Image" means a visual graphic or illustration generated by a generative AI model.

[1127] "Audio" refers to auditory narration or audio data generated by a generative AI model.

[1128] "Content" means comprehensive security awareness information, including text, images, and audio, generated by a generative AI model.

[1129] "Quality verification" is the process of checking the quality of each element of generated content (text, images, audio) and making corrections or improvements as necessary.

[1130] "Optimization" is the process of automated adjustments and refinements based on quality validation results to improve the quality of the generated content.

[1131] "Feedback" refers to opinions and requests provided by users regarding generated content.

[1132] "Regeneration" is the process of regenerating content by running the generative AI model again based on user feedback.

[1133] "Means of Final Review" means the means by which a user reviews and approves the final version of the generated content.

[1134] "Distribution" is the process of publishing the finalized security awareness content on an internet platform to reach a wide audience.

[1135] The present invention is a system for automatically generating security awareness content, with the aim of providing effective education on security threats on the Internet in particular. The system automates the process of optimizing and distributing the content generated based on user input requirements.

[1136] System Components

[1137] 1. Terminal: A device that allows users to input production requirements, review the generated content, and provide feedback if necessary. Terminals include smartphones, personal computers, tablets, etc.

[1138] 2. Server: The server is a central computing system that analyzes the generation requirements received from users, selects and launches an appropriate generative AI model, validates and optimizes the generated content, and finally sends it to users.

[1139] 3. Generative AI models: These include text generation models, image generation models, and speech synthesis models. For example, natural language processing models (GPT-4) are used for text generation, generative adversarial networks (GANs) are used for image generation, and WaveNet is used for speech synthesis.

[1140] Program processing explanation

[1141] 1. Enter content generation requirements

[1142] The user uses a device to input the requirements for the security awareness content they want to generate. This can be a detailed request, such as "a five-minute video about phishing scams." The input requirements are sent from the device to the server.

[1143] 2. Requirements Analysis

[1144] The server analyzes the generation requirements received from the user and selects the appropriate generative AI model. For example, if the request is for a "5-minute video," a text generation model, an image generation model, and a speech synthesis model will be activated.

[1145] 3. Content Generation

[1146] The generative AI model runs on the server and generates text, images, and audio according to the user's requirements, including phishing scenarios, warning images, explanatory illustrations, and audio narration.

[1147] 4. Quality verification and optimization

[1148] The generated content is verified by the server for quality, checking parameters such as sound quality, image quality, and content length, and optimizing it if necessary.

[1149] 5. Feedback processing and regeneration

[1150] The optimized content is sent to the device for review by the user, who provides feedback, which the server analyzes and regenerates if necessary.

[1151] 6. Finalize and distribute content

[1152] Once the user has given a final review and is satisfied with the generated content, the content is distributed to a platform on the Internet.

[1153] Hardware and software used

[1154] Hardware: Smartphones, personal computers, servers

[1155] Software: Natural language processing model (GPT-4), image generation model (GANs), speech synthesis model (WaveNet)

[1156] Specific examples

[1157] Input prompt example

[1158] A user fills out a form in your app with:

[1159] Content Topic:Phishing

[1160] Content format: 5-minute short videos

[1161] Video length: 5 minutes

[1162] Target audience: general users

[1163] Part of the processing flow

[1164] The prompts entered by the user are sent to the server, which then activates the generative AI model to generate text, images, and audio. The generated content is then sent to the device after quality verification, where it is regenerated after user confirmation and feedback, and finally distributed to the platform after final confirmation.

[1165] This invention makes it possible to generate security awareness content quickly and effectively, and is expected to improve users' security awareness.

[1166] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1167] Step 1:

[1168] The user inputs the generation requirements using a terminal. Input items include the content theme, format, length, and target audience. This input data is sent from the terminal to the server. Input examples include "Content theme: phishing scams," "Content format: 5-minute short video," and "Target audience: general users."

[1169] Step 2:

[1170] The server receives and analyzes the generation requirements sent from the device. Specifically, it uses natural language processing (NLP) to analyze the user's requirements as text data and selects an appropriate generation AI model. For example, if the theme "phishing scam" is detected, it selects a generation AI model specialized in phishing scams.

[1171] Step 3:

[1172] The server selects and launches an appropriate generative AI model based on the analysis results. The selected generative AI models include a text generation model (GPT-4), an image generation model (DALL-E), and a speech synthesis model (WaveNet). For example, these models are launched sequentially according to the requirement of a "5-minute short video."

[1173] Step 4:

[1174] The generative AI model generates content based on user requirements. Specifically, the text generation model generates phishing scam scenarios, the image generation model generates warning images and explanatory illustrations, and the speech synthesis model generates narration. The data generated by each model is integrated to create a single content file.

[1175] Step 5:

[1176] The server verifies the quality of the generated content and optimizes it as necessary. Specifically, it automatically checks parameters such as sound quality, image quality, and length, and makes corrections as necessary. Based on the results of this verification, if the quality of the generated content does not meet certain standards, it will automatically make corrections.

[1177] Step 6:

[1178] The optimized content is sent from the server to the terminal. The user checks the generated content on the terminal and inputs feedback. For example, the user may provide feedback such as "I would like the sound quality of the narration to be improved."

[1179] Step 7:

[1180] User feedback is sent to the server, which analyzes it and, if necessary, re-launches the generative AI model to regenerate new content that reflects the feedback.

[1181] Step 8:

[1182] The server resends the content to the device for the user to check. If the user is satisfied with the content after checking it, the content is distributed to an internet platform. For example, a specific distribution method such as "upload to SNS" is selected.

[1183] Through the above processing steps, users can easily create high-quality security awareness content and deliver it to a wide audience.

[1184] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1185] This invention combines an emotion engine with a system that automatically generates security awareness content using generative AI. This system is composed of a server, a terminal, a generative AI model, an emotion engine, etc.

[1186] System configuration

[1187] The system includes the following elements:

[1188] Terminal: Provides an interface for users to input generation requirements, review the generated content, get feedback, obtain sentiment data, and finally deliver it.

[1189] Server: A central computing system that receives and analyzes generative requirements, and manages and operates the appropriate generative AI models and emotion engines.

[1190] Generative AI model: An artificial intelligence model for generating media such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[1191] Emotion Engine: Recognizes user emotions and provides data to help adjust production requirements, optimize content, and regenerate it.

[1192] Program processing explanation

[1193] 1. Enter content requirements

[1194] The user inputs the requirements for the content they want to generate through their device. Input items include the purpose, theme, length, and format of the video. The emotion engine reads the user's emotions from their facial expressions and voice and adjusts the generation requirements accordingly.

[1195] 2. Submit your requirements

[1196] The terminal transmits the input requirements and emotion data generated by the emotion engine to the server. Specifically, the terminal transmits the requirements data and emotion data to the server using an HTTP request.

[1197] 3. Receiving and analyzing requirements

[1198] The server receives the input requirements and performs analysis. The received data is analyzed to extract each parameter (e.g., theme, format, length). Emotion data is also analyzed at this time.

[1199] 4. Selecting and starting the generation AI

[1200] The server selects and activates the appropriate generative AI model based on the analysis results. For example, it selects the text generation AI, image generation AI, and voice generation AI needed to generate short videos to combat phishing scams.

[1201] 5. Content Generation

[1202] The generative AI model generates content such as text, images, and audio. For example, a text generation AI generates a scenario, an image generation AI generates related images, and an audio generation AI generates narration audio. Based on data from the emotion engine, content is generated that matches the user's preferences and mood.

[1203] 6. Content validation and optimization

[1204] The server verifies the quality of the generated content, checking parameters such as sound quality, image quality, and length, and automatically correcting or optimizing as necessary. By taking into account data from the emotion engine, the content is more suited to the user's emotions.

[1205] 7. Preparing content for distribution

[1206] The optimized content is sent from the server to the device for the user to review, and data obtained from the emotion engine also helps with the review.

[1207] 8. Feedback and Regeneration

[1208] The user enters feedback and sends it to the server. The server receives the feedback and emotion data, reanalyzes it, and reruns the generative AI model as needed to regenerate the data.

[1209] 9. Finalize and distribute content

[1210] If the user is satisfied with the content after final confirmation, they can upload it to social media or their website. Based on the data obtained by the emotion engine, the content can be delivered in the most appropriate way for the user.

[1211] Specific examples

[1212] Short video generation to combat phishing scams

[1213] 1. Enter your content requirements

[1214] The user inputs the requirements for a "one-minute short video about phishing scams" using a terminal. The emotion engine reads emotional data from the user's facial expressions and voice and adjusts the requirements accordingly.

[1215] 2. Submit your requirements

[1216] The terminal transmits the input requirements and emotion data to the server.

[1217] 3. Receiving and analyzing requirements

[1218] The server analyzes the requirements, selects the appropriate generative AI model and emotion engine, and performs the analysis.

[1219] 4. Selecting and starting the generation AI

[1220] The server selects and activates text generation AI, image generation AI, and voice generation AI.

[1221] 5. Content Generation

[1222] The text generation AI generates phishing scam scenarios and points to watch out for, the image generation AI generates related warning images and explanatory illustrations, and the voice generation AI generates narration. Based on data from the emotion engine, content tailored to the user's preferences is generated.

[1223] 6. Content validation and optimization

[1224] The server verifies the quality of the video and optimizes the audio and video quality, taking into account the data from the emotion engine.

[1225] 7. Preparing content for distribution

[1226] The optimized video is sent from the server to the terminal and viewed by the user.

[1227] 8. Feedback and Regeneration

[1228] The user enters feedback and sends it to the server, which then reanalyzes it and reruns the generative AI model to regenerate it.

[1229] 9. Finalize and distribute content

[1230] The user then finalizes the video and uploads it to social media or their website. Based on the data from the emotion engine, the video is distributed in the most appropriate way for the user.

[1231] As a result, the present invention can efficiently and effectively generate security awareness content and raise the level of security knowledge of users and companies. Furthermore, by combining it with an emotion engine, it is possible to provide content that is suited to the user's emotions.

[1232] The processing flow will be explained below.

[1233] Step 1:

[1234] The user inputs the requirements for the content they wish to generate using their device. Specifically, they enter information such as "phishing scam," "1 minute," and "video format" into the device's input form. At this time, the emotion engine analyzes the user's facial expressions and voice in real time to collect emotional data.

[1235] Step 2:

[1236] The terminal transmits the input requirements and emotion data to the server. Specifically, an HTTP request including the requirement information and emotion data is transmitted to the server.

[1237] Step 3:

[1238] The server receives the requirements and emotional data and performs analysis, extracting parameters (e.g., topic, format, length) from the received data, and also analyzes the emotional data to determine the user's current emotional state.

[1239] Step 4:

[1240] The server selects and activates the appropriate generative AI model based on the analysis results, selecting the necessary text generation AI, image generation AI, and voice generation AI, and customizing the generation process based on emotion data.

[1241] Step 5:

[1242] The generative AI model generates content such as text, images, and audio. Specifically, the text generation AI creates a phishing scam scenario, the image generation AI generates related images, and the audio generation AI generates narration audio. Emotional data is used to generate content with a tone and style that matches the user's emotions.

[1243] Step 6:

[1244] The server aggregates the generated content, specifically creating a one-minute short video using the generated text, images, and audio.

[1245] Step 7:

[1246] The server verifies the quality of the generated content and optimizes it. Specifically, it checks the audio and video quality, removes or modifies unnecessary elements, and takes into account emotional data to optimize the content in a way that is likely to be perceived favorably by users.

[1247] Step 8:

[1248] The server sends the optimized content to the device, specifically by generating and notifying the user of the content URL so that the user can view it.

[1249] Step 9:

[1250] The user checks the generated content through their device. Specifically, they access the provided URL and watch the video, and the emotion engine collects the user's reactions again.

[1251] Step 10:

[1252] The user inputs feedback about the content and sends it to the server. Specifically, the user fills out the feedback in the evaluation form and presses the submit button.

[1253] Step 11:

[1254] The server receives the feedback and emotion data and re-analyzes it, identifying points that need to be regenerated based on the emotion data.

[1255] Step 12:

[1256] The server then initiates the regeneration process, reactivating the selected generative AI model to generate new content based on the feedback and emotional data.

[1257] Step 13:

[1258] The user performs a final check on the device and then uploads the generated content to social media or a website. Specifically, the user downloads the generated video file and completes the distribution procedure. It is also possible to adjust the timing and method of distribution based on data obtained from the emotion engine.

[1259] Example 2

[1260] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1261] In order to effectively generate and distribute security awareness content on the Internet, a wide range of processes are required, including adjusting generation requirements, content generation, quality verification, optimization, and feedback re-implementation. However, existing systems do not adequately integrate these processes, making it difficult to automatically generate and provide optimal content that responds to user emotions.

[1262] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1263] In this invention, the server includes means for a user to input generation requirements, means for a terminal to acquire emotion data and adjust the requirements, means for the server to receive and analyze the input requirements and emotion data, means for selecting and activating a generative AI model based on the analysis results, means for generating the necessary text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means for sending the optimized content to the user, means for regenerating the content based on user feedback, and means for delivering the generated content. This makes it possible to automatically generate and efficiently provide high-quality security awareness content that is suited to the user's emotions.

[1264] "User" is a person or organization that uses the system to generate security awareness content, provide input, and provide feedback.

[1265] A "terminal" is a device used by a user that provides an interface for inputting generation requirements, obtaining emotion data, reviewing generated content, and providing feedback.

[1266] "Emotion data" is data that is used to read emotions from the user's facial expressions and voice and to adjust generation requirements and optimize generated content.

[1267] The "server" is a central computing system that receives and analyzes generation requirements and emotion data, selects and launches a generative AI model, verifies and optimizes the quality of the generated content, and finally provides the content to users.

[1268] "Generation requirements" are requirement information such as purpose, theme, length, and format that a user specifies about the content that he or she wants to generate.

[1269] "Analysis" is the process in which the server analyzes the generation requirements and emotion data received and extracts each parameter.

[1270] A "generative AI model" is an artificial intelligence model for generating required media such as text, images, and audio, and includes text generation AI, image generation AI, and audio generation AI.

[1271] "Text generation AI" is an artificial intelligence model that writes appropriate scenarios and explanatory text based on the generation requirements specified by the user.

[1272] "Image generation AI" is an artificial intelligence model that generates relevant images and illustrations based on user-specified generation requirements.

[1273] "Voice generation AI" is an artificial intelligence model that generates narration and voice based on the generation requirements specified by the user.

[1274] "Content" refers to media for security awareness that combines text, images, audio, etc. generated by a generative AI model.

[1275] "Quality verification" is the process by which the server checks the quality of the generated content, such as sound quality, image quality, and length, and automatically corrects or optimizes it as necessary.

[1276] "Optimization" is the process of making necessary adjustments and modifications to improve the quality of the generated content.

[1277] "Feedback" refers to opinions and requests that users provide regarding the generated content, which are reanalyzed by the server and used for regeneration.

[1278] "Distribution" is the process of providing optimized content to users and other platforms.

[1279] This invention combines an emotion engine with a system that uses generative AI to automatically generate security awareness content. This system is configured so that users can input generation requirements, and the emotion engine adjusts those requirements to generate and distribute high-quality content.

[1280] System configuration

[1281] The system includes the following elements:

[1282] Terminal: Provides an interface for users to input generation requirements, review the generated content, receive feedback, obtain emotional data, and finally distribute it. Examples include PCs and smartphones.

[1283] Server: A central computing system that receives and analyzes generative requirements, and manages and operates the appropriate generative AI models and emotion engines.

[1284] Generative AI model: An artificial intelligence model for generating media such as text, images, and audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[1285] Emotion Engine: Recognizes user emotions and provides data to help adjust production requirements, optimize content, and regenerate it.

[1286] Program processing explanation

[1287] Entering content requirements

[1288] Users input the requirements for the content they want to generate through their device. These include the purpose, theme, length, and format of the video. The device then uses an emotion engine to read emotions from the user's facial expressions and voice and adjusts the generation requirements accordingly. For example, if a user wants to create a "one-minute short video about phishing scams," they can input these requirements into their device.

[1289] Submitting requirements

[1290] When the user completes the input and presses the send button, the device uses an HTTP request to send the input requirements and emotion data generated by the emotion engine to the server.

[1291] Receiving and parsing requirements

[1292] The server receives the HTTP request and stores it in a database. The analysis engine then analyzes the data and extracts parameters (e.g., theme, format, length). Sentiment data is also analyzed at this time, and adjustments are made according to requirements.

[1293] Selecting and launching the generation AI

[1294] The server selects the appropriate generative AI model based on the analysis results. For example, GPT-3 is used for text generation, GAN for image generation, and WaveNet for speech generation. It launches each AI model and sends the necessary input data via an API.

[1295] Content generation

[1296] Each generative AI model generates content based on the data it receives. The text generation AI generates a scenario, and the image generation AI generates related images based on that text. The voice generation AI uses the generated scenario and images to generate narration. The emotion engine evaluates the generated content and makes adjustments based on the user's mood and preferences.

[1297] Content validation and optimization

[1298] The server validates the generated content, checking the quality of each output (e.g., sound quality, image quality, text integrity) and automatically correcting or optimizing it. For example, if the voice is not clear, it adjusts the parameters of the voice generation AI and regenerates it.

[1299] Preparing content for distribution

[1300] The optimized content is sent from the server to the device, where the user can check the generated content on the device and also see the feedback provided by the emotion engine.

[1301] Feedback and Regeneration

[1302] The user inputs feedback on the generated content, which is sent via the device to the server, which then re-analyzes it and re-runs each generative AI model to regenerate the content.

[1303] Finalize and distribute content

[1304] If the user is satisfied with the generated content after final confirmation, they can upload it to social media or their website. The server can also suggest the optimal distribution method based on the data from the emotion engine.

[1305] Specific examples

[1306] A user types into their device, "I want to create a one-minute short video about phishing scams." The device uses an emotion engine to collect emotional data from the user's facial expressions and voice, and adjusts the requirements based on this data. The device then sends the requirements and emotional data to the server, which receives and analyzes them. After analyzing, the server selects an appropriate generative AI model (e.g., GPT-3 for text generation, GAN for image generation, WaveNet for voice generation) and activates each AI model to generate content. The generated content is then quality-verified and optimized on the server, and the optimized content is sent to the device. The user reviews the content and provides feedback, and the server reanalyzes and regenerates it. Finally, once the user is satisfied, the content is distributed to social media and the website.

[1307] This system makes it possible to efficiently and automatically generate and effectively deliver high-quality security awareness content that is tailored to the user's emotions.

[1308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1309] System program processing flow

[1310] Step 1:

[1311] The user inputs the content generation requirements using the terminal.

[1312] Input data: purpose of the video, subject, length, format, etc.

[1313] Specific operation: The user inputs into the device's input screen that they would like to create a "one-minute short video about phishing scams." The device uses an emotion engine to collect emotional data from the user's facial expressions and voice. This emotional data is used to adjust the requirements for content generation.

[1314] Step 2:

[1315] The terminal transmits the input requirements and emotion data to the server.

[1316] Input data: User-generated requirements and sentiment data.

[1317] Specific operation: The device sends the generation requirements and emotion data to the server in the form of an HTTP request. The data is packaged in JSON format.

[1318] Step 3:

[1319] The server receives the input requirements and emotion data and analyzes them.

[1320] Input data: Generation requirements and emotion data sent from the device.

[1321] How it works: The server receives an HTTP request and stores the information in a database. The analysis engine then analyzes the generation requirements and sentiment data to extract parameters (e.g., theme, format, length). The sentiment data is also analyzed, and the generation requirements are adjusted as needed.

[1322] Step 4:

[1323] The server selects and launches an appropriate generative AI model based on the analysis results.

[1324] Input data: Parsed generative requirements and sentiment data.

[1325] Specific operation: Based on the analysis results, the server selects and launches an appropriate generative AI model, such as a GPT-3 model for text generation, a GAN model for image generation, or a WaveNet model for voice generation. The necessary input data for each AI model is sent via API.

[1326] Step 5:

[1327] Generative AI models generate content such as text, images, and audio.

[1328] Input data: Input data for each generative AI model (e.g., scenario text, related images, narration script).

[1329] How it works: The text generation AI model generates a scenario, the image generation AI model generates related images, and then the voice generation AI model generates a narration voice. Reflecting data from the emotion engine, content is generated that matches the user's preferences and mood.

[1330] Step 6:

[1331] The server verifies the quality of the generated content and makes optimizations if necessary.

[1332] Input data: Text, images, and audio output by the generative AI model.

[1333] Specific operation: The server verifies the sound quality, image quality, length, etc. of the generated content, and automatically corrects any defects found. For example, if the audio is not clear, the parameters of the audio generation AI are adjusted and the content is generated again.

[1334] Step 7:

[1335] The optimized content is sent from the server to the terminal.

[1336] Input data: optimized text, images, and audio.

[1337] Specific operation: The server sends the optimized content to the device in the form of an HTTP response. The user checks the content on the device and also checks the feedback provided by the emotion engine.

[1338] Step 8:

[1339] The user inputs feedback on the generated content and transmits it to the server via the terminal.

[1340] Input data: User feedback and sentiment data.

[1341] Specific operation: The user enters their opinion or request into the feedback screen on the device and presses the send button. The device then sends the feedback and emotion data to the server.

[1342] Step 9:

[1343] The server re-analyzes the feedback and emotion data and re-runs the generative AI model to re-generate the content.

[1344] Input data: User feedback and sentiment data.

[1345] Specific operation: The server reanalyzes the received feedback and emotion data, reruns each generative AI model, and generates new content including modifications based on the user's requests.

[1346] Step 10:

[1347] The user then makes a final check and uploads the generated content to social media or their website.

[1348] Input data: Final verified content.

[1349] Specific operation: The user checks the content generated on the device and uploads it to social media or a website when satisfied. The server can also suggest the optimal distribution method based on the emotion engine data.

[1350] The above processing steps allow users to efficiently generate and distribute high-quality, emotionally appropriate security awareness content.

[1351] (Application example 2)

[1352] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1353] Conventional ad generation systems struggled to generate personalized content based on user emotions and preferences, and could only provide generic ads. Furthermore, they lacked the ability to regenerate the quality and effectiveness of generated content based on user feedback, making it difficult to maximize advertising effectiveness. This limited the effectiveness of advertising and prevented improvements in user engagement.

[1354] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1355] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the generation requirements, means for generating the required text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means including an emotion engine that acquires user emotion data and adjusts the generation requirements, means for sending the optimized content to the user, means for regenerating content based on user feedback, and means for delivering the generated content. This enables personalized content generation based on emotions and content regeneration based on user feedback.

[1356] A "user" is a person who uses a service or system and makes requests or feedback.

[1357] "Generation requirements" are specific conditions and requirements regarding the content that a user wants to generate.

[1358] A "means" is a method or device by which a system performs a specific function or process.

[1359] A "server" is a computer system that receives input data, analyzes it, and takes appropriate action.

[1360] A "generative AI model" is a model that uses artificial intelligence to automatically generate media such as text, images, and audio.

[1361] "Emotion data" is information about emotions acquired from the user's facial expressions, tone of voice, and the like.

[1362] The "emotion engine" is a system that recognizes user emotional data and provides data useful for adjusting generation requirements and optimizing content.

[1363] "Content" means media consisting of text, images, audio, or a combination thereof created by a generative AI model.

[1364] "Feedback" refers to ratings and opinions provided by users regarding generated content.

[1365] "Personalized" refers to a state that is tailored based on the preferences and feelings of a particular user.

[1366] An "advertisement" is visual or audio content created to promote a product or service.

[1367] "Optimization" is the process of improving the quality of content and making it best suited for a purpose.

[1368] "Distribution" refers to providing the generated content to intended users over the Internet.

[1369] The present invention is a system that uses a generative AI model incorporating an emotion engine to provide personalized advertising content to users. This system is composed of hardware and software such as a user terminal, a server, a generative AI model, and an emotion engine. A specific embodiment of this system will be described.

[1370] This system works as follows: First, the user inputs the requirements for the advertising content they want to generate using a device such as a smartphone. The requirements include the ad's theme, length, format, etc. The emotion engine then obtains emotional data from the user's facial expressions and tone of voice and adjusts the requirements accordingly.

[1371] The device then transmits the acquired generation requirements and emotion data to the server, which analyzes the received data and selects and activates an appropriate generative AI model based on that data. These generative AI models include various models for text generation, image generation, and speech generation.

[1372] Generative AI models generate the necessary media, such as text, images, and audio, to create advertising content. For example, text generation AI creates a scenario, image generation AI generates related visuals, and audio generation AI generates narration. These generation processes take into account user emotional data.

[1373] The generated ad content is verified for quality on the server, with parameters such as sound quality, image quality, length, and overall structure being checked, and optimizations made as needed based on data from the emotion engine.

[1374] The optimized content is then sent back to the user's device from the server, where it can be viewed by the user. When the user enters feedback, the device sends it to the server, which analyzes the feedback and performs any necessary regeneration.

[1375] Finally, advertising content that users are satisfied with is published on social media, websites, etc. At this time, the content is delivered in the most appropriate way based on the data obtained from the emotion engine.

[1376] The specific hardware and software used includes the following:

[1377] Device: Internet-enabled smartphone

[1378] Server: High-performance cloud computing system

[1379] Generative AI models: Natural language processing models such as OpenAI's GPT-4, image generation models, and speech generation models

[1380] Emotion engine: An emotion recognition system such as Microsoft Azure Face API

[1381] As a concrete example, the following prompt sentence can be input to a generative AI model:

[1382] "Generate a 30-second video ad about a new product introduction. The user emotion is 'joy' and the tone of voice is high-pitched."

[1383] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1384] Step 1:

[1385] The user operates the device to input requirements for generating advertising content, and the emotion engine obtains emotional data from the user's facial expressions and tone of voice. The input data includes the advertisement's theme, length, format, and emotional data, which are then used for subsequent processing.

[1386] Step 2:

[1387] The device sends the input generation requirements and emotion data to the server. Specifically, the data is transferred to the server using an HTTP request. The input data becomes the material for analysis processing on the server.

[1388] Step 3:

[1389] The server receives the data and analyzes the generation requirements and sentiment data. During this process, the data is checked for consistency and parameters are extracted, such as the theme and format of the ad and the user's sentiment information, which are then stored in a database.

[1390] Step 4:

[1391] Based on the analysis results, the server selects and activates the optimal generative AI model. Selection criteria include the application of text generation AI, image generation AI, and voice generation AI appropriate for the theme. Furthermore, emotion data is used to fine-tune the generated content.

[1392] Step 5:

[1393] After the generative AI model is selected, it generates advertising content such as text, images, and audio. Specifically, the generative AI model receives a prompt as input and generates output based on it. For example, a prompt might be, "Generate a 30-second video ad for a new product introduction. The user's emotion is 'joy' and the voice tone is high-pitched."

[1394] Step 6:

[1395] The server receives the generated ad content and verifies its quality. Audio quality, picture quality, and overall composition are checked, and any defects are automatically corrected. This verification uses image and sound quality optimization algorithms.

[1396] Step 7:

[1397] The optimized content is sent from the server to the device. The user is allowed to view the content for final confirmation. The user reviews the ad content and provides feedback if necessary.

[1398] Step 8:

[1399] Users input feedback via their devices and send it to the server. The feedback includes requests for content changes and improvements. This data is used as a reference when the server regenerates the content.

[1400] Step 9:

[1401] The server analyzes the feedback and re-runs the generative AI model if regeneration is necessary, setting new parameters based on the feedback data and generating new ad content.

[1402] Step 10:

[1403] The final regenerated ad content is then resent to the user's device. This loop is repeated until the user is satisfied. The final certified ad content is then delivered to the social networking site or website.

[1404] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1405] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1406] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1407] [Fourth embodiment]

[1408] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1409] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1410] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1411] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1412] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1413] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1414] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1415] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1416] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1417] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1418] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1419] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1420] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1421] This invention relates to a system that automatically generates security awareness content using generative AI. The system is composed of a server, a terminal, a generative AI model, and other components.

[1422] System configuration

[1423] The system includes the following elements:

[1424] Terminal: Provides an interface for users to input production requirements, review, feedback, and finally deliver the generated content.

[1425] Server: A central computing system that receives and analyzes production requirements, selects appropriate generative AI models, and generates, validates, optimizes, and regenerates content.

[1426] Generative AI model: An artificial intelligence model for generating media such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[1427] Program processing explanation

[1428] 1. Enter your content requirements

[1429] Users input the requirements for the content they want to generate through their device, including the purpose, theme, length, and format of the video.

[1430] 2. Submit your requirements

[1431] The device sends the input requirements to the server, which analyzes the received requirements and determines the required generative AI model.

[1432] 3. Launching the Generative AI

[1433] The server selects and activates the appropriate generative AI model based on the analysis results. For example, when creating a short video to combat phishing scams, it activates a text generation AI, an image generation AI, and a voice generation AI.

[1434] 4. Content Generation

[1435] The generative AI model generates content based on user requirements, such as phishing scenarios, warning images, explanatory illustrations, and narration audio.

[1436] 5. Content validation and optimization

[1437] The server verifies the quality of the generated content, checking parameters such as audio quality, video quality, and length, and automatically correcting and optimizing as needed.

[1438] 6. Preparing content for distribution

[1439] The optimized content is sent from the server to the device for the user to review, and if the user is not satisfied, they can enter feedback.

[1440] 7. Feedback and Regeneration

[1441] Once the user submits their feedback, the server re-analyzes it and re-runs the generative AI model, repeating this process until content that satisfies the user is generated.

[1442] 8. Finalize and distribute content

[1443] After the user has final confirmation and is satisfied with the content, they can upload it to social media or their website, allowing the security awareness content to reach a wider audience.

[1444] Specific examples

[1445] Short video generation to combat phishing scams

[1446] 1. Enter your content requirements

[1447] The user uses a device to input the requirements for a "one-minute short video about phishing scams." Input items include "phishing scams," "one minute," and "video format."

[1448] 2. Submit your requirements

[1449] The terminal sends the input requirements to the server, which receives the request and starts requirement analysis.

[1450] 3. Launching the Generative AI

[1451] Based on the analysis results, the server selects and activates an appropriate AI model, such as text generation AI, image generation AI, or voice generation AI.

[1452] 4. Content Generation

[1453] The text generation AI generates phishing scam scenarios and points to watch out for, the image generation AI generates related warning images and explanatory illustrations, and the audio generation AI generates narration audio.These are then combined to create a one-minute short video.

[1454] 5. Content validation and optimization

[1455] The server verifies the quality of the video and optimizes the sound and image quality.

[1456] 6. Preparing content for distribution

[1457] The optimized video is sent from the server to the terminal and viewed by the user.

[1458] 7. Feedback and Regeneration

[1459] The user provides feedback as needed and the server regenerates it.

[1460] 8. Finalize and distribute content

[1461] After the user confirms it, they can upload the generated video to social media or their website.

[1462] As a result, the present invention can efficiently and effectively generate security awareness content, thereby raising the level of security knowledge of users and companies.

[1463] The processing flow will be explained below.

[1464] Step 1:

[1465] The user inputs the requirements for the content they want to generate using their device (e.g., a one-minute short video about phishing scams). Specifically, they input information such as the theme, format, length, and purpose into the device's input form.

[1466] Step 2:

[1467] The terminal transmits the input requirements to the server. Specifically, the terminal transmits the requirement data to the server using an HTTP request.

[1468] Step 3:

[1469] The server receives the input requirements and performs analysis. Specifically, it analyzes the received data and extracts each parameter (e.g., topic, format, length).

[1470] Step 4:

[1471] The server selects and activates the appropriate generative AI model based on the analysis results. Specifically, it selects the text generation AI, image generation AI, and voice generation AI necessary for generating short videos to combat phishing scams.

[1472] Step 5:

[1473] The generative AI model generates content such as text, images, and audio. Specifically, the text generation AI generates the scenario, the image generation AI generates the related images, and the audio generation AI generates the narration audio.

[1474] Step 6:

[1475] The server aggregates the generated content, specifically creating a video file using the generated text, images, and audio.

[1476] Step 7:

[1477] The server verifies the quality of the generated content and optimizes it if necessary, specifically by checking audio and video quality and applying automatic corrections and enhancements.

[1478] Step 8:

[1479] The server sends the optimized content to the device. Specifically, it generates a content URL so that the user can view it and notifies the device.

[1480] Step 9:

[1481] The user views the generated content through their device, specifically by accessing the provided URL and watching the video.

[1482] Step 10:

[1483] The user enters feedback and sends it to the server. Specifically, the user enters feedback in the evaluation form and presses the submit button.

[1484] Step 11:

[1485] The server receives the feedback and initiates the regeneration process if necessary, specifically by analyzing the regeneration points and relaunching the associated generative AI models.

[1486] Step 12:

[1487] The user then performs a final check and uploads the generated content to social media or their website. Specifically, they download the generated video file and post it to each platform.

[1488] Example 1

[1489] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1490] In today's world, security awareness education via the Internet is extremely important. However, manually creating security awareness content requires a significant amount of time and expertise, making it difficult to generate content efficiently. It is also difficult to consistently improve the quality of generated content or quickly improve it based on feedback. For this reason, there is a need for a system that uses generative AI to automatically generate, optimize, and distribute high-quality security awareness content.

[1491] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1492] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the analysis results, means for generating necessary media data using a generative AI model including a text generator, an image generator, and a voice generator to create content, means for verifying the quality of the generated content and automatically correcting or optimizing it as necessary, means for transmitting the optimized content to the user, means for regenerating the content based on user feedback, and means for preparing the generated content after final confirmation for distribution and distributing it to multiple platforms. This enables the automatic generation and rapid correction of high-quality security awareness content based on user requirements.

[1493] "User" means a person or organization that uses the system to generate, review, and distribute security awareness content.

[1494] "Server" is a central computer system that analyzes the generation requirements entered by the user, selects, launches, and executes the appropriate generative AI model, and validates, optimizes, and delivers the generated content.

[1495] The "creation requirements" are information including detailed requests such as the purpose, theme, length, and format of the content the user wants to create.

[1496] A "generative AI model" is an artificial intelligence model used to generate media data such as text, images, and audio, and specifically includes text generators, image generators, and audio generators.

[1497] A "text generator" is a device that generates necessary text data based on user requirements.

[1498] An "image generating device" is a device that generates the necessary image data based on the user's requirements.

[1499] A "voice generating device" is a device that generates necessary voice data based on the user's requirements.

[1500] "Media data" refers to all data that forms content, such as text, images, and audio.

[1501] "Content" refers to a collection of data, including text, images, audio, etc., generated and optimized by a generative AI model for security awareness purposes.

[1502] "Feedback" is information including users' evaluations of the generated content and requests for improvement.

[1503] "Auto-remediation" is the process by which the server verifies the quality of generated content and automatically makes corrections as needed.

[1504] "Optimization" is the process of improving the generated content according to quality and user requirements.

[1505] "Distribution" is the process of publishing the final, verified generated content to multiple platforms.

[1506] "Platform" refers to a website, social networking site, or other online service for distributing Generated Content.

[1507] The present invention relates to a system that automatically generates security awareness content by utilizing a generative AI model. The system is configured by combining a server, a terminal, a generative AI model, etc. The configuration and operation for specifically implementing the present invention are described below.

[1508] System configuration

[1509] The system includes the following elements:

[1510] Terminal: A device through which a user inputs content generation requirements, checks, provides feedback, and finally distributes the generated content.

[1511] Server: A central computing system that receives and analyzes the generation requirements from users, selects and launches appropriate generative AI models, and generates, validates, optimizes, and regenerates content.

[1512] Generative AI model: An artificial intelligence model for generating media data such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[1513] Program processing

[1514] 1. Enter your content requirements

[1515] Users input the requirements for the content they want to generate through their device. Input items include the purpose, theme, length, format, etc. of the video. For example, they input the requirements for a "one-minute short video about phishing scams."

[1516] 2. Submit your requirements

[1517] The device sends the input requirements to the server, which analyzes the received requirements and selects a generative AI model suitable for content generation.

[1518] 3. Launching the Generative AI

[1519] Based on the analysis results, the server selects and activates a generative AI model, including a text generator, an image generator, and a voice generator. For example, when creating a short video to combat phishing scams, these three devices work together.

[1520] 4. Content Generation

[1521] The generative AI model generates the necessary media data based on the user's requirements. For example, it uses a text generator to create a scenario, an image generator to generate warning images and explanatory illustrations, and a voice generator to generate narration. These are then integrated to create content in the form of a one-minute short video.

[1522] 5. Content validation and optimization

[1523] The server verifies the quality of the generated content, checking audio quality, image quality, length, and script consistency, and automatically corrects and optimizes it if necessary.

[1524] 6. Preparing content for distribution

[1525] The server sends the optimized content to the device for user confirmation, and the user can preview the generated content through the device and provide feedback as needed.

[1526] 7. Feedback and Regeneration

[1527] When the user submits feedback from their device, the server re-analyzes and re-runs the necessary generative AI models, repeating this process until the user is satisfied.

[1528] 8. Finalize and distribute content

[1529] If the user is satisfied with the content after final confirmation, they can issue a command to upload it to a social networking site or website from their device. The server then formats the content for distribution and distributes it to the specified platform.

[1530] Specific examples

[1531] For example, to generate a one-minute short anti-phishing video, use the following prompt:

[1532] "Create a short 1-minute video about phishing scams. Please include the following:

[1533] Phishing scam method explained

[1534] Examples of fraudulent emails and how to deal with them

[1535] Attention to viewers

[1536] As a result, the present invention can efficiently and effectively generate security awareness content, thereby improving the security knowledge of users and organizations.

[1537] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1538] Step 1:

[1539] The user inputs the generation requirements using a terminal.

[1540] Specifically, the user inputs the prompt for a "one-minute short video about phishing scams." The input data includes information such as "phishing scams," "one minute," and "video format." This input information is then saved on the device.

[1541] Step 2:

[1542] The terminal transmits the requirements input by the user to the server.

[1543] Specifically, the device sends input data in JSON format or other appropriate data format to the server. The sent data includes the purpose, theme, length, format, etc. The server receives this data and begins analyzing it. Input data: "Phishing scam," "1 minute," "Video format"

[1544] Output data: Parsed requirements

[1545] Step 3:

[1546] The server analyzes the received requirements and selects the optimal generative AI model.

[1547] The server determines which generative AI models (text generator, image generator, and voice generator) are needed based on the analyzed requirements. For example, a short video to combat phishing requires these three generative AI models. Input data: Analyzed requirements

[1548] Output data: Selected generative AI model

[1549] Step 4:

[1550] The server launches the selected generative AI model.

[1551] The server uses an interface such as a REST API to launch the generative AI model and begin the generation process. For example, it sends instructions such as "Generate a phishing scam scenario" to the text generator and "Convert the generated scenario into audio" to the voice generator. Input data: Selected generative AI model

[1552] Output data: Start command

[1553] Step 5:

[1554] A generative AI model generates content based on user requirements.

[1555] Specifically, the text generator creates a phishing scam scenario, the image generator generates related warning images and explanatory illustrations, and the audio generator generates a narration based on the generated scenario. These are then integrated to create a one-minute short video. Input data: Generation requirements

[1556] Output Data: Generated Content

[1557] Step 6:

[1558] Validate the quality of the server-generated content.

[1559] Specifically, it checks the sound quality, image quality, content length, and consistency of the scenario, and automatically corrects or optimizes it if necessary. For example, if there are any unclear parts of the audio, it issues instructions to the audio generator again. Input data: Generated content

[1560] Output: Optimized content

[1561] Step 7:

[1562] The server sends the optimized content to the device for the user to view.

[1563] Specifically, the server converts the generated content into the appropriate format and sends a preview link or file to the device. The user can preview the generated video using this link. Input data: Optimized content

[1564] Output data: Preview link or file

[1565] Step 8:

[1566] The user inputs feedback through the terminal and transmits it to the server.

[1567] Specifically, users input specific feedback such as "Please make the video a little shorter" or "Please make the illustrations easier to understand." The device then sends this feedback to the server. Input data: User feedback

[1568] Output data: Feedback data

[1569] Step 9:

[1570] The server analyzes the feedback and re-runs any necessary generative AI models.

[1571] For example, based on feedback such as "Please shorten the length of the video," the system issues instructions to the text generator and modifies the scenario. This process is repeated until the user is satisfied. Input data: Feedback data

[1572] Output Data: Regenerated content

[1573] Step 10:

[1574] If the user is satisfied with the generated content after making a final check, they can issue instructions from their device to upload it to a social networking site or their homepage.

[1575] The server formats the content for distribution and distributes it to the specified platform, ensuring that the security awareness content reaches a wide audience. Input data: Final confirmation and distribution instructions

[1576] Output data: Streamed content

[1577] (Application example 1)

[1578] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1579] Despite the growing importance of security on the Internet in recent years, it is difficult to effectively communicate security alerts to users in an easy-to-understand manner. In particular, there is a demand for a system that can automatically and quickly generate content to promote awareness of specific threats such as phishing scams, but current technology is unable to meet this demand. In addition, optimizing the quality of the generated content based on user feedback is also an important issue.

[1580] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1581] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the generation requirements, means for generating the necessary text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means for sending the optimized content to the user, means for regenerating the content based on user feedback, means for the user to make final confirmation, and means for distributing the generated content to a platform on the Internet. This makes it possible to quickly and effectively generate security awareness content and promote user understanding.

[1582] "User" is the entity that inputs requirements for the generation of security awareness content, reviews the generated content, and provides feedback as needed.

[1583] "Generation requirements" are information that indicates the detailed specifications and requests for the security awareness content that a user wants to generate.

[1584] "Server" means a central computing system that analyzes the generation requirements received from the User, selects and launches an appropriate generative AI model, validates and optimizes the generated content, and transmits it to the User.

[1585] A "generative AI model" is an artificial intelligence model that generates media such as text, images, and audio, and performs appropriate generation as needed.

[1586] "Text" refers to sentences or character information generated by a generative AI model.

[1587] "Image" means a visual graphic or illustration generated by a generative AI model.

[1588] "Audio" refers to auditory narration or audio data generated by a generative AI model.

[1589] "Content" means comprehensive security awareness information, including text, images, and audio, generated by a generative AI model.

[1590] "Quality verification" is the process of checking the quality of each element of generated content (text, images, audio) and making corrections or improvements as necessary.

[1591] "Optimization" is the process of automated adjustments and refinements based on quality validation results to improve the quality of the generated content.

[1592] "Feedback" refers to opinions and requests provided by users regarding generated content.

[1593] "Regeneration" is the process of regenerating content by running the generative AI model again based on user feedback.

[1594] "Means of Final Review" means the means by which a user reviews and approves the final version of the generated content.

[1595] "Distribution" is the process of publishing the finalized security awareness content on an internet platform to reach a wide audience.

[1596] The present invention is a system for automatically generating security awareness content, with the aim of providing effective education on security threats on the Internet in particular. The system automates the process of optimizing and distributing the content generated based on user input requirements.

[1597] System Components

[1598] 1. Terminal: A device that allows users to input production requirements, review the generated content, and provide feedback if necessary. Terminals include smartphones, personal computers, tablets, etc.

[1599] 2. Server: The server is a central computing system that analyzes the generation requirements received from users, selects and launches an appropriate generative AI model, validates and optimizes the generated content, and finally sends it to users.

[1600] 3. Generative AI models: These include text generation models, image generation models, and speech synthesis models. For example, natural language processing models (GPT-4) are used for text generation, generative adversarial networks (GANs) are used for image generation, and WaveNet is used for speech synthesis.

[1601] Program processing explanation

[1602] 1. Enter content generation requirements

[1603] The user uses a device to input the requirements for the security awareness content they want to generate. This can be a detailed request, such as "a five-minute video about phishing scams." The input requirements are sent from the device to the server.

[1604] 2. Requirements Analysis

[1605] The server analyzes the generation requirements received from the user and selects the appropriate generative AI model. For example, if the request is for a "5-minute video," a text generation model, an image generation model, and a speech synthesis model will be activated.

[1606] 3. Content Generation

[1607] The generative AI model runs on the server and generates text, images, and audio according to the user's requirements, including phishing scenarios, warning images, explanatory illustrations, and audio narration.

[1608] 4. Quality verification and optimization

[1609] The generated content is verified by the server for quality, checking parameters such as sound quality, image quality, and content length, and optimizing it if necessary.

[1610] 5. Feedback processing and regeneration

[1611] The optimized content is sent to the device for review by the user, who provides feedback, which the server analyzes and regenerates if necessary.

[1612] 6. Finalize and distribute content

[1613] Once the user has given a final review and is satisfied with the generated content, the content is distributed to a platform on the Internet.

[1614] Hardware and software used

[1615] Hardware: Smartphones, personal computers, servers

[1616] Software: Natural language processing model (GPT-4), image generation model (GANs), speech synthesis model (WaveNet)

[1617] Specific examples

[1618] Input prompt example

[1619] A user fills out a form in your app with:

[1620] Content Topic:Phishing

[1621] Content format: 5-minute short videos

[1622] Video length: 5 minutes

[1623] Target audience: general users

[1624] Part of the processing flow

[1625] The prompts entered by the user are sent to the server, which then activates the generative AI model to generate text, images, and audio. The generated content is then sent to the device after quality verification, where it is regenerated after user confirmation and feedback, and finally distributed to the platform after final confirmation.

[1626] This invention makes it possible to generate security awareness content quickly and effectively, and is expected to improve users' security awareness.

[1627] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1628] Step 1:

[1629] The user inputs the generation requirements using a terminal. Input items include the content theme, format, length, and target audience. This input data is sent from the terminal to the server. Input examples include "Content theme: phishing scams," "Content format: 5-minute short video," and "Target audience: general users."

[1630] Step 2:

[1631] The server receives and analyzes the generation requirements sent from the device. Specifically, it uses natural language processing (NLP) to analyze the user's requirements as text data and selects an appropriate generation AI model. For example, if the theme "phishing scam" is detected, it selects a generation AI model specialized in phishing scams.

[1632] Step 3:

[1633] The server selects and launches an appropriate generative AI model based on the analysis results. The selected generative AI models include a text generation model (GPT-4), an image generation model (DALL-E), and a speech synthesis model (WaveNet). For example, these models are launched sequentially according to the requirement of a "5-minute short video."

[1634] Step 4:

[1635] The generative AI model generates content based on user requirements. Specifically, the text generation model generates phishing scam scenarios, the image generation model generates warning images and explanatory illustrations, and the speech synthesis model generates narration. The data generated by each model is integrated to create a single content file.

[1636] Step 5:

[1637] The server verifies the quality of the generated content and optimizes it as necessary. Specifically, it automatically checks parameters such as sound quality, image quality, and length, and makes corrections as necessary. Based on the results of this verification, if the quality of the generated content does not meet certain standards, it will automatically make corrections.

[1638] Step 6:

[1639] The optimized content is sent from the server to the terminal. The user checks the generated content on the terminal and inputs feedback. For example, the user may provide feedback such as "I would like the sound quality of the narration to be improved."

[1640] Step 7:

[1641] User feedback is sent to the server, which analyzes it and, if necessary, re-launches the generative AI model to regenerate new content that reflects the feedback.

[1642] Step 8:

[1643] The server resends the content to the device for the user to check. If the user is satisfied with the content after checking it, the content is distributed to an internet platform. For example, a specific distribution method such as "upload to SNS" is selected.

[1644] Through the above processing steps, users can easily create high-quality security awareness content and deliver it to a wide audience.

[1645] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1646] This invention combines an emotion engine with a system that automatically generates security awareness content using generative AI. This system is composed of a server, a terminal, a generative AI model, an emotion engine, etc.

[1647] System configuration

[1648] The system includes the following elements:

[1649] Terminal: Provides an interface for users to input generation requirements, review the generated content, get feedback, obtain sentiment data, and finally deliver it.

[1650] Server: A central computing system that receives and analyzes generative requirements, and manages and operates the appropriate generative AI models and emotion engines.

[1651] Generative AI model: An artificial intelligence model for generating media such as text, images, or audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[1652] Emotion Engine: Recognizes user emotions and provides data to help adjust production requirements, optimize content, and regenerate it.

[1653] Program processing explanation

[1654] 1. Enter your content requirements

[1655] The user inputs the requirements for the content they want to generate through their device. Input items include the purpose, theme, length, and format of the video. The emotion engine reads the user's emotions from their facial expressions and voice and adjusts the generation requirements accordingly.

[1656] 2. Submit your requirements

[1657] The terminal transmits the input requirements and emotion data generated by the emotion engine to the server. Specifically, the terminal transmits the requirements data and emotion data to the server using an HTTP request.

[1658] 3. Receiving and analyzing requirements

[1659] The server receives the input requirements and performs analysis. The received data is analyzed to extract each parameter (e.g., theme, format, length). Emotion data is also analyzed at this time.

[1660] 4. Selecting and starting the generation AI

[1661] The server selects and activates the appropriate generative AI model based on the analysis results. For example, it selects the text generation AI, image generation AI, and voice generation AI needed to generate short videos to combat phishing scams.

[1662] 5. Content Generation

[1663] The generative AI model generates content such as text, images, and audio. For example, a text generation AI generates a scenario, an image generation AI generates related images, and an audio generation AI generates narration audio. Based on data from the emotion engine, content is generated that matches the user's preferences and mood.

[1664] 6. Content validation and optimization

[1665] The server verifies the quality of the generated content, checking parameters such as sound quality, image quality, and length, and automatically correcting or optimizing as necessary. By taking into account data from the emotion engine, the content is more suited to the user's emotions.

[1666] 7. Preparing content for distribution

[1667] The optimized content is sent from the server to the device for the user to review, and data obtained from the emotion engine also helps with the review.

[1668] 8. Feedback and Regeneration

[1669] The user enters feedback and sends it to the server. The server receives the feedback and emotion data, reanalyzes it, and reruns the generative AI model as needed to regenerate the data.

[1670] 9. Finalize and distribute content

[1671] If the user is satisfied with the content after final confirmation, they can upload it to social media or their website. Based on the data obtained by the emotion engine, the content can be delivered in the most appropriate way for the user.

[1672] Specific examples

[1673] Short video generation to combat phishing scams

[1674] 1. Enter your content requirements

[1675] The user inputs the requirements for a "one-minute short video about phishing scams" using a terminal. The emotion engine reads emotional data from the user's facial expressions and voice and adjusts the requirements accordingly.

[1676] 2. Submit your requirements

[1677] The terminal transmits the input requirements and emotion data to the server.

[1678] 3. Receiving and analyzing requirements

[1679] The server analyzes the requirements, selects the appropriate generative AI model and emotion engine, and performs the analysis.

[1680] 4. Selecting and starting the generation AI

[1681] The server selects and activates text generation AI, image generation AI, and voice generation AI.

[1682] 5. Content Generation

[1683] The text generation AI generates phishing scam scenarios and points to watch out for, the image generation AI generates related warning images and explanatory illustrations, and the voice generation AI generates narration. Based on data from the emotion engine, content tailored to the user's preferences is generated.

[1684] 6. Content validation and optimization

[1685] The server verifies the quality of the video and optimizes the audio and video quality, taking into account the data from the emotion engine.

[1686] 7. Preparing content for distribution

[1687] The optimized video is sent from the server to the terminal and viewed by the user.

[1688] 8. Feedback and Regeneration

[1689] The user enters feedback and sends it to the server, which then reanalyzes it and reruns the generative AI model to regenerate it.

[1690] 9. Finalize and distribute content

[1691] The user then finalizes the video and uploads it to social media or their website. Based on the data from the emotion engine, the video is distributed in the most appropriate way for the user.

[1692] As a result, the present invention can efficiently and effectively generate security awareness content and raise the level of security knowledge of users and companies. Furthermore, by combining it with an emotion engine, it is possible to provide content that is suited to the user's emotions.

[1693] The processing flow will be explained below.

[1694] Step 1:

[1695] The user inputs the requirements for the content they wish to generate using their device. Specifically, they enter information such as "phishing scam," "1 minute," and "video format" into the device's input form. At this time, the emotion engine analyzes the user's facial expressions and voice in real time to collect emotional data.

[1696] Step 2:

[1697] The terminal transmits the input requirements and emotion data to the server. Specifically, an HTTP request including the requirement information and emotion data is transmitted to the server.

[1698] Step 3:

[1699] The server receives the requirements and emotional data and performs analysis, extracting parameters (e.g., topic, format, length) from the received data, and also analyzes the emotional data to determine the user's current emotional state.

[1700] Step 4:

[1701] The server selects and activates the appropriate generative AI model based on the analysis results, selecting the necessary text generation AI, image generation AI, and voice generation AI, and customizing the generation process based on emotion data.

[1702] Step 5:

[1703] The generative AI model generates content such as text, images, and audio. Specifically, the text generation AI creates a phishing scam scenario, the image generation AI generates related images, and the audio generation AI generates narration audio. Emotional data is used to generate content with a tone and style that matches the user's emotions.

[1704] Step 6:

[1705] The server aggregates the generated content, specifically creating a one-minute short video using the generated text, images, and audio.

[1706] Step 7:

[1707] The server verifies the quality of the generated content and optimizes it. Specifically, it checks the audio and video quality, removes or modifies unnecessary elements, and takes into account emotional data to optimize the content in a way that is likely to be favorable to users.

[1708] Step 8:

[1709] The server sends the optimized content to the device, specifically by generating and notifying the user of the content URL so that the user can view it.

[1710] Step 9:

[1711] The user checks the generated content through their device. Specifically, they access the provided URL and watch the video, and the emotion engine collects the user's reactions again.

[1712] Step 10:

[1713] The user inputs feedback about the content and sends it to the server. Specifically, the user fills out the feedback in the evaluation form and presses the submit button.

[1714] Step 11:

[1715] The server receives the feedback and emotion data and re-analyzes it, identifying points that need to be regenerated based on the emotion data.

[1716] Step 12:

[1717] The server then initiates the regeneration process, reactivating the selected generative AI model to generate new content based on the feedback and emotion data.

[1718] Step 13:

[1719] The user performs a final check on the device and then uploads the generated content to social media or a website. Specifically, the user downloads the generated video file and completes the distribution procedure. It is also possible to adjust the timing and method of distribution based on data obtained from the emotion engine.

[1720] Example 2

[1721] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1722] In order to effectively generate and distribute security awareness content on the Internet, a wide range of processes are required, including adjusting generation requirements, content generation, quality verification, optimization, and feedback re-implementation. However, existing systems do not adequately integrate these processes, making it difficult to automatically generate and provide optimal content that responds to user emotions.

[1723] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1724] In this invention, the server includes means for a user to input generation requirements, means for a terminal to acquire emotion data and adjust the requirements, means for the server to receive and analyze the input requirements and emotion data, means for selecting and activating a generative AI model based on the analysis results, means for generating the necessary text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means for sending the optimized content to the user, means for regenerating the content based on user feedback, and means for delivering the generated content. This makes it possible to automatically generate and efficiently provide high-quality security awareness content that is suited to the user's emotions.

[1725] "User" is a person or organization that uses the system to generate security awareness content, provide input, and provide feedback.

[1726] A "terminal" is a device used by a user that provides an interface for inputting generation requirements, obtaining emotion data, reviewing generated content, and providing feedback.

[1727] "Emotion data" is data that is used to read emotions from the user's facial expressions and voice and to adjust generation requirements and optimize generated content.

[1728] The "server" is a central computing system that receives and analyzes generation requirements and emotion data, selects and launches a generative AI model, verifies and optimizes the quality of the generated content, and finally provides the content to users.

[1729] "Generation requirements" are requirement information such as purpose, theme, length, and format that a user specifies about the content that he or she wants to generate.

[1730] "Analysis" is the process in which the server analyzes the generation requirements and emotion data received and extracts each parameter.

[1731] A "generative AI model" is an artificial intelligence model for generating required media such as text, images, and audio, and includes text generation AI, image generation AI, and audio generation AI.

[1732] "Text generation AI" is an artificial intelligence model that writes appropriate scenarios and explanatory text based on the generation requirements specified by the user.

[1733] "Image generation AI" is an artificial intelligence model that generates relevant images and illustrations based on user-specified generation requirements.

[1734] "Voice generation AI" is an artificial intelligence model that generates narration and voice based on the generation requirements specified by the user.

[1735] "Content" refers to media for security awareness that combines text, images, audio, etc. generated by a generative AI model.

[1736] "Quality verification" is the process by which the server checks the quality of the generated content, such as sound quality, image quality, and length, and automatically corrects or optimizes it as necessary.

[1737] "Optimization" is the process of making necessary adjustments and modifications to improve the quality of the generated content.

[1738] "Feedback" refers to opinions and requests that users provide regarding the generated content, which are reanalyzed by the server and used for regeneration.

[1739] "Distribution" is the process of providing optimized content to users and other platforms.

[1740] This invention combines an emotion engine with a system that uses generative AI to automatically generate security awareness content. This system is configured so that users can input generation requirements, and the emotion engine adjusts those requirements to generate and distribute high-quality content.

[1741] System configuration

[1742] The system includes the following elements:

[1743] Terminal: Provides an interface for users to input generation requirements, review the generated content, receive feedback, obtain emotional data, and finally distribute it. Examples include PCs and smartphones.

[1744] Server: A central computing system that receives and analyzes generative requirements, and manages and operates the appropriate generative AI models and emotion engines.

[1745] Generative AI model: An artificial intelligence model for generating media such as text, images, and audio. Examples include natural language processing (NLP) models, image generation models (such as GANs), and speech synthesis models (such as TTS).

[1746] Emotion Engine: Recognizes user emotions and provides data to help adjust production requirements, optimize content, and regenerate it.

[1747] Program processing explanation

[1748] Entering content requirements

[1749] Users input the requirements for the content they want to generate through their device. These include the purpose, theme, length, and format of the video. The device then uses an emotion engine to read emotions from the user's facial expressions and voice and adjusts the generation requirements accordingly. For example, if a user wants to create a "one-minute short video about phishing scams," they can input these requirements into their device.

[1750] Submitting requirements

[1751] When the user completes the input and presses the send button, the device uses an HTTP request to send the input requirements and emotion data generated by the emotion engine to the server.

[1752] Receiving and parsing requirements

[1753] The server receives the HTTP request and stores it in a database. The analysis engine then analyzes the data and extracts parameters (e.g., theme, format, length). Sentiment data is also analyzed at this time, and adjustments are made according to requirements.

[1754] Selecting and launching the generation AI

[1755] The server selects the appropriate generative AI model based on the analysis results. For example, GPT-3 is used for text generation, GAN for image generation, and WaveNet for speech generation. It launches each AI model and sends the necessary input data via an API.

[1756] Content generation

[1757] Each generative AI model generates content based on the data it receives. The text generation AI generates a scenario, and the image generation AI generates related images based on that text. The voice generation AI uses the generated scenario and images to generate narration. The emotion engine evaluates the generated content and makes adjustments based on the user's mood and preferences.

[1758] Content validation and optimization

[1759] The server validates the generated content, checking the quality of each output (e.g., sound quality, image quality, text integrity) and automatically correcting or optimizing it. For example, if the voice is not clear, it adjusts the parameters of the voice generation AI and regenerates it.

[1760] Preparing content for distribution

[1761] The optimized content is sent from the server to the device, where the user can check the generated content on the device and also see the feedback provided by the emotion engine.

[1762] Feedback and Regeneration

[1763] The user inputs feedback on the generated content, which is sent via the device to the server, which then re-analyzes it and re-runs each generative AI model to regenerate the content.

[1764] Finalize and distribute content

[1765] If the user is satisfied with the generated content after final confirmation, they can upload it to social media or their website. The server can also suggest the optimal distribution method based on the data from the emotion engine.

[1766] Specific examples

[1767] A user types into their device, "I want to create a one-minute short video about phishing scams." The device uses an emotion engine to collect emotional data from the user's facial expressions and voice, and adjusts the requirements based on this data. The device then sends the requirements and emotional data to the server, which receives and analyzes them. After analyzing, the server selects an appropriate generative AI model (e.g., GPT-3 for text generation, GAN for image generation, WaveNet for voice generation) and activates each AI model to generate content. The generated content is then quality-verified and optimized on the server, and the optimized content is sent to the device. The user reviews the content and provides feedback, and the server reanalyzes and regenerates it. Finally, once the user is satisfied, the content is distributed to social media and the website.

[1768] This system makes it possible to efficiently and automatically generate and effectively deliver high-quality security awareness content that is tailored to the user's emotions.

[1769] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1770] System program processing flow

[1771] Step 1:

[1772] The user inputs the content generation requirements using the terminal.

[1773] Input data: purpose of the video, subject, length, format, etc.

[1774] Specific operation: The user inputs into the device's input screen that they would like to create a "one-minute short video about phishing scams." The device uses an emotion engine to collect emotional data from the user's facial expressions and voice. This emotional data is used to adjust the requirements for content generation.

[1775] Step 2:

[1776] The terminal transmits the input requirements and emotion data to the server.

[1777] Input data: User-generated requirements and sentiment data.

[1778] Specific operation: The device sends the generation requirements and emotion data to the server in the form of an HTTP request. The data is packaged in JSON format.

[1779] Step 3:

[1780] The server receives the input requirements and emotion data and analyzes them.

[1781] Input data: Generation requirements and emotion data sent from the device.

[1782] How it works: The server receives an HTTP request and stores the information in a database. The analysis engine then analyzes the generation requirements and sentiment data to extract parameters (e.g., theme, format, length). The sentiment data is also analyzed, and the generation requirements are adjusted as needed.

[1783] Step 4:

[1784] The server selects and launches an appropriate generative AI model based on the analysis results.

[1785] Input data: Parsed generative requirements and sentiment data.

[1786] Specific operation: Based on the analysis results, the server selects and launches an appropriate generative AI model, such as a GPT-3 model for text generation, a GAN model for image generation, or a WaveNet model for voice generation. The necessary input data for each AI model is sent via API.

[1787] Step 5:

[1788] Generative AI models generate content such as text, images, and audio.

[1789] Input data: Input data for each generative AI model (e.g., scenario text, related images, narration script).

[1790] How it works: The text generation AI model generates a scenario, the image generation AI model generates related images, and then the voice generation AI model generates a narration voice. Reflecting data from the emotion engine, content is generated that matches the user's preferences and mood.

[1791] Step 6:

[1792] The server verifies the quality of the generated content and makes optimizations if necessary.

[1793] Input data: Text, images, and audio output by the generative AI model.

[1794] Specific operation: The server verifies the sound quality, image quality, length, etc. of the generated content, and automatically corrects any defects found. For example, if the audio is not clear, the parameters of the audio generation AI are adjusted and the content is generated again.

[1795] Step 7:

[1796] The optimized content is sent from the server to the terminal.

[1797] Input data: optimized text, images, and audio.

[1798] Specific operation: The server sends the optimized content to the device in the form of an HTTP response. The user checks the content on the device and also checks the feedback provided by the emotion engine.

[1799] Step 8:

[1800] The user inputs feedback on the generated content and transmits it to the server via the terminal.

[1801] Input data: User feedback and sentiment data.

[1802] Specific operation: The user enters their opinion or request into the feedback screen on the device and presses the send button. The device then sends the feedback and emotion data to the server.

[1803] Step 9:

[1804] The server re-analyzes the feedback and emotion data and re-runs the generative AI model to re-generate the content.

[1805] Input data: User feedback and sentiment data.

[1806] Specific operation: The server reanalyzes the received feedback and emotion data, reruns each generative AI model, and generates new content including modifications based on the user's requests.

[1807] Step 10:

[1808] The user then makes a final check and uploads the generated content to social media or their website.

[1809] Input data: Final verified content.

[1810] Specific operation: The user checks the content generated on the device and uploads it to social media or a website when satisfied. The server can also suggest the optimal distribution method based on the emotion engine data.

[1811] The above processing steps allow users to efficiently generate and distribute high-quality, emotionally appropriate security awareness content.

[1812] (Application example 2)

[1813] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1814] Conventional ad generation systems struggled to generate personalized content based on user emotions and preferences, and could only provide generic ads. Furthermore, they lacked the ability to regenerate the quality and effectiveness of generated content based on user feedback, making it difficult to maximize advertising effectiveness. This limited the effectiveness of advertising and prevented improvements in user engagement.

[1815] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1816] In this invention, the server includes means for a user to input generation requirements, means for the server to receive and analyze the input requirements, means for selecting and activating a generative AI model based on the generation requirements, means for generating the required text, images, and audio using the generative AI model to create content, means for verifying the quality of the generated content and optimizing it as necessary, means including an emotion engine that acquires user emotion data and adjusts the generation requirements, means for sending the optimized content to the user, means for regenerating content based on user feedback, and means for delivering the generated content. This enables personalized content generation based on emotions and content regeneration based on user feedback.

[1817] A "user" is a person who uses a service or system and makes requests or feedback.

[1818] "Generation requirements" are specific conditions and requirements regarding the content that a user wants to generate.

[1819] A "means" is a method or device by which a system performs a specific function or process.

[1820] A "server" is a computer system that receives input data, analyzes it, and takes appropriate action.

[1821] A "generative AI model" is a model that uses artificial intelligence to automatically generate media such as text, images, and audio.

[1822] "Emotion data" is information about emotions acquired from the user's facial expressions, tone of voice, and the like.

[1823] The "emotion engine" is a system that recognizes user emotional data and provides data useful for adjusting generation requirements and optimizing content.

[1824] "Content" means media consisting of text, images, audio, or a combination thereof created by a generative AI model.

[1825] "Feedback" refers to ratings and opinions provided by users regarding generated content.

[1826] "Personalized" refers to a state that is tailored based on the preferences and feelings of a particular user.

[1827] An "advertisement" is visual or audio content created to promote a product or service.

[1828] "Optimization" is the process of improving the quality of content and making it best suited for a purpose.

[1829] "Distribution" refers to providing the generated content to intended users over the Internet.

[1830] The present invention is a system that uses a generative AI model incorporating an emotion engine to provide personalized advertising content to users. This system is composed of hardware and software such as a user terminal, a server, a generative AI model, and an emotion engine. A specific embodiment of this system will be described.

[1831] This system works as follows: First, the user inputs the requirements for the advertising content they want to generate using a device such as a smartphone. The requirements include the ad's theme, length, format, etc. The emotion engine then obtains emotional data from the user's facial expressions and tone of voice and adjusts the requirements accordingly.

[1832] The device then transmits the acquired generation requirements and emotion data to the server, which analyzes the received data and selects and activates an appropriate generative AI model based on that data. These generative AI models include various models for text generation, image generation, and speech generation.

[1833] Generative AI models generate the necessary media, such as text, images, and audio, to create advertising content. For example, text generation AI creates a scenario, image generation AI generates related visuals, and audio generation AI generates narration. These generation processes take into account user emotional data.

[1834] The generated ad content is verified for quality on the server, with parameters such as sound quality, image quality, length, and overall structure being checked, and optimizations made as needed based on data from the emotion engine.

[1835] The optimized content is then sent back to the user's device from the server, where it can be viewed by the user. When the user enters feedback, the device sends it to the server, which analyzes the feedback and performs any necessary regeneration.

[1836] Finally, advertising content that users are satisfied with is published on social media, websites, etc. At this time, the content is delivered in the most appropriate way based on the data obtained from the emotion engine.

[1837] The specific hardware and software used includes the following:

[1838] Device: Internet-enabled smartphone

[1839] Server: High-performance cloud computing system

[1840] Generative AI models: Natural language processing models such as OpenAI's GPT-4, image generation models, and speech generation models

[1841] Emotion engine: An emotion recognition system such as Microsoft Azure Face API

[1842] As a concrete example, the following prompt sentence can be input to a generative AI model:

[1843] "Generate a 30-second video ad about a new product introduction. The user emotion is 'joy' and the tone of voice is high-pitched."

[1844] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1845] Step 1:

[1846] The user operates the device to input requirements for generating advertising content, and the emotion engine obtains emotional data from the user's facial expressions and tone of voice. The input data includes the advertisement's theme, length, format, and emotional data, which are then used for subsequent processing.

[1847] Step 2:

[1848] The device sends the input generation requirements and emotion data to the server. Specifically, the data is transferred to the server using an HTTP request. The input data becomes the material for analysis processing on the server.

[1849] Step 3:

[1850] The server receives the data and analyzes the generation requirements and sentiment data. During this process, the data is checked for consistency and parameters are extracted, such as the theme and format of the ad and the user's sentiment information, which are then stored in a database.

[1851] Step 4:

[1852] Based on the analysis results, the server selects and activates the optimal generative AI model. Selection criteria include the application of text generation AI, image generation AI, and voice generation AI appropriate for the theme. Furthermore, emotion data is used to fine-tune the generated content.

[1853] Step 5:

[1854] After the generative AI model is selected, it generates advertising content such as text, images, and audio. Specifically, the generative AI model receives a prompt as input and generates output based on it. For example, a prompt might be, "Generate a 30-second video ad for a new product introduction. The user's emotion is 'joy' and the voice tone is high-pitched."

[1855] Step 6:

[1856] The server receives the generated ad content and verifies its quality. Audio quality, picture quality, and overall composition are checked, and any defects are automatically corrected. This verification uses image and sound quality optimization algorithms.

[1857] Step 7:

[1858] The optimized content is sent from the server to the device. The user is allowed to view the content for final confirmation. The user reviews the ad content and provides feedback if necessary.

[1859] Step 8:

[1860] Users input feedback via their devices and send it to the server. The feedback includes requests for content changes and improvements. This data is used as a reference when the server regenerates the content.

[1861] Step 9:

[1862] The server analyzes the feedback and re-runs the generative AI model if regeneration is necessary, setting new parameters based on the feedback data and generating new ad content.

[1863] Step 10:

[1864] The final regenerated ad content is then resent to the user's device. This loop is repeated until the user is satisfied. The final certified ad content is then delivered to the social networking site or website.

[1865] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1866] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1867] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1868] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1869] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1870] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1871] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1872] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1873] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1874] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1875] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1876] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1877] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1878] 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.

[1879] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1880] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1881] The hardware ...

Claims

1. A system for automatically generating security awareness content on the Internet, comprising: a means for a user to input generation requirements; means for the server to receive and analyze the input requirements; A means for selecting and launching a generative AI model based on the generative requirements; A means to generate the necessary text, images, and audio using a generative AI model to create content; A means to verify the quality of the generated content and optimize it if necessary; means for transmitting the optimized content to the user; means for regeneration based on user feedback; A means of delivering generated content A system including:

2. The system according to claim 1 , wherein the security awareness content is generated as content relating to phishing scams.

3. 2. The system according to claim 1, wherein the generated content is in the form of a short video of about one minute.

Images