system

Abstract

Provide a system. A user interface means for accepting input of text or images; a transmitting means for transmitting the input text or image to a server; A generating means for generating a new image or video based on the input in the server; a transmitting means for transmitting the generated image or video to a user; a display means for displaying the transmitted image or video on a user interface; A system including:

Description

[Technical Field]

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

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

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

[0004] In today's advertising market, there is a demand for the rapid and efficient generation of high-quality advertising images and videos. However, conventional methods require designers and creators to create advertising materials manually, which is time-consuming and costly. Furthermore, it is difficult for users without special skills to easily generate advertising images and videos. Thus, there is a demand for the development of a system that can efficiently generate user-friendly, high-quality advertising materials. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. First, a user interface means is provided for accepting input of text or images. This interface is an input means for the user to easily create advertising materials and can be operated intuitively. Next, a transmission means is provided for transmitting the input text or images to a server. This allows the user's input content to be transmitted to the server.

[0006] The server is provided with a generation means for generating new images or videos based on user input. This generation means can quickly generate high-quality advertising materials by utilizing a pre-trained generative model. Furthermore, by providing a storage means for temporarily storing the generated images or videos, backups and future reuse are possible.

[0007] The generated image or video is sent to the user by the transmission means and displayed on the user interface by the display means. This allows the user to check the generated results and download or re-edit them as needed. In addition, the use of the HTTP protocol provides a stable communication environment. These means provide a user-friendly and efficient advertising material generation system.

[0008] "User interface means" refers to an interactive interface for a user to input text and images.

[0009] "Transmission means" is a communication means for transmitting input text or images to a server.

[0010] The "generation means" is a processing device or software for generating new images or videos based on text or images input to the server.

[0011] The "transmission means for transmitting the transmitted image or video to the user" is a communication means for transmitting the generated image or video to the user terminal.

[0012] "Display means" refers to a device or software for displaying the transmitted image or video on a user interface.

[0013] A "generative model" is a pre-trained neural network or other machine learning model used to generate new images or videos.

[0014] "Storage means" refers to a storage device or software for temporarily storing the generated images or videos.

[0015] "Advertising images" are images used for advertising purposes, such as to promote products or services.

[0016] "HTTP protocol" is an abbreviation for Hypertext Transfer Protocol, and is a protocol for communicating data between a web server and a client. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention provides a system that allows a user to input text and images, generates new advertising images and videos on a server based on the input text and images, and displays the images and videos on a user interface. The system includes a user interface means, a transmission means, a generation means, a storage means, and a display means.

[0039] User Interface Means

[0040] When a user accesses the system, they are first presented with a user interface that includes a text entry field and an image upload button. The user enters or uploads the text and images they want to use in their advertisement.

[0041] Transmission method

[0042] When the user completes the text and image input and clicks the "Generate" button, the input data is sent from the device to the server using an HTTP POST request. The sent data is in JSON format and contains information about the text and image.

[0043] generation means

[0044] The server analyzes the received request and generates new advertising images and videos based on the input data. Specifically, the server uses a pre-trained generative model to generate advertising materials that are optimal for the text and images provided by the user. This generative model is based on machine learning algorithms such as neural networks, and can generate high-quality images and videos in a short amount of time.

[0045] Preservation means

[0046] The generated images and videos are temporarily stored in the server's storage. The stored data is managed with consideration for future reuse and backup. This storage method allows users to re-acquire the advertising materials they have generated at a later date.

[0047] Display means

[0048] The generated advertising images and videos are sent back to the device and displayed on the user interface. The user can check the displayed results and download and use them as needed. If the results are not as expected, the user can modify the text or images and send a new request.

[0049] Specific examples

[0050] For example, suppose a user wants to generate advertising materials for a "summer sale." The user accesses the Web UI, enters the text "summer sale," and uploads an image of a beach. After that, the user clicks the "Generate" button, and the input information is sent to the server. The server generates advertising images and videos showing the summer sale based on the received text and images. The generated materials are temporarily saved, sent to the device, and displayed on the Web UI. The user can check the generated results and download them if they are satisfactory.

[0051] In this way, the system is designed to enable users to easily generate high-quality images and videos for advertising. The means described in this claim enable efficient creation of advertising materials while reducing time and costs.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] Users access the Web UI and enter text and images. For example, a user can enter the text "Summer Sale" and upload an image of the product in question.

[0055] Step 2:

[0056] The user clicks the "Generate" button on the Web UI, which converts the entered text and uploaded images into JSON format.

[0057] Step 3:

[0058] The terminal sends the data converted into JSON format to the server as an HTTP POST request. The sent data includes the text and image information entered by the user.

[0059] Step 4:

[0060] The server receives the HTTP POST request, parses its contents, extracts text and image information from the request, and prepares it for passing to the generative model.

[0061] Step 5:

[0062] The server then invokes pre-trained generative models to generate images and videos for advertisements based on user input, for example using a neural network to generate images related to "summer sales."

[0063] Step 6:

[0064] The generated images and videos are temporarily stored on the server, and the path and file name of the storage destination are uniquely determined and used in the next processing step.

[0065] Step 7:

[0066] The server sends the stored images and videos to the device as an HTTP response. At this time, the sent data is treated as binary image or video data.

[0067] Step 8:

[0068] The device analyzes the HTTP response received from the server, generates images and videos from the binary data, and converts the generated data into a format that can be displayed on the user interface.

[0069] Step 9:

[0070] The generated images and videos for advertising are displayed on the user's device in a web UI, where the user can check the results and download or edit them as needed.

[0071] Step 10:

[0072] If the user is not satisfied with the results, they can modify the text or images again and send a new request to the server. This process can be repeated.

[0073] In this way, users, terminals, and servers work together to efficiently generate high-quality advertising images and videos.

[0074] Example 1

[0075] 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."

[0076] Conventional advertising material generation systems lack the means for users to quickly and easily generate high-quality images and videos for advertising. They also lack mechanisms for efficiently storing, managing, and reusing the generated advertising materials. This results in high costs and time-consuming processes.

[0077] 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.

[0078] In this invention, the server includes a display device that accepts input of text or images, a transmission device that transmits the input text or images to a processing device, a generation device that generates new audiovisual data based on the input in the processing device, a transmission device that transmits the generated audiovisual data to a user, and a display device that displays the transmitted audiovisual data on a display device. This allows users to quickly and easily generate high-quality advertising images and videos. Furthermore, by including a storage device for temporary storage, data management and reuse after generation can be efficiently performed.

[0079] A "display device" is a device that provides an interface for a user to input text and images.

[0080] A "transmitting device" is a device that has the function of transmitting input text and images to a processing device.

[0081] A "processing device" is a device that generates new audiovisual data based on input data sent by a user.

[0082] A "generator" is a device that generates new audiovisual data using a pre-trained generative algorithm.

[0083] A "storage device" is a device for temporarily storing generated audiovisual data.

[0084] "Audiovisual data" refers to digital content such as images and videos generated for advertising purposes.

[0085] A "generative algorithm" is a machine learning model or other computational method used to generate audiovisual data based on input data.

[0086] MODE FOR CARRYING OUT THE INVENTION

[0087] The present invention provides a system in which a user inputs text and images, generates new advertising images and videos on a server based on the input text and images, and displays the images and videos on a user interface. The system includes a display device, a transmission device, a generation device, a storage device, and a display device.

[0088] When a user accesses the system using a web browser, the server renders and sends to the terminal a display image that includes a text entry field and an image upload button where the user can enter promotional text, such as "Summer Sale," and upload an image to be used in the advertising materials.

[0089] Next, when the user clicks the "Generate" button, the entered text and uploaded image are packaged in JSON format and sent to the server via an HTTP POST request. This sender provides a means for passing input data to the server.

[0090] The server parses the received JSON data and activates a generator, which includes a pre-trained generative AI model (e.g., a Generative Adversarial Network (GAN)) that generates new advertising images and videos based on user input. The generative AI model is based on machine learning algorithms and can generate content quickly and with high quality.

[0091] The generated data is temporarily stored in a storage device, which is used to store the generated data and facilitate future reuse and data management.

[0092] Finally, the server reloads the generated data and sends it to the display device. The display device on the terminal receives it and displays it on the user interface. The user can check the generated audiovisual data and download it if they are satisfied. If the result is not as expected, they can modify the text and images and send a new request.

[0093] Specific examples

[0094] For example, suppose a user wants to generate advertising materials for a "Summer Sale." The user accesses the Web UI, enters the text "Summer Sale," and uploads an image of a beach. After that, the user clicks the "Generate" button, and the input is sent to the server. Based on the received text and image, the server uses a generative AI model to generate advertising images and videos showing the summer sale. This generated material is temporarily stored and eventually sent to a display device and displayed on the Web UI. The user checks the generated results and downloads them if they are satisfactory. Below is an example of a prompt:

[0095] prompt:

[0096] I want to generate an image for an advertisement. The text is "Summer Sale" and the image I want to upload is a beach photo.

[0097] In this way, this system is designed to enable users to easily generate high-quality images and videos for advertising, thereby enabling efficient creation of advertising materials while reducing time and costs.

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1:

[0100] User Interface Display

[0101] When a user accesses the system from a web browser, the server renders a user interface and sends it to the terminal. This user interface includes text input fields and image upload buttons, and the user inputs and uploads the text and images they want to use in the advertising materials.

[0102] Input: Access request from a web browser

[0103] Output: User interface

[0104] Step 2:

[0105] Sending input data

[0106] When the user completes the text and image input and clicks the "Generate" button, the data is packaged in JSON format and sent to the server via an HTTP POST request. The sent data includes the text data entered by the user and the image data uploaded.

[0107] Input: User-entered text and images, HTTP POST requests

[0108] Output: JSON data sent to the server side

[0109] Step 3:

[0110] Data analysis

[0111] The server parses the received JSON data, where the data stream is parsed and each field (text content, image information, etc.) is identified.

[0112] Input: JSON format text data and image data

[0113] Output: Analyzed text and image data objects

[0114] Step 4:

[0115] Creation of advertising materials

[0116] The server uses a generator to generate audiovisual data for advertising based on the text and images obtained from the analysis. The generator uses a pre-trained generative AI model to generate appropriate images and videos based on the user's input data. For example, if a user enters "summer sale" and uploads an image of a beach, the generative AI model will generate advertising materials that fit that theme.

[0117] Input: Analyzed text and image data, generative AI model

[0118] Output: Generated audiovisual data

[0119] Step 5:

[0120] Saving generated data

[0121] The server temporarily stores the generated audiovisual data in a storage device, which stores the generated data along with the date and time of generation, the user ID, and metadata of the text and images used for input.

[0122] Input: Generated audiovisual data

[0123] Output: Data stored on the storage device

[0124] Step 6:

[0125] Viewing generated data

[0126] The server reloads the saved generated data and sends it to the user interface. The display device on the terminal receives this data and displays it on the user interface. The user can check the displayed advertising images and videos and download them if necessary.

[0127] Input: Data stored on storage device, user request

[0128] Output: Audiovisual data displayed on a display device

[0129] (Application example 1)

[0130] 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."

[0131] The modern advertising industry demands the efficient and rapid generation of high-quality advertising materials. However, achieving this requires specialized skills and expensive software, which is time-consuming and costly. Furthermore, generating advertising materials requires a system that allows users to easily upload text and images and then generate, save, display, and download optimal advertising materials based on those text and images. However, current systems have difficulty meeting all of these requirements. Furthermore, a function that allows users to easily download the generated advertising materials is also required. The objective of this invention is to solve these problems.

[0132] 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.

[0133] In this invention, the server includes a user interface means for accepting input of text or images, a transmission means for transmitting the input text or images to the server, a generation means for generating new images or videos based on the input at the server, a storage means for saving the generated images or videos, a display means for displaying the transmitted images or videos on the user interface, and a download means for the user to download the generated images or videos. This enables users to easily input and upload text and images they want to use in their advertisements, and then quickly generate, save, display, and download high-quality advertising materials based on them.

[0134] "User interface means" refers to an interface through which a user inputs text and images into the system.

[0135] The "transmission means" is a means having a function for transmitting text and images input by the user to the server.

[0136] The "generation means" is a means having a function of generating a new image or video based on an input in the server.

[0137] The "storage means" is a means having a function of temporarily storing the generated image or video.

[0138] The "display means" is a means having a function of displaying the generated image or video on the user's interface.

[0139] The "downloading means" is a means that has a function for a user to download generated images or videos.

[0140] A "generative AI model" is a machine learning model that is pre-trained to generate new advertising images and videos based on text and images.

[0141] A "prompt" is an instruction given to a generative AI model in the form of text input.

[0142] The present invention provides a system that allows users to easily create high-quality images and videos for advertising and download them as needed. This system integrates a series of functions from inputting text and images to creating, saving, displaying, and downloading.

[0143] System Configuration

[0144] User Interface Means

[0145] When a user accesses the system, a user interface is displayed, which includes a text input field and an image upload button, allowing the user to input or upload the text and images they want to use in their advertisement.

[0146] Transmission method

[0147] When the user completes the text and image input and clicks the "Generate" button, the input data is sent from the device to the server using an HTTP POST request. The sent data is in JSON format and contains information about the text and image.

[0148] generation means

[0149] The server analyzes the received request and generates new images and videos for advertising based on the input data. Specifically, the server uses a pre-trained generative AI model to generate advertising materials that are optimal for the text and images provided by the user. This generative AI model is based on machine learning algorithms such as neural networks, and can generate high-quality images and videos in a short amount of time.

[0150] Preservation means

[0151] The generated images and videos are temporarily stored in the server's storage. The stored data is managed with consideration for future reuse and backup. This storage method allows users to later retrieve the advertising materials they have generated.

[0152] Display means

[0153] The generated advertising images and videos are sent back to the device and displayed on the user interface. The user can check the generated results and download and use them as needed. If the results are not as expected, the user can modify the text or images and send a new request.

[0154] Download Method

[0155] If the user is satisfied with the generated image or video, the user can download it. The downloading means provides a function for saving the generated advertising material to the terminal. This function allows the user to freely use the generated advertising material in a local environment.

[0156] Hardware and software used

[0157] Hardware: Server (CPU or GPU)

[0158] software:

[0159] Framework: Flask (Python web framework)

[0160] Model: Generative AI model (e.g. CLIP, "clip-vit-base-patch32" from HuggingFace)

[0161] Specific examples

[0162] For example, if a user wants to generate advertising material for a "Summer Sale," the user enters the following prompt text:

[0163] Example prompt sentence:

[0164] "Make your ad with beach images that are perfect for summer sales."

[0165] The user uploads a beach image along with this prompt and clicks the "Generate" button. The server analyzes the received input data and generates appropriate advertising materials using a generative AI model. The generated advertising materials are displayed in the user interface, and the user can download and use them.

[0166] In this way, the present invention is designed to enable users to easily generate high-quality images and videos for advertising, thereby enabling efficient creation of advertising materials while reducing time and costs.

[0167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0168] Step 1:

[0169] When a user accesses the system, a user interface is displayed on the terminal.

[0170] How it works: A text entry field and an image upload button are displayed in the user interface. The user enters the text they want to use in their ad and uploads an image.

[0171] Step 2:

[0172] The user completes the text and image input and clicks the "Generate" button.

[0173] How it works: User-supplied data is packaged in JSON format and sent to the server via an HTTP POST request.

[0174] Input: Text entered by the user and images uploaded by the user.

[0175] Output: JSON formatted data sent to the server.

[0176] Step 3:

[0177] The server analyzes the received request.

[0178] How it works: The server receives an HTTP POST request and parses the JSON data contained within it, extracting text and image data.

[0179] Input: Text and image data in JSON format.

[0180] Output: Extracted text and image data.

[0181] Step 4:

[0182] The server uses the generative AI model to generate images or videos for the advertisement.

[0183] How it works: The extracted text and images are fed into a generative AI model, which then generates the optimal advertising materials. High-quality images and videos are generated in a short time.

[0184] Input: Extracted text and image data.

[0185] Output: The generated advertising image or video.

[0186] Step 5:

[0187] The generated images or videos are temporarily stored on the server.

[0188] How it works: The generated ad material is saved in server storage, allowing for future reuse and backup.

[0189] Input: Generated image or video for advertising.

[0190] Output: Materials stored in the server's storage.

[0191] Step 6:

[0192] The saved image or video is sent to the user's device.

[0193] How it works: The server sends the generated ad material to the user's device as an HTTP response. The sent data is then packaged in JSON format again.

[0194] Input: Materials stored in the server's storage.

[0195] Output: The advertising image or video sent to the user's device.

[0196] Step 7:

[0197] The material will be displayed on the user's device and can be checked.

[0198] Behavior: The user interface displays the material for review and allows the user to download the generated results, if desired.

[0199] Input: Advertising image or video sent to the user's device.

[0200] Output: Advertising images or videos displayed in the user interface.

[0201] Step 8:

[0202] The user downloads the generated material.

[0203] How it works: If the user is satisfied with the generated ad material, they can download it. Once the download process is complete, the material will be saved to the user's local storage.

[0204] Input: The displayed advertising image or video.

[0205] Output: Ad images or videos stored in the user's local storage.

[0206] 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.

[0207] The present invention provides a system that generates images and videos for advertising purposes based on text and images entered by a user, and further recognizes the user's emotional data and adaptively changes the content of the generated images. The system includes a user interface, a transmission means, a generation means, a storage means, a display means, and an emotion engine.

[0208] User Interface Means

[0209] Users access a web UI to input or upload the text and images they want to use in their ads, and the app incorporates an emotion engine that reads the user's facial expressions and voice in real time via a webcam and microphone.

[0210] Transmission method

[0211] The text, images, and even emotion data entered by the user are converted into JSON format and sent to the server as an HTTP POST request. The emotion data is treated as metadata that indicates the user's emotional state.

[0212] generation means

[0213] The server analyzes the received request and generates new images and videos for advertising based not only on text and image data but also on emotional data obtained from the emotion engine. The emotion engine detects the user's emotional state from their facial expressions and voice and uses this information to adjust the theme, color, and style of the generated content.

[0214] Preservation means

[0215] The generated images and videos are temporarily stored in the server storage, allowing the user to retrieve the generated images later.

[0216] Display means

[0217] The generated images and videos for advertising are sent from the server to the device and displayed on the Web UI. Users can check the results in real time and download or edit them as needed.

[0218] Emotion Engine

[0219] The emotion engine captures the user's facial expressions with a webcam and uses machine learning algorithms to analyze their emotions in real time. It also performs voice analysis to determine their emotional state from the tone and speed of their voice. This emotional data is reflected in the generated advertising materials, so content optimized for the user's current emotions is generated.

[0220] Specific examples

[0221] For example, suppose a user is trying to create an ad for a "Christmas sale." The user enters the text "Christmas sale" into the web UI and uploads a Christmas-related image. The emotion engine then captures the user's facial expressions and analyzes their emotions from their voice. If the user appears happy, the emotion engine will reflect a bright and cheerful theme in the ad images and videos it generates. Conversely, if the user appears calm, the generated content will be adjusted accordingly.

[0222] In this way, this system can generate high-quality advertising images and videos that incorporate the user's emotions, making it possible to provide more personalized advertising materials to users.

[0223] The processing flow will be explained below.

[0224] Step 1:

[0225] A user accesses the web UI and enters text or uploads an image. For example, a user enters the text "Christmas Sale" and uploads a Christmas-related image.

[0226] Step 2:

[0227] The user's device captures the user's facial expressions and voice through a webcam and microphone, and analyzes the emotional data in real time. This analysis is performed by an emotion engine, and the user's emotional state is obtained as numerical data.

[0228] Step 3:

[0229] When the user clicks the "Generate" button, the device converts the entered text, uploaded image, and analyzed emotion data into JSON format and sends it to the server.

[0230] Step 4:

[0231] The server receives the HTTP POST request and parses its contents, extracting text, images, and sentiment data from the request and preparing them for passing to the generative model.

[0232] Step 5:

[0233] The server calls a pre-trained generative model to generate images and videos for advertising based on the user's input data and emotional data. For example, if the user expresses a happy emotion, the generative model will reflect a bright and cheerful theme.

[0234] Step 6:

[0235] The generated images and videos are temporarily stored on the server, and the path and file name of the storage destination are uniquely determined and used in the next processing step.

[0236] Step 7:

[0237] The server sends the stored images and videos to the device as an HTTP response. At this time, the sent data is treated as binary image or video data.

[0238] Step 8:

[0239] The device analyzes the HTTP response received from the server, generates images and videos from the binary data, and converts the generated data into a format that can be displayed on the user interface.

[0240] Step 9:

[0241] The generated images and videos for advertising are displayed on the user's device via a web UI, allowing the user to check the results in real time and download or edit them as needed.

[0242] Step 10:

[0243] If the user is not satisfied with the results, they can modify the text or images again and send a new request to the server. This process can be repeated.

[0244] In this way, the user, terminal, server, and emotion engine work together to generate highly personalized advertising images and videos.

[0245] Example 2

[0246] 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."

[0247] Conventional systems have traditionally generated advertising content without considering the user's emotional state, making it difficult to generate advertising materials that match the user's desired mood and tone. Furthermore, the lack of a mechanism for incorporating user feedback in real time makes it difficult to maximize advertising effectiveness.

[0248] 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.

[0249] In this invention, the server comprises: an input device means for accepting input of text or images;

[0250] Emotion analysis means that reads the user's facial expressions and voice in real time;

[0251] a transmitting device means for transmitting the input text, image, and emotion data to a server;

[0252] a content generation means in the server for generating new images or videos based on input text, images, and emotion data;

[0253] a storage means for temporarily storing the generated image or video;

[0254] a transmitting device means for transmitting the stored images or videos to a user;

[0255] a display device for displaying the transmitted image or video;

[0256] This makes it possible to generate advertising content that is optimized for user emotions and reflect feedback in real time.

[0257] "Text" is character string information that a user inputs to create advertising content.

[0258] "Image" means visual information uploaded by a user to create advertising content.

[0259] "Input device means" refers to an interface that allows a user to input text and images. Specifically, it includes a Web UI that is used via a browser.

[0260] The "emotion analysis means" is a device that reads the user's facial expressions and voice in real time, and analyzes this data to determine the user's emotional state.

[0261] "Transmission device means" refers to a device for transmitting input text, images, and emotion data to a server, mainly using HTTP protocol and REST API.

[0262] A "server" is a central processing unit that generates new images and videos based on the data it receives.

[0263] "Content generation means" means a device that generates new images or videos based on input text, images, and emotion data within the server, utilizing a generative AI model.

[0264] A "generative AI model" is a pre-trained machine learning model used to generate images and videos. Examples include Generative Adversarial Networks (GANs) and CLIP.

[0265] "Storage means" refers to a device for temporarily storing the generated images or videos. Cloud storage is typically used.

[0266] The "transmitting device means" is a device for transmitting the generated image or video to the user's terminal.

[0267] "Display device means" means a device for displaying the generated images or videos on a user interface. Display technology such as HTML5 is used.

[0268] "User" means a person who uses the system to create advertising content.

[0269] The present invention provides a system for generating images and videos for advertising purposes based on text and images entered by a user and emotion data acquired in real time. The system includes an input device, emotion analysis means, transmission device, content generation means, storage means, transmission device means, and display device means.

[0270] input device means

[0271] Users access the Web UI through a browser and input or upload the text and images they want to use in their ads. Specifically, an interface using HTML5 and JavaScript (registered trademark) is used, allowing users to easily provide text and images to the system.

[0272] Emotion analysis means

[0273] The Web UI is equipped with a camera and microphone to capture the user's facial expressions and voice in real time. The emotion analysis tool uses data obtained from these input devices to determine the user's emotional state. This analysis uses libraries such as OpenCV and Dlib and applies machine learning algorithms.

[0274] Transmitter means

[0275] The device converts the text, image, and emotion data entered by the user into JSON format and sends it to the server as an HTTP POST request using the HTTP protocol and REST API, allowing the server to receive all the necessary information comprehensively.

[0276] Content Creation Methods

[0277] The server generates new advertising images and videos based on the received data, using text, images, and emotion data. A pre-trained generative AI model, such as GAN (Generative Adversarial Networks) or CLIP, is used for generation. The generative AI model is implemented using machine learning libraries such as TENSORFLOW (registered trademark) and PyTorch, and analyzes the received data and adaptively adjusts the generated content.

[0278] storage means

[0279] The server temporarily stores the generated images and videos in cloud storage, such as AWS (registered trademark) S3 or Google (registered trademark) Cloud Storage. The stored data is managed so that users can access and retrieve it later.

[0280] Transmitter means

[0281] The server sends the generated advertising images and videos to the user's device, allowing the user to check the results in real time. Communication is via the HTTP protocol, and data is sent in JSON format.

[0282] display means

[0283] The device displays images and videos sent from the server on the Web UI. <video>Tags and Tags are used, and users can review the generated content and download or further edit it if necessary.

[0284] Specific examples

[0285] For example, if a user is trying to create an ad for "Christmas Sale," they enter the text "Christmas Sale" into the Web UI and upload a Christmas-related image. At that time, the emotion engine captures the user's facial expressions and analyzes emotions from their voice. If the user seems happy, the emotion engine will reflect a bright and cheerful theme in the ad images and videos it generates. Below is an example of a prompt sentence:

[0286] Example prompt sentence:

[0287] "Generate an image to advertise a Christmas sale. The user's emotional state seems happy."

[0288] In this way, this system can generate high-quality advertising images and videos that incorporate the user's emotions, making it possible to provide more personalized advertising materials to users.

[0289] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0290] Step 1:

[0291] Users access the Web UI through a browser and enter or upload the text and images they want to use in their ads. The entered text and images are sent to the server through form elements in the Web UI. The input data is mainly written in HTML5 and JavaScript.

[0292] Input: Text input and image upload

[0293] Output: Text and image input data as form data

[0294] Step 2:

[0295] The user's device activates a webcam and microphone to capture the user's facial expressions and voice, thereby obtaining the user's emotional data in real time. Libraries such as OpenCV and Dlib are used for emotion analysis.

[0296] Input: Real-time facial image and audio data

[0297] Output: Captured emotion data

[0298] Step 3:

[0299] The device converts the input text, image, and emotion data into JSON format, which is then ready to be sent to the server.

[0300] Input: Text, images, and captured emotion data

[0301] Output: JSON format data

[0302] Step 4:

[0303] The device sends the generated JSON data to the server as an HTTP POST request, using the HTTP protocol and the REST API.

[0304] Input: JSON format data

[0305] Output: Data sent to the server

[0306] Step 5:

[0307] The server parses the JSON data of the received HTTP POST request using the Python standard library json to extract text data, image data, and emotion data.

[0308] Input: JSON format data

[0309] Output: Extracted text, images, and sentiment data

[0310] Step 6:

[0311] The server then uses the extracted data to generate new images and videos using generative AI models, such as GAN and CLIP, using TensorFlow and PyTorch. The generative AI model adjusts the theme, color, and style of the generated content based on the emotion data.

[0312] Input: Text, image, and sentiment data

[0313] Output: The generated image or video

[0314] Step 7:

[0315] The server temporarily stores the generated images and videos for advertising in cloud storage, using AWS S3 or Google Cloud Storage. The stored data is managed so that users can access and retrieve it later.

[0316] Input: Generated images or videos

[0317] Output: Snapshot image or video

[0318] Step 8:

[0319] The server sends the generated advertising images and videos to the user's device as an HTTP response, using the HTTP protocol for transfer.

[0320] Input: Generated images or videos

[0321] Output: Data sent to the user's terminal

[0322] Step 9:

[0323] The user's device displays the received images and videos on the Web UI. <video>Tags and Tags are used, and users can review the generated content and download or further edit it if necessary.

[0324] Input: Image or video sent from the server

[0325] Output: Image or video displayed on the Web UI

[0326] (Application example 2)

[0327] 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."

[0328] Conventional ad generation systems generate ad materials from text and images based on user input, but it is difficult to generate personalized ad materials that reflect the user's emotional state. Furthermore, since it is not possible to check and adjust the generated results in real time, there is a problem that it is difficult to increase user satisfaction.

[0329] 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.

[0330] In this invention, the server includes a user interface means for accepting input of text, images, and voice, a transmission means for transmitting the input text, images, voice, and emotion data to the server, a generation means for generating new images or videos based on the input in the server, a transmission means for transmitting the generated images or videos to the user, a display means for displaying the transmitted images or videos on the user interface, and a means for adjusting the theme and style of the images or videos generated by the generation means based on the emotion data, including an emotion engine for collecting and analyzing user emotion data. This enables the generation of personalized advertising materials that reflect the user's emotional state in real time.

[0331] The "user interface means for accepting input of text, images, and voice" is an interface for a user to input text, images, and voice to be used in creating advertising materials.

[0332] The "transmission means for transmitting input text, image, voice, and emotion data to a server" is a means for transmitting data and emotion data input by a user to a server.

[0333] The "generation means" is a mechanism that generates new images and videos for advertising based on data input to the server.

[0334] The "display means" is a means for displaying the generated advertising images and videos on the user interface.

[0335] The "emotion engine" is a system that includes machine learning algorithms that collect and analyze the user's facial expressions and voice data to detect the user's emotional state.

[0336] The "means for adjusting the theme or style of the image or video generated by the generation means based on emotional data" is a mechanism for automatically adjusting the theme or style of the advertising material generated by the generation means based on emotional data analyzed by the emotion engine.

[0337] A "generative AI model" is an artificial intelligence model that is pre-trained and used to generate new images and videos.

[0338] The present invention provides a system that generates images and videos for advertising purposes based on text, images, and audio input by a user, and further recognizes the user's emotional data and adaptively changes the content of the generated images. A specific embodiment of the invention will be described below.

[0339] Hardware and software used

[0340] Hardware:

[0341] Smart glasses (e.g. Vuzix Blade, Nreal Light)

[0342] A device equipped with a webcam and microphone

[0343] Cloud servers (e.g. AWS EC2 instances)

[0344] software:

[0345] Frontend: Customized Web UI using React.js

[0346] Backend: Python (Flask) and TensorFlow

[0347] Generative AI models: GPT-4® and DALL-E

[0348] System Components

[0349] 1. User Interface Means:

[0350] Users use the smart glasses to input text, images, and audio using voice commands and gestures, and the glasses' camera and microphone are used to capture facial and audio data in real time.

[0351] 2. Means of transmission:

[0352] The captured data and input text, images, and audio are converted into JSON format and sent to the server as an HTTP POST request.

[0353] 3. Generation means:

[0354] The server analyzes the received data and generates new advertising images and videos based on the emotion data, using pre-trained generative AI models (GPT-4 and DALL-E).

[0355] 4. Display means:

[0356] The generated advertising images and videos are displayed in real time on the user interface, where users can check the results through the glasses' display and make edits if necessary.

[0357] 5. Emotion Engine:

[0358] The emotion engine uses machine learning algorithms to analyze a user's facial expressions and voice data to infer their emotional state, and then adjusts the theme and style of the ad material it generates based on this emotional data.

[0359] Data processing and calculation

[0360] The server analyzes the data received from the front-end and compares it with the emotional data obtained by the emotion engine. The analyzed data is input into the generative AI model to generate advertising materials. The generated materials are temporarily stored on the cloud server so that users can access them at any time.

[0361] Specific examples

[0362] For example, if a user is trying to create a TV ad for a new product, they can put on the smart glasses, say "new 4K TV," and scan an image of the product with the camera. At the same time, the emotion engine will detect that the user is smiling. Based on this information, the ad generated by the generative AI model will be tailored to a bright and cheerful theme.

[0363] Prompt Sentence Examples

[0364] Prompt 1: "Generate an ad for a new 4K TV. The user will smile."

[0365] Prompt 2: "The theme should be fun and bright colors."

[0366] This allows users to generate emotion-based personalized advertising material in real time.

[0367] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0368] Step 1:

[0369] Users wear smart glasses and input text, images, and voice using voice commands and gestures. The smart glasses' cameras and microphones automatically capture the user's facial expressions and voice, collecting the necessary data in real time. This allows the input data to be collected as text, image files, audio files, and emotional data.

[0370] Step 2:

[0371] The collected data is temporarily stored as a document in the smart glasses. The stored data is converted to JSON format and sent to the server as an HTTP POST request. Through this sending process, the server receives input data from the user interface.

[0372] Step 3:

[0373] The server analyzes the received JSON data. The analysis includes text data analysis, image and audio data preprocessing, and emotion data analysis. The results of this processing are analyzed text data, image data, audio data, and emotion metadata.

[0374] Step 4:

[0375] The server inputs the analyzed data into a generative AI model, which uses pre-trained GPT-4 and DALL-E models to generate images and videos for advertisements that reflect the user's emotional data. This process outputs optimized advertising materials.

[0376] Step 5:

[0377] The generated advertising materials are temporarily stored in the server storage, and this storage process allows users to access and download the generated materials at any time.

[0378] Step 6:

[0379] The server transmits the generated advertising images and videos in real time to the user interface, where the transmitted advertising materials are further displayed on the display of the user's smart glasses, allowing the user to check the generated results in real time.

[0380] Step 7:

[0381] Users can review the displayed ad material and, if necessary, re-edit or adjust it using voice commands or gestures. During this adjustment process, the generative AI model performs further optimization based on user feedback, and improved ad material is generated and displayed again.

[0382] The above steps result in a system that allows users to generate and edit emotion-based personalized advertising materials in real time.

[0383] 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.

[0384] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0385] 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.

[0386] [Second embodiment]

[0387] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0388] 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.

[0389] 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).

[0390] 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.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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."

[0399] The present invention provides a system that allows a user to input text and images, generates new advertising images and videos on a server based on the input text and images, and displays the images and videos on a user interface. The system includes a user interface means, a transmission means, a generation means, a storage means, and a display means.

[0400] User Interface Means

[0401] When a user accesses the system, they are first presented with a user interface that includes a text entry field and an image upload button. The user enters or uploads the text and images they want to use in their advertisement.

[0402] Transmission method

[0403] When the user completes the text and image input and clicks the "Generate" button, the input data is sent from the device to the server using an HTTP POST request. The sent data is in JSON format and contains information about the text and image.

[0404] generation means

[0405] The server analyzes the received request and generates new advertising images and videos based on the input data. Specifically, the server uses a pre-trained generative model to generate advertising materials that are optimal for the text and images provided by the user. This generative model is based on machine learning algorithms such as neural networks, and can generate high-quality images and videos in a short amount of time.

[0406] Preservation means

[0407] The generated images and videos are temporarily stored in the server's storage. The stored data is managed with consideration for future reuse and backup. This storage method allows users to re-acquire the advertising materials they have generated at a later date.

[0408] Display means

[0409] The generated advertising images and videos are sent back to the device and displayed on the user interface. The user can check the displayed results and download and use them as needed. If the results are not as expected, the user can modify the text or images and send a new request.

[0410] Specific examples

[0411] For example, suppose a user wants to generate advertising materials for a "summer sale." The user accesses the Web UI, enters the text "summer sale," and uploads an image of a beach. After that, the user clicks the "Generate" button, and the input information is sent to the server. The server generates advertising images and videos showing the summer sale based on the received text and images. The generated materials are temporarily saved, sent to the device, and displayed on the Web UI. The user can check the generated results and download them if they are satisfactory.

[0412] In this way, the system is designed to enable users to easily generate high-quality images and videos for advertising. The means described in this claim enable efficient creation of advertising materials while reducing time and costs.

[0413] The processing flow will be explained below.

[0414] Step 1:

[0415] Users access the Web UI and enter text and images. For example, a user can enter the text "Summer Sale" and upload an image of the product in question.

[0416] Step 2:

[0417] The user clicks the "Generate" button on the Web UI, which converts the entered text and uploaded images into JSON format.

[0418] Step 3:

[0419] The terminal sends the data converted into JSON format to the server as an HTTP POST request. The sent data includes the text and image information entered by the user.

[0420] Step 4:

[0421] The server receives the HTTP POST request, parses its contents, extracts text and image information from the request, and prepares it for passing to the generative model.

[0422] Step 5:

[0423] The server then invokes pre-trained generative models to generate images and videos for advertisements based on user input, for example using a neural network to generate images related to "summer sales."

[0424] Step 6:

[0425] The generated images and videos are temporarily stored on the server, and the path and file name of the storage destination are uniquely determined and used in the next processing step.

[0426] Step 7:

[0427] The server sends the stored images and videos to the device as an HTTP response. At this time, the sent data is treated as binary image or video data.

[0428] Step 8:

[0429] The device analyzes the HTTP response received from the server, generates images and videos from the binary data, and converts the generated data into a format that can be displayed on the user interface.

[0430] Step 9:

[0431] The generated images and videos for advertising are displayed on the user's device in a web UI, where the user can check the results and download or edit them as needed.

[0432] Step 10:

[0433] If the user is not satisfied with the results, they can modify the text or images again and send a new request to the server. This process can be repeated.

[0434] In this way, users, terminals, and servers work together to efficiently generate high-quality advertising images and videos.

[0435] Example 1

[0436] 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."

[0437] Conventional advertising material generation systems lack the means for users to quickly and easily generate high-quality images and videos for advertising. They also lack mechanisms for efficiently storing, managing, and reusing the generated advertising materials. This results in high costs and time-consuming processes.

[0438] 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.

[0439] In this invention, the server includes a display device that accepts input of text or images, a transmission device that transmits the input text or images to a processing device, a generation device that generates new audiovisual data based on the input in the processing device, a transmission device that transmits the generated audiovisual data to a user, and a display device that displays the transmitted audiovisual data on a display device. This allows users to quickly and easily generate high-quality advertising images and videos. Furthermore, by including a storage device for temporary storage, data management and reuse after generation can be efficiently performed.

[0440] A "display device" is a device that provides an interface for a user to input text and images.

[0441] A "transmitting device" is a device that has the function of transmitting input text and images to a processing device.

[0442] A "processing device" is a device that generates new audiovisual data based on input data sent by a user.

[0443] A "generator" is a device that generates new audiovisual data using a pre-trained generative algorithm.

[0444] A "storage device" is a device for temporarily storing generated audiovisual data.

[0445] "Audiovisual data" refers to digital content such as images and videos generated for advertising purposes.

[0446] A "generative algorithm" is a machine learning model or other computational method used to generate audiovisual data based on input data.

[0447] MODE FOR CARRYING OUT THE INVENTION

[0448] The present invention provides a system in which a user inputs text and images, generates new advertising images and videos on a server based on the input text and images, and displays the images and videos on a user interface. The system includes a display device, a transmission device, a generation device, a storage device, and a display device.

[0449] When a user accesses the system using a web browser, the server renders and sends to the terminal a display image that includes a text entry field and an image upload button where the user can enter promotional text, such as "Summer Sale," and upload an image to be used in the advertising materials.

[0450] Next, when the user clicks the "Generate" button, the entered text and uploaded image are packaged in JSON format and sent to the server via an HTTP POST request. This sender provides a means for passing input data to the server.

[0451] The server parses the received JSON data and activates a generator, which includes a pre-trained generative AI model (e.g., a Generative Adversarial Network (GAN)) that generates new advertising images and videos based on user input. The generative AI model is based on machine learning algorithms and can generate content quickly and with high quality.

[0452] The generated data is temporarily stored in a storage device, which is used to store the generated data and facilitate future reuse and data management.

[0453] Finally, the server reloads the generated data and sends it to the display device. The display device on the terminal receives it and displays it on the user interface. The user can check the generated audiovisual data and download it if they are satisfied. If the result is not as expected, they can modify the text and images and send a new request.

[0454] Specific examples

[0455] For example, suppose a user wants to generate advertising materials for a "Summer Sale." The user accesses the Web UI, enters the text "Summer Sale," and uploads an image of a beach. After that, the user clicks the "Generate" button, and the input is sent to the server. Based on the received text and image, the server uses a generative AI model to generate advertising images and videos showing the summer sale. This generated material is temporarily stored and eventually sent to a display device and displayed on the Web UI. The user checks the generated results and downloads them if they are satisfactory. Below is an example of a prompt:

[0456] prompt:

[0457] I want to generate an image for an advertisement. The text is "Summer Sale" and the image I want to upload is a beach photo.

[0458] In this way, this system is designed to enable users to easily generate high-quality images and videos for advertising, thereby enabling efficient creation of advertising materials while reducing time and costs.

[0459] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0460] Step 1:

[0461] User Interface Display

[0462] When a user accesses the system from a web browser, the server renders a user interface and sends it to the terminal. This user interface includes text input fields and image upload buttons, and the user inputs and uploads the text and images they want to use in the advertising materials.

[0463] Input: Access request from a web browser

[0464] Output: User interface

[0465] Step 2:

[0466] Sending input data

[0467] When the user completes the text and image input and clicks the "Generate" button, the data is packaged in JSON format and sent to the server via an HTTP POST request. The sent data includes the text data entered by the user and the image data uploaded.

[0468] Input: User-entered text and images, HTTP POST requests

[0469] Output: JSON data sent to the server side

[0470] Step 3:

[0471] Data analysis

[0472] The server parses the received JSON data, where the data stream is parsed and each field (text content, image information, etc.) is identified.

[0473] Input: JSON format text data and image data

[0474] Output: Analyzed text and image data objects

[0475] Step 4:

[0476] Creation of advertising materials

[0477] The server uses a generator to generate audiovisual data for advertising based on the text and images obtained from the analysis. The generator uses a pre-trained generative AI model to generate appropriate images and videos based on the user's input data. For example, if a user enters "summer sale" and uploads an image of a beach, the generative AI model will generate advertising materials that fit that theme.

[0478] Input: Analyzed text and image data, generative AI model

[0479] Output: Generated audiovisual data

[0480] Step 5:

[0481] Saving generated data

[0482] The server temporarily stores the generated audiovisual data in a storage device, which stores the generated data along with the date and time of generation, the user ID, and metadata of the text and images used for input.

[0483] Input: Generated audiovisual data

[0484] Output: Data stored on the storage device

[0485] Step 6:

[0486] Viewing generated data

[0487] The server reloads the saved generated data and sends it to the user interface. The display device on the terminal receives this data and displays it on the user interface. The user can check the displayed advertising images and videos and download them if necessary.

[0488] Input: Data stored on storage device, user request

[0489] Output: Audiovisual data displayed on a display device

[0490] (Application example 1)

[0491] 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."

[0492] The modern advertising industry demands the efficient and rapid generation of high-quality advertising materials. However, achieving this requires specialized skills and expensive software, which is time-consuming and costly. Furthermore, generating advertising materials requires a system that allows users to easily upload text and images and then generate, save, display, and download optimal advertising materials based on those text and images. However, current systems have difficulty meeting all of these requirements. Furthermore, a function that allows users to easily download the generated advertising materials is also required. The objective of this invention is to solve these problems.

[0493] 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.

[0494] In this invention, the server includes a user interface means for accepting input of text or images, a transmission means for transmitting the input text or images to the server, a generation means for generating new images or videos based on the input at the server, a storage means for saving the generated images or videos, a display means for displaying the transmitted images or videos on the user interface, and a download means for the user to download the generated images or videos. This enables users to easily input and upload text and images they want to use in their advertisements, and then quickly generate, save, display, and download high-quality advertising materials based on them.

[0495] "User interface means" refers to an interface through which a user inputs text and images into the system.

[0496] The "transmission means" is a means having a function for transmitting text and images input by the user to the server.

[0497] The "generation means" is a means having a function of generating a new image or video based on an input in the server.

[0498] The "storage means" is a means having a function of temporarily storing the generated image or video.

[0499] The "display means" is a means having a function of displaying the generated image or video on the user's interface.

[0500] The "downloading means" is a means that has a function for a user to download generated images or videos.

[0501] A "generative AI model" is a machine learning model that is pre-trained to generate new advertising images and videos based on text and images.

[0502] A "prompt" is an instruction given to a generative AI model in the form of text input.

[0503] The present invention provides a system that allows users to easily create high-quality images and videos for advertising and download them as needed. This system integrates a series of functions from inputting text and images to creating, saving, displaying, and downloading.

[0504] System Configuration

[0505] User Interface Means

[0506] When a user accesses the system, a user interface is displayed, which includes a text input field and an image upload button, allowing the user to input or upload the text and images they want to use in their advertisement.

[0507] Transmission method

[0508] When the user completes the text and image input and clicks the "Generate" button, the input data is sent from the device to the server using an HTTP POST request. The sent data is in JSON format and contains information about the text and image.

[0509] generation means

[0510] The server analyzes the received request and generates new images and videos for advertising based on the input data. Specifically, the server uses a pre-trained generative AI model to generate advertising materials that are optimal for the text and images provided by the user. This generative AI model is based on machine learning algorithms such as neural networks, and can generate high-quality images and videos in a short amount of time.

[0511] Preservation means

[0512] The generated images and videos are temporarily stored in the server's storage. The stored data is managed with consideration for future reuse and backup. This storage method allows users to later retrieve the advertising materials they have generated.

[0513] Display means

[0514] The generated advertising images and videos are sent back to the device and displayed on the user interface. The user can check the generated results and download and use them as needed. If the results are not as expected, the user can modify the text or images and send a new request.

[0515] Download Method

[0516] If the user is satisfied with the generated image or video, the user can download it. The downloading means provides a function for saving the generated advertising material to the terminal. This function allows the user to freely use the generated advertising material in a local environment.

[0517] Hardware and software used

[0518] Hardware: Server (CPU or GPU)

[0519] software:

[0520] Framework: Flask (Python web framework)

[0521] Model: Generative AI model (e.g. CLIP, "clip-vit-base-patch32" from HuggingFace)

[0522] Specific examples

[0523] For example, if a user wants to generate advertising material for a "Summer Sale," the user enters the following prompt text:

[0524] Example prompt sentence:

[0525] "Make your ad with beach images that are perfect for summer sales."

[0526] The user uploads a beach image along with this prompt and clicks the "Generate" button. The server analyzes the received input data and generates appropriate advertising materials using a generative AI model. The generated advertising materials are displayed in the user interface, and the user can download and use them.

[0527] In this way, the present invention is designed to enable users to easily generate high-quality images and videos for advertising, thereby enabling efficient creation of advertising materials while reducing time and costs.

[0528] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0529] Step 1:

[0530] When a user accesses the system, a user interface is displayed on the terminal.

[0531] How it works: A text entry field and an image upload button are displayed in the user interface. The user enters the text they want to use in their ad and uploads an image.

[0532] Step 2:

[0533] The user completes the text and image input and clicks the "Generate" button.

[0534] How it works: User-supplied data is packaged in JSON format and sent to the server via an HTTP POST request.

[0535] Input: Text entered by the user and images uploaded by the user.

[0536] Output: JSON formatted data sent to the server.

[0537] Step 3:

[0538] The server analyzes the received request.

[0539] How it works: The server receives an HTTP POST request and parses the JSON data contained within it, extracting text and image data.

[0540] Input: Text and image data in JSON format.

[0541] Output: Extracted text and image data.

[0542] Step 4:

[0543] The server uses the generative AI model to generate images or videos for the advertisement.

[0544] How it works: The extracted text and images are fed into a generative AI model, which then generates the optimal advertising materials. High-quality images and videos are generated in a short time.

[0545] Input: Extracted text and image data.

[0546] Output: The generated advertising image or video.

[0547] Step 5:

[0548] The generated images or videos are temporarily stored on the server.

[0549] How it works: The generated ad material is saved in server storage, allowing for future reuse and backup.

[0550] Input: Generated image or video for advertising.

[0551] Output: Materials stored in the server's storage.

[0552] Step 6:

[0553] The saved image or video is sent to the user's device.

[0554] How it works: The server sends the generated ad material to the user's device as an HTTP response. The sent data is then packaged in JSON format again.

[0555] Input: Materials stored in the server's storage.

[0556] Output: The advertising image or video sent to the user's device.

[0557] Step 7:

[0558] The material will be displayed on the user's device and can be checked.

[0559] Behavior: The user interface displays the material for review and allows the user to download the generated results, if desired.

[0560] Input: Advertising image or video sent to the user's device.

[0561] Output: Advertising images or videos displayed in the user interface.

[0562] Step 8:

[0563] The user downloads the generated material.

[0564] How it works: If the user is satisfied with the generated ad material, they can download it. Once the download process is complete, the material will be saved to the user's local storage.

[0565] Input: The displayed advertising image or video.

[0566] Output: Ad images or videos stored in the user's local storage.

[0567] 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.

[0568] The present invention provides a system that generates images and videos for advertising purposes based on text and images entered by a user, and further recognizes the user's emotional data and adaptively changes the content of the generated images. The system includes a user interface, a transmission means, a generation means, a storage means, a display means, and an emotion engine.

[0569] User Interface Means

[0570] Users access a web UI to input or upload the text and images they want to use in their ads, and the app incorporates an emotion engine that reads the user's facial expressions and voice in real time via a webcam and microphone.

[0571] Transmission method

[0572] The text, images, and even emotion data entered by the user are converted into JSON format and sent to the server as an HTTP POST request. The emotion data is treated as metadata that indicates the user's emotional state.

[0573] generation means

[0574] The server analyzes the received request and generates new images and videos for advertising based not only on text and image data but also on emotional data obtained from the emotion engine. The emotion engine detects the user's emotional state from their facial expressions and voice and uses this information to adjust the theme, color, and style of the generated content.

[0575] Preservation means

[0576] The generated images and videos are temporarily stored in the server storage, allowing the user to retrieve the generated images later.

[0577] Display means

[0578] The generated images and videos for advertising are sent from the server to the device and displayed on the Web UI. Users can check the results in real time and download or edit them as needed.

[0579] Emotion Engine

[0580] The emotion engine captures the user's facial expressions with a webcam and uses machine learning algorithms to analyze their emotions in real time. It also performs voice analysis to determine their emotional state from the tone and speed of their voice. This emotional data is reflected in the generated advertising materials, so content optimized for the user's current emotions is generated.

[0581] Specific examples

[0582] For example, suppose a user is trying to create an ad for a "Christmas sale." The user enters the text "Christmas sale" into the web UI and uploads a Christmas-related image. The emotion engine then captures the user's facial expressions and analyzes their emotions from their voice. If the user appears happy, the emotion engine will reflect a bright and cheerful theme in the ad images and videos it generates. Conversely, if the user appears calm, the generated content will be adjusted accordingly.

[0583] In this way, this system can generate high-quality advertising images and videos that incorporate the user's emotions, making it possible to provide more personalized advertising materials to users.

[0584] The processing flow will be explained below.

[0585] Step 1:

[0586] A user accesses the web UI and enters text or uploads an image. For example, a user enters the text "Christmas Sale" and uploads a Christmas-related image.

[0587] Step 2:

[0588] The user's device captures the user's facial expressions and voice through a webcam and microphone, and analyzes the emotional data in real time. This analysis is performed by an emotion engine, and the user's emotional state is obtained as numerical data.

[0589] Step 3:

[0590] When the user clicks the "Generate" button, the device converts the entered text, uploaded image, and analyzed emotion data into JSON format and sends it to the server.

[0591] Step 4:

[0592] The server receives the HTTP POST request and parses its contents, extracting text, images, and sentiment data from the request and preparing them for passing to the generative model.

[0593] Step 5:

[0594] The server calls a pre-trained generative model to generate images and videos for advertising based on the user's input data and emotional data. For example, if the user expresses a happy emotion, the generative model will reflect a bright and cheerful theme.

[0595] Step 6:

[0596] The generated images and videos are temporarily stored on the server, and the path and file name of the storage destination are uniquely determined and used in the next processing step.

[0597] Step 7:

[0598] The server sends the stored images and videos to the device as an HTTP response. At this time, the sent data is treated as binary image or video data.

[0599] Step 8:

[0600] The device analyzes the HTTP response received from the server, generates images and videos from the binary data, and converts the generated data into a format that can be displayed on the user interface.

[0601] Step 9:

[0602] The generated images and videos for advertising are displayed on the user's device via a web UI, allowing the user to check the results in real time and download or edit them as needed.

[0603] Step 10:

[0604] If the user is not satisfied with the results, they can modify the text or images again and send a new request to the server. This process can be repeated.

[0605] In this way, the user, terminal, server, and emotion engine work together to generate highly personalized advertising images and videos.

[0606] Example 2

[0607] 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."

[0608] Conventional systems have traditionally generated advertising content without considering the user's emotional state, making it difficult to generate advertising materials that match the user's desired mood and tone. Furthermore, the lack of a mechanism for incorporating user feedback in real time makes it difficult to maximize advertising effectiveness.

[0609] 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.

[0610] In this invention, the server comprises: an input device means for accepting input of text or images;

[0611] Emotion analysis means that reads the user's facial expressions and voice in real time;

[0612] a transmitting device means for transmitting the input text, image, and emotion data to a server;

[0613] a content generation means in the server for generating new images or videos based on input text, images, and emotion data;

[0614] a storage means for temporarily storing the generated image or video;

[0615] a transmitting device means for transmitting the stored images or videos to a user;

[0616] a display device for displaying the transmitted image or video;

[0617] This makes it possible to generate advertising content that is optimized for user emotions and reflect feedback in real time.

[0618] "Text" is character string information that a user inputs to create advertising content.

[0619] "Image" means visual information uploaded by a user to create advertising content.

[0620] "Input device means" refers to an interface that allows a user to input text and images. Specifically, it includes a Web UI that is used via a browser.

[0621] The "emotion analysis means" is a device that reads the user's facial expressions and voice in real time, and analyzes this data to determine the user's emotional state.

[0622] "Transmission device means" refers to a device for transmitting input text, images, and emotion data to a server, mainly using HTTP protocol and REST API.

[0623] A "server" is a central processing unit that generates new images and videos based on the data it receives.

[0624] "Content generation means" means a device that generates new images or videos based on input text, images, and emotion data within the server, utilizing a generative AI model.

[0625] A "generative AI model" is a pre-trained machine learning model used to generate images and videos. Examples include Generative Adversarial Networks (GANs) and CLIP.

[0626] "Storage means" refers to a device for temporarily storing the generated images or videos. Cloud storage is typically used.

[0627] The "transmitting device means" is a device for transmitting the generated image or video to the user's terminal.

[0628] "Display device means" means a device for displaying the generated images or videos on a user interface. Display technology such as HTML5 is used.

[0629] "User" means a person who uses the system to create advertising content.

[0630] The present invention provides a system for generating images and videos for advertising purposes based on text and images entered by a user and emotion data acquired in real time. The system includes an input device, emotion analysis means, transmission device, content generation means, storage means, transmission device means, and display device means.

[0631] input device means

[0632] Users access the Web UI through a browser and input or upload the text and images they want to use in their ads. Specifically, an interface using HTML5 and JavaScript is used, allowing users to easily provide text and images to the system.

[0633] Emotion analysis means

[0634] The Web UI is equipped with a camera and microphone to capture the user's facial expressions and voice in real time. The emotion analysis tool uses data obtained from these input devices to determine the user's emotional state. This analysis uses libraries such as OpenCV and Dlib and applies machine learning algorithms.

[0635] Transmitter means

[0636] The device converts the text, image, and emotion data entered by the user into JSON format and sends it to the server as an HTTP POST request using the HTTP protocol and REST API, allowing the server to receive all the necessary information comprehensively.

[0637] Content Creation Methods

[0638] The server uses the received data to generate new advertising images and videos using text, images, and emotion data. A pre-trained generative AI model, such as GAN (Generative Adversarial Networks) or CLIP, is used for generation. The generative AI model is implemented using machine learning libraries such as TensorFlow and PyTorch, and analyzes the received data and adaptively adjusts the generated content.

[0639] storage means

[0640] The server temporarily stores the generated images and videos in cloud storage, such as AWS S3 or Google Cloud Storage, and manages the stored data so that users can access and retrieve them later.

[0641] Transmitter means

[0642] The server sends the generated advertising images and videos to the user's device, allowing the user to check the results in real time. Communication is via the HTTP protocol, and data is sent in JSON format.

[0643] display means

[0644] The device displays images and videos sent from the server on the Web UI. <video>Tags and Tags are used, and users can review the generated content and download or further edit it if necessary.

[0645] Specific examples

[0646] For example, if a user is trying to create an ad for "Christmas Sale," they enter the text "Christmas Sale" into the Web UI and upload a Christmas-related image. At that time, the emotion engine captures the user's facial expressions and analyzes emotions from their voice. If the user seems happy, the emotion engine will reflect a bright and cheerful theme in the ad images and videos it generates. Below is an example of a prompt sentence:

[0647] Example prompt sentence:

[0648] "Generate an image to advertise a Christmas sale. The user's emotional state seems happy."

[0649] In this way, this system can generate high-quality advertising images and videos that incorporate the user's emotions, making it possible to provide more personalized advertising materials to users.

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

[0651] Step 1:

[0652] Users access the Web UI through a browser and enter or upload the text and images they want to use in their ads. The entered text and images are sent to the server through form elements in the Web UI. The input data is mainly written in HTML5 and JavaScript.

[0653] Input: Text input and image upload

[0654] Output: Text and image input data as form data

[0655] Step 2:

[0656] The user's device activates a webcam and microphone to capture the user's facial expressions and voice, thereby obtaining the user's emotional data in real time. Libraries such as OpenCV and Dlib are used for emotion analysis.

[0657] Input: Real-time facial image and audio data

[0658] Output: Captured emotion data

[0659] Step 3:

[0660] The device converts the input text, image, and emotion data into JSON format, which is then ready to be sent to the server.

[0661] Input: Text, images, and captured emotion data

[0662] Output: JSON format data

[0663] Step 4:

[0664] The device sends the generated JSON data to the server as an HTTP POST request, using the HTTP protocol and the REST API.

[0665] Input: JSON format data

[0666] Output: Data sent to the server

[0667] Step 5:

[0668] The server parses the JSON data of the received HTTP POST request using the Python standard library json to extract text data, image data, and emotion data.

[0669] Input: JSON format data

[0670] Output: Extracted text, images, and sentiment data

[0671] Step 6:

[0672] The server then uses the extracted data to generate new images and videos using generative AI models, such as GAN and CLIP, using TensorFlow and PyTorch. The generative AI model adjusts the theme, color, and style of the generated content based on the emotion data.

[0673] Input: Text, image, and sentiment data

[0674] Output: The generated image or video

[0675] Step 7:

[0676] The server temporarily stores the generated images and videos for advertising in cloud storage, using AWS S3 or Google Cloud Storage. The stored data is managed so that users can access and retrieve it later.

[0677] Input: Generated images or videos

[0678] Output: Snapshot image or video

[0679] Step 8:

[0680] The server sends the generated advertising images and videos to the user's device as an HTTP response, using the HTTP protocol for transfer.

[0681] Input: Generated images or videos

[0682] Output: Data sent to the user's terminal

[0683] Step 9:

[0684] The user's device displays the received images and videos on the Web UI. <video>Tags and Tags are used, and users can review the generated content and download or further edit it if necessary.

[0685] Input: Image or video sent from the server

[0686] Output: Image or video displayed on the Web UI

[0687] (Application example 2)

[0688] 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."

[0689] Conventional ad generation systems generate ad materials from text and images based on user input, but it is difficult to generate personalized ad materials that reflect the user's emotional state. Furthermore, since it is not possible to check and adjust the generated results in real time, there is a problem that it is difficult to increase user satisfaction.

[0690] 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.

[0691] In this invention, the server includes a user interface means for accepting input of text, images, and voice, a transmission means for transmitting the input text, images, voice, and emotion data to the server, a generation means for generating new images or videos based on the input in the server, a transmission means for transmitting the generated images or videos to the user, a display means for displaying the transmitted images or videos on the user interface, and a means for adjusting the theme and style of the images or videos generated by the generation means based on the emotion data, including an emotion engine for collecting and analyzing user emotion data. This enables the generation of personalized advertising materials that reflect the user's emotional state in real time.

[0692] The "user interface means for accepting input of text, images, and voice" is an interface for a user to input text, images, and voice to be used in creating advertising materials.

[0693] The "transmission means for transmitting input text, image, voice, and emotion data to a server" is a means for transmitting data and emotion data input by a user to a server.

[0694] The "generation means" is a mechanism that generates new images and videos for advertising based on data input to the server.

[0695] The "display means" is a means for displaying the generated advertising images and videos on the user interface.

[0696] The "emotion engine" is a system that includes machine learning algorithms that collect and analyze the user's facial expressions and voice data to detect the user's emotional state.

[0697] The "means for adjusting the theme or style of the image or video generated by the generation means based on emotional data" is a mechanism for automatically adjusting the theme or style of the advertising material generated by the generation means based on emotional data analyzed by the emotion engine.

[0698] A "generative AI model" is an artificial intelligence model that is pre-trained and used to generate new images and videos.

[0699] The present invention provides a system that generates images and videos for advertising purposes based on text, images, and audio input by a user, and further recognizes the user's emotional data and adaptively changes the content of the generated images. A specific embodiment of the invention will be described below.

[0700] Hardware and software used

[0701] Hardware:

[0702] Smart glasses (e.g. Vuzix Blade, Nreal Light)

[0703] A device equipped with a webcam and microphone

[0704] Cloud servers (e.g. AWS EC2 instances)

[0705] software:

[0706] Frontend: Customized Web UI using React.js

[0707] Backend: Python (Flask) and TensorFlow

[0708] Generative AI models: GPT-4 and DALL-E

[0709] System Components

[0710] 1. User Interface Means:

[0711] Users use the smart glasses to input text, images, and audio using voice commands and gestures, and the glasses' camera and microphone are used to capture facial and audio data in real time.

[0712] 2. Means of transmission:

[0713] The captured data and input text, images, and audio are converted into JSON format and sent to the server as an HTTP POST request.

[0714] 3. Generation means:

[0715] The server analyzes the received data and generates new advertising images and videos based on the emotion data, using pre-trained generative AI models (GPT-4 and DALL-E).

[0716] 4. Display means:

[0717] The generated advertising images and videos are displayed in real time on the user interface, where users can check the results through the glasses' display and make edits if necessary.

[0718] 5. Emotion Engine:

[0719] The emotion engine uses machine learning algorithms to analyze a user's facial expressions and voice data to infer their emotional state, and then adjusts the theme and style of the ad material it generates based on this emotional data.

[0720] Data processing and calculation

[0721] The server analyzes the data received from the front-end and compares it with the emotional data obtained by the emotion engine. The analyzed data is input into the generative AI model to generate advertising materials. The generated materials are temporarily stored on the cloud server so that users can access them at any time.

[0722] Specific examples

[0723] For example, if a user is trying to create a TV ad for a new product, they can put on the smart glasses, say "new 4K TV," and scan an image of the product with the camera. At the same time, the emotion engine will detect that the user is smiling. Based on this information, the ad generated by the generative AI model will be tailored to a bright and cheerful theme.

[0724] Prompt Sentence Examples

[0725] Prompt 1: "Generate an ad for a new 4K TV. The user will smile."

[0726] Prompt 2: "The theme should be fun and bright colors."

[0727] This allows users to generate emotion-based personalized advertising material in real time.

[0728] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0729] Step 1:

[0730] Users wear smart glasses and input text, images, and voice using voice commands and gestures. The smart glasses' cameras and microphones automatically capture the user's facial expressions and voice, collecting the necessary data in real time. This allows the input data to be collected as text, image files, audio files, and emotional data.

[0731] Step 2:

[0732] The collected data is temporarily stored as a document in the smart glasses. The stored data is converted to JSON format and sent to the server as an HTTP POST request. Through this sending process, the server receives input data from the user interface.

[0733] Step 3:

[0734] The server analyzes the received JSON data. The analysis includes text data analysis, image and audio data preprocessing, and emotion data analysis. The results of this processing are analyzed text data, image data, audio data, and emotion metadata.

[0735] Step 4:

[0736] The server inputs the analyzed data into a generative AI model, which uses pre-trained GPT-4 and DALL-E models to generate images and videos for advertisements that reflect the user's emotional data. This process outputs optimized advertising materials.

[0737] Step 5:

[0738] The generated advertising materials are temporarily stored in the server storage, and this storage process allows users to access and download the generated materials at any time.

[0739] Step 6:

[0740] The server transmits the generated advertising images and videos in real time to the user interface, where the transmitted advertising materials are further displayed on the display of the user's smart glasses, allowing the user to check the generated results in real time.

[0741] Step 7:

[0742] Users can review the displayed ad material and, if necessary, re-edit or adjust it using voice commands or gestures. During this adjustment process, the generative AI model performs further optimization based on user feedback, and improved ad material is generated and displayed again.

[0743] The above steps result in a system that allows users to generate and edit emotion-based personalized advertising materials in real time.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] [Third embodiment]

[0748] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0749] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0750] 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).

[0751] 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.

[0752] 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.

[0753] 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).

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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."

[0760] The present invention provides a system that allows a user to input text and images, generates new advertising images and videos on a server based on the input text and images, and displays the images and videos on a user interface. The system includes a user interface means, a transmission means, a generation means, a storage means, and a display means.

[0761] User Interface Means

[0762] When a user accesses the system, they are first presented with a user interface that includes a text entry field and an image upload button. The user enters or uploads the text and images they want to use in their advertisement.

[0763] Transmission method

[0764] When the user completes the text and image input and clicks the "Generate" button, the input data is sent from the device to the server using an HTTP POST request. The sent data is in JSON format and contains information about the text and image.

[0765] generation means

[0766] The server analyzes the received request and generates new advertising images and videos based on the input data. Specifically, the server uses a pre-trained generative model to generate advertising materials that are optimal for the text and images provided by the user. This generative model is based on machine learning algorithms such as neural networks, and can generate high-quality images and videos in a short amount of time.

[0767] Preservation means

[0768] The generated images and videos are temporarily stored in the server's storage. The stored data is managed with consideration for future reuse and backup. This storage method allows users to re-acquire the advertising materials they have generated at a later date.

[0769] Display means

[0770] The generated advertising images and videos are sent back to the device and displayed on the user interface. The user can check the displayed results and download and use them as needed. If the results are not as expected, the user can modify the text or images and send a new request.

[0771] Specific examples

[0772] For example, suppose a user wants to generate advertising materials for a "summer sale." The user accesses the Web UI, enters the text "summer sale," and uploads an image of a beach. After that, the user clicks the "Generate" button, and the input information is sent to the server. The server generates advertising images and videos showing the summer sale based on the received text and images. The generated materials are temporarily saved, sent to the device, and displayed on the Web UI. The user can check the generated results and download them if they are satisfactory.

[0773] In this way, the system is designed to enable users to easily generate high-quality images and videos for advertising. The means described in this claim enable efficient creation of advertising materials while reducing time and costs.

[0774] The processing flow will be explained below.

[0775] Step 1:

[0776] Users access the Web UI and enter text and images. For example, a user can enter the text "Summer Sale" and upload an image of the product in question.

[0777] Step 2:

[0778] The user clicks the "Generate" button on the Web UI, which converts the entered text and uploaded images into JSON format.

[0779] Step 3:

[0780] The terminal sends the data converted into JSON format to the server as an HTTP POST request. The sent data includes the text and image information entered by the user.

[0781] Step 4:

[0782] The server receives the HTTP POST request, parses its contents, extracts text and image information from the request, and prepares it for passing to the generative model.

[0783] Step 5:

[0784] The server then invokes pre-trained generative models to generate images and videos for advertisements based on user input, for example using a neural network to generate images related to "summer sales."

[0785] Step 6:

[0786] The generated images and videos are temporarily stored on the server, and the path and file name of the storage destination are uniquely determined and used in the next processing step.

[0787] Step 7:

[0788] The server sends the stored images and videos to the device as an HTTP response. At this time, the sent data is treated as binary image or video data.

[0789] Step 8:

[0790] The device analyzes the HTTP response received from the server, generates images and videos from the binary data, and converts the generated data into a format that can be displayed on the user interface.

[0791] Step 9:

[0792] The generated images and videos for advertising are displayed on the user's device in a web UI, where the user can check the results and download or edit them as needed.

[0793] Step 10:

[0794] If the user is not satisfied with the results, they can modify the text or images again and send a new request to the server. This process can be repeated.

[0795] In this way, users, terminals, and servers work together to efficiently generate high-quality advertising images and videos.

[0796] Example 1

[0797] 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."

[0798] Conventional advertising material generation systems lack the means for users to quickly and easily generate high-quality images and videos for advertising. They also lack mechanisms for efficiently storing, managing, and reusing the generated advertising materials. This results in high costs and time-consuming processes.

[0799] 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.

[0800] In this invention, the server includes a display device that accepts input of text or images, a transmission device that transmits the input text or images to a processing device, a generation device that generates new audiovisual data based on the input in the processing device, a transmission device that transmits the generated audiovisual data to a user, and a display device that displays the transmitted audiovisual data on a display device. This allows users to quickly and easily generate high-quality advertising images and videos. Furthermore, by including a storage device for temporary storage, data management and reuse after generation can be efficiently performed.

[0801] A "display device" is a device that provides an interface for a user to input text and images.

[0802] A "transmitting device" is a device that has the function of transmitting input text and images to a processing device.

[0803] A "processing device" is a device that generates new audiovisual data based on input data sent by a user.

[0804] A "generator" is a device that generates new audiovisual data using a pre-trained generative algorithm.

[0805] A "storage device" is a device for temporarily storing generated audiovisual data.

[0806] "Audiovisual data" refers to digital content such as images and videos generated for advertising purposes.

[0807] A "generative algorithm" is a machine learning model or other computational method used to generate audiovisual data based on input data.

[0808] MODE FOR CARRYING OUT THE INVENTION

[0809] The present invention provides a system in which a user inputs text and images, generates new advertising images and videos on a server based on the input text and images, and displays the images and videos on a user interface. The system includes a display device, a transmission device, a generation device, a storage device, and a display device.

[0810] When a user accesses the system using a web browser, the server renders and sends to the terminal a display image that includes a text entry field and an image upload button where the user can enter promotional text, such as "Summer Sale," and upload an image to be used in the advertising materials.

[0811] Next, when the user clicks the "Generate" button, the entered text and uploaded image are packaged in JSON format and sent to the server via an HTTP POST request. This sender provides a means for passing input data to the server.

[0812] The server parses the received JSON data and activates a generator, which includes a pre-trained generative AI model (e.g., a Generative Adversarial Network (GAN)) that generates new advertising images and videos based on user input. The generative AI model is based on machine learning algorithms and can generate content quickly and with high quality.

[0813] The generated data is temporarily stored in a storage device, which is used to store the generated data and facilitate future reuse and data management.

[0814] Finally, the server reloads the generated data and sends it to the display device. The display device on the terminal receives it and displays it on the user interface. The user can check the generated audiovisual data and download it if they are satisfied. If the result is not as expected, they can modify the text and images and send a new request.

[0815] Specific examples

[0816] For example, suppose a user wants to generate advertising materials for a "Summer Sale." The user accesses the Web UI, enters the text "Summer Sale," and uploads an image of a beach. After that, the user clicks the "Generate" button, and the input is sent to the server. Based on the received text and image, the server uses a generative AI model to generate advertising images and videos showing the summer sale. This generated material is temporarily stored and eventually sent to a display device and displayed on the Web UI. The user checks the generated results and downloads them if they are satisfactory. Below is an example of a prompt:

[0817] prompt:

[0818] I want to generate an image for an advertisement. The text is "Summer Sale" and the image I want to upload is a beach photo.

[0819] In this way, this system is designed to enable users to easily generate high-quality images and videos for advertising, thereby enabling efficient creation of advertising materials while reducing time and costs.

[0820] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0821] Step 1:

[0822] User Interface Display

[0823] When a user accesses the system from a web browser, the server renders a user interface and sends it to the terminal. This user interface includes text input fields and image upload buttons, and the user inputs and uploads the text and images they want to use in the advertising materials.

[0824] Input: Access request from a web browser

[0825] Output: User interface

[0826] Step 2:

[0827] Sending input data

[0828] When the user completes the text and image input and clicks the "Generate" button, the data is packaged in JSON format and sent to the server via an HTTP POST request. The sent data includes the text data entered by the user and the image data uploaded.

[0829] Input: User-entered text and images, HTTP POST requests

[0830] Output: JSON data sent to the server side

[0831] Step 3:

[0832] Data analysis

[0833] The server parses the received JSON data, where the data stream is parsed and each field (text content, image information, etc.) is identified.

[0834] Input: JSON format text data and image data

[0835] Output: Analyzed text and image data objects

[0836] Step 4:

[0837] Creation of advertising materials

[0838] The server uses a generator to generate audiovisual data for advertising based on the text and images obtained from the analysis. The generator uses a pre-trained generative AI model to generate appropriate images and videos based on the user's input data. For example, if a user enters "summer sale" and uploads an image of a beach, the generative AI model will generate advertising materials that fit that theme.

[0839] Input: Analyzed text and image data, generative AI model

[0840] Output: Generated audiovisual data

[0841] Step 5:

[0842] Saving generated data

[0843] The server temporarily stores the generated audiovisual data in a storage device, which stores the generated data along with the date and time of generation, the user ID, and metadata of the text and images used for input.

[0844] Input: Generated audiovisual data

[0845] Output: Data stored on the storage device

[0846] Step 6:

[0847] Viewing generated data

[0848] The server reloads the saved generated data and sends it to the user interface. The display device on the terminal receives this data and displays it on the user interface. The user can check the displayed advertising images and videos and download them if necessary.

[0849] Input: Data stored on storage device, user request

[0850] Output: Audiovisual data displayed on a display device

[0851] (Application example 1)

[0852] 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."

[0853] The modern advertising industry demands the efficient and rapid generation of high-quality advertising materials. However, achieving this requires specialized skills and expensive software, which is time-consuming and costly. Furthermore, generating advertising materials requires a system that allows users to easily upload text and images and then generate, save, display, and download optimal advertising materials based on those text and images. However, current systems have difficulty meeting all of these requirements. Furthermore, a function that allows users to easily download the generated advertising materials is also required. The objective of this invention is to solve these problems.

[0854] 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.

[0855] In this invention, the server includes a user interface means for accepting input of text or images, a transmission means for transmitting the input text or images to the server, a generation means for generating new images or videos based on the input at the server, a storage means for saving the generated images or videos, a display means for displaying the transmitted images or videos on the user interface, and a download means for the user to download the generated images or videos. This enables users to easily input and upload text and images they want to use in their advertisements, and then quickly generate, save, display, and download high-quality advertising materials based on them.

[0856] "User interface means" refers to an interface through which a user inputs text and images into the system.

[0857] The "transmission means" is a means having a function for transmitting text and images input by the user to the server.

[0858] The "generation means" is a means having a function of generating a new image or video based on an input in the server.

[0859] The "storage means" is a means having a function of temporarily storing the generated image or video.

[0860] The "display means" is a means having a function of displaying the generated image or video on the user's interface.

[0861] The "downloading means" is a means that has a function for a user to download generated images or videos.

[0862] A "generative AI model" is a machine learning model that is pre-trained to generate new advertising images and videos based on text and images.

[0863] A "prompt" is an instruction given to a generative AI model in the form of text input.

[0864] The present invention provides a system that allows users to easily create high-quality images and videos for advertising and download them as needed. This system integrates a series of functions from inputting text and images to creating, saving, displaying, and downloading.

[0865] System Configuration

[0866] User Interface Means

[0867] When a user accesses the system, a user interface is displayed, which includes a text input field and an image upload button, allowing the user to input or upload the text and images they want to use in their advertisement.

[0868] Transmission method

[0869] When the user completes the text and image input and clicks the "Generate" button, the input data is sent from the device to the server using an HTTP POST request. The sent data is in JSON format and contains information about the text and image.

[0870] generation means

[0871] The server analyzes the received request and generates new images and videos for advertising based on the input data. Specifically, the server uses a pre-trained generative AI model to generate advertising materials that are optimal for the text and images provided by the user. This generative AI model is based on machine learning algorithms such as neural networks, and can generate high-quality images and videos in a short amount of time.

[0872] Preservation means

[0873] The generated images and videos are temporarily stored in the server's storage. The stored data is managed with consideration for future reuse and backup. This storage method allows users to later retrieve the advertising materials they have generated.

[0874] Display means

[0875] The generated advertising images and videos are sent back to the device and displayed on the user interface. The user can check the generated results and download and use them as needed. If the results are not as expected, the user can modify the text or images and send a new request.

[0876] Download Method

[0877] If the user is satisfied with the generated image or video, the user can download it. The downloading means provides a function for saving the generated advertising material to the terminal. This function allows the user to freely use the generated advertising material in a local environment.

[0878] Hardware and software used

[0879] Hardware: Server (CPU or GPU)

[0880] software:

[0881] Framework: Flask (Python web framework)

[0882] Model: Generative AI model (e.g. CLIP, "clip-vit-base-patch32" from HuggingFace)

[0883] Specific examples

[0884] For example, if a user wants to generate advertising material for a "Summer Sale," the user enters the following prompt text:

[0885] Example prompt sentence:

[0886] "Make your ad with beach images that are perfect for summer sales."

[0887] The user uploads a beach image along with this prompt and clicks the "Generate" button. The server analyzes the received input data and generates appropriate advertising materials using a generative AI model. The generated advertising materials are displayed in the user interface, and the user can download and use them.

[0888] In this way, the present invention is designed to enable users to easily generate high-quality images and videos for advertising, thereby enabling efficient creation of advertising materials while reducing time and costs.

[0889] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0890] Step 1:

[0891] When a user accesses the system, a user interface is displayed on the terminal.

[0892] How it works: A text entry field and an image upload button are displayed in the user interface. The user enters the text they want to use in their ad and uploads an image.

[0893] Step 2:

[0894] The user completes the text and image input and clicks the "Generate" button.

[0895] How it works: User-supplied data is packaged in JSON format and sent to the server via an HTTP POST request.

[0896] Input: Text entered by the user and images uploaded by the user.

[0897] Output: JSON formatted data sent to the server.

[0898] Step 3:

[0899] The server analyzes the received request.

[0900] How it works: The server receives an HTTP POST request and parses the JSON data contained within it, extracting text and image data.

[0901] Input: Text and image data in JSON format.

[0902] Output: Extracted text and image data.

[0903] Step 4:

[0904] The server uses the generative AI model to generate images or videos for the advertisement.

[0905] How it works: The extracted text and images are fed into a generative AI model, which then generates the optimal advertising materials. High-quality images and videos are generated in a short time.

[0906] Input: Extracted text and image data.

[0907] Output: The generated advertising image or video.

[0908] Step 5:

[0909] The generated images or videos are temporarily stored on the server.

[0910] How it works: The generated ad material is saved in server storage, allowing for future reuse and backup.

[0911] Input: Generated image or video for advertising.

[0912] Output: Materials stored in the server's storage.

[0913] Step 6:

[0914] The saved image or video is sent to the user's device.

[0915] How it works: The server sends the generated ad material to the user's device as an HTTP response. The sent data is then packaged in JSON format again.

[0916] Input: Materials stored in the server's storage.

[0917] Output: The advertising image or video sent to the user's device.

[0918] Step 7:

[0919] The material will be displayed on the user's device and can be checked.

[0920] Behavior: The user interface displays the material for review and allows the user to download the generated results, if desired.

[0921] Input: Advertising image or video sent to the user's device.

[0922] Output: Advertising images or videos displayed in the user interface.

[0923] Step 8:

[0924] The user downloads the generated material.

[0925] How it works: If the user is satisfied with the generated ad material, they can download it. Once the download process is complete, the material will be saved to the user's local storage.

[0926] Input: The displayed advertising image or video.

[0927] Output: Ad images or videos stored in the user's local storage.

[0928] 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.

[0929] The present invention provides a system that generates images and videos for advertising purposes based on text and images entered by a user, and further recognizes the user's emotional data and adaptively changes the content of the generated images. The system includes a user interface, a transmission means, a generation means, a storage means, a display means, and an emotion engine.

[0930] User Interface Means

[0931] Users access a web UI to input or upload the text and images they want to use in their ads, and the app incorporates an emotion engine that reads the user's facial expressions and voice in real time via a webcam and microphone.

[0932] Transmission method

[0933] The text, images, and even emotion data entered by the user are converted into JSON format and sent to the server as an HTTP POST request. The emotion data is treated as metadata that indicates the user's emotional state.

[0934] generation means

[0935] The server analyzes the received request and generates new images and videos for advertising based not only on text and image data but also on emotional data obtained from the emotion engine. The emotion engine detects the user's emotional state from their facial expressions and voice and uses this information to adjust the theme, color, and style of the generated content.

[0936] Preservation means

[0937] The generated images and videos are temporarily stored in the server storage, allowing the user to retrieve the generated images later.

[0938] Display means

[0939] The generated images and videos for advertising are sent from the server to the device and displayed on the Web UI. Users can check the results in real time and download or edit them as needed.

[0940] Emotion Engine

[0941] The emotion engine captures the user's facial expressions with a webcam and uses machine learning algorithms to analyze their emotions in real time. It also performs voice analysis to determine their emotional state from the tone and speed of their voice. This emotional data is reflected in the generated advertising materials, so content optimized for the user's current emotions is generated.

[0942] Specific examples

[0943] For example, suppose a user is trying to create an ad for a "Christmas sale." The user enters the text "Christmas sale" into the web UI and uploads a Christmas-related image. The emotion engine then captures the user's facial expressions and analyzes their emotions from their voice. If the user appears happy, the emotion engine will reflect a bright and cheerful theme in the ad images and videos it generates. Conversely, if the user appears calm, the generated content will be adjusted accordingly.

[0944] In this way, this system can generate high-quality advertising images and videos that incorporate the user's emotions, making it possible to provide more personalized advertising materials to users.

[0945] The processing flow will be explained below.

[0946] Step 1:

[0947] A user accesses the web UI and enters text or uploads an image. For example, a user enters the text "Christmas Sale" and uploads a Christmas-related image.

[0948] Step 2:

[0949] The user's device captures the user's facial expressions and voice through a webcam and microphone, and analyzes the emotional data in real time. This analysis is performed by an emotion engine, and the user's emotional state is obtained as numerical data.

[0950] Step 3:

[0951] When the user clicks the "Generate" button, the device converts the entered text, uploaded image, and analyzed emotion data into JSON format and sends it to the server.

[0952] Step 4:

[0953] The server receives the HTTP POST request and parses its contents, extracting text, images, and sentiment data from the request and preparing them for passing to the generative model.

[0954] Step 5:

[0955] The server calls a pre-trained generative model to generate images and videos for advertising based on the user's input data and emotional data. For example, if the user expresses a happy emotion, the generative model will reflect a bright and cheerful theme.

[0956] Step 6:

[0957] The generated images and videos are temporarily stored on the server, and the path and file name of the storage destination are uniquely determined and used in the next processing step.

[0958] Step 7:

[0959] The server sends the stored images and videos to the device as an HTTP response. At this time, the sent data is treated as binary image or video data.

[0960] Step 8:

[0961] The device analyzes the HTTP response received from the server, generates images and videos from the binary data, and converts the generated data into a format that can be displayed on the user interface.

[0962] Step 9:

[0963] The generated images and videos for advertising are displayed on the user's device via a web UI, allowing the user to check the results in real time and download or edit them as needed.

[0964] Step 10:

[0965] If the user is not satisfied with the results, they can modify the text or images again and send a new request to the server. This process can be repeated.

[0966] In this way, the user, terminal, server, and emotion engine work together to generate highly personalized advertising images and videos.

[0967] Example 2

[0968] 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."

[0969] Conventional systems have traditionally generated advertising content without considering the user's emotional state, making it difficult to generate advertising materials that match the user's desired mood and tone. Furthermore, the lack of a mechanism for incorporating user feedback in real time makes it difficult to maximize advertising effectiveness.

[0970] 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.

[0971] In this invention, the server comprises: an input device means for accepting input of text or images;

[0972] Emotion analysis means that reads the user's facial expressions and voice in real time;

[0973] a transmitting device means for transmitting the input text, image, and emotion data to a server;

[0974] a content generation means in the server for generating new images or videos based on input text, images, and emotion data;

[0975] a storage means for temporarily storing the generated image or video;

[0976] a transmitting device means for transmitting the stored images or videos to a user;

[0977] a display device for displaying the transmitted image or video;

[0978] This makes it possible to generate advertising content that is optimized for user emotions and reflect feedback in real time.

[0979] "Text" is character string information that a user inputs to create advertising content.

[0980] "Image" means visual information uploaded by a user to create advertising content.

[0981] "Input device means" refers to an interface that allows a user to input text and images. Specifically, it includes a Web UI that is used via a browser.

[0982] The "emotion analysis means" is a device that reads the user's facial expressions and voice in real time, and analyzes this data to determine the user's emotional state.

[0983] "Transmission device means" refers to a device for transmitting input text, images, and emotion data to a server, mainly using HTTP protocol and REST API.

[0984] A "server" is a central processing unit that generates new images and videos based on the data it receives.

[0985] "Content generation means" means a device that generates new images or videos based on input text, images, and emotion data within the server, utilizing a generative AI model.

[0986] A "generative AI model" is a pre-trained machine learning model used to generate images and videos. Examples include Generative Adversarial Networks (GANs) and CLIP.

[0987] "Storage means" refers to a device for temporarily storing the generated images or videos. Cloud storage is typically used.

[0988] The "transmitting device means" is a device for transmitting the generated image or video to the user's terminal.

[0989] "Display device means" means a device for displaying the generated images or videos on a user interface. Display technology such as HTML5 is used.

[0990] "User" means a person who uses the system to create advertising content.

[0991] The present invention provides a system for generating images and videos for advertising purposes based on text and images entered by a user and emotion data acquired in real time. The system includes an input device, emotion analysis means, transmission device, content generation means, storage means, transmission device means, and display device means.

[0992] input device means

[0993] Users access the Web UI through a browser and input or upload the text and images they want to use in their ads. Specifically, an interface using HTML5 and JavaScript is used, allowing users to easily provide text and images to the system.

[0994] Emotion analysis means

[0995] The Web UI is equipped with a camera and microphone to capture the user's facial expressions and voice in real time. The emotion analysis tool uses data obtained from these input devices to determine the user's emotional state. This analysis uses libraries such as OpenCV and Dlib and applies machine learning algorithms.

[0996] Transmitter means

[0997] The device converts the text, image, and emotion data entered by the user into JSON format and sends it to the server as an HTTP POST request using the HTTP protocol and REST API, allowing the server to receive all the necessary information comprehensively.

[0998] Content Creation Methods

[0999] The server uses the received data to generate new advertising images and videos using text, images, and emotion data. A pre-trained generative AI model, such as GAN (Generative Adversarial Networks) or CLIP, is used for generation. The generative AI model is implemented using machine learning libraries such as TensorFlow and PyTorch, and analyzes the received data and adaptively adjusts the generated content.

[1000] storage means

[1001] The server temporarily stores the generated images and videos in cloud storage, such as AWS S3 or Google Cloud Storage, and manages the stored data so that users can access and retrieve them later.

[1002] Transmitter means

[1003] The server sends the generated advertising images and videos to the user's device, allowing the user to check the results in real time. Communication is via the HTTP protocol, and data is sent in JSON format.

[1004] display means

[1005] The device displays images and videos sent from the server on the Web UI. <video>Tags and Tags are used, and users can review the generated content and download or further edit it if necessary.

[1006] Specific examples

[1007] For example, if a user is trying to create an ad for "Christmas Sale," they enter the text "Christmas Sale" into the Web UI and upload a Christmas-related image. At that time, the emotion engine captures the user's facial expressions and analyzes emotions from their voice. If the user seems happy, the emotion engine will reflect a bright and cheerful theme in the ad images and videos it generates. Below is an example of a prompt sentence:

[1008] Example prompt sentence:

[1009] "Generate an image to advertise a Christmas sale. The user's emotional state seems happy."

[1010] In this way, this system can generate high-quality advertising images and videos that incorporate the user's emotions, making it possible to provide more personalized advertising materials to users.

[1011] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1012] Step 1:

[1013] Users access the Web UI through a browser and enter or upload the text and images they want to use in their ads. The entered text and images are sent to the server through form elements in the Web UI. The input data is mainly written in HTML5 and JavaScript.

[1014] Input: Text input and image upload

[1015] Output: Text and image input data as form data

[1016] Step 2:

[1017] The user's device activates a webcam and microphone to capture the user's facial expressions and voice, thereby obtaining the user's emotional data in real time. Libraries such as OpenCV and Dlib are used for emotion analysis.

[1018] Input: Real-time facial image and audio data

[1019] Output: Captured emotion data

[1020] Step 3:

[1021] The device converts the input text, image, and emotion data into JSON format, which is then ready to be sent to the server.

[1022] Input: Text, images, and captured emotion data

[1023] Output: JSON format data

[1024] Step 4:

[1025] The device sends the generated JSON data to the server as an HTTP POST request, using the HTTP protocol and the REST API.

[1026] Input: JSON format data

[1027] Output: Data sent to the server

[1028] Step 5:

[1029] The server parses the JSON data of the received HTTP POST request using the Python standard library json to extract text data, image data, and emotion data.

[1030] Input: JSON format data

[1031] Output: Extracted text, images, and sentiment data

[1032] Step 6:

[1033] The server then uses the extracted data to generate new images and videos using generative AI models, such as GAN and CLIP, using TensorFlow and PyTorch. The generative AI model adjusts the theme, color, and style of the generated content based on the emotion data.

[1034] Input: Text, image, and sentiment data

[1035] Output: The generated image or video

[1036] Step 7:

[1037] The server temporarily stores the generated images and videos for advertising in cloud storage, using AWS S3 or Google Cloud Storage. The stored data is managed so that users can access and retrieve it later.

[1038] Input: Generated images or videos

[1039] Output: Snapshot image or video

[1040] Step 8:

[1041] The server sends the generated advertising images and videos to the user's device as an HTTP response, using the HTTP protocol for transfer.

[1042] Input: Generated images or videos

[1043] Output: Data sent to the user's terminal

[1044] Step 9:

[1045] The user's device displays the received images and videos on the Web UI. <video>Tags and Tags are used, and users can review the generated content and download or further edit it if necessary.

[1046] Input: Image or video sent from the server

[1047] Output: Image or video displayed on the Web UI

[1048] (Application example 2)

[1049] 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."

[1050] Conventional ad generation systems generate ad materials from text and images based on user input, but it is difficult to generate personalized ad materials that reflect the user's emotional state. Furthermore, since it is not possible to check and adjust the generated results in real time, there is a problem that it is difficult to increase user satisfaction.

[1051] 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.

[1052] In this invention, the server includes a user interface means for accepting input of text, images, and voice, a transmission means for transmitting the input text, images, voice, and emotion data to the server, a generation means for generating new images or videos based on the input in the server, a transmission means for transmitting the generated images or videos to the user, a display means for displaying the transmitted images or videos on the user interface, and a means for adjusting the theme and style of the images or videos generated by the generation means based on the emotion data, including an emotion engine for collecting and analyzing user emotion data. This enables the generation of personalized advertising materials that reflect the user's emotional state in real time.

[1053] The "user interface means for accepting input of text, images, and voice" is an interface for a user to input text, images, and voice to be used in creating advertising materials.

[1054] The "transmission means for transmitting input text, image, voice, and emotion data to a server" is a means for transmitting data and emotion data input by a user to a server.

[1055] The "generation means" is a mechanism that generates new images and videos for advertising based on data input to the server.

[1056] The "display means" is a means for displaying the generated advertising images and videos on the user interface.

[1057] The "emotion engine" is a system that includes machine learning algorithms that collect and analyze the user's facial expressions and voice data to detect the user's emotional state.

[1058] The "means for adjusting the theme or style of the image or video generated by the generation means based on emotional data" is a mechanism for automatically adjusting the theme or style of the advertising material generated by the generation means based on emotional data analyzed by the emotion engine.

[1059] A "generative AI model" is an artificial intelligence model that is pre-trained and used to generate new images and videos.

[1060] The present invention provides a system that generates images and videos for advertising purposes based on text, images, and audio input by a user, and further recognizes the user's emotional data and adaptively changes the content of the generated images. A specific embodiment of the invention will be described below.

[1061] Hardware and software used

[1062] Hardware:

[1063] Smart glasses (e.g. Vuzix Blade, Nreal Light)

[1064] A device equipped with a webcam and microphone

[1065] Cloud servers (e.g. AWS EC2 instances)

[1066] software:

[1067] Frontend: Customized Web UI using React.js

[1068] Backend: Python (Flask) and TensorFlow

[1069] Generative AI models: GPT-4 and DALL-E

[1070] System Components

[1071] 1. User Interface Means:

[1072] Users use the smart glasses to input text, images, and audio using voice commands and gestures, and the glasses' camera and microphone are used to capture facial and audio data in real time.

[1073] 2. Means of transmission:

[1074] The captured data and input text, images, and audio are converted into JSON format and sent to the server as an HTTP POST request.

[1075] 3. Generation means:

[1076] The server analyzes the received data and generates new advertising images and videos based on the emotion data, using pre-trained generative AI models (GPT-4 and DALL-E).

[1077] 4. Display means:

[1078] The generated advertising images and videos are displayed in real time on the user interface, where users can check the results through the glasses' display and make edits if necessary.

[1079] 5. Emotion Engine:

[1080] The emotion engine uses machine learning algorithms to analyze a user's facial expressions and voice data to infer their emotional state, and then adjusts the theme and style of the ad material it generates based on this emotional data.

[1081] Data processing and calculation

[1082] The server analyzes the data received from the front-end and compares it with the emotional data obtained by the emotion engine. The analyzed data is input into the generative AI model to generate advertising materials. The generated materials are temporarily stored on the cloud server so that users can access them at any time.

[1083] Specific examples

[1084] For example, if a user is trying to create a TV ad for a new product, they can put on the smart glasses, say "new 4K TV," and scan an image of the product with the camera. At the same time, the emotion engine will detect that the user is smiling. Based on this information, the ad generated by the generative AI model will be tailored to a bright and cheerful theme.

[1085] Prompt Sentence Examples

[1086] Prompt 1: "Generate an ad for a new 4K TV. The user will smile."

[1087] Prompt 2: "The theme should be fun and bright colors."

[1088] This allows users to generate emotion-based personalized advertising material in real time.

[1089] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1090] Step 1:

[1091] Users wear smart glasses and input text, images, and voice using voice commands and gestures. The smart glasses' cameras and microphones automatically capture the user's facial expressions and voice, collecting the necessary data in real time. This allows the input data to be collected as text, image files, audio files, and emotional data.

[1092] Step 2:

[1093] The collected data is temporarily stored as a document in the smart glasses. The stored data is converted to JSON format and sent to the server as an HTTP POST request. Through this sending process, the server receives input data from the user interface.

[1094] Step 3:

[1095] The server analyzes the received JSON data. The analysis includes text data analysis, image and audio data preprocessing, and emotion data analysis. The results of this processing are analyzed text data, image data, audio data, and emotion metadata.

[1096] Step 4:

[1097] The server inputs the analyzed data into a generative AI model, which uses pre-trained GPT-4 and DALL-E models to generate images and videos for advertisements that reflect the user's emotional data. This process outputs optimized advertising materials.

[1098] Step 5:

[1099] The generated advertising materials are temporarily stored in the server storage, and this storage process allows users to access and download the generated materials at any time.

[1100] Step 6:

[1101] The server transmits the generated advertising images and videos in real time to the user interface, where the transmitted advertising materials are further displayed on the display of the user's smart glasses, allowing the user to check the generated results in real time.

[1102] Step 7:

[1103] Users can review the displayed ad material and, if necessary, re-edit or adjust it using voice commands or gestures. During this adjustment process, the generative AI model performs further optimization based on user feedback, and improved ad material is generated and displayed again.

[1104] The above steps result in a system that allows users to generate and edit emotion-based personalized advertising materials in real time.

[1105] 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.

[1106] 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.

[1107] 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.

[1108] [Fourth embodiment]

[1109] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1110] 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.

[1111] 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).

[1112] 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.

[1113] 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.

[1114] 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).

[1115] 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.

[1116] 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.

[1117] 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.

[1118] 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.

[1119] 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.

[1120] 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.

[1121] 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."

[1122] The present invention provides a system that allows a user to input text and images, generates new advertising images and videos on a server based on the input text and images, and displays the images and videos on a user interface. The system includes a user interface means, a transmission means, a generation means, a storage means, and a display means.

[1123] User Interface Means

[1124] When a user accesses the system, they are first presented with a user interface that includes a text entry field and an image upload button. The user enters or uploads the text and images they want to use in their advertisement.

[1125] Transmission method

[1126] When the user completes the text and image input and clicks the "Generate" button, the input data is sent from the device to the server using an HTTP POST request. The sent data is in JSON format and contains information about the text and image.

[1127] generation means

[1128] The server analyzes the received request and generates new advertising images and videos based on the input data. Specifically, the server uses a pre-trained generative model to generate advertising materials that are optimal for the text and images provided by the user. This generative model is based on machine learning algorithms such as neural networks, and can generate high-quality images and videos in a short amount of time.

[1129] Preservation means

[1130] The generated images and videos are temporarily stored in the server's storage. The stored data is managed with consideration for future reuse and backup. This storage method allows users to re-acquire the advertising materials they have generated at a later date.

[1131] Display means

[1132] The generated advertising images and videos are sent back to the device and displayed on the user interface. The user can check the displayed results and download and use them as needed. If the results are not as expected, the user can modify the text or images and send a new request.

[1133] Specific examples

[1134] For example, suppose a user wants to generate advertising materials for a "summer sale." The user accesses the Web UI, enters the text "summer sale," and uploads an image of a beach. After that, the user clicks the "Generate" button, and the input information is sent to the server. The server generates advertising images and videos showing the summer sale based on the received text and images. The generated materials are temporarily saved, sent to the device, and displayed on the Web UI. The user can check the generated results and download them if they are satisfactory.

[1135] In this way, the system is designed to enable users to easily generate high-quality images and videos for advertising. The means described in this claim enable efficient creation of advertising materials while reducing time and costs.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] Users access the Web UI and enter text and images. For example, a user can enter the text "Summer Sale" and upload an image of the product in question.

[1139] Step 2:

[1140] The user clicks the "Generate" button on the Web UI, which converts the entered text and uploaded images into JSON format.

[1141] Step 3:

[1142] The terminal sends the data converted into JSON format to the server as an HTTP POST request. The sent data includes the text and image information entered by the user.

[1143] Step 4:

[1144] The server receives the HTTP POST request, parses its contents, extracts text and image information from the request, and prepares it for passing to the generative model.

[1145] Step 5:

[1146] The server then invokes pre-trained generative models to generate images and videos for advertisements based on user input, for example using a neural network to generate images related to "summer sales."

[1147] Step 6:

[1148] The generated images and videos are temporarily stored on the server, and the path and file name of the storage destination are uniquely determined and used in the next processing step.

[1149] Step 7:

[1150] The server sends the stored images and videos to the device as an HTTP response. At this time, the sent data is treated as binary image or video data.

[1151] Step 8:

[1152] The device analyzes the HTTP response received from the server, generates images and videos from the binary data, and converts the generated data into a format that can be displayed on the user interface.

[1153] Step 9:

[1154] The generated images and videos for advertising are displayed on the user's device in a web UI, where the user can check the results and download or edit them as needed.

[1155] Step 10:

[1156] If the user is not satisfied with the results, they can modify the text or images again and send a new request to the server. This process can be repeated.

[1157] In this way, users, terminals, and servers work together to efficiently generate high-quality advertising images and videos.

[1158] Example 1

[1159] 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."

[1160] Conventional advertising material generation systems lack the means for users to quickly and easily generate high-quality images and videos for advertising. They also lack mechanisms for efficiently storing, managing, and reusing the generated advertising materials. This results in high costs and time-consuming processes.

[1161] 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.

[1162] In this invention, the server includes a display device that accepts input of text or images, a transmission device that transmits the input text or images to a processing device, a generation device that generates new audiovisual data based on the input in the processing device, a transmission device that transmits the generated audiovisual data to a user, and a display device that displays the transmitted audiovisual data on a display device. This allows users to quickly and easily generate high-quality advertising images and videos. Furthermore, by including a storage device for temporary storage, data management and reuse after generation can be efficiently performed.

[1163] A "display device" is a device that provides an interface for a user to input text and images.

[1164] A "transmitting device" is a device that has the function of transmitting input text and images to a processing device.

[1165] A "processing device" is a device that generates new audiovisual data based on input data sent by a user.

[1166] A "generator" is a device that generates new audiovisual data using a pre-trained generative algorithm.

[1167] A "storage device" is a device for temporarily storing generated audiovisual data.

[1168] "Audiovisual data" refers to digital content such as images and videos generated for advertising purposes.

[1169] A "generative algorithm" is a machine learning model or other computational method used to generate audiovisual data based on input data.

[1170] MODE FOR CARRYING OUT THE INVENTION

[1171] The present invention provides a system in which a user inputs text and images, generates new advertising images and videos on a server based on the input text and images, and displays the images and videos on a user interface. The system includes a display device, a transmission device, a generation device, a storage device, and a display device.

[1172] When a user accesses the system using a web browser, the server renders and sends to the terminal a display image that includes a text entry field and an image upload button where the user can enter promotional text, such as "Summer Sale," and upload an image to be used in the advertising materials.

[1173] Next, when the user clicks the "Generate" button, the entered text and uploaded image are packaged in JSON format and sent to the server via an HTTP POST request. This sender provides a means for passing input data to the server.

[1174] The server parses the received JSON data and activates a generator, which includes a pre-trained generative AI model (e.g., a Generative Adversarial Network (GAN)) that generates new advertising images and videos based on user input. The generative AI model is based on machine learning algorithms and can generate content quickly and with high quality.

[1175] The generated data is temporarily stored in a storage device, which is used to store the generated data and facilitate future reuse and data management.

[1176] Finally, the server reloads the generated data and sends it to the display device. The display device on the terminal receives it and displays it on the user interface. The user can check the generated audiovisual data and download it if they are satisfied. If the result is not as expected, they can modify the text and images and send a new request.

[1177] Specific examples

[1178] For example, suppose a user wants to generate advertising materials for a "Summer Sale." The user accesses the Web UI, enters the text "Summer Sale," and uploads an image of a beach. After that, the user clicks the "Generate" button, and the input is sent to the server. Based on the received text and image, the server uses a generative AI model to generate advertising images and videos showing the summer sale. This generated material is temporarily stored and eventually sent to a display device and displayed on the Web UI. The user checks the generated results and downloads them if they are satisfactory. Below is an example of a prompt:

[1179] prompt:

[1180] I want to generate an image for an advertisement. The text is "Summer Sale" and the image I want to upload is a beach photo.

[1181] In this way, this system is designed to enable users to easily generate high-quality images and videos for advertising, thereby enabling efficient creation of advertising materials while reducing time and costs.

[1182] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1183] Step 1:

[1184] User Interface Display

[1185] When a user accesses the system from a web browser, the server renders a user interface and sends it to the terminal. This user interface includes text input fields and image upload buttons, and the user inputs and uploads the text and images they want to use in the advertising materials.

[1186] Input: Access request from a web browser

[1187] Output: User interface

[1188] Step 2:

[1189] Sending input data

[1190] When the user completes the text and image input and clicks the "Generate" button, the data is packaged in JSON format and sent to the server via an HTTP POST request. The sent data includes the text data entered by the user and the image data uploaded.

[1191] Input: User-entered text and images, HTTP POST requests

[1192] Output: JSON data sent to the server side

[1193] Step 3:

[1194] Data analysis

[1195] The server parses the received JSON data, where the data stream is parsed and each field (text content, image information, etc.) is identified.

[1196] Input: JSON format text data and image data

[1197] Output: Analyzed text and image data objects

[1198] Step 4:

[1199] Creation of advertising materials

[1200] The server uses a generator to generate audiovisual data for advertising based on the text and images obtained from the analysis. The generator uses a pre-trained generative AI model to generate appropriate images and videos based on the user's input data. For example, if a user enters "summer sale" and uploads an image of a beach, the generative AI model will generate advertising materials that fit that theme.

[1201] Input: Analyzed text and image data, generative AI model

[1202] Output: Generated audiovisual data

[1203] Step 5:

[1204] Saving generated data

[1205] The server temporarily stores the generated audiovisual data in a storage device, which stores the generated data along with the date and time of generation, the user ID, and metadata of the text and images used for input.

[1206] Input: Generated audiovisual data

[1207] Output: Data stored on the storage device

[1208] Step 6:

[1209] Viewing generated data

[1210] The server reloads the saved generated data and sends it to the user interface. The display device on the terminal receives this data and displays it on the user interface. The user can check the displayed advertising images and videos and download them if necessary.

[1211] Input: Data stored on storage device, user request

[1212] Output: Audiovisual data displayed on a display device

[1213] (Application example 1)

[1214] 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."

[1215] The modern advertising industry demands the efficient and rapid generation of high-quality advertising materials. However, achieving this requires specialized skills and expensive software, which is time-consuming and costly. Furthermore, generating advertising materials requires a system that allows users to easily upload text and images and then generate, save, display, and download optimal advertising materials based on those text and images. However, current systems have difficulty meeting all of these requirements. Furthermore, a function that allows users to easily download the generated advertising materials is also required. The objective of this invention is to solve these problems.

[1216] 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.

[1217] In this invention, the server includes a user interface means for accepting input of text or images, a transmission means for transmitting the input text or images to the server, a generation means for generating new images or videos based on the input at the server, a storage means for saving the generated images or videos, a display means for displaying the transmitted images or videos on the user interface, and a download means for the user to download the generated images or videos. This enables users to easily input and upload text and images they want to use in their advertisements, and then quickly generate, save, display, and download high-quality advertising materials based on them.

[1218] "User interface means" refers to an interface through which a user inputs text and images into the system.

[1219] The "transmission means" is a means having a function for transmitting text and images input by the user to the server.

[1220] The "generation means" is a means having a function of generating a new image or video based on an input in the server.

[1221] The "storage means" is a means having a function of temporarily storing the generated image or video.

[1222] The "display means" is a means having a function of displaying the generated image or video on the user's interface.

[1223] The "downloading means" is a means that has a function for a user to download generated images or videos.

[1224] A "generative AI model" is a machine learning model that is pre-trained to generate new advertising images and videos based on text and images.

[1225] A "prompt" is an instruction given to a generative AI model in the form of text input.

[1226] The present invention provides a system that allows users to easily create high-quality images and videos for advertising and download them as needed. This system integrates a series of functions from inputting text and images to creating, saving, displaying, and downloading.

[1227] System Configuration

[1228] User Interface Means

[1229] When a user accesses the system, a user interface is displayed, which includes a text input field and an image upload button, allowing the user to input or upload the text and images they want to use in their advertisement.

[1230] Transmission method

[1231] When the user completes the text and image input and clicks the "Generate" button, the input data is sent from the device to the server using an HTTP POST request. The sent data is in JSON format and contains information about the text and image.

[1232] generation means

[1233] The server analyzes the received request and generates new images and videos for advertising based on the input data. Specifically, the server uses a pre-trained generative AI model to generate advertising materials that are optimal for the text and images provided by the user. This generative AI model is based on machine learning algorithms such as neural networks, and can generate high-quality images and videos in a short amount of time.

[1234] Preservation means

[1235] The generated images and videos are temporarily stored in the server's storage. The stored data is managed with consideration for future reuse and backup. This storage method allows users to later retrieve the advertising materials they have generated.

[1236] Display means

[1237] The generated advertising images and videos are sent back to the device and displayed on the user interface. The user can check the generated results and download and use them as needed. If the results are not as expected, the user can modify the text or images and send a new request.

[1238] Download Method

[1239] If the user is satisfied with the generated image or video, the user can download it. The downloading means provides a function for saving the generated advertising material to the terminal. This function allows the user to freely use the generated advertising material in a local environment.

[1240] Hardware and software used

[1241] Hardware: Server (CPU or GPU)

[1242] software:

[1243] Framework: Flask (Python web framework)

[1244] Model: Generative AI model (e.g. CLIP, "clip-vit-base-patch32" from HuggingFace)

[1245] Specific examples

[1246] For example, if a user wants to generate advertising material for a "Summer Sale," the user enters the following prompt text:

[1247] Example prompt sentence:

[1248] "Make your ad with beach images that are perfect for summer sales."

[1249] The user uploads a beach image along with this prompt and clicks the "Generate" button. The server analyzes the received input data and generates appropriate advertising materials using a generative AI model. The generated advertising materials are displayed in the user interface, and the user can download and use them.

[1250] In this way, the present invention is designed to enable users to easily generate high-quality images and videos for advertising, thereby enabling efficient creation of advertising materials while reducing time and costs.

[1251] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1252] Step 1:

[1253] When a user accesses the system, a user interface is displayed on the terminal.

[1254] How it works: A text entry field and an image upload button are displayed in the user interface. The user enters the text they want to use in their ad and uploads an image.

[1255] Step 2:

[1256] The user completes the text and image input and clicks the "Generate" button.

[1257] How it works: User-supplied data is packaged in JSON format and sent to the server via an HTTP POST request.

[1258] Input: Text entered by the user and images uploaded by the user.

[1259] Output: JSON formatted data sent to the server.

[1260] Step 3:

[1261] The server analyzes the received request.

[1262] How it works: The server receives an HTTP POST request and parses the JSON data contained within it, extracting text and image data.

[1263] Input: Text and image data in JSON format.

[1264] Output: Extracted text and image data.

[1265] Step 4:

[1266] The server uses the generative AI model to generate images or videos for the advertisement.

[1267] How it works: The extracted text and images are fed into a generative AI model, which then generates the optimal advertising materials. High-quality images and videos are generated in a short time.

[1268] Input: Extracted text and image data.

[1269] Output: The generated advertising image or video.

[1270] Step 5:

[1271] The generated images or videos are temporarily stored on the server.

[1272] How it works: The generated ad material is saved in server storage, allowing for future reuse and backup.

[1273] Input: Generated image or video for advertising.

[1274] Output: Materials stored in the server's storage.

[1275] Step 6:

[1276] The saved image or video is sent to the user's device.

[1277] How it works: The server sends the generated ad material to the user's device as an HTTP response. The sent data is then packaged in JSON format again.

[1278] Input: Materials stored in the server's storage.

[1279] Output: The advertising image or video sent to the user's device.

[1280] Step 7:

[1281] The material will be displayed on the user's device and can be checked.

[1282] Behavior: The user interface displays the material for review and allows the user to download the generated results, if desired.

[1283] Input: Advertising image or video sent to the user's device.

[1284] Output: Advertising images or videos displayed in the user interface.

[1285] Step 8:

[1286] The user downloads the generated material.

[1287] How it works: If the user is satisfied with the generated ad material, they can download it. Once the download process is complete, the material will be saved to the user's local storage.

[1288] Input: The displayed advertising image or video.

[1289] Output: Ad images or videos stored in the user's local storage.

[1290] 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.

[1291] The present invention provides a system that generates images and videos for advertising purposes based on text and images entered by a user, and further recognizes the user's emotional data and adaptively changes the content of the generated images. The system includes a user interface, a transmission means, a generation means, a storage means, a display means, and an emotion engine.

[1292] User Interface Means

[1293] Users access a web UI to input or upload the text and images they want to use in their ads, and the app incorporates an emotion engine that reads the user's facial expressions and voice in real time via a webcam and microphone.

[1294] Transmission method

[1295] The text, images, and even emotion data entered by the user are converted into JSON format and sent to the server as an HTTP POST request. The emotion data is treated as metadata that indicates the user's emotional state.

[1296] generation means

[1297] The server analyzes the received request and generates new images and videos for advertising based not only on text and image data but also on emotional data obtained from the emotion engine. The emotion engine detects the user's emotional state from their facial expressions and voice and uses this information to adjust the theme, color, and style of the generated content.

[1298] Preservation means

[1299] The generated images and videos are temporarily stored in the server storage, allowing the user to retrieve the generated images later.

[1300] Display means

[1301] The generated images and videos for advertising are sent from the server to the device and displayed on the Web UI. Users can check the results in real time and download or edit them as needed.

[1302] Emotion Engine

[1303] The emotion engine captures the user's facial expressions with a webcam and uses machine learning algorithms to analyze their emotions in real time. It also performs voice analysis to determine their emotional state from the tone and speed of their voice. This emotional data is reflected in the generated advertising materials, so content optimized for the user's current emotions is generated.

[1304] Specific examples

[1305] For example, suppose a user is trying to create an ad for a "Christmas sale." The user enters the text "Christmas sale" into the web UI and uploads a Christmas-related image. The emotion engine then captures the user's facial expressions and analyzes their emotions from their voice. If the user appears happy, the emotion engine will reflect a bright and cheerful theme in the ad images and videos it generates. Conversely, if the user appears calm, the generated content will be adjusted accordingly.

[1306] In this way, this system can generate high-quality advertising images and videos that incorporate the user's emotions, making it possible to provide more personalized advertising materials to users.

[1307] The processing flow will be explained below.

[1308] Step 1:

[1309] A user accesses the web UI and enters text or uploads an image. For example, a user enters the text "Christmas Sale" and uploads a Christmas-related image.

[1310] Step 2:

[1311] The user's device captures the user's facial expressions and voice through a webcam and microphone, and analyzes the emotional data in real time. This analysis is performed by an emotion engine, and the user's emotional state is obtained as numerical data.

[1312] Step 3:

[1313] When the user clicks the "Generate" button, the device converts the entered text, uploaded image, and analyzed emotion data into JSON format and sends it to the server.

[1314] Step 4:

[1315] The server receives the HTTP POST request and parses its contents, extracting text, images, and sentiment data from the request and preparing them for passing to the generative model.

[1316] Step 5:

[1317] The server calls a pre-trained generative model to generate images and videos for advertising based on the user's input data and emotional data. For example, if the user expresses a happy emotion, the generative model will reflect a bright and cheerful theme.

[1318] Step 6:

[1319] The generated images and videos are temporarily stored on the server, and the path and file name of the storage destination are uniquely determined and used in the next processing step.

[1320] Step 7:

[1321] The server sends the stored images and videos to the device as an HTTP response. At this time, the sent data is treated as binary image or video data.

[1322] Step 8:

[1323] The device analyzes the HTTP response received from the server, generates images and videos from the binary data, and converts the generated data into a format that can be displayed on the user interface.

[1324] Step 9:

[1325] The generated images and videos for advertising are displayed on the user's device via a web UI, allowing the user to check the results in real time and download or edit them as needed.

[1326] Step 10:

[1327] If the user is not satisfied with the results, they can modify the text or images again and send a new request to the server. This process can be repeated.

[1328] In this way, the user, terminal, server, and emotion engine work together to generate highly personalized advertising images and videos.

[1329] Example 2

[1330] 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."

[1331] Conventional systems have traditionally generated advertising content without considering the user's emotional state, making it difficult to generate advertising materials that match the user's desired mood and tone. Furthermore, the lack of a mechanism for incorporating user feedback in real time makes it difficult to maximize advertising effectiveness.

[1332] 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.

[1333] In this invention, the server comprises: an input device means for accepting input of text or images;

[1334] Emotion analysis means that reads the user's facial expressions and voice in real time;

[1335] a transmitting device means for transmitting the input text, image, and emotion data to a server;

[1336] a content generation means in the server for generating new images or videos based on input text, images, and emotion data;

[1337] a storage means for temporarily storing the generated image or video;

[1338] a transmitting device means for transmitting the stored images or videos to a user;

[1339] a display device for displaying the transmitted image or video;

[1340] This makes it possible to generate advertising content that is optimized for user emotions and reflect feedback in real time.

[1341] "Text" is character string information that a user inputs to create advertising content.

[1342] "Image" means visual information uploaded by a user to create advertising content.

[1343] "Input device means" refers to an interface that allows a user to input text and images. Specifically, it includes a Web UI that is used via a browser.

[1344] The "emotion analysis means" is a device that reads the user's facial expressions and voice in real time, and analyzes this data to determine the user's emotional state.

[1345] "Transmission device means" refers to a device for transmitting input text, images, and emotion data to a server, mainly using HTTP protocol and REST API.

[1346] A "server" is a central processing unit that generates new images and videos based on the data it receives.

[1347] "Content generation means" means a device that generates new images or videos based on input text, images, and emotion data within the server, utilizing a generative AI model.

[1348] A "generative AI model" is a pre-trained machine learning model used to generate images and videos. Examples include Generative Adversarial Networks (GANs) and CLIP.

[1349] "Storage means" refers to a device for temporarily storing the generated images or videos. Cloud storage is typically used.

[1350] The "transmitting device means" is a device for transmitting the generated image or video to the user's terminal.

[1351] "Display device means" means a device for displaying the generated images or videos on a user interface. Display technology such as HTML5 is used.

[1352] "User" means a person who uses the system to create advertising content.

[1353] The present invention provides a system for generating images and videos for advertising purposes based on text and images entered by a user and emotion data acquired in real time. The system includes an input device, emotion analysis means, transmission device, content generation means, storage means, transmission device means, and display device means.

[1354] input device means

[1355] Users access the Web UI through a browser and input or upload the text and images they want to use in their ads. Specifically, an interface using HTML5 and JavaScript is used, allowing users to easily provide text and images to the system.

[1356] Emotion analysis means

[1357] The Web UI is equipped with a camera and microphone to capture the user's facial expressions and voice in real time. The emotion analysis tool uses data obtained from these input devices to determine the user's emotional state. This analysis uses libraries such as OpenCV and Dlib and applies machine learning algorithms.

[1358] Transmitter means

[1359] The device converts the text, image, and emotion data entered by the user into JSON format and sends it to the server as an HTTP POST request using the HTTP protocol and REST API, allowing the server to receive all the necessary information comprehensively.

[1360] Content Creation Methods

[1361] The server uses the received data to generate new advertising images and videos using text, images, and emotion data. A pre-trained generative AI model, such as GAN (Generative Adversarial Networks) or CLIP, is used for generation. The generative AI model is implemented using machine learning libraries such as TensorFlow and PyTorch, and analyzes the received data and adaptively adjusts the generated content.

[1362] storage means

[1363] The server temporarily stores the generated images and videos in cloud storage, such as AWS S3 or Google Cloud Storage, and manages the stored data so that users can access and retrieve them later.

[1364] Transmitter means

[1365] The server sends the generated advertising images and videos to the user's device, allowing the user to check the results in real time. Communication is via the HTTP protocol, and data is sent in JSON format.

[1366] display means

[1367] The device displays images and videos sent from the server on the Web UI. <video>Tags and Tags are used, and users can review the generated content and download or further edit it if necessary.

[1368] Specific examples

[1369] For example, if a user is trying to create an ad for "Christmas Sale," they enter the text "Christmas Sale" into the Web UI and upload a Christmas-related image. At that time, the emotion engine captures the user's facial expressions and analyzes emotions from their voice. If the user seems happy, the emotion engine will reflect a bright and cheerful theme in the ad images and videos it generates. Below is an example of a prompt sentence:

[1370] Example prompt sentence:

[1371] "Generate an image to advertise a Christmas sale. The user's emotional state seems happy."

[1372] In this way, this system can generate high-quality advertising images and videos that incorporate the user's emotions, making it possible to provide more personalized advertising materials to users.

[1373] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1374] Step 1:

[1375] Users access the Web UI through a browser and enter or upload the text and images they want to use in their ads. The entered text and images are sent to the server through form elements in the Web UI. The input data is mainly written in HTML5 and JavaScript.

[1376] Input: Text input and image upload

[1377] Output: Text and image input data as form data

[1378] Step 2:

[1379] The user's device activates a webcam and microphone to capture the user's facial expressions and voice, thereby obtaining the user's emotional data in real time. Libraries such as OpenCV and Dlib are used for emotion analysis.

[1380] Input: Real-time facial image and audio data

[1381] Output: Captured emotion data

[1382] Step 3:

[1383] The device converts the input text, image, and emotion data into JSON format, which is then ready to be sent to the server.

[1384] Input: Text, images, and captured emotion data

[1385] Output: JSON format data

[1386] Step 4:

[1387] The device sends the generated JSON data to the server as an HTTP POST request, using the HTTP protocol and the REST API.

[1388] Input: JSON format data

[1389] Output: Data sent to the server

[1390] Step 5:

[1391] The server parses the JSON data of the received HTTP POST request using the Python standard library json to extract text data, image data, and emotion data.

[1392] Input: JSON format data

[1393] Output: Extracted text, images, and sentiment data

[1394] Step 6:

[1395] The server then uses the extracted data to generate new images and videos using generative AI models, such as GAN and CLIP, using TensorFlow and PyTorch. The generative AI model adjusts the theme, color, and style of the generated content based on the emotion data.

[1396] Input: Text, image, and sentiment data

[1397] Output: The generated image or video

[1398] Step 7:

[1399] The server temporarily stores the generated images and videos for advertising in cloud storage, using AWS S3 or Google Cloud Storage. The stored data is managed so that users can access and retrieve it later.

[1400] Input: Generated images or videos

[1401] Output: Snapshot image or video

[1402] Step 8:

[1403] The server sends the generated advertising images and videos to the user's device as an HTTP response, using the HTTP protocol for transfer.

[1404] Input: Generated images or videos

[1405] Output: Data sent to the user's terminal

[1406] Step 9:

[1407] The user's device displays the received images and videos on the Web UI. <video>Tags and Tags are used, and users can review the generated content and download or further edit it if necessary.

[1408] Input: Image or video sent from the server

[1409] Output: Image or video displayed on the Web UI

[1410] (Application example 2)

[1411] 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."

[1412] Conventional ad generation systems generate ad materials from text and images based on user input, but it is difficult to generate personalized ad materials that reflect the user's emotional state. Furthermore, since it is not possible to check and adjust the generated results in real time, there is a problem that it is difficult to increase user satisfaction.

[1413] 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.

[1414] In this invention, the server includes a user interface means for accepting input of text, images, and voice, a transmission means for transmitting the input text, images, voice, and emotion data to the server, a generation means for generating new images or videos based on the input in the server, a transmission means for transmitting the generated images or videos to the user, a display means for displaying the transmitted images or videos on the user interface, and a means for adjusting the theme and style of the images or videos generated by the generation means based on the emotion data, including an emotion engine for collecting and analyzing user emotion data. This enables the generation of personalized advertising materials that reflect the user's emotional state in real time.

[1415] The "user interface means for accepting input of text, images, and voice" is an interface for a user to input text, images, and voice to be used in creating advertising materials.

[1416] The "transmission means for transmitting input text, image, voice, and emotion data to a server" is a means for transmitting data and emotion data input by a user to a server.

[1417] The "generation means" is a mechanism that generates new images and videos for advertising based on data input to the server.

[1418] The "display means" is a means for displaying the generated advertising images and videos on the user interface.

[1419] The "emotion engine" is a system that includes machine learning algorithms that collect and analyze the user's facial expressions and voice data to detect the user's emotional state.

[1420] The "means for adjusting the theme or style of the image or video generated by the generation means based on emotional data" is a mechanism for automatically adjusting the theme or style of the advertising material generated by the generation means based on emotional data analyzed by the emotion engine.

[1421] A "generative AI model" is an artificial intelligence model that is pre-trained and used to generate new images and videos.

[1422] The present invention provides a system that generates images and videos for advertising purposes based on text, images, and audio input by a user, and further recognizes the user's emotional data and adaptively changes the content of the generated images. A specific embodiment of the invention will be described below.

[1423] Hardware and software used

[1424] Hardware:

[1425] Smart glasses (e.g. Vuzix Blade, Nreal Light)

[1426] A device equipped with a webcam and microphone

[1427] Cloud servers (e.g. AWS EC2 instances)

[1428] software:

[1429] Frontend: Customized Web UI using React.js

[1430] Backend: Python (Flask) and TensorFlow

[1431] Generative AI models: GPT-4 and DALL-E

[1432] System Components

[1433] 1. User Interface Means:

[1434] Users use the smart glasses to input text, images, and audio using voice commands and gestures, and the glasses' camera and microphone are used to capture facial and audio data in real time.

[1435] 2. Means of transmission:

[1436] The captured data and input text, images, and audio are converted into JSON format and sent to the server as an HTTP POST request.

[1437] 3. Generation means:

[1438] The server analyzes the received data and generates new advertising images and videos based on the emotion data, using pre-trained generative AI models (GPT-4 and DALL-E).

[1439] 4. Display means:

[1440] The generated advertising images and videos are displayed in real time on the user interface, where users can check the results through the glasses' display and make edits if necessary.

[1441] 5. Emotion Engine:

[1442] The emotion engine uses machine learning algorithms to analyze a user's facial expressions and voice data to infer their emotional state, and then adjusts the theme and style of the ad material it generates based on this emotional data.

[1443] Data processing and calculation

[1444] The server analyzes the data received from the front-end and compares it with the emotional data obtained by the emotion engine. The analyzed data is input into the generative AI model to generate advertising materials. The generated materials are temporarily stored on the cloud server so that users can access them at any time.

[1445] Specific examples

[1446] For example, if a user is trying to create a TV ad for a new product, they can put on the smart glasses, say "new 4K TV," and scan an image of the product with the camera. At the same time, the emotion engine will detect that the user is smiling. Based on this information, the ad generated by the generative AI model will be tailored to a bright and cheerful theme.

[1447] Prompt Sentence Examples

[1448] Prompt 1: "Generate an ad for a new 4K TV. The user will smile."

[1449] Prompt 2: "The theme should be fun and bright colors."

[1450] This allows users to generate emotion-based personalized advertising material in real time.

[1451] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1452] Step 1:

[1453] Users wear smart glasses and input text, images, and voice using voice commands and gestures. The smart glasses' cameras and microphones automatically capture the user's facial expressions and voice, collecting the necessary data in real time. This allows the input data to be collected as text, image files, audio files, and emotional data.

[1454] Step 2:

[1455] The collected data is temporarily stored as a document in the smart glasses. The stored data is converted to JSON format and sent to the server as an HTTP POST request. Through this sending process, the server receives input data from the user interface.

[1456] Step 3:

[1457] The server analyzes the received JSON data. The analysis includes text data analysis, image and audio data preprocessing, and emotion data analysis. The results of this processing are analyzed text data, image data, audio data, and emotion metadata.

[1458] Step 4:

[1459] The server inputs the analyzed data into a generative AI model, which uses pre-trained GPT-4 and DALL-E models to generate images and videos for advertisements that reflect the user's emotional data. This process outputs optimized advertising materials.

[1460] Step 5:

[1461] The generated advertising materials are temporarily stored in the server storage, and this storage process allows users to access and download the generated materials at any time.

[1462] Step 6:

[1463] The server transmits the generated advertising images and videos in real time to the user interface, where the transmitted advertising materials are further displayed on the display of the user's smart glasses, allowing the user to check the generated results in real time.

[1464] Step 7:

[1465] Users can review the displayed ad material and, if necessary, re-edit or adjust it using voice commands or gestures. During this adjustment process, the generative AI model performs further optimization based on user feedback, and improved ad material is generated and displayed again.

[1466] The above steps result in a system that allows users to generate and edit emotion-based personalized advertising materials in real time.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] 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.

[1471] 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.

[1472] 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.

[1473] 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).

[1474] 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.

[1475] 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."

[1476] 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.

[1477] 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).

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] 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.

[1483] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1484] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1485] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1486] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1487] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1488] The following is further disclosed regarding the above embodiment.

[1489] (Claim 1)

[1490] a user interface means for accepting input of text or images;

[1491] a transmitting means for transmitting the input text or image to a server;

[1492] A generating means for generating a new image or video based on the input in the server;

[1493] a transmitting means for transmitting the generated image or video to a user;

[1494] a display means for displaying the transmitted image or video on a user interface;

[1495] A system including:

[1496] (Claim 2)

[1497] The system of claim 1, wherein the generating means generates new images or videos using a pre-trained generative model.

[1498] (Claim 3)

[1499] 10. The system of claim 1, further comprising a storage means for temporarily storing the generated image or video.

[1500] (Claim 4)

[1501] 2. The system according to claim 1, wherein the transmitting means for transmitting the image or video generated based on a request from the user uses the HTTP protocol.

[1502] (Claim 5)

[1503] 10. The system according to claim 1, which provides an interface for a user to generate an advertising image by inputting text.

[1504] (Claim 6)

[1505] 2. The system according to claim 1, which provides an interface for a user to generate an advertising image or video by inputting an image.

[1506] "Example 1"

[1507] (Claim 1)

[1508] a display device that accepts text or image input;

[1509] a transmitting device for transmitting input text or images to the processing device;

[1510] a generating device for generating new audiovisual data based on the input from the processing device;

[1511] a transmitting device for transmitting the generated audiovisual data to a user;

[1512] a display device that displays the transmitted audiovisual data on the display device;

[1513] A system including:

[1514] (Claim 2)

[1515] 2. The system of claim 1, wherein the generator generates new audiovisual data using a pre-trained generation algorithm.

[1516] (Claim 3)

[1517] 10. The system of claim 1, further comprising a storage device for temporarily storing the generated audiovisual data.

[1518] "Application Example 1"

[1519] (Claim 1)

[1520] a user interface means for accepting input of text or images;

[1521] a transmitting means for transmitting the input text or image to a server;

[1522] A generating means for generating a new image or video based on the input in the server;

[1523] A storage means for storing the generated image or video;

[1524] a display means for displaying the transmitted image or video on a user interface;

[1525] a download means for allowing a user to download the generated image or video;

[1526] A system including:

[1527] (Claim 2)

[1528] The system of claim 1, wherein the generating means generates new images or videos using a pre-trained generative AI model.

[1529] (Claim 3)

[1530] 10. The system of claim 1, further comprising a storage means for temporarily storing the generated image or video.

[1531] "Example 2: Combining Emotion Engines"

[1532] (Claim 1)

[1533] an input device means for accepting input of text or images;

[1534] Emotion analysis means that reads the user's facial expressions and voice in real time;

[1535] a transmitting device means for transmitting the input text, image, and emotion data to a server;

[1536] a content generation means in the server for generating new images or videos based on input text, images, and emotion data;

[1537] a storage means for temporarily storing the generated image or video;

[1538] a transmitting device means for transmitting the stored images or videos to a user;

[1539] a display device for displaying the transmitted image or video;

[1540] A system including:

[1541] (Claim 2)

[1542] 2. The system of claim 1, wherein the content generation means generates new images or videos using a pre-trained generative AI model.

[1543] (Claim 3)

[1544] 10. The system of claim 1, further comprising a storage means for temporarily storing the generated images or videos.

[1545] "Application example 2 when combining emotion engines"

[1546] (Claim 1)

[1547] a user interface means for accepting input of text, images, and voice;

[1548] a transmitting means for transmitting the input text, image, voice, and emotion data to a server;

[1549] A generating means for generating a new image or video based on the input in the server;

[1550] a transmitting means for transmitting the generated image or video to a user;

[1551] a display means for displaying the transmitted image or video on a user interface;

[1552] a means for adjusting the theme or style of the image or video generated by the generating means based on the emotion data, the emotion engine including the emotion engine collecting and analyzing the emotion data of the user;

[1553] A system including:

[1554] (Claim 2)

[1555] 2. The system of claim 1, wherein the generating means generates new images or videos using a pre-trained generative AI model.

[1556] (Claim 3)

[1557] 10. The system of claim 1, further comprising a storage means for temporarily storing the generated image or video. [Explanation of symbols]

[1558] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / video> < / video> < / url:> < / video> < / video> < / url:> < / video> < / video> < / url:> < / video> < / video>

Claims

1. a user interface means for accepting input of text or images; a transmitting means for transmitting the input text or image to a server; A generating means for generating a new image or video based on the input in the server; a transmitting means for transmitting the generated image or video to a user; a display means for displaying the transmitted image or video on a user interface; A system including:

2. The system of claim 1 , wherein the generating means generates new images or videos using a pre-trained generative model.

3. The system of claim 1 , further comprising a storage means for temporarily storing the generated images or videos.

4. 2. The system according to claim 1, wherein the transmitting means for transmitting the image or video generated in response to a request from a user uses the HTTP protocol.

5. 2. The system according to claim 1, wherein the system provides an interface for a user to generate an advertising image by inputting text.

6. 2. The system according to claim 1, which provides an interface for a user to generate an image or video for advertising by inputting an image.

Images