system

Abstract

We provide the system. [Solution] Means for receiving input data, A means for generating advertising copy using generative artificial intelligence based on the input data, A means for generating an advertising image using an image generation tool based on the generated advertising text and the input data, A means for generating advertising creative by combining the generated advertising text and advertising images, A user interface means for reviewing and adjusting the generated advertising creative, A system that includes this.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] The conventional work of creating advertising creatives has problems that it requires a great deal of time and cost by hand. Also, since collaboration by multiple experts (for example, copywriters and designers) is required, it takes time for communication and adjustment, and it is difficult to create advertisements quickly. Furthermore, when creating multiple variations of advertisements in a short period, these problems have become more prominent. The present invention aims to solve these problems and improve the efficiency of creating advertising creatives.

Means for Solving the Problems

[0005] The present invention relates to a system that receives input data, generates advertising text using generative artificial intelligence based on the input data, and further generates advertising images using an image generation tool based on the generated advertising text and the input data. This system includes a user interface means for generating advertising creative by combining the generated advertising text and advertising images, and for reviewing and adjusting the generated advertising creative.

[0006] The user interface allows users to review the generated ad creatives and, if necessary, instruct the regeneration of ad copy and images. The generative artificial intelligence and image generation tools are configured to perform the generation based on specific keywords and instructions, thereby significantly reducing the time and cost of creating ad creatives.

[0007] "Input data" refers to information provided by the user, such as the target customer base, product information, and advertising theme.

[0008] "Generative artificial intelligence" is an artificial intelligence technology that generates advertising copy based on input data.

[0009] "Advertising copy" refers to advertising slogans and messages generated by generative artificial intelligence.

[0010] An "advertising image" is a visual element of an advertisement generated using an image generation tool.

[0011] An "image generation tool" is software that automatically creates advertising images based on input data and generated advertising text.

[0012] "Advertising creative" refers to the final form of an advertisement, created by combining the generated advertising copy and advertising images.

[0013] A "user interface means" is an interface for users to review and adjust the generated advertising creative.

[0014] "Regeneration" refers to the process by which generative artificial intelligence or image generation tools regenerate promotional text and advertising images based on user instructions.

[0015] A "keyword" is a specific word or phrase used when giving generation instructions to generative artificial intelligence and image generation tools. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

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

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

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

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0037] This invention relates to a system for automatically generating advertising creatives. Specifically, it is a system that generates advertising copy using generative artificial intelligence (AI) based on input data, and further generates advertising images using an image generation tool. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[0038] Program Processing Overview

[0039] 1. User input

[0040] The user provides input data on the device:

[0041] Users provide the system with input data such as target customer segments, product information, and advertising themes using their devices. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[0042] 2. Generating a catchy slogan

[0043] The server receives the input data:

[0044] The server receives input data sent by the user from the terminal and passes it on to the generative artificial intelligence.

[0045] The server sends a request to the generative artificial intelligence:

[0046] The server sends a request to the generative artificial intelligence to generate advertising copy based on the input data. The generative artificial intelligence then generates a tagline based on this request. For example, from the input data, it might generate the tagline "Let the scent of spring blossom in your heart."

[0047] The server receives the generated advertisement:

[0048] The server receives catchphrases generated by the generative artificial intelligence and stores them in a database.

[0049] 3. Generating advertising images

[0050] The server sends a request to the image generation tool:

[0051] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[0052] The server receives the generated ad image:

[0053] The server receives the advertising images generated by the image generation tool and stores them in the database.

[0054] 4. Generating advertising creatives

[0055] The server creates the ad creative:

[0056] The server retrieves generated advertising copy and images from a database and automatically generates advertising creatives by combining them.

[0057] 5. Review and adjust results

[0058] The server presents the generated results to the user:

[0059] The server sends the generated ad creative to the user's device and presents it to the user.

[0060] The user reviews the generated results and provides instructions for adjustments:

[0061] Users can review the ad creatives generated on their devices and request adjustments or changes as needed. For example, they can send a request to the server to "make the tagline a little shorter."

[0062] The server will regenerate:

[0063] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[0064] 6. Final Output

[0065] User final confirmation:

[0066] The user reviews the final ad creative on their device and confirms that there are no problems.

[0067] The server outputs a file:

[0068] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[0069] This invention allows users to create advertising creatives in a short amount of time, significantly reducing time and costs. Furthermore, because high-quality advertising copy and images are automatically generated based on the input data, it is possible to quickly deliver consistent and effective advertisements.

[0070] The following describes the processing flow.

[0071] Step 1:

[0072] The user logs into the system to begin creating ad creatives on their device. A user ID and password are required for login.

[0073] Step 2:

[0074] Users provide input data such as target customer segments, product information, and advertising themes to an input screen using their devices. For example, for an advertising theme of "New Spring Floral Perfume," users might input keywords such as "spring, floral, perfume, for women."

[0075] Step 3:

[0076] The user submits the input data to the system by pressing the submit button. This input data is used to generate the ad creative.

[0077] Step 4:

[0078] The server receives input data sent from the terminal and stores it in the database. This data is used in subsequent generation processes.

[0079] Step 5:

[0080] The server creates a request to the generative artificial intelligence to generate advertising copy based on the input data. The request includes keywords such as "spring, floral, perfume, women's."

[0081] Step 6:

[0082] The server sends a request to a generative artificial intelligence (AI), which generates advertising copy (catchphrases) based on the input data. For example, it might generate the catchphrase, "Let the scent of spring blossom in your heart."

[0083] Step 7:

[0084] The server receives the advertising copy generated by the generative artificial intelligence and stores it in a database. This advertising copy is then used in the next step.

[0085] Step 8:

[0086] The server creates a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. The request includes keywords such as "spring, floral, perfume, women's, elegant image".

[0087] Step 9:

[0088] The server sends a request to an image generation tool, which generates an advertising image based on the input data and advertising text. For example, it might generate an image of an elegant (floral) perfume bottle.

[0089] Step 10:

[0090] The server receives the advertising image generated by the image generation tool and stores it in the database. This advertising image is used in the next step.

[0091] Step 11:

[0092] The server retrieves promotional text and advertising images generated from the database, and automatically generates advertising creatives by combining them.

[0093] Step 12:

[0094] The server sends the generated ad creative to the user's device and presents it to the user.

[0095] Step 13:

[0096] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might submit additional requests such as, "Could you make the tagline a little shorter?"

[0097] Step 14:

[0098] The server receives the user's adjustment request and sends a regeneration request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[0099] Step 15:

[0100] The server resends the regenerated ad creative to the user's device and presents it to the user.

[0101] Step 16:

[0102] The user reviews the final ad creative on their device and confirms that there are no problems.

[0103] Step 17:

[0104] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[0105] (Example 1)

[0106] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0107] Traditional advertising creative generation was time-consuming and costly, and it was difficult to deliver consistent and effective advertisements quickly. Furthermore, realizing the advertising image that users envisioned required considerable effort and expertise. In addition, the difficulty in regenerating advertising copy and images made it difficult to adjust the content of advertisements on a case-by-case basis. As a result, there were challenges such as decreased efficiency in marketing activities and limitations on the quality and impact of advertisements.

[0108] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0109] In this invention, the server includes means for receiving input data, means for generating advertising text using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising text and the input data, means for generating advertising creative by combining the generated advertising text and advertising images, user interface means for reviewing and adjusting the generated advertising creative, and means for finally outputting the generated advertising creative. This makes it possible to generate high-quality advertising creative in a short time and to quickly provide effective advertisements while maintaining consistency. In addition, since users can easily make adjustment requests and instruct the regeneration of advertising text and images, more flexible and adaptable advertising creation is realized.

[0110] "Input data" refers to information that users provide to the system, such as target customer segments, product information, and advertising themes.

[0111] "Generative artificial intelligence" is an artificial intelligence technology that generates advertising copy based on input data provided by the user.

[0112] "Advertising copy" refers to advertising slogans and messages generated by generative artificial intelligence.

[0113] An "image generation tool" is software or hardware used to generate advertising images based on input data and generated advertising text.

[0114] An "advertising image" is a visual element for advertising that is generated using an image generation tool.

[0115] "Advertising creative" refers to the final form of an advertisement, created by combining the generated advertising copy and advertising images.

[0116] A "user interface means" is an interface that allows users to review and adjust generated advertising creatives.

[0117] "The means of final output" refers to the function of outputting the generated advertising creative as a file in an appropriate format and providing it to the user.

[0118] A "server" is a computer that operates the entire system and performs various generation processes and data management.

[0119] This invention relates to a system for automatically generating advertising creatives. Specifically, it is a system that generates advertising copy using generative artificial intelligence (AI) based on input data, and further generates advertising images using an image generation tool. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[0120] Hardware and software configuration

[0121] server:

[0122] The server is a computer that operates the entire system and performs various generation processes and data management. The server receives input data, sends requests to the generative artificial intelligence, and processes the storage and regeneration requests of the generated data.

[0123] Terminal:

[0124] Users access the system using a device. The device provides an interface for users to provide input data and to review and adjust the generated ad creatives.

[0125] Generative artificial intelligence models:

[0126] Generative artificial intelligence models are AI technologies used to generate advertising copy based on input data. For example, natural language processing (NLP) models fulfill this role.

[0127] Image generation tool:

[0128] Image generation tools are tools for generating images for advertisements based on input data and generated advertising text. For example, an AI model for image generation can fulfill this role.

[0129] Specific methods for data processing and data calculation

[0130] This system performs data processing and calculations using the following methods.

[0131] 1. The user provides the input data:

[0132] Users provide input data to the system using their devices, such as target customer segments, product information, and advertising themes. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[0133] 2. The server receives the input data and passes it to the generative artificial intelligence:

[0134] The server receives input data sent by the user and passes it to the generative artificial intelligence. The generative artificial intelligence generates advertising text based on this input data.

[0135] 3. The server receives the generated advertisement text and saves it to the database:

[0136] The system receives advertising copy generated by a generative artificial intelligence and stores it in a database.

[0137] 4. The server sends a request to the image generation tool:

[0138] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[0139] 5. The server receives the generated ad image and saves it to the database:

[0140] The server receives the advertising images generated by the image generation tool and stores them in the database.

[0141] 6. The server creates the ad creative:

[0142] The generated advertising copy and images are retrieved from a database, and they are combined to automatically generate advertising creatives.

[0143] 7. The server presents the generated results to the user:

[0144] The server sends the generated ad creative to the user's device and presents it to the user.

[0145] 8. The user reviews the generated results and provides instructions for adjustments:

[0146] Users can review the ad creatives generated on their devices and request adjustments or changes as needed. For example, they can send a request to the server to "make the tagline a little shorter."

[0147] 9. The server performs regeneration:

[0148] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[0149] 10. The user performs final confirmation:

[0150] The user reviews the final ad creative on their device and confirms that there are no problems.

[0151] 11. The server outputs the file:

[0152] The server outputs the final ad creative in the appropriate format and provides the user with a download link.

[0153] Example of a prompt

[0154] prompt:

[0155] Advertisement theme: New spring floral perfumes

[0156] Target customer base: Women, 20-30 years old

[0157] Keywords: Spring, Floral, Perfume, Elegant

[0158] This system allows users to generate high-quality ad creatives in a short amount of time, significantly reducing time and costs. It also enables the rapid delivery of consistent and highly effective ads, allowing users to easily request adjustments and review the generated results at each stage.

[0159] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0160] Step 1:

[0161] The user provides the input data.

[0162] Users use their devices to provide the system with input data such as target customer segments, product information, and advertising themes.

[0163] Input: Target customer base, product information, advertising theme, etc.

[0164] Output: Input data is sent to the server.

[0165] Specific operation:

[0166] The user enters the following into their device: "Target customer base: Women, 20-30 years old", "Product information: New floral perfume", and "Advertising theme: Spring".

[0167] When the user clicks the "Submit" button, the input data is sent to the server.

[0168] Step 2:

[0169] The server receives the input data.

[0170] The server receives input data sent from the user's terminal.

[0171] Input: Input data submitted by the user

[0172] Output: Received input data

[0173] Specific operation:

[0174] The server receives data sent from the terminal and stores it as input data.

[0175] Step 3:

[0176] The server sends a request to the generative artificial intelligence.

[0177] The server sends a request to a generative artificial intelligence (AI) to generate advertising copy based on the input data.

[0178] Input: Received input data

[0179] Output: Send a request to generate advertising copy to a generative AI.

[0180] Specific operation:

[0181] The server generates and sends the prompt "Spring, New release, Floral, Perfume, For women" to the AI ​​model.

[0182] Step 4:

[0183] Generative artificial intelligence generates advertising copy.

[0184] Generative artificial intelligence generates advertising text based on requests from a server.

[0185] Input: Server request (prompt)

[0186] Output: Generated advertisement text

[0187] Specific operation:

[0188] A generative AI model analyzes the prompt and generates the tagline, "Let's let the scent of spring blossom in our hearts."

[0189] Step 5:

[0190] The server receives the generated advertisement text.

[0191] The server receives advertising text generated by a generative artificial intelligence system and stores it in a database.

[0192] Input: Advertising text generated by a generative artificial intelligence.

[0193] Output: Advertisement text stored in the database

[0194] Specific operation:

[0195] The server receives the generated advertisement text and saves it to the database.

[0196] Step 6:

[0197] The server sends a request to the image generation tool.

[0198] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data.

[0199] Input: Generated ad copy, received input data

[0200] Output: Send a request to the image generation tool.

[0201] Specific operation:

[0202] The server sends a request to the image generation tool that includes the keywords "spring, floral, perfume, feminine, elegant image".

[0203] Step 7:

[0204] Image generation tool generates advertising images

[0205] The image generation tool generates advertising images based on requests from the server.

[0206] Input: Server request

[0207] Output: Generated ad images

[0208] Specific operation:

[0209] The image generation tool analyzes the request and generates an advertising image for an elegant floral perfume.

[0210] Step 8:

[0211] The server receives the generated ad images.

[0212] The server receives the advertising images generated by the image generation tool and stores them in the database.

[0213] Input: Advertisement image generated from an image generation tool

[0214] Output: Advertisement images stored in the database

[0215] Specific operation:

[0216] The server receives the generated ad image and saves it to the database.

[0217] Step 9:

[0218] The server creates the ad creative.

[0219] The server retrieves generated advertising copy and images from a database and automatically generates advertising creatives by combining them.

[0220] Input: Advertising text and images retrieved from the database

[0221] Output: Generated ad creative

[0222] Specific operation:

[0223] The server lays out the promotional text and ad images, and generates the ad creative.

[0224] Step 10:

[0225] The server presents the generated results to the user.

[0226] The server sends the generated ad creative to the user's device and presents it to the user.

[0227] Input: Generated ad creative

[0228] Output: Ad creative sent to the user's device

[0229] Specific operation:

[0230] The server displays the advertising creative on the device via a pre-configured user interface.

[0231] Step 11:

[0232] The user reviews the generated results and gives instructions for adjustments.

[0233] Users can review the ad creatives generated on their devices and request adjustments or changes as needed.

[0234] Input: Adjustment request from the user

[0235] Output: Coordination request sent to the server

[0236] Specific operation:

[0237] The user reviews the creative on their device's interface, enters any necessary adjustments such as "I want to make the tagline a little shorter," and then submits it.

[0238] Step 12:

[0239] The server will regenerate.

[0240] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[0241] Input: Adjustment request from the user

[0242] Output: Regenerated ad creative

[0243] Specific operation:

[0244] The server generates a new prompt and sends another request to the AI ​​model and image generation tool.

[0245] A new tagline and image are generated, and the creative is regenerated again.

[0246] Step 13:

[0247] The user performs a final check.

[0248] The user reviews the final ad creative on their device and confirms that there are no problems.

[0249] Input: Regenerated ad creative

[0250] Output: Final verification results, no feedback.

[0251] Specific operation:

[0252] The user performs a final check and clicks the "Complete" button if they determine there are no problems.

[0253] Step 14:

[0254] The server outputs the file.

[0255] The server outputs the final ad creative as a file in the appropriate format and provides the user with a download link.

[0256] Input: Final approved ad creative

[0257] Output: Files output in the appropriate format (e.g., JPEG, PNG) and a download link.

[0258] Specific operation:

[0259] The server saves the ad creative in JPEG format and provides the user with a download link.

[0260] (Application Example 1)

[0261] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0262] Traditionally, the process of creating advertising creatives has been time-consuming and labor-intensive, requiring specialized knowledge and skills, especially for small businesses and individuals, making it difficult to create efficient and effective advertisements. Furthermore, the limited available materials made it difficult to quickly generate advertisements tailored to target customer segments. This resulted in an inability to adapt to situations requiring short-term advertising deployments, negatively impacting customer acquisition and sales.

[0263] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0264] In this invention, the server includes means for receiving input data, means for generating advertising copy using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising copy and the input data, means for generating advertising creative by combining the generated advertising copy and advertising images, means for a user interface for reviewing and adjusting the generated advertising creative, means for the user to provide input data such as target customer base, product information, and advertising theme using a smartphone, and means for presenting the generated advertising creative to the user's smartphone and accepting user review and adjustments. This makes it possible to generate advertising creative efficiently and effectively and create high-quality advertisements in a short amount of time.

[0265] "Input data" refers to information provided by the user, such as the target customer base, product information, and advertising theme.

[0266] "Generative artificial intelligence" refers to an AI system that generates advertising copy based on input data.

[0267] "Advertising copy" refers to catchphrases and messages for advertisements created by generative artificial intelligence.

[0268] An "image generation tool" is software or a system that generates advertising images based on generated advertising text and input data.

[0269] "Advertising images" are visual advertising materials created using image generation tools.

[0270] "Advertising creative" refers to the final advertising work created by combining the generated advertising copy and advertising images.

[0271] A "user interface means" is an interface that allows users to review and adjust the generated advertising creative.

[0272] A "smartphone" is a personal information device used by users to provide input data and to review and adjust the generated advertising creatives.

[0273] The system implementing this invention mainly consists of a smartphone and a server. The user provides input data such as target customer base, product information, and advertising theme using the smartphone. The server receives this data and generates advertising copy using generative artificial intelligence (AI). Based on the generated advertising copy and input data, the server generates advertising images using an image generation tool. Subsequently, the generated advertising copy and advertising images are combined to create advertising creatives, which are then presented to the user via the smartphone for review and adjustment.

[0274] The server uses the following hardware and software:

[0275] Generative artificial intelligence: For example, we use OpenAI's GPT-4® or Google Cloud AI's Text Generation API as generative AI models.

[0276] Image generation tools: Use image generation APIs such as DALL-E 2 or MidJourney.

[0277] Database: A database solution for storing and managing generated data (e.g., MySQL®, PostgreSQL).

[0278] Specifically, the server receives input data sent by the user and first sends a prompt to the generation AI model to generate advertising text. Examples of such prompts include the following:

[0279] Product Information: "Organic Soap", Target Customer Base: "Naturally-minded women in their 20s", Theme: "Autumn New Product Campaign"

[0280] Based on this prompt, the generative AI model generates the following advertisement:

[0281] Experience the refreshing feeling of autumn with natural soap.

[0282] Next, based on the generated ad copy and input data, the server sends a request to the image generation tool to generate the ad image. For example, the request may include the following:

[0283] The advertisement image for the natural-looking organic soap features a design inspired by autumn scenery and organic ingredients.

[0284] Integrate the generated image and promotional text to automatically create an ad creative. The created ad creative is sent to the user's smartphone, and the user checks it and sends an adjustment request to the server if necessary. The server uses the generative artificial intelligence and image generation tool again to generate a new promotional text and ad image, and updates the ad creative again.

[0285] In this way, the user can create efficient and high-quality ad creatives in a short time. A major advantage of this invention is that especially small businesses and individuals can quickly create effective ads without the need for specialized knowledge or skills.

[0286] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0287] Step 1:

[0288] The user uses a smartphone to input input data such as the target customer segment, product information, and ad theme. Specifically, the user opens a dedicated application and inputs data such as "Target customer segment: Women in their 20s", "Product information: Organic soap", and "Ad theme: Autumn new product campaign" into a form. These data are sent from the smartphone to the server.

[0289] Step 2:

[0290] The server receives the input data sent from the user. This input data includes the target customer segment, product information, and ad theme. The server generates a prompt text based on this data and sends it to the generative artificial intelligence (AI). An example of this prompt text is: "Product information: Organic soap, Target customer segment: Women in their 20s, Theme: Autumn new product campaign".

[0291] Step 3:

[0292] A generative artificial intelligence generates advertising copy based on prompt text received from the server. For example, based on the prompt text, a tagline such as "Enjoy the refreshing feeling of autumn with natural soap" is generated. This generated advertising copy is then sent to the server.

[0293] Step 4:

[0294] The server receives the generated ad copy and saves it to the database. At the same time, it sends a request to the image generation tool for generating the ad image. This request includes the generated ad copy and input data. For example, the request might be for "an ad image for a natural-tasting organic soap, with a design inspired by autumn scenery and organic materials."

[0295] Step 5:

[0296] The image generation tool generates an advertising image based on a request received from the server. The generated advertising image is sent to the server. Specifically, an image of "organic soap displayed against an autumn background" is generated.

[0297] Step 6:

[0298] The server receives the generated ad images and stores them in a database. Next, it combines the received ad copy and images to create ad creatives. This automatically generates visually appealing ad materials.

[0299] Step 7:

[0300] The server sends the generated ad creative to the user's smartphone. The user reviews the ad creative on their smartphone and requests adjustments or modifications as needed. For example, they might send a request to "make the tagline a little shorter."

[0301] Step 8:

[0302] The server receives an adjustment request from the user and sends requests to the generative artificial intelligence and the image generation tool again. As a result, new catchphrases and advertising images are generated, and the advertising creative is updated again.

[0303] Step 9:

[0304] The user checks the final advertising creative on the smartphone and confirms that there are no problems. The server outputs the final advertising creative in an appropriate format (e.g., JPEG, PNG) and provides a download link to the user. As a result, the user can quickly obtain high-quality advertising creatives.

[0305] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0306] The present invention relates to a system for automatically generating advertising creatives by generating promotional texts using generative artificial intelligence (AI) based on input data, further generating advertising images using an image generation tool, and incorporating an emotion engine for recognizing the user's emotional state. This system creates advertising creatives by combining the generated promotional texts and advertising images and includes user interface means for the user to confirm and adjust.

[0307] Outline of Program Processing

[0308] 1. User Input

[0309] The user provides input data on the terminal:

[0310] The user uses the terminal to provide the system with input data such as the target customer group, product information, and advertising theme. For example, for an advertising theme of "New Floral Perfume in Spring", keywords such as "Spring, Floral, Perfume, for Women" are input.

[0311] 2. Recognition of emotional states

[0312] The server uses an emotion engine to analyze the user's emotional state:

[0313] The server analyzes voice, facial expressions, or text data acquired from the user's device, and the emotion engine recognizes the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive."

[0314] 3. Generating a catchy slogan

[0315] The server sends a request to the generative artificial intelligence to generate advertising copy:

[0316] The server creates and sends a request to the generative artificial intelligence (AI) to generate advertising copy based on the input data and the user's emotional state. The AI ​​then generates a tagline based on this request. For example, based on the input data and positive emotions, it might generate the tagline, "Let the scent of spring blossom in your heart."

[0317] The server receives the generated advertisement:

[0318] The server receives the tagline generated by the generative artificial intelligence and stores it in a database. This advertising copy is used in the next step.

[0319] 4. Generating advertising images

[0320] The server sends a request to the image generation tool:

[0321] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy, input data, and the user's emotional state. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[0322] The server receives the generated ad image:

[0323] The server receives the advertising images generated by the image generation tool and stores them in the database. These advertising images are then used in the next step.

[0324] 5. Generating advertising creatives

[0325] The server creates the ad creative:

[0326] The server automatically generates ad creatives by combining the generated ad copy, ad images, and the user's emotional state.

[0327] 6. Review and adjust results

[0328] The server presents the generated results to the user:

[0329] The server sends the generated ad creative to the user's device and presents it to the user.

[0330] The user reviews the generated results and provides instructions for adjustments:

[0331] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might enter additional requests such as, "Could you make the tagline a little shorter?"

[0332] The server will regenerate:

[0333] The server then sends another request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[0334] 7. Final Output

[0335] User final confirmation:

[0336] The user reviews the final ad creative on their device and confirms that there are no problems.

[0337] The server outputs a file:

[0338] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[0339] This invention allows users to create high-quality advertising creatives in a short amount of time, significantly reducing time and costs. Furthermore, it enables the generation of advertising creatives that respond to the user's emotional state, allowing for the delivery of more appropriate and effective advertisements.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The user logs into the system to begin creating ad creatives on their device. A user ID and password are required for login.

[0343] Step 2:

[0344] Users provide input data such as target customer segments, product information, and advertising themes to input forms using their devices. For example, for an advertising theme of "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[0345] Step 3:

[0346] The user submits the input data to the system by pressing the submit button. The input data is received by the server and stored in the database.

[0347] Step 4:

[0348] The server uses an emotion engine to analyze voice, facial, or text data acquired from the user's device to recognize the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive."

[0349] Step 5:

[0350] The server combines emotional state information obtained from the emotion engine and creates a request for promotional text generation from the generative artificial intelligence. The request includes input data and the user's emotional state (e.g., "positive").

[0351] Step 6:

[0352] The server sends a request to a generative artificial intelligence (AI), which generates a catchy slogan based on the input data and emotional state information. For example, it might generate the slogan, "Let the scent of spring blossom in your heart."

[0353] Step 7:

[0354] The server receives the advertising copy generated by the generative artificial intelligence and stores it in a database. This advertising copy is then used in the next step.

[0355] Step 8:

[0356] The server creates a request to the image generation tool to generate an advertising image based on the generated ad copy, input data, and sentiment state information. The request includes keywords such as "spring, floral, perfume, women's, elegant image."

[0357] Step 9:

[0358] The server sends a request to an image generation tool, which generates an advertising image based on input data, advertising text, and sentiment information. For example, it might generate an image of an elegant (floral) perfume bottle.

[0359] Step 10:

[0360] The server receives the advertising image generated by the image generation tool and stores it in the database. This advertising image is used in the next step.

[0361] Step 11:

[0362] The server retrieves promotional text and ad images generated from the database, combines them, and automatically generates ad creatives. Emotional state information is also taken into consideration.

[0363] Step 12:

[0364] The server sends the generated ad creative to the user's device and presents it to the user.

[0365] Step 13:

[0366] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might request, "I'd like the tagline to be a little shorter."

[0367] Step 14:

[0368] The server receives the user's adjustment request and sends a regeneration request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[0369] Step 15:

[0370] The server resends the regenerated ad creative to the user's device and presents it to the user.

[0371] Step 16:

[0372] The user reviews the final ad creative on their device and confirms that there are no problems.

[0373] Step 17:

[0374] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[0375] (Example 2)

[0376] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0377] The modern advertising industry demands the rapid generation of high-quality advertising creatives. However, doing this manually is time-consuming and costly, and creating advertisements that reflect user emotions and needs is even more difficult. Furthermore, traditional systems have the problem of not being able to flexibly regenerate advertising copy and images as requested by users.

[0378] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data using a terminal, means for generating advertising copy using a generation AI model based on the input data and the user's emotional state, and means for generating advertising images using an image generation tool based on the generated advertising copy, the emotional state, and the input data. This enables the automatic generation of high-quality advertising creatives that are tailored to the user's emotional state. Furthermore, it is equipped with interface means for checking and adjusting the generated advertising creatives, and it is also possible to instruct the regeneration of advertising copy and advertising images, thereby realizing a flexible advertising creation process.

[0379] A "terminal" is a device used by a user to provide input data to a system, and generally refers to information processing devices such as computers and smartphones.

[0380] "Input data" refers to information that users provide to the system, including detailed data such as target customer segments, product information, and advertising themes.

[0381] "Emotional state" refers to data that represents a user's current emotions, and is classified as positive, negative, neutral, etc., by analyzing voice, facial expressions, text, etc.

[0382] A "generative AI model" is an artificial intelligence system that generates advertising copy based on input data and emotional states, and refers to, for example, a large-scale language model.

[0383] "Advertising text" refers to advertising wording such as copywriting and catchphrases generated by generative AI models.

[0384] An "image generation tool" refers to a system or software that generates advertising images based on input data, generated advertising text, and emotional states.

[0385] "Advertising images" refer to visual advertising elements generated by image generation tools, and include photographs, illustrations, graphic designs, etc.

[0386] "Advertising creative" refers to complete advertising content created by combining generated advertising copy and advertising images.

[0387] "Interface means" refers to means by which users can review and adjust generated advertising creatives, and generally includes user-friendly screens and operating methods.

[0388] This invention is a system that automatically generates advertising creatives by generating advertising copy using generative artificial intelligence (AI) based on input data, generating advertising images using an image generation tool, and incorporating an emotion engine that recognizes the user's emotional state. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[0389] First, the user uses their device to input the target customer base, product information, and advertising theme. For example, for an advertising theme of "New Spring Floral Perfume," they can input keywords such as "spring, floral, perfume, women's." Users can also provide voice and facial expression data. This data is transmitted to the server via the device.

[0390] Next, the server uses an emotion engine to analyze the voice, facial expressions, or text data provided by the user to recognize the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive." This emotion analysis is performed using tools such as IBM Watson®'s emotion analysis API.

[0391] Next, the server creates and sends a request to a generative AI model (e.g., OpenAI GPT-4) to generate advertising copy, based on the input data and the user's emotional state. The following are examples of the specific prompts used:

[0392] Based on the following keywords—"spring," "floral," "perfume," "women's," and "elegant"—and the user's emotional state—"positive," please generate a tagline for a new floral perfume.

[0393] The generative AI model generates a tagline based on this request, creating an advertisement such as, "Let the scent of spring blossom in your heart." The generated advertisement is received by the server and stored in the database.

[0394] The server then sends a request to an image generation tool (e.g., MidJourney or DALL-E) to generate an advertising image, based on the generated ad copy, input data, and the user's emotional state. The prompt might look something like this:

[0395] Please generate an ad image based on the keywords "spring, floral, perfume, women's, elegant image".

[0396] The image generation tool generates an advertisement image based on this prompt, creating an image that, for example, includes an elegant background and a floral design. The generated advertisement image is also received by the server and stored in the database.

[0397] Ultimately, the server combines the generated ad copy, ad images, and sentiment states to create ad creatives. The generated ad creatives are presented to the user through a user interface. The user can review the generated ad creatives and, if necessary, request the regeneration of the ad copy and ad images. Upon receiving a regeneration request, the server sends new prompt text to the generation AI model and image generation tools to generate new ad copy and ad images.

[0398] This system enables users to efficiently generate high-quality ad creatives, saving both time and money. Furthermore, it allows for the creation of ad creatives tailored to the user's emotional state, providing personalized and effective advertising.

[0399] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0400] Step 1:

[0401] The user provides input data on their device.

[0402] The user uses a terminal to input data such as target customer segment, product information, and advertising theme into the system. Specifically, the user enters the advertising theme "New Spring Floral Perfume" and keywords such as "spring, floral, perfume, for women" into the input form on the terminal. The entered data is then sent from the terminal to the server.

[0403] Input: Target customer base, product information, advertising theme, keywords

[0404] Output: Send input data to the server

[0405] Step 2:

[0406] The server uses an emotion engine to analyze the user's emotional state.

[0407] The server acquires voice data, facial expression data, and text data sent from the terminal. Next, it sends this data to the emotion engine for analysis to recognize the user's emotional state. For example, if the user's facial expression is smiling, the emotion engine recognizes it as "positive."

[0408] Input: Audio data, facial expression data, text data

[0409] Output: User's emotional state (e.g., positive)

[0410] Step 3:

[0411] The server sends a request to the AI ​​model to generate advertising copy.

[0412] The server creates a request to the AI ​​model to generate advertising copy based on the input data and the user's emotional state. The prompt text includes the advertising theme and emotional state. For example, it generates a prompt text like the following:

[0413] Based on the following keywords—"spring," "floral," "perfume," "women's," and "elegant"—and the user's emotional state—"positive," please generate a tagline for a new floral perfume.

[0414] The generative AI model generates catchphrases based on this.

[0415] Input: Input data, user's emotional state

[0416] Output: Prompt text for the generating AI model, generated catchphrase

[0417] Step 4:

[0418] The server receives the generated advertisement text.

[0419] The server receives the catchphrase from the generating AI model and saves it to the database. Let's assume the generated catchphrase is "Let's let the scent of spring blossom in our hearts."

[0420] Input: Catchphrases from a generated AI model

[0421] Output: Catchphrases stored in the database

[0422] Step 5:

[0423] The server sends a request to the image generation tool.

[0424] The server sends a request to the image generation tool to generate an advertising image based on the generated tagline, input data, and the user's emotional state. The prompt message will likely include something like this:

[0425] Please generate an ad image based on the keywords "spring, floral, perfume, women's, elegant image".

[0426] The image generation tool generates advertising images based on this.

[0427] Input: Generated tagline, input data, user's emotional state

[0428] Output: Prompt text for the image generation tool, generated advertisement image

[0429] Step 6:

[0430] The server receives the generated ad images.

[0431] The server receives the advertising images generated by the image generation tool and stores them in the database.

[0432] Input: Advertisement image from an image generation tool

[0433] Output: Advertisement images stored in the database

[0434] Step 7:

[0435] The server creates the ad creative.

[0436] The server automatically generates ad creatives by combining the generated ad copy, ad images, and emotional states. For example, it might place the tagline "Let the scent of spring blossom in your heart" on an elegant background image.

[0437] Input: Generated ad copy, ad images, sentiment status

[0438] Output: Generated ad creative

[0439] Step 8:

[0440] The server presents the generated results to the user.

[0441] The server sends the generated ad creative to the user's device and displays it.

[0442] Input: Generated ad creative

[0443] Output: Generated results sent to the user's terminal

[0444] Step 9:

[0445] The user reviews the generated results and gives instructions for adjustments.

[0446] Users can review the ad creative generated on their device and enter requests for adjustments or changes as needed. For example, they can enter specific requests such as "I'd like the tagline to be a little shorter" or "I'd like to change the background color."

[0447] Input: Generated ad creative, user adjustment requests

[0448] Output: Sending adjustment request to the server

[0449] Step 10:

[0450] The server will regenerate.

[0451] The server processes the adjustment requests collected through the user interface, sends new prompt messages to the generation AI model and image generation tools, and generates new promotional text and advertising images.

[0452] Input: User adjustment request

[0453] Output: New prompt text, new promotional text, and advertising image

[0454] Step 11:

[0455] The user performs a final check.

[0456] The user reviews the final ad creative on their device and confirms that there are no problems.

[0457] Input: Regenerated ad creative

[0458] Output: User's final approval

[0459] Step 12:

[0460] The server outputs the file.

[0461] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link. Through this link, the user can obtain the final ad creative.

[0462] Input: Final ad creative

[0463] Output: Download link

[0464] (Application Example 2)

[0465] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0466] Current methods for generating ad creatives are time-consuming and labor-intensive, as advertisers must manually create and combine promotional text and images. Furthermore, because ads are created uniformly, it's difficult to provide personalized ads tailored to individual users' emotional states and destination information. This results in limited ad effectiveness.

[0467] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0468] In this invention, the server includes means for receiving input data, means for generating advertising text using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising text and the input data, means for generating advertising creative by combining the generated advertising text and advertising images, user interface means for checking and adjusting the generated advertising creative, means for acquiring passenger destination information, means for recognizing passenger emotional states, and means for generating advertising text and advertising images as personalized advertisements based on the passenger destination information and emotional states. This makes it possible to automatically generate highly effective personalized advertisements tailored to the emotional states and destination information of individual users and provide them in a short amount of time.

[0469] "Input data" refers to information provided by the user to the system for generating advertisements, including, for example, target customer segments, product information, and themes of advertisements.

[0470] "Generative artificial intelligence" refers to an artificial intelligence program that automatically generates advertising copy based on input data.

[0471] An "image generation tool" is a software tool that automatically generates advertising images based on generated advertising text and input data.

[0472] "Advertising creative" refers to advertising materials created by combining generated advertising copy and advertising images.

[0473] A "user interface means" is an interface means that allows the user to review the generated advertising creative and instruct it to be adjusted or regenerated as needed.

[0474] "Destination information" refers to information about the destination set by the passenger.

[0475] "Emotional state" refers to information that represents a passenger's emotions, and is analyzed from, for example, facial expressions and tone of voice.

[0476] "Personalized advertising" refers to advertisements that are individually tailored based on a passenger's destination information and emotional state.

[0477] In order to implement the system of the present invention, the following program must be implemented. This program automatically generates advertising creatives based on user input data and provides personalized advertisements to the user.

[0478] Program Processing Overview

[0479] 1. Receiving input data:

[0480] The system receives information necessary for ad generation from the user's device, such as target customer segment, product information, and ad theme, and sends it to the server.

[0481] 2. Obtaining destination information:

[0482] The server retrieves destination information from the system inside the passenger's autonomous vehicle.

[0483] 3. Recognition of emotional states:

[0484] The server uses emotion recognition software to analyze passengers' camera and audio streams, including their smiles and tone of voice, to recognize their emotional state. This emotion recognition software is called "EmotionRecognition."

[0485] 4. Generating promotional text:

[0486] The server uses generative artificial intelligence (AI text generator) to generate promotional text based on the passenger's emotional state and destination information. For example, it might use a prompt such as, "Generate a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring."

[0487] 5. Generating advertising images:

[0488] The server uses an image generation tool (AI image generator) to generate personalized advertising images based on the generated promotional text and destination information. For example, it might use a prompt such as, "Generate a beautiful image that reflects spring, Tokyo Tower, tourism, and positive emotions."

[0489] 6. Generating ad creatives:

[0490] The server combines the generated promotional text and advertising images to create personalized ads as advertising creatives.

[0491] 7. Display of advertisements:

[0492] The server displays the generated ad creatives on displays inside the autonomous vehicle and on passengers' smart devices (smartphones and head-mounted displays).

[0493] 8. Verification and adjustment via the user interface:

[0494] Users review the displayed ad creatives and instruct the system to adjust or regenerate them as needed.

[0495] Hardware and software to be used

[0496] Camera and microphone: Devices for detecting the emotional state of passengers.

[0497] Autonomous vehicle display: A device for displaying advertisements.

[0498] Smart devices (smartphones, head-mounted displays): Devices used to display advertisements individually.

[0499] EmotionRecognition: Emotion recognition software. Analyzes passengers' emotional states in real time.

[0500] AI Text Generator: A generative artificial intelligence system. It generates advertising text based on emotional states and destination information.

[0501] AI Image Generator: Image generation tool. Generates advertising images.

[0502] Specific examples and prompt statements

[0503] For example, if a passenger is heading to "Tokyo Tower," use the following prompt:

[0504] EmotionRecognition:

[0505] "Use the camera and audio streams to determine if the passenger is smiling."

[0506] AI Text Generator:

[0507] "Please create a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring."

[0508] AI Image Generator:

[0509] "Please generate a beautiful image that reflects spring, Tokyo Tower, sightseeing, and positive emotions."

[0510] This embodiment makes it possible to automatically generate highly effective personalized advertisements tailored to each user's emotional state and destination information, and deliver them in a short amount of time.

[0511] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0512] Step 1:

[0513] The user's device inputs the information necessary for ad generation and sends it to the server. The input data includes target customer segment, product information, and ad theme. The server receives this data and uses it for further processing.

[0514] Step 2:

[0515] The server retrieves passenger destination information from the system within the autonomous vehicle. This destination information is used in a later processing step to personalize the advertisement content.

[0516] Step 3:

[0517] The server analyzes the camera and audio streams and uses emotion recognition software to recognize the passenger's emotional state. Specifically, it uses information such as whether the passenger is smiling and their tone of voice to classify their emotional state as "positive" or "negative." This is how the emotional state is obtained.

[0518] Step 4:

[0519] Based on emotional states and destination information, the server sends prompts to a generative artificial intelligence (AI text generator) to generate appropriate advertising copy. For example, if the prompt is "Generate a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring," the generated slogan will be output.

[0520] Step 5:

[0521] The server sends prompts to an image generation tool (AI image generator) based on the advertisement text and destination information, and generates an advertising image. For example, if the prompt is "Generate a beautiful image that reflects spring, Tokyo Tower, tourism, and positive emotions," the generated image will be output.

[0522] Step 6:

[0523] The server combines the generated promotional text and advertising images to create advertising creatives. Specifically, the generated text is placed on the images, resulting in visually appealing advertising materials.

[0524] Step 7:

[0525] The server sends the generated ad creatives to displays in the autonomous vehicle and to passengers' smart devices for display. This allows passengers to visually see personalized ads while on their way to their destination.

[0526] Step 8:

[0527] Users review the displayed ad creative and instruct it to be adjusted or regenerated as needed. Specifically, they request revisions to the tagline or regeneration of images through the user interface. This request is sent to the server, the regeneration process is performed again, and a new ad creative is created.

[0528] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0529] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0530] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0531] [Second Embodiment]

[0532] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0533] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0534] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0535] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0536] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0537] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0538] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0539] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0540] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0541] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0542] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0543] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0544] This invention relates to a system for automatically generating advertising creatives. Specifically, it is a system that generates advertising copy using generative artificial intelligence (AI) based on input data, and further generates advertising images using an image generation tool. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[0545] Program Processing Overview

[0546] 1. User input

[0547] The user provides input data on the device:

[0548] Users provide the system with input data such as target customer segments, product information, and advertising themes using their devices. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[0549] 2. Generating a catchy slogan

[0550] The server receives the input data:

[0551] The server receives input data sent by the user from the terminal and passes it on to the generative artificial intelligence.

[0552] The server sends a request to the generative artificial intelligence:

[0553] The server sends a request to the generative artificial intelligence to generate advertising copy based on the input data. The generative artificial intelligence then generates a tagline based on this request. For example, from the input data, it might generate the tagline "Let the scent of spring blossom in your heart."

[0554] The server receives the generated advertisement:

[0555] The server receives catchphrases generated by the generative artificial intelligence and stores them in a database.

[0556] 3. Generating advertising images

[0557] The server sends a request to the image generation tool:

[0558] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[0559] The server receives the generated ad image:

[0560] The server receives the advertising images generated by the image generation tool and stores them in the database.

[0561] 4. Generating advertising creatives

[0562] The server creates the ad creative:

[0563] The server retrieves generated advertising copy and images from a database and automatically generates advertising creatives by combining them.

[0564] 5. Review and adjust results

[0565] The server presents the generated results to the user:

[0566] The server sends the generated ad creative to the user's device and presents it to the user.

[0567] The user reviews the generated results and provides instructions for adjustments:

[0568] Users can review the ad creatives generated on their devices and request adjustments or changes as needed. For example, they can send a request to the server to "make the tagline a little shorter."

[0569] The server will regenerate:

[0570] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[0571] 6. Final Output

[0572] User final confirmation:

[0573] The user reviews the final ad creative on their device and confirms that there are no problems.

[0574] The server outputs a file:

[0575] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[0576] This invention allows users to create advertising creatives in a short amount of time, significantly reducing time and costs. Furthermore, because high-quality advertising copy and images are automatically generated based on the input data, it is possible to quickly deliver consistent and effective advertisements.

[0577] The following describes the processing flow.

[0578] Step 1:

[0579] The user logs into the system to begin creating ad creatives on their device. A user ID and password are required for login.

[0580] Step 2:

[0581] Users provide input data such as target customer segments, product information, and advertising themes to an input screen using their devices. For example, for an advertising theme of "New Spring Floral Perfume," users might input keywords such as "spring, floral, perfume, for women."

[0582] Step 3:

[0583] The user submits the input data to the system by pressing the submit button. This input data is used to generate the ad creative.

[0584] Step 4:

[0585] The server receives input data sent from the terminal and stores it in the database. This data is used in subsequent generation processes.

[0586] Step 5:

[0587] The server creates a request to the generative artificial intelligence to generate advertising copy based on the input data. The request includes keywords such as "spring, floral, perfume, women's."

[0588] Step 6:

[0589] The server sends a request to a generative artificial intelligence (AI), which generates advertising copy (catchphrases) based on the input data. For example, it might generate the catchphrase, "Let the scent of spring blossom in your heart."

[0590] Step 7:

[0591] The server receives the advertising copy generated by the generative artificial intelligence and stores it in a database. This advertising copy is then used in the next step.

[0592] Step 8:

[0593] The server creates a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. The request includes keywords such as "spring, floral, perfume, women's, elegant image."

[0594] Step 9:

[0595] The server sends a request to an image generation tool, which generates an advertising image based on the input data and advertising text. For example, it might generate an image of an elegant (floral) perfume bottle.

[0596] Step 10:

[0597] The server receives the advertising image generated by the image generation tool and stores it in the database. This advertising image is used in the next step.

[0598] Step 11:

[0599] The server retrieves promotional text and advertising images generated from the database, and automatically generates advertising creatives by combining them.

[0600] Step 12:

[0601] The server sends the generated ad creative to the user's device and presents it to the user.

[0602] Step 13:

[0603] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might submit additional requests such as, "Could you make the tagline a little shorter?"

[0604] Step 14:

[0605] The server receives the user's adjustment request and sends a regeneration request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[0606] Step 15:

[0607] The server resends the regenerated ad creative to the user's device and presents it to the user.

[0608] Step 16:

[0609] The user reviews the final ad creative on their device and confirms that there are no problems.

[0610] Step 17:

[0611] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[0612] (Example 1)

[0613] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0614] Traditional advertising creative generation was time-consuming and costly, and it was difficult to deliver consistent and effective advertisements quickly. Furthermore, realizing the advertising image that users envisioned required considerable effort and expertise. In addition, the difficulty in regenerating advertising copy and images made it difficult to adjust the content of advertisements on a case-by-case basis. As a result, there were challenges such as decreased efficiency in marketing activities and limitations on the quality and impact of advertisements.

[0615] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0616] In this invention, the server includes means for receiving input data, means for generating advertising text using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising text and the input data, means for generating advertising creative by combining the generated advertising text and advertising images, user interface means for reviewing and adjusting the generated advertising creative, and means for finally outputting the generated advertising creative. This makes it possible to generate high-quality advertising creative in a short time and to quickly provide effective advertisements while maintaining consistency. In addition, since users can easily make adjustment requests and instruct the regeneration of advertising text and images, more flexible and adaptable advertising creation is realized.

[0617] "Input data" refers to information that users provide to the system, such as target customer segments, product information, and advertising themes.

[0618] "Generative artificial intelligence" is an artificial intelligence technology that generates advertising copy based on input data provided by the user.

[0619] "Advertising copy" refers to advertising slogans and messages generated by generative artificial intelligence.

[0620] An "image generation tool" is software or hardware used to generate advertising images based on input data and generated advertising text.

[0621] An "advertising image" is a visual element for advertising that is generated using an image generation tool.

[0622] "Advertising creative" refers to the final form of an advertisement, created by combining the generated advertising copy and advertising images.

[0623] A "user interface means" is an interface that allows users to review and adjust generated advertising creatives.

[0624] "The means of final output" refers to the function of outputting the generated advertising creative as a file in an appropriate format and providing it to the user.

[0625] A "server" is a computer that operates the entire system and performs various generation processes and data management.

[0626] This invention relates to a system for automatically generating advertising creatives. Specifically, it is a system that generates advertising copy using generative artificial intelligence (AI) based on input data, and further generates advertising images using an image generation tool. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[0627] Hardware and software configuration

[0628] server:

[0629] The server is a computer that operates the entire system and performs various generation processes and data management. The server receives input data, sends requests to the generative artificial intelligence, and processes the storage and regeneration requests of the generated data.

[0630] Terminal:

[0631] Users access the system using a device. The device provides an interface for users to provide input data and to review and adjust the generated ad creatives.

[0632] Generative artificial intelligence models:

[0633] Generative artificial intelligence models are AI technologies used to generate advertising copy based on input data. For example, natural language processing (NLP) models fulfill this role.

[0634] Image generation tool:

[0635] Image generation tools are tools for generating images for advertisements based on input data and generated advertising text. For example, an AI model for image generation can fulfill this role.

[0636] Specific methods for data processing and data calculation

[0637] This system performs data processing and calculations using the following methods.

[0638] 1. The user provides the input data:

[0639] Users provide input data to the system using their devices, such as target customer segments, product information, and advertising themes. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[0640] 2. The server receives the input data and passes it to the generative artificial intelligence:

[0641] The server receives input data sent by the user and passes it to the generative artificial intelligence. The generative artificial intelligence generates advertising text based on this input data.

[0642] 3. The server receives the generated advertisement text and saves it to the database:

[0643] The system receives advertising copy generated by a generative artificial intelligence and stores it in a database.

[0644] 4. The server sends a request to the image generation tool:

[0645] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[0646] 5. The server receives the generated ad image and saves it to the database:

[0647] The server receives the advertising images generated by the image generation tool and stores them in the database.

[0648] 6. The server creates the ad creative:

[0649] The generated advertising copy and images are retrieved from a database, and they are combined to automatically generate advertising creatives.

[0650] 7. The server presents the generated results to the user:

[0651] The server sends the generated ad creative to the user's device and presents it to the user.

[0652] 8. The user reviews the generated results and provides instructions for adjustments:

[0653] Users can review the ad creatives generated on their devices and request adjustments or changes as needed. For example, they can send a request to the server to "make the tagline a little shorter."

[0654] 9. The server performs regeneration:

[0655] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[0656] 10. The user performs final confirmation:

[0657] The user reviews the final ad creative on their device and confirms that there are no problems.

[0658] 11. The server outputs the file:

[0659] The server outputs the final ad creative in the appropriate format and provides the user with a download link.

[0660] Example of a prompt

[0661] prompt:

[0662] Advertisement theme: New spring floral perfumes

[0663] Target customer base: Women, 20-30 years old

[0664] Keywords: Spring, Floral, Perfume, Elegant

[0665] This system allows users to generate high-quality ad creatives in a short amount of time, significantly reducing time and costs. It also enables the rapid delivery of consistent and highly effective ads, allowing users to easily request adjustments and review the generated results at each stage.

[0666] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0667] Step 1:

[0668] The user provides the input data.

[0669] Users use their devices to provide the system with input data such as target customer segments, product information, and advertising themes.

[0670] Input: Target customer base, product information, advertising theme, etc.

[0671] Output: Input data is sent to the server.

[0672] Specific operation:

[0673] The user enters the following into their device: "Target customer base: Women, 20-30 years old", "Product information: New floral perfume", and "Advertising theme: Spring".

[0674] When the user clicks the "Submit" button, the input data is sent to the server.

[0675] Step 2:

[0676] The server receives the input data.

[0677] The server receives input data sent from the user's terminal.

[0678] Input: Input data submitted by the user

[0679] Output: Received input data

[0680] Specific operation:

[0681] The server receives data sent from the terminal and stores it as input data.

[0682] Step 3:

[0683] The server sends a request to the generative artificial intelligence.

[0684] The server sends a request to a generative artificial intelligence (AI) to generate advertising copy based on the input data.

[0685] Input: Received input data

[0686] Output: Send a request to generate advertising copy to a generative AI.

[0687] Specific operation:

[0688] The server generates and sends the prompt "Spring, New release, Floral, Perfume, For women" to the AI ​​model.

[0689] Step 4:

[0690] Generative artificial intelligence generates advertising copy.

[0691] Generative artificial intelligence generates advertising text based on requests from a server.

[0692] Input: Server request (prompt)

[0693] Output: Generated advertisement text

[0694] Specific operation:

[0695] A generative AI model analyzes the prompt and generates the tagline, "Let's let the scent of spring blossom in our hearts."

[0696] Step 5:

[0697] The server receives the generated advertisement text.

[0698] The server receives advertising text generated by a generative artificial intelligence system and stores it in a database.

[0699] Input: Advertising text generated by a generative artificial intelligence.

[0700] Output: Advertisement text stored in the database

[0701] Specific operation:

[0702] The server receives the generated advertisement text and saves it to the database.

[0703] Step 6:

[0704] The server sends a request to the image generation tool.

[0705] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data.

[0706] Input: Generated ad copy, received input data

[0707] Output: Send a request to the image generation tool.

[0708] Specific operation:

[0709] The server sends a request to the image generation tool that includes the keywords "spring, floral, perfume, feminine, elegant image".

[0710] Step 7:

[0711] Image generation tool generates advertising images

[0712] The image generation tool generates advertising images based on requests from the server.

[0713] Input: Server request

[0714] Output: Generated ad images

[0715] Specific operation:

[0716] The image generation tool analyzes the request and generates an advertising image for an elegant floral perfume.

[0717] Step 8:

[0718] The server receives the generated ad images.

[0719] The server receives the advertising images generated by the image generation tool and stores them in the database.

[0720] Input: Advertisement image generated from an image generation tool

[0721] Output: Advertisement images stored in the database

[0722] Specific operation:

[0723] The server receives the generated ad image and saves it to the database.

[0724] Step 9:

[0725] The server creates the ad creative.

[0726] The server retrieves generated advertising copy and images from a database and automatically generates advertising creatives by combining them.

[0727] Input: Advertising text and images retrieved from the database

[0728] Output: Generated ad creative

[0729] Specific operation:

[0730] The server lays out the promotional text and ad images, and generates the ad creative.

[0731] Step 10:

[0732] The server presents the generated results to the user.

[0733] The server sends the generated ad creative to the user's device and presents it to the user.

[0734] Input: Generated ad creative

[0735] Output: Ad creative sent to the user's device

[0736] Specific operation:

[0737] The server displays the advertising creative on the device via a pre-configured user interface.

[0738] Step 11:

[0739] The user reviews the generated results and gives instructions for adjustments.

[0740] Users can review the ad creatives generated on their devices and request adjustments or changes as needed.

[0741] Input: Adjustment request from the user

[0742] Output: Coordination request sent to the server

[0743] Specific operation:

[0744] The user reviews the creative on their device's interface, enters any necessary adjustments such as "I want to make the tagline a little shorter," and then submits it.

[0745] Step 12:

[0746] The server will regenerate.

[0747] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[0748] Input: Adjustment request from the user

[0749] Output: Regenerated ad creative

[0750] Specific operation:

[0751] The server generates a new prompt and sends another request to the AI ​​model and image generation tool.

[0752] A new tagline and image are generated, and the creative is regenerated again.

[0753] Step 13:

[0754] The user performs a final check.

[0755] The user reviews the final ad creative on their device and confirms that there are no problems.

[0756] Input: Regenerated ad creative

[0757] Output: Final verification results, no feedback.

[0758] Specific operation:

[0759] The user performs a final check and clicks the "Complete" button if they determine there are no problems.

[0760] Step 14:

[0761] The server outputs the file.

[0762] The server outputs the final ad creative as a file in the appropriate format and provides the user with a download link.

[0763] Input: Final approved ad creative

[0764] Output: Files output in the appropriate format (e.g., JPEG, PNG) and a download link.

[0765] Specific operation:

[0766] The server saves the ad creative in JPEG format and provides the user with a download link.

[0767] (Application Example 1)

[0768] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0769] Traditionally, the process of creating advertising creatives has been time-consuming and labor-intensive, requiring specialized knowledge and skills, especially for small businesses and individuals, making it difficult to create efficient and effective advertisements. Furthermore, the limited available materials made it difficult to quickly generate advertisements tailored to target customer segments. This resulted in an inability to adapt to situations requiring short-term advertising deployments, negatively impacting customer acquisition and sales.

[0770] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0771] In this invention, the server includes means for receiving input data, means for generating advertising copy using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising copy and the input data, means for generating advertising creative by combining the generated advertising copy and advertising images, means for a user interface for reviewing and adjusting the generated advertising creative, means for the user to provide input data such as target customer base, product information, and advertising theme using a smartphone, and means for presenting the generated advertising creative to the user's smartphone and accepting user review and adjustments. This makes it possible to generate advertising creative efficiently and effectively and create high-quality advertisements in a short amount of time.

[0772] "Input data" refers to information provided by the user, such as the target customer base, product information, and advertising theme.

[0773] "Generative artificial intelligence" refers to an AI system that generates advertising copy based on input data.

[0774] "Advertising copy" refers to catchphrases and messages for advertisements created by generative artificial intelligence.

[0775] An "image generation tool" is software or a system that generates advertising images based on generated advertising text and input data.

[0776] "Advertising images" are visual advertising materials created using image generation tools.

[0777] "Advertising creative" refers to the final advertising work created by combining the generated advertising copy and advertising images.

[0778] A "user interface means" is an interface that allows users to review and adjust the generated advertising creative.

[0779] A "smartphone" is a personal information device used by users to provide input data and to review and adjust the generated advertising creatives.

[0780] The system implementing this invention mainly consists of a smartphone and a server. The user provides input data such as target customer base, product information, and advertising theme using the smartphone. The server receives this data and generates advertising copy using generative artificial intelligence (AI). Based on the generated advertising copy and input data, the server generates advertising images using an image generation tool. Subsequently, the generated advertising copy and advertising images are combined to create advertising creatives, which are then presented to the user via the smartphone for review and adjustment.

[0781] The server uses the following hardware and software:

[0782] Generative artificial intelligence: For generative AI models, we use, for example, OpenAI's GPT-4 or Google Cloud AI's Text Generation API.

[0783] Image generation tools: Use image generation APIs such as DALL-E 2 or MidJourney.

[0784] Database: A database solution for storing and managing generated data (e.g., MySQL, PostgreSQL).

[0785] Specifically, the server receives input data sent by the user and first sends a prompt to the generation AI model to generate advertising text. Examples of such prompts include the following:

[0786] Product Information: "Organic Soap", Target Customer Base: "Naturally-minded women in their 20s", Theme: "Autumn New Product Campaign"

[0787] Based on this prompt, the generative AI model generates the following advertisement:

[0788] Experience the refreshing feeling of autumn with natural soap.

[0789] Next, based on the generated ad copy and input data, the server sends a request to the image generation tool to generate the ad image. For example, the request may include the following:

[0790] The advertisement image for the natural-looking organic soap features a design inspired by autumn scenery and organic ingredients.

[0791] The generated images and ad copy are integrated to automatically create ad creatives. The created ad creatives are sent to the user's smartphone, where the user reviews them and sends adjustment requests to the server as needed. The server then uses generative artificial intelligence and image generation tools to generate new ad copy and ad images, updating the ad creatives again.

[0792] In this way, users can create high-quality advertising creatives quickly and efficiently. A major advantage of this invention is that it allows small businesses and individuals, in particular, to quickly create effective advertisements without requiring specialized knowledge or skills.

[0793] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0794] Step 1:

[0795] Users input data such as target customer segment, product information, and advertising theme using their smartphones. Specifically, users open a dedicated application and enter data such as "Target customer segment: Women in their 20s," "Product information: Organic soap," and "Advertising theme: Autumn new product campaign" into a form. This data is then sent from the smartphone to the server.

[0796] Step 2:

[0797] The server receives input data sent by the user. This input data includes the target customer base, product information, and the theme of the advertisement. Based on this data, the server generates a prompt and sends it to a generative artificial intelligence (AI). An example of such a prompt is: "Product information: Organic soap, Target customer base: Women in their 20s, Theme: Autumn new product campaign".

[0798] Step 3:

[0799] A generative artificial intelligence generates advertising copy based on prompt text received from the server. For example, based on the prompt text, a tagline such as "Enjoy the refreshing feeling of autumn with natural soap" is generated. This generated advertising copy is then sent to the server.

[0800] Step 4:

[0801] The server receives the generated ad copy and saves it to the database. At the same time, it sends a request to the image generation tool for generating the ad image. This request includes the generated ad copy and input data. For example, the request might be for "an ad image for a natural-tasting organic soap, with a design inspired by autumn scenery and organic materials."

[0802] Step 5:

[0803] The image generation tool generates an advertising image based on a request received from the server. The generated advertising image is sent to the server. Specifically, an image of "organic soap displayed against an autumn background" is generated.

[0804] Step 6:

[0805] The server receives the generated ad images and stores them in a database. Next, it combines the received ad copy and images to create ad creatives. This automatically generates visually appealing ad materials.

[0806] Step 7:

[0807] The server sends the generated ad creative to the user's smartphone. The user reviews the ad creative on their smartphone and requests adjustments or modifications as needed. For example, they might send a request to "make the tagline a little shorter."

[0808] Step 8:

[0809] The server receives the adjustment request from the user and sends another request to the generative artificial intelligence and image generation tools. This generates new taglines and advertising images, and the advertising creative is updated again.

[0810] Step 9:

[0811] The user reviews the final ad creative on their smartphone to confirm there are no issues. The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link. This allows the user to quickly obtain high-quality ad creatives.

[0812] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0813] This invention relates to a system that automatically generates advertising creatives by generating advertising copy using generative artificial intelligence (AI) based on input data, generating advertising images using an image generation tool, and incorporating an emotion engine that recognizes the user's emotional state. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[0814] Program Processing Overview

[0815] 1. User input

[0816] The user provides input data on the device:

[0817] Users provide the system with input data such as target customer segments, product information, and advertising themes using their devices. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[0818] 2. Recognition of emotional states

[0819] The server uses an emotion engine to analyze the user's emotional state:

[0820] The server analyzes voice, facial expressions, or text data acquired from the user's device, and the emotion engine recognizes the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive."

[0821] 3. Generating a catchy slogan

[0822] The server sends a request to the generative artificial intelligence to generate advertising copy:

[0823] The server creates and sends a request to the generative artificial intelligence (AI) to generate advertising copy based on the input data and the user's emotional state. The AI ​​then generates a tagline based on this request. For example, based on the input data and positive emotions, it might generate the tagline, "Let the scent of spring blossom in your heart."

[0824] The server receives the generated advertisement:

[0825] The server receives the tagline generated by the generative artificial intelligence and stores it in a database. This advertising copy is used in the next step.

[0826] 4. Generating advertising images

[0827] The server sends a request to the image generation tool:

[0828] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy, input data, and the user's emotional state. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[0829] The server receives the generated ad image:

[0830] The server receives the advertising images generated by the image generation tool and stores them in the database. These advertising images are then used in the next step.

[0831] 5. Generating advertising creatives

[0832] The server creates the ad creative:

[0833] The server automatically generates ad creatives by combining the generated ad copy, ad images, and the user's emotional state.

[0834] 6. Review and adjust results

[0835] The server presents the generated results to the user:

[0836] The server sends the generated ad creative to the user's device and presents it to the user.

[0837] The user reviews the generated results and provides instructions for adjustments:

[0838] Users can review the ad creative generated on their device and enter requests for adjustments or changes as needed. For example, they might enter additional requests such as, "Could you make the tagline a little shorter?"

[0839] The server will regenerate:

[0840] The server then sends another request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[0841] 7. Final Output

[0842] User final confirmation:

[0843] The user reviews the final ad creative on their device and confirms that there are no problems.

[0844] The server outputs a file:

[0845] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[0846] This invention allows users to create high-quality advertising creatives in a short amount of time, significantly reducing time and costs. Furthermore, it enables the generation of advertising creatives that respond to the user's emotional state, allowing for the delivery of more appropriate and effective advertisements.

[0847] The following describes the processing flow.

[0848] Step 1:

[0849] The user logs into the system to begin creating ad creatives on their device. A user ID and password are required for login.

[0850] Step 2:

[0851] Users provide input data such as target customer segments, product information, and advertising themes to input forms using their devices. For example, for an advertising theme of "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[0852] Step 3:

[0853] The user submits the input data to the system by pressing the submit button. The input data is received by the server and stored in the database.

[0854] Step 4:

[0855] The server uses an emotion engine to analyze voice, facial, or text data acquired from the user's device to recognize the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive."

[0856] Step 5:

[0857] The server combines emotional state information obtained from the emotion engine and creates a request for promotional text generation from the generative artificial intelligence. The request includes input data and the user's emotional state (e.g., "positive").

[0858] Step 6:

[0859] The server sends a request to a generative artificial intelligence (AI), which generates a catchy slogan based on the input data and emotional state information. For example, it might generate the slogan, "Let the scent of spring blossom in your heart."

[0860] Step 7:

[0861] The server receives the advertising copy generated by the generative artificial intelligence and stores it in a database. This advertising copy is then used in the next step.

[0862] Step 8:

[0863] The server creates a request to the image generation tool to generate an advertising image based on the generated ad copy, input data, and sentiment state information. The request includes keywords such as "spring, floral, perfume, women's, elegant image."

[0864] Step 9:

[0865] The server sends a request to an image generation tool, which generates an advertising image based on the input data, advertising text, and sentiment information. For example, it might generate an image of an elegant (floral) perfume bottle.

[0866] Step 10:

[0867] The server receives the advertising image generated by the image generation tool and stores it in the database. This advertising image is used in the next step.

[0868] Step 11:

[0869] The server retrieves promotional text and ad images generated from the database, combines them, and automatically generates ad creatives. Emotional state information is also taken into consideration.

[0870] Step 12:

[0871] The server sends the generated ad creative to the user's device and presents it to the user.

[0872] Step 13:

[0873] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might request, "I'd like the tagline to be a little shorter."

[0874] Step 14:

[0875] The server receives the user's adjustment request and sends a regeneration request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[0876] Step 15:

[0877] The server resends the regenerated ad creative to the user's device and presents it to the user.

[0878] Step 16:

[0879] The user reviews the final ad creative on their device and confirms that there are no problems.

[0880] Step 17:

[0881] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[0882] (Example 2)

[0883] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0884] The modern advertising industry demands the rapid generation of high-quality advertising creatives. However, doing this manually is time-consuming and costly, and creating ads that reflect user emotions and needs is even more difficult. Furthermore, traditional systems have the problem of not being able to flexibly regenerate the advertising copy and images that users desire.

[0885] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data using a terminal, means for generating advertising copy using a generation AI model based on the input data and the user's emotional state, and means for generating advertising images using an image generation tool based on the generated advertising copy, the emotional state, and the input data. This enables the automatic generation of high-quality advertising creatives that are tailored to the user's emotional state. Furthermore, it is equipped with interface means for checking and adjusting the generated advertising creatives, and it is also possible to instruct the regeneration of advertising copy and advertising images, thereby realizing a flexible advertising creation process.

[0886] A "terminal" is a device used by a user to provide input data to a system, and generally refers to information processing devices such as computers and smartphones.

[0887] "Input data" refers to information that users provide to the system, including detailed data such as target customer segments, product information, and advertising themes.

[0888] "Emotional state" refers to data that represents a user's current emotions, and is classified as positive, negative, neutral, etc., by analyzing voice, facial expressions, text, etc.

[0889] A "generative AI model" is an artificial intelligence system that generates advertising copy based on input data and emotional states, and refers to, for example, a large-scale language model.

[0890] "Advertising text" refers to advertising wording such as copywriting and catchphrases generated by generative AI models.

[0891] An "image generation tool" refers to a system or software that generates advertising images based on input data, generated advertising text, and emotional states.

[0892] "Advertising images" refer to visual advertising elements generated by image generation tools, and include photographs, illustrations, graphic designs, etc.

[0893] "Advertising creative" refers to complete advertising content created by combining generated advertising copy and advertising images.

[0894] "Interface means" refers to means by which users can review and adjust generated advertising creatives, and generally includes user-friendly screens and operating methods.

[0895] This invention is a system that automatically generates advertising creatives by generating advertising copy using generative artificial intelligence (AI) based on input data, generating advertising images using an image generation tool, and incorporating an emotion engine that recognizes the user's emotional state. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[0896] First, the user uses their device to input the target customer base, product information, and advertising theme. For example, for an advertising theme of "New Spring Floral Perfume," they can input keywords such as "spring, floral, perfume, women's." Users can also provide voice and facial expression data. This data is transmitted to the server via the device.

[0897] Next, the server uses an emotion engine to analyze the voice, facial expressions, or text data provided by the user to recognize the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive." This emotion analysis is performed using tools such as IBM Watson's emotion analysis API.

[0898] Next, the server creates and sends a request to a generative AI model (e.g., OpenAI GPT-4) to generate advertising copy, based on the input data and the user's emotional state. The following are examples of the specific prompts used:

[0899] Based on the following keywords—"spring," "floral," "perfume," "women's," and "elegant"—and the user's emotional state—"positive," please generate a tagline for a new floral perfume.

[0900] The generative AI model generates a tagline based on this request, creating an advertisement such as, "Let the scent of spring blossom in your heart." The generated advertisement is received by the server and stored in the database.

[0901] The server then sends a request to an image generation tool (e.g., MidJourney or DALL-E) to generate an advertising image, based on the generated ad copy, input data, and the user's emotional state. The prompt might look something like this:

[0902] Please generate an ad image based on the keywords "spring, floral, perfume, women's, elegant image".

[0903] The image generation tool generates an advertisement image based on this prompt, creating an image that, for example, includes an elegant background and a floral design. The generated advertisement image is also received by the server and stored in the database.

[0904] Ultimately, the server combines the generated ad copy, ad images, and sentiment state to create ad creatives. The generated ad creatives are presented to the user through a user interface. The user can review the generated ad creatives and, if necessary, instruct the server to regenerate the ad copy and ad images. Upon receiving a regeneration request, the server sends new prompts to the generation AI model and image generation tools to generate new ad copy and ad images.

[0905] This system enables users to efficiently generate high-quality ad creatives, saving both time and money. Furthermore, it allows for the creation of ad creatives tailored to the user's emotional state, providing personalized and effective advertising.

[0906] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0907] Step 1:

[0908] The user provides input data on their device.

[0909] The user uses a terminal to input data such as target customer segment, product information, and advertising theme into the system. Specifically, the user enters the advertising theme "New Spring Floral Perfume" and keywords such as "spring, floral, perfume, for women" into the input form on the terminal. The entered data is then sent from the terminal to the server.

[0910] Input: Target customer base, product information, advertising theme, keywords

[0911] Output: Send input data to the server

[0912] Step 2:

[0913] The server uses an emotion engine to analyze the user's emotional state.

[0914] The server acquires voice data, facial expression data, and text data sent from the terminal. Next, it sends this data to the emotion engine for analysis to recognize the user's emotional state. For example, if the user's facial expression is smiling, the emotion engine recognizes it as "positive."

[0915] Input: Audio data, facial expression data, text data

[0916] Output: User's emotional state (e.g., positive)

[0917] Step 3:

[0918] The server sends a request to the AI ​​model to generate advertising copy.

[0919] The server creates a request to the AI ​​model to generate advertising copy based on the input data and the user's emotional state. The prompt text includes the advertising theme and emotional state. For example, it generates a prompt text like the following:

[0920] Based on the following keywords—"spring," "floral," "perfume," "women's," and "elegant"—and the user's emotional state—"positive," please generate a tagline for a new floral perfume.

[0921] The generative AI model generates catchphrases based on this.

[0922] Input: Input data, user's emotional state

[0923] Output: Prompt text for the generating AI model, generated catchphrase

[0924] Step 4:

[0925] The server receives the generated advertisement text.

[0926] The server receives the catchphrase from the generating AI model and saves it to the database. Let's assume the generated catchphrase is "Let's let the scent of spring blossom in our hearts."

[0927] Input: Catchphrases from a generated AI model

[0928] Output: Catchphrases stored in the database

[0929] Step 5:

[0930] The server sends a request to the image generation tool.

[0931] The server sends a request to the image generation tool to generate an advertising image based on the generated tagline, input data, and the user's emotional state. The prompt message will use something like the following:

[0932] Please generate an ad image based on the keywords "spring, floral, perfume, women's, elegant image".

[0933] The image generation tool generates advertising images based on this.

[0934] Input: Generated tagline, input data, user's emotional state

[0935] Output: Prompt text for the image generation tool, generated advertisement image

[0936] Step 6:

[0937] The server receives the generated ad images.

[0938] The server receives the advertising images generated by the image generation tool and stores them in the database.

[0939] Input: Advertisement image from an image generation tool

[0940] Output: Advertisement images stored in the database

[0941] Step 7:

[0942] The server creates the ad creative.

[0943] The server automatically generates ad creatives by combining the generated ad copy, ad images, and emotional states. For example, it might place the tagline "Let the scent of spring blossom in your heart" on an elegant background image.

[0944] Input: Generated ad copy, ad image, sentiment state

[0945] Output: Generated ad creative

[0946] Step 8:

[0947] The server presents the generated results to the user.

[0948] The server sends the generated ad creative to the user's device and displays it.

[0949] Input: Generated ad creative

[0950] Output: Generated results sent to the user's terminal

[0951] Step 9:

[0952] The user reviews the generated results and gives instructions for adjustments.

[0953] Users can review the ad creative generated on their device and enter requests for adjustments or changes as needed. For example, they can enter specific requests such as "I'd like the tagline to be a little shorter" or "I'd like to change the background color."

[0954] Input: Generated ad creative, user adjustment requests

[0955] Output: Sending adjustment request to the server

[0956] Step 10:

[0957] The server will regenerate.

[0958] The server processes the adjustment requests collected through the user interface, sends new prompt messages to the generation AI model and image generation tools, and generates new promotional text and advertising images.

[0959] Input: User adjustment request

[0960] Output: New prompt text, new promotional text, and advertising image

[0961] Step 11:

[0962] The user performs a final check.

[0963] The user reviews the final ad creative on their device and confirms that there are no problems.

[0964] Input: Regenerated ad creative

[0965] Output: User's final approval

[0966] Step 12:

[0967] The server outputs the file.

[0968] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link. Through this link, the user can obtain the final ad creative.

[0969] Input: Final ad creative

[0970] Output: Download link

[0971] (Application Example 2)

[0972] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0973] Current methods for generating ad creatives are time-consuming and labor-intensive, as advertisers must manually create and combine promotional text and images. Furthermore, because ads are created uniformly, it's difficult to provide personalized ads tailored to individual users' emotional states and destination information. This results in limited ad effectiveness.

[0974] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0975] In this invention, the server includes means for receiving input data, means for generating advertising text using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising text and the input data, means for generating advertising creative by combining the generated advertising text and advertising images, user interface means for checking and adjusting the generated advertising creative, means for acquiring passenger destination information, means for recognizing passenger emotional states, and means for generating advertising text and advertising images as personalized advertisements based on the passenger destination information and emotional states. This makes it possible to automatically generate highly effective personalized advertisements tailored to the emotional states and destination information of individual users and provide them in a short amount of time.

[0976] "Input data" refers to information provided by the user to the system for generating advertisements, including, for example, target customer segments, product information, and themes of advertisements.

[0977] "Generative artificial intelligence" refers to an artificial intelligence program that automatically generates advertising copy based on input data.

[0978] An "image generation tool" is a software tool that automatically generates advertising images based on generated advertising text and input data.

[0979] "Advertising creative" refers to advertising materials created by combining generated advertising copy and advertising images.

[0980] A "user interface means" is an interface means that allows the user to review the generated advertising creative and instruct it to be adjusted or regenerated as needed.

[0981] "Destination information" refers to information about the destination set by the passenger.

[0982] "Emotional state" refers to information that represents a passenger's emotions, and is analyzed from, for example, facial expressions and tone of voice.

[0983] "Personalized advertising" refers to advertisements that are individually tailored based on a passenger's destination information and emotional state.

[0984] In order to implement the system of the present invention, the following program must be implemented. This program automatically generates advertising creatives based on user input data and provides personalized advertisements to the user.

[0985] Program Processing Overview

[0986] 1. Receiving input data:

[0987] The system receives information necessary for ad generation from the user's device, such as target customer segment, product information, and ad theme, and sends it to the server.

[0988] 2. Obtaining destination information:

[0989] The server retrieves destination information from the system inside the passenger's autonomous vehicle.

[0990] 3. Recognition of emotional states:

[0991] The server uses emotion recognition software to analyze passengers' camera and audio streams, including their smiles and tone of voice, to recognize their emotional state. This emotion recognition software is called "EmotionRecognition."

[0992] 4. Generating promotional text:

[0993] The server uses generative artificial intelligence (AI text generator) to generate promotional text based on the passenger's emotional state and destination information. For example, it might use a prompt such as, "Generate a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring."

[0994] 5. Generating advertising images:

[0995] The server uses an image generation tool (AI image generator) to generate personalized advertising images based on the generated promotional text and destination information. For example, it might use a prompt such as, "Generate a beautiful image that reflects spring, Tokyo Tower, tourism, and positive emotions."

[0996] 6. Generating ad creatives:

[0997] The server combines the generated promotional text and advertising images to create personalized ads as advertising creatives.

[0998] 7. Display of advertisements:

[0999] The server displays the generated ad creatives on displays inside the autonomous vehicle and on passengers' smart devices (smartphones and head-mounted displays).

[1000] 8. Verification and adjustment via the user interface:

[1001] Users review the displayed ad creatives and instruct the system to adjust or regenerate them as needed.

[1002] Hardware and software to be used

[1003] Camera and microphone: Devices for detecting the emotional state of passengers.

[1004] Autonomous vehicle display: A device for displaying advertisements.

[1005] Smart devices (smartphones, head-mounted displays): Devices used to display advertisements individually.

[1006] EmotionRecognition: Emotion recognition software. Analyzes passengers' emotional states in real time.

[1007] AI Text Generator: A generative artificial intelligence system. It generates advertising text based on emotional states and destination information.

[1008] AI Image Generator: Image generation tool. Generates advertising images.

[1009] Specific examples and prompt statements

[1010] For example, if a passenger is heading to "Tokyo Tower," use the following prompt:

[1011] EmotionRecognition:

[1012] "Use the camera and audio streams to determine if the passenger is smiling."

[1013] AI Text Generator:

[1014] "Please create a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring."

[1015] AI Image Generator:

[1016] "Please generate a beautiful image that reflects spring, Tokyo Tower, sightseeing, and positive emotions."

[1017] This embodiment makes it possible to automatically generate highly effective personalized advertisements tailored to each user's emotional state and destination information, and deliver them in a short amount of time.

[1018] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1019] Step 1:

[1020] The user's device inputs the information necessary for ad generation and sends it to the server. The input data includes target customer segment, product information, and ad theme. The server receives this data and uses it for further processing.

[1021] Step 2:

[1022] The server retrieves passenger destination information from the system within the autonomous vehicle. This destination information is used in a later processing step to personalize the advertisement content.

[1023] Step 3:

[1024] The server analyzes the camera and audio streams and uses emotion recognition software to recognize the passenger's emotional state. Specifically, it uses information such as whether the passenger is smiling and their tone of voice to classify their emotional state as "positive" or "negative." This allows the emotional state to be determined.

[1025] Step 4:

[1026] Based on emotional states and destination information, the server sends prompts to a generative artificial intelligence (AI text generator) to generate appropriate advertising copy. For example, if the prompt is "Generate a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring," the generated slogan will be output.

[1027] Step 5:

[1028] The server sends prompts to an image generation tool (AI image generator) based on the advertisement text and destination information, and generates an advertising image. For example, if the prompt is "Generate a beautiful image that reflects spring, Tokyo Tower, tourism, and positive emotions," the generated image will be output.

[1029] Step 6:

[1030] The server combines the generated promotional text and advertising images to create advertising creatives. Specifically, the generated text is placed on the images, resulting in visually appealing advertising materials.

[1031] Step 7:

[1032] The server sends the generated ad creatives to displays in the autonomous vehicle and to passengers' smart devices for display. This allows passengers to visually see personalized ads while on their way to their destination.

[1033] Step 8:

[1034] Users review the displayed ad creative and instruct it to be adjusted or regenerated as needed. Specifically, they request revisions to the tagline or regeneration of images through the user interface. This request is sent to the server, the regeneration process is performed again, and a new ad creative is created.

[1035] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1036] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1037] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1038] [Third Embodiment]

[1039] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1040] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1041] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1042] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1043] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1044] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1045] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1046] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1047] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1048] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1049] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1050] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1051] This invention relates to a system for automatically generating advertising creatives. Specifically, it is a system that generates advertising copy using generative artificial intelligence (AI) based on input data, and further generates advertising images using an image generation tool. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[1052] Program Processing Overview

[1053] 1. User input

[1054] The user provides input data on the device:

[1055] Users provide the system with input data such as target customer segments, product information, and advertising themes using their devices. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[1056] 2. Generating a catchy slogan

[1057] The server receives the input data:

[1058] The server receives input data sent by the user from the terminal and passes it on to the generative artificial intelligence.

[1059] The server sends a request to the generative artificial intelligence:

[1060] The server sends a request to the generative artificial intelligence to generate advertising copy based on the input data. The generative artificial intelligence then generates a tagline based on this request. For example, from the input data, it might generate the tagline "Let the scent of spring blossom in your heart."

[1061] The server receives the generated advertisement:

[1062] The server receives catchphrases generated by the generative artificial intelligence and stores them in a database.

[1063] 3. Generating advertising images

[1064] The server sends a request to the image generation tool:

[1065] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[1066] The server receives the generated ad image:

[1067] The server receives the advertising images generated by the image generation tool and stores them in the database.

[1068] 4. Generating advertising creatives

[1069] The server creates the ad creative:

[1070] The server retrieves generated advertising copy and images from a database and automatically generates advertising creatives by combining them.

[1071] 5. Review and adjust results

[1072] The server presents the generated results to the user:

[1073] The server sends the generated ad creative to the user's device and presents it to the user.

[1074] The user reviews the generated results and provides instructions for adjustments:

[1075] Users can review the ad creatives generated on their devices and request adjustments or changes as needed. For example, they can send a request to the server to "make the tagline a little shorter."

[1076] The server will regenerate:

[1077] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[1078] 6. Final Output

[1079] User final confirmation:

[1080] The user reviews the final ad creative on their device and confirms that there are no problems.

[1081] The server outputs a file:

[1082] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[1083] This invention allows users to create advertising creatives in a short amount of time, significantly reducing time and costs. Furthermore, because high-quality advertising copy and images are automatically generated based on the input data, it is possible to quickly deliver consistent and effective advertisements.

[1084] The following describes the processing flow.

[1085] Step 1:

[1086] The user logs into the system to begin creating ad creatives on their device. A user ID and password are required for login.

[1087] Step 2:

[1088] Users provide input data such as target customer segments, product information, and advertising themes to an input screen using their devices. For example, for an advertising theme of "New Spring Floral Perfume," users might input keywords such as "spring, floral, perfume, for women."

[1089] Step 3:

[1090] The user submits the input data to the system by pressing the submit button. This input data is used to generate the ad creative.

[1091] Step 4:

[1092] The server receives input data sent from the terminal and stores it in the database. This data is used in subsequent generation processes.

[1093] Step 5:

[1094] The server creates a request to the generative artificial intelligence to generate advertising copy based on the input data. The request includes keywords such as "spring, floral, perfume, women's."

[1095] Step 6:

[1096] The server sends a request to a generative artificial intelligence (AI), which generates advertising copy (catchphrases) based on the input data. For example, it might generate the catchphrase, "Let the scent of spring blossom in your heart."

[1097] Step 7:

[1098] The server receives the advertising copy generated by the generative artificial intelligence and stores it in a database. This advertising copy is then used in the next step.

[1099] Step 8:

[1100] The server creates a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. The request includes keywords such as "spring, floral, perfume, women's, elegant image".

[1101] Step 9:

[1102] The server sends a request to an image generation tool, which generates an advertising image based on the input data and advertising text. For example, it might generate an image of an elegant (floral) perfume bottle.

[1103] Step 10:

[1104] The server receives the advertising image generated by the image generation tool and stores it in the database. This advertising image is used in the next step.

[1105] Step 11:

[1106] The server retrieves promotional text and advertising images generated from the database, and automatically generates advertising creatives by combining them.

[1107] Step 12:

[1108] The server sends the generated ad creative to the user's device and presents it to the user.

[1109] Step 13:

[1110] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might submit additional requests such as, "Could you make the tagline a little shorter?"

[1111] Step 14:

[1112] The server receives the user's adjustment request and sends a regeneration request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[1113] Step 15:

[1114] The server resends the regenerated ad creative to the user's device and presents it to the user.

[1115] Step 16:

[1116] The user reviews the final ad creative on their device and confirms that there are no problems.

[1117] Step 17:

[1118] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[1119] (Example 1)

[1120] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1121] Traditional advertising creative generation was time-consuming and costly, and it was difficult to deliver consistent and effective advertisements quickly. Furthermore, realizing the advertising image that users envisioned required considerable effort and expertise. In addition, the difficulty in regenerating advertising copy and images made it difficult to adjust the content of advertisements on a case-by-case basis. As a result, there were challenges such as decreased efficiency in marketing activities and limitations on the quality and impact of advertisements.

[1122] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1123] In this invention, the server includes means for receiving input data, means for generating advertising text using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising text and the input data, means for generating advertising creative by combining the generated advertising text and advertising images, user interface means for reviewing and adjusting the generated advertising creative, and means for finally outputting the generated advertising creative. This makes it possible to generate high-quality advertising creative in a short time and to quickly provide effective advertisements while maintaining consistency. In addition, since users can easily make adjustment requests and instruct the regeneration of advertising text and images, more flexible and adaptable advertising creation is realized.

[1124] "Input data" refers to information that users provide to the system, such as target customer segments, product information, and advertising themes.

[1125] "Generative artificial intelligence" is an artificial intelligence technology that generates advertising copy based on input data provided by the user.

[1126] "Advertising copy" refers to advertising slogans and messages generated by generative artificial intelligence.

[1127] An "image generation tool" is software or hardware used to generate advertising images based on input data and generated advertising text.

[1128] An "advertising image" is a visual element for advertising that is generated using an image generation tool.

[1129] "Advertising creative" refers to the final form of an advertisement, created by combining the generated advertising copy and advertising images.

[1130] A "user interface means" is an interface that allows users to review and adjust generated advertising creatives.

[1131] "The means of final output" refers to the function of outputting the generated advertising creative as a file in an appropriate format and providing it to the user.

[1132] A "server" is a computer that operates the entire system and performs various generation processes and data management.

[1133] This invention relates to a system for automatically generating advertising creatives. Specifically, it is a system that generates advertising copy using generative artificial intelligence (AI) based on input data, and further generates advertising images using an image generation tool. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[1134] Hardware and software configuration

[1135] server:

[1136] The server is a computer that operates the entire system and performs various generation processes and data management. The server receives input data, sends requests to the generative artificial intelligence, and processes the storage and regeneration requests of the generated data.

[1137] Terminal:

[1138] Users access the system using a device. The device provides an interface for users to provide input data and to review and adjust the generated ad creatives.

[1139] Generative artificial intelligence models:

[1140] Generative artificial intelligence models are AI technologies used to generate advertising copy based on input data. For example, natural language processing (NLP) models fulfill this role.

[1141] Image generation tool:

[1142] Image generation tools are tools for generating images for advertisements based on input data and generated advertising text. For example, an AI model for image generation can fulfill this role.

[1143] Specific methods for data processing and data calculation

[1144] This system performs data processing and calculations using the following methods.

[1145] 1. The user provides the input data:

[1146] Users provide input data to the system using their devices, such as target customer segments, product information, and advertising themes. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[1147] 2. The server receives the input data and passes it to the generative artificial intelligence:

[1148] The server receives input data sent by the user and passes it to the generative artificial intelligence. The generative artificial intelligence generates advertising text based on this input data.

[1149] 3. The server receives the generated advertisement text and saves it to the database:

[1150] The system receives advertising copy generated by a generative artificial intelligence and stores it in a database.

[1151] 4. The server sends a request to the image generation tool:

[1152] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[1153] 5. The server receives the generated ad image and saves it to the database:

[1154] The server receives the advertising images generated by the image generation tool and stores them in the database.

[1155] 6. The server creates the ad creative:

[1156] The generated advertising copy and images are retrieved from a database, and they are combined to automatically generate advertising creatives.

[1157] 7. The server presents the generated results to the user:

[1158] The server sends the generated ad creative to the user's device and presents it to the user.

[1159] 8. The user reviews the generated results and provides instructions for adjustments:

[1160] Users can review the ad creatives generated on their devices and request adjustments or changes as needed. For example, they can send a request to the server to "make the tagline a little shorter."

[1161] 9. The server performs regeneration:

[1162] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[1163] 10. The user performs final confirmation:

[1164] The user reviews the final ad creative on their device and confirms that there are no problems.

[1165] 11. The server outputs the file:

[1166] The server outputs the final ad creative in the appropriate format and provides the user with a download link.

[1167] Example of a prompt

[1168] prompt:

[1169] Advertisement theme: New spring floral perfumes

[1170] Target customer base: Women, 20-30 years old

[1171] Keywords: Spring, Floral, Perfume, Elegant

[1172] This system allows users to generate high-quality ad creatives in a short amount of time, significantly reducing time and costs. It also enables the rapid delivery of consistent and highly effective ads, allowing users to easily request adjustments and review the generated results at each stage.

[1173] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1174] Step 1:

[1175] The user provides the input data.

[1176] Users use their devices to provide the system with input data such as target customer segments, product information, and advertising themes.

[1177] Input: Target customer base, product information, advertising theme, etc.

[1178] Output: Input data is sent to the server.

[1179] Specific operation:

[1180] The user enters the following into their device: "Target customer base: Women, 20-30 years old", "Product information: New floral perfume", and "Advertising theme: Spring".

[1181] When the user clicks the "Submit" button, the input data is sent to the server.

[1182] Step 2:

[1183] The server receives the input data.

[1184] The server receives input data sent from the user's terminal.

[1185] Input: Input data submitted by the user

[1186] Output: Received input data

[1187] Specific operation:

[1188] The server receives data sent from the terminal and stores it as input data.

[1189] Step 3:

[1190] The server sends a request to the generative artificial intelligence.

[1191] The server sends a request to a generative artificial intelligence (AI) to generate advertising copy based on the input data.

[1192] Input: Received input data

[1193] Output: Send a request to generate advertising copy to a generative AI.

[1194] Specific operation:

[1195] The server generates and sends the prompt "Spring, New release, Floral, Perfume, For women" to the AI ​​model.

[1196] Step 4:

[1197] Generative artificial intelligence generates advertising copy.

[1198] Generative artificial intelligence generates advertising text based on requests from a server.

[1199] Input: Server request (prompt)

[1200] Output: Generated advertisement text

[1201] Specific operation:

[1202] A generative AI model analyzes the prompt and generates the tagline, "Let's let the scent of spring blossom in our hearts."

[1203] Step 5:

[1204] The server receives the generated advertisement text.

[1205] The server receives advertising text generated by a generative artificial intelligence system and stores it in a database.

[1206] Input: Advertising text generated by a generative artificial intelligence.

[1207] Output: Advertisement text stored in the database

[1208] Specific operation:

[1209] The server receives the generated advertisement text and saves it to the database.

[1210] Step 6:

[1211] The server sends a request to the image generation tool.

[1212] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data.

[1213] Input: Generated ad copy, received input data

[1214] Output: Send a request to the image generation tool.

[1215] Specific operation:

[1216] The server sends a request to the image generation tool that includes the keywords "spring, floral, perfume, feminine, elegant image".

[1217] Step 7:

[1218] Image generation tool generates advertising images

[1219] The image generation tool generates advertising images based on requests from the server.

[1220] Input: Server request

[1221] Output: Generated ad images

[1222] Specific operation:

[1223] The image generation tool analyzes the request and generates an advertising image for an elegant floral perfume.

[1224] Step 8:

[1225] The server receives the generated ad images.

[1226] The server receives the advertising images generated by the image generation tool and stores them in the database.

[1227] Input: Advertisement image generated from an image generation tool

[1228] Output: Advertisement images stored in the database

[1229] Specific operation:

[1230] The server receives the generated ad image and saves it to the database.

[1231] Step 9:

[1232] The server creates the ad creative.

[1233] The server retrieves generated advertising copy and images from a database and automatically generates advertising creatives by combining them.

[1234] Input: Advertising text and images retrieved from the database

[1235] Output: Generated ad creative

[1236] Specific operation:

[1237] The server lays out the promotional text and ad images, and generates the ad creative.

[1238] Step 10:

[1239] The server presents the generated results to the user.

[1240] The server sends the generated ad creative to the user's device and presents it to the user.

[1241] Input: Generated ad creative

[1242] Output: Ad creative sent to the user's device

[1243] Specific operation:

[1244] The server displays the advertising creative on the device via a pre-configured user interface.

[1245] Step 11:

[1246] The user reviews the generated results and gives instructions for adjustments.

[1247] Users can review the ad creatives generated on their devices and request adjustments or changes as needed.

[1248] Input: Adjustment request from the user

[1249] Output: Coordination request sent to the server

[1250] Specific operation:

[1251] The user reviews the creative on their device's interface, enters any necessary adjustments such as "I want to make the tagline a little shorter," and then submits it.

[1252] Step 12:

[1253] The server will regenerate.

[1254] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[1255] Input: Adjustment request from the user

[1256] Output: Regenerated ad creative

[1257] Specific operation:

[1258] The server generates a new prompt and sends another request to the AI ​​model and image generation tool.

[1259] A new tagline and image are generated, and the creative is regenerated again.

[1260] Step 13:

[1261] The user performs a final check.

[1262] The user reviews the final ad creative on their device and confirms that there are no problems.

[1263] Input: Regenerated ad creative

[1264] Output: Final verification results, no feedback.

[1265] Specific operation:

[1266] The user performs a final check and clicks the "Complete" button if they determine there are no problems.

[1267] Step 14:

[1268] The server outputs the file.

[1269] The server outputs the final ad creative as a file in the appropriate format and provides the user with a download link.

[1270] Input: Final approved ad creative

[1271] Output: Files output in the appropriate format (e.g., JPEG, PNG) and a download link.

[1272] Specific operation:

[1273] The server saves the ad creative in JPEG format and provides the user with a download link.

[1274] (Application Example 1)

[1275] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1276] Traditionally, the process of creating advertising creatives has been time-consuming and labor-intensive, requiring specialized knowledge and skills, especially for small businesses and individuals, making it difficult to create efficient and effective advertisements. Furthermore, the limited available materials made it difficult to quickly generate advertisements tailored to target customer segments. This resulted in an inability to adapt to situations requiring short-term advertising deployments, negatively impacting customer acquisition and sales.

[1277] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1278] In this invention, the server includes means for receiving input data, means for generating advertising copy using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising copy and the input data, means for generating advertising creative by combining the generated advertising copy and advertising images, means for a user interface for reviewing and adjusting the generated advertising creative, means for the user to provide input data such as target customer base, product information, and advertising theme using a smartphone, and means for presenting the generated advertising creative to the user's smartphone and accepting user review and adjustments. This makes it possible to generate advertising creative efficiently and effectively and create high-quality advertisements in a short amount of time.

[1279] "Input data" refers to information provided by the user, such as the target customer base, product information, and advertising theme.

[1280] "Generative artificial intelligence" refers to an AI system that generates advertising copy based on input data.

[1281] "Advertising copy" refers to catchphrases and messages for advertisements created by generative artificial intelligence.

[1282] An "image generation tool" is software or a system that generates advertising images based on generated advertising text and input data.

[1283] "Advertising images" are visual advertising materials created using image generation tools.

[1284] "Advertising creative" refers to the final advertising work created by combining the generated advertising copy and advertising images.

[1285] A "user interface means" is an interface that allows users to review and adjust the generated advertising creative.

[1286] A "smartphone" is a personal information device used by users to provide input data and to review and adjust the generated advertising creatives.

[1287] The system implementing this invention mainly consists of a smartphone and a server. The user provides input data such as target customer base, product information, and advertising theme using the smartphone. The server receives this data and generates advertising copy using generative artificial intelligence (AI). Based on the generated advertising copy and input data, the server generates advertising images using an image generation tool. Subsequently, the generated advertising copy and advertising images are combined to create advertising creatives, which are then presented to the user via the smartphone for review and adjustment.

[1288] The server uses the following hardware and software:

[1289] Generative artificial intelligence: For generative AI models, we use, for example, OpenAI's GPT-4 or Google Cloud AI's Text Generation API.

[1290] Image generation tools: Use image generation APIs such as DALL-E 2 or MidJourney.

[1291] Database: A database solution for storing and managing generated data (e.g., MySQL, PostgreSQL).

[1292] Specifically, the server receives input data sent by the user and first sends a prompt to the generation AI model to generate advertising text. Examples of such prompts include the following:

[1293] Product Information: "Organic Soap", Target Customer Base: "Naturally-minded women in their 20s", Theme: "Autumn New Product Campaign"

[1294] Based on this prompt, the generative AI model generates the following advertisement:

[1295] Experience the refreshing feeling of autumn with natural soap.

[1296] Next, based on the generated ad copy and input data, the server sends a request to the image generation tool to generate the ad image. For example, the request may include the following:

[1297] The advertisement image for the natural-looking organic soap features a design inspired by autumn scenery and organic ingredients.

[1298] The generated images and ad copy are integrated to automatically create ad creatives. The created ad creatives are sent to the user's smartphone, where the user reviews them and sends adjustment requests to the server as needed. The server then uses generative artificial intelligence and image generation tools to generate new ad copy and ad images, updating the ad creatives again.

[1299] In this way, users can create high-quality advertising creatives quickly and efficiently. A major advantage of this invention is that it allows small businesses and individuals, in particular, to quickly create effective advertisements without requiring specialized knowledge or skills.

[1300] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1301] Step 1:

[1302] Users input data such as target customer segment, product information, and advertising theme using their smartphones. Specifically, users open a dedicated application and enter data such as "Target customer segment: Women in their 20s," "Product information: Organic soap," and "Advertising theme: Autumn new product campaign" into a form. This data is then sent from the smartphone to the server.

[1303] Step 2:

[1304] The server receives input data sent by the user. This input data includes the target customer base, product information, and the theme of the advertisement. Based on this data, the server generates a prompt and sends it to a generative artificial intelligence (AI). An example of such a prompt is: "Product information: Organic soap, Target customer base: Women in their 20s, Theme: Autumn new product campaign".

[1305] Step 3:

[1306] A generative artificial intelligence generates advertising copy based on prompt text received from the server. For example, based on the prompt text, a tagline such as "Enjoy the refreshing feeling of autumn with natural soap" is generated. This generated advertising copy is then sent to the server.

[1307] Step 4:

[1308] The server receives the generated ad copy and saves it to the database. At the same time, it sends a request to the image generation tool for generating the ad image. This request includes the generated ad copy and input data. For example, the request might be for "an ad image for a natural-tasting organic soap, with a design inspired by autumn scenery and organic materials."

[1309] Step 5:

[1310] The image generation tool generates an advertising image based on a request received from the server. The generated advertising image is sent to the server. Specifically, an image of "organic soap displayed against an autumn background" is generated.

[1311] Step 6:

[1312] The server receives the generated ad images and stores them in a database. Next, it combines the received ad copy and images to create ad creatives. This automatically generates visually appealing ad materials.

[1313] Step 7:

[1314] The server sends the generated ad creative to the user's smartphone. The user reviews the ad creative on their smartphone and requests adjustments or modifications as needed. For example, they might send a request to "make the tagline a little shorter."

[1315] Step 8:

[1316] The server receives the adjustment request from the user and sends another request to the generative artificial intelligence and image generation tools. This generates new taglines and advertising images, and the advertising creative is updated again.

[1317] Step 9:

[1318] The user reviews the final ad creative on their smartphone to confirm there are no issues. The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link. This allows the user to quickly obtain high-quality ad creatives.

[1319] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1320] This invention relates to a system that automatically generates advertising creatives by generating advertising copy using generative artificial intelligence (AI) based on input data, generating advertising images using an image generation tool, and incorporating an emotion engine that recognizes the user's emotional state. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[1321] Program Processing Overview

[1322] 1. User input

[1323] The user provides input data on the device:

[1324] Users provide the system with input data such as target customer segments, product information, and advertising themes using their devices. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[1325] 2. Recognition of emotional states

[1326] The server uses an emotion engine to analyze the user's emotional state:

[1327] The server analyzes voice, facial expressions, or text data acquired from the user's device, and the emotion engine recognizes the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive."

[1328] 3. Generating a catchy slogan

[1329] The server sends a request to the generative artificial intelligence to generate advertising copy:

[1330] The server creates and sends a request to the generative artificial intelligence (AI) to generate advertising copy based on the input data and the user's emotional state. The AI ​​then generates a tagline based on this request. For example, based on the input data and positive emotions, it might generate the tagline, "Let the scent of spring blossom in your heart."

[1331] The server receives the generated advertisement:

[1332] The server receives the tagline generated by the generative artificial intelligence and stores it in a database. This advertising copy is used in the next step.

[1333] 4. Generating advertising images

[1334] The server sends a request to the image generation tool:

[1335] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy, input data, and the user's emotional state. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[1336] The server receives the generated ad image:

[1337] The server receives the advertising images generated by the image generation tool and stores them in the database. These advertising images are then used in the next step.

[1338] 5. Generating advertising creatives

[1339] The server creates the ad creative:

[1340] The server automatically generates ad creatives by combining the generated ad copy, ad images, and the user's emotional state.

[1341] 6. Review and adjust results

[1342] The server presents the generated results to the user:

[1343] The server sends the generated ad creative to the user's device and presents it to the user.

[1344] The user reviews the generated results and provides instructions for adjustments:

[1345] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might enter additional requests such as, "Could you make the tagline a little shorter?"

[1346] The server will regenerate:

[1347] The server then sends another request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[1348] 7. Final Output

[1349] User final confirmation:

[1350] The user reviews the final ad creative on their device and confirms that there are no problems.

[1351] The server outputs a file:

[1352] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[1353] This invention allows users to create high-quality advertising creatives in a short amount of time, significantly reducing time and costs. Furthermore, it enables the generation of advertising creatives that respond to the user's emotional state, allowing for the delivery of more appropriate and effective advertisements.

[1354] The following describes the processing flow.

[1355] Step 1:

[1356] The user logs into the system to begin creating ad creatives on their device. A user ID and password are required for login.

[1357] Step 2:

[1358] Users provide input data such as target customer segments, product information, and advertising themes to input forms using their devices. For example, for an advertising theme of "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[1359] Step 3:

[1360] The user submits the input data to the system by pressing the submit button. The input data is received by the server and stored in the database.

[1361] Step 4:

[1362] The server uses an emotion engine to analyze voice, facial, or text data acquired from the user's device to recognize the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive."

[1363] Step 5:

[1364] The server combines emotional state information obtained from the emotion engine and creates a request for promotional text generation from the generative artificial intelligence. The request includes input data and the user's emotional state (e.g., "positive").

[1365] Step 6:

[1366] The server sends a request to a generative artificial intelligence (AI), which generates a catchy slogan based on the input data and emotional state information. For example, it might generate the slogan, "Let the scent of spring blossom in your heart."

[1367] Step 7:

[1368] The server receives the advertising copy generated by the generative artificial intelligence and stores it in a database. This advertising copy is then used in the next step.

[1369] Step 8:

[1370] The server creates a request to the image generation tool to generate an advertising image based on the generated ad copy, input data, and sentiment state information. The request includes keywords such as "spring, floral, perfume, women's, elegant image."

[1371] Step 9:

[1372] The server sends a request to an image generation tool, which generates an advertising image based on input data, advertising text, and sentiment information. For example, it might generate an image of an elegant (floral) perfume bottle.

[1373] Step 10:

[1374] The server receives the advertising image generated by the image generation tool and stores it in the database. This advertising image is used in the next step.

[1375] Step 11:

[1376] The server retrieves promotional text and ad images generated from the database, combines them, and automatically generates ad creatives. Emotional state information is also taken into consideration.

[1377] Step 12:

[1378] The server sends the generated ad creative to the user's device and presents it to the user.

[1379] Step 13:

[1380] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might request, "I'd like the tagline to be a little shorter."

[1381] Step 14:

[1382] The server receives the user's adjustment request and sends a regeneration request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[1383] Step 15:

[1384] The server resends the regenerated ad creative to the user's device and presents it to the user.

[1385] Step 16:

[1386] The user reviews the final ad creative on their device and confirms that there are no problems.

[1387] Step 17:

[1388] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[1389] (Example 2)

[1390] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1391] The modern advertising industry demands the rapid generation of high-quality advertising creatives. However, doing this manually is time-consuming and costly, and creating ads that reflect user emotions and needs is even more difficult. Furthermore, traditional systems have the problem of not being able to flexibly regenerate the advertising copy and images that users desire.

[1392] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data using a terminal, means for generating advertising copy using a generation AI model based on the input data and the user's emotional state, and means for generating advertising images using an image generation tool based on the generated advertising copy, the emotional state, and the input data. This enables the automatic generation of high-quality advertising creatives that are tailored to the user's emotional state. Furthermore, it is equipped with interface means for checking and adjusting the generated advertising creatives, and it is also possible to instruct the regeneration of advertising copy and advertising images, thereby realizing a flexible advertising creation process.

[1393] A "terminal" is a device used by a user to provide input data to a system, and generally refers to information processing devices such as computers and smartphones.

[1394] "Input data" refers to information that users provide to the system, including detailed data such as target customer segments, product information, and advertising themes.

[1395] "Emotional state" refers to data that represents a user's current emotions, and is classified as positive, negative, neutral, etc., by analyzing voice, facial expressions, text, etc.

[1396] A "generative AI model" is an artificial intelligence system that generates advertising copy based on input data and emotional states, and refers to, for example, a large-scale language model.

[1397] "Advertising text" refers to advertising wording such as copywriting and catchphrases generated by generative AI models.

[1398] An "image generation tool" refers to a system or software that generates advertising images based on input data, generated advertising text, and emotional states.

[1399] "Advertising images" refer to visual advertising elements generated by image generation tools, and include photographs, illustrations, graphic designs, etc.

[1400] "Advertising creative" refers to complete advertising content created by combining generated advertising copy and advertising images.

[1401] "Interface means" refers to means by which users can review and adjust generated advertising creatives, and generally includes user-friendly screens and operating methods.

[1402] This invention is a system that automatically generates advertising creatives by generating advertising copy using generative artificial intelligence (AI) based on input data, generating advertising images using an image generation tool, and incorporating an emotion engine that recognizes the user's emotional state. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[1403] First, the user uses their device to input the target customer base, product information, and advertising theme. For example, for an advertising theme of "New Spring Floral Perfume," they can input keywords such as "spring, floral, perfume, women's." Users can also provide voice and facial expression data. This data is transmitted to the server via the device.

[1404] Next, the server uses an emotion engine to analyze the voice, facial expressions, or text data provided by the user to recognize the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive." This emotion analysis is performed using tools such as IBM Watson's emotion analysis API.

[1405] Next, the server creates and sends a request to a generative AI model (e.g., OpenAI GPT-4) to generate advertising copy, based on the input data and the user's emotional state. The following are examples of the specific prompts used:

[1406] Based on the following keywords—"spring," "floral," "perfume," "women's," and "elegant"—and the user's emotional state—"positive," please generate a tagline for a new floral perfume.

[1407] The generative AI model generates a tagline based on this request, creating an advertisement such as, "Let the scent of spring blossom in your heart." The generated advertisement is received by the server and stored in the database.

[1408] The server then sends a request to an image generation tool (e.g., MidJourney or DALL-E) to generate an advertising image, based on the generated ad copy, input data, and the user's emotional state. The prompt might look something like this:

[1409] Please generate an ad image based on the keywords "spring, floral, perfume, women's, elegant image".

[1410] The image generation tool generates an advertisement image based on this prompt, creating an image that, for example, includes an elegant background and a floral design. The generated advertisement image is also received by the server and stored in the database.

[1411] Ultimately, the server combines the generated ad copy, ad images, and sentiment state to create ad creatives. The generated ad creatives are presented to the user through a user interface. The user can review the generated ad creatives and, if necessary, instruct the server to regenerate the ad copy and ad images. Upon receiving a regeneration request, the server sends new prompts to the generation AI model and image generation tools to generate new ad copy and ad images.

[1412] This system enables users to efficiently generate high-quality ad creatives, saving both time and money. Furthermore, it allows for the creation of ad creatives tailored to the user's emotional state, providing personalized and effective advertising.

[1413] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1414] Step 1:

[1415] The user provides input data on their device.

[1416] The user uses a terminal to input data such as target customer segment, product information, and advertising theme into the system. Specifically, the user enters the advertising theme "New Spring Floral Perfume" and keywords such as "spring, floral, perfume, for women" into the input form on the terminal. The entered data is then sent from the terminal to the server.

[1417] Input: Target customer base, product information, advertising theme, keywords

[1418] Output: Send input data to the server

[1419] Step 2:

[1420] The server uses an emotion engine to analyze the user's emotional state.

[1421] The server acquires voice data, facial expression data, and text data sent from the terminal. Next, it sends this data to the emotion engine for analysis to recognize the user's emotional state. For example, if the user's facial expression is smiling, the emotion engine recognizes it as "positive."

[1422] Input: Audio data, facial expression data, text data

[1423] Output: User's emotional state (e.g., positive)

[1424] Step 3:

[1425] The server sends a request to the AI ​​model to generate advertising copy.

[1426] The server creates a request to the AI ​​model to generate advertising copy based on the input data and the user's emotional state. The prompt text includes the advertising theme and emotional state. For example, it generates a prompt text like the following:

[1427] Based on the following keywords—"spring," "floral," "perfume," "women's," and "elegant"—and the user's emotional state—"positive," please generate a tagline for a new floral perfume.

[1428] The generative AI model generates catchphrases based on this.

[1429] Input: Input data, user's emotional state

[1430] Output: Prompt text for the generating AI model, generated catchphrase

[1431] Step 4:

[1432] The server receives the generated advertisement text.

[1433] The server receives the catchphrase from the generating AI model and saves it to the database. Let's assume the generated catchphrase is "Let's let the scent of spring blossom in our hearts."

[1434] Input: Catchphrases from a generated AI model

[1435] Output: Catchphrases stored in the database

[1436] Step 5:

[1437] The server sends a request to the image generation tool.

[1438] The server sends a request to the image generation tool to generate an advertising image based on the generated tagline, input data, and the user's emotional state. The prompt message will use something like the following:

[1439] Please generate an ad image based on the keywords "spring, floral, perfume, women's, elegant image".

[1440] The image generation tool generates advertising images based on this.

[1441] Input: Generated tagline, input data, user's emotional state

[1442] Output: Prompt text for the image generation tool, generated advertisement image

[1443] Step 6:

[1444] The server receives the generated ad images.

[1445] The server receives the advertising images generated by the image generation tool and stores them in the database.

[1446] Input: Advertisement image from an image generation tool

[1447] Output: Advertisement images stored in the database

[1448] Step 7:

[1449] The server creates the ad creative.

[1450] The server automatically generates ad creatives by combining the generated ad copy, ad images, and emotional states. For example, it might place the tagline "Let the scent of spring blossom in your heart" on an elegant background image.

[1451] Input: Generated ad copy, ad images, sentiment status

[1452] Output: Generated ad creative

[1453] Step 8:

[1454] The server presents the generated results to the user.

[1455] The server sends the generated ad creative to the user's device and displays it.

[1456] Input: Generated ad creative

[1457] Output: Generated results sent to the user's terminal

[1458] Step 9:

[1459] The user reviews the generated results and gives instructions for adjustments.

[1460] Users can review the ad creative generated on their device and enter requests for adjustments or changes as needed. For example, they can enter specific requests such as "I'd like the tagline to be a little shorter" or "I'd like to change the background color."

[1461] Input: Generated ad creative, user adjustment requests

[1462] Output: Sending adjustment request to the server

[1463] Step 10:

[1464] The server will regenerate.

[1465] The server processes the adjustment requests collected through the user interface, sends new prompt messages to the generation AI model and image generation tools, and generates new promotional text and advertising images.

[1466] Input: User adjustment request

[1467] Output: New prompt text, new promotional text, and advertising image

[1468] Step 11:

[1469] The user performs a final check.

[1470] The user reviews the final ad creative on their device and confirms that there are no problems.

[1471] Input: Regenerated ad creative

[1472] Output: User's final approval

[1473] Step 12:

[1474] The server outputs the file.

[1475] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link. Through this link, the user can obtain the final ad creative.

[1476] Input: Final ad creative

[1477] Output: Download link

[1478] (Application Example 2)

[1479] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1480] Current methods for generating ad creatives are time-consuming and labor-intensive, as advertisers must manually create and combine promotional text and images. Furthermore, because ads are created uniformly, it's difficult to provide personalized ads tailored to individual users' emotional states and destination information. This results in limited ad effectiveness.

[1481] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1482] In this invention, the server includes means for receiving input data, means for generating advertising text using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising text and the input data, means for generating advertising creative by combining the generated advertising text and advertising images, user interface means for checking and adjusting the generated advertising creative, means for acquiring passenger destination information, means for recognizing passenger emotional states, and means for generating advertising text and advertising images as personalized advertisements based on the passenger destination information and emotional states. This makes it possible to automatically generate highly effective personalized advertisements tailored to the emotional states and destination information of individual users and provide them in a short amount of time.

[1483] "Input data" refers to information provided by the user to the system for generating advertisements, including, for example, target customer segments, product information, and themes of advertisements.

[1484] "Generative artificial intelligence" refers to an artificial intelligence program that automatically generates advertising copy based on input data.

[1485] An "image generation tool" is a software tool that automatically generates advertising images based on generated advertising text and input data.

[1486] "Advertising creative" refers to advertising materials created by combining generated advertising copy and advertising images.

[1487] A "user interface means" is an interface means that allows the user to review the generated advertising creative and instruct it to be adjusted or regenerated as needed.

[1488] "Destination information" refers to information about the destination set by the passenger.

[1489] "Emotional state" refers to information that represents a passenger's emotions, and is analyzed from, for example, facial expressions and tone of voice.

[1490] "Personalized advertising" refers to advertisements that are individually tailored based on a passenger's destination information and emotional state.

[1491] In order to realize the system of the present invention, the following program must be implemented. This program automatically generates advertising creatives based on user input data and provides personalized advertisements to the user.

[1492] Program Processing Overview

[1493] 1. Receiving input data:

[1494] The system receives information necessary for ad generation from the user's device, such as target customer segment, product information, and ad theme, and sends it to the server.

[1495] 2. Obtaining destination information:

[1496] The server retrieves destination information from the system inside the passenger's autonomous vehicle.

[1497] 3. Recognition of emotional states:

[1498] The server uses emotion recognition software to analyze passengers' camera and audio streams, including their smiles and tone of voice, to recognize their emotional state. This emotion recognition software is called "EmotionRecognition."

[1499] 4. Generating promotional text:

[1500] The server uses generative artificial intelligence (AI text generator) to generate promotional text based on the passenger's emotional state and destination information. For example, it might use a prompt such as, "Generate a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring."

[1501] 5. Generating advertising images:

[1502] The server uses an image generation tool (AI image generator) to generate personalized advertising images based on the generated promotional text and destination information. For example, it might use a prompt such as, "Generate a beautiful image that reflects spring, Tokyo Tower, tourism, and positive emotions."

[1503] 6. Generating ad creatives:

[1504] The server combines the generated promotional text and advertising images to create personalized ads as advertising creatives.

[1505] 7. Display of advertisements:

[1506] The server displays the generated ad creatives on displays inside the autonomous vehicle and on passengers' smart devices (smartphones and head-mounted displays).

[1507] 8. Verification and adjustment via the user interface:

[1508] Users review the displayed ad creatives and instruct the system to adjust or regenerate them as needed.

[1509] Hardware and software to be used

[1510] Camera and microphone: Devices for detecting the emotional state of passengers.

[1511] Autonomous vehicle display: A device for displaying advertisements.

[1512] Smart devices (smartphones, head-mounted displays): Devices used to display advertisements individually.

[1513] EmotionRecognition: Emotion recognition software. Analyzes passengers' emotional states in real time.

[1514] AI Text Generator: A generative artificial intelligence system. It generates advertising text based on emotional states and destination information.

[1515] AI Image Generator: Image generation tool. Generates advertising images.

[1516] Specific examples and prompt statements

[1517] For example, if a passenger is heading to "Tokyo Tower," use the following prompt:

[1518] EmotionRecognition:

[1519] "Use the camera and audio streams to determine if the passenger is smiling."

[1520] AI Text Generator:

[1521] "Please create a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring."

[1522] AI Image Generator:

[1523] "Please generate a beautiful image that reflects spring, Tokyo Tower, sightseeing, and positive emotions."

[1524] This embodiment makes it possible to automatically generate highly effective personalized advertisements tailored to each user's emotional state and destination information, and deliver them in a short amount of time.

[1525] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1526] Step 1:

[1527] The user's device inputs the information necessary for ad generation and sends it to the server. The input data includes target customer segment, product information, and ad theme. The server receives this data and uses it for further processing.

[1528] Step 2:

[1529] The server retrieves passenger destination information from the system within the autonomous vehicle. This destination information is used in a later processing step to personalize the advertisement content.

[1530] Step 3:

[1531] The server analyzes the camera and audio streams and uses emotion recognition software to recognize the passenger's emotional state. Specifically, it uses information such as whether the passenger is smiling and their tone of voice to classify their emotional state as "positive" or "negative." This allows the emotional state to be determined.

[1532] Step 4:

[1533] Based on emotional states and destination information, the server sends prompts to a generative artificial intelligence (AI text generator) to generate appropriate advertising copy. For example, if the prompt is "Generate a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring," the generated slogan will be output.

[1534] Step 5:

[1535] The server sends prompts to an image generation tool (AI image generator) based on the advertisement text and destination information, and generates an advertising image. For example, if the prompt is "Generate a beautiful image that reflects spring, Tokyo Tower, tourism, and positive emotions," the generated image will be output.

[1536] Step 6:

[1537] The server combines the generated promotional text and advertising images to create advertising creatives. Specifically, the generated text is placed on the images, resulting in visually appealing advertising materials.

[1538] Step 7:

[1539] The server sends the generated ad creatives to displays in the autonomous vehicle and to passengers' smart devices for display. This allows passengers to visually see personalized ads while on their way to their destination.

[1540] Step 8:

[1541] Users review the displayed ad creative and instruct it to be adjusted or regenerated as needed. Specifically, they request revisions to the tagline or regeneration of images through the user interface. This request is sent to the server, the regeneration process is performed again, and a new ad creative is created.

[1542] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1543] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1544] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1545] [Fourth Embodiment]

[1546] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1547] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1548] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1549] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1550] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1551] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1552] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1553] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1554] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1555] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1556] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1557] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1558] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1559] This invention relates to a system for automatically generating advertising creatives. Specifically, it is a system that generates advertising copy using generative artificial intelligence (AI) based on input data, and further generates advertising images using an image generation tool. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[1560] Program Processing Overview

[1561] 1. User input

[1562] The user provides input data on the device:

[1563] Users provide the system with input data such as target customer segments, product information, and advertising themes using their devices. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[1564] 2. Generating a catchy slogan

[1565] The server receives the input data:

[1566] The server receives input data sent by the user from the terminal and passes it on to the generative artificial intelligence.

[1567] The server sends a request to the generative artificial intelligence:

[1568] The server sends a request to the generative artificial intelligence to generate advertising copy based on the input data. The generative artificial intelligence then generates a tagline based on this request. For example, from the input data, it might generate the tagline "Let the scent of spring blossom in your heart."

[1569] The server receives the generated advertisement:

[1570] The server receives catchphrases generated by the generative artificial intelligence and stores them in a database.

[1571] 3. Generating advertising images

[1572] The server sends a request to the image generation tool:

[1573] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[1574] The server receives the generated ad image:

[1575] The server receives the advertising images generated by the image generation tool and stores them in the database.

[1576] 4. Generating advertising creatives

[1577] The server creates the ad creative:

[1578] The server retrieves generated advertising copy and images from a database and automatically generates advertising creatives by combining them.

[1579] 5. Review and adjust results

[1580] The server presents the generated results to the user:

[1581] The server sends the generated ad creative to the user's device and presents it to the user.

[1582] The user reviews the generated results and provides instructions for adjustments:

[1583] Users can review the ad creatives generated on their devices and request adjustments or changes as needed. For example, they can send a request to the server to "make the tagline a little shorter."

[1584] The server will regenerate:

[1585] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[1586] 6. Final Output

[1587] User final confirmation:

[1588] The user reviews the final ad creative on their device and confirms that there are no problems.

[1589] The server outputs a file:

[1590] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[1591] This invention allows users to create advertising creatives in a short amount of time, significantly reducing time and costs. Furthermore, because high-quality advertising copy and images are automatically generated based on the input data, it is possible to quickly deliver consistent and effective advertisements.

[1592] The following describes the processing flow.

[1593] Step 1:

[1594] The user logs into the system to begin creating ad creatives on their device. A user ID and password are required for login.

[1595] Step 2:

[1596] Users provide input data such as target customer segments, product information, and advertising themes to an input screen using their devices. For example, for an advertising theme of "New Spring Floral Perfume," users might input keywords such as "spring, floral, perfume, for women."

[1597] Step 3:

[1598] The user submits the input data to the system by pressing the submit button. This input data is used to generate the ad creative.

[1599] Step 4:

[1600] The server receives input data sent from the terminal and stores it in the database. This data is used in subsequent generation processes.

[1601] Step 5:

[1602] The server creates a request to the generative artificial intelligence to generate advertising copy based on the input data. The request includes keywords such as "spring, floral, perfume, women's."

[1603] Step 6:

[1604] The server sends a request to a generative artificial intelligence (AI), which generates advertising copy (catchphrases) based on the input data. For example, it might generate the catchphrase, "Let the scent of spring blossom in your heart."

[1605] Step 7:

[1606] The server receives the advertising copy generated by the generative artificial intelligence and stores it in a database. This advertising copy is then used in the next step.

[1607] Step 8:

[1608] The server creates a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. The request includes keywords such as "spring, floral, perfume, women's, elegant image".

[1609] Step 9:

[1610] The server sends a request to an image generation tool, which generates an advertising image based on the input data and advertising text. For example, it might generate an image of an elegant (floral) perfume bottle.

[1611] Step 10:

[1612] The server receives the advertising image generated by the image generation tool and stores it in the database. This advertising image is used in the next step.

[1613] Step 11:

[1614] The server retrieves promotional text and advertising images generated from the database, and automatically generates advertising creatives by combining them.

[1615] Step 12:

[1616] The server sends the generated ad creative to the user's device and presents it to the user.

[1617] Step 13:

[1618] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might submit additional requests such as, "Could you make the tagline a little shorter?"

[1619] Step 14:

[1620] The server receives the user's adjustment request and sends a regeneration request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[1621] Step 15:

[1622] The server resends the regenerated ad creative to the user's device and presents it to the user.

[1623] Step 16:

[1624] The user reviews the final ad creative on their device and confirms that there are no problems.

[1625] Step 17:

[1626] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[1627] (Example 1)

[1628] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1629] Traditional advertising creative generation was time-consuming and costly, and it was difficult to deliver consistent and effective advertisements quickly. Furthermore, realizing the advertising image that users envisioned required considerable effort and expertise. In addition, the difficulty in regenerating advertising copy and images made it difficult to adjust the content of advertisements on a case-by-case basis. As a result, there were challenges such as decreased efficiency in marketing activities and limitations on the quality and impact of advertisements.

[1630] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1631] In this invention, the server includes means for receiving input data, means for generating advertising text using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising text and the input data, means for generating advertising creative by combining the generated advertising text and advertising images, user interface means for reviewing and adjusting the generated advertising creative, and means for finally outputting the generated advertising creative. This makes it possible to generate high-quality advertising creative in a short time and to quickly provide effective advertisements while maintaining consistency. In addition, since users can easily make adjustment requests and instruct the regeneration of advertising text and images, more flexible and adaptable advertising creation is realized.

[1632] "Input data" refers to information that users provide to the system, such as target customer segments, product information, and advertising themes.

[1633] "Generative artificial intelligence" is an artificial intelligence technology that generates advertising copy based on input data provided by the user.

[1634] "Advertising copy" refers to advertising slogans and messages generated by generative artificial intelligence.

[1635] An "image generation tool" is software or hardware used to generate advertising images based on input data and generated advertising text.

[1636] An "advertising image" is a visual element for advertising that is generated using an image generation tool.

[1637] "Advertising creative" refers to the final form of an advertisement, created by combining the generated advertising copy and advertising images.

[1638] A "user interface means" is an interface that allows users to review and adjust generated advertising creatives.

[1639] "The means of final output" refers to the function of outputting the generated advertising creative as a file in an appropriate format and providing it to the user.

[1640] A "server" is a computer that operates the entire system and performs various generation processes and data management.

[1641] This invention relates to a system for automatically generating advertising creatives. Specifically, it is a system that generates advertising copy using generative artificial intelligence (AI) based on input data, and further generates advertising images using an image generation tool. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[1642] Hardware and software configuration

[1643] server:

[1644] The server is a computer that operates the entire system and performs various generation processes and data management. The server receives input data, sends requests to the generative artificial intelligence, and processes the storage and regeneration requests of the generated data.

[1645] Terminal:

[1646] Users access the system using a device. The device provides an interface for users to provide input data and to review and adjust the generated ad creatives.

[1647] Generative artificial intelligence models:

[1648] Generative artificial intelligence models are AI technologies used to generate advertising copy based on input data. For example, natural language processing (NLP) models fulfill this role.

[1649] Image generation tool:

[1650] Image generation tools are tools for generating images for advertisements based on input data and generated advertising text. For example, an AI model for image generation can fulfill this role.

[1651] Specific methods for data processing and data calculation

[1652] This system performs data processing and calculations using the following methods.

[1653] 1. The user provides the input data:

[1654] Users provide input data to the system using their devices, such as target customer segments, product information, and advertising themes. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[1655] 2. The server receives the input data and passes it to the generative artificial intelligence:

[1656] The server receives input data sent by the user and passes it to the generative artificial intelligence. The generative artificial intelligence generates advertising text based on this input data.

[1657] 3. The server receives the generated advertisement text and saves it to the database:

[1658] The system receives advertising copy generated by a generative artificial intelligence and stores it in a database.

[1659] 4. The server sends a request to the image generation tool:

[1660] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[1661] 5. The server receives the generated ad image and saves it to the database:

[1662] The server receives the advertising images generated by the image generation tool and stores them in the database.

[1663] 6. The server creates the ad creative:

[1664] The generated advertising copy and images are retrieved from a database, and they are combined to automatically generate advertising creatives.

[1665] 7. The server presents the generated results to the user:

[1666] The server sends the generated ad creative to the user's device and presents it to the user.

[1667] 8. The user reviews the generated results and provides instructions for adjustments:

[1668] Users can review the ad creatives generated on their devices and request adjustments or changes as needed. For example, they can send a request to the server to "make the tagline a little shorter."

[1669] 9. The server performs regeneration:

[1670] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[1671] 10. The user performs final confirmation:

[1672] The user reviews the final ad creative on their device and confirms that there are no problems.

[1673] 11. The server outputs the file:

[1674] The server outputs the final ad creative in the appropriate format and provides the user with a download link.

[1675] Example of a prompt

[1676] prompt:

[1677] Advertisement theme: New spring floral perfumes

[1678] Target customer base: Women, 20-30 years old

[1679] Keywords: Spring, Floral, Perfume, Elegant

[1680] This system allows users to generate high-quality ad creatives in a short amount of time, significantly reducing time and costs. It also enables the rapid delivery of consistent and highly effective ads, allowing users to easily request adjustments and review the generated results at each stage.

[1681] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1682] Step 1:

[1683] The user provides the input data.

[1684] Users use their devices to provide the system with input data such as target customer segments, product information, and advertising themes.

[1685] Input: Target customer base, product information, advertising theme, etc.

[1686] Output: Input data is sent to the server.

[1687] Specific operation:

[1688] The user enters the following into their device: "Target customer base: Women, 20-30 years old", "Product information: New floral perfume", and "Advertising theme: Spring".

[1689] When the user clicks the "Submit" button, the input data is sent to the server.

[1690] Step 2:

[1691] The server receives the input data.

[1692] The server receives input data sent from the user's terminal.

[1693] Input: Input data submitted by the user

[1694] Output: Received input data

[1695] Specific operation:

[1696] The server receives data sent from the terminal and stores it as input data.

[1697] Step 3:

[1698] The server sends a request to the generative artificial intelligence.

[1699] The server sends a request to a generative artificial intelligence (AI) to generate advertising copy based on the input data.

[1700] Input: Received input data

[1701] Output: Send a request to generate advertising copy to a generative AI.

[1702] Specific operation:

[1703] The server generates and sends the prompt "Spring, New release, Floral, Perfume, For women" to the AI ​​model.

[1704] Step 4:

[1705] Generative artificial intelligence generates advertising copy.

[1706] Generative artificial intelligence generates advertising text based on requests from a server.

[1707] Input: Server request (prompt)

[1708] Output: Generated advertisement text

[1709] Specific operation:

[1710] A generative AI model analyzes the prompt and generates the tagline, "Let's let the scent of spring blossom in our hearts."

[1711] Step 5:

[1712] The server receives the generated advertisement text.

[1713] The server receives advertising text generated by a generative artificial intelligence system and stores it in a database.

[1714] Input: Advertising text generated by a generative artificial intelligence.

[1715] Output: Advertisement text stored in the database

[1716] Specific operation:

[1717] The server receives the generated advertisement text and saves it to the database.

[1718] Step 6:

[1719] The server sends a request to the image generation tool.

[1720] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy and input data.

[1721] Input: Generated ad copy, received input data

[1722] Output: Send a request to the image generation tool.

[1723] Specific operation:

[1724] The server sends a request to the image generation tool that includes the keywords "spring, floral, perfume, feminine, elegant image".

[1725] Step 7:

[1726] Image generation tool generates advertising images

[1727] The image generation tool generates advertising images based on requests from the server.

[1728] Input: Server request

[1729] Output: Generated ad images

[1730] Specific operation:

[1731] The image generation tool analyzes the request and generates an advertising image for an elegant floral perfume.

[1732] Step 8:

[1733] The server receives the generated ad images.

[1734] The server receives the advertising images generated by the image generation tool and stores them in the database.

[1735] Input: Advertisement image generated from an image generation tool

[1736] Output: Advertisement images stored in the database

[1737] Specific operation:

[1738] The server receives the generated ad image and saves it to the database.

[1739] Step 9:

[1740] The server creates the ad creative.

[1741] The server retrieves generated advertising copy and images from a database and automatically generates advertising creatives by combining them.

[1742] Input: Advertising text and images retrieved from the database

[1743] Output: Generated ad creative

[1744] Specific operation:

[1745] The server lays out the promotional text and ad images, and generates the ad creative.

[1746] Step 10:

[1747] The server presents the generated results to the user.

[1748] The server sends the generated ad creative to the user's device and presents it to the user.

[1749] Input: Generated ad creative

[1750] Output: Ad creative sent to the user's device

[1751] Specific operation:

[1752] The server displays the advertising creative on the device via a pre-configured user interface.

[1753] Step 11:

[1754] The user reviews the generated results and gives instructions for adjustments.

[1755] Users can review the ad creatives generated on their devices and request adjustments or changes as needed.

[1756] Input: Adjustment request from the user

[1757] Output: Coordination request sent to the server

[1758] Specific operation:

[1759] The user reviews the creative on their device's interface, enters any necessary adjustments such as "I want to make the tagline a little shorter," and then submits it.

[1760] Step 12:

[1761] The server will regenerate.

[1762] The server then sends another request to the generative artificial intelligence and image generation tools to generate new taglines and images, and presents the regenerated advertising creative to the user again.

[1763] Input: Adjustment request from the user

[1764] Output: Regenerated ad creative

[1765] Specific operation:

[1766] The server generates a new prompt and sends another request to the AI ​​model and image generation tool.

[1767] A new tagline and image are generated, and the creative is regenerated again.

[1768] Step 13:

[1769] The user performs a final check.

[1770] The user reviews the final ad creative on their device and confirms that there are no problems.

[1771] Input: Regenerated ad creative

[1772] Output: Final verification results, no feedback.

[1773] Specific operation:

[1774] The user performs a final check and clicks the "Complete" button if they determine there are no problems.

[1775] Step 14:

[1776] The server outputs the file.

[1777] The server outputs the final ad creative as a file in the appropriate format and provides the user with a download link.

[1778] Input: Final approved ad creative

[1779] Output: Files output in the appropriate format (e.g., JPEG, PNG) and a download link.

[1780] Specific operation:

[1781] The server saves the ad creative in JPEG format and provides the user with a download link.

[1782] (Application Example 1)

[1783] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1784] Traditionally, the process of creating advertising creatives has been time-consuming and labor-intensive, requiring specialized knowledge and skills, especially for small businesses and individuals, making it difficult to create efficient and effective advertisements. Furthermore, the limited available materials made it difficult to quickly generate advertisements tailored to target customer segments. This resulted in an inability to adapt to situations requiring short-term advertising deployments, negatively impacting customer acquisition and sales.

[1785] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1786] In this invention, the server includes means for receiving input data, means for generating advertising copy using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising copy and the input data, means for generating advertising creative by combining the generated advertising copy and advertising images, means for a user interface for reviewing and adjusting the generated advertising creative, means for the user to provide input data such as target customer base, product information, and advertising theme using a smartphone, and means for presenting the generated advertising creative to the user's smartphone and accepting user review and adjustments. This makes it possible to generate advertising creative efficiently and effectively and create high-quality advertisements in a short amount of time.

[1787] "Input data" refers to information provided by the user, such as the target customer base, product information, and advertising theme.

[1788] "Generative artificial intelligence" refers to an AI system that generates advertising copy based on input data.

[1789] "Advertising copy" refers to catchphrases and messages for advertisements created by generative artificial intelligence.

[1790] An "image generation tool" is software or a system that generates advertising images based on generated advertising text and input data.

[1791] "Advertising images" are visual advertising materials created using image generation tools.

[1792] "Advertising creative" refers to the final advertising work created by combining the generated advertising copy and advertising images.

[1793] A "user interface means" is an interface that allows users to review and adjust the generated advertising creative.

[1794] A "smartphone" is a personal information device used by users to provide input data and to review and adjust the generated advertising creatives.

[1795] The system implementing this invention mainly consists of a smartphone and a server. The user provides input data such as target customer base, product information, and advertising theme using the smartphone. The server receives this data and generates advertising copy using generative artificial intelligence (AI). Based on the generated advertising copy and input data, the server generates advertising images using an image generation tool. Subsequently, the generated advertising copy and advertising images are combined to create advertising creatives, which are then presented to the user via the smartphone for review and adjustment.

[1796] The server uses the following hardware and software:

[1797] Generative artificial intelligence: For generative AI models, we use, for example, OpenAI's GPT-4 or Google Cloud AI's Text Generation API.

[1798] Image generation tools: Use image generation APIs such as DALL-E 2 or MidJourney.

[1799] Database: A database solution for storing and managing generated data (e.g., MySQL, PostgreSQL).

[1800] Specifically, the server receives input data sent by the user and first sends a prompt to the generation AI model to generate advertising text. Examples of such prompts include the following:

[1801] Product Information: "Organic Soap", Target Customer Base: "Naturally-minded women in their 20s", Theme: "Autumn New Product Campaign"

[1802] Based on this prompt, the generative AI model generates the following advertisement:

[1803] Experience the refreshing feeling of autumn with natural soap.

[1804] Next, based on the generated ad copy and input data, the server sends a request to the image generation tool to generate the ad image. For example, the request may include the following:

[1805] The advertisement image for the natural-looking organic soap features a design inspired by autumn scenery and organic ingredients.

[1806] The generated images and ad copy are integrated to automatically create ad creatives. The created ad creatives are sent to the user's smartphone, where the user reviews them and sends adjustment requests to the server as needed. The server then uses generative artificial intelligence and image generation tools to generate new ad copy and ad images, updating the ad creatives again.

[1807] In this way, users can create high-quality advertising creatives quickly and efficiently. A major advantage of this invention is that it allows small businesses and individuals, in particular, to quickly create effective advertisements without requiring specialized knowledge or skills.

[1808] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1809] Step 1:

[1810] Users input data such as target customer segment, product information, and advertising theme using their smartphones. Specifically, users open a dedicated application and enter data such as "Target customer segment: Women in their 20s," "Product information: Organic soap," and "Advertising theme: Autumn new product campaign" into a form. This data is then sent from the smartphone to the server.

[1811] Step 2:

[1812] The server receives input data sent by the user. This input data includes the target customer base, product information, and the theme of the advertisement. Based on this data, the server generates a prompt and sends it to a generative artificial intelligence (AI). An example of such a prompt is: "Product information: Organic soap, Target customer base: Women in their 20s, Theme: Autumn new product campaign".

[1813] Step 3:

[1814] A generative artificial intelligence generates advertising copy based on prompt text received from the server. For example, based on the prompt text, a tagline such as "Enjoy the refreshing feeling of autumn with natural soap" is generated. This generated advertising copy is then sent to the server.

[1815] Step 4:

[1816] The server receives the generated ad copy and saves it to the database. At the same time, it sends a request to the image generation tool for generating the ad image. This request includes the generated ad copy and input data. For example, the request might be for "an ad image for a natural-tasting organic soap, with a design inspired by autumn scenery and organic materials."

[1817] Step 5:

[1818] The image generation tool generates an advertising image based on a request received from the server. The generated advertising image is sent to the server. Specifically, an image of "organic soap displayed against an autumn background" is generated.

[1819] Step 6:

[1820] The server receives the generated ad images and stores them in a database. Next, it combines the received ad copy and images to create ad creatives. This automatically generates visually appealing ad materials.

[1821] Step 7:

[1822] The server sends the generated ad creative to the user's smartphone. The user reviews the ad creative on their smartphone and requests adjustments or modifications as needed. For example, they might send a request to "make the tagline a little shorter."

[1823] Step 8:

[1824] The server receives the adjustment request from the user and sends another request to the generative artificial intelligence and image generation tools. This generates new taglines and advertising images, and the advertising creative is updated again.

[1825] Step 9:

[1826] The user reviews the final ad creative on their smartphone to confirm there are no issues. The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link. This allows the user to quickly obtain high-quality ad creatives.

[1827] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1828] This invention relates to a system that automatically generates advertising creatives by generating advertising copy using generative artificial intelligence (AI) based on input data, generating advertising images using an image generation tool, and incorporating an emotion engine that recognizes the user's emotional state. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[1829] Program Processing Overview

[1830] 1. User input

[1831] The user provides input data on the device:

[1832] Users provide the system with input data such as target customer segments, product information, and advertising themes using their devices. For example, for an advertising theme like "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[1833] 2. Recognition of emotional states

[1834] The server uses an emotion engine to analyze the user's emotional state:

[1835] The server analyzes voice, facial expressions, or text data acquired from the user's device, and the emotion engine recognizes the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive."

[1836] 3. Generating a catchy slogan

[1837] The server sends a request to the generative artificial intelligence to generate advertising copy:

[1838] The server creates and sends a request to the generative artificial intelligence (AI) to generate advertising copy based on the input data and the user's emotional state. The AI ​​then generates a tagline based on this request. For example, based on the input data and positive emotions, it might generate the tagline, "Let the scent of spring blossom in your heart."

[1839] The server receives the generated advertisement:

[1840] The server receives the tagline generated by the generative artificial intelligence and stores it in a database. This advertising copy is used in the next step.

[1841] 4. Generating advertising images

[1842] The server sends a request to the image generation tool:

[1843] The server sends a request to the image generation tool to generate an advertising image based on the generated ad copy, input data, and the user's emotional state. For example, it might send a request that includes the keywords "spring, floral, perfume, women's, elegant image".

[1844] The server receives the generated ad image:

[1845] The server receives the advertising images generated by the image generation tool and stores them in the database. These advertising images are then used in the next step.

[1846] 5. Generating advertising creatives

[1847] The server creates the ad creative:

[1848] The server automatically generates ad creatives by combining the generated ad copy, ad images, and the user's emotional state.

[1849] 6. Review and adjust results

[1850] The server presents the generated results to the user:

[1851] The server sends the generated ad creative to the user's device and presents it to the user.

[1852] The user reviews the generated results and provides instructions for adjustments:

[1853] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might enter additional requests such as, "Could you make the tagline a little shorter?"

[1854] The server will regenerate:

[1855] The server then sends another request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[1856] 7. Final Output

[1857] User final confirmation:

[1858] The user reviews the final ad creative on their device and confirms that there are no problems.

[1859] The server outputs a file:

[1860] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[1861] This invention allows users to create high-quality advertising creatives in a short amount of time, significantly reducing time and costs. Furthermore, it enables the generation of advertising creatives that respond to the user's emotional state, allowing for the delivery of more appropriate and effective advertisements.

[1862] The following describes the processing flow.

[1863] Step 1:

[1864] The user logs into the system to begin creating ad creatives on their device. A user ID and password are required for login.

[1865] Step 2:

[1866] Users provide input data such as target customer segments, product information, and advertising themes to input forms using their devices. For example, for an advertising theme of "New Spring Floral Perfume," they might input keywords such as "spring, floral, perfume, women's."

[1867] Step 3:

[1868] The user submits the input data to the system by pressing the submit button. The input data is received by the server and stored in the database.

[1869] Step 4:

[1870] The server uses an emotion engine to analyze voice, facial, or text data acquired from the user's device to recognize the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive."

[1871] Step 5:

[1872] The server combines emotional state information obtained from the emotion engine and creates a request for promotional text generation from the generative artificial intelligence. The request includes input data and the user's emotional state (e.g., "positive").

[1873] Step 6:

[1874] The server sends a request to a generative artificial intelligence (AI), which generates a catchy slogan based on the input data and emotional state information. For example, it might generate the slogan, "Let the scent of spring blossom in your heart."

[1875] Step 7:

[1876] The server receives the advertising copy generated by the generative artificial intelligence and stores it in a database. This advertising copy is then used in the next step.

[1877] Step 8:

[1878] The server creates a request to the image generation tool to generate an advertising image based on the generated ad copy, input data, and sentiment state information. The request includes keywords such as "spring, floral, perfume, women's, elegant image."

[1879] Step 9:

[1880] The server sends a request to an image generation tool, which generates an advertising image based on input data, advertising text, and sentiment information. For example, it might generate an image of an elegant (floral) perfume bottle.

[1881] Step 10:

[1882] The server receives the advertising image generated by the image generation tool and stores it in the database. This advertising image is used in the next step.

[1883] Step 11:

[1884] The server retrieves promotional text and ad images generated from the database, combines them, and automatically generates ad creatives. Emotional state information is also taken into consideration.

[1885] Step 12:

[1886] The server sends the generated ad creative to the user's device and presents it to the user.

[1887] Step 13:

[1888] Users can review the ad creative generated on their device and submit requests for adjustments or changes as needed. For example, they might request, "I'd like the tagline to be a little shorter."

[1889] Step 14:

[1890] The server receives the user's adjustment request and sends a regeneration request to the generative artificial intelligence or image generation tool to generate new taglines and images.

[1891] Step 15:

[1892] The server resends the regenerated ad creative to the user's device and presents it to the user.

[1893] Step 16:

[1894] The user reviews the final ad creative on their device and confirms that there are no problems.

[1895] Step 17:

[1896] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link.

[1897] (Example 2)

[1898] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1899] The modern advertising industry demands the rapid generation of high-quality advertising creatives. However, doing this manually is time-consuming and costly, and creating ads that reflect user emotions and needs is even more difficult. Furthermore, traditional systems have the problem of not being able to flexibly regenerate the advertising copy and images that users desire.

[1900] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data using a terminal, means for generating advertising copy using a generation AI model based on the input data and the user's emotional state, and means for generating advertising images using an image generation tool based on the generated advertising copy, the emotional state, and the input data. This enables the automatic generation of high-quality advertising creatives that are tailored to the user's emotional state. Furthermore, it is equipped with interface means for checking and adjusting the generated advertising creatives, and it is also possible to instruct the regeneration of advertising copy and advertising images, thereby realizing a flexible advertising creation process.

[1901] A "terminal" is a device used by a user to provide input data to a system, and generally refers to information processing devices such as computers and smartphones.

[1902] "Input data" refers to information that users provide to the system, including detailed data such as target customer segments, product information, and advertising themes.

[1903] "Emotional state" refers to data that represents a user's current emotions, and is classified as positive, negative, neutral, etc., by analyzing voice, facial expressions, text, etc.

[1904] A "generative AI model" is an artificial intelligence system that generates advertising copy based on input data and emotional states, and refers to, for example, a large-scale language model.

[1905] "Advertising text" refers to advertising wording such as copywriting and catchphrases generated by generative AI models.

[1906] An "image generation tool" refers to a system or software that generates advertising images based on input data, generated advertising text, and emotional states.

[1907] "Advertising images" refer to visual advertising elements generated by image generation tools, and include photographs, illustrations, graphic designs, etc.

[1908] "Advertising creative" refers to complete advertising content created by combining generated advertising copy and advertising images.

[1909] "Interface means" refers to means by which users can review and adjust generated advertising creatives, and generally includes user-friendly screens and operating methods.

[1910] This invention is a system that automatically generates advertising creatives by generating advertising copy using generative artificial intelligence (AI) based on input data, generating advertising images using an image generation tool, and incorporating an emotion engine that recognizes the user's emotional state. This system combines the generated advertising copy and advertising images to create advertising creatives and includes a user interface means for the user to review and adjust them.

[1911] First, the user uses their device to input the target customer base, product information, and advertising theme. For example, for an advertising theme of "New Spring Floral Perfume," they can input keywords such as "spring, floral, perfume, women's." Users can also provide voice and facial expression data. This data is transmitted to the server via the device.

[1912] Next, the server uses an emotion engine to analyze the voice, facial expressions, or text data provided by the user to recognize the user's emotional state. For example, if the user is smiling through the camera, the emotion engine will recognize this as "positive." This emotion analysis is performed using tools such as IBM Watson's emotion analysis API.

[1913] Next, the server creates and sends a request to a generative AI model (e.g., OpenAI GPT-4) to generate advertising copy, based on the input data and the user's emotional state. The following are examples of the specific prompts used:

[1914] Based on the following keywords—"spring," "floral," "perfume," "women's," and "elegant"—and the user's emotional state—"positive," please generate a tagline for a new floral perfume.

[1915] The generative AI model generates a tagline based on this request, creating an advertisement such as, "Let the scent of spring blossom in your heart." The generated advertisement is received by the server and stored in the database.

[1916] The server then sends a request to an image generation tool (e.g., MidJourney or DALL-E) to generate an advertising image, based on the generated ad copy, input data, and the user's emotional state. The prompt might look something like this:

[1917] Please generate an ad image based on the keywords "spring, floral, perfume, women's, elegant image".

[1918] The image generation tool generates an advertisement image based on this prompt, creating an image that, for example, includes an elegant background and a floral design. The generated advertisement image is also received by the server and stored in the database.

[1919] Ultimately, the server combines the generated ad copy, ad images, and sentiment state to create ad creatives. The generated ad creatives are presented to the user through a user interface. The user can review the generated ad creatives and, if necessary, instruct the server to regenerate the ad copy and ad images. Upon receiving a regeneration request, the server sends new prompts to the generation AI model and image generation tools to generate new ad copy and ad images.

[1920] This system enables users to efficiently generate high-quality ad creatives, saving both time and money. Furthermore, it allows for the creation of ad creatives tailored to the user's emotional state, providing personalized and effective advertising.

[1921] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1922] Step 1:

[1923] The user provides input data on their device.

[1924] The user uses a terminal to input data such as target customer segment, product information, and advertising theme into the system. Specifically, the user enters the advertising theme "New Spring Floral Perfume" and keywords such as "spring, floral, perfume, for women" into the input form on the terminal. The entered data is then sent from the terminal to the server.

[1925] Input: Target customer base, product information, advertising theme, keywords

[1926] Output: Send input data to the server

[1927] Step 2:

[1928] The server uses an emotion engine to analyze the user's emotional state.

[1929] The server acquires voice data, facial expression data, and text data sent from the terminal. Next, it sends this data to the emotion engine for analysis to recognize the user's emotional state. For example, if the user's facial expression is smiling, the emotion engine recognizes it as "positive."

[1930] Input: Audio data, facial expression data, text data

[1931] Output: User's emotional state (e.g., positive)

[1932] Step 3:

[1933] The server sends a request to the AI ​​model to generate advertising copy.

[1934] The server creates a request to the AI ​​model to generate advertising copy based on the input data and the user's emotional state. The prompt text includes the advertising theme and emotional state. For example, it generates a prompt text like the following:

[1935] Based on the following keywords—"spring," "floral," "perfume," "women's," and "elegant"—and the user's emotional state—"positive," please generate a tagline for a new floral perfume.

[1936] The generative AI model generates catchphrases based on this.

[1937] Input: Input data, user's emotional state

[1938] Output: Prompt text for the generating AI model, generated catchphrase

[1939] Step 4:

[1940] The server receives the generated advertisement text.

[1941] The server receives the catchphrase from the generating AI model and saves it to the database. Let's assume the generated catchphrase is "Let's let the scent of spring blossom in our hearts."

[1942] Input: Catchphrases from a generated AI model

[1943] Output: Catchphrases stored in the database

[1944] Step 5:

[1945] The server sends a request to the image generation tool.

[1946] The server sends a request to the image generation tool to generate an advertising image based on the generated tagline, input data, and the user's emotional state. The prompt message will use something like the following:

[1947] Please generate an ad image based on the keywords "spring, floral, perfume, women's, elegant image".

[1948] The image generation tool generates advertising images based on this.

[1949] Input: Generated tagline, input data, user's emotional state

[1950] Output: Prompt text for the image generation tool, generated advertisement image

[1951] Step 6:

[1952] The server receives the generated ad images.

[1953] The server receives the advertising images generated by the image generation tool and stores them in the database.

[1954] Input: Advertisement image from an image generation tool

[1955] Output: Advertisement images stored in the database

[1956] Step 7:

[1957] The server creates the ad creative.

[1958] The server automatically generates ad creatives by combining the generated ad copy, ad images, and emotional states. For example, it might place the tagline "Let the scent of spring blossom in your heart" on an elegant background image.

[1959] Input: Generated ad copy, ad images, sentiment status

[1960] Output: Generated ad creative

[1961] Step 8:

[1962] The server presents the generated results to the user.

[1963] The server sends the generated ad creative to the user's device and displays it.

[1964] Input: Generated ad creative

[1965] Output: Generated results sent to the user's terminal

[1966] Step 9:

[1967] The user reviews the generated results and gives instructions for adjustments.

[1968] Users can review the ad creative generated on their device and enter requests for adjustments or changes as needed. For example, they can enter specific requests such as "I'd like the tagline to be a little shorter" or "I'd like to change the background color."

[1969] Input: Generated ad creative, user adjustment requests

[1970] Output: Sending adjustment request to the server

[1971] Step 10:

[1972] The server will regenerate.

[1973] The server processes the adjustment requests collected through the user interface, sends new prompt messages to the generation AI model and image generation tools, and generates new promotional text and advertising images.

[1974] Input: User adjustment request

[1975] Output: New prompt text, new promotional text, and advertising image

[1976] Step 11:

[1977] The user performs a final check.

[1978] The user reviews the final ad creative on their device and confirms that there are no problems.

[1979] Input: Regenerated ad creative

[1980] Output: User's final approval

[1981] Step 12:

[1982] The server outputs the file.

[1983] The server outputs the final ad creative in the appropriate format (e.g., JPEG, PNG) and provides the user with a download link. Through this link, the user can obtain the final ad creative.

[1984] Input: Final ad creative

[1985] Output: Download link

[1986] (Application Example 2)

[1987] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1988] Current methods for generating ad creatives are time-consuming and labor-intensive, as advertisers must manually create and combine promotional text and images. Furthermore, because ads are created uniformly, it's difficult to provide personalized ads tailored to individual users' emotional states and destination information. This results in limited ad effectiveness.

[1989] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1990] In this invention, the server includes means for receiving input data, means for generating advertising text using generative artificial intelligence based on the input data, means for generating advertising images using an image generation tool based on the generated advertising text and the input data, means for generating advertising creative by combining the generated advertising text and advertising images, user interface means for checking and adjusting the generated advertising creative, means for acquiring passenger destination information, means for recognizing passenger emotional states, and means for generating advertising text and advertising images as personalized advertisements based on the passenger destination information and emotional states. This makes it possible to automatically generate highly effective personalized advertisements tailored to the emotional states and destination information of individual users and provide them in a short amount of time.

[1991] "Input data" refers to information provided by the user to the system for generating advertisements, including, for example, target customer segments, product information, and themes of advertisements.

[1992] "Generative artificial intelligence" refers to an artificial intelligence program that automatically generates advertising copy based on input data.

[1993] An "image generation tool" is a software tool that automatically generates advertising images based on generated advertising text and input data.

[1994] "Advertising creative" refers to advertising materials created by combining generated advertising copy and advertising images.

[1995] A "user interface means" is an interface means that allows the user to review the generated advertising creative and instruct it to be adjusted or regenerated as needed.

[1996] "Destination information" refers to information about the destination set by the passenger.

[1997] "Emotional state" refers to information that represents a passenger's emotions, and is analyzed from, for example, facial expressions and tone of voice.

[1998] "Personalized advertising" refers to advertisements that are individually tailored based on a passenger's destination information and emotional state.

[1999] In order to realize the system of the present invention, the following program must be implemented. This program automatically generates advertising creatives based on user input data and provides personalized advertisements to the user.

[2000] Program Processing Overview

[2001] 1. Receiving input data:

[2002] The system receives information necessary for ad generation from the user's device, such as target customer segment, product information, and ad theme, and sends it to the server.

[2003] 2. Obtaining destination information:

[2004] The server retrieves destination information from the system inside the passenger's autonomous vehicle.

[2005] 3. Recognition of emotional states:

[2006] The server uses emotion recognition software to analyze passengers' camera and audio streams, including their smiles and tone of voice, to recognize their emotional state. This emotion recognition software is called "EmotionRecognition."

[2007] 4. Generating promotional text:

[2008] The server uses generative artificial intelligence (AI text generator) to generate promotional text based on the passenger's emotional state and destination information. For example, it might use a prompt such as, "Generate a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring."

[2009] 5. Generating advertising images:

[2010] The server uses an image generation tool (AI image generator) to generate personalized advertising images based on the generated promotional text and destination information. For example, it might use a prompt such as, "Generate a beautiful image that reflects spring, Tokyo Tower, tourism, and positive emotions."

[2011] 6. Generating ad creatives:

[2012] The server combines the generated promotional text and advertising images to create personalized ads as advertising creatives.

[2013] 7. Display of advertisements:

[2014] The server displays the generated ad creatives on displays inside the autonomous vehicle and on passengers' smart devices (smartphones and head-mounted displays).

[2015] 8. Verification and adjustment via the user interface:

[2016] Users review the displayed ad creatives and instruct the system to adjust or regenerate them as needed.

[2017] Hardware and software to be used

[2018] Camera and microphone: Devices for detecting the emotional state of passengers.

[2019] Autonomous vehicle display: A device for displaying advertisements.

[2020] Smart devices (smartphones, head-mounted displays): Devices used to display advertisements individually.

[2021] EmotionRecognition: Emotion recognition software. Analyzes passengers' emotional states in real time.

[2022] AI Text Generator: A generative artificial intelligence system. It generates advertising text based on emotional states and destination information.

[2023] AI Image Generator: Image generation tool. Generates advertising images.

[2024] Specific examples and prompt statements

[2025] For example, if a passenger is heading to "Tokyo Tower," use the following prompt:

[2026] EmotionRecognition:

[2027] "Use the camera and audio streams to determine if the passenger is smiling."

[2028] AI Text Generator:

[2029] "Please create a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring."

[2030] AI Image Generator:

[2031] "Please generate a beautiful image that reflects spring, Tokyo Tower, sightseeing, and positive emotions."

[2032] This embodiment makes it possible to automatically generate highly effective personalized advertisements tailored to each user's emotional state and destination information, and deliver them in a short amount of time.

[2033] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2034] Step 1:

[2035] The user's device inputs the information necessary for ad generation and sends it to the server. This input data includes target customer segment, product information, and ad theme. The server receives this data and uses it for further processing.

[2036] Step 2:

[2037] The server retrieves passenger destination information from the system within the autonomous vehicle. This destination information is used in a later processing step to personalize the advertisement content.

[2038] Step 3:

[2039] The server analyzes the camera and audio streams and uses emotion recognition software to recognize the passenger's emotional state. Specifically, it uses information such as whether the passenger is smiling and their tone of voice to classify their emotional state as "positive" or "negative." This allows the emotional state to be determined.

[2040] Step 4:

[2041] Based on emotional states and destination information, the server sends prompts to a generative artificial intelligence (AI text generator) to generate appropriate advertising copy. For example, if the prompt is "Generate a catchy slogan that reflects positive emotions for visitors to Tokyo Tower in the spring," the generated slogan will be output.

[2042] Step 5:

[2043] The server sends prompts to an image generation tool (AI image generator) based on the advertisement text and destination information, and generates an advertising image. For example, if the prompt is "Generate a beautiful image that reflects spring, Tokyo Tower, tourism, and positive emotions," the generated image will be output.

[2044] Step 6:

[2045] The server combines the generated promotional text and advertising images to create advertising creatives. Specifically, the generated text is placed on the images, resulting in visually appealing advertising materials.

[2046] Step 7:

[2047] The server sends the generated ad creatives to displays in the autonomous vehicle and to passengers' smart devices for display. This allows passengers to visually see personalized ads while on their way to their destination.

[2048] Step 8:

[2049] Users review the displayed ad creative and instruct it to be adjusted or regenerated as needed. Specifically, they request revisions to the tagline or regeneration of images through the user interface. This request is sent to the server, the regeneration process is performed again, and a new ad creative is created.

[2050] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[2051] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2052] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[2053] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2054] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[2055] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[2056] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[2057] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[2058] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[2059] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[2060] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[2061] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[2062] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[2063] 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.

[2064] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[2065] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[2066] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[2067] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[2068] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[2069] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[2070] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[2071] The following is further disclosed regarding the embodiments described above.

[2072] (Claim 1)

[2073] A means for receiving input data,

[2074] A means for generating advertising copy using generative artificial intelligence based on the input data,

[2075] A means for generating an advertising image using an image generation tool based on the generated advertising text and the input data,

[2076] A means for generating advertising creative by combining the generated advertising text and advertising images,

[2077] A user interface means for reviewing and adjusting the generated advertising creative,

[2078] A system that includes this.

[2079] (Claim 2)

[2080] The system according to claim 1, characterized in that the user interface means includes means for confirming the generated advertising creative and, if necessary, for regenerating the advertising text and advertising images.

[2081] (Claim 3)

[2082] The system according to claim 1, characterized in that the generative artificial intelligence and image generation tool are configured to perform the generation based on specific keywords and instructions.

[2083] "Example 1"

[2084] (Claim 1)

[2085] A means for receiving input data,

[2086] A means for generating advertising copy using generative artificial intelligence based on the input data,

[2087] A means for generating an advertising image using an image generation tool based on the generated advertising text and the input data,

[2088] A means for generating advertising creative by combining the generated advertising text and advertising images,

[2089] A user interface means for reviewing and adjusting the generated advertising creative,

[2090] A means for finally outputting the generated advertising creative,

[2091] A system that includes this.

[2092] (Claim 2)

[2093] The system according to claim 1, characterized in that the user interface means includes means for confirming the generated advertising creative and, if necessary, for regenerating the advertising text and advertising images.

[2094] (Claim 3)

[2095] The system according to claim 1, characterized in that the generative artificial intelligence and image generation tool are configured to perform the generation based on specific keywords and instructions.

[2096] "Application Example 1"

[2097] (Claim 1)

[2098] A means for receiving input data,

[2099] A means for generating advertising copy using generative artificial intelligence based on the input data,

[2100] A means for generating an advertising image using an image generation tool based on the generated advertising text and the input data,

[2101] A means for generating advertising creative by combining the generated advertising text and advertising images,

[2102] A user interface means for reviewing and adjusting the generated advertising creative,

[2103] A means by which users provide input data such as target customer segments, product information, and advertising themes using smartphones,

[2104] A means of displaying the generated advertising creative on the user's smartphone and accepting user confirmation and adjustments,

[2105] A system that includes this.

[2106] (Claim 2)

[2107] The system according to claim 1, characterized in that the user interface means includes means for confirming the generated advertising creative and, if necessary, for regenerating the advertising text and advertising images.

[2108] (Claim 3)

[2109] The system according to claim 1, characterized in that the generative artificial intelligence and image generation tool are configured to perform the generation based on specific keywords and instructions.

[2110] "Example 2 of combining an emotion engine"

[2111] (Claim 1)

[2112] A means of receiving input data using a terminal,

[2113] A means for generating advertising copy using a generation AI model based on the input data and the user's emotional state,

[2114] A means for generating an advertising image using an image generation tool based on the generated advertising text, the emotional state, and the input data,

[2115] A means for generating advertising creative by combining the generated advertising text, advertising images, and emotional state,

[2116] Interface means for reviewing and adjusting the generated advertising creative,

[2117] A system that includes this.

[2118] (Claim 2)

[2119] The system according to claim 1, characterized in that the interface means includes means for confirming the generated advertising creative and, if necessary, for regenerating the advertising copy and advertising images.

[2120] (Claim 3)

[2121] The system according to claim 1, characterized in that the generation AI model and image generation tool are configured to perform the generation based on specific keywords and emotional states.

[2122] "Application example 2 when combining with an emotional engine"

[2123] (Claim 1)

[2124] A means for receiving input data,

[2125] A means for generating advertising copy using generative artificial intelligence based on the input data,

[2126] A means for generating an advertising image using an image generation tool based on the generated advertising text and the input data,

[2127] A means for generating advertising creative by combining the generated advertising text and advertising images,

[2128] A user interface means for reviewing and adjusting the generated advertising creative,

[2129] Means for obtaining passenger destination information,

[2130] Means for recognizing the emotional state of passengers,

[2131] A means for generating advertising text and advertising images as personalized advertisements based on the passenger's destination information and emotional state,

[2132] A system that includes this.

[2133] (Claim 2)

[2134] The system according to claim 1, characterized in that the user interface means includes means for confirming the generated advertising creative and, if necessary, for regenerating the advertising text and advertising images.

[2135] (Claim 3)

[2136] The system according to claim 1, characterized in that the generative artificial intelligence and image generation ...

Claims

1. A means for receiving input data, A means for generating advertising copy using generative artificial intelligence based on the input data, A means for generating an advertising image using an image generation tool based on the generated advertising text and the input data, A means for generating advertising creative by combining the generated advertising text and advertising images, A user interface means for reviewing and adjusting the generated advertising creative, A system that includes this.

2. The system according to claim 1, characterized in that the user interface means includes means for confirming the generated advertising creative and, if necessary, for regenerating the advertising text and advertising images.

3. The system according to claim 1, characterized in that the generative artificial intelligence and image generation tool are configured to perform the generation based on specific keywords and instructions.

Images