system

Abstract

The system according to this embodiment aims to automatically replace advertisement images that are unpleasant to the user. [Solution] The system according to the embodiment comprises a learning unit, a checking unit, a generation unit, and a replacement unit. The learning unit learns advertising images that users find unpleasant. The checking unit checks advertising images based on the features learned by the learning unit. The generation unit generates alternative images to replace advertising images that the checking unit has determined to be unpleasant. The replacement unit replaces the advertising images with the alternative images generated by the generation unit.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , , ,

[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] In the conventional technology, an advertisement image that gives an unpleasant experience to the user may be displayed, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically replace an advertisement image that is unpleasant to the user.

[0006] ​​The system according to this embodiment comprises a learning unit, a checking unit, a generation unit, and a replacement unit. The learning unit learns advertising images that users find unpleasant. The checking unit checks advertising images based on the features learned by the learning unit. The generation unit generates alternative images to replace advertising images that the checking unit has determined to be unpleasant. The replacement unit replaces the advertising images with the alternative images generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically replace advertisement images that are unpleasant to the user. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, 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), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] 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.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The advertising image replacement system according to an embodiment of the present invention is a system for mitigating the unpleasant experience that web advertisements give to users. This advertising image replacement system improves the user experience by learning advertising images that users find unpleasant, checking advertising images, generating alternative images, and replacing the advertising images. The advertising image replacement system according to an embodiment of the present invention consists of the following steps. First, it learns advertising images that users find unpleasant. Using a generation AI, it analyzes past advertising image data and extracts features that users find unpleasant. Next, it checks the advertising image when the advertisement is published. The generation AI analyzes the advertising image and determines whether it is likely to be unpleasant for the user. At this time, a threshold is set, and if the threshold is exceeded, it is replaced with an alternative image. The generation AI is used to generate the alternative image. The generation AI generates a mild alternative image that reflects the content that the advertisement wants to convey. For example, if the message of the advertisement is "Introducing a new cosmetic product," the generation AI generates a mild image that reflects that message. This alternative image is replaced with the original advertising image and displayed to the user. With this system, users can receive the message of the advertisement without seeing unpleasant advertising images. Furthermore, advertisers can protect their profitability while preventing damage to the image of their web ads. In addition, this system can check ad images and generate alternative images in real time. This allows for quick responses each time an ad is displayed, minimizing the unpleasant user experience. Thus, the ad image replacement system reduces the unpleasant user experience and protects advertisers' profitability.

[0029] The advertising image replacement system according to this embodiment comprises a learning unit, a checking unit, a generation unit, and a replacement unit. The learning unit learns advertising images that users find unpleasant. The learning unit analyzes past advertising image data using, for example, a generation AI, and extracts features that users find unpleasant. For example, the learning unit takes past advertising image data as input to the generation AI and outputs features that users find unpleasant. The checking unit checks advertising images based on the features learned by the learning unit. The checking unit analyzes advertising images using, for example, a generation AI, and determines whether there is a possibility that users will find them unpleasant. For example, the checking unit takes an advertising image as input to the generation AI and outputs the possibility that users will find it unpleasant. The generation unit generates alternative images to replace advertising images that the checking unit has determined to be unpleasant. The generation unit generates mild alternative images that reflect the message the advertisement wants to convey using, for example, a generation AI. For example, the generation unit takes the advertisement message as input to the generation AI and outputs a mild alternative image. The replacement unit replaces the advertising image with the alternative image generated by the generation unit. The replacement unit replaces the original advertisement image with an alternative image generated using, for example, a generation AI. For example, the replacement unit takes an alternative image generated by a generation AI as input and outputs a process that replaces the advertisement image. As a result, the advertisement image replacement system according to this embodiment improves the user experience by automatically replacing advertisement images that users find unpleasant.

[0030] The learning unit learns which advertising images users find unpleasant. Specifically, the learning unit uses generative AI to analyze past advertising image data and extract features that users find unpleasant. The generative AI, for example, uses deep learning technology to learn from a large dataset of advertising images and associates it with user response data. As a result, the generative AI learns that certain colors, compositions, facial expressions, and text content are likely to cause discomfort to users. Furthermore, the learning unit continuously collects user feedback data and updates the generative AI model to respond to the latest trends and changes in user preferences. For example, it collects data on which users rated advertising images as "unpleasant" and adds this to the generative AI's training data. This allows the learning unit to extract features of advertising images that users find unpleasant with high accuracy and improve the overall accuracy of the system.

[0031] The checking unit checks advertising images based on features learned by the learning unit. Specifically, the checking unit uses a generative AI to analyze advertising images and determine whether they are likely to be offensive to users. The generative AI builds a model to evaluate advertising images based on the features extracted by the learning unit. This model takes advertising images as input and outputs a score indicating the likelihood of users finding them offensive. For example, if the colors of an advertising image are excessively flashy or the text contains offensive content, the generative AI will output a high offensiveness score. Based on this score, the checking unit determines that an advertising image is likely to cause offense to users and flags it as inappropriate. Furthermore, because the checking unit can analyze advertising images in real time, it can quickly detect inappropriate images before they are delivered to users and address them before they are displayed. This allows the checking unit to proactively eliminate advertising images that users might find offensive, thereby improving the user experience.

[0032] The generation unit generates alternative images to replace advertising images that have been deemed offensive by the checking unit. Specifically, the generation unit uses a generation AI to generate milder alternative images that reflect the message the advertisement wants to convey. The generation AI takes the advertisement's message and brand image as input and generates images that will be well-received by users based on that. For example, if the advertisement's message is to promote a "healthy lifestyle," the generation AI will generate images that include bright colors, calm scenery, and smiling people. The generation unit verifies the alternative images output by the generation AI to confirm whether they accurately reflect the intent of the advertisement. Furthermore, the generation unit can undergo evaluation by the checking unit again to ensure that the generated alternative images do not cause discomfort to users. This allows the generation unit to provide alternative images that are comfortable for users while achieving the objectives of the advertisement.

[0033] The replacement unit replaces the original ad image with a replacement image generated by the generation unit. Specifically, the replacement unit replaces the original ad image with a replacement image generated using generation AI. The replacement unit can work in conjunction with the ad delivery system to replace ad images in real time. For example, if an ad image displayed on a website or application is determined to be inappropriate, the replacement unit immediately retrieves a replacement image provided by the generation unit and replaces the original ad image. This process occurs without delay when the user views the ad, allowing ad images to be replaced without compromising the user experience. Furthermore, the replacement unit manages ad delivery logs and records which ad images have been replaced, providing transparency to advertisers. This allows the replacement unit to quickly and efficiently replace ad images that users find unpleasant, improving the user experience and providing a reliable service to advertisers.

[0034] The learning unit can analyze past advertising image data and extract features that users find unpleasant. For example, the learning unit can use a generative AI to analyze past advertising image data and extract features that users find unpleasant. For instance, the learning unit can use a generative AI to take past advertising image data as input and output features that users find unpleasant. The learning unit can also use image analysis and data mining techniques when analyzing past advertising image data. For example, the learning unit can use image analysis techniques to analyze the colors and shapes of advertising images and extract features that users find unpleasant. The learning unit can also use data mining techniques to analyze the text content of advertising images and extract features that users find unpleasant. In this way, the learning unit can accurately extract features that users find unpleasant by analyzing past data.

[0035] The checking unit can analyze advertising images and determine whether they may be offensive to users. For example, the checking unit can use a generative AI to analyze advertising images and determine whether they may be offensive to users. For example, the checking unit takes an advertising image as input and outputs whether it is likely to be offensive to users. The checking unit can also use image analysis technology and data mining technology when analyzing advertising images. For example, the checking unit can use image analysis technology to analyze the colors and shapes of advertising images and determine whether it is likely to be offensive to users. The checking unit can also use data mining technology to analyze the text content of advertising images and determine whether it is likely to be offensive to users. In this way, the checking unit can determine in advance whether an advertising image is likely to be offensive to users by analyzing it.

[0036] The generation unit can generate mild alternative images that reflect the message the advertisement wants to convey. For example, the generation unit can use a generation AI to generate mild alternative images that reflect the message the advertisement wants to convey. For example, the generation unit can use a generation AI that takes the advertisement's message as input and output a mild alternative image. The generation unit can also use image generation algorithms and design standards when generating alternative images that reflect the message the advertisement wants to convey. For example, the generation unit can use an image generation algorithm to generate alternative images that reflect the message of the advertisement. The generation unit can also use design standards to generate alternative images that reflect the message of the advertisement. In this way, the generation unit can generate images that are not offensive to the user without compromising the message of the advertisement.

[0037] The replacement unit can replace the original ad image with a generated alternative image. For example, the replacement unit can replace the original ad image with an alternative image generated using a generation AI. For example, the replacement unit can take an alternative image generated by a generation AI as input and output a process that replaces the ad image. Furthermore, when replacing ad images, the replacement unit can perform replacements in real time or based on user actions. For example, the replacement unit can replace ad images in real time. Also, the replacement unit can replace ad images based on user actions. This allows the replacement unit to quickly replace unpleasant ad images with alternative images.

[0038] The checking unit can perform real-time checks on advertising images. For example, the checking unit can use a generation AI to perform real-time checks on advertising images. For instance, the checking unit takes advertising images as input and outputs real-time check results. The checking unit can also consider processing speed and latency when performing real-time checks on advertising images. For example, the checking unit can use high-performance hardware to improve processing speed. The checking unit can also use efficient algorithms to minimize latency. As a result, the checking unit can respond quickly by checking advertising images in real time.

[0039] The learning unit can analyze the background and color patterns of advertising images to identify elements that users find unpleasant. For example, the learning unit can use generative AI to analyze the background and color patterns of advertising images and identify elements that users find unpleasant. For example, the learning unit can use generative AI to take the background and color patterns of advertising images as input and output unpleasant elements. For example, the learning unit can analyze the impact that the background color of an advertising image has on the user, and the generative AI can identify unpleasant color patterns. The learning unit can also analyze the design elements of advertising images (e.g., fonts, layout), and the generative AI can identify unpleasant elements. Furthermore, the learning unit can analyze the dynamic elements of advertising images (e.g., animations, effects), and the generative AI can identify unpleasant elements. In this way, the learning unit can identify unpleasant elements by analyzing the background and color patterns of advertising images.

[0040] The learning unit can identify which ads were perceived as offensive by referring to a user's past ad click history. For example, the learning unit can use generative AI to refer to a user's past ad click history and identify which ads were perceived as offensive. For example, the learning unit can use generative AI as input to identify offensive ads. For example, the learning unit can collect ad images that users did not click on, and the generative AI can identify offensive elements. The learning unit can also collect ad images that users closed quickly, and the generative AI can identify offensive elements. Furthermore, the learning unit can collect ad images to which users gave negative feedback, and the generative AI can identify offensive elements. In this way, the learning unit can identify offensive ads by referring to past click history.

[0041] The learning unit can analyze the text content of advertising images and identify words and phrases that users find offensive. For example, the learning unit can use a generative AI to analyze the text content of advertising images and identify words and phrases that users find offensive. For example, the learning unit can use a generative AI to take the text content of an advertising image as input and output offensive words and phrases. For example, the learning unit can analyze the catchphrase of an advertising image and have the generative AI identify offensive words and phrases. The learning unit can also analyze the description of an advertising image and have the generative AI identify offensive words and phrases. Furthermore, the learning unit can analyze the entire text element of an advertising image and have the generative AI identify offensive words and phrases. In this way, the learning unit can identify offensive words and phrases by analyzing the text content of advertising images.

[0042] The learning unit can learn different elements of unpleasantness for each device based on the user's device information. For example, the learning unit uses a generative AI to learn different elements of unpleasantness for each device based on the user's device information. For example, the learning unit takes the user's device information as input to the generative AI and outputs elements of unpleasantness. For example, the learning unit identifies elements of unpleasantness in advertising images for smartphone users, and the generative AI learns them. The learning unit can also identify elements of unpleasantness in advertising images for tablet users, and the generative AI learns them. Furthermore, the learning unit can identify elements of unpleasantness in advertising images for desktop users, and the generative AI learns them. As a result, the learning unit can generate advertising images with higher accuracy by learning different elements of unpleasantness for each device.

[0043] The checking unit can analyze the movement and animation of advertising images and identify movements that users find unpleasant. For example, the checking unit can use a generative AI to analyze the movement and animation of advertising images and identify movements that users find unpleasant. For example, the checking unit can use a generative AI to take the movement and animation of advertising images as input and output unpleasant movements. For example, the checking unit can analyze the animation speed of advertising images and have the generative AI identify unpleasant movements. The checking unit can also analyze the dynamic effects of advertising images and have the generative AI identify unpleasant movements. Furthermore, the checking unit can analyze the transition effects of advertising images and have the generative AI identify unpleasant movements. In this way, the checking unit can identify unpleasant movements by analyzing the movement and animation of advertising images.

[0044] The checking unit can analyze the audio elements of an advertisement image and identify sounds that users find unpleasant. For example, the checking unit can use a generative AI to analyze the audio elements of an advertisement image and identify sounds that users find unpleasant. For example, the checking unit can use a generative AI that takes the audio elements of an advertisement image as input and output unpleasant sounds. For example, the checking unit can analyze the background music of an advertisement image and have the generative AI identify unpleasant sounds. The checking unit can also analyze the narration of an advertisement image and have the generative AI identify unpleasant sounds. Furthermore, the checking unit can analyze the sound effects of an advertisement image and have the generative AI identify unpleasant sounds. In this way, the checking unit can identify unpleasant sounds by analyzing the audio elements of an advertisement image.

[0045] The checking unit can determine the degree of unpleasantness of an advertisement image based on its display location. For example, the checking unit uses a generating AI to determine the degree of unpleasantness based on the display location of the advertisement image. For example, the checking unit uses a generating AI that takes the display location of the advertisement image as input and outputs the degree of unpleasantness. For example, the checking unit analyzes the degree of unpleasantness of an advertisement image displayed at the top of a webpage, and the generating AI makes a determination. The checking unit can also analyze the degree of unpleasantness of an advertisement image displayed in a sidebar, and the generating AI makes a determination. Furthermore, the checking unit can analyze the degree of unpleasantness of an advertisement image displayed in the footer, and the generating AI makes a determination. As a result, the checking unit can determine the degree of unpleasantness based on the display location of the advertisement image, enabling more appropriate checking of advertisement images.

[0046] The checking unit can evaluate the degree of deviation from the content by referring to the related content of the advertising image. For example, the checking unit can use a generating AI to refer to the related content of the advertising image and evaluate the degree of deviation from the content. For example, the checking unit can use a generating AI to take the advertising image and related content as input and output the degree of deviation. For example, the checking unit can analyze the content of an article related to the advertising image, and the generating AI can evaluate the degree of deviation. The checking unit can also analyze the content of a video related to the advertising image, and the generating AI can evaluate the degree of deviation. Furthermore, the checking unit can analyze product information related to the advertising image, and the generating AI can evaluate the degree of deviation. In this way, the checking unit can evaluate the degree of deviation from the content by referring to the related content of the advertising image.

[0047] The generation unit can analyze the message of an advertisement and select the most appropriate colors and designs for that message. For example, the generation unit can use a generation AI to analyze the message of an advertisement and select the most appropriate colors and designs for that message. For example, the generation unit can use a generation AI to take the message of an advertisement as input and output the optimal colors and designs. For example, the generation unit can analyze the catchphrase of an advertisement and have the generation AI select the optimal colors and designs. The generation unit can also analyze the description of an advertisement and have the generation AI select the optimal colors and designs. Furthermore, the generation unit can analyze the overall theme of an advertisement and have the generation AI select the optimal colors and designs. As a result, the generation unit can generate effective alternative images by selecting the most appropriate colors and designs for the message of the advertisement.

[0048] The generation unit can generate customized alternative images for different audiences based on the target audience of the advertisement. For example, the generation unit uses a generation AI to generate customized alternative images for different audiences based on the target audience of the advertisement. For example, the generation unit's generation AI takes target audience data as input and outputs a customized alternative image. For example, the generation unit's generation AI can generate an advertisement image for young people. The generation unit can also use its generation AI to generate an advertisement image for middle-aged and older people. Furthermore, the generation unit's generation AI can generate an advertisement image for audiences with specific interests. As a result, the generation unit can display advertisements more effectively by generating customized alternative images based on the target audience.

[0049] The generation unit can generate alternative images that effectively convey a message in a short time, based on the ad's display time. For example, the generation unit uses a generation AI to generate alternative images that effectively convey a message in a short time, based on the ad's display time. For example, the generation unit's generation AI takes the ad's display time as input and outputs an effective alternative image in a short time. For example, the generation unit's generation AI generates a visually impactful alternative image in a short time. The generation unit can also have its generation AI generate an alternative image that gets straight to the point in a short time. Furthermore, the generation unit's generation AI can also generate an alternative image that grabs the user's attention in a short time. In this way, the generation unit can grab the user's attention by generating alternative images that effectively convey a message in a short time.

[0050] The generation unit can generate highly relevant alternative images by referencing the products and services related to the advertisement. For example, the generation unit uses a generation AI to reference the products and services related to the advertisement and generate highly relevant alternative images. For example, the generation unit's generation AI takes data on the products and services related to the advertisement as input and outputs highly relevant alternative images. For example, the generation unit analyzes the products related to the advertisement, and the generation AI generates highly relevant alternative images. The generation unit can also analyze the services related to the advertisement, and the generation AI generates highly relevant alternative images. Furthermore, the generation unit can analyze the content related to the advertisement, and the generation AI generates highly relevant alternative images. In this way, the generation unit can generate highly relevant alternative images by referencing the products and services related to the advertisement.

[0051] The replacement unit can save the original data of the ad image during replacement, allowing for later reference. For example, the replacement unit can use a generation AI to save the original data of the ad image during replacement, allowing for later reference. For instance, the replacement unit uses a generation AI as input and outputs the saved result. Alternatively, the replacement unit can save the ad image before replacement to a database for later analysis. Furthermore, the replacement unit can log the ad image before replacement for troubleshooting. Additionally, the replacement unit can save the ad image before replacement as a backup, allowing for restoration as needed. This enables the replacement unit to save the original data of the ad image, making it available for later reference and analysis.

[0052] The replacement unit can analyze ad click-through rates and engagement data to select the optimal replacement method. For example, the replacement unit can use a generative AI to analyze ad click-through rates and engagement data and select the optimal replacement method. For example, the replacement unit can use a generative AI to take ad click-through rates and engagement data as input and output the optimal replacement method. For example, the replacement unit can analyze ad click-through rates and the generative AI can select the optimal replacement method. The replacement unit can also analyze ad engagement data and the generative AI can select the optimal replacement method. Furthermore, the replacement unit can analyze ad conversion rates and the generative AI can select the optimal replacement method. In this way, the replacement unit can select the optimal replacement method by analyzing ad click-through rates and engagement data.

[0053] The replacement unit can select the optimal replacement method based on the ad's display location. For example, the replacement unit uses a generating AI to select the optimal replacement method based on the ad's display location. For example, the replacement unit takes the ad's display location as input and outputs the optimal replacement method. For example, when replacing an ad image displayed at the top of a webpage, the generating AI selects the optimal method. The replacement unit can also use the generating AI to select the optimal method when replacing an ad image displayed in the sidebar. Furthermore, the replacement unit can use the generating AI to select the optimal method when replacing an ad image displayed in the footer. As a result, the replacement unit can display ads more effectively by selecting the optimal replacement method based on the ad's display location.

[0054] The replacement unit can refer to the relevant content of the advertisement and perform replacements while maintaining consistency with the content. For example, the replacement unit can use a generating AI to refer to the relevant content of the advertisement and perform replacements while maintaining consistency with the content. For example, the replacement unit can take the advertisement image and related content as input and output a result in which the generating AI performs replacements while maintaining consistency. For example, the replacement unit can analyze the content of an article related to the advertisement image, and the generating AI will perform replacements while maintaining consistency. The replacement unit can also analyze the content of a video related to the advertisement image, and the generating AI will perform replacements while maintaining consistency. Furthermore, the replacement unit can analyze product information related to the advertisement image, and the generating AI will perform replacements while maintaining consistency. In this way, the replacement unit can refer to the relevant content of the advertisement and perform replacements while maintaining consistency with the content.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The ad image replacement system can identify which ads were perceived as offensive by referencing a user's past browsing history. For example, it can collect ad images that a user has viewed in the past, and the generating AI can identify the offensive elements. It can also collect ad images that a user has viewed for extended periods, and the generating AI can identify the positive elements. Furthermore, it can collect ad images that users have given negative feedback on, and the generating AI can identify the offensive elements. In this way, offensive ads can be identified by referring to past browsing history.

[0057] The ad image replacement system can generate alternative images that effectively convey a message in a short amount of time, based on the ad's display time. For example, it can use a generation AI to generate effective alternative images in a short amount of time based on the ad's display time. For instance, the generation AI can generate visually impactful alternative images in a short amount of time. It can also generate alternative images that capture the key points in a short amount of time. Furthermore, the generation AI can generate alternative images that grab the user's attention in a short amount of time. In this way, by generating alternative images that effectively convey a message in a short amount of time, it is possible to attract the user's attention.

[0058] An advertising image replacement system can generate highly relevant alternative images by referencing the products and services related to the advertisement. For example, it can use a generation AI to reference the products and services related to the advertisement and generate highly relevant alternative images. For instance, it can analyze the products related to the advertisement, and the generation AI can generate highly relevant alternative images. It can also analyze the services related to the advertisement, and the generation AI can generate highly relevant alternative images. Furthermore, it can analyze the content related to the advertisement, and the generation AI can generate highly relevant alternative images. In this way, highly relevant alternative images can be generated by referencing the products and services related to the advertisement.

[0059] An ad image replacement system can generate customized alternative images for different audiences based on the target audience of an ad. For example, a generation AI can be used to generate customized alternative images for different audiences based on the target audience of an ad. For instance, the generation AI can generate ad images for younger demographics. It can also generate ad images for middle-aged and older demographics. Furthermore, the generation AI can generate ad images for audiences with specific interests. This allows for more effective ad display by generating customized alternative images based on the target audience.

[0060] The ad image replacement system can analyze ad click-through rates and engagement data to select the optimal replacement method. For example, it can use a generation AI to analyze ad click-through rates and engagement data and select the optimal replacement method. For instance, it can analyze ad click-through rates and have the generation AI select the optimal replacement method. It can also analyze ad engagement data and have the generation AI select the optimal replacement method. Furthermore, it can analyze ad conversion rates and have the generation AI select the optimal replacement method. In this way, by analyzing ad click-through rates and engagement data, the optimal replacement method can be selected.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The learning unit learns what users find offensive in advertisements. For example, it uses a generative AI to analyze past advertisement image data and extract features that users find offensive. The generative AI takes past advertisement image data as input and outputs features that users find offensive. Step 2: The checking unit checks the advertisement image based on the features learned by the learning unit. For example, it uses a generative AI to analyze the advertisement image and determine whether it is likely to be offensive to the user. The generative AI takes the advertisement image as input and outputs whether it is likely to be offensive to the user. Step 3: The generation unit generates alternative images to replace the advertising images that the checking unit has determined to be offensive. For example, it uses a generation AI to generate a milder alternative image that reflects the message the advertisement wants to convey. The generation AI takes the advertisement's message as input and outputs a milder alternative image. Step 4: The replacement unit replaces the advertisement image with the replacement image generated by the generation unit. For example, it replaces the original advertisement image with a replacement image generated using the generation AI. It takes the replacement image generated by the generation AI as input and outputs the process of replacing the advertisement image.

[0063] (Example of form 2) The advertising image replacement system according to an embodiment of the present invention is a system for mitigating the unpleasant experience that web advertisements give to users. This advertising image replacement system improves the user experience by learning advertising images that users find unpleasant, checking advertising images, generating alternative images, and replacing the advertising images. The advertising image replacement system according to an embodiment of the present invention consists of the following steps. First, it learns advertising images that users find unpleasant. Using a generation AI, it analyzes past advertising image data and extracts features that users find unpleasant. Next, it checks the advertising image when the advertisement is published. The generation AI analyzes the advertising image and determines whether it is likely to be unpleasant for the user. At this time, a threshold is set, and if the threshold is exceeded, it is replaced with an alternative image. The generation AI is used to generate the alternative image. The generation AI generates a mild alternative image that reflects the content that the advertisement wants to convey. For example, if the message of the advertisement is "Introducing a new cosmetic product," the generation AI generates a mild image that reflects that message. This alternative image is replaced with the original advertising image and displayed to the user. With this system, users can receive the message of the advertisement without seeing unpleasant advertising images. Furthermore, advertisers can protect their profitability while preventing damage to the image of their web ads. In addition, this system can check ad images and generate alternative images in real time. This allows for quick responses each time an ad is displayed, minimizing the unpleasant user experience. Thus, the ad image replacement system reduces the unpleasant user experience and protects advertisers' profitability.

[0064] The advertising image replacement system according to this embodiment comprises a learning unit, a checking unit, a generation unit, and a replacement unit. The learning unit learns advertising images that users find unpleasant. The learning unit analyzes past advertising image data using, for example, a generation AI, and extracts features that users find unpleasant. For example, the learning unit takes past advertising image data as input to the generation AI and outputs features that users find unpleasant. The checking unit checks advertising images based on the features learned by the learning unit. The checking unit analyzes advertising images using, for example, a generation AI, and determines whether there is a possibility that users will find them unpleasant. For example, the checking unit takes an advertising image as input to the generation AI and outputs the possibility that users will find it unpleasant. The generation unit generates alternative images to replace advertising images that the checking unit has determined to be unpleasant. The generation unit generates mild alternative images that reflect the message the advertisement wants to convey using, for example, a generation AI. For example, the generation unit takes the advertisement message as input to the generation AI and outputs a mild alternative image. The replacement unit replaces the advertising image with the alternative image generated by the generation unit. The replacement unit replaces the original advertisement image with an alternative image generated using, for example, a generation AI. For example, the replacement unit takes an alternative image generated by a generation AI as input and outputs a process that replaces the advertisement image. As a result, the advertisement image replacement system according to this embodiment improves the user experience by automatically replacing advertisement images that users find unpleasant.

[0065] The learning unit learns which advertising images users find unpleasant. Specifically, the learning unit uses generative AI to analyze past advertising image data and extract features that users find unpleasant. The generative AI, for example, uses deep learning technology to learn from a large dataset of advertising images and associates it with user response data. As a result, the generative AI learns that certain colors, compositions, facial expressions, and text content are likely to cause discomfort to users. Furthermore, the learning unit continuously collects user feedback data and updates the generative AI model to respond to the latest trends and changes in user preferences. For example, it collects data on which users rated advertising images as "unpleasant" and adds this to the generative AI's training data. This allows the learning unit to extract features of advertising images that users find unpleasant with high accuracy and improve the overall accuracy of the system.

[0066] The checking unit checks advertising images based on features learned by the learning unit. Specifically, the checking unit uses a generative AI to analyze advertising images and determine whether they are likely to be offensive to users. The generative AI builds a model to evaluate advertising images based on the features extracted by the learning unit. This model takes advertising images as input and outputs a score indicating the likelihood of users finding them offensive. For example, if the colors of an advertising image are excessively flashy or the text contains offensive content, the generative AI will output a high offensiveness score. Based on this score, the checking unit determines that an advertising image is likely to cause offense to users and flags it as inappropriate. Furthermore, because the checking unit can analyze advertising images in real time, it can quickly detect inappropriate images before they are delivered to users and address them before they are displayed. This allows the checking unit to proactively eliminate advertising images that users might find offensive, thereby improving the user experience.

[0067] The generation unit generates alternative images to replace advertising images that have been deemed offensive by the checking unit. Specifically, the generation unit uses a generation AI to generate milder alternative images that reflect the message the advertisement wants to convey. The generation AI takes the advertisement's message and brand image as input and generates images that will be well-received by users based on that. For example, if the advertisement's message is to promote a "healthy lifestyle," the generation AI will generate images that include bright colors, calm scenery, and smiling people. The generation unit verifies the alternative images output by the generation AI to confirm whether they accurately reflect the intent of the advertisement. Furthermore, the generation unit can undergo evaluation by the checking unit again to ensure that the generated alternative images do not cause discomfort to users. This allows the generation unit to provide alternative images that are comfortable for users while achieving the objectives of the advertisement.

[0068] The replacement unit replaces the original ad image with a replacement image generated by the generation unit. Specifically, the replacement unit replaces the original ad image with a replacement image generated using generation AI. The replacement unit can work in conjunction with the ad delivery system to replace ad images in real time. For example, if an ad image displayed on a website or application is determined to be inappropriate, the replacement unit immediately retrieves a replacement image provided by the generation unit and replaces the original ad image. This process occurs without delay when the user views the ad, allowing ad images to be replaced without compromising the user experience. Furthermore, the replacement unit manages ad delivery logs and records which ad images have been replaced, providing transparency to advertisers. This allows the replacement unit to quickly and efficiently replace ad images that users find unpleasant, improving the user experience and providing a reliable service to advertisers.

[0069] The learning unit can analyze past advertising image data and extract features that users find unpleasant. For example, the learning unit can use a generative AI to analyze past advertising image data and extract features that users find unpleasant. For instance, the learning unit can use a generative AI to take past advertising image data as input and output features that users find unpleasant. The learning unit can also use image analysis and data mining techniques when analyzing past advertising image data. For example, the learning unit can use image analysis techniques to analyze the colors and shapes of advertising images and extract features that users find unpleasant. The learning unit can also use data mining techniques to analyze the text content of advertising images and extract features that users find unpleasant. In this way, the learning unit can accurately extract features that users find unpleasant by analyzing past data.

[0070] The checking unit can analyze advertising images and determine whether they may be offensive to users. For example, the checking unit can use a generative AI to analyze advertising images and determine whether they may be offensive to users. For example, the checking unit takes an advertising image as input and outputs whether it is likely to be offensive to users. The checking unit can also use image analysis technology and data mining technology when analyzing advertising images. For example, the checking unit can use image analysis technology to analyze the colors and shapes of advertising images and determine whether it is likely to be offensive to users. The checking unit can also use data mining technology to analyze the text content of advertising images and determine whether it is likely to be offensive to users. In this way, the checking unit can determine in advance whether an advertising image is likely to be offensive to users by analyzing it.

[0071] The generation unit can generate mild alternative images that reflect the message the advertisement wants to convey. For example, the generation unit can use a generation AI to generate mild alternative images that reflect the message the advertisement wants to convey. For example, the generation unit can use a generation AI that takes the advertisement's message as input and output a mild alternative image. The generation unit can also use image generation algorithms and design standards when generating alternative images that reflect the message the advertisement wants to convey. For example, the generation unit can use an image generation algorithm to generate alternative images that reflect the message of the advertisement. The generation unit can also use design standards to generate alternative images that reflect the message of the advertisement. In this way, the generation unit can generate images that are not offensive to the user without compromising the message of the advertisement.

[0072] The replacement unit can replace the original ad image with a generated alternative image. For example, the replacement unit can replace the original ad image with an alternative image generated using a generation AI. For example, the replacement unit can take an alternative image generated by a generation AI as input and output a process that replaces the ad image. Furthermore, when replacing ad images, the replacement unit can perform replacements in real time or based on user actions. For example, the replacement unit can replace ad images in real time. Also, the replacement unit can replace ad images based on user actions. This allows the replacement unit to quickly replace unpleasant ad images with alternative images.

[0073] The checking unit can perform real-time checks on advertising images. For example, the checking unit can use a generation AI to perform real-time checks on advertising images. For instance, the checking unit takes advertising images as input and outputs real-time check results. The checking unit can also consider processing speed and latency when performing real-time checks on advertising images. For example, the checking unit can use high-performance hardware to improve processing speed. The checking unit can also use efficient algorithms to minimize latency. As a result, the checking unit can respond quickly by checking advertising images in real time.

[0074] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, the learning unit can use a generative AI to estimate the user's emotions and select training data based on the estimated user emotions. For example, the learning unit can use a generative AI to take user emotion data as input and output the results of the training data selection. For example, the learning unit can collect advertising images that users found unpleasant, and the generative AI can learn their characteristics. The learning unit can also collect advertising images that users found favorable, and the generative AI can learn their characteristics. Furthermore, the learning unit can analyze user emotion data and select and learn advertising images associated with specific emotions. For example, the learning unit can analyze user emotion data over time and identify patterns of emotion change. This allows the learning unit to select training data based on user emotions, enabling more accurate learning. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0075] The learning unit can analyze the background and color patterns of advertising images to identify elements that users find unpleasant. For example, the learning unit can use generative AI to analyze the background and color patterns of advertising images and identify elements that users find unpleasant. For example, the learning unit can use generative AI to take the background and color patterns of advertising images as input and output unpleasant elements. For example, the learning unit can analyze the impact that the background color of an advertising image has on the user, and the generative AI can identify unpleasant color patterns. The learning unit can also analyze the design elements of advertising images (e.g., fonts, layout), and the generative AI can identify unpleasant elements. Furthermore, the learning unit can analyze the dynamic elements of advertising images (e.g., animations, effects), and the generative AI can identify unpleasant elements. In this way, the learning unit can identify unpleasant elements by analyzing the background and color patterns of advertising images.

[0076] The learning unit can identify which ads were perceived as offensive by referring to a user's past ad click history. For example, the learning unit can use generative AI to refer to a user's past ad click history and identify which ads were perceived as offensive. For example, the learning unit can use generative AI as input to identify offensive ads. For example, the learning unit can collect ad images that users did not click on, and the generative AI can identify offensive elements. The learning unit can also collect ad images that users closed quickly, and the generative AI can identify offensive elements. Furthermore, the learning unit can collect ad images to which users gave negative feedback, and the generative AI can identify offensive elements. In this way, the learning unit can identify offensive ads by referring to past click history.

[0077] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit might use a generative AI to estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For instance, the learning unit might use a generative AI to input user emotion data and output the result of adjusting the learning frequency. For example, if the user expresses discomfort, the learning unit might increase the learning frequency to quickly identify the unpleasant elements. Conversely, if the user expresses positive emotions, the learning unit can decrease the learning frequency to conserve resources. Furthermore, the learning unit can analyze user emotion data in real time and dynamically adjust the learning frequency. This allows the learning unit to learn efficiently by adjusting the learning frequency based on user emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0078] The learning unit can analyze the text content of advertising images and identify words and phrases that users find offensive. For example, the learning unit can use a generative AI to analyze the text content of advertising images and identify words and phrases that users find offensive. For example, the learning unit can use a generative AI to take the text content of an advertising image as input and output offensive words and phrases. For example, the learning unit can analyze the catchphrase of an advertising image and have the generative AI identify offensive words and phrases. The learning unit can also analyze the description of an advertising image and have the generative AI identify offensive words and phrases. Furthermore, the learning unit can analyze the entire text element of an advertising image and have the generative AI identify offensive words and phrases. In this way, the learning unit can identify offensive words and phrases by analyzing the text content of advertising images.

[0079] The learning unit can learn different elements of unpleasantness for each device based on the user's device information. For example, the learning unit uses a generative AI to learn different elements of unpleasantness for each device based on the user's device information. For example, the learning unit takes the user's device information as input to the generative AI and outputs elements of unpleasantness. For example, the learning unit identifies elements of unpleasantness in advertising images for smartphone users, and the generative AI learns them. The learning unit can also identify elements of unpleasantness in advertising images for tablet users, and the generative AI learns them. Furthermore, the learning unit can identify elements of unpleasantness in advertising images for desktop users, and the generative AI learns them. As a result, the learning unit can generate advertising images with higher accuracy by learning different elements of unpleasantness for each device.

[0080] The checking unit can estimate the user's emotions and adjust the checking criteria based on the estimated emotions. For example, the checking unit can use generative AI to estimate the user's emotions and adjust the checking criteria based on the estimated emotions. For example, the checking unit can use generative AI to input user emotion data and output the result of adjusting the checking criteria. For example, if the user indicates discomfort, the checking unit can tighten the checking criteria and eliminate unpleasant advertising images. Conversely, if the user indicates positive emotions, the checking unit can loosen the checking criteria and allow the advertising images. Furthermore, the checking unit can analyze user emotion data in real time and dynamically adjust the checking criteria. This allows the checking unit to check advertising images more appropriately by adjusting the checking criteria based on user emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0081] The checking unit can analyze the movement and animation of advertising images and identify movements that users find unpleasant. For example, the checking unit can use a generative AI to analyze the movement and animation of advertising images and identify movements that users find unpleasant. For example, the checking unit can use a generative AI to take the movement and animation of advertising images as input and output unpleasant movements. For example, the checking unit can analyze the animation speed of advertising images and have the generative AI identify unpleasant movements. The checking unit can also analyze the dynamic effects of advertising images and have the generative AI identify unpleasant movements. Furthermore, the checking unit can analyze the transition effects of advertising images and have the generative AI identify unpleasant movements. In this way, the checking unit can identify unpleasant movements by analyzing the movement and animation of advertising images.

[0082] The checking unit can analyze the audio elements of an advertisement image and identify sounds that users find unpleasant. For example, the checking unit can use a generative AI to analyze the audio elements of an advertisement image and identify sounds that users find unpleasant. For example, the checking unit can use a generative AI that takes the audio elements of an advertisement image as input and output unpleasant sounds. For example, the checking unit can analyze the background music of an advertisement image and have the generative AI identify unpleasant sounds. The checking unit can also analyze the narration of an advertisement image and have the generative AI identify unpleasant sounds. Furthermore, the checking unit can analyze the sound effects of an advertisement image and have the generative AI identify unpleasant sounds. In this way, the checking unit can identify unpleasant sounds by analyzing the audio elements of an advertisement image.

[0083] The checking unit can estimate the user's emotions and adjust the order in which the check results are displayed based on the estimated emotions. For example, the checking unit can use generative AI to estimate the user's emotions and adjust the order in which the check results are displayed based on the estimated emotions. For example, the checking unit can use generative AI to take user emotion data as input and output the result of adjusting the display order. For example, if the user shows discomfort, the checking unit can respond quickly by displaying an unpleasant advertisement image first. Also, if the user shows positive emotions, the checking unit can prioritize other tasks by delaying the display of the check results. Furthermore, the checking unit can analyze the user's emotion data in real time and dynamically adjust the display order of the check results. This allows the checking unit to respond efficiently by adjusting the order in which the check results are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0084] The checking unit can determine the degree of unpleasantness of an advertisement image based on its display location. For example, the checking unit uses a generating AI to determine the degree of unpleasantness based on the display location of the advertisement image. For example, the checking unit uses a generating AI that takes the display location of the advertisement image as input and outputs the degree of unpleasantness. For example, the checking unit analyzes the degree of unpleasantness of an advertisement image displayed at the top of a webpage, and the generating AI makes a determination. The checking unit can also analyze the degree of unpleasantness of an advertisement image displayed in a sidebar, and the generating AI makes a determination. Furthermore, the checking unit can analyze the degree of unpleasantness of an advertisement image displayed in the footer, and the generating AI makes a determination. As a result, the checking unit can determine the degree of unpleasantness based on the display location of the advertisement image, enabling more appropriate checking of advertisement images.

[0085] The checking unit can evaluate the degree of deviation from the content by referring to the related content of the advertising image. For example, the checking unit can use a generating AI to refer to the related content of the advertising image and evaluate the degree of deviation from the content. For example, the checking unit can use a generating AI to take the advertising image and related content as input and output the degree of deviation. For example, the checking unit can analyze the content of an article related to the advertising image, and the generating AI can evaluate the degree of deviation. The checking unit can also analyze the content of a video related to the advertising image, and the generating AI can evaluate the degree of deviation. Furthermore, the checking unit can analyze product information related to the advertising image, and the generating AI can evaluate the degree of deviation. In this way, the checking unit can evaluate the degree of deviation from the content by referring to the related content of the advertising image.

[0086] The generation unit can estimate the user's emotions and adjust the method of generating alternative images based on the estimated user emotions. For example, the generation unit can use a generation AI to estimate the user's emotions and adjust the method of generating alternative images based on the estimated user emotions. For example, the generation unit can use the generation AI to take user emotion data as input and output the result of adjusting the generation method. For example, if the user expresses discomfort, the generation AI can generate an alternative image using milder colors and designs. Also, if the user expresses positive emotions, the generation AI can generate an alternative image that emphasizes the advertising message. Furthermore, the generation unit can analyze the user's emotion data in real time and dynamically adjust the method of generating alternative images using the generation AI. This allows the generation unit to generate more appropriate alternative images by adjusting the method of generating alternative images based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The generation unit can analyze the message of an advertisement and select the most appropriate colors and designs for that message. For example, the generation unit can use a generation AI to analyze the message of an advertisement and select the most appropriate colors and designs for that message. For example, the generation unit can use a generation AI to take the message of an advertisement as input and output the optimal colors and designs. For example, the generation unit can analyze the catchphrase of an advertisement and have the generation AI select the optimal colors and designs. The generation unit can also analyze the description of an advertisement and have the generation AI select the optimal colors and designs. Furthermore, the generation unit can analyze the overall theme of an advertisement and have the generation AI select the optimal colors and designs. As a result, the generation unit can generate effective alternative images by selecting the most appropriate colors and designs for the message of the advertisement.

[0088] The generation unit can generate customized alternative images for different audiences based on the target audience of the advertisement. For example, the generation unit uses a generation AI to generate customized alternative images for different audiences based on the target audience of the advertisement. For example, the generation unit's generation AI takes target audience data as input and outputs a customized alternative image. For example, the generation unit's generation AI can generate an advertisement image for young people. The generation unit can also use its generation AI to generate an advertisement image for middle-aged and older people. Furthermore, the generation unit's generation AI can generate an advertisement image for audiences with specific interests. As a result, the generation unit can display advertisements more effectively by generating customized alternative images based on the target audience.

[0089] The generation unit can estimate the user's emotions and adjust the display method of alternative images based on the estimated user emotions. For example, the generation unit can use a generation AI to estimate the user's emotions and adjust the display method of alternative images based on the estimated user emotions. For example, the generation unit can use the generation AI to take user emotion data as input and output the result of the display method adjustment. For example, if the user shows discomfort, the generation AI can display the alternative image less prominently. Also, if the user shows positive emotions, the generation AI can display the alternative image more prominently. Furthermore, the generation unit can analyze the user's emotion data in real time and the generation AI can dynamically adjust the display method of alternative images. This allows the generation unit to display more appropriate advertisements by adjusting the display method of alternative images based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The generation unit can generate alternative images that effectively convey a message in a short time, based on the ad's display time. For example, the generation unit uses a generation AI to generate alternative images that effectively convey a message in a short time, based on the ad's display time. For example, the generation unit's generation AI takes the ad's display time as input and outputs an effective alternative image in a short time. For example, the generation unit's generation AI generates a visually impactful alternative image in a short time. The generation unit can also have its generation AI generate an alternative image that gets straight to the point in a short time. Furthermore, the generation unit's generation AI can also generate an alternative image that grabs the user's attention in a short time. In this way, the generation unit can grab the user's attention by generating alternative images that effectively convey a message in a short time.

[0091] The generation unit can generate highly relevant alternative images by referencing the products and services related to the advertisement. For example, the generation unit uses a generation AI to reference the products and services related to the advertisement and generate highly relevant alternative images. For example, the generation unit's generation AI takes data on the products and services related to the advertisement as input and outputs highly relevant alternative images. For example, the generation unit analyzes the products related to the advertisement, and the generation AI generates highly relevant alternative images. The generation unit can also analyze the services related to the advertisement, and the generation AI generates highly relevant alternative images. Furthermore, the generation unit can analyze the content related to the advertisement, and the generation AI generates highly relevant alternative images. In this way, the generation unit can generate highly relevant alternative images by referencing the products and services related to the advertisement.

[0092] The replacement unit can estimate the user's emotions and adjust the replacement timing based on the estimated emotions. For example, the replacement unit can use generative AI to estimate the user's emotions and adjust the replacement timing based on the estimated emotions. For example, the replacement unit takes user emotion data as input and outputs the result of adjusting the replacement timing. For example, if the user shows discomfort, the replacement unit will immediately replace it with an alternative image. The replacement unit can also extend the display time of the ad before replacing it if the user shows positive emotions. Furthermore, the replacement unit can analyze user emotion data in real time and dynamically adjust the replacement timing. This allows the replacement unit to replace ad images at a more appropriate time by adjusting the replacement timing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The replacement unit can save the original data of the ad image during replacement, allowing for later reference. For example, the replacement unit can use a generation AI to save the original data of the ad image during replacement, allowing for later reference. For instance, the replacement unit uses a generation AI as input and outputs the saved result. Alternatively, the replacement unit can save the ad image before replacement to a database for later analysis. Furthermore, the replacement unit can log the ad image before replacement for troubleshooting. Additionally, the replacement unit can save the ad image before replacement as a backup, allowing for restoration as needed. This enables the replacement unit to save the original data of the ad image, making it available for later reference and analysis.

[0094] The replacement unit can analyze ad click-through rates and engagement data to select the optimal replacement method. For example, the replacement unit can use a generative AI to analyze ad click-through rates and engagement data and select the optimal replacement method. For example, the replacement unit can use a generative AI to take ad click-through rates and engagement data as input and output the optimal replacement method. For example, the replacement unit can analyze ad click-through rates and the generative AI can select the optimal replacement method. The replacement unit can also analyze ad engagement data and the generative AI can select the optimal replacement method. Furthermore, the replacement unit can analyze ad conversion rates and the generative AI can select the optimal replacement method. In this way, the replacement unit can select the optimal replacement method by analyzing ad click-through rates and engagement data.

[0095] The replacement unit can estimate the user's emotions and determine the replacement priority based on the estimated emotions. For example, the replacement unit can use generative AI to estimate the user's emotions and determine the replacement priority based on the estimated emotions. For example, the replacement unit takes user emotion data as input and outputs the result of determining the replacement priority. For example, if the user indicates discomfort, the replacement unit will prioritize replacing it with an alternative image. The replacement unit can also prioritize other tasks before replacing if the user indicates positive emotions. Furthermore, the replacement unit can analyze user emotion data in real time and dynamically determine the replacement priority. This allows the replacement unit to replace advertising images in a more appropriate order by determining the replacement priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The replacement unit can select the optimal replacement method based on the ad's display location. For example, the replacement unit uses a generating AI to select the optimal replacement method based on the ad's display location. For example, the replacement unit takes the ad's display location as input and outputs the optimal replacement method. For example, when replacing an ad image displayed at the top of a webpage, the generating AI selects the optimal method. The replacement unit can also use the generating AI to select the optimal method when replacing an ad image displayed in the sidebar. Furthermore, the replacement unit can use the generating AI to select the optimal method when replacing an ad image displayed in the footer. As a result, the replacement unit can display ads more effectively by selecting the optimal replacement method based on the ad's display location.

[0097] The replacement unit can refer to the relevant content of the advertisement and perform replacements while maintaining consistency with the content. For example, the replacement unit can use a generating AI to refer to the relevant content of the advertisement and perform replacements while maintaining consistency with the content. For example, the replacement unit can take the advertisement image and related content as input and output a result in which the generating AI performs replacements while maintaining consistency. For example, the replacement unit can analyze the content of an article related to the advertisement image, and the generating AI will perform replacements while maintaining consistency. The replacement unit can also analyze the content of a video related to the advertisement image, and the generating AI will perform replacements while maintaining consistency. Furthermore, the replacement unit can analyze product information related to the advertisement image, and the generating AI will perform replacements while maintaining consistency. In this way, the replacement unit can refer to the relevant content of the advertisement and perform replacements while maintaining consistency with the content.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The ad image replacement system can estimate a user's emotions and adjust the frequency of ad display based on those emotions. For example, if a user expresses discomfort, the ad display frequency can be reduced. Conversely, if a user expresses positive emotions, the ad display frequency can be increased. Furthermore, the system can analyze user emotion data in real time and dynamically adjust the ad display frequency. This allows for more appropriate ad display by adjusting the ad display frequency based on user emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0100] The ad image replacement system can identify which ads were perceived as offensive by referencing a user's past browsing history. For example, it can collect ad images that a user has viewed in the past, and the generating AI can identify the offensive elements. It can also collect ad images that a user has viewed for extended periods, and the generating AI can identify the positive elements. Furthermore, it can collect ad images that users have given negative feedback on, and the generating AI can identify the offensive elements. In this way, offensive ads can be identified by referring to past browsing history.

[0101] The ad image replacement system can estimate a user's emotions and adjust the ad's display position based on those emotions. For example, if a user expresses discomfort, the ad can be displayed in a less prominent position. Conversely, if a user expresses positive emotions, the ad can be displayed in a more prominent position. Furthermore, the system can analyze user emotion data in real time and dynamically adjust the ad's display position. This allows for more appropriate ad display by adjusting the ad's position based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0102] The ad image replacement system can generate alternative images that effectively convey a message in a short amount of time, based on the ad's display time. For example, it can use a generation AI to generate effective alternative images in a short amount of time based on the ad's display time. For instance, the generation AI can generate visually impactful alternative images in a short amount of time. It can also generate alternative images that capture the key points in a short amount of time. Furthermore, the generation AI can generate alternative images that grab the user's attention in a short amount of time. In this way, by generating alternative images that effectively convey a message in a short amount of time, it is possible to attract the user's attention.

[0103] The ad image replacement system can estimate a user's emotions and adjust the order in which ads are displayed based on those emotions. For example, if a user expresses discomfort, the system can quickly respond by displaying an unpleasant ad image first. Conversely, if a user expresses positive emotions, the system can prioritize other tasks by delaying the display of the ad. Furthermore, it can analyze user emotion data in real time and dynamically adjust the order in which ads are displayed. This enables efficient responses by adjusting the order in which ads are displayed based on user emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] An advertising image replacement system can generate highly relevant alternative images by referencing the products and services related to the advertisement. For example, it can use a generation AI to reference the products and services related to the advertisement and generate highly relevant alternative images. For instance, it can analyze the products related to the advertisement, and the generation AI can generate highly relevant alternative images. It can also analyze the services related to the advertisement, and the generation AI can generate highly relevant alternative images. Furthermore, it can analyze the content related to the advertisement, and the generation AI can generate highly relevant alternative images. In this way, highly relevant alternative images can be generated by referencing the products and services related to the advertisement.

[0105] The ad image replacement system can estimate a user's emotions and adjust how ads are displayed based on those emotions. For example, if a user expresses discomfort, the ad can be displayed less prominently. Conversely, if a user expresses positive emotions, the ad can be displayed more prominently. Furthermore, the system can analyze user emotion data in real time and dynamically adjust how ads are displayed. This allows for more appropriate ad display by adjusting how ads are displayed based on user emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0106] An ad image replacement system can generate customized alternative images for different audiences based on the target audience of an ad. For example, a generation AI can be used to generate customized alternative images for different audiences based on the target audience of an ad. For instance, the generation AI can generate ad images for younger demographics. It can also generate ad images for middle-aged and older demographics. Furthermore, the generation AI can generate ad images for audiences with specific interests. This allows for more effective ad display by generating customized alternative images based on the target audience.

[0107] The ad image replacement system can estimate a user's emotions and adjust the timing of ad display based on those emotions. For example, if a user expresses discomfort, the ad display can be delayed. Conversely, if a user expresses positive emotions, the ad display can be brought forward. Furthermore, it can analyze user emotion data in real time and dynamically adjust the ad display timing. This allows for more appropriate ad display by adjusting the ad display timing based on user emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The ad image replacement system can analyze ad click-through rates and engagement data to select the optimal replacement method. For example, it can use a generation AI to analyze ad click-through rates and engagement data and select the optimal replacement method. For instance, it can analyze ad click-through rates and have the generation AI select the optimal replacement method. It can also analyze ad engagement data and have the generation AI select the optimal replacement method. Furthermore, it can analyze ad conversion rates and have the generation AI select the optimal replacement method. In this way, by analyzing ad click-through rates and engagement data, the optimal replacement method can be selected.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The learning unit learns what users find offensive in advertisements. For example, it uses a generative AI to analyze past advertisement image data and extract features that users find offensive. The generative AI takes past advertisement image data as input and outputs features that users find offensive. Step 2: The checking unit checks the advertisement image based on the features learned by the learning unit. For example, it uses a generative AI to analyze the advertisement image and determine whether it is likely to be offensive to the user. The generative AI takes the advertisement image as input and outputs whether it is likely to be offensive to the user. Step 3: The generation unit generates alternative images to replace the advertising images that the checking unit has determined to be offensive. For example, it uses a generation AI to generate a milder alternative image that reflects the message the advertisement wants to convey. The generation AI takes the advertisement's message as input and outputs a milder alternative image. Step 4: The replacement unit replaces the advertisement image with the replacement image generated by the generation unit. For example, it replaces the original advertisement image with a replacement image generated using the generation AI. It takes the replacement image generated by the generation AI as input and outputs the process of replacing the advertisement image.

[0111] 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.

[0112] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements, including the learning unit, checking unit, generation unit, and replacement unit described above, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the learning unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The checking unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The replacement unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] 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.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0118] 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.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0120] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] 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.

[0122] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] 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.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements, including the learning unit, checking unit, generation unit, and replacement unit described above, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The checking unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The replacement unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] 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.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0134] 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.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0136] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] 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.

[0138] 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.

[0139] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements, including the learning unit, checking unit, generation unit, and replacement unit described above, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The checking unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The replacement unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0150] 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.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0152] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] 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.

[0154] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] 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.

[0156] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] 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.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements, including the learning unit, checking unit, generation unit, and replacement unit described above, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The checking unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The replacement unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0164] 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.

[0165] Figure 9 shows the 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.

[0166] 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.

[0167] 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.

[0168] 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, and motorcycles, 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 based, for example, 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.

[0169] 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."

[0170] 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.

[0171] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] 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 other things 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.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) A learning unit that learns which advertising images users find unpleasant, A checking unit checks the advertisement image based on the features learned by the learning unit, A generation unit generates alternative images to replace advertising images that have been determined to be offensive by the aforementioned checking unit, The system includes a replacement unit that replaces the alternative image generated by the generation unit with the advertisement image. A system characterized by the following features. (Note 2) The aforementioned learning unit, By analyzing past advertising image data, we extract features that users find unpleasant. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned checking unit is The system analyzes advertising images to determine whether they might be offensive to users. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Generate mild alternative images that reflect the message the advertisement wants to convey. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned replacement part is Replace the original ad image with the generated alternative image. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned checking unit is Check advertising images in real time. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, By analyzing the background and color patterns of advertising images, we identify elements that users find unpleasant. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, By referring to the user's past ad click history, we can identify which ads were perceived as offensive. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, We analyze the text content of ad images to identify words and phrases that users may find offensive. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, Based on the user's device information, it learns the elements that cause discomfort, which differ from device to device. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned checking unit is The system estimates the user's emotions and adjusts the check criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned checking unit is By analyzing the movement and animation of advertising images, we identify movements that users find unpleasant. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned checking unit is We analyze the audio elements of ad images to identify sounds that users find unpleasant. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned checking unit is It estimates the user's emotions and adjusts the order in which the check results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned checking unit is The degree of unpleasantness is determined based on the placement of the advertisement image. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned checking unit is Refer to related content for the ad image and evaluate the degree of discrepancy with the content. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts the method of generating alternative images based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is Analyze the advertising message and select the most appropriate colors and design for that message. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is Based on the target audience of the ad, we generate alternative images customized for different audiences. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is It estimates the user's emotions and adjusts how alternative images are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is Based on the ad's display time, generate alternative images that effectively convey the message in a short amount of time. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is By referencing related products and services in the advertisement, it generates highly relevant alternative images. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned replacement part is It estimates the user's emotions and adjusts the timing of replacements based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned replacement part is During replacement, the original data of the ad image is saved so that it can be referenced later. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned replacement part is Analyze ad click-through rates and engagement data to select the optimal replacement method. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned replacement part is The system estimates the user's emotions and determines replacement priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned replacement part is The optimal replacement method is selected based on the ad's display location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned replacement part is Refer to the ad's related content and replace it to maintain consistency with the content. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A learning unit that learns which advertising images users find unpleasant, A checking unit checks the advertisement image based on the features learned by the learning unit, A generation unit generates alternative images to replace advertising images that have been determined to be offensive by the aforementioned checking unit, The system includes a replacement unit that replaces the alternative image generated by the generation unit with the advertisement image. A system characterized by the following features.

2. The aforementioned learning unit, By analyzing past advertising image data, we extract features that users find unpleasant. The system according to feature 1.

3. The aforementioned checking unit is The system analyzes advertising images to determine whether they might be offensive to users. The system according to feature 1.

4. The generating unit is Generate mild alternative images that reflect the message the advertisement wants to convey. The system according to feature 1.

5. The aforementioned replacement part is Replace the original ad image with the generated alternative image. The system according to feature 1.

6. The aforementioned checking unit is Check advertising images in real time. The system according to feature 1.

7. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system according to feature 1.

8. The aforementioned learning unit, By analyzing the background and color patterns of advertising images, we identify elements that users find unpleasant. The system according to feature 1.

Images