System

Abstract

An object of the system according to the embodiment is to automatically detect and eliminate malvertising.SOLUTION: A system includes an advertisement text analysis unit, an advertisement image analysis unit, a display context analysis unit, and a learning unit. The advertisement text analysis unit analyzes the text of the advertisement. The advertisement image analysis unit analyzes the image of the advertisement. The display context analyzer analyzes a context in which the advertisement is displayed. The learning unit periodically learns new data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies are inadequate in detecting and eliminating fraudulent advertising in the Internet advertising market, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically detect and eliminate fraudulent advertising. [Means for solving the problem]

[0006] The system according to the embodiment includes an advertisement text analysis unit, an advertisement image analysis unit, a display context analysis unit, and a learning unit. The advertisement text analysis unit analyzes the text of an advertisement. The advertisement image analysis unit analyzes the image of the advertisement. The display context analysis unit analyzes the context in which the advertisement is displayed. The learning unit periodically learns new data. [Effects of the Invention]

[0007] The system according to the embodiment can automatically detect and eliminate fraudulent advertising. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A fraudulent advertising detection system according to an embodiment of the present invention is a system that automatically detects and eliminates fraudulent advertising in the internet advertising market by utilizing generative AI. As a result, the fraudulent advertising detection system can effectively detect and eliminate fraudulent advertising in the internet advertising market.

[0029] A fraudulent advertising detection system according to an embodiment includes an advertising text analysis unit, an advertising image analysis unit, a display context analysis unit, and a learning unit. The advertising text analysis unit analyzes the text of an advertisement. For example, the generation AI analyzes the context of the advertising text to detect deceptive content, misleading expressions, and unauthorized use of celebrities. The generation AI can also use natural language processing technology to understand the meaning and intent of the advertising text and identify potential fraudulent activity. The generation AI can also evaluate the tone and nuance of the text to detect advertisements with fraudulent intent. The advertising image analysis unit analyzes the image of the advertisement. For example, the generation AI can analyze the characteristics of the advertising image to detect advertisements that use fake logos or images of celebrities without permission. The generation AI can also use image recognition technology to analyze the content of the advertising image and identify fraudulent elements. The generation AI can also analyze image metadata to identify the source of fraudulent images. The display context analysis unit analyzes the context in which the advertisement is displayed. For example, the generation AI can analyze the content of the web page or application in which the advertisement is displayed to detect fraudulent advertisements. The generation AI can also analyze themes and topics of display contexts to prevent the display of fraudulent advertisements. Furthermore, the generation AI can perform individually optimized fraudulent advertisement detection by taking into account a user's past browsing history and behavioral patterns. The learning unit periodically learns new data. For example, the generation AI can learn new fraudulent advertisement patterns and techniques to improve detection accuracy. The generation AI can also perform learning by taking into account not only past fraudulent advertisement data but also future trend prediction data. Furthermore, the generation AI can learn fraudulent advertisement data from different industries and regions to improve detection accuracy from a global perspective. This allows the fraudulent advertisement detection system according to the embodiment to automatically detect and remove fraudulent advertisements. For example, the generation AI analyzes advertisement text, images, and display contexts in real time to detect fraudulent advertisements. The generation AI also periodically learns to learn new fraudulent advertisement patterns and techniques to improve detection accuracy. This is expected to create an environment in which legitimate advertisements are effectively displayed, benefiting advertisers and ad distribution platforms.

[0030] The ad text analysis unit can detect deceptive content, misleading language, and unauthorized use of celebrities. For example, the ad text analysis unit uses a generation AI to analyze the context of ad text and detect deceptive content, misleading language, and unauthorized use of celebrities. For example, the generation AI uses natural language processing technology to understand the meaning and intent of ad text and identify potential fraudulent activity. The generation AI also evaluates the tone and nuance of the text to detect ads with deceptive intent. This improves the accuracy of detecting fraudulent ads by detecting deceptive content, misleading language, and unauthorized use of celebrities.

[0031] The advertising image analysis unit can detect advertisements that use fake logos or celebrity images without permission. For example, the generation AI analyzes the characteristics of advertising images to detect advertisements that use fake logos or celebrity images without permission. For example, the generation AI uses image recognition technology to analyze the content of advertising images and identify fraudulent elements. The generation AI also analyzes image metadata to identify the source of fraudulent images. This improves the accuracy of detecting fraudulent advertisements by detecting advertisements that use fake logos or celebrity images without permission.

[0032] The display context analysis unit can analyze the content of advertisements displayed on specific websites or applications to detect fraudulent advertisements. For example, the display context analysis unit uses a generation AI to analyze the content of web pages or applications on which advertisements are displayed to detect fraudulent advertisements. For example, the generation AI analyzes themes and topics of the display context to prevent the display of fraudulent advertisements. The generation AI also takes into account a user's past browsing history and behavioral patterns to perform individually optimized fraudulent advertisement detection. This improves the accuracy of fraudulent advertisement detection by analyzing the content of advertisements displayed on specific websites or applications to detect fraudulent advertisements.

[0033] The learning unit periodically learns new data and can master new patterns and techniques of fraudulent advertising. For example, the generation AI periodically learns new data and masters new patterns and techniques of fraudulent advertising. For example, the generation AI performs learning by taking into account not only past fraudulent advertising data but also future trend prediction data. The generation AI also learns fraudulent advertising data from different industries and regions, improving detection accuracy from a global perspective. This allows the system to periodically learn new data and master new patterns and techniques of fraudulent advertising, thereby improving detection accuracy.

[0034] The ad text analysis unit can perform individually optimized fraudulent ad detection by taking into account the user's past search history and behavioral patterns. In the ad text analysis unit, for example, the generation AI refers to the user's past search history and performs individually optimized fraudulent ad detection. For example, the generation AI identifies fraudulent ad detection related to keywords the user has previously searched for. The generation AI also analyzes the user's behavioral patterns and performs individually optimized fraudulent ad detection. For example, the generation AI detects fraudulent ad detection related to websites the user frequently visits. Furthermore, the generation AI performs individually optimized fraudulent ad detection by taking into account the user's past click history. For example, the generation AI identifies fraudulent ad detection related to ads the user has previously clicked. This improves detection accuracy by performing individually optimized fraudulent ad detection by taking into account the user's past search history and behavioral patterns.

[0035] The ad text analysis unit can link the analysis results of ad text with other advertising platforms and social media, enabling widespread detection of fraudulent ads. For example, the generation AI can link the analysis results of ad text with other advertising platforms, enabling widespread detection of fraudulent ads. For example, the generation AI can share data among multiple advertising networks to simultaneously detect fraudulent ads. The generation AI can also link the analysis results of ad text with social media, enabling widespread detection of fraudulent ads. For example, the generation AI can detect fraudulent ads spreading on social media and respond quickly. The generation AI can also link the analysis results of ad text with other advertising platforms and social media, enabling widespread detection of fraudulent ads. For example, the generation AI can integrate data across different platforms to build a comprehensive fraudulent ad detection system. This allows the analysis results of ad text to be linked with other advertising platforms and social media, enabling widespread detection of fraudulent ads, improving detection accuracy.

[0036] The ad text analysis unit uses generation AI to support multiple languages ​​for ad text and can detect fraudulent ads in different languages. The ad text analysis unit, for example, uses generation AI to support multiple languages ​​for ad text and can detect fraudulent ads in different languages. For example, the generation AI identifies fraudulent ads in multiple languages, such as English, French, and Chinese. The generation AI can also identify fraudulent ads by taking into account nuances and differences in expression between languages. Furthermore, the generation AI can identify misleading expressions and false claims in different languages. As a result, detection accuracy is improved by using generation AI to support multiple languages ​​for ad text and can detect fraudulent ads in different languages.

[0037] The advertising image analysis unit can analyze the metadata of advertising images and identify the source of fraudulent images. For example, the generation AI analyzes the metadata of advertising images and identifies the source of fraudulent images. For example, the generation AI detects counterfeit images based on the date and time the image was created and the creator information. The generation AI can also identify counterfeit images based on the image's editing history and information about the software used. Furthermore, the generation AI can identify the source of counterfeit images based on the image's geotag information. This improves detection accuracy by analyzing the metadata of advertising images and identifying the source of fraudulent images.

[0038] The advertising image analysis unit can detect subtle features within an image and identify counterfeit images. For example, the generative AI can detect subtle features within an image and identify counterfeit images. For example, the generative AI can identify unnatural pixel variations and color inconsistencies. The generative AI can also identify unnatural variations in the edges and texture of an image. Furthermore, the generative AI can identify unnatural patterns of compression artifacts and noise in an image. This improves detection accuracy by detecting subtle features within an image and identifying counterfeit images.

[0039] The advertising image analysis unit can link the analysis results of advertising images with other image recognition systems to achieve widespread detection of fraudulent advertising. For example, the advertising image analysis unit can link the analysis results of advertising images with other image recognition systems to achieve widespread detection of fraudulent advertising. For example, the generation AI can share data between multiple image recognition systems to simultaneously detect fraudulent advertising. The generation AI can also integrate data between different platforms to build a comprehensive fraudulent advertising detection system. Furthermore, the generation AI can share data between social media and advertising networks to quickly detect fraudulent advertising. This allows the analysis results of advertising images to be linked with other image recognition systems to achieve widespread detection of fraudulent advertising, improving detection accuracy.

[0040] The advertising image analysis unit uses generation AI to perform video analysis of advertising images and detect fraudulent elements within video ads. For example, the advertising image analysis unit uses generation AI to perform video analysis of advertising images and detect fraudulent elements within video ads. For example, generation AI can identify fake logos or unauthorized use of celebrities within videos. Generation AI can also identify unnatural editing or compositing within videos. Furthermore, generation AI can identify misleading expressions or false claims within videos. This improves detection accuracy by using generation AI to perform video analysis of advertising images and detect fraudulent elements within video ads.

[0041] The display context analysis unit can analyze the overall theme or topic of a webpage on which an advertisement is displayed and prevent the display of fraudulent advertisements. For example, the generation AI can analyze the overall theme or topic of a webpage on which an advertisement is displayed and prevent the display of fraudulent advertisements. For example, the generation AI can detect advertisements displayed on webpages containing fraudulent content. The generation AI can also identify advertisements that do not match the content of the webpage. Furthermore, the generation AI can detect fraudulent advertisements related to the topic of the webpage. This improves detection accuracy by analyzing the overall theme or topic of a webpage on which an advertisement is displayed and preventing the display of fraudulent advertisements.

[0042] The display context analysis unit can perform individually optimized fraudulent ad detection by taking into account the user's past browsing history and behavioral patterns in the display context of the ad. In the display context analysis unit, for example, the generation AI refers to the user's past browsing history and performs individually optimized fraudulent ad detection. For example, the generation AI identifies fraudulent ads related to websites the user has previously visited. The generation AI also analyzes the user's behavioral patterns and performs individually optimized fraudulent ad detection. For example, the generation AI detects fraudulent ads related to content the user frequently accesses. Furthermore, the generation AI performs individually optimized fraudulent ad detection by taking into account the user's past click history. For example, the generation AI identifies fraudulent ads related to ads the user has previously clicked. This improves detection accuracy by performing individually optimized fraudulent ad detection by taking into account the user's past browsing history and behavioral patterns in the display context of the ad.

[0043] The display context analysis unit can link the results of ad display context analysis with other ad distribution platforms to achieve widespread detection of fraudulent ads. For example, the display context analysis unit allows the generation AI to link the results of ad display context analysis with other ad distribution platforms to achieve widespread detection of fraudulent ads. For example, the generation AI can share data between multiple ad networks to simultaneously detect fraudulent ads. The generation AI can also integrate data between different platforms to build a comprehensive fraudulent ad detection system. Furthermore, the generation AI can share data between social media and ad networks to quickly detect fraudulent ads. This allows the results of ad display context analysis to be linked with other ad distribution platforms to achieve widespread detection of fraudulent ads, improving detection accuracy.

[0044] The display context analysis unit uses generation AI to support multiple languages ​​for the display context of an ad and can detect fraudulent ads in different languages. The display context analysis unit, for example, uses generation AI to support multiple languages ​​for the display context of an ad and can detect fraudulent ads in different languages. For example, the generation AI identifies fraudulent ads in multiple languages, such as English, French, and Chinese. The generation AI can also identify fraudulent ads by taking into account nuances and differences in expression between languages. Furthermore, the generation AI can identify misleading expressions and false claims in different languages. This improves detection accuracy by using generation AI to support multiple languages ​​for the display context of an ad and can detect fraudulent ads in different languages.

[0045] When learning new fraudulent advertising patterns, the learning unit can take into account not only past fraudulent advertising data but also future trend prediction data. For example, when the generation AI learns new fraudulent advertising patterns, the learning unit takes into account not only past fraudulent advertising data but also future trend prediction data. For example, the generation AI learns fraud techniques that are predicted for the future. The generation AI can also learn fraud techniques based on new technologies and market trends. Furthermore, the generation AI can learn fraud techniques based on predicted future changes in consumer behavior. This improves detection accuracy by taking into account not only past fraudulent advertising data but also future trend prediction data when learning new fraudulent advertising patterns.

[0046] The learning unit can improve detection accuracy from a global perspective by including fraudulent advertising data from different industries and regions in the learning dataset. For example, the learning unit can improve detection accuracy from a global perspective by including fraudulent advertising data from different industries and regions in the dataset that the generation AI learns from. For example, the generation AI learns about fraudulent advertising in different countries and regions. The generation AI can also learn fraud techniques in different industries. Furthermore, the generation AI can learn fraud techniques based on different cultures and market environments. This improves detection accuracy by including fraudulent advertising data from different industries and regions in the learning dataset and improving detection accuracy from a global perspective.

[0047] The learning unit can improve detection accuracy by sharing learning results with other AI systems and mutually complementing learning data. The learning unit, for example, improves detection accuracy by having the generation AI share learning results with other AI systems and mutually complementing learning data. For example, the generation AI can share data between different AI systems to improve the detection accuracy of fraudulent advertisements. The generation AI can also share algorithms between different AI systems to improve the detection accuracy of fraudulent advertisements. Furthermore, the generation AI can also share models between different AI systems to improve the detection accuracy of fraudulent advertisements. This allows learning results to be shared with other AI systems and mutually complementing learning data, improving detection accuracy.

[0048] The learning unit can improve multimedia-compatible detection accuracy by including fraudulent advertising data of different media formats in the learning dataset. The learning unit, for example, includes fraudulent advertising data of different media formats in the dataset that the generation AI learns from. For example, the generation AI learns from data on audio ads and video ads to improve multimedia-compatible detection accuracy. The generation AI can also learn from data on image ads and text ads to improve multimedia-compatible detection accuracy. Furthermore, the generation AI can also learn from data on interactive ads and banner ads to improve multimedia-compatible detection accuracy. In this way, by including fraudulent advertising data of different media formats in the learning dataset and improving multimedia-compatible detection accuracy, detection accuracy is improved.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The fraudulent ad detection system can also be equipped with a function to adjust the frequency of ad display. For example, it can limit the frequency of ad display to prevent a particular ad from being displayed multiple times in a short period of time. Also, by reducing the frequency of displaying ads that a user has previously clicked, it is possible to maintain the effectiveness of the ads while reducing user annoyance. Furthermore, adjusting the frequency of ad display can also enable advertisers to realize effective advertising campaigns.

[0051] The fraudulent ad detection system can also be equipped with a function to optimize the timing of ad display. For example, the effectiveness of ads can be maximized by displaying ads at times when users are most likely to respond to ads. It can also analyze users' past behavioral patterns and predict the optimal display timing. Furthermore, the effectiveness of ads can be further increased by adjusting the timing of ad display to match specific events or seasons.

[0052] The fraudulent ad detection system can also be equipped with a function to optimize the display location of ads. For example, it can maximize the effectiveness of ads by displaying them in specific locations on web pages or applications where users are most likely to respond to ads. It can also analyze users' past behavioral patterns and predict the optimal display location. Furthermore, it can further increase the effectiveness of ads by displaying ads related to specific content or themes.

[0053] The fraudulent ad detection system can also be equipped with a function to optimize the creative elements of ads. For example, it can select the most effective ad creative based on past user response data. It can also create ads that are more likely to attract users' attention by adjusting elements such as ad color, font, and layout. Furthermore, it can regularly update the creative elements of ads to always provide fresh ads, thereby maintaining the effectiveness of ads.

[0054] The fraudulent ad detection system can also link ad display context with other ad distribution platforms to achieve widespread fraudulent ad detection. For example, Generation AI can share data between multiple ad networks to simultaneously detect fraudulent ads. Generation AI can also integrate data between different platforms to build a comprehensive fraudulent ad detection system. Furthermore, data can be shared between social media and ad networks to quickly detect fraudulent ads. This allows ad display context to be linked with other ad distribution platforms to achieve widespread fraudulent ad detection, improving detection accuracy.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The ad text analysis unit analyzes the ad text. For example, the generation AI analyzes the context of the ad text to detect deceptive content, misleading statements, and unauthorized use of celebrities. The generation AI can also use natural language processing techniques to understand the meaning and intent of the ad text and identify potential fraudulent activity. Furthermore, the generation AI can evaluate the tone and nuance of the text to detect ads with deceptive intent. Step 2: The advertising image analysis unit analyzes the advertising image. For example, the generation AI analyzes the characteristics of the advertising image and detects advertisements that use fake logos or images of celebrities without permission. The generation AI can also use image recognition technology to analyze the content of the advertising image and identify fraudulent elements. Furthermore, the generation AI can analyze the image metadata and identify the source of the fraudulent image. Step 3: The display context analysis unit analyzes the context in which the ad is displayed. For example, the generation AI analyzes the content of the web page or application in which the ad is displayed to detect fraudulent ads. The generation AI can also analyze the themes and topics of the display context to prevent the display of fraudulent ads. Furthermore, the generation AI can take into account the user's past browsing history and behavioral patterns to perform individually optimized fraudulent ad detection. Step 4: The learning unit periodically learns new data. For example, the generation AI learns new fraudulent ad patterns and techniques to improve detection accuracy. The generation AI can also learn by taking into account not only past fraudulent ad data, but also future trend prediction data. Furthermore, the generation AI can learn from fraudulent ad data from different industries and regions to improve detection accuracy from a global perspective.

[0057] (Example 2) A fraudulent advertising detection system according to an embodiment of the present invention is a system that automatically detects and eliminates fraudulent advertising in the internet advertising market by utilizing generative AI. As a result, the fraudulent advertising detection system can effectively detect and eliminate fraudulent advertising in the internet advertising market.

[0058] A fraudulent advertising detection system according to an embodiment includes an advertising text analysis unit, an advertising image analysis unit, a display context analysis unit, and a learning unit. The advertising text analysis unit analyzes the text of an advertisement. For example, the generation AI analyzes the context of the advertising text to detect deceptive content, misleading expressions, and unauthorized use of celebrities. The generation AI can also use natural language processing technology to understand the meaning and intent of the advertising text and identify potential fraudulent activity. The generation AI can also evaluate the tone and nuance of the text to detect advertisements with fraudulent intent. The advertising image analysis unit analyzes the image of the advertisement. For example, the generation AI can analyze the characteristics of the advertising image to detect advertisements that use fake logos or images of celebrities without permission. The generation AI can also use image recognition technology to analyze the content of the advertising image and identify fraudulent elements. The generation AI can also analyze image metadata to identify the source of fraudulent images. The display context analysis unit analyzes the context in which the advertisement is displayed. For example, the generation AI can analyze the content of the web page or application in which the advertisement is displayed to detect fraudulent advertisements. The generation AI can also analyze themes and topics of display contexts to prevent the display of fraudulent advertisements. Furthermore, the generation AI can perform individually optimized fraudulent advertisement detection by taking into account a user's past browsing history and behavioral patterns. The learning unit periodically learns new data. For example, the generation AI can learn new fraudulent advertisement patterns and techniques to improve detection accuracy. The generation AI can also perform learning by taking into account not only past fraudulent advertisement data but also future trend prediction data. Furthermore, the generation AI can learn fraudulent advertisement data from different industries and regions to improve detection accuracy from a global perspective. This allows the fraudulent advertisement detection system according to the embodiment to automatically detect and remove fraudulent advertisements. For example, the generation AI analyzes advertisement text, images, and display contexts in real time to detect fraudulent advertisements. The generation AI also periodically learns to learn new fraudulent advertisement patterns and techniques to improve detection accuracy. This is expected to create an environment in which legitimate advertisements are effectively displayed, benefiting advertisers and ad distribution platforms.

[0059] The ad text analysis unit can detect deceptive content, misleading language, and unauthorized use of celebrities. For example, the ad text analysis unit uses a generation AI to analyze the context of ad text and detect deceptive content, misleading language, and unauthorized use of celebrities. For example, the generation AI uses natural language processing technology to understand the meaning and intent of ad text and identify potential fraudulent activity. The generation AI also evaluates the tone and nuance of the text to detect ads with deceptive intent. This improves the accuracy of detecting fraudulent ads by detecting deceptive content, misleading language, and unauthorized use of celebrities.

[0060] The advertising image analysis unit can detect advertisements that use fake logos or celebrity images without permission. For example, the generation AI analyzes the characteristics of advertising images to detect advertisements that use fake logos or celebrity images without permission. For example, the generation AI uses image recognition technology to analyze the content of advertising images and identify fraudulent elements. The generation AI also analyzes image metadata to identify the source of fraudulent images. This improves the accuracy of detecting fraudulent advertisements by detecting advertisements that use fake logos or celebrity images without permission.

[0061] The display context analysis unit can analyze the content of advertisements displayed on specific websites or applications to detect fraudulent advertisements. For example, the display context analysis unit uses a generation AI to analyze the content of web pages or applications on which advertisements are displayed to detect fraudulent advertisements. For example, the generation AI analyzes themes and topics of the display context to prevent the display of fraudulent advertisements. The generation AI also takes into account a user's past browsing history and behavioral patterns to perform individually optimized fraudulent advertisement detection. This improves the accuracy of fraudulent advertisement detection by analyzing the content of advertisements displayed on specific websites or applications to detect fraudulent advertisements.

[0062] The learning unit periodically learns new data and can master new patterns and techniques of fraudulent advertising. For example, the generation AI periodically learns new data and masters new patterns and techniques of fraudulent advertising. For example, the generation AI performs learning by taking into account not only past fraudulent advertising data but also future trend prediction data. The generation AI also learns fraudulent advertising data from different industries and regions, improving detection accuracy from a global perspective. This allows the system to periodically learn new data and master new patterns and techniques of fraudulent advertising, thereby improving detection accuracy.

[0063] The ad text analysis unit can perform individually optimized fraudulent ad detection by taking into account the user's past search history and behavioral patterns. In the ad text analysis unit, for example, the generation AI refers to the user's past search history and performs individually optimized fraudulent ad detection. For example, the generation AI identifies fraudulent ad detection related to keywords the user has previously searched for. The generation AI also analyzes the user's behavioral patterns and performs individually optimized fraudulent ad detection. For example, the generation AI detects fraudulent ad detection related to websites the user frequently visits. Furthermore, the generation AI performs individually optimized fraudulent ad detection by taking into account the user's past click history. For example, the generation AI identifies fraudulent ad detection related to ads the user has previously clicked. This improves detection accuracy by performing individually optimized fraudulent ad detection by taking into account the user's past search history and behavioral patterns.

[0064] The ad text analysis unit uses the emotion estimation function to evaluate the emotional impact of ad text on a user and detect ads that may evoke negative emotions. In the ad text analysis unit, for example, the generation AI uses the emotion estimation function to evaluate the emotional impact of ad text on a user. For example, the generation AI detects ads if the ad text is likely to evoke anxiety or fear in a user. The generation AI also analyzes the emotional impact of ad text on a user and identifies ads that may evoke negative emotions. For example, the generation AI detects ads if the ad text evokes anger or sadness in a user. The generation AI also evaluates the emotional impact of ad text on a user and eliminates ads that may evoke negative emotions. For example, the generation AI detects ads if the ad text evokes stress or discomfort in a user. This improves detection accuracy by using the emotion estimation function to evaluate the emotional impact of ad text on a user and detects ads that may evoke negative emotions.

[0065] The ad text analysis unit can link the analysis results of ad text with other advertising platforms and social media, enabling widespread detection of fraudulent ads. For example, the generation AI can link the analysis results of ad text with other advertising platforms, enabling widespread detection of fraudulent ads. For example, the generation AI can share data among multiple advertising networks to simultaneously detect fraudulent ads. The generation AI can also link the analysis results of ad text with social media, enabling widespread detection of fraudulent ads. For example, the generation AI can detect fraudulent ads spreading on social media and respond quickly. The generation AI can also link the analysis results of ad text with other advertising platforms and social media, enabling widespread detection of fraudulent ads. For example, the generation AI can integrate data across different platforms to build a comprehensive fraudulent ad detection system. This allows the analysis results of ad text to be linked with other advertising platforms and social media, enabling widespread detection of fraudulent ads, improving detection accuracy.

[0066] The ad text analysis unit uses generation AI to support multiple languages ​​for ad text and can detect fraudulent ads in different languages. The ad text analysis unit, for example, uses generation AI to support multiple languages ​​for ad text and can detect fraudulent ads in different languages. For example, the generation AI identifies fraudulent ads in multiple languages, such as English, French, and Chinese. The generation AI can also identify fraudulent ads by taking into account nuances and differences in expression between languages. Furthermore, the generation AI can identify misleading expressions and false claims in different languages. As a result, detection accuracy is improved by using generation AI to support multiple languages ​​for ad text and can detect fraudulent ads in different languages.

[0067] The ad text analysis unit uses the emotion estimation function to analyze the emotional impact of ad text on specific target segments, thereby enabling optimal ad display for each target segment. In the ad text analysis unit, for example, the generation AI uses the emotion estimation function to analyze the emotional impact of ad text on specific target segments. For example, the generation AI evaluates emotional responses for different target segments, such as young people and the elderly. The generation AI also analyzes the emotional impact of ad text on specific target segments and optimally displays ads for each target segment. For example, the generation AI prioritizes displaying ads that evoke positive emotions. Furthermore, the generation AI analyzes the emotional impact of ad text on specific target segments and optimally displays ads for each target segment. For example, the generation AI eliminates ads that evoke negative emotions. As a result, the effectiveness of advertising is improved by using the emotion estimation function to analyze the emotional impact of ad text on specific target segments and optimally displaying ads for each target segment.

[0068] The advertising image analysis unit can analyze the metadata of advertising images and identify the source of fraudulent images. For example, the generation AI analyzes the metadata of advertising images and identifies the source of fraudulent images. For example, the generation AI detects counterfeit images based on the date and time the image was created and the creator information. The generation AI can also identify counterfeit images based on the image's editing history and information about the software used. Furthermore, the generation AI can identify the source of counterfeit images based on the image's geotag information. This improves detection accuracy by analyzing the metadata of advertising images and identifying the source of fraudulent images.

[0069] The advertising image analysis unit can detect subtle features within an image and identify counterfeit images. For example, the generative AI can detect subtle features within an image and identify counterfeit images. For example, the generative AI can identify unnatural pixel variations and color inconsistencies. The generative AI can also identify unnatural variations in the edges and texture of an image. Furthermore, the generative AI can identify unnatural patterns of compression artifacts and noise in an image. This improves detection accuracy by detecting subtle features within an image and identifying counterfeit images.

[0070] The advertising image analysis unit uses the emotion estimation function to evaluate the emotional impact of advertising images on users and detect images that may evoke negative emotions. In the advertising image analysis unit, for example, the generation AI uses the emotion estimation function to evaluate the emotional impact of advertising images on users. For example, the generation AI detects images that evoke anxiety or fear in users. The generation AI also analyzes the emotional impact of advertising images on users and identifies images that may evoke negative emotions. For example, the generation AI detects images that evoke anger or sadness in users. The generation AI also evaluates the emotional impact of advertising images on users and eliminates images that may evoke negative emotions. For example, the generation AI detects images that evoke stress or discomfort in users. This improves detection accuracy by using the emotion estimation function to evaluate the emotional impact of advertising images on users and detects images that may evoke negative emotions.

[0071] The advertising image analysis unit can link the analysis results of advertising images with other image recognition systems to achieve widespread detection of fraudulent advertising. For example, the advertising image analysis unit can link the analysis results of advertising images with other image recognition systems to achieve widespread detection of fraudulent advertising. For example, the generation AI can share data between multiple image recognition systems to simultaneously detect fraudulent advertising. The generation AI can also integrate data between different platforms to build a comprehensive fraudulent advertising detection system. Furthermore, the generation AI can share data between social media and advertising networks to quickly detect fraudulent advertising. This allows the analysis results of advertising images to be linked with other image recognition systems to achieve widespread detection of fraudulent advertising, improving detection accuracy.

[0072] The advertising image analysis unit uses generation AI to perform video analysis of advertising images and detect fraudulent elements within video ads. For example, the advertising image analysis unit uses generation AI to perform video analysis of advertising images and detect fraudulent elements within video ads. For example, generation AI can identify fake logos or unauthorized use of celebrities within videos. Generation AI can also identify unnatural editing or compositing within videos. Furthermore, generation AI can identify misleading expressions or false claims within videos. This improves detection accuracy by using generation AI to perform video analysis of advertising images and detect fraudulent elements within video ads.

[0073] The advertising image analysis unit uses the emotion estimation function to analyze the emotional impact of advertising images on specific target segments, thereby enabling optimal advertising display for each target segment. In the advertising image analysis unit, for example, the generation AI uses the emotion estimation function to analyze the emotional impact of advertising images on specific target segments. For example, the generation AI evaluates emotional responses to different target segments, such as young people and the elderly. The generation AI also analyzes the emotional impact of advertising images on specific target segments and optimally displays ads for each target segment. For example, the generation AI prioritizes displaying ads that evoke positive emotions. Furthermore, the generation AI analyzes the emotional impact of advertising images on specific target segments and optimally displays ads for each target segment. For example, the generation AI eliminates ads that evoke negative emotions. As a result, the effectiveness of advertising is improved by using the emotion estimation function to analyze the emotional impact of advertising images on specific target segments and optimally displaying ads for each target segment.

[0074] The display context analysis unit can analyze the overall theme or topic of a webpage on which an advertisement is displayed and prevent the display of fraudulent advertisements. For example, the generation AI can analyze the overall theme or topic of a webpage on which an advertisement is displayed and prevent the display of fraudulent advertisements. For example, the generation AI can detect advertisements displayed on webpages containing fraudulent content. The generation AI can also identify advertisements that do not match the content of the webpage. Furthermore, the generation AI can detect fraudulent advertisements related to the topic of the webpage. This improves detection accuracy by analyzing the overall theme or topic of a webpage on which an advertisement is displayed and preventing the display of fraudulent advertisements.

[0075] The display context analysis unit can perform individually optimized fraudulent ad detection by taking into account the user's past browsing history and behavioral patterns in the display context of the ad. In the display context analysis unit, for example, the generation AI refers to the user's past browsing history and performs individually optimized fraudulent ad detection. For example, the generation AI identifies fraudulent ads related to websites the user has previously visited. The generation AI also analyzes the user's behavioral patterns and performs individually optimized fraudulent ad detection. For example, the generation AI detects fraudulent ads related to content the user frequently accesses. Furthermore, the generation AI performs individually optimized fraudulent ad detection by taking into account the user's past click history. For example, the generation AI identifies fraudulent ads related to ads the user has previously clicked. This improves detection accuracy by performing individually optimized fraudulent ad detection by taking into account the user's past browsing history and behavioral patterns in the display context of the ad.

[0076] The display context analysis unit uses the emotion estimation function to evaluate the emotional impact of the display context of an advertisement on a user and detects advertisements that may evoke negative emotions. In the display context analysis unit, for example, the generation AI uses the emotion estimation function to evaluate the emotional impact of the display context of an advertisement on a user. For example, the generation AI detects an advertisement if the content of a webpage on which an advertisement is displayed causes anxiety or fear in the user. The generation AI also analyzes the emotional impact of the display context of an advertisement on a user and identifies advertisements that may evoke negative emotions. For example, the generation AI detects an advertisement if the content of a webpage on which an advertisement is displayed causes anger or sadness in the user. The generation AI also evaluates the emotional impact of the display context of an advertisement on a user and eliminates advertisements that may evoke negative emotions. For example, the generation AI detects an advertisement if the content of a webpage on which an advertisement is displayed causes stress or discomfort in the user. This improves detection accuracy by using the emotion estimation function to evaluate the emotional impact of the display context of an advertisement on a user and detects advertisements that may evoke negative emotions.

[0077] The display context analysis unit can link the results of ad display context analysis with other ad distribution platforms to achieve widespread detection of fraudulent ads. For example, the display context analysis unit allows the generation AI to link the results of ad display context analysis with other ad distribution platforms to achieve widespread detection of fraudulent ads. For example, the generation AI can share data between multiple ad networks to simultaneously detect fraudulent ads. The generation AI can also integrate data between different platforms to build a comprehensive fraudulent ad detection system. Furthermore, the generation AI can share data between social media and ad networks to quickly detect fraudulent ads. This allows the results of ad display context analysis to be linked with other ad distribution platforms to achieve widespread detection of fraudulent ads, improving detection accuracy.

[0078] The display context analysis unit uses generation AI to support multiple languages ​​for the display context of an ad and can detect fraudulent ads in different languages. The display context analysis unit, for example, uses generation AI to support multiple languages ​​for the display context of an ad and can detect fraudulent ads in different languages. For example, the generation AI identifies fraudulent ads in multiple languages, such as English, French, and Chinese. The generation AI can also identify fraudulent ads by taking into account nuances and differences in expression between languages. Furthermore, the generation AI can identify misleading expressions and false claims in different languages. This improves detection accuracy by using generation AI to support multiple languages ​​for the display context of an ad and can detect fraudulent ads in different languages.

[0079] The display context analysis unit uses the emotion estimation function to analyze the emotional impact of the display context of an advertisement on a specific target group, thereby optimally displaying the advertisement for each target group. In the display context analysis unit, for example, the generation AI uses the emotion estimation function to analyze the emotional impact of the display context of an advertisement on a specific target group. For example, the generation AI evaluates emotional responses to different target groups, such as young people and the elderly. The generation AI also analyzes the emotional impact of the display context of an advertisement on a specific target group, thereby optimally displaying the advertisement for each target group. For example, the generation AI prioritizes displaying advertisements that evoke positive emotions. Furthermore, the generation AI analyzes the emotional impact of the display context of an advertisement on a specific target group, thereby optimally displaying the advertisement for each target group. For example, the generation AI eliminates advertisements that evoke negative emotions. As a result, the effectiveness of the advertisement is improved by using the emotion estimation function to analyze the emotional impact of the display context of an advertisement on a specific target group and optimally displaying the advertisement for each target group.

[0080] When learning new fraudulent advertising patterns, the learning unit can take into account not only past fraudulent advertising data but also future trend prediction data. For example, when the generation AI learns new fraudulent advertising patterns, the learning unit takes into account not only past fraudulent advertising data but also future trend prediction data. For example, the generation AI learns fraud techniques that are predicted for the future. The generation AI can also learn fraud techniques based on new technologies and market trends. Furthermore, the generation AI can learn fraud techniques based on predicted future changes in consumer behavior. This improves detection accuracy by taking into account not only past fraudulent advertising data but also future trend prediction data when learning new fraudulent advertising patterns.

[0081] The learning unit can improve detection accuracy from a global perspective by including fraudulent advertising data from different industries and regions in the learning dataset. For example, the learning unit can improve detection accuracy from a global perspective by including fraudulent advertising data from different industries and regions in the dataset that the generation AI learns from. For example, the generation AI learns about fraudulent advertising in different countries and regions. The generation AI can also learn fraud techniques in different industries. Furthermore, the generation AI can learn fraud techniques based on different cultures and market environments. This improves detection accuracy by including fraudulent advertising data from different industries and regions in the learning dataset and improving detection accuracy from a global perspective.

[0082] The learning unit includes user emotional reaction data in a dataset used for learning using the emotion estimation function, thereby improving the accuracy of detecting fraudulent advertisements that are likely to resonate emotionally. The learning unit, for example, includes user emotional reaction data in a dataset used for learning by the generation AI using the emotion estimation function. For example, the generation AI learns advertisements that make users feel uncomfortable and detects fraudulent advertisements that are likely to resonate emotionally. The generation AI can also learn advertisements that make users feel anger or sadness and detect fraudulent advertisements that are likely to resonate emotionally. Furthermore, the generation AI can learn advertisements that make users feel stressed or anxious and detect fraudulent advertisements that are likely to resonate emotionally. In this way, including user emotional reaction data in a dataset used for learning using the emotion estimation function improves the accuracy of detecting fraudulent advertisements that are likely to resonate emotionally, thereby improving detection accuracy.

[0083] The learning unit can improve detection accuracy by sharing learning results with other AI systems and mutually complementing learning data. The learning unit, for example, improves detection accuracy by having the generation AI share learning results with other AI systems and mutually complementing learning data. For example, the generation AI can share data between different AI systems to improve the detection accuracy of fraudulent advertisements. The generation AI can also share algorithms between different AI systems to improve the detection accuracy of fraudulent advertisements. Furthermore, the generation AI can also share models between different AI systems to improve the detection accuracy of fraudulent advertisements. This allows learning results to be shared with other AI systems and mutually complementing learning data, improving detection accuracy.

[0084] The learning unit can improve multimedia-compatible detection accuracy by including fraudulent advertising data of different media formats in the learning dataset. The learning unit, for example, includes fraudulent advertising data of different media formats in the dataset that the generation AI learns from. For example, the generation AI learns from data on audio ads and video ads to improve multimedia-compatible detection accuracy. The generation AI can also learn from data on image ads and text ads to improve multimedia-compatible detection accuracy. Furthermore, the generation AI can also learn from data on interactive ads and banner ads to improve multimedia-compatible detection accuracy. In this way, by including fraudulent advertising data of different media formats in the learning dataset and improving multimedia-compatible detection accuracy, detection accuracy is improved.

[0085] The learning unit includes emotional response data of a specific target group in the dataset used for learning using the emotion estimation function, enabling optimal fraudulent ad detection for each target group. For example, the learning unit includes emotional response data of a specific target group in the dataset used for learning by the generation AI using the emotion estimation function. For example, the generation AI learns the emotional responses of different target groups, such as young people and the elderly, to optimally detect fraudulent ads. The generation AI can also learn the emotional responses of target groups with specific interests and concerns to optimally detect fraudulent ads. Furthermore, the generation AI can learn the emotional responses of target groups belonging to specific regions or cultures to optimally detect fraudulent ads. This allows the emotion response data of a specific target group to be included in the dataset used for learning using the emotion estimation function, enabling optimal fraudulent ad detection for each target group, thereby improving detection accuracy.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The fraudulent advertising detection system can also be equipped with a function to estimate user emotions and optimize the display of advertisements based on the estimated emotions. For example, the emotion estimation function can be used to evaluate the emotional response of users when viewing an advertisement and eliminate advertisements that may evoke negative emotions. It can also maximize the effectiveness of advertisements by preferentially displaying advertisements that elicit positive emotions from users. Furthermore, by accumulating user emotion data and analyzing long-term emotional trends, it is possible to achieve more accurate advertisement display optimization.

[0088] The fraudulent ad detection system can also be equipped with a function to adjust the frequency of ad display. For example, it can limit the frequency of ad display to prevent a particular ad from being displayed multiple times in a short period of time. Also, by reducing the frequency of displaying ads that a user has previously clicked, it is possible to maintain the effectiveness of the ads while reducing user annoyance. Furthermore, adjusting the frequency of ad display can also enable advertisers to realize effective advertising campaigns.

[0089] The fraudulent ad detection system can also be equipped with a function to optimize the timing of ad display. For example, the effectiveness of ads can be maximized by displaying ads at times when users are most likely to respond to ads. It can also analyze users' past behavioral patterns and predict the optimal display timing. Furthermore, the effectiveness of ads can be further increased by adjusting the timing of ad display to match specific events or seasons.

[0090] The fraudulent ad detection system can also be equipped with a function to optimize the display location of ads. For example, it can maximize the effectiveness of ads by displaying them in specific locations on web pages or applications where users are most likely to respond to ads. It can also analyze users' past behavioral patterns and predict the optimal display location. Furthermore, it can further increase the effectiveness of ads by displaying ads related to specific content or themes.

[0091] The fraudulent ad detection system can also be equipped with a function to optimize the creative elements of ads. For example, it can select the most effective ad creative based on past user response data. It can also create ads that are more likely to attract users' attention by adjusting elements such as ad color, font, and layout. Furthermore, it can regularly update the creative elements of ads to always provide fresh ads, thereby maintaining the effectiveness of ads.

[0092] The fraudulent advertising detection system can also be equipped with a function to estimate a user's emotions and customize the content of advertisements based on the estimated emotions. For example, using the emotion estimation function, if a user expresses positive emotions, advertising content that matches those emotions can be displayed. Also, if a user expresses negative emotions, advertising content that alleviates those emotions can be displayed. Furthermore, by accumulating user emotional data and analyzing long-term emotional trends, more accurate customization of advertising content can be achieved.

[0093] The fraudulent advertising detection system can also be equipped with a function to estimate a user's emotions and optimize the display order of advertisements based on the estimated emotions. For example, using the emotion estimation function, if a user expresses positive emotions, advertisements that match those emotions can be displayed preferentially. Also, if a user expresses negative emotions, advertisements that alleviate those emotions can be postponed. Furthermore, by accumulating user emotion data and analyzing long-term emotional trends, it is possible to achieve more accurate optimization of the display order of advertisements.

[0094] The fraudulent advertising detection system can also be equipped with a function to estimate user emotions and optimize the ad display format based on the estimated emotions. For example, if a user expresses positive emotions using the emotion estimation function, a display format (banner ad, pop-up ad, etc.) that matches those emotions can be selected. Also, if a user expresses negative emotions, a display format that alleviates those emotions can be selected. Furthermore, by accumulating user emotion data and analyzing long-term emotional trends, it is possible to achieve more accurate optimization of ad display formats.

[0095] The fraudulent advertising detection system can further include a function for estimating a user's emotions and adjusting the frequency of advertisement display based on the estimated emotions. For example, using the emotion estimation function, if a user expresses positive emotions, the frequency of advertisements that match those emotions can be increased. Also, if a user expresses negative emotions, the frequency of advertisements can be reduced to alleviate those emotions. Furthermore, by accumulating user emotion data and analyzing long-term emotional trends, more accurate adjustment of advertisement display frequency can be achieved.

[0096] The fraudulent ad detection system can also link ad display context with other ad distribution platforms to achieve widespread fraudulent ad detection. For example, Generation AI can share data between multiple ad networks to simultaneously detect fraudulent ads. Generation AI can also integrate data between different platforms to build a comprehensive fraudulent ad detection system. Furthermore, data can be shared between social media and ad networks to quickly detect fraudulent ads. This allows ad display context to be linked with other ad distribution platforms to achieve widespread fraudulent ad detection, improving detection accuracy.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The ad text analysis unit analyzes the ad text. For example, the generation AI analyzes the context of the ad text to detect deceptive content, misleading statements, and unauthorized use of celebrities. The generation AI can also use natural language processing techniques to understand the meaning and intent of the ad text and identify potential fraudulent activity. Furthermore, the generation AI can evaluate the tone and nuance of the text to detect ads with deceptive intent. Step 2: The advertising image analysis unit analyzes the advertising image. For example, the generation AI analyzes the characteristics of the advertising image and detects advertisements that use fake logos or images of celebrities without permission. The generation AI can also use image recognition technology to analyze the content of the advertising image and identify fraudulent elements. Furthermore, the generation AI can analyze the image metadata and identify the source of the fraudulent image. Step 3: The display context analysis unit analyzes the context in which the ad is displayed. For example, the generation AI analyzes the content of the web page or application in which the ad is displayed to detect fraudulent ads. The generation AI can also analyze the themes and topics of the display context to prevent the display of fraudulent ads. Furthermore, the generation AI can take into account the user's past browsing history and behavioral patterns to perform individually optimized fraudulent ad detection. Step 4: The learning unit periodically learns new data. For example, the generation AI learns new fraudulent ad patterns and techniques to improve detection accuracy. The generation AI can also learn by taking into account not only past fraudulent ad data, but also future trend prediction data. Furthermore, the generation AI can learn from fraudulent ad data from different industries and regions to improve detection accuracy from a global perspective.

[0099] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0100] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0104] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0105] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0106] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0108] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0109] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0110] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0111] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0112] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0113] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0119] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 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.

[0134] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0140] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0146] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0149] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0150] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0151] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0152] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0153] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0154] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0155] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0156] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0157] 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.

[0158] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0159] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0160] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0161] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0162] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0163] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0164] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0165] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0166] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an advertisement text analysis unit that analyzes advertisement text; an advertisement image analysis unit that analyzes advertisement images; a display context analysis unit that analyzes a context in which an advertisement is displayed; A learning unit that periodically learns new data. A system characterized by:

2. The advertisement text analysis unit Detect deceptive or misleading content and unauthorized use of celebrities 2. The system of claim 1.

3. The advertising image analysis unit Detect ads that use the aforementioned fake logos or celebrity images without permission 2. The system of claim 1.

4. The display context analysis unit Analyze the content of the ads displayed on specific websites and applications to detect fraudulent ads 2. The system of claim 1.

5. The learning unit Regularly learn from this new data and learn new patterns and techniques of fraudulent advertising 2. The system of claim 1.

Images