System

Abstract

An object of a system according to an embodiment is to filter unauthorized advertisements and automatically distribute sound advertisements.SOLUTION: A system includes an advertisement image analysis part, an advertisement text analysis part, a link destination information analysis part, a total analysis part, and a distribution part. The advertisement image analysis unit analyzes the advertisement image. The advertisement text analysis unit analyzes the advertisement text. The link destination information analysis unit analyzes the link destination information. The comprehensive analysis unit comprehensively analyzes the results analyzed by the advertisement image analysis unit, the advertisement text analysis unit, and the link destination information analysis unit, and filters unauthorized advertisements. The distribution part automatically distributes sound advertisements filtered by the total analysis part.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 technology can allow fraudulent or deceptive advertising to slip through the cracks.

[0005] The system according to the embodiment aims to filter fraudulent advertisements and automatically deliver sound advertisements. [Means for solving the problem]

[0006] The system according to the embodiment includes an advertising image analysis unit, an advertising text analysis unit, a link destination information analysis unit, a comprehensive analysis unit, and a distribution unit. The advertising image analysis unit analyzes advertising images. The advertising text analysis unit analyzes advertising text. The link destination information analysis unit analyzes link destination information. The comprehensive analysis unit comprehensively analyzes the results of the analyses by the advertising image analysis unit, advertising text analysis unit, and link destination information analysis unit, and filters out fraudulent advertisements. The distribution unit automatically distributes sound advertisements filtered out by the comprehensive analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can filter fraudulent advertisements and automatically deliver healthy advertisements. [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 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) The advertising integrity assurance system according to an embodiment of the present invention uses AI to comprehensively analyze advertisement images, text, and link destination information, and automatically delivers a healthy online advertising environment. As a result, the advertising integrity assurance system can filter fraudulent advertisements such as fraudulent and phishing sites, providing a safe online advertising environment for users.

[0029] An advertising integrity assurance system according to an embodiment includes an advertising image analysis unit, an advertising text analysis unit, a link destination information analysis unit, a comprehensive analysis unit, and a distribution unit. The advertising image analysis unit analyzes advertising images. For example, the generation AI recognizes text and symbols in advertising images and determines whether they are related to fraud or phishing. The generation AI can also analyze the color tones and patterns of the images to check for fraudulent content. The generation AI can also analyze the background information of the images to detect hidden messages and symbols. The advertising text analysis unit analyzes advertising text. For example, the generation AI can analyze keywords and phrases in the text to determine whether they are related to fraud or phishing. The generation AI can also analyze the context of the text to detect ambiguous expressions or misleading phrases. The generation AI can also analyze historical usage patterns of the text to detect phrases that have been used in fraudulent activities in the past. The link destination information analysis unit analyzes information about links included in advertisements. For example, the generation AI can analyze the URL and content of the linked site to determine whether it is a phishing site or a fraudulent site. The generation AI can also analyze the code of linked sites to detect hidden malware and phishing code. Furthermore, the generation AI can analyze the update history of linked sites to detect past fraudulent activity. The comprehensive analysis unit comprehensively analyzes the results of the ad image analysis unit, ad text analysis unit, and link information analysis unit to filter fraudulent ads. For example, the generation AI integrates the analysis results of each element to determine whether the ad as a whole is healthy. The generation AI can also analyze the interrelationships between each element of the ad to detect signs of complex fraud. Furthermore, the generation AI can analyze the ad distribution history to detect advertising patterns that have previously been used in fraudulent activity. The distribution unit automatically distributes healthy ads filtered by the comprehensive analysis unit. For example, the generation AI sends ads determined to be healthy to an ad distribution platform so that they can be displayed to users. The generation AI can also optimize the distribution schedule of healthy ads to distribute them during times when users are most interested.Furthermore, the generation AI can analyze healthy ad distribution channels and identify the most effective channel. As a result, the advertising integrity assurance system according to the embodiment can ensure the integrity of ads and provide a safe online advertising environment for users. For example, the output unit displays healthy ads to users via web applications or mobile applications. If users wish to receive feedback in paper form, the results are printed using a printer. Sending the results via email provides quick feedback by sending the results directly to the user.

[0030] The advertising image analysis unit can analyze subtle patterns and color changes within advertising images to detect signs of fraud. The advertising image analysis unit, for example, uses a generative AI to analyze subtle patterns and color changes within advertising images. For example, it detects unnatural color changes or pattern inconsistencies in specific parts of the image and determines whether they are signs of fraud. The generative AI can also analyze changes in the hue and brightness of the image to identify abnormal patterns. Furthermore, the generative AI can analyze changes in the texture and edges of the image to detect signs of fraud. This makes it possible to detect signs of fraud by analyzing subtle patterns and color changes within advertising images.

[0031] The advertising image analysis unit can analyze background information of advertising images and detect messages or symbols hidden in the background. The advertising image analysis unit can, for example, use generation AI to analyze background information of advertising images and detect messages or symbols hidden in the background. For example, it can identify text or symbols embedded subtly in the background. The generation AI can also analyze changes in the color or texture of the background to detect hidden messages. Furthermore, the generation AI can analyze objects or patterns in the background to identify hidden symbols. This makes it possible to detect hidden messages or symbols by analyzing background information of advertising images.

[0032] The advertising image analysis unit can detect dynamic fraudulent advertising by including video ads in the analysis of advertising images. The advertising image analysis unit can detect dynamic fraudulent advertising by, for example, including video ads in the analysis of advertising images. For example, it can analyze each frame in the video to identify signs of fraud. The generation AI can also analyze the movement and changes in the video to detect abnormal patterns. Furthermore, the generation AI can analyze the audio and text in the video to identify signs of fraud. As a result, it is possible to detect dynamic fraudulent advertising by including video ads in the analysis of advertising images.

[0033] The advertising image analysis unit can use generative AI to analyze 3D models of advertising images and detect three-dimensional fraudulent advertising. The advertising image analysis unit can, for example, use generative AI to analyze 3D models of advertising images and detect three-dimensional fraudulent advertising. For example, the unit can analyze the shape and texture of the 3D model to identify signs of fraud. The generative AI can also analyze the movement and changes of the 3D model to detect abnormal patterns. Furthermore, the generative AI can analyze changes in light and shadow in the 3D model to identify signs of fraud. As a result, three-dimensional fraudulent advertising can be detected by analyzing the 3D models of advertising images.

[0034] The ad text analysis unit can use generative AI to analyze the context of ad text and detect ambiguous expressions that may be fraudulent. The ad text analysis unit can, for example, use generative AI to analyze the context of ad text and detect ambiguous expressions that may be fraudulent. For example, it can identify ambiguous expressions and misleading phrases. The generative AI can also analyze the context of the text and related topics to identify ambiguous expressions. Furthermore, the generative AI can analyze the meaning and intent of the text and detect expressions that may be fraudulent. As a result, by analyzing the context of the ad text, it is possible to detect ambiguous expressions that may be fraudulent.

[0035] The ad text analysis unit uses the generation AI to analyze the historical usage patterns of the ad text and can detect phrases that have been used in fraudulent activities in the past. The ad text analysis unit, for example, uses the generation AI to analyze the historical usage patterns of the ad text and detect phrases that have been used in fraudulent activities in the past. For example, it refers to a database of past fraudulent ads and identifies similar phrases. The generation AI can also analyze the frequency of use and changes in the text to identify signs of fraud. Furthermore, the generation AI can analyze the meaning and intent of the text and detect phrases that have been used in fraudulent activities in the past. As a result, by analyzing the historical usage patterns of the ad text, it is possible to detect phrases that have been used in fraudulent activities in the past.

[0036] The ad text analysis unit can detect voice fraud ads by including the text of voice ads in the analysis of ad text. The ad text analysis unit can detect voice fraud ads, for example, by including the text of voice ads in the analysis of ad text. For example, the ad text analysis unit can automatically transcribe the text of voice ads and identify signs of fraud. The generation AI can also analyze the content of voice ads and identify signs of fraud. Furthermore, the generation AI can analyze historical usage patterns of voice ads and detect phrases that have been used for fraud in the past. As a result, voice fraud ads can be detected by including the text of voice ads in the analysis of ad text.

[0037] The ad text analysis unit can use generative AI to analyze translations of ad text to detect fraudulent ads in different languages. The ad text analysis unit can, for example, use generative AI to analyze translations of ad text to detect fraudulent ads in different languages. For example, it can analyze the translated text to identify signs of fraud. The generative AI can also analyze the meaning and intent of text in different languages ​​to identify signs of fraud. Furthermore, the generative AI can analyze historical usage patterns of text in different languages ​​to detect phrases that have been used for fraud in the past. This allows fraudulent ads in different languages ​​to be detected by analyzing translations of ad text.

[0038] The link information analysis unit can use generation AI to analyze the code of linked sites and detect hidden malware or phishing code. The link information analysis unit can, for example, use generation AI to analyze the code of linked sites and detect hidden malware or phishing code. For example, it can analyze the HTML and JavaScript code of the site to identify malicious scripts. The generation AI can also analyze the CSS and other code of the site to detect malware or phishing code. Furthermore, the generation AI can analyze the change history of the site's code and identify history of malware or phishing code being embedded in the past. This makes it possible to detect hidden malware and phishing code by analyzing the code of linked sites.

[0039] The link destination information analysis unit can use the generation AI to analyze the update history of the linked site and detect past histories of fraudulent acts. The link destination information analysis unit can, for example, use the generation AI to analyze the update history of the linked site and detect past histories of fraudulent acts. For example, it can refer to a database of the site's update history to identify histories of fraudulent acts. The generation AI can also analyze the site's version history and change log to identify signs of fraudulent acts. Furthermore, the generation AI can analyze the updates and changes to the site and evaluate the possibility of fraudulent acts. In this way, by analyzing the update history of the linked site, it is possible to detect past histories of fraudulent acts.

[0040] The link destination information analysis unit can detect fraudulent advertisements on social media by including social media links in the link destination analysis. The link destination information analysis unit can detect fraudulent advertisements on social media by, for example, including social media links in the link destination analysis. For example, it can analyze links included in social media posts and comments to identify signs of fraud. The generation AI can also analyze social media accounts and profiles to identify signs of fraud. Furthermore, the generation AI can analyze social media post history and comment history to detect signs of fraudulent advertisements. As a result, it is possible to detect fraudulent advertisements on social media by including social media links in the link destination analysis.

[0041] The linked information analysis unit can use the generation AI to analyze user reviews of linked sites and detect signs of fraud. The linked information analysis unit can, for example, use the generation AI to analyze user reviews of linked sites and detect signs of fraud. For example, it can analyze the text of user reviews and identify signs of fraud. The generation AI can also analyze ratings and comments in user reviews and identify signs of fraud. Furthermore, the generation AI can analyze patterns and trends in user reviews and detect signs of fraud. This makes it possible to detect signs of fraud by analyzing user reviews of linked sites.

[0042] The comprehensive analysis unit uses generative AI to analyze the interrelationships between each element of an advertisement and can detect signs of complex fraud. The comprehensive analysis unit, for example, uses generative AI to analyze the interrelationships between each element of an advertisement and can detect signs of complex fraud. For example, it integrates information on images, text, and linked pages to identify signs of fraud. The generative AI can also analyze the relationships and interactions between each element to identify signs of fraud. Furthermore, the generative AI can analyze the overall structure and patterns of an advertisement and can detect signs of complex fraud. This makes it possible to detect signs of complex fraud by analyzing the interrelationships between each element of an advertisement.

[0043] The comprehensive analysis unit can use the generation AI to analyze the ad delivery history and detect advertising patterns that have been used in the past to commit fraudulent acts. The comprehensive analysis unit, for example, uses the generation AI to analyze the ad delivery history and detect advertising patterns that have been used in the past to commit fraudulent acts. For example, it refers to a database of past delivery history to identify fraudulent advertising patterns. The generation AI can also analyze changes and trends in the delivery history to identify signs of fraud. Furthermore, the generation AI can analyze detailed data in the delivery history and detect advertising patterns that have been used in the past to commit fraudulent acts. In this way, by analyzing the ad delivery history, it is possible to detect advertising patterns that have been used in the past to commit fraudulent acts.

[0044] The comprehensive analysis unit can detect deceptive advertisements based on user behavior patterns by including a user's behavior history in the comprehensive analysis. The comprehensive analysis unit can detect deceptive advertisements based on a user's behavior patterns, for example, by including a user's behavior history in the comprehensive analysis. For example, the comprehensive analysis unit can analyze a user's past click history and browsing history to identify signs of fraud. The generation AI can also analyze a user's behavior patterns and trends to identify signs of fraud. Furthermore, the generation AI can integrate user behavior data to detect complex signs of fraud. As a result, by including a user's behavior history in the comprehensive analysis, it can detect deceptive advertisements based on a user's behavior patterns.

[0045] The comprehensive analysis unit can use the generation AI to analyze the areas where advertisements are delivered and detect trends in fraudulent advertisements by region. The comprehensive analysis unit can, for example, use the generation AI to analyze the areas where advertisements are delivered and detect trends in fraudulent advertisements by region. For example, it can identify patterns of fraudulent advertisements that are frequently delivered in specific regions. The generation AI can also analyze advertising delivery data by region and identify signs of fraud. Furthermore, the generation AI can analyze trends and changes in advertisements by region and detect signs of fraudulent advertisements. In this way, by analyzing the areas where advertisements are delivered, it is possible to detect trends in fraudulent advertisements by region.

[0046] The distribution unit can use the generation AI to optimize the distribution schedule of healthy advertisements and distribute them during times when users are most interested. The distribution unit can, for example, use the generation AI to optimize the distribution schedule of healthy advertisements and distribute them during times when users are most interested. For example, the distribution unit can analyze past user behavior data to identify the optimal distribution time. The generation AI can also analyze the advertisement distribution history to identify an effective distribution schedule. Furthermore, the generation AI can analyze user behavior patterns and tendencies to predict the optimal distribution time. This allows the distribution schedule of healthy advertisements to be optimized and distributed during times when users are most interested.

[0047] The distribution unit can use the generation AI to analyze the distribution history of healthy advertisements and identify the most effective distribution pattern. The distribution unit can, for example, use the generation AI to analyze the distribution history of healthy advertisements and identify the most effective distribution pattern. For example, the distribution unit can refer to a database of past distribution history to identify an effective distribution pattern. The generation AI can also analyze changes and trends in the distribution history to identify an effective distribution pattern. Furthermore, the generation AI can analyze detailed data of the distribution history to identify the most effective distribution pattern. In this way, the most effective distribution pattern can be identified by analyzing the distribution history of healthy advertisements.

[0048] The distribution unit can deliver advertisements based on the user's interests by including personalized advertisements in the automatic distribution of wholesome advertisements. The distribution unit, for example, delivers advertisements based on the user's interests by including personalized advertisements in the automatic distribution of wholesome advertisements. For example, the distribution unit analyzes the user's past behavioral data to identify advertisements based on their interests. The generation AI can also analyze the user's profile and preferences to generate personalized advertisements. Furthermore, the generation AI can analyze the user's behavioral patterns and tendencies to deliver optimal personalized advertisements. In this way, by including personalized advertisements in the automatic distribution of wholesome advertisements, advertisements based on the user's interests can be delivered.

[0049] The distribution unit can use the generation AI to analyze healthy advertising distribution channels and identify the most effective channel. The distribution unit can, for example, use the generation AI to analyze healthy advertising distribution channels and identify the most effective channel. For example, the distribution unit can refer to a database of past distribution channels to identify an effective channel. The generation AI can also analyze changes and trends in distribution channels to identify an effective channel. Furthermore, the generation AI can analyze detailed data on distribution channels and identify the most effective channel. In this way, the most effective channel can be identified by analyzing healthy advertising distribution channels.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The advertising integrity assurance system may further include a behavioral analysis unit that analyzes a user's behavioral history. The behavioral analysis unit may, for example, analyze a user's past click history or browsing history to identify signs of fraud. The behavioral analysis unit may also analyze a user's behavioral patterns and tendencies to identify signs of fraud. Furthermore, the behavioral analysis unit may integrate user behavioral data to detect signs of multiple frauds. This allows for more effective detection of fraudulent advertisements by analyzing a user's behavioral history.

[0052] The advertising integrity assurance system can further include a regional analysis unit that analyzes the region in which advertisements are delivered. The regional analysis unit, for example, uses generative AI to analyze the region in which advertisements are delivered and detect trends in fraudulent advertisements by region. For example, it identifies patterns of fraudulent advertisements that are frequently delivered in specific regions. The regional analysis unit can also analyze advertisement delivery data by region and identify signs of fraud. Furthermore, the regional analysis unit can analyze trends and changes in advertisements by region and detect signs of fraudulent advertisements. In this way, by analyzing the region in which advertisements are delivered, trends in fraudulent advertisements by region can be detected.

[0053] The advertising integrity assurance system can further include a channel analysis unit that analyzes advertising distribution channels. The channel analysis unit, for example, uses a generation AI to analyze advertising distribution channels and identify the most effective channel. For example, it refers to a database of past distribution channels to identify effective channels. The channel analysis unit can also analyze changes and trends in distribution channels to identify effective channels. Furthermore, the channel analysis unit can analyze detailed data on distribution channels to identify the most effective channel. In this way, the most effective channel can be identified by analyzing advertising distribution channels.

[0054] The advertising integrity assurance system may further include a schedule optimization unit that optimizes the delivery schedule of advertisements. The schedule optimization unit, for example, uses a generation AI to optimize the delivery schedule of healthy advertisements and deliver them during times when users are most interested. For example, the schedule optimization unit may analyze past user behavior data to identify the optimal delivery time. The schedule optimization unit may also analyze the delivery history of advertisements and identify an effective delivery schedule. Furthermore, the schedule optimization unit may analyze user behavior patterns and tendencies to predict the optimal delivery time. This allows the delivery schedule of healthy advertisements to be optimized and delivered during times when users are most interested.

[0055] The advertising integrity assurance system can further include an effectiveness evaluation unit that evaluates the effectiveness of advertisements. The effectiveness evaluation unit evaluates the effectiveness of advertisements using, for example, a generation AI, and identifies the most effective advertisement. For example, the effectiveness evaluation unit analyzes the click-through rate and conversion rate of advertisements to identify effective advertisements. The effectiveness evaluation unit can also analyze the number of times an advertisement is displayed and the engagement rate to identify effective advertisements. Furthermore, the effectiveness evaluation unit can analyze the distribution history of advertisements to identify the most effective advertisements. In this way, the effectiveness of advertisements can be evaluated and the most effective advertisements can be identified.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The advertising image analysis unit analyzes the advertising image. For example, the generation AI recognizes text and symbols in the advertising image and determines whether they are related to fraud or phishing. The generation AI can also analyze the color tone and patterns of the image to check whether it contains fraudulent content. Furthermore, the generation AI can analyze the background information of the image to detect hidden messages and symbols. Step 2: The ad text analysis unit analyzes the ad text. For example, the generation AI analyzes keywords and phrases in the text to determine whether they are related to fraud or phishing. The generation AI can also analyze the context of the text to detect ambiguous expressions or misleading phrases. Furthermore, the generation AI can analyze the historical usage patterns of the text to detect phrases that have been used in fraudulent activities in the past. Step 3: The link information analysis unit analyzes the information of the link contained in the advertisement. For example, the generation AI analyzes the URL and content of the linked site to determine whether it is a phishing site or a fraudulent site. The generation AI can also analyze the code of the linked site to detect hidden malware or phishing code. Furthermore, the generation AI can analyze the update history of the linked site to detect any history of past fraudulent activity. Step 4: The comprehensive analysis unit comprehensively analyzes the results of the analysis by the ad image analysis unit, ad text analysis unit, and link information analysis unit to filter out fraudulent ads. For example, the generation AI integrates the analysis results of each element to determine whether the ad as a whole is sound. The generation AI can also analyze the interrelationships between each element of the ad to detect signs of complex fraud. Furthermore, the generation AI can analyze the ad distribution history to detect advertising patterns that have previously been associated with fraudulent activity. Step 5: The distribution unit automatically distributes healthy ads filtered by the comprehensive analysis unit. For example, the generation AI sends ads that are deemed healthy to an ad distribution platform so that they are displayed to users. The generation AI can also optimize the distribution schedule of healthy ads and distribute them during times when users are most interested. Furthermore, the generation AI can analyze the distribution channels for healthy ads and identify the most effective channels.

[0058] (Example 2) The advertising integrity assurance system according to an embodiment of the present invention uses AI to comprehensively analyze advertisement images, text, and link destination information, and automatically delivers a healthy online advertising environment. As a result, the advertising integrity assurance system can filter fraudulent advertisements such as fraudulent and phishing sites, providing a safe online advertising environment for users.

[0059] An advertising integrity assurance system according to an embodiment includes an advertising image analysis unit, an advertising text analysis unit, a link destination information analysis unit, a comprehensive analysis unit, and a distribution unit. The advertising image analysis unit analyzes advertising images. For example, the generation AI recognizes text and symbols in advertising images and determines whether they are related to fraud or phishing. The generation AI can also analyze the color tones and patterns of the images to check for fraudulent content. The generation AI can also analyze the background information of the images to detect hidden messages and symbols. The advertising text analysis unit analyzes advertising text. For example, the generation AI can analyze keywords and phrases in the text to determine whether they are related to fraud or phishing. The generation AI can also analyze the context of the text to detect ambiguous expressions or misleading phrases. The generation AI can also analyze historical usage patterns of the text to detect phrases that have been used in fraudulent activities in the past. The link destination information analysis unit analyzes information about links included in advertisements. For example, the generation AI can analyze the URL and content of the linked site to determine whether it is a phishing site or a fraudulent site. The generation AI can also analyze the code of linked sites to detect hidden malware and phishing code. Furthermore, the generation AI can analyze the update history of linked sites to detect past fraudulent activity. The comprehensive analysis unit comprehensively analyzes the results of the ad image analysis unit, ad text analysis unit, and link information analysis unit to filter fraudulent ads. For example, the generation AI integrates the analysis results of each element to determine whether the ad as a whole is healthy. The generation AI can also analyze the interrelationships between each element of the ad to detect signs of complex fraud. Furthermore, the generation AI can analyze the ad distribution history to detect advertising patterns that have previously been used in fraudulent activity. The distribution unit automatically distributes healthy ads filtered by the comprehensive analysis unit. For example, the generation AI sends ads determined to be healthy to an ad distribution platform so that they can be displayed to users. The generation AI can also optimize the distribution schedule of healthy ads to distribute them during times when users are most interested.Furthermore, the generation AI can analyze healthy ad distribution channels and identify the most effective channel. As a result, the advertising integrity assurance system according to the embodiment can ensure the integrity of ads and provide a safe online advertising environment for users. For example, the output unit displays healthy ads to users via web applications or mobile applications. If users wish to receive feedback in paper form, the results are printed using a printer. Sending the results via email provides quick feedback by sending the results directly to the user.

[0060] The advertising image analysis unit can analyze subtle patterns and color changes within advertising images to detect signs of fraud. The advertising image analysis unit, for example, uses a generative AI to analyze subtle patterns and color changes within advertising images. For example, it detects unnatural color changes or pattern inconsistencies in specific parts of the image and determines whether they are signs of fraud. The generative AI can also analyze changes in the hue and brightness of the image to identify abnormal patterns. Furthermore, the generative AI can analyze changes in the texture and edges of the image to detect signs of fraud. This makes it possible to detect signs of fraud by analyzing subtle patterns and color changes within advertising images.

[0061] The advertising image analysis unit can analyze background information of advertising images and detect messages or symbols hidden in the background. The advertising image analysis unit can, for example, use generation AI to analyze background information of advertising images and detect messages or symbols hidden in the background. For example, it can identify text or symbols embedded subtly in the background. The generation AI can also analyze changes in the color or texture of the background to detect hidden messages. Furthermore, the generation AI can analyze objects or patterns in the background to identify hidden symbols. This makes it possible to detect hidden messages or symbols by analyzing background information of advertising images.

[0062] The advertising image analysis unit uses the emotion estimation function to analyze the emotional response of a user who has viewed an advertising image, and can filter out images that may evoke negative emotions. The advertising image analysis unit, for example, uses the emotion estimation function to analyze the emotional response of a user who has viewed an advertising image. For example, it analyzes the user's facial expressions and eye movements to identify images that may evoke negative emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate the emotional response. Furthermore, the emotion estimation function can analyze the user's behavioral data and filter out images that may evoke negative emotions. In this way, by analyzing the emotional response of a user who has viewed an advertising image, it is possible to filter out images that may evoke negative emotions.

[0063] The advertising image analysis unit can detect dynamic fraudulent advertising by including video ads in the analysis of advertising images. The advertising image analysis unit can detect dynamic fraudulent advertising by, for example, including video ads in the analysis of advertising images. For example, it can analyze each frame in the video to identify signs of fraud. The generation AI can also analyze the movement and changes in the video to detect abnormal patterns. Furthermore, the generation AI can analyze the audio and text in the video to identify signs of fraud. As a result, it is possible to detect dynamic fraudulent advertising by including video ads in the analysis of advertising images.

[0064] The advertising image analysis unit can use generative AI to analyze 3D models of advertising images and detect three-dimensional fraudulent advertising. The advertising image analysis unit can, for example, use generative AI to analyze 3D models of advertising images and detect three-dimensional fraudulent advertising. For example, the unit can analyze the shape and texture of the 3D model to identify signs of fraud. The generative AI can also analyze the movement and changes of the 3D model to detect abnormal patterns. Furthermore, the generative AI can analyze changes in light and shadow in the 3D model to identify signs of fraud. As a result, three-dimensional fraudulent advertising can be detected by analyzing the 3D models of advertising images.

[0065] The advertising image analysis unit uses the emotion estimation function to monitor the emotions of users who view advertising images in real time, and can prioritize the delivery of images that elicit positive emotions. The advertising image analysis unit, for example, uses the emotion estimation function to monitor the emotions of users who view advertising images in real time. For example, it analyzes the user's facial expressions and eye movements to identify images that elicit positive emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate emotional responses. Furthermore, the emotion estimation function can analyze the user's behavioral data and prioritize the delivery of images that elicit positive emotions. This makes it possible to monitor the emotions of users who view advertising images in real time, and prioritize the delivery of images that elicit positive emotions.

[0066] The ad text analysis unit can use generative AI to analyze the context of ad text and detect ambiguous expressions that may be fraudulent. The ad text analysis unit can, for example, use generative AI to analyze the context of ad text and detect ambiguous expressions that may be fraudulent. For example, it can identify ambiguous expressions and misleading phrases. The generative AI can also analyze the context of the text and related topics to identify ambiguous expressions. Furthermore, the generative AI can analyze the meaning and intent of the text and detect expressions that may be fraudulent. As a result, by analyzing the context of the ad text, it is possible to detect ambiguous expressions that may be fraudulent.

[0067] The ad text analysis unit uses the generation AI to analyze the historical usage patterns of the ad text and can detect phrases that have been used in fraudulent activities in the past. The ad text analysis unit, for example, uses the generation AI to analyze the historical usage patterns of the ad text and detect phrases that have been used in fraudulent activities in the past. For example, it refers to a database of past fraudulent ads and identifies similar phrases. The generation AI can also analyze the frequency of use and changes in the text to identify signs of fraud. Furthermore, the generation AI can analyze the meaning and intent of the text and detect phrases that have been used in fraudulent activities in the past. As a result, by analyzing the historical usage patterns of the ad text, it is possible to detect phrases that have been used in fraudulent activities in the past.

[0068] The advertising text analysis unit can use the emotion estimation function to analyze the emotional response of a user who reads the advertising text and filter out text that may evoke negative emotions. The advertising text analysis unit, for example, uses the emotion estimation function to analyze the emotional response of a user who reads the advertising text. For example, it can analyze the user's facial expressions and voice to identify text that may evoke negative emotions. The emotion estimation function can also analyze the user's biometric data and behavioral data to evaluate the emotional response. Furthermore, the emotion estimation function can analyze the user's text input and click data to filter out text that may evoke negative emotions. In this way, by analyzing the emotional response of a user who reads the advertising text, it is possible to filter out text that may evoke negative emotions.

[0069] The ad text analysis unit can detect voice fraud ads by including the text of voice ads in the analysis of ad text. The ad text analysis unit can detect voice fraud ads, for example, by including the text of voice ads in the analysis of ad text. For example, the ad text analysis unit can automatically transcribe the text of voice ads and identify signs of fraud. The generation AI can also analyze the content of voice ads and identify signs of fraud. Furthermore, the generation AI can analyze historical usage patterns of voice ads and detect phrases that have been used for fraud in the past. As a result, voice fraud ads can be detected by including the text of voice ads in the analysis of ad text.

[0070] The ad text analysis unit can use generative AI to analyze translations of ad text to detect fraudulent ads in different languages. The ad text analysis unit can, for example, use generative AI to analyze translations of ad text to detect fraudulent ads in different languages. For example, it can analyze the translated text to identify signs of fraud. The generative AI can also analyze the meaning and intent of text in different languages ​​to identify signs of fraud. Furthermore, the generative AI can analyze historical usage patterns of text in different languages ​​to detect phrases that have been used for fraud in the past. This allows fraudulent ads in different languages ​​to be detected by analyzing translations of ad text.

[0071] The advertising text analysis unit uses the emotion estimation function to monitor the emotions of users who read the advertising text in real time, and can prioritize the delivery of text that elicits positive emotions. The advertising text analysis unit, for example, uses the emotion estimation function to monitor the emotions of users who read the advertising text in real time. For example, it analyzes the user's facial expressions and voice to identify text that elicits positive emotions. The emotion estimation function can also analyze the user's biometric data and behavioral data to evaluate emotional responses. Furthermore, the emotion estimation function can analyze the user's text input and click data to prioritize the delivery of text that elicits positive emotions. This makes it possible to monitor the emotions of users who read the advertising text in real time, and prioritize the delivery of text that elicits positive emotions.

[0072] The link information analysis unit can use generation AI to analyze the code of linked sites and detect hidden malware or phishing code. The link information analysis unit can, for example, use generation AI to analyze the code of linked sites and detect hidden malware or phishing code. For example, it can analyze the HTML and JavaScript code of the site to identify malicious scripts. The generation AI can also analyze the CSS and other code of the site to detect malware or phishing code. Furthermore, the generation AI can analyze the change history of the site's code and identify history of malware or phishing code being embedded in the past. This makes it possible to detect hidden malware and phishing code by analyzing the code of linked sites.

[0073] The link destination information analysis unit can use the generation AI to analyze the update history of the linked site and detect past histories of fraudulent acts. The link destination information analysis unit can, for example, use the generation AI to analyze the update history of the linked site and detect past histories of fraudulent acts. For example, it can refer to a database of the site's update history to identify histories of fraudulent acts. The generation AI can also analyze the site's version history and change log to identify signs of fraudulent acts. Furthermore, the generation AI can analyze the updates and changes to the site and evaluate the possibility of fraudulent acts. In this way, by analyzing the update history of the linked site, it is possible to detect past histories of fraudulent acts.

[0074] The linked information analysis unit uses the emotion estimation function to analyze the emotional response of users who visit linked sites, and can filter out sites that may evoke negative emotions. The linked information analysis unit, for example, uses the emotion estimation function to analyze the emotional response of users who visit linked sites. For example, it analyzes the user's facial expressions and eye movements to identify sites that may evoke negative emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate the emotional response. Furthermore, the emotion estimation function can analyze the user's behavioral data to filter out sites that may evoke negative emotions. In this way, by analyzing the emotional response of users who visit linked sites, it is possible to filter out sites that may evoke negative emotions.

[0075] The link destination information analysis unit can detect fraudulent advertisements on social media by including social media links in the link destination analysis. The link destination information analysis unit can detect fraudulent advertisements on social media by, for example, including social media links in the link destination analysis. For example, it can analyze links included in social media posts and comments to identify signs of fraud. The generation AI can also analyze social media accounts and profiles to identify signs of fraud. Furthermore, the generation AI can analyze social media post history and comment history to detect signs of fraudulent advertisements. As a result, it is possible to detect fraudulent advertisements on social media by including social media links in the link destination analysis.

[0076] The linked information analysis unit can use the generation AI to analyze user reviews of linked sites and detect signs of fraud. The linked information analysis unit can, for example, use the generation AI to analyze user reviews of linked sites and detect signs of fraud. For example, it can analyze the text of user reviews and identify signs of fraud. The generation AI can also analyze ratings and comments in user reviews and identify signs of fraud. Furthermore, the generation AI can analyze patterns and trends in user reviews and detect signs of fraud. This makes it possible to detect signs of fraud by analyzing user reviews of linked sites.

[0077] The linked information analysis unit uses the emotion estimation function to monitor the emotions of users who visit linked sites in real time, and can prioritize the delivery of sites that elicit positive emotions. The linked information analysis unit, for example, uses the emotion estimation function to monitor the emotions of users who visit linked sites in real time. For example, it analyzes the user's facial expressions and eye movements to identify sites that elicit positive emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate emotional responses. Furthermore, the emotion estimation function can analyze the user's behavioral data to prioritize the delivery of sites that elicit positive emotions. This makes it possible to monitor the emotions of users who visit linked sites in real time, and prioritize the delivery of sites that elicit positive emotions.

[0078] The comprehensive analysis unit uses generative AI to analyze the interrelationships between each element of an advertisement and can detect signs of complex fraud. The comprehensive analysis unit, for example, uses generative AI to analyze the interrelationships between each element of an advertisement and can detect signs of complex fraud. For example, it integrates information on images, text, and linked pages to identify signs of fraud. The generative AI can also analyze the relationships and interactions between each element to identify signs of fraud. Furthermore, the generative AI can analyze the overall structure and patterns of an advertisement and can detect signs of complex fraud. This makes it possible to detect signs of complex fraud by analyzing the interrelationships between each element of an advertisement.

[0079] The comprehensive analysis unit can use the generation AI to analyze the ad delivery history and detect advertising patterns that have been used in the past to commit fraudulent acts. The comprehensive analysis unit, for example, uses the generation AI to analyze the ad delivery history and detect advertising patterns that have been used in the past to commit fraudulent acts. For example, it refers to a database of past delivery history to identify fraudulent advertising patterns. The generation AI can also analyze changes and trends in the delivery history to identify signs of fraud. Furthermore, the generation AI can analyze detailed data in the delivery history and detect advertising patterns that have been used in the past to commit fraudulent acts. In this way, by analyzing the ad delivery history, it is possible to detect advertising patterns that have been used in the past to commit fraudulent acts.

[0080] The comprehensive analysis unit uses the emotion estimation function to analyze the emotional response of a user who has viewed the entire advertisement, and can filter out advertisements that may evoke negative emotions. The comprehensive analysis unit, for example, uses the emotion estimation function to analyze the emotional response of a user who has viewed the entire advertisement. For example, the comprehensive analysis unit analyzes the user's facial expressions and eye movements to identify advertisements that may evoke negative emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate the emotional response. Furthermore, the emotion estimation function can analyze the user's behavioral data to filter out advertisements that may evoke negative emotions. In this way, by analyzing the emotional response of a user who has viewed the entire advertisement, it is possible to filter out advertisements that may evoke negative emotions.

[0081] The comprehensive analysis unit can detect deceptive advertisements based on user behavior patterns by including a user's behavior history in the comprehensive analysis. The comprehensive analysis unit can detect deceptive advertisements based on a user's behavior patterns, for example, by including a user's behavior history in the comprehensive analysis. For example, the comprehensive analysis unit can analyze a user's past click history and browsing history to identify signs of fraud. The generation AI can also analyze a user's behavior patterns and trends to identify signs of fraud. Furthermore, the generation AI can integrate user behavior data to detect complex signs of fraud. As a result, by including a user's behavior history in the comprehensive analysis, it can detect deceptive advertisements based on a user's behavior patterns.

[0082] The comprehensive analysis unit can use the generation AI to analyze the areas where advertisements are delivered and detect trends in fraudulent advertisements by region. The comprehensive analysis unit can, for example, use the generation AI to analyze the areas where advertisements are delivered and detect trends in fraudulent advertisements by region. For example, it can identify patterns of fraudulent advertisements that are frequently delivered in specific regions. The generation AI can also analyze advertising delivery data by region and identify signs of fraud. Furthermore, the generation AI can analyze trends and changes in advertisements by region and detect signs of fraudulent advertisements. In this way, by analyzing the areas where advertisements are delivered, it is possible to detect trends in fraudulent advertisements by region.

[0083] The comprehensive analysis unit uses the emotion estimation function to monitor the emotions of users who view the entire advertisement in real time, and can prioritize delivery of advertisements that elicit positive emotions. The comprehensive analysis unit, for example, uses the emotion estimation function to monitor the emotions of users who view the entire advertisement in real time. For example, it analyzes the user's facial expressions and eye movements to identify advertisements that elicit positive emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate emotional responses. Furthermore, the emotion estimation function can analyze the user's behavioral data to prioritize delivery of advertisements that elicit positive emotions. This makes it possible to monitor the emotions of users who view the entire advertisement in real time, and prioritize delivery of advertisements that elicit positive emotions.

[0084] The distribution unit can use the generation AI to optimize the distribution schedule of healthy advertisements and distribute them during times when users are most interested. The distribution unit can, for example, use the generation AI to optimize the distribution schedule of healthy advertisements and distribute them during times when users are most interested. For example, the distribution unit can analyze past user behavior data to identify the optimal distribution time. The generation AI can also analyze the advertisement distribution history to identify an effective distribution schedule. Furthermore, the generation AI can analyze user behavior patterns and tendencies to predict the optimal distribution time. This allows the distribution schedule of healthy advertisements to be optimized and distributed during times when users are most interested.

[0085] The distribution unit can use the generation AI to analyze the distribution history of healthy advertisements and identify the most effective distribution pattern. The distribution unit can, for example, use the generation AI to analyze the distribution history of healthy advertisements and identify the most effective distribution pattern. For example, the distribution unit can refer to a database of past distribution history to identify an effective distribution pattern. The generation AI can also analyze changes and trends in the distribution history to identify an effective distribution pattern. Furthermore, the generation AI can analyze detailed data of the distribution history to identify the most effective distribution pattern. In this way, the most effective distribution pattern can be identified by analyzing the distribution history of healthy advertisements.

[0086] The delivery unit can use the emotion estimation function to analyze the emotional response of a user who has viewed a healthy advertisement and optimize a delivery method that elicits positive emotions. The delivery unit, for example, uses the emotion estimation function to analyze the emotional response of a user who has viewed a healthy advertisement. For example, the delivery unit analyzes the user's facial expressions and eye movements to identify a delivery method that elicits positive emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate the emotional response. Furthermore, the emotion estimation function can analyze the user's behavioral data and optimize a delivery method that elicits positive emotions. In this way, by analyzing the emotional response of a user who has viewed a healthy advertisement, a delivery method that elicits positive emotions can be optimized.

[0087] The distribution unit can deliver advertisements based on the user's interests by including personalized advertisements in the automatic distribution of wholesome advertisements. The distribution unit, for example, delivers advertisements based on the user's interests by including personalized advertisements in the automatic distribution of wholesome advertisements. For example, the distribution unit analyzes the user's past behavioral data to identify advertisements based on their interests. The generation AI can also analyze the user's profile and preferences to generate personalized advertisements. Furthermore, the generation AI can analyze the user's behavioral patterns and tendencies to deliver optimal personalized advertisements. In this way, by including personalized advertisements in the automatic distribution of wholesome advertisements, advertisements based on the user's interests can be delivered.

[0088] The distribution unit can use the generation AI to analyze healthy advertising distribution channels and identify the most effective channel. The distribution unit can, for example, use the generation AI to analyze healthy advertising distribution channels and identify the most effective channel. For example, the distribution unit can refer to a database of past distribution channels to identify an effective channel. The generation AI can also analyze changes and trends in distribution channels to identify an effective channel. Furthermore, the generation AI can analyze detailed data on distribution channels and identify the most effective channel. In this way, the most effective channel can be identified by analyzing healthy advertising distribution channels.

[0089] The distribution unit uses the emotion estimation function to monitor the emotions of users who have viewed healthy advertisements in real time, and can continuously deliver advertisements that elicit positive emotions. The distribution unit, for example, uses the emotion estimation function to monitor the emotions of users who have viewed healthy advertisements in real time. For example, the distribution unit analyzes the user's facial expressions and eye movements to identify advertisements that elicit positive emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate emotional responses. Furthermore, the emotion estimation function can analyze the user's behavioral data and continuously deliver advertisements that elicit positive emotions. This makes it possible to monitor the emotions of users who have viewed healthy advertisements in real time, and continuously deliver advertisements that elicit positive emotions.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The advertising integrity assurance system may further include a behavioral analysis unit that analyzes a user's behavioral history. The behavioral analysis unit may, for example, analyze a user's past click history or browsing history to identify signs of fraud. The behavioral analysis unit may also analyze a user's behavioral patterns and tendencies to identify signs of fraud. Furthermore, the behavioral analysis unit may integrate user behavioral data to detect signs of multiple frauds. This allows for more effective detection of fraudulent advertisements by analyzing a user's behavioral history.

[0092] The advertising integrity assurance system can further include a regional analysis unit that analyzes the region in which advertisements are delivered. The regional analysis unit, for example, uses generative AI to analyze the region in which advertisements are delivered and detect trends in fraudulent advertisements by region. For example, it identifies patterns of fraudulent advertisements that are frequently delivered in specific regions. The regional analysis unit can also analyze advertisement delivery data by region and identify signs of fraud. Furthermore, the regional analysis unit can analyze trends and changes in advertisements by region and detect signs of fraudulent advertisements. In this way, by analyzing the region in which advertisements are delivered, trends in fraudulent advertisements by region can be detected.

[0093] The advertising integrity assurance system can further include a channel analysis unit that analyzes advertising distribution channels. The channel analysis unit, for example, uses a generation AI to analyze advertising distribution channels and identify the most effective channel. For example, it refers to a database of past distribution channels to identify effective channels. The channel analysis unit can also analyze changes and trends in distribution channels to identify effective channels. Furthermore, the channel analysis unit can analyze detailed data on distribution channels to identify the most effective channel. In this way, the most effective channel can be identified by analyzing advertising distribution channels.

[0094] The advertising integrity assurance system may further include a schedule optimization unit that optimizes the delivery schedule of advertisements. The schedule optimization unit, for example, uses a generation AI to optimize the delivery schedule of healthy advertisements and deliver them during times when users are most interested. For example, the schedule optimization unit may analyze past user behavior data to identify the optimal delivery time. The schedule optimization unit may also analyze the delivery history of advertisements and identify an effective delivery schedule. Furthermore, the schedule optimization unit may analyze user behavior patterns and tendencies to predict the optimal delivery time. This allows the delivery schedule of healthy advertisements to be optimized and delivered during times when users are most interested.

[0095] The advertising integrity assurance system can further include an effectiveness evaluation unit that evaluates the effectiveness of advertisements. The effectiveness evaluation unit evaluates the effectiveness of advertisements using, for example, a generation AI, and identifies the most effective advertisement. For example, the effectiveness evaluation unit analyzes the click-through rate and conversion rate of advertisements to identify effective advertisements. The effectiveness evaluation unit can also analyze the number of times an advertisement is displayed and the engagement rate to identify effective advertisements. Furthermore, the effectiveness evaluation unit can analyze the distribution history of advertisements to identify the most effective advertisements. In this way, the effectiveness of advertisements can be evaluated and the most effective advertisements can be identified.

[0096] The advertising integrity assurance system can further use an emotion estimation function to analyze the emotional response of a user who has viewed the entire advertisement and filter out advertisements that may evoke negative emotions. For example, the system can analyze a user's facial expressions and eye movements to identify advertisements that may evoke negative emotions. The emotion estimation function can also analyze a user's voice and biometric data to evaluate the emotional response. Furthermore, the emotion estimation function can analyze user behavior data and filter out advertisements that may evoke negative emotions. In this way, by analyzing the emotional response of a user who has viewed the entire advertisement, it is possible to filter out advertisements that may evoke negative emotions.

[0097] The advertising integrity assurance system also uses an emotion estimation function to monitor the emotions of users who view the entire advertisement in real time, and can prioritize the delivery of advertisements that elicit positive emotions. For example, it can analyze the user's facial expressions and eye movements to identify advertisements that elicit positive emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate emotional responses. Furthermore, the emotion estimation function can analyze user behavior data to prioritize the delivery of advertisements that elicit positive emotions. This allows the system to monitor the emotions of users who view the entire advertisement in real time, and prioritize the delivery of advertisements that elicit positive emotions.

[0098] The advertising integrity assurance system can further use an emotion estimation function to analyze the emotional response of users who view advertising images and filter out images that may evoke negative emotions. For example, the system can analyze the user's facial expressions and eye movements to identify images that may evoke negative emotions. The emotion estimation function can also analyze the user's voice and biometric data to evaluate the emotional response. Furthermore, the emotion estimation function can analyze the user's behavioral data and filter out images that may evoke negative emotions. In this way, by analyzing the emotional response of users who view advertising images, it is possible to filter out images that may evoke negative emotions.

[0099] The ad integrity assurance system can further use an emotion estimation function to analyze the emotional response of users who read ad text and filter out text that may evoke negative emotions. For example, the system can analyze the user's facial expressions and voice to identify text that may evoke negative emotions. The emotion estimation function can also analyze the user's biometric data and behavioral data to evaluate the emotional response. Furthermore, the emotion estimation function can analyze the user's text input and click data to filter out text that may evoke negative emotions. This makes it possible to filter out text that may evoke negative emotions by analyzing the user's emotional response when reading ad text.

[0100] The ad integrity assurance system can further use an emotion estimation function to analyze the emotional responses of users who visit linked sites and filter out sites that may evoke negative emotions. For example, it can analyze a user's facial expressions and eye movements to identify sites that may evoke negative emotions. The emotion estimation function can also analyze a user's voice and biometric data to evaluate their emotional responses. Furthermore, the emotion estimation function can analyze user behavior data and filter out sites that may evoke negative emotions. This makes it possible to filter out sites that may evoke negative emotions by analyzing the emotional responses of users who visit linked sites.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The advertising image analysis unit analyzes the advertising image. For example, the generation AI recognizes text and symbols in the advertising image and determines whether they are related to fraud or phishing. The generation AI can also analyze the color tone and patterns of the image to check whether it contains fraudulent content. Furthermore, the generation AI can analyze the background information of the image to detect hidden messages and symbols. Step 2: The ad text analysis unit analyzes the ad text. For example, the generation AI analyzes keywords and phrases in the text to determine whether they are related to fraud or phishing. The generation AI can also analyze the context of the text to detect ambiguous expressions or misleading phrases. Furthermore, the generation AI can analyze the historical usage patterns of the text to detect phrases that have been used in fraudulent activities in the past. Step 3: The link information analysis unit analyzes the information of the link contained in the advertisement. For example, the generation AI analyzes the URL and content of the linked site to determine whether it is a phishing site or a fraudulent site. The generation AI can also analyze the code of the linked site to detect hidden malware or phishing code. Furthermore, the generation AI can analyze the update history of the linked site to detect any history of past fraudulent activity. Step 4: The comprehensive analysis unit comprehensively analyzes the results of the analysis by the ad image analysis unit, ad text analysis unit, and link information analysis unit to filter out fraudulent ads. For example, the generation AI integrates the analysis results of each element to determine whether the ad as a whole is sound. The generation AI can also analyze the interrelationships between each element of the ad to detect signs of complex fraud. Furthermore, the generation AI can analyze the ad distribution history to detect advertising patterns that have previously been associated with fraudulent activity. Step 5: The distribution unit automatically distributes healthy ads filtered by the comprehensive analysis unit. For example, the generation AI sends ads that are deemed healthy to an ad distribution platform so that they are displayed to users. The generation AI can also optimize the distribution schedule of healthy ads and distribute them during times when users are most interested. Furthermore, the generation AI can analyze the distribution channels for healthy ads and identify the most effective channels.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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]

[0170] 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 advertising image analysis unit that analyzes advertising images; an advertisement text analysis unit that analyzes advertisement text; a link destination information analysis unit that analyzes link destination information; a comprehensive analysis unit that comprehensively analyzes the results of the analyses performed by the advertisement image analysis unit, the advertisement text analysis unit, and the link destination information analysis unit, and filters out fraudulent advertisements; a distribution unit that automatically distributes the healthy advertisements filtered by the comprehensive analysis unit. A system characterized by:

2. The advertising image analysis unit Detecting dynamic fraudulent ads by including video ads in the analysis of the ad images 2. The system of claim 1.

3. The advertisement text analysis unit Generative AI is used to analyze the context of the ad text and detect ambiguous language that may be fraudulent.

2. The system of claim 1.

4. The link destination information analysis unit Uses generative AI to analyze linked code and detect hidden malware and phishing code 2. The system of claim 1.

5. The comprehensive analysis unit Using generative AI to analyze the interrelationships between each of the elements of the ad to detect signs of complex fraud 2. The system of claim 1.

6. The distribution unit Generative AI is used to optimize the delivery schedule of these healthy ads, delivering them during times when users are most interested.

2. The system of claim 1.

7. The advertising image analysis unit Using an emotion estimation function, the emotional response of the user who viewed the advertising image is analyzed, and images that may evoke negative emotions are filtered out.

2. The system of claim 1.

8. The advertisement text analysis unit Using an emotion estimation function, the emotional response of users who read the advertising text is analyzed, and text that may evoke negative emotions is filtered out.

2. The system of claim 1.

Images