system

Abstract

The system according to this embodiment aims to identify and remove fraudulent or inappropriate content in online advertisements in advance. [Solution] The system according to the embodiment comprises an analysis unit, an identification unit, and a removal unit. The analysis unit analyzes the image, text, and link destination of the advertisement. The identification unit identifies fraudulent or inappropriate content based on the advertisement content analyzed by the analysis unit. The removal unit removes the inappropriate advertisement identified by the identification unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, fraud and inappropriate content in online advertisements have not been sufficiently identified and removed in advance, and there is room for improvement.

[0005] The system according to the embodiment aims to identify and remove fraud and inappropriate content in online advertisements in advance.

Means for Solving the Problems

[0006] The system according to the embodiment includes an analysis unit, an identification unit, and a removal unit. The analysis unit analyzes the image, text, and link destination of an advertisement. The identification unit identifies fraud or inappropriate content based on the advertisement content analyzed by the analysis unit. The removal unit removes inappropriate advertisements identified by the identification unit. [Effects of the Invention]

[0007] The system according to this embodiment can identify and remove fraudulent or inappropriate content in online advertisements in advance. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

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

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

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

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

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

[0019] The smart device 14 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0028] (Example of form 1) An advertising monitoring system according to an embodiment of the present invention is a system that uses AI to analyze the images, text, and destinations of advertisements to identify and remove fraudulent or inappropriate content in advance. By using AI to analyze the images, text, and destinations of advertisements to identify and remove fraudulent or inappropriate content in advance, the advertising monitoring system provides a safe and reliable online advertising environment. For example, the advertising monitoring system is equipped with image and text analysis technology using deep learning. The advertising monitoring system is equipped with a real-time advertising content monitoring system. The advertising monitoring system is equipped with fraudulent link detection and blocking functions. As a result, the advertising monitoring system is expected to improve user trust by reducing fraudulent advertisements, increase advertising revenue, and protect the brand value of advertisers. The advertising monitoring system is beneficial to companies using online advertising, consumers seeking a safe browsing environment for end users, and advertising platforms that want to maximize advertising revenue. The advertising monitoring system provides innovative advertising filtering technology that realizes automated monitoring of advertising content using the latest AI technology, strengthens the reliability of the advertising industry by improving the accuracy of fraud detection, and improves the user experience. As a result, the advertising monitoring system can provide a safe and reliable online advertising environment.

[0029] The ad monitoring system according to this embodiment comprises an analysis unit, an identification unit, and a removal unit. The analysis unit analyzes the ad's image, text, and link destination. The analysis unit, for example, analyzes the ad's image and recognizes objects within the image. The analysis unit analyzes the ad's text and analyzes the text's context and linguistic patterns. The analysis unit analyzes the ad's link destination and evaluates the reliability of the linked domain. The identification unit identifies fraudulent or inappropriate content based on the ad content analyzed by the analysis unit. The identification unit, for example, determines that an image containing violent scenes is inappropriate based on the ad's image analysis results. The identification unit identifies potentially fraudulent content based on the ad's text analysis results. The identification unit identifies unreliable links based on the ad's link destination analysis results. The removal unit removes inappropriate ads identified by the identification unit. The removal unit, for example, quickly deletes inappropriate ads. The removal unit blocks inappropriate ads. The removal unit stops the display of inappropriate ads. As a result, the advertising monitoring system according to this embodiment can provide a safe and reliable online advertising environment by analyzing the images, text, and destinations of advertisements, and identifying and removing fraudulent or inappropriate content.

[0030] The analysis unit analyzes the images, text, and links in advertisements. Specifically, in ad image analysis, it uses image recognition technology to recognize objects within the image. For example, it utilizes computer vision algorithms with deep learning to analyze people, objects, and backgrounds in detail. This makes it possible to identify violent scenes or inappropriate content contained in ad images. In ad text analysis, it uses natural language processing (NLP) technology to analyze the context and linguistic patterns of the text. Specifically, it performs morphological and grammatical analysis to extract keywords and phrases within the text and identify text that may contain fraudulent or inappropriate content. Furthermore, in ad link analysis, it comprehensively analyzes domain registration information, past access history, and security ratings to evaluate the reliability of the linked domain. This makes it possible to identify unreliable links and phishing sites, protecting users. The analysis unit processes these analysis results in real time and provides them quickly to the identification unit, thereby improving the overall efficiency and accuracy of the system.

[0031] The identification unit identifies fraudulent or inappropriate content based on the ad content analyzed by the analysis unit. Specifically, based on the image analysis results of the ad, it analyzes the features of objects and scenes within the image in detail to determine if images containing violent scenes are inappropriate. For example, it evaluates the facial expressions and poses of people in the image, the background situation, etc., to determine whether or not it contains violent acts or inappropriate scenes. Based on the text analysis results of the ad, it analyzes the frequency and context of keywords and phrases within the text to identify potentially fraudulent content. For example, if it contains many fraud-related keywords such as "free," "limited," and "now," or if the context is unnatural, it is judged to be highly likely to be fraudulent. Based on the link analysis results of the ad, it comprehensively analyzes the evaluation of the linked domain, past access history, security evaluation, etc. to identify unreliable links. For example, domains that have been reported as phishing sites in the past or domains with low security evaluations are judged to be unreliable. The identification unit quickly provides these identification results to the removal unit and instructs it to remove inappropriate ads. This allows the identification unit to analyze the ad content in detail and identify fraudulent or inappropriate content with high accuracy.

[0032] The removal unit removes inappropriate advertisements identified by the identification unit. Specifically, to quickly remove inappropriate advertisements, it works with the ad delivery system to immediately stop the relevant advertisements. For example, it uses the ad delivery platform's API to specify the ID of the inappropriate advertisement and send a command to stop its delivery. It also instructs the ad delivery system to add specific advertisers or domains to a blacklist in order to block inappropriate advertisements. This prevents inappropriate advertisements from the same advertiser or domain from being delivered again. Furthermore, to stop the display of inappropriate advertisements, it sends a command to the user's browser or application to block the display of the relevant advertisement. For example, it can use browser extensions or application filtering functions to prevent the display of inappropriate advertisements. The removal unit performs these removal processes in real time, ensuring user safety by quickly and reliably removing inappropriate advertisements. The removal unit also records logs of the removal process so that they can be used for later audits and analysis. This allows the removal unit to improve the reliability and transparency of the entire system.

[0033] The analysis unit includes image and text analysis techniques using deep learning. For example, the analysis unit uses deep learning to analyze images of advertisements and recognize objects within the images. The analysis unit uses deep learning to analyze the text of advertisements and analyze the context and linguistic patterns of the text. The analysis unit uses deep learning to analyze the destination of links in advertisements and evaluate the reliability of the destination domain. As a result, the accuracy of image and text analysis is improved by using deep learning. Deep learning is implemented using techniques such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs).

[0034] The identification unit includes a system that monitors ad content in real time. For example, the identification unit monitors the image analysis results of ads in real time and determines that images containing violent scenes are inappropriate. The identification unit monitors the text analysis results of ads in real time and identifies potentially fraudulent content. The identification unit monitors the destination analysis results of ads in real time and identifies unreliable links. This allows for the rapid identification of inappropriate ads by monitoring ad content in real time. Real time is defined by criteria such as response time and processing speed.

[0035] The removal unit includes malicious link detection and blocking functions. For example, the removal unit detects and blocks malicious links. The removal unit detects malicious links and notifies the user. The removal unit detects malicious links and stops displaying advertisements. This protects users from malicious links by detecting and blocking them. Malicious links are clearly defined, for example, phishing sites and malware sites.

[0036] The analysis unit detects inappropriate content by analyzing the color tone and composition of images during the image analysis of advertisements. For example, the analysis unit analyzes the color tone of an advertisement image and determines that an image with excessively stimulating colors is inappropriate. The analysis unit analyzes the composition of an advertisement image and determines that an image containing violent scenes is inappropriate. The analysis unit comprehensively analyzes the color tone and composition of an advertisement image and determines that an image containing sexual content is inappropriate. In this way, inappropriate content can be effectively detected by analyzing the color tone and composition of an image. Color tone and composition are analyzed based on criteria such as hue, saturation, brightness, and compositional patterns.

[0037] The analysis unit assesses the likelihood of fraud by analyzing the context and linguistic patterns of the text during the text analysis of advertisements. For example, the analysis unit analyzes the context of the advertisement text and determines that content that excessively emphasizes benefits may be fraudulent. The analysis unit analyzes the linguistic patterns of the advertisement text and detects when certain phrases or expressions are associated with fraud. The analysis unit comprehensively analyzes the context and linguistic patterns of the advertisement text and determines that it may be fraudulent if it cites unreliable sources. In this way, the likelihood of fraud can be effectively assessed by analyzing the context and linguistic patterns of the text. Context and linguistic patterns are analyzed using, for example, natural language processing techniques and text mining techniques.

[0038] The analytics department evaluates the reliability of the destination domain when analyzing the landing pages of advertisements and reflects this in the analysis results. For example, the analytics department evaluates the reliability of the landing page domain of an advertisement and determines that a domain with low reliability is inappropriate. The analytics department analyzes the past history of the landing page domain of an advertisement and determines that a domain with a history of fraudulent activity is inappropriate. The analytics department checks the owner information of the landing page domain of an advertisement and determines that an owner with low reliability is inappropriate. In this way, by evaluating the reliability of the landing page domain, it is possible to effectively detect links with low reliability. The reliability of a domain is evaluated based on criteria such as the domain's history, security rating, and user rating.

[0039] The analysis unit detects inappropriate content during image analysis of advertisements using object recognition technology within the image. For example, the analysis unit recognizes objects within the advertisement image and determines that images containing violent scenes are inappropriate. The analysis unit recognizes objects within the advertisement image and determines that images containing sexual content are inappropriate. The analysis unit recognizes objects within the advertisement image and determines that images containing excessively stimulating content are inappropriate. In this way, inappropriate content can be effectively detected by using object recognition technology within the image. Object recognition technology is implemented using technologies such as YOLO and Faster R-CNN.

[0040] The identification unit improves identification accuracy by referring to past identification results when identifying ad content. For example, the identification unit refers to past identification results to identify ads with similar patterns. The identification unit refers to past identification results and incorporates feedback to improve identification accuracy. The identification unit refers to past identification results and adjusts the identification criteria to improve accuracy. In this way, identification accuracy is improved by referring to past identification results. Past identification results are referred to based on criteria such as the database structure and the reference algorithm.

[0041] The identification unit identifies advertisements based on the advertiser's past behavior history when identifying advertisement content. For example, the identification unit analyzes the advertiser's past behavior history to identify cases of fraudulent activity. The identification unit analyzes the advertiser's past behavior history to identify unreliable advertisers. The identification unit analyzes the advertiser's past behavior history to identify advertisements that have had problems in the past. In this way, unreliable advertisers can be effectively identified by considering the advertiser's past behavior history. The advertiser's past behavior history is considered based on criteria such as past advertising history and violation history.

[0042] The identification unit identifies advertisements by considering the location and time of day they are displayed. For example, the identification unit considers the location of the advertisement to identify inappropriate advertisements in specific locations. The identification unit considers the time of day the advertisement is displayed to identify inappropriate advertisements in specific time periods. The identification unit comprehensively considers the location and time of day the advertisement is displayed to identify inappropriate advertisements. This makes it possible to identify advertisements that are appropriate for specific locations and time periods by considering the location and time of day the advertisement is displayed. The location and time of day the advertisement is displayed are considered based on criteria such as geographical information and time characteristics.

[0043] The identification unit identifies advertisements based on the attribute information of the target audience. For example, the identification unit considers the age range of the target audience to identify inappropriate advertisements. The identification unit considers the gender of the target audience to identify inappropriate advertisements. The identification unit considers the interests of the target audience to identify inappropriate advertisements. This allows for more accurate identification by considering the attribute information of the target audience. The attribute information of the target audience is considered based on criteria such as age, gender, and interests.

[0044] The removal unit evaluates the scope of impact of inappropriate ads to determine the removal priority. For example, the removal unit evaluates the scope of impact of ads and prioritizes the removal of ads that have a wide-ranging impact. The removal unit evaluates the scope of impact of ads and prioritizes the removal of ads that affect specific target audiences. The removal unit evaluates the scope of impact of ads and prioritizes the removal of ads with a significant impact. This allows for the priority removal of ads with a significant impact by evaluating the scope of impact. The scope of impact of ads is evaluated based on criteria such as the number of affected users and the severity of the impact.

[0045] The removal unit optimizes how advertisers are notified when inappropriate ads are removed. For example, the removal unit optimizes how advertisers are notified to quickly notify them of the removal of inappropriate ads. The removal unit optimizes how advertisers are notified to include detailed reasons. The removal unit optimizes how advertisers are notified to propose measures to prevent recurrence. This optimizes how advertisers are notified to quickly and thoroughly. The notification method is optimized based on criteria such as the timing and format of the notification.

[0046] The removal unit applies different removal methods to each advertising platform when removing inappropriate ads. For example, the removal unit applies different removal methods to each advertising platform to quickly remove inappropriate ads. The removal unit applies different removal methods to each advertising platform to remove inappropriate ads in the most optimal way. The removal unit applies different removal methods to each advertising platform to effectively remove inappropriate ads. This enables rapid and optimal ad removal by applying different removal methods to each advertising platform. The removal methods are applied based on criteria such as platform-specific characteristics and removal algorithms.

[0047] The removal unit saves relevant data about inappropriate advertisements when they are removed for future analysis. For example, the removal unit saves relevant data about inappropriate advertisements for future analysis. The removal unit saves relevant data about inappropriate advertisements for use in formulating measures to prevent recurrence. The removal unit saves relevant data about inappropriate advertisements for use in analyzing advertiser behavior patterns. This allows the saving of relevant data about advertisements to be used for future analysis and the formulation of measures to prevent recurrence. The relevant data is saved according to criteria such as the database structure and data storage format.

[0048] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0049] The analytics unit can adjust its analysis methods when analyzing ad images, text, and links, taking into account the user's browsing history. For example, it can analyze the trends of ads the user has viewed in the past and prioritize the analysis of ads with similar trends. The analytics unit can learn the characteristics of ads that the user has found offensive in the past and focus its analysis on ads with those characteristics. The analytics unit can also analyze relevant ads in detail, taking into account the content of ads the user has shown interest in in the past. By adjusting the analysis method based on the user's browsing history, it becomes possible to perform ad analysis that is more tailored to the user.

[0050] The identification unit can adjust its identification criteria when identifying ad content, taking into account the frequency of ad display. For example, if a particular ad is displayed frequently in a short period, it will focus on identifying that ad. If an ad is displayed frequently, the identification unit will determine that it is likely to be fraudulent or contain inappropriate content and will identify it in detail. Even if an ad is displayed infrequently, the identification unit will adjust its identification criteria by referring to past identification results. This allows for more effective ad identification by adjusting the identification criteria according to the frequency of ad display.

[0051] The removal unit can evaluate the impact of inappropriate advertisements and determine the priority of removal. For example, if an advertisement has a high impact, it will be removed first. The removal unit evaluates the impact of advertisements and focuses on removing advertisements that have a significant impact on specific target audiences. The removal unit evaluates the impact of advertisements and quickly removes advertisements that have a wide-ranging impact. By determining the priority of removal based on the impact of advertisements, more effective ad removal becomes possible.

[0052] The analysis unit can detect inappropriate content by analyzing the movement of objects within an image during image analysis of an advertisement. For example, it can analyze the movement of objects in an advertisement image and determine that an image containing violent movements is inappropriate. The analysis unit can analyze the movement of objects in an advertisement image and determine that an image containing sexual movements is inappropriate. The analysis unit can analyze the movement of objects in an advertisement image and determine that an image containing excessively stimulating movements is inappropriate. In this way, inappropriate content can be effectively detected by analyzing the movement of objects within an image.

[0053] The identification unit can identify advertisements based on the attribute information of the target audience. For example, it can identify inappropriate advertisements by considering the age range of the target audience. The identification unit can identify inappropriate advertisements by considering the gender of the target audience. The identification unit can identify inappropriate advertisements by considering the interests of the target audience. This allows for more accurate identification by considering the attribute information of the target audience.

[0054] The following briefly describes the processing flow for example form 1.

[0055] Step 1: The analysis unit analyzes the ad's image, text, and destination. For example, the analysis unit analyzes the ad's image and recognizes objects within the image. The analysis unit analyzes the ad's text and analyzes the context and linguistic patterns of the text. The analysis unit analyzes the ad's destination and evaluates the reliability of the destination domain. Step 2: The identification unit identifies fraudulent or inappropriate content based on the ad content analyzed by the analysis unit. For example, the identification unit determines that images containing violent scenes are inappropriate based on the image analysis results of the ad. The identification unit identifies potentially fraudulent content based on the text analysis results of the ad. The identification unit identifies unreliable links based on the destination analysis results of the ad. Step 3: The removal unit removes the inappropriate advertisements identified by the identification unit. For example, the removal unit quickly deletes inappropriate advertisements. The removal unit blocks inappropriate advertisements. The removal unit stops displaying inappropriate advertisements.

[0056] (Example of form 2) An advertising monitoring system according to an embodiment of the present invention is a system that uses AI to analyze the images, text, and destinations of advertisements to identify and remove fraudulent or inappropriate content in advance. By using AI to analyze the images, text, and destinations of advertisements to identify and remove fraudulent or inappropriate content in advance, the advertising monitoring system provides a safe and reliable online advertising environment. For example, the advertising monitoring system is equipped with image and text analysis technology using deep learning. The advertising monitoring system is equipped with a real-time advertising content monitoring system. The advertising monitoring system is equipped with fraudulent link detection and blocking functions. As a result, the advertising monitoring system is expected to improve user trust by reducing fraudulent advertisements, increase advertising revenue, and protect the brand value of advertisers. The advertising monitoring system is beneficial to companies using online advertising, consumers seeking a safe browsing environment for end users, and advertising platforms that want to maximize advertising revenue. The advertising monitoring system provides innovative advertising filtering technology that realizes automated monitoring of advertising content using the latest AI technology, strengthens the reliability of the advertising industry by improving the accuracy of fraud detection, and improves the user experience. As a result, the advertising monitoring system can provide a safe and reliable online advertising environment.

[0057] The ad monitoring system according to this embodiment comprises an analysis unit, an identification unit, and a removal unit. The analysis unit analyzes the ad's image, text, and link destination. The analysis unit, for example, analyzes the ad's image and recognizes objects within the image. The analysis unit analyzes the ad's text and analyzes the text's context and linguistic patterns. The analysis unit analyzes the ad's link destination and evaluates the reliability of the linked domain. The identification unit identifies fraudulent or inappropriate content based on the ad content analyzed by the analysis unit. The identification unit, for example, determines that an image containing violent scenes is inappropriate based on the ad's image analysis results. The identification unit identifies potentially fraudulent content based on the ad's text analysis results. The identification unit identifies unreliable links based on the ad's link destination analysis results. The removal unit removes inappropriate ads identified by the identification unit. The removal unit, for example, quickly deletes inappropriate ads. The removal unit blocks inappropriate ads. The removal unit stops the display of inappropriate ads. As a result, the advertising monitoring system according to this embodiment can provide a safe and reliable online advertising environment by analyzing the images, text, and destinations of advertisements, and identifying and removing fraudulent or inappropriate content.

[0058] The analysis unit analyzes the images, text, and links in advertisements. Specifically, in ad image analysis, it uses image recognition technology to recognize objects within the image. For example, it utilizes computer vision algorithms with deep learning to analyze people, objects, and backgrounds in detail. This makes it possible to identify violent scenes or inappropriate content contained in ad images. In ad text analysis, it uses natural language processing (NLP) technology to analyze the context and linguistic patterns of the text. Specifically, it performs morphological and grammatical analysis to extract keywords and phrases within the text and identify text that may contain fraudulent or inappropriate content. Furthermore, in ad link analysis, it comprehensively analyzes domain registration information, past access history, and security ratings to evaluate the reliability of the linked domain. This makes it possible to identify unreliable links and phishing sites, protecting users. The analysis unit processes these analysis results in real time and provides them quickly to the identification unit, thereby improving the overall efficiency and accuracy of the system.

[0059] The identification unit identifies fraudulent or inappropriate content based on the ad content analyzed by the analysis unit. Specifically, based on the image analysis results of the ad, it analyzes the features of objects and scenes within the image in detail to determine if images containing violent scenes are inappropriate. For example, it evaluates the facial expressions and poses of people in the image, the background situation, etc., to determine whether or not it contains violent acts or inappropriate scenes. Based on the text analysis results of the ad, it analyzes the frequency and context of keywords and phrases within the text to identify potentially fraudulent content. For example, if it contains many fraud-related keywords such as "free," "limited," and "now," or if the context is unnatural, it is judged to be highly likely to be fraudulent. Based on the link analysis results of the ad, it comprehensively analyzes the evaluation of the linked domain, past access history, security evaluation, etc. to identify unreliable links. For example, domains that have been reported as phishing sites in the past or domains with low security evaluations are judged to be unreliable. The identification unit quickly provides these identification results to the removal unit and instructs it to remove inappropriate ads. This allows the identification unit to analyze the ad content in detail and identify fraudulent or inappropriate content with high accuracy.

[0060] The removal unit removes inappropriate advertisements identified by the identification unit. Specifically, to quickly remove inappropriate advertisements, it works with the ad delivery system to immediately stop the relevant advertisements. For example, it uses the ad delivery platform's API to specify the ID of the inappropriate advertisement and send a command to stop its delivery. It also instructs the ad delivery system to add specific advertisers or domains to a blacklist in order to block inappropriate advertisements. This prevents inappropriate advertisements from the same advertiser or domain from being delivered again. Furthermore, to stop the display of inappropriate advertisements, it sends a command to the user's browser or application to block the display of the relevant advertisement. For example, it can use browser extensions or application filtering functions to prevent the display of inappropriate advertisements. The removal unit performs these removal processes in real time, ensuring user safety by quickly and reliably removing inappropriate advertisements. The removal unit also records logs of the removal process so that they can be used for later audits and analysis. This allows the removal unit to improve the reliability and transparency of the entire system.

[0061] The analysis unit includes image and text analysis techniques using deep learning. For example, the analysis unit uses deep learning to analyze images of advertisements and recognize objects within the images. The analysis unit uses deep learning to analyze the text of advertisements and analyze the context and linguistic patterns of the text. The analysis unit uses deep learning to analyze the destination of links in advertisements and evaluate the reliability of the destination domain. As a result, the accuracy of image and text analysis is improved by using deep learning. Deep learning is implemented using techniques such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs).

[0062] The identification unit includes a system that monitors ad content in real time. For example, the identification unit monitors the image analysis results of ads in real time and determines that images containing violent scenes are inappropriate. The identification unit monitors the text analysis results of ads in real time and identifies potentially fraudulent content. The identification unit monitors the destination analysis results of ads in real time and identifies unreliable links. This allows for the rapid identification of inappropriate ads by monitoring ad content in real time. Real time is defined by criteria such as response time and processing speed.

[0063] The removal unit includes malicious link detection and blocking functions. For example, the removal unit detects and blocks malicious links. The removal unit detects malicious links and notifies the user. The removal unit detects malicious links and stops displaying advertisements. This protects users from malicious links by detecting and blocking them. Malicious links are clearly defined, for example, phishing sites and malware sites.

[0064] The analysis unit estimates the user's emotions and adjusts the analysis methods for the ad's images, text, and links based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit prioritizes analyzing elements that provide a sense of security in the ad's image analysis. If the user is excited, the analysis unit focuses on analyzing content that promotes calmness in the ad's text analysis. If the user is relaxed, the analysis unit prioritizes analyzing content that helps maintain a relaxed state in the ad's link analysis. By adjusting the analysis method according to the user's emotions, more appropriate ad analysis becomes possible. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0065] The analysis unit detects inappropriate content by analyzing the color tone and composition of images during the image analysis of advertisements. For example, the analysis unit analyzes the color tone of an advertisement image and determines that an image with excessively stimulating colors is inappropriate. The analysis unit analyzes the composition of an advertisement image and determines that an image containing violent scenes is inappropriate. The analysis unit comprehensively analyzes the color tone and composition of an advertisement image and determines that an image containing sexual content is inappropriate. In this way, inappropriate content can be effectively detected by analyzing the color tone and composition of an image. Color tone and composition are analyzed based on criteria such as hue, saturation, brightness, and compositional patterns.

[0066] The analysis unit assesses the likelihood of fraud by analyzing the context and linguistic patterns of the text during the text analysis of advertisements. For example, the analysis unit analyzes the context of the advertisement text and determines that content that excessively emphasizes benefits may be fraudulent. The analysis unit analyzes the linguistic patterns of the advertisement text and detects when certain phrases or expressions are associated with fraud. The analysis unit comprehensively analyzes the context and linguistic patterns of the advertisement text and determines that it may be fraudulent if it cites unreliable sources. In this way, the likelihood of fraud can be effectively assessed by analyzing the context and linguistic patterns of the text. Context and linguistic patterns are analyzed using, for example, natural language processing techniques and text mining techniques.

[0067] The analytics unit estimates the user's emotions and determines the priority of ads to analyze based on those estimated emotions. For example, if the user is feeling anxious, the analytics unit prioritizes ads that provide a sense of security. If the user is excited, the analytics unit prioritizes ads that promote calmness. If the user is relaxed, the analytics unit prioritizes ads that maintain a relaxed state. By prioritizing ads according to the user's emotions, more appropriate ad analysis becomes possible. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Ad priority is determined by criteria such as user interest level and ad importance.

[0068] The analytics department evaluates the reliability of the destination domain when analyzing the landing pages of advertisements and reflects this in the analysis results. For example, the analytics department evaluates the reliability of the landing page domain of an advertisement and determines that a domain with low reliability is inappropriate. The analytics department analyzes the past history of the landing page domain of an advertisement and determines that a domain with a history of fraudulent activity is inappropriate. The analytics department checks the owner information of the landing page domain of an advertisement and determines that an owner with low reliability is inappropriate. In this way, by evaluating the reliability of the landing page domain, it is possible to effectively detect links with low reliability. The reliability of a domain is evaluated based on criteria such as the domain's history, security rating, and user rating.

[0069] The analysis unit detects inappropriate content during image analysis of advertisements using object recognition technology within the image. For example, the analysis unit recognizes objects within the advertisement image and determines that images containing violent scenes are inappropriate. The analysis unit recognizes objects within the advertisement image and determines that images containing sexual content are inappropriate. The analysis unit recognizes objects within the advertisement image and determines that images containing excessively stimulating content are inappropriate. In this way, inappropriate content can be effectively detected by using object recognition technology within the image. Object recognition technology is implemented using technologies such as YOLO and Faster R-CNN.

[0070] The identification unit estimates the user's emotions and adjusts the identification criteria based on the estimated emotions. For example, if the user is feeling anxious, the identification unit prioritizes identifying advertisements that provide a sense of security. If the user is excited, the identification unit prioritizes identifying advertisements that promote calmness. If the user is relaxed, the identification unit prioritizes identifying advertisements that maintain a relaxed state. By adjusting the identification criteria according to the user's emotions, more appropriate advertisement identification becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Identification criteria are adjusted based on criteria such as emotion scores or parameters of the identification algorithm.

[0071] The identification unit improves identification accuracy by referring to past identification results when identifying ad content. For example, the identification unit refers to past identification results to identify ads with similar patterns. The identification unit refers to past identification results and incorporates feedback to improve identification accuracy. The identification unit refers to past identification results and adjusts the identification criteria to improve accuracy. In this way, identification accuracy is improved by referring to past identification results. Past identification results are referred to based on criteria such as the database structure and the reference algorithm.

[0072] The identification unit identifies advertisements based on the advertiser's past behavior history when identifying advertisement content. For example, the identification unit analyzes the advertiser's past behavior history to identify cases of fraudulent activity. The identification unit analyzes the advertiser's past behavior history to identify unreliable advertisers. The identification unit analyzes the advertiser's past behavior history to identify advertisements that have had problems in the past. In this way, unreliable advertisers can be effectively identified by considering the advertiser's past behavior history. The advertiser's past behavior history is considered based on criteria such as past advertising history and violation history.

[0073] The identification unit estimates the user's emotions and adjusts the display method of the identification results based on the estimated emotions. For example, if the user is feeling anxious, the identification unit provides a display method that provides a sense of security. If the user is excited, the identification unit provides a display method that encourages calmness. If the user is relaxed, the identification unit provides a display method that maintains a relaxed state. By adjusting the display method of the identification results according to the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. The display method of the identification results is adjusted based on criteria such as display format and display timing.

[0074] The identification unit identifies advertisements by considering the location and time of day they are displayed. For example, the identification unit considers the location of the advertisement to identify inappropriate advertisements in specific locations. The identification unit considers the time of day the advertisement is displayed to identify inappropriate advertisements in specific time periods. The identification unit comprehensively considers the location and time of day the advertisement is displayed to identify inappropriate advertisements. This makes it possible to identify advertisements that are appropriate for specific locations and time periods by considering the location and time of day the advertisement is displayed. The location and time of day the advertisement is displayed are considered based on criteria such as geographical information and time characteristics.

[0075] The identification unit identifies advertisements based on the attribute information of the target audience. For example, the identification unit considers the age range of the target audience to identify inappropriate advertisements. The identification unit considers the gender of the target audience to identify inappropriate advertisements. The identification unit considers the interests of the target audience to identify inappropriate advertisements. This allows for more accurate identification by considering the attribute information of the target audience. The attribute information of the target audience is considered based on criteria such as age, gender, and interests.

[0076] The removal unit estimates the user's emotions and adjusts the removal method based on the estimated emotions. For example, if the user is feeling anxious, the removal unit quickly removes inappropriate ads. If the user is excited, the removal unit removes inappropriate ads to encourage calmness. If the user is relaxed, the removal unit removes inappropriate ads to maintain a relaxed state. This allows for more appropriate ad removal by adjusting the removal method according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The removal method is adjusted based on criteria such as emotion scores or parameters of the removal algorithm.

[0077] The removal unit evaluates the scope of impact of inappropriate ads to determine the removal priority. For example, the removal unit evaluates the scope of impact of ads and prioritizes the removal of ads that have a wide-ranging impact. The removal unit evaluates the scope of impact of ads and prioritizes the removal of ads that affect specific target audiences. The removal unit evaluates the scope of impact of ads and prioritizes the removal of ads with a significant impact. This allows for the priority removal of ads with a significant impact by evaluating the scope of impact. The scope of impact of ads is evaluated based on criteria such as the number of affected users and the severity of the impact.

[0078] The removal unit optimizes how advertisers are notified when inappropriate ads are removed. For example, the removal unit optimizes how advertisers are notified to quickly notify them of the removal of inappropriate ads. The removal unit optimizes how advertisers are notified to include detailed reasons. The removal unit optimizes how advertisers are notified to propose measures to prevent recurrence. This optimizes how advertisers are notified to quickly and thoroughly. The notification method is optimized based on criteria such as the timing and format of the notification.

[0079] The removal unit estimates the user's emotions and determines the priority of ads to remove based on the estimated emotions. For example, if the user is feeling anxious, the removal unit prioritizes removing inappropriate ads to provide reassurance. If the user is excited, the removal unit prioritizes removing inappropriate ads to promote calmness. If the user is relaxed, the removal unit prioritizes removing inappropriate ads to maintain a relaxed state. This allows for more appropriate ad removal by determining the priority of ad removal according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The priority of ad removal is determined by criteria such as emotion score or ad impact.

[0080] The removal unit applies different removal methods to each advertising platform when removing inappropriate ads. For example, the removal unit applies different removal methods to each advertising platform to quickly remove inappropriate ads. The removal unit applies different removal methods to each advertising platform to remove inappropriate ads in the most optimal way. The removal unit applies different removal methods to each advertising platform to effectively remove inappropriate ads. This enables rapid and optimal ad removal by applying different removal methods to each advertising platform. The removal methods are applied based on criteria such as platform-specific characteristics and removal algorithms.

[0081] The removal unit saves relevant data about inappropriate advertisements when they are removed for future analysis. For example, the removal unit saves relevant data about inappropriate advertisements for future analysis. The removal unit saves relevant data about inappropriate advertisements for use in formulating measures to prevent recurrence. The removal unit saves relevant data about inappropriate advertisements for use in analyzing advertiser behavior patterns. This allows the saving of relevant data about advertisements to be used for future analysis and the formulation of measures to prevent recurrence. The relevant data is saved according to criteria such as the database structure and data storage format.

[0082] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0083] The analytics unit can adjust its analysis methods when analyzing ad images, text, and links, taking into account the user's browsing history. For example, it can analyze the trends of ads the user has viewed in the past and prioritize the analysis of ads with similar trends. The analytics unit can learn the characteristics of ads that the user has found offensive in the past and focus its analysis on ads with those characteristics. The analytics unit can also analyze relevant ads in detail, taking into account the content of ads the user has shown interest in in the past. By adjusting the analysis method based on the user's browsing history, it becomes possible to perform ad analysis that is more tailored to the user.

[0084] The identification unit can adjust its identification criteria when identifying ad content, taking into account the frequency of ad display. For example, if a particular ad is displayed frequently in a short period, it will focus on identifying that ad. If an ad is displayed frequently, the identification unit will determine that it is likely to be fraudulent or contain inappropriate content and will identify it in detail. Even if an ad is displayed infrequently, the identification unit will adjust its identification criteria by referring to past identification results. This allows for more effective ad identification by adjusting the identification criteria according to the frequency of ad display.

[0085] The removal unit can evaluate the impact of inappropriate advertisements and determine the priority of removal. For example, if an advertisement has a high impact, it will be removed first. The removal unit evaluates the impact of advertisements and focuses on removing advertisements that have a significant impact on specific target audiences. The removal unit evaluates the impact of advertisements and quickly removes advertisements that have a wide-ranging impact. By determining the priority of removal based on the impact of advertisements, more effective ad removal becomes possible.

[0086] The analysis unit can detect inappropriate content by analyzing the movement of objects within an image during image analysis of an advertisement. For example, it can analyze the movement of objects in an advertisement image and determine that an image containing violent movements is inappropriate. The analysis unit can analyze the movement of objects in an advertisement image and determine that an image containing sexual movements is inappropriate. The analysis unit can analyze the movement of objects in an advertisement image and determine that an image containing excessively stimulating movements is inappropriate. In this way, inappropriate content can be effectively detected by analyzing the movement of objects within an image.

[0087] The identification unit can identify advertisements based on the attribute information of the target audience. For example, it can identify inappropriate advertisements by considering the age range of the target audience. The identification unit can identify inappropriate advertisements by considering the gender of the target audience. The identification unit can identify inappropriate advertisements by considering the interests of the target audience. This allows for more accurate identification by considering the attribute information of the target audience.

[0088] The analytics unit can estimate the user's emotions and adjust the analysis methods for ad images, text, and links based on those estimated emotions. For example, if the user is feeling anxious, the analytics unit will prioritize analyzing elements that provide a sense of security in the ad's image analysis. If the user is excited, the analytics unit will focus on analyzing content that promotes calmness in the ad's text analysis. If the user is relaxed, the analytics unit will prioritize analyzing content that helps maintain that relaxed state in the ad's link analysis. By adjusting the analysis method according to the user's emotions, more appropriate ad analysis becomes possible.

[0089] The identification unit can estimate the user's emotions and adjust the identification criteria based on those emotions. For example, if the user is feeling anxious, it will prioritize identifying advertisements that provide a sense of security. If the user is excited, it will prioritize identifying advertisements that promote calmness. If the user is relaxed, it will prioritize identifying advertisements that maintain a relaxed state. By adjusting the identification criteria according to the user's emotions, more appropriate advertisement identification becomes possible.

[0090] The removal unit can estimate the user's emotions and adjust the removal method based on those emotions. For example, if the user is feeling anxious, it will quickly remove inappropriate ads. If the user is excited, the removal unit will remove inappropriate ads to encourage calmness. If the user is relaxed, the removal unit will remove inappropriate ads to maintain that relaxed state. This allows for more appropriate ad removal by adjusting the removal method according to the user's emotions.

[0091] The analytics unit can estimate the user's emotions and determine the priority of ads to analyze based on those estimated emotions. For example, if a user is feeling anxious, it will prioritize ads that provide a sense of security. If a user is excited, the analytics unit will prioritize ads that promote calmness. If a user is relaxed, the analytics unit will prioritize ads that maintain that relaxed state. By prioritizing ads according to the user's emotions, more appropriate ad analysis becomes possible.

[0092] The identification unit can estimate the user's emotions and adjust the display method of the identification results based on the estimated emotions. For example, if the user is feeling anxious, it provides a display method that provides a sense of security. If the user is excited, it provides a display method that encourages calmness. If the user is relaxed, it provides a display method that maintains a relaxed state. By adjusting the display method of the identification results according to the user's emotions, a more appropriate display becomes possible.

[0093] The following briefly describes the processing flow for example form 2.

[0094] Step 1: The analysis unit analyzes the ad's image, text, and destination. For example, the analysis unit analyzes the ad's image and recognizes objects within the image. The analysis unit analyzes the ad's text and analyzes the context and linguistic patterns of the text. The analysis unit analyzes the ad's destination and evaluates the reliability of the destination domain. Step 2: The identification unit identifies fraudulent or inappropriate content based on the ad content analyzed by the analysis unit. For example, the identification unit determines that images containing violent scenes are inappropriate based on the image analysis results of the ad. The identification unit identifies potentially fraudulent content based on the text analysis results of the ad. The identification unit identifies unreliable links based on the destination analysis results of the ad. Step 3: The removal unit removes the inappropriate advertisements identified by the identification unit. For example, the removal unit quickly deletes inappropriate advertisements. The removal unit blocks inappropriate advertisements. The removal unit stops displaying inappropriate advertisements.

[0095] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0096] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0097] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0098] Each of the multiple elements described above, including the analysis unit, identification unit, and removal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and analyzes the image, text, and link destination of the advertisement. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies fraudulent or inappropriate content based on the analyzed advertisement content. The removal unit is implemented by the control unit 46A of the smart device 14 and removes the identified inappropriate advertisement. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0099] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0100] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0101] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0102] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0103] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0104] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0105] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0106] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0107] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0108] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0109] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0110] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0113] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements described above, including the analysis unit, identification unit, and removal unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes the image, text, and link destination of the advertisement. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies fraudulent or inappropriate content based on the analyzed advertisement content. The removal unit is implemented by the control unit 46A of the smart glasses 214 and removes the identified inappropriate advertisement. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0115] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0116] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0127] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0129] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements, including the analysis unit, identification unit, and removal unit described above, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes the image, text, and link destination of the advertisement. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies fraudulent or inappropriate content based on the analyzed advertisement content. The removal unit is implemented by the control unit 46A of the headset terminal 314 and removes the identified inappropriate advertisement. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0131] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0132] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0139] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0140] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0141] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0142] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0144] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0147] Each of the multiple elements, including the analysis unit, identification unit, and removal unit described above, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and analyzes the image, text, and link destination of the advertisement. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies fraudulent or inappropriate content based on the analyzed advertisement content. The removal unit is implemented by the control unit 46A of the robot 414 and removes the identified inappropriate advertisement. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

[0149] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0150] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0151] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0152] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

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

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

[0155] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

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

[0157] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0158] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0159] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

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

[0161] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0162] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0163] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0164] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0165] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0166] (Note 1) An analysis unit that analyzes the images, text, and links in advertisements, An identification unit that identifies fraudulent or inappropriate content based on the advertising content analyzed by the aforementioned analysis unit, The system includes a removal unit that removes inappropriate advertisements identified by the identification unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Includes image and text analysis techniques using deep learning. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned identification unit is Includes a system that monitors ad content in real time. The system described in Appendix 1, characterized by the features described herein. (Note 4) The removal section is, Includes malicious link detection and blocking features. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit, We estimate the user's emotions and adjust the analysis of ad images, text, and landing pages based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, When analyzing images in advertisements, the color tone and composition of the images are analyzed to detect inappropriate content. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, When analyzing ad text, we analyze the text context and language patterns to assess the likelihood of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, It estimates user sentiment and determines ad prioritization based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, When analyzing the destination of an ad link, the trustworthiness of the linked domain is evaluated and reflected in the analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, When analyzing images in advertisements, object recognition technology within the images is used to detect inappropriate content. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned identification unit is We estimate the user's emotions and adjust the identification criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned identification unit is When identifying ad content, we improve identification accuracy by referring to past identification results. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned identification unit is When identifying ad content, the system uses the advertiser's past behavioral history for identification. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned identification unit is It estimates the user's emotions and adjusts how the identification results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned identification unit is When identifying ad content, the location and time of day the ad is displayed are taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned identification unit is When identifying ad content, the identification is performed based on the attribute information of the ad's target audience. The system described in Appendix 1, characterized by the features described herein. (Note 17) The removal section is, The system estimates the user's emotions and adjusts the removal method based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The removal section is, When removing inappropriate ads, the scope of the ad's impact is evaluated to determine the priority of removal. The system described in Appendix 1, characterized by the features described herein. (Note 19) The removal section is, Optimize how advertisers are notified when inappropriate ads are removed. The system described in Appendix 1, characterized by the features described herein. (Note 20) The removal section is, It estimates the user's emotions and determines the priority of ads to remove based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The removal section is, When removing inappropriate ads, different removal methods are applied depending on the ad display platform. The system described in Appendix 1, characterized by the features described herein. (Note 22) The removal section is, When removing inappropriate ads, the associated data is saved and used for future analysis. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes the images, text, and links in advertisements, An identification unit that identifies fraudulent or inappropriate content based on the advertising content analyzed by the aforementioned analysis unit, The system includes a removal unit that removes inappropriate advertisements identified by the identification unit. A system characterized by the following features.

2. The aforementioned analysis unit, Includes image and text analysis techniques using deep learning. The system according to feature 1.

3. The aforementioned identification unit is Includes a system that monitors ad content in real time. The system according to feature 1.

4. The removal section is, Includes malicious link detection and blocking features. The system according to feature 1.

5. The aforementioned analysis unit, We estimate the user's emotions and adjust the analysis of ad images, text, and landing pages based on those estimated emotions. The system according to feature 1.

6. The aforementioned analysis unit, When analyzing images in advertisements, the color tone and composition of the images are analyzed to detect inappropriate content. The system according to feature 1.

7. The aforementioned analysis unit, When analyzing ad text, we analyze the text context and language patterns to assess the likelihood of fraud. The system according to feature 1.

8. The aforementioned analysis unit, It estimates user sentiment and determines ad prioritization based on that estimated sentiment. The system according to feature 1.

9. The aforementioned analysis unit, When analyzing the destination of an ad link, the trustworthiness of the linked domain is evaluated and reflected in the analysis results. The system according to feature 1.

10. The aforementioned analysis unit, When analyzing images in advertisements, object recognition technology within the images is used to detect inappropriate content. The system according to feature 1.

Images