system

Abstract

The system according to this embodiment aims to detect and block harmful content on social media in real time. [Solution] The system according to the embodiment comprises a detection unit, a blocking unit, a development unit, and an interface unit. The detection unit detects harmful content on social networking services (SNS) in real time. The blocking unit blocks the harmful content detected by the detection unit. The development unit develops filtering agents specific to each SNS platform. The interface unit provides an interface for parents to use the system.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [[ID=第十三条]]

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, it is difficult to detect and block harmful content on SNS in real time, and there is room for improvement to protect children from online risks.

[0005] The system according to the embodiment aims to detect and block harmful content on SNS in real time.

Means for Solving the Problems

[0006] ]> The system according to this embodiment comprises a detection unit, a blocking unit, a development unit, and an interface unit. The detection unit detects harmful content on social networking services (SNS) in real time. The blocking unit blocks the harmful content detected by the detection unit. The development unit develops filtering agents specific to each SNS platform. The interface unit provides an interface for parents to use the system. [Effects of the Invention]

[0007] The system according to this embodiment can detect and block harmful content on social media in real time. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The SNS filtering AI agent system according to an embodiment of the present invention is a system for protecting children from harmful content and comments on social networking services (SNS). This system detects harmful text, images, and videos on SNS in real time and immediately blocks them, preventing children from encountering them. Furthermore, filtering agents specialized for each SNS platform are developed, and optimal filtering is implemented according to the characteristics of each platform. For example, if a certain SNS platform tends to have a high volume of offensive comments, the filtering agent specialized for that platform will detect and block offensive comments in real time. Similarly, if another platform sees a high volume of inappropriate images and videos being posted, the filtering agent specialized for that platform will detect and block inappropriate images and videos in real time. In this way, children can use SNS in a safe online environment, and parents can confidently monitor their children's internet use. Moreover, it contributes to improving the overall health of SNS platforms. As a result, the SNS filtering AI agent system can protect children from harmful content and comments on SNS.

[0029] The SNS filtering AI agent system according to this embodiment comprises a detection unit, a blocking unit, a development unit, and an interface unit. The detection unit detects harmful content on SNS in real time. The detection unit detects harmful text using, for example, natural language processing technology. The detection unit can also detect harmful images using image recognition technology. Furthermore, the detection unit can also detect harmful videos using video analysis technology. For example, the detection unit uses natural language processing technology to detect text containing offensive comments or discriminatory remarks. It uses image recognition technology to detect images containing violence or pornography. It uses video analysis technology to detect videos containing violent acts or inappropriate content. The blocking unit immediately blocks the harmful content detected by the detection unit. The blocking unit blocks harmful content by, for example, applying filtering rules. Furthermore, the blocking unit can adjust the strength of the block based on user settings. Furthermore, the blocking unit has high-speed processing capability to block harmful content in real time. For example, the blocking unit applies filtering rules to immediately block offensive comments and inappropriate images. It adjusts the strength of the block based on user settings and performs strict filtering as needed. The high-speed blocking unit blocks harmful content in real time. The development unit develops filtering agents specialized for each SNS platform. For example, the development unit analyzes the characteristics of each platform and develops the optimal filtering agent based on that analysis. The development unit can also evaluate the performance of the filtering agents and make improvements as needed. Furthermore, the development unit has the capability to rapidly develop filtering agents to support new SNS platforms. For example, the development unit analyzes the characteristics of each platform and develops filtering agents specialized for platforms where offensive comments are frequent. They evaluate the performance of the filtering agents and make improvements as needed. They rapidly develop filtering agents to support new SNS platforms.The interface unit provides a user-friendly interface for parents to use the system. For example, the interface unit provides an intuitive user interface. The interface unit can also provide a guide to help parents easily configure the system. Furthermore, the interface unit has a function to visually display system usage and filtering results. For example, the interface unit provides an intuitive user interface, making it easy for parents to operate the system. It provides a guide to make system configuration easy. It visually displays system usage and filtering results, allowing parents to confirm the system's effectiveness. As a result, the SNS filtering AI agent system according to this embodiment can protect children from harmful content and comments on social media.

[0030] The detection unit detects harmful content on social media in real time. Specifically, it uses natural language processing technology to detect harmful text. Natural language processing technology includes tokenization, morphological analysis, grammatical analysis, and semantic analysis to analyze the meaning of text. This enables high-precision detection of text containing offensive comments or discriminatory remarks. For example, it can not only detect specific keywords or phrases but also understand the context to identify remarks with harmful intent. It can also detect harmful images using image recognition technology. Image recognition technology includes convolutional neural networks (CNNs) to extract and classify features in images. This enables high-precision detection of images containing violence or pornography. For example, it can identify specific patterns or objects in an image and determine whether they contain harmful content. It can also detect harmful videos using video analysis technology. Video analysis technology includes recurrent neural networks (RNNs) and long-term short-term memory (LSTMs) to extract and analyze features frame by frame of a video. This enables high-precision detection of videos containing violent acts or inappropriate content. For example, it can analyze the movement and sound in a video and determine whether it contains harmful content. This allows the detection unit to analyze various types of content, including text, images, and videos, in real time and quickly detect harmful content.

[0031] The blocking unit immediately blocks harmful content detected by the detection unit. Specifically, it blocks harmful content by applying filtering rules. Filtering rules include specific keywords or phrases, image features, and video content. This allows for the immediate blocking of offensive comments and inappropriate images. The strength of the blocking can also be adjusted based on user settings. For example, parents can choose to perform strict filtering or allow for a certain degree of tolerance, depending on the filtering level they have set. The blocking unit has high-speed processing capabilities to block harmful content in real time. This prevents the spread of harmful content on social media and protects users. Furthermore, the blocking unit can collect user feedback and continuously improve the accuracy and effectiveness of the filtering rules. For example, if a user objects to blocked content, the filtering rules are reviewed and adjusted as needed based on that feedback. This allows the blocking unit to provide flexible filtering tailored to user needs and improve the overall reliability and effectiveness of the system.

[0032] The development department develops filtering agents specifically tailored to each social networking service (SNS) platform. Specifically, they analyze the characteristics of each platform and develop the optimal filtering agent based on that analysis. For example, because certain SNS platforms tend to have a high concentration of specific types of harmful content, they develop a filtering agent specifically for that platform. The development department can also evaluate the performance of the filtering agents and make improvements as needed. Performance evaluation includes detection accuracy, processing speed, and user feedback. This allows for continuous improvement of the filtering agent's performance. Furthermore, the development department has the capability to rapidly develop filtering agents to support new SNS platforms. For example, by quickly developing and deploying filtering agents for newly emerging SNS platforms, they can protect users from harmful content. This allows the development department to provide high-performance filtering agents tailored to each SNS platform, maximizing the overall system effectiveness.

[0033] The interface unit provides a user-friendly interface for parents to use the system. Specifically, it provides an intuitive user interface. For example, it provides a simple and easy-to-understand menu structure and operation guide so that parents can easily configure the system. The interface unit can also provide guides to help parents easily configure the system. For example, it provides a step-by-step configuration guide and FAQ for parents using the system for the first time. Furthermore, the interface unit has a function to visually display the system usage status and filtering results. For example, it can display the type and number of filtered content and the list of blocked users in graphs and charts, so that parents can see the effectiveness of the system at a glance. In this way, the interface unit can support parents in easily operating and effectively using the system. In addition, the interface unit can collect user feedback and continuously improve the usability and functionality of the interface. For example, it can review the interface design and functions based on requests and opinions from parents and make improvements as needed. In this way, the interface unit can provide a user-friendly interface and improve the overall usability and effectiveness of the system.

[0034] The algorithm section implements specific filtering methods and algorithms. For example, the algorithm section can implement keyword filtering. Keyword filtering is a method of detecting and blocking content containing specific keywords. The algorithm section can also implement image recognition filtering. Image recognition filtering is a method of detecting and blocking harmful images. Furthermore, the algorithm section can also implement machine learning algorithms. Machine learning algorithms are methods of detecting harmful content with high accuracy by learning from large amounts of data. For example, the algorithm section can implement keyword filtering to detect and block offensive comments containing specific keywords. It can implement image recognition filtering to detect and block images containing violence or pornography. It can implement machine learning algorithms to detect harmful content with high accuracy by learning from large amounts of data. In this way, the accuracy of filtering is improved by implementing specific filtering methods and algorithms.

[0035] The Platform Specialization Department develops filtering agents specialized for each platform. For example, the Platform Specialization Department develops filtering agents using the API of a specific SNS platform. It analyzes the characteristics of a specific platform and develops the optimal filtering agent based on that analysis. The Platform Specialization Department can also develop filtering agents considering the user base and posting trends of each platform. Furthermore, the Platform Specialization Department can develop filtering agents considering the technical constraints of each platform. For example, the Platform Specialization Department uses the API of a specific SNS platform to develop a filtering agent specialized for a platform where aggressive comments are frequent. It analyzes the characteristics of a specific platform and develops the optimal filtering agent based on that analysis. It develops filtering agents considering the user base and posting trends of each platform. It develops filtering agents considering the technical constraints of each platform. By developing filtering agents specialized for each platform, optimal filtering according to the characteristics of each platform becomes possible. Some or all of the above processing in the Platform Specialization Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Platform Specialization Department can input the characteristics of a specific platform into a generative AI and have the generative AI develop the optimal filtering agent.

[0036] The User Guide Department provides guidance for parents to use the system. For example, the User Guide Department provides an operation manual. The operation manual explains the basic operation methods of the system. The User Guide Department may also provide an FAQ. The FAQ is a collection of frequently asked questions and their answers. Furthermore, the User Guide Department may provide video tutorials. Video tutorials visually explain how to use the system. For example, the User Guide Department provides an operation manual so that parents can understand the basic operation methods of the system. It provides an FAQ, which provides a collection of frequently asked questions and their answers. It provides video tutorials, which visually explain how to use the system. This makes it easier for parents to use the system by providing guidance for them to use the system. Some or all of the above processes in the User Guide Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the User Guide Department can input a parent's question into a generative AI and have the generative AI generate the best answer.

[0037] The detection unit can detect harmful text, images, and videos on social media in real time. For example, the detection unit can detect harmful text using natural language processing technology. For instance, it can detect text containing offensive comments or discriminatory remarks. The detection unit can also detect harmful images using image recognition technology. For example, it can detect images containing violence or pornography. Furthermore, the detection unit can detect harmful videos using video analysis technology. For example, it can detect videos containing violent acts or inappropriate content. This allows for the detection of harmful text, images, and videos on social media in real time, protecting children from harmful content. Some or all of the above-described processes in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input text, images, and videos from social media into a generative AI and have the generative AI perform the detection of harmful content.

[0038] The blocking unit can immediately block harmful content detected by the detection unit. The blocking unit blocks harmful content by, for example, applying filtering rules. For example, the blocking unit can immediately block offensive comments or inappropriate images. The blocking unit can also adjust the strength of the blocking based on user settings. For example, the blocking unit can perform strict filtering as needed based on user settings. Furthermore, the blocking unit has high-speed processing capabilities to block harmful content in real time. For example, the blocking unit has high-speed processing capabilities and can block harmful content in real time. This prevents children from being exposed to harmful content by immediately blocking detected harmful content. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input detected harmful content into a generative AI and leave the blocking to the generative AI.

[0039] The development department can develop filtering agents specialized for each SNS platform. For example, the development department can analyze the characteristics of each platform and develop the optimal filtering agent based on that analysis. For example, the development department can develop a filtering agent specialized for platforms where aggressive comments are frequent. The development department can also evaluate the performance of the filtering agents and make improvements as needed. For example, the development department can evaluate the performance of the filtering agents and make improvements as needed. Furthermore, the development department has the capability to rapidly develop filtering agents to support new SNS platforms. For example, the development department can rapidly develop filtering agents to support new SNS platforms. This enables optimal filtering tailored to the characteristics of each platform by developing filtering agents specialized for each SNS platform. Some or all of the above processes performed by the development department may be carried out using, for example, generative AI, or not using generative AI. For example, the development department can input the characteristics of each platform into a generative AI and have the generative AI develop the optimal filtering agent.

[0040] The interface unit can provide a user-friendly interface for parents to use the system. For example, the interface unit can provide an intuitive user interface. For example, the interface unit can make it easy for parents to operate the system. The interface unit can also provide a guide to make it easy for parents to configure the system. For example, the interface unit can provide a guide to make it easy to configure the system. Furthermore, the interface unit has a function to visually display the system usage status and filtering results. For example, the interface unit can visually display the system usage status and filtering results so that parents can check the effectiveness of the system. This makes it easier for parents to use the system by providing a user-friendly interface. Some or all of the above processing in the interface unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the interface unit can input the parent's operations into the generative AI and have the generative AI provide the optimal interface.

[0041] The detection unit can optimize its detection algorithm by referring to patterns of past harmful content. For example, the detection unit can refer to a database of previously detected harmful content. For example, the detection unit can refer to a database of previously detected harmful content and prioritize the detection of content with similar patterns. The detection unit can also learn patterns of past harmful content to improve the detection accuracy of new harmful content. For example, the detection unit can learn patterns of past harmful content to improve the detection accuracy of new harmful content. Furthermore, the detection unit can adjust its detection algorithm in real time based on patterns of past harmful content to perform optimal filtering. For example, the detection unit adjusts its detection algorithm in real time based on patterns of past harmful content to perform optimal filtering. This improves the accuracy of the detection algorithm by referring to patterns of past harmful content. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input data of past harmful content into a generative AI and have the generative AI perform the optimization of the detection algorithm.

[0042] The detection unit can improve detection accuracy by considering the attribute information of the content's poster. For example, the detection unit considers attribute information such as the content's poster's age and gender. For example, the detection unit can improve the detection accuracy of harmful content by considering attribute information such as the content's poster's age and gender. The detection unit can also refer to the poster's past posting history and prioritize the detection of content from posters with specific attributes. For example, the detection unit refers to the poster's past posting history and prioritizes the detection of content from posters with specific attributes. Furthermore, the detection unit can detect and filter content from posters with specific attributes in real time based on the poster's attribute information. For example, the detection unit detects and filters content from posters with specific attributes in real time based on the poster's attribute information. This improves detection accuracy by considering the attribute information of the content's poster. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input the poster's attribute information into a generative AI and have the generative AI perform the improvement of detection accuracy.

[0043] The detection unit can improve detection accuracy by considering the geographical distribution of content. For example, the detection unit considers the location where the content is posted. For example, the detection unit can consider the location where the content is posted and prioritize the detection of harmful content that frequently occurs in a particular area. The detection unit can also improve the detection accuracy of harmful content in a particular area based on geographical distribution. For example, the detection unit can improve the detection accuracy of harmful content in a particular area based on geographical distribution. Furthermore, the detection unit can analyze geographical distribution in real time and quickly detect harmful content in a particular area. For example, the detection unit analyzes geographical distribution in real time and quickly detects harmful content in a particular area. This improves detection accuracy by considering the geographical distribution of content. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input geographical distribution data of the content into a generative AI and have the generative AI perform the improvement of detection accuracy.

[0044] The detection unit can improve the accuracy of detecting harmful content by referring to relevant external databases. For example, the detection unit can refer to external databases and learn the latest patterns of harmful content to improve detection accuracy. The detection unit can also adjust its detection algorithm in real time based on information obtained from external databases. For example, the detection unit adjusts its detection algorithm in real time based on information obtained from external databases. Furthermore, the detection unit can use external databases to improve the accuracy of detecting specific harmful content. For example, the detection unit uses external databases to improve the accuracy of detecting specific harmful content. This improves detection accuracy by referring to relevant external databases. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input information from external databases into a generative AI and have the generative AI perform the improvement of detection accuracy.

[0045] The blocking unit can optimize its blocking algorithm by referring to past blocking history. For example, the blocking unit can refer to past blocking history and prioritize blocking content with similar patterns. The blocking unit can also learn from past blocking history to improve the accuracy of blocking new harmful content. For example, the blocking unit can learn from past blocking history to improve the accuracy of blocking new harmful content. Furthermore, the blocking unit can adjust its blocking algorithm in real time based on past blocking history to perform optimal filtering. For example, the blocking unit adjusts its blocking algorithm in real time based on past blocking history to perform optimal filtering. This improves the accuracy of the blocking algorithm by referring to past blocking history. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input past blocking history data into a generative AI and have the generative AI perform the optimization of the blocking algorithm.

[0046] The blocking unit can determine the priority of blocking by considering the impact of the content. For example, the blocking unit can evaluate the impact of the content. For example, the blocking unit can evaluate the impact of the content and prioritize blocking content with a high impact. The blocking unit can also quickly block content with a high impact to minimize the impact on users. For example, the blocking unit can quickly block content with a high impact to minimize the impact on users. Furthermore, the blocking unit can adjust the priority of blocking in real time based on the impact evaluation. For example, the blocking unit adjusts the priority of blocking in real time based on the impact evaluation. This improves the priority of blocking by considering the impact of the content. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the blocking unit can input content impact data into a generative AI and have the generative AI determine the priority of blocking.

[0047] The blocking unit can improve its blocking accuracy by considering the attribute information of the content creator. For example, the blocking unit considers attribute information such as the age and gender of the content creator. For example, the blocking unit can improve the accuracy of blocking harmful content by considering attribute information such as the age and gender of the content creator. The blocking unit can also refer to the creator's past posting history and preferentially block content from creators with specific attributes. For example, the blocking unit refers to the creator's past posting history and preferentially blocks content from creators with specific attributes. Furthermore, the blocking unit can block and filter content from creators with specific attributes in real time based on the creator's attribute information. For example, the blocking unit blocks and filters content from creators with specific attributes in real time based on the creator's attribute information. This improves blocking accuracy by considering the attribute information of the content creator. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input the creator's attribute information into a generative AI and have the generative AI perform the improvement of blocking accuracy.

[0048] The blocking unit can improve blocking accuracy by referring to relevant external databases. For example, the blocking unit can refer to external databases and learn the latest patterns of harmful content to improve blocking accuracy. The blocking unit can also adjust its blocking algorithm in real time based on information obtained from external databases. For example, the blocking unit adjusts its blocking algorithm in real time based on information obtained from external databases. Furthermore, the blocking unit can use external databases to improve the blocking accuracy of specific harmful content. For example, the blocking unit uses external databases to improve the blocking accuracy of specific harmful content. This improves blocking accuracy by referring to relevant external databases. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input information from external databases into a generative AI and have the generative AI perform the improvement of blocking accuracy.

[0049] The development department can develop the optimal filtering agent by thoroughly analyzing the characteristics of each SNS platform. For example, the development department can analyze the characteristics of each platform. For example, the development department can analyze the characteristics of each platform in detail and develop the optimal filtering agent for a specific platform. The development department can also develop filtering agents by considering the user base and posting trends of each platform. For example, the development department can develop filtering agents by considering the user base and posting trends of each platform. Furthermore, the development department can develop filtering agents by considering the technical constraints of each platform. For example, the development department can develop filtering agents by considering the technical constraints of each platform. In this way, by thoroughly analyzing the characteristics of each SNS platform, it becomes possible to develop the optimal filtering agent. Some or all of the above processing by the development department may be performed using, for example, a generative AI, or not using a generative AI. For example, the development department can input characteristic data for each platform into a generative AI and have the generative AI develop the optimal filtering agent.

[0050] The development department can optimize the development algorithm by referring to past filtering agent performance data. For example, the development department can refer to past filtering agent performance data and prioritize the development of agents with similar patterns. The development department can also learn from past performance data to improve the accuracy of developing new filtering agents. For example, the development department can learn from past performance data to improve the accuracy of developing new filtering agents. Furthermore, the development department can adjust the development algorithm in real time based on past performance data to develop the optimal filtering agent. For example, the development department adjusts the development algorithm in real time based on past performance data to develop the optimal filtering agent. This improves the accuracy of the development algorithm by referring to past filtering agent performance data. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input past performance data into generative AI and have the generative AI perform the optimization of the development algorithm.

[0051] The development department can develop filtering agents by considering the user attribute information of each SNS platform. For example, the development department can consider the user attribute information of each platform. For example, the development department can analyze the user attribute information of each platform in detail and develop a filtering agent that is optimal for a specific user segment. The development department can also develop an optimal filtering agent for users with specific attributes based on the user attribute information. For example, the development department can develop an optimal filtering agent for users with specific attributes based on the user attribute information. Furthermore, the development department can analyze the user attribute information in real time and develop an optimal filtering agent for users with specific attributes. For example, the development department can analyze the user attribute information in real time and develop an optimal filtering agent for users with specific attributes. This makes it possible to develop an optimal filtering agent by considering the user attribute information of each SNS platform. Some or all of the above processing by the development department may be performed using, for example, a generative AI, or not using a generative AI. For example, the development department can input user attribute information into a generative AI and have the generative AI develop an optimal filtering agent.

[0052] The development department can improve the accuracy of filtering agent development by referring to relevant external databases. For example, the development department can refer to external databases to learn the latest patterns of harmful content and improve the accuracy of filtering agent development. The development department can also adjust the development algorithm in real time based on information obtained from external databases. For example, the development department adjusts the development algorithm in real time based on information obtained from external databases. Furthermore, the development department can use external databases to improve the accuracy of filtering agents for specific harmful content. For example, the development department uses external databases to improve the accuracy of filtering agents for specific harmful content. This improves the accuracy of filtering agent development by referring to relevant external databases. Some or all of the above processes in the development department may be performed using, for example, a generative AI, or not using a generative AI. For example, the development department can input information from external databases into a generative AI and have the generative AI perform the improvement of development accuracy.

[0053] The interface unit can select the optimal display method by referring to the user's past operation history. For example, the interface unit can refer to the user's past operation history and prioritize the display of frequently used functions. The interface unit can also provide the user with a preferred display method based on the past operation history. For example, the interface unit can provide the user with a preferred display method based on the past operation history. Furthermore, the interface unit can analyze the past operation history in real time and select the optimal display method. For example, the interface unit analyzes the past operation history in real time and selects the optimal display method. This ensures that the optimal display method is provided by referring to the user's past operation history. Some or all of the above processing in the interface unit may be performed using, for example, a generation AI, or without a generation AI. For example, the interface unit can input past operation history data into a generation AI and have the generation AI select the optimal display method.

[0054] The interface unit can customize the displayed content by considering the user's attribute information. For example, the interface unit can consider the user's attribute information such as age and gender. For example, the interface unit can consider the user's attribute information such as age and gender and provide optimal displayed content. The interface unit can also provide customized displayed content for users with specific attributes based on the user's attribute information. For example, the interface unit can provide customized displayed content for users with specific attributes based on the user's attribute information. Furthermore, the interface unit can analyze the user's attribute information in real time and provide optimal displayed content. For example, the interface unit analyzes the user's attribute information in real time and provides optimal displayed content. As a result, by considering the user's attribute information, the displayed content is customized, and a more appropriate interface is provided. Some or all of the above processing in the interface unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the interface unit can input the user's attribute information into a generative AI and have the generative AI perform the customization of the displayed content.

[0055] The interface unit can select the optimal display method by considering the user's device information. For example, the interface unit can consider the user's device information. For example, if the user is using a smartphone, the interface unit can provide a display method that matches the screen size. Also, if the user is using a tablet, the interface unit can provide a display method optimized for a larger screen. For example, if the user is using a tablet, the interface unit can provide a display method optimized for a larger screen. Furthermore, if the user is using a smartwatch, the interface unit can provide a concise and highly visible display method. For example, if the user is using a smartwatch, the interface unit can provide a concise and highly visible display method. In this way, the optimal display method is provided by considering the user's device information. Some or all of the above processing in the interface unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interface unit can input the user's device information into a generative AI and have the generative AI select the optimal display method.

[0056] The interface unit can customize the displayed content by referring to a related external database. For example, the interface unit can refer to an external database and customize the displayed content based on the latest information. The interface unit can also adjust the displayed content in real time based on information obtained from the external database. For example, the interface unit adjusts the displayed content in real time based on information obtained from the external database. Furthermore, the interface unit can use the external database to provide the most suitable displayed content for a specific user. For example, the interface unit uses the external database to provide the most suitable displayed content for a specific user. As a result, by referring to a related external database, the displayed content is customized, and a more appropriate interface is provided. Some or all of the above processing in the interface unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interface unit can input information from the external database into a generative AI and have the generative AI perform the customization of the displayed content.

[0057] The algorithm unit can optimize its algorithm by referring to past filtering data. For example, the algorithm unit can refer to past filtering data and prioritize filtering content with similar patterns. The algorithm unit can also learn from past filtering data to improve the accuracy of filtering new harmful content. For example, the algorithm unit can learn from past filtering data to improve the accuracy of filtering new harmful content. Furthermore, the algorithm unit can adjust the algorithm in real time based on past filtering data to perform optimal filtering. For example, the algorithm unit adjusts the algorithm in real time based on past filtering data to perform optimal filtering. This improves the accuracy of the algorithm by referring to past filtering data. Some or all of the above processing in the algorithm unit may be performed using, for example, a generative AI, or without a generative AI. For example, the algorithm unit can input past filtering data into a generative AI and have the generative AI perform algorithm optimization.

[0058] The algorithm unit can customize the algorithm by taking into account the characteristics of each SNS platform. For example, the algorithm unit can analyze the characteristics of each platform. For example, the algorithm unit can analyze the characteristics of each platform in detail and implement an algorithm that is optimal for a particular platform. The algorithm unit can also implement the algorithm by taking into account the user base and posting trends of each platform. For example, the algorithm unit implements the algorithm by taking into account the user base and posting trends of each platform. Furthermore, the algorithm unit can implement the algorithm by taking into account the technical constraints of each platform. For example, the algorithm unit implements the algorithm by taking into account the technical constraints of each platform. This makes it possible to implement an optimal algorithm by taking into account the characteristics of each SNS platform. Some or all of the above processing in the algorithm unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the algorithm unit can input characteristic data of each platform into a generative AI and have the generative AI perform the algorithm customization.

[0059] The algorithm unit can improve the accuracy of the algorithm by referring to relevant external databases. For example, the algorithm unit can refer to external databases and learn the latest patterns of harmful content to improve the accuracy of the algorithm. The algorithm unit can also adjust the algorithm in real time based on information obtained from external databases. For example, the algorithm unit adjusts the algorithm in real time based on information obtained from external databases. Furthermore, the algorithm unit can use external databases to improve the accuracy of the algorithm for specific harmful content. For example, the algorithm unit uses external databases to improve the accuracy of the algorithm for specific harmful content. This improves the accuracy of the algorithm by referring to relevant external databases. Some or all of the above processing in the algorithm unit may be performed using, for example, a generative AI, or without a generative AI. For example, the algorithm unit can input information from an external database into a generative AI and have the generative AI perform the algorithm accuracy improvement.

[0060] The algorithm unit can customize the algorithm by considering the user attribute information of each SNS platform. For example, the algorithm unit can consider the user attribute information of each platform. For example, the algorithm unit can analyze the user attribute information of each platform in detail and implement an algorithm that is optimal for a specific user segment. The algorithm unit can also implement an optimal algorithm for users with specific attributes based on the user attribute information. For example, the algorithm unit implements an optimal algorithm for users with specific attributes based on the user attribute information. Furthermore, the algorithm unit can analyze the user attribute information in real time and implement an optimal algorithm for users with specific attributes. For example, the algorithm unit analyzes the user attribute information in real time and implements an optimal algorithm for users with specific attributes. This makes it possible to implement an optimal algorithm by considering the user attribute information of each SNS platform. Some or all of the above processing in the algorithm unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the algorithm unit can input user attribute information into a generative AI and have the generative AI perform the algorithm customization.

[0061] The platform-specific unit can develop the optimal filtering agent by analyzing the characteristics of each platform in detail. For example, the platform-specific unit can analyze the characteristics of each platform and develop the optimal filtering agent for a specific platform. The platform-specific unit can also develop filtering agents by considering the user base and posting trends of each platform. For example, the platform-specific unit can develop filtering agents by considering the user base and posting trends of each platform. Furthermore, the platform-specific unit can also develop filtering agents by considering the technical constraints of each platform. For example, the platform-specific unit can develop filtering agents by considering the technical constraints of each platform. This makes it possible to develop the optimal filtering agent by analyzing the characteristics of each platform in detail. Some or all of the above processing in the platform-specific unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the platform-specific unit can input characteristic data for each platform into a generative AI and have the generative AI develop the optimal filtering agent.

[0062] The platform-specific unit can optimize the development algorithm by referring to past agent performance data. For example, the platform-specific unit can refer to past agent performance data and prioritize the development of agents with similar patterns. The platform-specific unit can also learn from past performance data to improve the accuracy of developing new filtering agents. For example, the platform-specific unit can learn from past performance data to improve the accuracy of developing new filtering agents. Furthermore, the platform-specific unit can adjust the development algorithm in real time based on past performance data to develop the optimal filtering agent. For example, the platform-specific unit adjusts the development algorithm in real time based on past performance data to develop the optimal filtering agent. This improves the accuracy of the development algorithm by referring to past agent performance data. Some or all of the above processing in the platform-specific unit may be performed using, for example, a generative AI, or without a generative AI. For example, the platform-specific unit can input past performance data into a generative AI and have the generative AI perform the optimization of the development algorithm.

[0063] The platform-specific unit can develop agents by considering the user attribute information of each platform. For example, the platform-specific unit can consider the user attribute information of each platform. For example, the platform-specific unit can analyze the user attribute information of each platform in detail and develop a filtering agent that is optimal for a specific user segment. The platform-specific unit can also develop an optimal filtering agent for users with specific attributes based on the user attribute information. For example, the platform-specific unit can develop an optimal filtering agent for users with specific attributes based on the user attribute information. Furthermore, the platform-specific unit can analyze the user attribute information in real time and develop an optimal filtering agent for users with specific attributes. For example, the platform-specific unit analyzes the user attribute information in real time and develops an optimal filtering agent for users with specific attributes. This makes it possible to develop an optimal filtering agent by considering the user attribute information of each platform. Some or all of the above processing in the platform-specific unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the platform-specific unit can input user attribute information into a generative AI and have the generative AI execute the agent development.

[0064] The platform-specific unit can improve the accuracy of agent development by referring to relevant external databases. For example, the platform-specific unit can refer to external databases and learn the latest patterns of harmful content to improve the accuracy of filtering agent development. The platform-specific unit can also adjust the development algorithm in real time based on information obtained from external databases. For example, the platform-specific unit adjusts the development algorithm in real time based on information obtained from external databases. Furthermore, the platform-specific unit can use external databases to improve the accuracy of filtering agents for specific harmful content. For example, the platform-specific unit uses external databases to improve the accuracy of filtering agents for specific harmful content. This improves the accuracy of agent development by referring to relevant external databases. Some or all of the above processing in the platform-specific unit may be performed using, for example, a generative AI, or without a generative AI. For example, the platform-specific unit can input information from external databases into a generative AI and have the generative AI perform the improvement of development accuracy.

[0065] The user guide unit can optimize the guide content by referring to past user feedback. For example, the user guide unit can refer to past user feedback and provide guide content that improves upon frequently pointed-out issues. The user guide unit can also prioritize providing information that users are looking for based on past feedback. For example, the user guide unit prioritizes providing information that users are looking for based on past feedback. Furthermore, the user guide unit can analyze past feedback in real time and provide optimal guide content. For example, the user guide unit analyzes past feedback in real time and provides optimal guide content. This improves the accuracy of the guide content by referring to past user feedback. Some or all of the above processing in the user guide unit may be performed using, for example, a generative AI, or without a generative AI. For example, the user guide unit can input past feedback data into a generative AI and have the generative AI perform the optimization of the guide content.

[0066] The user guide unit can customize the guide content by considering the user's attribute information. For example, the user guide unit can consider the user's attribute information such as age and gender. For example, the user guide unit can consider the user's attribute information such as age and gender to provide optimal guide content. The user guide unit can also provide customized guide content for users with specific attributes based on the user's attribute information. For example, the user guide unit can provide customized guide content for users with specific attributes based on the user's attribute information. Furthermore, the user guide unit can analyze the user's attribute information in real time to provide optimal guide content. For example, the user guide unit can analyze the user's attribute information in real time to provide optimal guide content. As a result, by considering the user's attribute information, the guide content is customized, and a more appropriate guide is provided. Some or all of the above processing in the user guide unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the user guide unit can input the user's attribute information into a generative AI and have the generative AI perform the customization of the guide content.

[0067] The user guide unit can optimize the guide content by referring to relevant external databases. For example, the user guide unit can refer to external databases and optimize the guide content based on the latest information. The user guide unit can also adjust the guide content in real time based on information obtained from external databases. For example, the user guide unit adjusts the guide content in real time based on information obtained from external databases. Furthermore, the user guide unit can use external databases to provide guide content that is optimal for a specific user. For example, the user guide unit uses external databases to provide guide content that is optimal for a specific user. This improves the accuracy of the guide content by referring to relevant external databases. Some or all of the above processing in the user guide unit may be performed using, for example, a generative AI, or without a generative AI. For example, the user guide unit can input information from an external database into a generative AI and have the generative AI perform the optimization of the guide content.

[0068] The user guide unit can customize the guide content by taking into account the user's device information. For example, the user guide unit can take into account the user's device information. For example, if the user is using a smartphone, the user guide unit can provide guide content that is adapted to the screen size. Also, if the user is using a tablet, the user guide unit can provide guide content optimized for a larger screen. Furthermore, if the user is using a smartwatch, the user guide unit can provide concise and highly visible guide content. In this way, by taking into account the user's device information, the guide content is customized, and a more appropriate guide is provided. Some or all of the above processing in the user guide unit may be performed using, for example, a generative AI, or without a generative AI. For example, the user guide unit can input the user's device information into a generative AI and have the generative AI perform the customization of the guide content.

[0069] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0070] The SNS filtering AI agent system can optimize its filtering algorithm by referencing the user's past behavior history. For example, if a user has previously shown a strong reaction to a particular type of harmful content, that type of content can be prioritized for blocking. Furthermore, if a user frequently encounters harmful content during certain time periods, the filtering intensity can be increased during those times. In addition, the system can analyze the user's behavior history in real time and dynamically adjust the filtering algorithm. This enables optimal filtering based on user behavior patterns, providing more effective protection.

[0071] The SNS filtering AI agent system can optimize its filtering algorithm by considering the user's device information. For example, if the user is using a smartphone, the system can apply a filtering algorithm optimized for smartphones. Similarly, if the user is using a tablet, it can apply a filtering algorithm optimized for tablets. Furthermore, if the user is using a desktop PC, it can apply a filtering algorithm optimized for desktop PCs. This enables optimal filtering tailored to the user's device, providing more effective protection.

[0072] The SNS filtering AI agent system can optimize its filtering algorithm by considering the user's geographical information. For example, it can learn patterns of harmful content that frequently occur in a particular region and apply a filtering algorithm tailored to that region. Furthermore, if the user is traveling, the system can apply a filtering algorithm appropriate to their destination. In addition, it can analyze the user's geographical information in real time and dynamically adjust the filtering algorithm. This enables optimal filtering based on the user's geographical information, providing more effective protection.

[0073] The SNS filtering AI agent system can customize its filtering algorithm by considering user attribute information. For example, it can apply the optimal filtering algorithm based on the user's age, gender, and interests. It can also apply filtering algorithms tailored to the user's occupation and lifestyle. Furthermore, it can analyze user attribute information in real time and dynamically adjust the filtering algorithm. This enables optimal filtering based on user attribute information, providing more effective protection.

[0074] The SNS filtering AI agent system can optimize its filtering algorithm by referencing past user feedback. For example, if a user has expressed dissatisfaction with filtering results in the past, the algorithm can be improved based on that feedback. Similarly, if a user has given a high rating to a particular filtering result, the algorithm can be strengthened based on that result. Furthermore, it can analyze user feedback in real time and dynamically adjust the filtering algorithm. This enables optimal filtering based on user feedback, providing more effective protection.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The detection unit detects harmful content on social media in real time. For example, it uses natural language processing technology to detect harmful text, image recognition technology to detect harmful images, and video analysis technology to detect harmful videos. This makes it possible to detect offensive comments, discriminatory remarks, violent images and pornography, violent acts, and videos containing inappropriate content. Step 2: The blocking unit immediately blocks the harmful content detected by the detection unit. For example, it can block harmful content by applying filtering rules and adjust the blocking strength based on user settings. Furthermore, it has high-speed processing capabilities and blocks harmful content in real time. Step 3: The development department develops filtering agents specifically for each SNS platform. For example, they analyze the characteristics of each platform, develop the optimal filtering agent based on that analysis, evaluate its performance, and make improvements as needed. They also have the capability to rapidly develop filtering agents to support new SNS platforms. Step 4: The interface section provides a user-friendly interface for parents to use the system. For example, it provides an intuitive user interface and a guide to help parents easily configure the system. It also has a function to visually display system usage and filtering results.

[0077] (Example of form 2) The SNS filtering AI agent system according to an embodiment of the present invention is a system for protecting children from harmful content and comments on social networking services (SNS). This system detects harmful text, images, and videos on SNS in real time and immediately blocks them, preventing children from encountering them. Furthermore, filtering agents specialized for each SNS platform are developed, and optimal filtering is implemented according to the characteristics of each platform. For example, if a certain SNS platform tends to have a high volume of offensive comments, the filtering agent specialized for that platform will detect and block offensive comments in real time. Similarly, if another platform sees a high volume of inappropriate images and videos being posted, the filtering agent specialized for that platform will detect and block inappropriate images and videos in real time. In this way, children can use SNS in a safe online environment, and parents can confidently monitor their children's internet use. Moreover, it contributes to improving the overall health of SNS platforms. As a result, the SNS filtering AI agent system can protect children from harmful content and comments on SNS.

[0078] The SNS filtering AI agent system according to this embodiment comprises a detection unit, a blocking unit, a development unit, and an interface unit. The detection unit detects harmful content on SNS in real time. The detection unit detects harmful text using, for example, natural language processing technology. The detection unit can also detect harmful images using image recognition technology. Furthermore, the detection unit can also detect harmful videos using video analysis technology. For example, the detection unit uses natural language processing technology to detect text containing offensive comments or discriminatory remarks. It uses image recognition technology to detect images containing violence or pornography. It uses video analysis technology to detect videos containing violent acts or inappropriate content. The blocking unit immediately blocks the harmful content detected by the detection unit. The blocking unit blocks harmful content by, for example, applying filtering rules. Furthermore, the blocking unit can adjust the strength of the block based on user settings. Furthermore, the blocking unit has high-speed processing capability to block harmful content in real time. For example, the blocking unit applies filtering rules to immediately block offensive comments and inappropriate images. It adjusts the strength of the block based on user settings and performs strict filtering as needed. The high-speed blocking unit blocks harmful content in real time. The development unit develops filtering agents specialized for each SNS platform. For example, the development unit analyzes the characteristics of each platform and develops the optimal filtering agent based on that analysis. The development unit can also evaluate the performance of the filtering agents and make improvements as needed. Furthermore, the development unit has the capability to rapidly develop filtering agents to support new SNS platforms. For example, the development unit analyzes the characteristics of each platform and develops filtering agents specialized for platforms where offensive comments are frequent. They evaluate the performance of the filtering agents and make improvements as needed. They rapidly develop filtering agents to support new SNS platforms.The interface unit provides a user-friendly interface for parents to use the system. For example, the interface unit provides an intuitive user interface. The interface unit can also provide a guide to help parents easily configure the system. Furthermore, the interface unit has a function to visually display system usage and filtering results. For example, the interface unit provides an intuitive user interface, making it easy for parents to operate the system. It provides a guide to make system configuration easy. It visually displays system usage and filtering results, allowing parents to confirm the system's effectiveness. As a result, the SNS filtering AI agent system according to this embodiment can protect children from harmful content and comments on social media.

[0079] The detection unit detects harmful content on social media in real time. Specifically, it uses natural language processing technology to detect harmful text. Natural language processing technology includes tokenization, morphological analysis, grammatical analysis, and semantic analysis to analyze the meaning of text. This enables high-precision detection of text containing offensive comments or discriminatory remarks. For example, it can not only detect specific keywords or phrases but also understand the context to identify remarks with harmful intent. It can also detect harmful images using image recognition technology. Image recognition technology includes convolutional neural networks (CNNs) to extract and classify features in images. This enables high-precision detection of images containing violence or pornography. For example, it can identify specific patterns or objects in an image and determine whether they contain harmful content. It can also detect harmful videos using video analysis technology. Video analysis technology includes recurrent neural networks (RNNs) and long-term short-term memory (LSTMs) to extract and analyze features frame by frame of a video. This enables high-precision detection of videos containing violent acts or inappropriate content. For example, it can analyze the movement and sound in a video and determine whether it contains harmful content. This allows the detection unit to analyze various types of content, including text, images, and videos, in real time and quickly detect harmful content.

[0080] The blocking unit immediately blocks harmful content detected by the detection unit. Specifically, it blocks harmful content by applying filtering rules. Filtering rules include specific keywords or phrases, image features, and video content. This allows for the immediate blocking of offensive comments and inappropriate images. The strength of the blocking can also be adjusted based on user settings. For example, parents can choose to perform strict filtering or allow for a certain degree of tolerance, depending on the filtering level they have set. The blocking unit has high-speed processing capabilities to block harmful content in real time. This prevents the spread of harmful content on social media and protects users. Furthermore, the blocking unit can collect user feedback and continuously improve the accuracy and effectiveness of the filtering rules. For example, if a user objects to blocked content, the filtering rules are reviewed and adjusted as needed based on that feedback. This allows the blocking unit to provide flexible filtering tailored to user needs and improve the overall reliability and effectiveness of the system.

[0081] The development department develops filtering agents specifically tailored to each social networking service (SNS) platform. Specifically, they analyze the characteristics of each platform and develop the optimal filtering agent based on that analysis. For example, because certain SNS platforms tend to have a high concentration of specific types of harmful content, they develop a filtering agent specifically for that platform. The development department can also evaluate the performance of the filtering agents and make improvements as needed. Performance evaluation includes detection accuracy, processing speed, and user feedback. This allows for continuous improvement of the filtering agent's performance. Furthermore, the development department has the capability to rapidly develop filtering agents to support new SNS platforms. For example, by quickly developing and deploying filtering agents for newly emerging SNS platforms, they can protect users from harmful content. This allows the development department to provide high-performance filtering agents tailored to each SNS platform, maximizing the overall system effectiveness.

[0082] The interface unit provides a user-friendly interface for parents to use the system. Specifically, it provides an intuitive user interface. For example, it provides a simple and easy-to-understand menu structure and operation guide so that parents can easily configure the system. The interface unit can also provide guides to help parents easily configure the system. For example, it provides a step-by-step configuration guide and FAQ for parents using the system for the first time. Furthermore, the interface unit has a function to visually display the system usage status and filtering results. For example, it can display the type and number of filtered content and the list of blocked users in graphs and charts, so that parents can see the effectiveness of the system at a glance. In this way, the interface unit can support parents in easily operating and effectively using the system. In addition, the interface unit can collect user feedback and continuously improve the usability and functionality of the interface. For example, it can review the interface design and functions based on requests and opinions from parents and make improvements as needed. In this way, the interface unit can provide a user-friendly interface and improve the overall usability and effectiveness of the system.

[0083] The algorithm section implements specific filtering methods and algorithms. For example, the algorithm section can implement keyword filtering. Keyword filtering is a method of detecting and blocking content containing specific keywords. The algorithm section can also implement image recognition filtering. Image recognition filtering is a method of detecting and blocking harmful images. Furthermore, the algorithm section can also implement machine learning algorithms. Machine learning algorithms are methods of detecting harmful content with high accuracy by learning from large amounts of data. For example, the algorithm section can implement keyword filtering to detect and block offensive comments containing specific keywords. It can implement image recognition filtering to detect and block images containing violence or pornography. It can implement machine learning algorithms to detect harmful content with high accuracy by learning from large amounts of data. In this way, the accuracy of filtering is improved by implementing specific filtering methods and algorithms.

[0084] The Platform Specialization Department develops filtering agents specialized for each platform. For example, the Platform Specialization Department develops filtering agents using the API of a specific SNS platform. It analyzes the characteristics of a specific platform and develops the optimal filtering agent based on that analysis. The Platform Specialization Department can also develop filtering agents considering the user base and posting trends of each platform. Furthermore, the Platform Specialization Department can develop filtering agents considering the technical constraints of each platform. For example, the Platform Specialization Department uses the API of a specific SNS platform to develop a filtering agent specialized for a platform where aggressive comments are frequent. It analyzes the characteristics of a specific platform and develops the optimal filtering agent based on that analysis. It develops filtering agents considering the user base and posting trends of each platform. It develops filtering agents considering the technical constraints of each platform. By developing filtering agents specialized for each platform, optimal filtering according to the characteristics of each platform becomes possible. Some or all of the above processing in the Platform Specialization Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Platform Specialization Department can input the characteristics of a specific platform into a generative AI and have the generative AI develop the optimal filtering agent.

[0085] The User Guide Department provides guidance for parents to use the system. For example, the User Guide Department provides an operation manual. The operation manual explains the basic operation methods of the system. The User Guide Department may also provide an FAQ. The FAQ is a collection of frequently asked questions and their answers. Furthermore, the User Guide Department may provide video tutorials. Video tutorials visually explain how to use the system. For example, the User Guide Department provides an operation manual so that parents can understand the basic operation methods of the system. It provides an FAQ, which provides a collection of frequently asked questions and their answers. It provides video tutorials, which visually explain how to use the system. This makes it easier for parents to use the system by providing guidance for them to use the system. Some or all of the above processes in the User Guide Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the User Guide Department can input a parent's question into a generative AI and have the generative AI generate the best answer.

[0086] The detection unit can detect harmful text, images, and videos on social media in real time. For example, the detection unit can detect harmful text using natural language processing technology. For instance, it can detect text containing offensive comments or discriminatory remarks. The detection unit can also detect harmful images using image recognition technology. For example, it can detect images containing violence or pornography. Furthermore, the detection unit can detect harmful videos using video analysis technology. For example, it can detect videos containing violent acts or inappropriate content. This allows for the detection of harmful text, images, and videos on social media in real time, protecting children from harmful content. Some or all of the above-described processes in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input text, images, and videos from social media into a generative AI and have the generative AI perform the detection of harmful content.

[0087] The blocking unit can immediately block harmful content detected by the detection unit. The blocking unit blocks harmful content by, for example, applying filtering rules. For example, the blocking unit can immediately block offensive comments or inappropriate images. The blocking unit can also adjust the strength of the blocking based on user settings. For example, the blocking unit can perform strict filtering as needed based on user settings. Furthermore, the blocking unit has high-speed processing capabilities to block harmful content in real time. For example, the blocking unit has high-speed processing capabilities and can block harmful content in real time. This prevents children from being exposed to harmful content by immediately blocking detected harmful content. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input detected harmful content into a generative AI and leave the blocking to the generative AI.

[0088] The development department can develop filtering agents specialized for each SNS platform. For example, the development department can analyze the characteristics of each platform and develop the optimal filtering agent based on that analysis. For example, the development department can develop a filtering agent specialized for platforms where aggressive comments are frequent. The development department can also evaluate the performance of the filtering agents and make improvements as needed. For example, the development department can evaluate the performance of the filtering agents and make improvements as needed. Furthermore, the development department has the capability to rapidly develop filtering agents to support new SNS platforms. For example, the development department can rapidly develop filtering agents to support new SNS platforms. This enables optimal filtering tailored to the characteristics of each platform by developing filtering agents specialized for each SNS platform. Some or all of the above processes performed by the development department may be carried out using, for example, generative AI, or not using generative AI. For example, the development department can input the characteristics of each platform into a generative AI and have the generative AI develop the optimal filtering agent.

[0089] The interface unit can provide a user-friendly interface for parents to use the system. For example, the interface unit can provide an intuitive user interface. For example, the interface unit can make it easy for parents to operate the system. The interface unit can also provide a guide to make it easy for parents to configure the system. For example, the interface unit can provide a guide to make it easy to configure the system. Furthermore, the interface unit has a function to visually display the system usage status and filtering results. For example, the interface unit can visually display the system usage status and filtering results so that parents can check the effectiveness of the system. This makes it easier for parents to use the system by providing a user-friendly interface. Some or all of the above processing in the interface unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the interface unit can input the parent's operations into the generative AI and have the generative AI provide the optimal interface.

[0090] The detection unit can estimate the user's emotions and adjust the accuracy of harmful content detection based on the estimated user emotions. The detection unit can estimate the user's emotions using, for example, facial recognition technology. For example, the detection unit can capture the user's facial expressions with a camera and estimate the emotions using facial recognition technology. The detection unit can also estimate the user's emotions using text analysis technology. For example, the detection unit can analyze the user's text messages and estimate the emotions. Furthermore, the detection unit can also estimate the user's emotions using speech analysis technology. For example, the detection unit can record the user's voice and estimate the emotions using speech analysis technology. This allows for more appropriate filtering by adjusting the accuracy of harmful content detection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0091] The detection unit can optimize its detection algorithm by referring to patterns of past harmful content. For example, the detection unit can refer to a database of previously detected harmful content. For example, the detection unit can refer to a database of previously detected harmful content and prioritize the detection of content with similar patterns. The detection unit can also learn patterns of past harmful content to improve the detection accuracy of new harmful content. For example, the detection unit can learn patterns of past harmful content to improve the detection accuracy of new harmful content. Furthermore, the detection unit can adjust its detection algorithm in real time based on patterns of past harmful content to perform optimal filtering. For example, the detection unit adjusts its detection algorithm in real time based on patterns of past harmful content to perform optimal filtering. This improves the accuracy of the detection algorithm by referring to patterns of past harmful content. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input data of past harmful content into a generative AI and have the generative AI perform the optimization of the detection algorithm.

[0092] The detection unit can improve detection accuracy by considering the attribute information of the content's poster. For example, the detection unit considers attribute information such as the content's poster's age and gender. For example, the detection unit can improve the detection accuracy of harmful content by considering attribute information such as the content's poster's age and gender. The detection unit can also refer to the poster's past posting history and prioritize the detection of content from posters with specific attributes. For example, the detection unit refers to the poster's past posting history and prioritizes the detection of content from posters with specific attributes. Furthermore, the detection unit can detect and filter content from posters with specific attributes in real time based on the poster's attribute information. For example, the detection unit detects and filters content from posters with specific attributes in real time based on the poster's attribute information. This improves detection accuracy by considering the attribute information of the content's poster. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input the poster's attribute information into a generative AI and have the generative AI perform the improvement of detection accuracy.

[0093] The detection unit can estimate the user's emotions and determine the detection priority for harmful content based on the estimated user emotions. The detection unit can estimate the user's emotions using, for example, facial recognition technology. For example, the detection unit can capture the user's facial expressions with a camera and estimate the emotions using facial recognition technology. The detection unit can also estimate the user's emotions using text analysis technology. For example, the detection unit can analyze the user's text messages and estimate the emotions. Furthermore, the detection unit can also estimate the user's emotions using speech analysis technology. For example, the detection unit can record the user's voice and estimate the emotions using speech analysis technology. This allows for more appropriate filtering by determining the detection priority for harmful content based on the user's emotions. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0094] The detection unit can improve detection accuracy by considering the geographical distribution of content. For example, the detection unit considers the location where the content is posted. For example, the detection unit can consider the location where the content is posted and prioritize the detection of harmful content that frequently occurs in a particular area. The detection unit can also improve the detection accuracy of harmful content in a particular area based on geographical distribution. For example, the detection unit can improve the detection accuracy of harmful content in a particular area based on geographical distribution. Furthermore, the detection unit can analyze geographical distribution in real time and quickly detect harmful content in a particular area. For example, the detection unit analyzes geographical distribution in real time and quickly detects harmful content in a particular area. This improves detection accuracy by considering the geographical distribution of content. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input geographical distribution data of the content into a generative AI and have the generative AI perform the improvement of detection accuracy.

[0095] The detection unit can improve the accuracy of detecting harmful content by referring to relevant external databases. For example, the detection unit can refer to external databases and learn the latest patterns of harmful content to improve detection accuracy. The detection unit can also adjust its detection algorithm in real time based on information obtained from external databases. For example, the detection unit adjusts its detection algorithm in real time based on information obtained from external databases. Furthermore, the detection unit can use external databases to improve the accuracy of detecting specific harmful content. For example, the detection unit uses external databases to improve the accuracy of detecting specific harmful content. This improves detection accuracy by referring to relevant external databases. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input information from external databases into a generative AI and have the generative AI perform the improvement of detection accuracy.

[0096] The blocking unit can estimate the user's emotions and adjust the timing of the blocks based on the estimated emotions. The blocking unit can estimate the user's emotions using, for example, facial recognition technology. For example, the blocking unit can capture the user's facial expression with a camera and estimate the emotions using facial recognition technology. The blocking unit can also estimate the user's emotions using text analysis technology. For example, the blocking unit can analyze the user's text message and estimate the emotions. Furthermore, the blocking unit can also estimate the user's emotions using speech analysis technology. For example, the blocking unit can record the user's voice and estimate the emotions using speech analysis technology. This allows for more appropriate filtering by adjusting the timing of the blocks based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the block unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0097] The blocking unit can optimize its blocking algorithm by referring to past blocking history. For example, the blocking unit can refer to past blocking history and prioritize blocking content with similar patterns. The blocking unit can also learn from past blocking history to improve the accuracy of blocking new harmful content. For example, the blocking unit can learn from past blocking history to improve the accuracy of blocking new harmful content. Furthermore, the blocking unit can adjust its blocking algorithm in real time based on past blocking history to perform optimal filtering. For example, the blocking unit adjusts its blocking algorithm in real time based on past blocking history to perform optimal filtering. This improves the accuracy of the blocking algorithm by referring to past blocking history. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input past blocking history data into a generative AI and have the generative AI perform the optimization of the blocking algorithm.

[0098] The blocking unit can determine the priority of blocking by considering the impact of the content. For example, the blocking unit can evaluate the impact of the content. For example, the blocking unit can evaluate the impact of the content and prioritize blocking content with a high impact. The blocking unit can also quickly block content with a high impact to minimize the impact on users. For example, the blocking unit can quickly block content with a high impact to minimize the impact on users. Furthermore, the blocking unit can adjust the priority of blocking in real time based on the impact evaluation. For example, the blocking unit adjusts the priority of blocking in real time based on the impact evaluation. This improves the priority of blocking by considering the impact of the content. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the blocking unit can input content impact data into a generative AI and have the generative AI determine the priority of blocking.

[0099] The blocking unit can estimate the user's emotions and adjust the blocking method based on the estimated user emotions. For example, the blocking unit can estimate the user's emotions using facial recognition technology. For example, the blocking unit can capture the user's facial expression with a camera and estimate the emotions using facial recognition technology. The blocking unit can also estimate the user's emotions using text analysis technology. For example, the blocking unit can analyze the user's text message and estimate the emotions. Furthermore, the blocking unit can also estimate the user's emotions using speech analysis technology. For example, the blocking unit can record the user's voice and estimate the emotions using speech analysis technology. This allows for more appropriate filtering by adjusting the blocking method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the blocking unit may be performed using a generative AI, for example, or without a generative AI. For example, the block unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0100] The blocking unit can improve its blocking accuracy by considering the attribute information of the content creator. For example, the blocking unit considers attribute information such as the age and gender of the content creator. For example, the blocking unit can improve the accuracy of blocking harmful content by considering attribute information such as the age and gender of the content creator. The blocking unit can also refer to the creator's past posting history and preferentially block content from creators with specific attributes. For example, the blocking unit refers to the creator's past posting history and preferentially blocks content from creators with specific attributes. Furthermore, the blocking unit can block and filter content from creators with specific attributes in real time based on the creator's attribute information. For example, the blocking unit blocks and filters content from creators with specific attributes in real time based on the creator's attribute information. This improves blocking accuracy by considering the attribute information of the content creator. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input the creator's attribute information into a generative AI and have the generative AI perform the improvement of blocking accuracy.

[0101] The blocking unit can improve blocking accuracy by referring to relevant external databases. For example, the blocking unit can refer to external databases and learn the latest patterns of harmful content to improve blocking accuracy. The blocking unit can also adjust its blocking algorithm in real time based on information obtained from external databases. For example, the blocking unit adjusts its blocking algorithm in real time based on information obtained from external databases. Furthermore, the blocking unit can use external databases to improve the blocking accuracy of specific harmful content. For example, the blocking unit uses external databases to improve the blocking accuracy of specific harmful content. This improves blocking accuracy by referring to relevant external databases. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input information from external databases into a generative AI and have the generative AI perform the improvement of blocking accuracy.

[0102] The development department can estimate the user's emotions and determine the development priority of filtering agents based on the estimated user emotions. For example, the development department can estimate the user's emotions using facial recognition technology. For example, the development department can capture the user's facial expressions with a camera and estimate the emotions using facial recognition technology. The development department can also estimate the user's emotions using text analysis technology. For example, the development department can analyze the user's text messages and estimate the emotions. Furthermore, the development department can also estimate the user's emotions using speech analysis technology. For example, the development department can record the user's voice and estimate the emotions using speech analysis technology. This allows for the development of more appropriate filtering agents by determining the development priority of filtering agents based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the development department may be performed using generative AI, for example, or without generative AI. For example, the development department can input user emotion data into a generative AI and have the AI ​​perform emotion estimation.

[0103] The development department can develop the optimal filtering agent by thoroughly analyzing the characteristics of each SNS platform. For example, the development department can analyze the characteristics of each platform. For example, the development department can analyze the characteristics of each platform in detail and develop the optimal filtering agent for a specific platform. The development department can also develop filtering agents by considering the user base and posting trends of each platform. For example, the development department can develop filtering agents by considering the user base and posting trends of each platform. Furthermore, the development department can develop filtering agents by considering the technical constraints of each platform. For example, the development department can develop filtering agents by considering the technical constraints of each platform. In this way, by thoroughly analyzing the characteristics of each SNS platform, it becomes possible to develop the optimal filtering agent. Some or all of the above processing by the development department may be performed using, for example, a generative AI, or not using a generative AI. For example, the development department can input characteristic data for each platform into a generative AI and have the generative AI develop the optimal filtering agent.

[0104] The development department can optimize the development algorithm by referring to past filtering agent performance data. For example, the development department can refer to past filtering agent performance data and prioritize the development of agents with similar patterns. The development department can also learn from past performance data to improve the accuracy of developing new filtering agents. For example, the development department can learn from past performance data to improve the accuracy of developing new filtering agents. Furthermore, the development department can adjust the development algorithm in real time based on past performance data to develop the optimal filtering agent. For example, the development department adjusts the development algorithm in real time based on past performance data to develop the optimal filtering agent. This improves the accuracy of the development algorithm by referring to past filtering agent performance data. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input past performance data into generative AI and have the generative AI perform the optimization of the development algorithm.

[0105] The development department can estimate the user's emotions and adjust the development method of the filtering agent based on the estimated user emotions. For example, the development department can estimate the user's emotions using facial recognition technology. For example, the development department can capture the user's facial expressions with a camera and estimate the emotions using facial recognition technology. The development department can also estimate the user's emotions using text analysis technology. For example, the development department can analyze the user's text messages and estimate the emotions. Furthermore, the development department can also estimate the user's emotions using speech analysis technology. For example, the development department can record the user's voice and estimate the emotions using speech analysis technology. This makes it possible to develop a more appropriate filtering agent by adjusting the development method of the filtering agent based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the development department may be performed using generative AI, for example, or without generative AI. For example, the development department can input user emotion data into a generative AI and have the AI ​​perform emotion estimation.

[0106] The development department can develop filtering agents by considering the user attribute information of each SNS platform. For example, the development department can consider the user attribute information of each platform. For example, the development department can analyze the user attribute information of each platform in detail and develop a filtering agent that is optimal for a specific user segment. The development department can also develop an optimal filtering agent for users with specific attributes based on the user attribute information. For example, the development department can develop an optimal filtering agent for users with specific attributes based on the user attribute information. Furthermore, the development department can analyze the user attribute information in real time and develop an optimal filtering agent for users with specific attributes. For example, the development department can analyze the user attribute information in real time and develop an optimal filtering agent for users with specific attributes. This makes it possible to develop an optimal filtering agent by considering the user attribute information of each SNS platform. Some or all of the above processing by the development department may be performed using, for example, a generative AI, or not using a generative AI. For example, the development department can input user attribute information into a generative AI and have the generative AI develop an optimal filtering agent.

[0107] The development department can improve the accuracy of filtering agent development by referring to relevant external databases. For example, the development department can refer to external databases to learn the latest patterns of harmful content and improve the accuracy of filtering agent development. The development department can also adjust the development algorithm in real time based on information obtained from external databases. For example, the development department adjusts the development algorithm in real time based on information obtained from external databases. Furthermore, the development department can use external databases to improve the accuracy of filtering agents for specific harmful content. For example, the development department uses external databases to improve the accuracy of filtering agents for specific harmful content. This improves the accuracy of filtering agent development by referring to relevant external databases. Some or all of the above processes in the development department may be performed using, for example, a generative AI, or not using a generative AI. For example, the development department can input information from external databases into a generative AI and have the generative AI perform the improvement of development accuracy.

[0108] The interface unit can estimate the user's emotions and adjust the interface display method based on the estimated user emotions. The interface unit can estimate the user's emotions using, for example, facial expression recognition technology. For example, the interface unit can capture the user's facial expression with a camera and estimate the emotion using facial expression recognition technology. The interface unit can also estimate the user's emotions using text analysis technology. For example, the interface unit can analyze the user's text message and estimate the emotion. Furthermore, the interface unit can also estimate the user's emotions using speech analysis technology. For example, the interface unit can record the user's voice and estimate the emotion using speech analysis technology. By adjusting the interface display method based on the user's emotions, a more appropriate interface is provided. Emotion estimation is implemented using, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the interface unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interface unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0109] The interface unit can select the optimal display method by referring to the user's past operation history. For example, the interface unit can refer to the user's past operation history and prioritize the display of frequently used functions. The interface unit can also provide the user with a preferred display method based on the past operation history. For example, the interface unit can provide the user with a preferred display method based on the past operation history. Furthermore, the interface unit can analyze the past operation history in real time and select the optimal display method. For example, the interface unit analyzes the past operation history in real time and selects the optimal display method. This ensures that the optimal display method is provided by referring to the user's past operation history. Some or all of the above processing in the interface unit may be performed using, for example, a generation AI, or without a generation AI. For example, the interface unit can input past operation history data into a generation AI and have the generation AI select the optimal display method.

[0110] The interface unit can customize the displayed content by considering the user's attribute information. For example, the interface unit can consider the user's attribute information such as age and gender. For example, the interface unit can consider the user's attribute information such as age and gender and provide optimal displayed content. The interface unit can also provide customized displayed content for users with specific attributes based on the user's attribute information. For example, the interface unit can provide customized displayed content for users with specific attributes based on the user's attribute information. Furthermore, the interface unit can analyze the user's attribute information in real time and provide optimal displayed content. For example, the interface unit analyzes the user's attribute information in real time and provides optimal displayed content. As a result, by considering the user's attribute information, the displayed content is customized, and a more appropriate interface is provided. Some or all of the above processing in the interface unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the interface unit can input the user's attribute information into a generative AI and have the generative AI perform the customization of the displayed content.

[0111] The interface unit can estimate the user's emotions and adjust the interface's operation procedures based on the estimated user emotions. For example, the interface unit can estimate the user's emotions using facial recognition technology. For instance, the interface unit can capture the user's facial expressions with a camera and estimate their emotions using facial recognition technology. The interface unit can also estimate the user's emotions using text analysis technology. For example, the interface unit can analyze the user's text messages and estimate their emotions. Furthermore, the interface unit can also estimate the user's emotions using speech analysis technology. For example, the interface unit can record the user's voice and estimate their emotions using speech analysis technology. This allows for the provision of more appropriate operation procedures by adjusting the interface's operation procedures based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the interface unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interface unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0112] The interface unit can select the optimal display method by considering the user's device information. For example, the interface unit can consider the user's device information. For example, if the user is using a smartphone, the interface unit can provide a display method that matches the screen size. Also, if the user is using a tablet, the interface unit can provide a display method optimized for a larger screen. For example, if the user is using a tablet, the interface unit can provide a display method optimized for a larger screen. Furthermore, if the user is using a smartwatch, the interface unit can provide a concise and highly visible display method. For example, if the user is using a smartwatch, the interface unit can provide a concise and highly visible display method. In this way, the optimal display method is provided by considering the user's device information. Some or all of the above processing in the interface unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interface unit can input the user's device information into a generative AI and have the generative AI select the optimal display method.

[0113] The interface unit can customize the displayed content by referring to a related external database. For example, the interface unit can refer to an external database and customize the displayed content based on the latest information. The interface unit can also adjust the displayed content in real time based on information obtained from the external database. For example, the interface unit adjusts the displayed content in real time based on information obtained from the external database. Furthermore, the interface unit can use the external database to provide the most suitable displayed content for a specific user. For example, the interface unit uses the external database to provide the most suitable displayed content for a specific user. As a result, by referring to a related external database, the displayed content is customized, and a more appropriate interface is provided. Some or all of the above processing in the interface unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interface unit can input information from the external database into a generative AI and have the generative AI perform the customization of the displayed content.

[0114] The algorithm unit can estimate the user's emotions and adjust the parameters of the filtering algorithm based on the estimated user emotions. For example, the algorithm unit can estimate the user's emotions using facial recognition technology. For example, the algorithm unit can capture the user's facial expression with a camera and estimate the emotions using facial recognition technology. The algorithm unit can also estimate the user's emotions using text analysis technology. For example, the algorithm unit can analyze the user's text message and estimate the emotions. Furthermore, the algorithm unit can also estimate the user's emotions using speech analysis technology. For example, the algorithm unit can record the user's voice and estimate the emotions using speech analysis technology. This allows for more appropriate filtering by adjusting the parameters of the filtering algorithm based on the user's emotions. Emotion estimation is implemented using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the algorithm unit may be performed using a generative AI, for example, or without a generative AI. For example, the algorithm unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0115] The algorithm unit can optimize its algorithm by referring to past filtering data. For example, the algorithm unit can refer to past filtering data and prioritize filtering content with similar patterns. The algorithm unit can also learn from past filtering data to improve the accuracy of filtering new harmful content. For example, the algorithm unit can learn from past filtering data to improve the accuracy of filtering new harmful content. Furthermore, the algorithm unit can adjust the algorithm in real time based on past filtering data to perform optimal filtering. For example, the algorithm unit adjusts the algorithm in real time based on past filtering data to perform optimal filtering. This improves the accuracy of the algorithm by referring to past filtering data. Some or all of the above processing in the algorithm unit may be performed using, for example, a generative AI, or without a generative AI. For example, the algorithm unit can input past filtering data into a generative AI and have the generative AI perform algorithm optimization.

[0116] The algorithm unit can customize the algorithm by taking into account the characteristics of each SNS platform. For example, the algorithm unit can analyze the characteristics of each platform. For example, the algorithm unit can analyze the characteristics of each platform in detail and implement an algorithm that is optimal for a particular platform. The algorithm unit can also implement the algorithm by taking into account the user base and posting trends of each platform. For example, the algorithm unit implements the algorithm by taking into account the user base and posting trends of each platform. Furthermore, the algorithm unit can implement the algorithm by taking into account the technical constraints of each platform. For example, the algorithm unit implements the algorithm by taking into account the technical constraints of each platform. This makes it possible to implement an optimal algorithm by taking into account the characteristics of each SNS platform. Some or all of the above processing in the algorithm unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the algorithm unit can input characteristic data of each platform into a generative AI and have the generative AI perform the algorithm customization.

[0117] The algorithm unit can estimate the user's emotions and adjust the scope of the filtering algorithm based on the estimated emotions. For example, the algorithm unit can estimate the user's emotions using facial recognition technology. For example, the algorithm unit can capture the user's facial expression with a camera and estimate the emotions using facial recognition technology. The algorithm unit can also estimate the user's emotions using text analysis technology. For example, the algorithm unit can analyze the user's text message and estimate the emotions. Furthermore, the algorithm unit can also estimate the user's emotions using speech analysis technology. For example, the algorithm unit can record the user's voice and estimate the emotions using speech analysis technology. This allows for more appropriate filtering by adjusting the scope of the filtering algorithm based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the algorithm unit may be performed using a generative AI, for example, or without a generative AI. For example, the algorithm unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0118] The algorithm unit can improve the accuracy of the algorithm by referring to relevant external databases. For example, the algorithm unit can refer to external databases and learn the latest patterns of harmful content to improve the accuracy of the algorithm. The algorithm unit can also adjust the algorithm in real time based on information obtained from external databases. For example, the algorithm unit adjusts the algorithm in real time based on information obtained from external databases. Furthermore, the algorithm unit can use external databases to improve the accuracy of the algorithm for specific harmful content. For example, the algorithm unit uses external databases to improve the accuracy of the algorithm for specific harmful content. This improves the accuracy of the algorithm by referring to relevant external databases. Some or all of the above processing in the algorithm unit may be performed using, for example, a generative AI, or without a generative AI. For example, the algorithm unit can input information from an external database into a generative AI and have the generative AI perform the algorithm accuracy improvement.

[0119] The algorithm unit can customize the algorithm by considering the user attribute information of each SNS platform. For example, the algorithm unit can consider the user attribute information of each platform. For example, the algorithm unit can analyze the user attribute information of each platform in detail and implement an algorithm that is optimal for a specific user segment. The algorithm unit can also implement an optimal algorithm for users with specific attributes based on the user attribute information. For example, the algorithm unit implements an optimal algorithm for users with specific attributes based on the user attribute information. Furthermore, the algorithm unit can analyze the user attribute information in real time and implement an optimal algorithm for users with specific attributes. For example, the algorithm unit analyzes the user attribute information in real time and implements an optimal algorithm for users with specific attributes. This makes it possible to implement an optimal algorithm by considering the user attribute information of each SNS platform. Some or all of the above processing in the algorithm unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the algorithm unit can input user attribute information into a generative AI and have the generative AI perform the algorithm customization.

[0120] The platform-specific unit can estimate the user's emotions and determine the development priority of platform-specific filtering agents based on the estimated user emotions. For example, the platform-specific unit can estimate user emotions using facial recognition technology. For instance, it can capture the user's facial expressions with a camera and estimate their emotions using facial recognition technology. The platform-specific unit can also estimate user emotions using text analysis technology. For example, it can analyze the user's text messages and estimate their emotions. Furthermore, the platform-specific unit can estimate user emotions using speech analysis technology. For example, it can record the user's voice and estimate their emotions using speech analysis technology. This allows for the development of more appropriate filtering agents by determining the development priority of platform-specific filtering agents based on user emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the platform-specific unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the platform-specific unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0121] The platform-specific unit can develop the optimal filtering agent by analyzing the characteristics of each platform in detail. For example, the platform-specific unit can analyze the characteristics of each platform and develop the optimal filtering agent for a specific platform. The platform-specific unit can also develop filtering agents by considering the user base and posting trends of each platform. For example, the platform-specific unit can develop filtering agents by considering the user base and posting trends of each platform. Furthermore, the platform-specific unit can also develop filtering agents by considering the technical constraints of each platform. For example, the platform-specific unit can develop filtering agents by considering the technical constraints of each platform. This makes it possible to develop the optimal filtering agent by analyzing the characteristics of each platform in detail. Some or all of the above processing in the platform-specific unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the platform-specific unit can input characteristic data for each platform into a generative AI and have the generative AI develop the optimal filtering agent.

[0122] The platform-specific unit can optimize the development algorithm by referring to past agent performance data. For example, the platform-specific unit can refer to past agent performance data and prioritize the development of agents with similar patterns. The platform-specific unit can also learn from past performance data to improve the accuracy of developing new filtering agents. For example, the platform-specific unit can learn from past performance data to improve the accuracy of developing new filtering agents. Furthermore, the platform-specific unit can adjust the development algorithm in real time based on past performance data to develop the optimal filtering agent. For example, the platform-specific unit adjusts the development algorithm in real time based on past performance data to develop the optimal filtering agent. This improves the accuracy of the development algorithm by referring to past agent performance data. Some or all of the above processing in the platform-specific unit may be performed using, for example, a generative AI, or without a generative AI. For example, the platform-specific unit can input past performance data into a generative AI and have the generative AI perform the optimization of the development algorithm.

[0123] The platform-specific unit can estimate the user's emotions and adjust the development method of the platform-specific filtering agent based on the estimated user emotions. For example, the platform-specific unit can estimate the user's emotions using facial recognition technology. For instance, it can capture the user's facial expressions with a camera and estimate their emotions using facial recognition technology. The platform-specific unit can also estimate the user's emotions using text analysis technology. For example, it can analyze the user's text messages and estimate their emotions. Furthermore, the platform-specific unit can also estimate the user's emotions using speech analysis technology. For example, it can record the user's voice and estimate their emotions using speech analysis technology. This allows for the development of more appropriate filtering agents by adjusting the development method of the platform-specific filtering agent based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the platform-specific unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the platform-specific unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0124] The platform-specific unit can develop agents by considering the user attribute information of each platform. For example, the platform-specific unit can consider the user attribute information of each platform. For example, the platform-specific unit can analyze the user attribute information of each platform in detail and develop a filtering agent that is optimal for a specific user segment. The platform-specific unit can also develop an optimal filtering agent for users with specific attributes based on the user attribute information. For example, the platform-specific unit can develop an optimal filtering agent for users with specific attributes based on the user attribute information. Furthermore, the platform-specific unit can analyze the user attribute information in real time and develop an optimal filtering agent for users with specific attributes. For example, the platform-specific unit analyzes the user attribute information in real time and develops an optimal filtering agent for users with specific attributes. This makes it possible to develop an optimal filtering agent by considering the user attribute information of each platform. Some or all of the above processing in the platform-specific unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the platform-specific unit can input user attribute information into a generative AI and have the generative AI execute the agent development.

[0125] The platform-specific unit can improve the accuracy of agent development by referring to relevant external databases. For example, the platform-specific unit can refer to external databases and learn the latest patterns of harmful content to improve the accuracy of filtering agent development. The platform-specific unit can also adjust the development algorithm in real time based on information obtained from external databases. For example, the platform-specific unit adjusts the development algorithm in real time based on information obtained from external databases. Furthermore, the platform-specific unit can use external databases to improve the accuracy of filtering agents for specific harmful content. For example, the platform-specific unit uses external databases to improve the accuracy of filtering agents for specific harmful content. This improves the accuracy of agent development by referring to relevant external databases. Some or all of the above processing in the platform-specific unit may be performed using, for example, a generative AI, or without a generative AI. For example, the platform-specific unit can input information from external databases into a generative AI and have the generative AI perform the improvement of development accuracy.

[0126] The user guide unit can estimate the user's emotions and adjust the content of the user guide based on the estimated emotions. For example, the user guide unit can estimate the user's emotions using facial recognition technology. For example, the user guide unit can capture the user's facial expressions with a camera and estimate the emotions using facial recognition technology. The user guide unit can also estimate the user's emotions using text analysis technology. For example, the user guide unit can analyze the user's text messages and estimate the emotions. Furthermore, the user guide unit can also estimate the user's emotions using speech analysis technology. For example, the user guide unit can record the user's voice and estimate the emotions using speech analysis technology. By adjusting the content of the user guide based on the user's emotions, a more appropriate guide can be provided. 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. Some or all of the above-described processing in the user guide unit may be performed using, for example, a generative AI, or without a generative AI. For example, the user guide section can input user emotion data into a generating AI and have the AI ​​perform emotion estimation.

[0127] The user guide unit can optimize the guide content by referring to past user feedback. For example, the user guide unit can refer to past user feedback and provide guide content that improves upon frequently pointed-out issues. The user guide unit can also prioritize providing information that users are looking for based on past feedback. For example, the user guide unit prioritizes providing information that users are looking for based on past feedback. Furthermore, the user guide unit can analyze past feedback in real time and provide optimal guide content. For example, the user guide unit analyzes past feedback in real time and provides optimal guide content. This improves the accuracy of the guide content by referring to past user feedback. Some or all of the above processing in the user guide unit may be performed using, for example, a generative AI, or without a generative AI. For example, the user guide unit can input past feedback data into a generative AI and have the generative AI perform the optimization of the guide content.

[0128] The user guide unit can customize the guide content by considering the user's attribute information. For example, the user guide unit can consider the user's attribute information such as age and gender. For example, the user guide unit can consider the user's attribute information such as age and gender to provide optimal guide content. The user guide unit can also provide customized guide content for users with specific attributes based on the user's attribute information. For example, the user guide unit can provide customized guide content for users with specific attributes based on the user's attribute information. Furthermore, the user guide unit can analyze the user's attribute information in real time to provide optimal guide content. For example, the user guide unit can analyze the user's attribute information in real time to provide optimal guide content. As a result, by considering the user's attribute information, the guide content is customized, and a more appropriate guide is provided. Some or all of the above processing in the user guide unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the user guide unit can input the user's attribute information into a generative AI and have the generative AI perform the customization of the guide content.

[0129] The user guide unit can estimate the user's emotions and adjust the display method of the user guide based on the estimated user emotions. For example, the user guide unit can estimate the user's emotions using facial recognition technology. For example, the user guide unit can capture the user's facial expressions with a camera and estimate the emotions using facial recognition technology. The user guide unit can also estimate the user's emotions using text analysis technology. For example, the user guide unit can analyze the user's text messages and estimate the emotions. Furthermore, the user guide unit can also estimate the user's emotions using speech analysis technology. For example, the user guide unit can record the user's voice and estimate the emotions using speech analysis technology. By adjusting the display method of the user guide based on the user's emotions, a more appropriate guide can be provided. 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. Some or all of the above-described processing in the user guide unit may be performed using a generative AI, for example, or without a generative AI. For example, the user guide section can input user emotion data into a generating AI and have the AI ​​perform emotion estimation.

[0130] The user guide unit can optimize the guide content by referring to relevant external databases. For example, the user guide unit can refer to external databases and optimize the guide content based on the latest information. The user guide unit can also adjust the guide content in real time based on information obtained from external databases. For example, the user guide unit adjusts the guide content in real time based on information obtained from external databases. Furthermore, the user guide unit can use external databases to provide guide content that is optimal for a specific user. For example, the user guide unit uses external databases to provide guide content that is optimal for a specific user. This improves the accuracy of the guide content by referring to relevant external databases. Some or all of the above processing in the user guide unit may be performed using, for example, a generative AI, or without a generative AI. For example, the user guide unit can input information from an external database into a generative AI and have the generative AI perform the optimization of the guide content.

[0131] The user guide unit can customize the guide content by taking into account the user's device information. For example, the user guide unit can take into account the user's device information. For example, if the user is using a smartphone, the user guide unit can provide guide content that is adapted to the screen size. Also, if the user is using a tablet, the user guide unit can provide guide content optimized for a larger screen. Furthermore, if the user is using a smartwatch, the user guide unit can provide concise and highly visible guide content. In this way, by taking into account the user's device information, the guide content is customized, and a more appropriate guide is provided. Some or all of the above processing in the user guide unit may be performed using, for example, a generative AI, or without a generative AI. For example, the user guide unit can input the user's device information into a generative AI and have the generative AI perform the customization of the guide content.

[0132] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0133] The SNS filtering AI agent system can estimate a user's emotions and adjust the filtering intensity based on that estimation. For example, if a user is stressed, the system can increase the filtering intensity and block more harmful content. Conversely, if a user is relaxed, the filtering intensity can be relaxed, blocking only the minimum necessary harmful content. Furthermore, if a user's emotions change rapidly, the system can adjust the filtering intensity in real time to provide optimal filtering. This enables flexible filtering that responds to the user's emotions, providing a more appropriate online environment.

[0134] The SNS filtering AI agent system can optimize its filtering algorithm by referencing the user's past behavior history. For example, if a user has previously shown a strong reaction to a particular type of harmful content, that type of content can be prioritized for blocking. Furthermore, if a user frequently encounters harmful content during certain time periods, the filtering intensity can be increased during those times. In addition, the system can analyze the user's behavior history in real time and dynamically adjust the filtering algorithm. This enables optimal filtering based on user behavior patterns, providing more effective protection.

[0135] The SNS filtering AI agent system can estimate a user's emotions and adjust the notification method of filtering results based on those emotions. For example, if a user is feeling anxious, the system can choose a notification method that gently explains the filtering results. If a user is excited, the system can choose a method that quickly and concisely notifies them of the filtering results. Furthermore, if the user's emotions change, the system can adjust the notification method in real time to provide the most appropriate notification. This enables appropriate notifications tailored to the user's emotions, increasing user understanding and a sense of security.

[0136] The SNS filtering AI agent system can optimize its filtering algorithm by considering the user's device information. For example, if the user is using a smartphone, the system can apply a filtering algorithm optimized for smartphones. Similarly, if the user is using a tablet, it can apply a filtering algorithm optimized for tablets. Furthermore, if the user is using a desktop PC, it can apply a filtering algorithm optimized for desktop PCs. This enables optimal filtering tailored to the user's device, providing more effective protection.

[0137] The SNS filtering AI agent system can estimate the user's emotions and adjust the filtering agent's operating speed based on that estimation. For example, if the user is in a hurry, the system can speed up the filtering agent's operation to quickly block harmful content. Conversely, if the user is relaxed, the system can return the filtering agent's operating speed to normal, providing stable filtering. Furthermore, if the user's emotions change, the system can adjust its operating speed in real time to provide optimal filtering. This enables flexible filtering that responds to the user's emotions, providing a more appropriate online environment.

[0138] The SNS filtering AI agent system can optimize its filtering algorithm by considering the user's geographical information. For example, it can learn patterns of harmful content that frequently occur in a particular region and apply a filtering algorithm tailored to that region. Furthermore, if the user is traveling, the system can apply a filtering algorithm appropriate to their destination. In addition, it can analyze the user's geographical information in real time and dynamically adjust the filtering algorithm. This enables optimal filtering based on the user's geographical information, providing more effective protection.

[0139] The SNS filtering AI agent system can estimate a user's emotions and customize the filtering agent's interface based on those emotions. For example, if a user is stressed, the system can change the interface to a simple and intuitive design to make it easier to use. Conversely, if a user is relaxed, the system can change the interface to a detailed and informative design to allow the user to easily obtain the information they need. Furthermore, if the user's emotions change, the system can adjust the interface in real time to provide the optimal user experience. This ensures that an appropriate interface is provided according to the user's emotions, thereby improving user satisfaction.

[0140] The SNS filtering AI agent system can customize its filtering algorithm by considering user attribute information. For example, it can apply the optimal filtering algorithm based on the user's age, gender, and interests. It can also apply filtering algorithms tailored to the user's occupation and lifestyle. Furthermore, it can analyze user attribute information in real time and dynamically adjust the filtering algorithm. This enables optimal filtering based on user attribute information, providing more effective protection.

[0141] The SNS filtering AI agent system can estimate a user's emotions and adjust the filtering agent's learning parameters based on those estimates. For example, if a user is feeling anxious, the system adjusts the learning parameters to perform more stringent filtering. Conversely, if a user is relaxed, the system adjusts the learning parameters to perform more flexible filtering. Furthermore, if a user's emotions change, the system can adjust the learning parameters in real time to provide optimal filtering. This enables flexible filtering that responds to the user's emotions, providing a more appropriate online environment.

[0142] The SNS filtering AI agent system can optimize its filtering algorithm by referencing past user feedback. For example, if a user has expressed dissatisfaction with filtering results in the past, the algorithm can be improved based on that feedback. Similarly, if a user has given a high rating to a particular filtering result, the algorithm can be strengthened based on that result. Furthermore, it can analyze user feedback in real time and dynamically adjust the filtering algorithm. This enables optimal filtering based on user feedback, providing more effective protection.

[0143] The following briefly describes the processing flow for example form 2.

[0144] Step 1: The detection unit detects harmful content on social media in real time. For example, it uses natural language processing technology to detect harmful text, image recognition technology to detect harmful images, and video analysis technology to detect harmful videos. This makes it possible to detect offensive comments, discriminatory remarks, violent images and pornography, violent acts, and videos containing inappropriate content. Step 2: The blocking unit immediately blocks the harmful content detected by the detection unit. For example, it can block harmful content by applying filtering rules and adjust the blocking strength based on user settings. Furthermore, it has high-speed processing capabilities and blocks harmful content in real time. Step 3: The development department develops filtering agents specifically for each SNS platform. For example, they analyze the characteristics of each platform, develop the optimal filtering agent based on that analysis, evaluate its performance, and make improvements as needed. They also have the capability to rapidly develop filtering agents to support new SNS platforms. Step 4: The interface section provides a user-friendly interface for parents to use the system. For example, it provides an intuitive user interface and a guide to help parents easily configure the system. It also has a function to visually display system usage and filtering results.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] Each of the multiple elements described above, including the detection unit, blocking unit, development unit, interface unit, algorithm unit, platform-specific unit, and user guide unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the detection unit uses the camera 42 and microphone 38B of the smart device 14 to detect harmful content, which is then processed in real time by the control unit 46A. The blocking unit immediately blocks harmful content using the specific processing unit 290 of the data processing unit 12. The development unit develops filtering agents specific to each SNS platform using the specific processing unit 290 of the data processing unit 12. The interface unit provides a user-friendly interface using the control unit 46A of the smart device 14. The algorithm unit implements a filtering algorithm using the specific processing unit 290 of the data processing unit 12. The platform-specific unit develops filtering agents specific to each platform using the specific processing unit 290 of the data processing unit 12. The user guide unit provides a guide for parents using the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0149] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] Each of the multiple elements described above, including the detection unit, blocking unit, development unit, interface unit, algorithm unit, platform-specific unit, and user guide unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the detection unit uses the camera 42 and microphone 238 of the smart glasses 214 to detect harmful content, which is processed in real time by the control unit 46A. The blocking unit immediately blocks harmful content using the specific processing unit 290 of the data processing unit 12. The development unit develops filtering agents specific to each SNS platform using the specific processing unit 290 of the data processing unit 12. The interface unit provides a user-friendly interface using the control unit 46A of the smart glasses 214. The algorithm unit implements filtering algorithms using the specific processing unit 290 of the data processing unit 12. The platform-specific unit develops filtering agents specific to each platform using the specific processing unit 290 of the data processing unit 12. The user guide unit provides a guide for parents using the control unit 46A of the smart glasses 214. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0165] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] Each of the multiple elements described above, including the detection unit, blocking unit, development unit, interface unit, algorithm unit, platform-specific unit, and user guide unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the detection unit uses the camera 42 and microphone 238 of the headset terminal 314 to detect harmful content, which is processed in real time by the control unit 46A. The blocking unit immediately blocks harmful content using the specific processing unit 290 of the data processing unit 12. The development unit develops filtering agents specific to each SNS platform using the specific processing unit 290 of the data processing unit 12. The interface unit provides a user-friendly interface using the control unit 46A of the headset terminal 314. The algorithm unit implements filtering algorithms using the specific processing unit 290 of the data processing unit 12. The platform-specific unit develops filtering agents specific to each platform using the specific processing unit 290 of the data processing unit 12. The user guide unit provides a guide for parents using the control unit 46A of the headset terminal 314. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0181] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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).

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.).

[0194] 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.

[0195] 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.

[0196] 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.

[0197] Each of the multiple elements described above, including the detection unit, blocking unit, development unit, interface unit, algorithm unit, platform-specific unit, and user guide unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the detection unit uses the camera 42 and microphone 238 of the robot 414 to detect harmful content, which is then processed in real time by the control unit 46A. The blocking unit immediately blocks harmful content using the specific processing unit 290 of the data processing unit 12. The development unit develops filtering agents specific to each SNS platform using the specific processing unit 290 of the data processing unit 12. The interface unit provides a user-friendly interface using the control unit 46A of the robot 414. The algorithm unit implements a filtering algorithm using the specific processing unit 290 of the data processing unit 12. The platform-specific unit develops filtering agents specific to each platform using the specific processing unit 290 of the data processing unit 12. The user guide unit provides a guide for parents using the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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."

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] (Note 1) A detection unit that detects harmful content on social media in real time, A blocking unit that blocks harmful content detected by the detection unit, The development department develops filtering agents specialized for each SNS platform, It includes an interface section for parents to use the system. A system characterized by the following features. (Note 2) It further includes an algorithm section that implements specific filtering methods and algorithms. The system described in Appendix 1, characterized by the features described herein. (Note 3) Furthermore, the company has a platform-specific division that develops filtering agents tailored to each platform. The system described in Appendix 1, characterized by the features described herein. (Note 4) It also includes a user guide section that provides guidance for parents to use the system. The system described in Appendix 1, characterized by the features described herein. (Note 5) The detection unit is Detect harmful text, images, and videos on social media in real time. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned block section is The detection unit immediately blocks harmful content detected by the detection unit. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned development department, Develop filtering agents specialized for each social networking platform. The system described in Appendix 1, characterized by the features described herein. (Note 8) The interface unit is Provides a user-friendly interface for parents to use the system. The system described in Appendix 1, characterized by the features described herein. (Note 9) The detection unit is It estimates the user's emotions and adjusts the accuracy of harmful content detection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The detection unit is We optimize the detection algorithm by referring to past patterns of harmful content. The system described in Appendix 1, characterized by the features described herein. (Note 11) The detection unit is Improve detection accuracy by considering the attribute information of content creators. The system described in Appendix 1, characterized by the features described herein. (Note 12) The detection unit is The system estimates user sentiment and determines the priority for detecting harmful content based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The detection unit is Improve detection accuracy by considering the geographical distribution of content. The system described in Appendix 1, characterized by the features described herein. (Note 14) The detection unit is Improve the accuracy of harmful content detection by referencing relevant external databases. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned block section is It estimates the user's emotions and adjusts the timing of blocking based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned block section is Optimize the blocking algorithm by referring to past blocking history. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned block section is Prioritize blocking based on the impact of the content. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned block section is It estimates the user's emotions and adjusts the blocking method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned block section is Improve blocking accuracy by considering the attribute information of content creators. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned block section is Improve block accuracy by referencing relevant external databases. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned development department, The system estimates user sentiment and determines the development priorities for filtering agents based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned development department, We develop the optimal filtering agent by thoroughly analyzing the characteristics of each SNS platform. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned development department, Optimize the development algorithm by referring to past filtering agent performance data. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned development department, We estimate the user's emotions and adjust the development method of the filtering agent based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned development department, Develop a filtering agent that takes into account user attribute information for each social networking service (SNS) platform. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned development department, Improve the accuracy of filtering agent development by referencing relevant external databases. The system described in Appendix 1, characterized by the features described herein. (Note 27) The interface unit is It estimates the user's emotions and adjusts the interface display based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The interface unit is The system selects the optimal display method by referring to the user's past operation history. The system described in Appendix 1, characterized by the features described herein. (Note 29) The interface unit is Customize the displayed content based on the user's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The interface unit is It estimates the user's emotions and adjusts the interface operation procedures based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The interface unit is The optimal display method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 32) The interface unit is Customize the displayed content by referring to related external databases. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned algorithm unit is The system estimates the user's emotions and adjusts the parameters of the filtering algorithm based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned algorithm unit is Optimize the algorithm by referring to past filtering data. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned algorithm unit is The algorithm is customized to take into account the characteristics of each social networking platform. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned algorithm unit is It estimates the user's emotions and adjusts the scope of the filtering algorithm based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned algorithm unit is Improve the accuracy of the algorithm by referencing relevant external databases. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned algorithm unit is The algorithm is customized by taking into account user attribute information for each social networking platform. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned platform-specific unit is, The system estimates user sentiment and determines the development priorities for platform-specific filtering agents based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned platform-specific unit is, We develop the optimal filtering agent by thoroughly analyzing the characteristics of each platform. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned platform-specific unit is, Optimize the development algorithm by referring to past agent performance data. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned platform-specific unit is, We estimate user sentiment and adjust the development method of platform-specific filtering agents based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned platform-specific unit is, Develop agents while considering user attribute information for each platform. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned platform-specific unit is, Improve agent development accuracy by referencing relevant external databases. The system described in Appendix 1, characterized by the features described herein. (Note 45) The user guide section is, We estimate the user's emotions and adjust the content of the user guide based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 46) The user guide section is, We optimize the guide content by referring to past user feedback. The system described in Appendix 1, characterized by the features described herein. (Note 47) The user guide section is, Customize the guide content by taking user attribute information into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 48) The user guide section is, Estimate the user's emotion and adjust the display method of the user guide based on the estimated user emotion The system according to Appendix 1, characterized in that it is such (Appendix 49) The user guide part optimizes the guide content by referring to the relevant external database The system according to Appendix 1, characterized in that it is such (Appendix 50) The user guide part customizes the guide content in consideration of the user's device information The system according to Appendix 1, characterized in that it is such

Explanation of reference signs

[0217] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset-type terminal 414 Robot

Claims

1. A detection unit that detects harmful content on social media in real time, A blocking unit that blocks harmful content detected by the detection unit, The development department develops filtering agents specialized for each SNS platform, It includes an interface section for parents to use the system. A system characterized by the following features.

2. It further includes an algorithm section that implements specific filtering methods and algorithms. The system according to feature 1.

3. Furthermore, the company has a platform-specific division that develops filtering agents tailored to each platform. The system according to feature 1.

4. It also includes a user guide section that provides guidance for parents to use the system. The system according to feature 1.

5. The detection unit is Real-time detection of harmful text, images, and videos on social media. The system according to feature 1.

6. The aforementioned block section is The detection unit immediately blocks the harmful content it detects. The system according to feature 1.

7. The aforementioned development department, Develop filtering agents specialized for each social networking platform. The system according to feature 1.

8. The interface unit is Provides a user-friendly interface for parents to use the system. The system according to feature 1.

9. The detection unit is It estimates the user's emotions and adjusts the accuracy of harmful content detection based on the estimated user emotions. The system according to feature 1.

10. The detection unit is We optimize the detection algorithm by referring to past patterns of harmful content. The system according to feature 1.

11. The detection unit is Improve detection accuracy by considering the attribute information of the content creator. The system according to feature 1.

Images