System

Abstract

To provide a system for preliminarily analyzing article contents to be contributed by a user, and for automatically blocking contents having social risks such as discrimination or slander.SOLUTION: A system includes a contribution content analysis part and an automatic block part. A contribution content analysis part analyzes article contents contributed by a user. The automatic blocking unit automatically blocks an article when the article content analyzed by the contribution content analysis unit includes a content having a social risk such as discrimination, slander, or the like.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology does not adequately detect and automatically block articles posted by users that contain social risks such as discrimination or slander, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze the content of articles posted by users in advance and automatically block content that poses a social risk, such as discrimination or slander. [Means for solving the problem]

[0006] The system according to the embodiment includes a post content analysis unit and an automatic blocking unit. The post content analysis unit analyzes the content of articles posted by users. The automatic blocking unit automatically blocks articles when the article content analyzed by the post content analysis unit contains discriminatory, defamatory, or other content that poses a social risk. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the content of articles posted by users in advance and automatically block content that poses a social risk, such as discrimination or slander. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A social media platform according to an embodiment of the present invention is a system that automatically checks the content of articles posted by users and uses a generation AI to block discriminatory, defamatory, and other socially risky content. This allows the social media platform to check the content of articles posted by users in advance and automatically block discriminatory, defamatory, and other socially risky content, preventing others from viewing them.

[0029] An SNS platform according to an embodiment includes a post content analysis unit and an automatic blocking unit. The post content analysis unit analyzes the content of articles posted by users. For example, the generation AI receives as input the text of an article that a user intends to post and analyzes the content. The generation AI checks the content of the article using a prompt such as, "Does this post contain discriminatory language?" The generation AI can also analyze the context and keywords of the article content using natural language processing technology. For example, the generation AI analyzes the content of the article using a text generation AI (e.g., LLM). The automatic blocking unit automatically blocks an article if the article content analyzed by the post content analysis unit contains discriminatory, defamatory, or other socially risky content. For example, if the generation AI detects discriminatory content such as "All XX people are bad," the automatic blocking unit blocks the article. The automatic blocking unit also prevents others from viewing the blocked article. For example, the blocked article is prevented from appearing on the user's timeline or feed. As a result, the SNS platform according to the embodiment can check the content of articles posted by users in advance and automatically block discriminatory, defamatory, or other content that poses a social risk, preventing others from viewing the content.

[0030] The post content analysis unit can improve the accuracy of judgment by referencing the poster's past posting history and detecting specific patterns. For example, when the generation AI analyzes the posted content, the post content analysis unit refers to the poster's past posting history and detects specific patterns. For example, it may prioritize checking posts by users who have made discriminatory posts in the past. In addition, based on the poster's past posting history, it learns specific expression and phrasing patterns, and the generation AI detects those patterns, improving the accuracy of judgment. For example, it displays a warning if a previously problematic expression is used again. In addition, the generation AI analyzes the poster's past posting history and detects specific patterns to evaluate the risk of the posted content. For example, it strictly checks posts by users who have made defamatory comments in the past. In this way, by referring to the past posting history, it is possible to detect specific patterns and improve the accuracy of judgment.

[0031] The post content analysis unit can infer the poster's intention and detect intentional discrimination or slander. For example, when the generation AI analyzes the content of a post, the post content analysis unit infers the poster's intention and detects intentional discrimination or slander. For example, it determines whether there is an intention to attack a specific group. The context of the post is also analyzed, and the generation AI infers the poster's intention, thereby detecting intentional discrimination or slander. For example, it reads the intention from specific wording and expressions. The generation AI also analyzes the background information of the post content to infer the poster's intention and detect intentional discrimination or slander. For example, it determines the intention based on the poster's past statements and actions. In this way, it is possible to detect intentional discrimination and slander by inferring the poster's intention.

[0032] The post content analysis unit simultaneously analyzes the content of images and videos, and can detect risks contained in media other than text. For example, when the generation AI analyzes the post content, the post content analysis unit simultaneously analyzes the content of images and videos, and can detect risks contained in media other than text. For example, it detects discriminatory images and videos. The generation AI also analyzes the images and videos included in the post content and detects risks contained in media other than text. For example, it detects violent scenes and inappropriate content. The generation AI also analyzes the content of images and videos simultaneously, and can detect risks contained in media other than text. For example, it detects images and videos containing defamatory content. This allows the content of images and videos to be simultaneously analyzed and risks contained in media other than text to be detected.

[0033] The post content analysis unit cross-checks post content across different SNS platforms and can block content that is deemed problematic on other platforms in advance. The post content analysis unit, for example, cross-checks post content across different SNS platforms and blocks content that is deemed problematic on other platforms in advance. For example, it blocks posts that are determined to be discriminatory on other SNS. In addition, the generation AI cross-checks post content across different SNS platforms and blocks content that is deemed problematic in advance. For example, it blocks posts that are determined to be defamatory on other platforms. In addition, it cross-checks post content across different SNS platforms and blocks content that is deemed problematic on other platforms in advance. For example, it blocks posts that are determined to pose a high social risk on other SNS. This makes it possible to cross-check post content across different SNS platforms and block content that is deemed problematic on other platforms in advance.

[0034] The auto-blocking unit can analyze the reason for the block in detail and suggest specific improvements to the user. For example, when the generation AI performs an automatic block, the auto-blocking unit analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it displays a message such as, "This expression is discriminatory. Please consider using a different expression." In addition, in the auto-blocking function, the generation AI analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it displays a message such as, "This post contains defamatory content. Please change the expression to one that is based on specific facts." In addition, when the generation AI performs an automatic block, it analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it displays a message such as, "This post contains content that poses a high social risk. Please consider using expressions that reduce the risk." In this way, the reason for the block can be analyzed in detail and specific improvements can be suggested to the user.

[0035] The auto-blocking unit can temporarily save the content to be blocked, allowing the administrator to check it later. For example, in the auto-blocking function, the generation AI temporarily saves the content to be blocked, allowing the administrator to check it later. For example, a system will be built that allows administrators to review blocked posts. In addition, a function will be introduced that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, a system will be developed that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, a system will be developed that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, a system will be developed that allows the administrator to check detailed information about blocked posts. This will allow the content to be temporarily saved, allowing the administrator to check it later.

[0036] The auto-blocking unit can be strengthened during specific time periods or during specific event periods, allowing for strict monitoring of posts during high-risk periods. The auto-blocking unit, for example, strengthens the auto-blocking function during specific time periods or during specific event periods, allowing for strict monitoring of posts during high-risk periods. For example, it strictly checks post content late at night or during specific event periods. In addition, the generative AI strengthens the auto-blocking function during specific time periods or during event periods, allowing for strict monitoring of posts during high-risk periods. For example, it strictly checks post content during election periods or periods of heightened social tension. In addition, a system can be constructed in which the auto-blocking function is strengthened during specific time periods or during event periods, allowing for strict monitoring of posts during high-risk periods. For example, it strictly checks post content at night or during specific event periods. This allows for the auto-blocking function to be strengthened during specific time periods or during event periods, allowing for strict monitoring of posts during high-risk periods.

[0037] The auto-blocking unit can handle different languages ​​and cultural spheres, and manage risk from a global perspective. The auto-blocking unit, for example, introduces an auto-blocking function that handles different languages ​​and cultural spheres, and manages risk from a global perspective. For example, a multilingual generation AI is used to detect discrimination and defamation in each language. Furthermore, the generation AI introduces an auto-blocking function that handles different languages ​​and cultural spheres, and manages risk from a global perspective. For example, blocking criteria are set that take into account social risks in each cultural sphere. Furthermore, an auto-blocking function that handles different languages ​​and cultural spheres is introduced, and a system that manages risk from a global perspective is constructed. For example, a multilingual generation AI is used to detect defamation in each language. This allows risk management from a global perspective, and manages risk from a global perspective.

[0038] When providing feedback, the post content analysis unit can refer to the user's past posting history and present specific examples of improvement. For example, when the generation AI provides feedback, the post content analysis unit can refer to the user's past posting history and present specific examples of improvement. For example, it can advise the user to avoid expressions that have been problematic in the past. Furthermore, when providing feedback on posted content, the generation AI can refer to the user's past posting history and present specific examples of improvement. For example, it can show how the post should be improved by comparing it with past posts. Furthermore, a system can be constructed in which the generation AI refers to the user's past posting history and presents specific examples of improvement when providing feedback. For example, it can specifically show areas for improvement based on the past posting history. This makes it possible to refer to the user's past posting history and present specific examples of improvement when providing feedback.

[0039] The post content analysis unit customizes the feedback content according to the user's level of understanding, allowing for more effective instruction. The post content analysis unit, for example, customizes the feedback content according to the user's level of understanding, allowing for more effective instruction. For example, it may provide basic advice to beginners and detailed areas for improvement to advanced users. The generation AI also customizes the feedback content according to the user's level of understanding, allowing for more effective instruction. For example, it may adjust the level of advice based on the user's past feedback history. A system may also be built that customizes the feedback content according to the user's level of understanding, allowing for more effective instruction. For example, it may evaluate the user's level of understanding and provide feedback accordingly. This allows for the feedback content to be customized according to the user's level of understanding, allowing for more effective instruction.

[0040] The post content analysis unit can share the feedback content with other users and create community guidelines for improving common problems. The post content analysis unit, for example, shares the feedback content with other users and creates community guidelines for improving common problems. For example, it provides guidelines that summarize common problems and how to improve them. The generation AI also shares the feedback content with other users and creates community guidelines for improving common problems. For example, it updates the guidelines based on the feedback content. A system is also constructed that shares the feedback content with other users and creates community guidelines for improving common problems. For example, it aggregates the feedback content and provides it as guidelines. This makes it possible to share the feedback content with other users and create community guidelines for improving common problems.

[0041] The post content analysis unit can automatically translate feedback messages into different languages ​​to accommodate international users. The post content analysis unit, for example, automatically translates feedback messages into different languages ​​to accommodate international users. For example, it translates into multiple languages ​​such as English, French, and Chinese. In addition, the generation AI automatically translates feedback messages into different languages ​​to accommodate international users. For example, it builds a feedback system that supports multiple languages. In addition, it develops a system that automatically translates feedback messages into different languages ​​to accommodate international users. For example, it automatically translates feedback messages according to the user's language settings. This allows feedback messages to be automatically translated into different languages ​​to accommodate international users.

[0042] The post content analysis unit integrates data from different social media platforms and can learn more diverse patterns. For example, when the generation AI learns, the post content analysis unit integrates data from different social media platforms and learns more diverse patterns. For example, a learning model is built based on data collected from multiple social media platforms. Data from different social media platforms is also integrated so that the generation AI can learn more diverse patterns. For example, patterns of discrimination and defamation on each platform are learned. Furthermore, when the generation AI learns, data from different social media platforms is integrated to build a system that learns more diverse patterns. For example, data from each platform is collected in real time and reflected in the learning model. This allows data from different social media platforms to be integrated and learn more diverse patterns.

[0043] The post content analysis unit can adapt the learning function to different languages ​​and cultural areas to perform risk assessment from a global perspective. The post content analysis unit, for example, adapts the learning function to different languages ​​and cultural areas to perform risk assessment from a global perspective. For example, a multilingual learning model is constructed to learn risks in each language. Furthermore, the generative AI adapts the learning function to different languages ​​and cultural areas to perform risk assessment from a global perspective. For example, learning data that takes into account social risks in each cultural area is used. Furthermore, the learning function is adapted to different languages ​​and cultural areas to build a system that performs risk assessment from a global perspective. For example, a multilingual learning model is updated in real time to learn risks in each language. This allows the learning function to adapt to different languages ​​and cultural areas to perform risk assessment from a global perspective.

[0044] The post content analysis unit can share learning data with other AI models, thereby mutually enhancing learning effects. The post content analysis unit, for example, shares learning data with other AI models, thereby mutually enhancing learning effects. For example, learning data is exchanged between different AI models, improving judgment accuracy. The generation AI also shares learning data with other AI models, thereby mutually enhancing learning effects. For example, the learning model is updated based on data obtained from other AI models. Furthermore, a system is constructed in which learning data is shared with other AI models, thereby mutually enhancing learning effects. For example, data is shared between different AI models in real time, maximizing learning effects. This allows learning data to be shared with other AI models, thereby mutually enhancing learning effects.

[0045] The post content analysis unit can automatically suggest filtering settings based on a user's past posting history and behavioral patterns. The post content analysis unit, for example, automatically suggests filtering settings based on a user's past posting history and behavioral patterns. For example, it adjusts filtering settings based on post content that has been problematic in the past. In addition, the generation AI automatically suggests filtering settings based on a user's past posting history and behavioral patterns. For example, it analyzes a user's behavioral patterns and suggests optimal filtering settings. In addition, a system is constructed that automatically suggests filtering settings based on a user's past posting history and behavioral patterns. For example, it automatically adjusts filtering settings based on a user's posting history. This makes it possible to automatically suggest filtering settings based on a user's past posting history and behavioral patterns.

[0046] The post content analysis unit can save the change history of filtering settings, allowing the user to refer to past settings. The post content analysis unit, for example, saves the change history of filtering settings, allowing the user to refer to past settings. For example, it displays a list of past filtering settings, allowing the user to select. In addition, the generation AI saves the change history of filtering settings, allowing the user to refer to past settings. For example, it suggests optimal settings based on the change history. In addition, a system is constructed that saves the change history of filtering settings, allowing the user to refer to past settings. For example, it automatically adjusts filtering settings based on past settings. This makes it possible to save the change history of filtering settings, allowing the user to refer to past settings.

[0047] The post content analysis unit can share filtering settings between different SNS platforms to perform unified risk management. The post content analysis unit, for example, shares filtering settings between different SNS platforms to perform unified risk management. For example, the same filtering settings are applied across multiple SNSs. The generation AI also shares filtering settings between different SNS platforms to perform unified risk management. For example, it unifies risk management standards across each platform. It also builds a system that shares filtering settings between different SNS platforms to perform unified risk management. For example, it synchronizes the settings of each platform in real time. This allows filtering settings to be shared between different SNS platforms to perform unified risk management.

[0048] The post content analysis unit can adapt filtering settings to different languages ​​and cultural spheres and apply them to users globally. The post content analysis unit, for example, adapts filtering settings to different languages ​​and cultural spheres and applies them to users globally. For example, it provides filtering settings that support multiple languages. Furthermore, the generation AI adapts filtering settings to different languages ​​and cultural spheres and applies them to users globally. For example, it provides settings that take into account risk management standards in each cultural sphere. Furthermore, a system is built that adapts filtering settings to different languages ​​and cultural spheres and applies them to users globally. For example, it updates multilingual filtering settings in real time. This allows filtering settings to be adapted to different languages ​​and cultural spheres and applied to users globally.

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

[0050] The social media platform includes a post content analysis unit that analyzes user posts and an automatic blocking unit that automatically blocks posts. The post content analysis unit analyzes the content of posts posted by users and uses generation AI to detect discriminatory, defamatory, or other socially risky content. For example, the generation AI checks the content of posts using a prompt such as, "Does this post contain discriminatory language?" The generation AI can also analyze the context and keywords of the post content using natural language processing technology. The automatic blocking unit automatically blocks posts analyzed by the post content analysis unit if they contain discriminatory, defamatory, or other socially risky content. For example, if the generation AI detects discriminatory content such as "All people of this kind are bad," it blocks the post. The automatic blocking unit also prevents others from viewing blocked posts. For example, blocked posts are prevented from appearing on users' timelines or feeds. This will enable social media platforms to check the content of articles posted by users in advance and automatically block discriminatory, defamatory, or other content that poses a social risk, preventing others from viewing it.

[0051] The post content analysis unit can improve the accuracy of its judgment by referencing the poster's past posting history and detecting specific patterns. For example, it can prioritize checking posts by users who have made discriminatory posts in the past. It can also learn specific expression and phrasing patterns based on the poster's past posting history, and the generation AI can detect those patterns to improve its judgment accuracy. For example, it can display a warning if a poster uses a previously problematic expression again. The generation AI can also analyze the poster's past posting history and detect specific patterns to evaluate the risk of the post content. For example, it can strictly check posts by users who have made defamatory comments in the past. In this way, it can detect specific patterns by referencing the past posting history, improving its judgment accuracy.

[0052] The post content analysis unit can infer the poster's intention and detect intentional discrimination or slander. For example, it determines whether there is an intention to attack a specific group. In addition, the context of the post content is analyzed, and the generation AI can infer the poster's intention, thereby detecting intentional discrimination or slander. For example, it can read the intention from specific wording and expressions. In addition, the generation AI can analyze the background information of the post content to infer the poster's intention and detect intentional discrimination or slander. For example, it can determine the intention based on the poster's past statements and actions. In this way, it can detect intentional discrimination and slander by inferring the poster's intention.

[0053] The post content analysis unit simultaneously analyzes the content of images and videos, and can detect risks contained in media other than text. For example, it can detect discriminatory images and videos. The generation AI also analyzes the images and videos included in the post content and detects risks contained in media other than text. For example, it can detect violent scenes and inappropriate content. When the generation AI analyzes the post content, it also simultaneously analyzes the content of images and videos and detects risks contained in media other than text. For example, it can detect images and videos containing defamatory content. This allows the content of images and videos to be simultaneously analyzed and risks contained in media other than text to be detected.

[0054] The post content analysis unit cross-checks post content across different social media platforms and can block content that is deemed problematic on other platforms in advance. For example, it blocks posts that are deemed discriminatory on other social media platforms. The generation AI also cross-checks post content across different social media platforms and can block content that is deemed problematic on other platforms in advance. For example, it blocks posts that are deemed defamatory on other platforms. The generation AI also cross-checks post content across different social media platforms and can block content that is deemed problematic on other platforms in advance. For example, it blocks posts that are deemed to pose a high social risk on other social media platforms. This makes it possible to cross-check post content across different social media platforms and block content that is deemed problematic on other platforms in advance.

[0055] The auto-blocking unit can analyze the reason for the block in detail and suggest specific improvements to the user. For example, it can display a message such as, "This expression is discriminatory. Please consider using a different expression." In addition, in the auto-blocking function, the generation AI analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it can display a message such as, "This post contains defamatory content. Please change the expression to one that is based on specific facts." In addition, when the generation AI performs an auto-block, it analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it can display a message such as, "This post contains content that poses a high social risk. Please consider using wording that reduces the risk." This allows for a detailed analysis of the reason for the block and suggests specific improvements to the user.

[0056] The auto-blocking unit can temporarily save the content to be blocked, allowing the administrator to check it later. For example, in the auto-blocking function, the generation AI can temporarily save the content to be blocked, allowing the administrator to check it later. For example, we will build a system that allows administrators to review blocked posts. We will also introduce a function that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, we will allow administrators to view the history of blocked posts. We will also develop a system in the auto-blocking function that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, we will allow administrators to check detailed information about blocked posts. This will allow the content to be temporarily saved, allowing the administrator to check it later.

[0057] The auto-blocking unit can be strengthened during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times. For example, the auto-blocking function can be strengthened during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times. For example, post content can be strictly checked late at night or during specific events. In addition, the generative AI can strengthen the auto-blocking function during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times. For example, post content can be strictly checked during election periods or times of heightened social tension. In addition, the auto-blocking function can be strengthened during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times. For example, post content can be strictly checked late at night or during specific events. This allows for the auto-blocking function to be strengthened during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The post content analysis unit analyzes the content of the article posted by the user. For example, the generation AI receives the text of the article that the user is about to post as input and analyzes its content. The generation AI checks the content of the article using a prompt such as, "Does this post contain discriminatory language?" The generation AI can also use natural language processing technology to analyze the context and keywords of the article content. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze the content of the article. Step 2: The auto-blocking unit automatically blocks articles if the content analyzed by the post content analysis unit is found to be discriminatory, defamatory, or otherwise socially risky. For example, if the generation AI detects discriminatory content such as "all ___ people are bad," the article will be blocked. The auto-blocking unit also prevents others from viewing the blocked article. For example, blocked articles will not appear on users' timelines or feeds.

[0060] (Example 2) A social media platform according to an embodiment of the present invention is a system that automatically checks the content of articles posted by users and uses a generation AI to block discriminatory, defamatory, and other socially risky content. This allows the social media platform to check the content of articles posted by users in advance and automatically block discriminatory, defamatory, and other socially risky content, preventing others from viewing them.

[0061] An SNS platform according to an embodiment includes a post content analysis unit and an automatic blocking unit. The post content analysis unit analyzes the content of articles posted by users. For example, the generation AI receives as input the text of an article that a user intends to post and analyzes the content. The generation AI checks the content of the article using a prompt such as, "Does this post contain discriminatory language?" The generation AI can also analyze the context and keywords of the article content using natural language processing technology. For example, the generation AI analyzes the content of the article using a text generation AI (e.g., LLM). The automatic blocking unit automatically blocks an article if the article content analyzed by the post content analysis unit contains discriminatory, defamatory, or other socially risky content. For example, if the generation AI detects discriminatory content such as "All XX people are bad," the automatic blocking unit blocks the article. The automatic blocking unit also prevents others from viewing the blocked article. For example, the blocked article is prevented from appearing on the user's timeline or feed. As a result, the SNS platform according to the embodiment can check the content of articles posted by users in advance and automatically block discriminatory, defamatory, or other content that poses a social risk, preventing others from viewing the content.

[0062] The post content analysis unit can improve the accuracy of judgment by referencing the poster's past posting history and detecting specific patterns. For example, when the generation AI analyzes the posted content, the post content analysis unit refers to the poster's past posting history and detects specific patterns. For example, it may prioritize checking posts by users who have made discriminatory posts in the past. In addition, based on the poster's past posting history, it learns specific expression and phrasing patterns, and the generation AI detects those patterns, improving the accuracy of judgment. For example, it displays a warning if a previously problematic expression is used again. In addition, the generation AI analyzes the poster's past posting history and detects specific patterns to evaluate the risk of the posted content. For example, it strictly checks posts by users who have made defamatory comments in the past. In this way, by referring to the past posting history, it is possible to detect specific patterns and improve the accuracy of judgment.

[0063] The post content analysis unit can infer the poster's intention and detect intentional discrimination or slander. For example, when the generation AI analyzes the content of a post, the post content analysis unit infers the poster's intention and detects intentional discrimination or slander. For example, it determines whether there is an intention to attack a specific group. The context of the post is also analyzed, and the generation AI infers the poster's intention, thereby detecting intentional discrimination or slander. For example, it reads the intention from specific wording and expressions. The generation AI also analyzes the background information of the post content to infer the poster's intention and detect intentional discrimination or slander. For example, it determines the intention based on the poster's past statements and actions. In this way, it is possible to detect intentional discrimination and slander by inferring the poster's intention.

[0064] The post content analysis unit can use the emotion estimation function to analyze the emotional tone of the post content and prioritize checking posts with strong negative emotions. The post content analysis unit, for example, uses the emotion estimation function to analyze the emotional tone of the post content and prioritize checking posts with strong negative emotions. For example, posts with strong emotions of anger or hatred are detected. The emotional tone of the post content is also analyzed, and the generation AI prioritizes checking posts with strong negative emotions. For example, posts containing emotions of sadness or despair are detected. The emotion estimation function can also be used to analyze the emotional tone of the post content and prioritize checking posts with strong negative emotions. For example, posts containing aggressive language or expressions are detected. This makes it possible to use the emotion estimation function to prioritize checking posts with strong negative emotions.

[0065] The post content analysis unit simultaneously analyzes the content of images and videos, and can detect risks contained in media other than text. For example, when the generation AI analyzes the post content, the post content analysis unit simultaneously analyzes the content of images and videos, and can detect risks contained in media other than text. For example, it detects discriminatory images and videos. The generation AI also analyzes the images and videos included in the post content and detects risks contained in media other than text. For example, it detects violent scenes and inappropriate content. The generation AI also analyzes the content of images and videos simultaneously, and can detect risks contained in media other than text. For example, it detects images and videos containing defamatory content. This allows the content of images and videos to be simultaneously analyzed and risks contained in media other than text to be detected.

[0066] The post content analysis unit cross-checks post content across different SNS platforms and can block content that is deemed problematic on other platforms in advance. The post content analysis unit, for example, cross-checks post content across different SNS platforms and blocks content that is deemed problematic on other platforms in advance. For example, it blocks posts that are determined to be discriminatory on other SNS. In addition, the generation AI cross-checks post content across different SNS platforms and blocks content that is deemed problematic in advance. For example, it blocks posts that are determined to be defamatory on other platforms. In addition, it cross-checks post content across different SNS platforms and blocks content that is deemed problematic on other platforms in advance. For example, it blocks posts that are determined to pose a high social risk on other SNS. This makes it possible to cross-check post content across different SNS platforms and block content that is deemed problematic on other platforms in advance.

[0067] The post content analysis unit can analyze the emotions of the poster when they enter their post content in real time, and display a warning if the negative emotions are strong. The post content analysis unit, for example, uses an emotion estimation function to analyze the emotions of the poster when they enter their post content in real time, and display a warning if the negative emotions are strong. For example, a warning is displayed if the emotions of anger or hatred are strong. The emotion estimation function can also be used to analyze the emotions of the poster when they enter their post content in real time, and display a warning if the negative emotions are strong. For example, a warning is displayed if the emotions of sadness or despair are strong. The emotion estimation function can also be used to analyze the emotions of the poster when they enter their post content in real time, and display a warning if the negative emotions are strong. For example, a warning is displayed if the content contains offensive language or expressions. This makes it possible to analyze the emotions of the poster when they enter their post content in real time, and display a warning if the negative emotions are strong.

[0068] The auto-blocking unit can analyze the reason for the block in detail and suggest specific improvements to the user. For example, when the generation AI performs an automatic block, the auto-blocking unit analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it displays a message such as, "This expression is discriminatory. Please consider using a different expression." In addition, in the auto-blocking function, the generation AI analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it displays a message such as, "This post contains defamatory content. Please change the expression to one that is based on specific facts." In addition, when the generation AI performs an automatic block, it analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it displays a message such as, "This post contains content that poses a high social risk. Please consider using expressions that reduce the risk." In this way, the reason for the block can be analyzed in detail and specific improvements can be suggested to the user.

[0069] The auto-blocking unit can temporarily save the content to be blocked, allowing the administrator to check it later. For example, in the auto-blocking function, the generation AI temporarily saves the content to be blocked, allowing the administrator to check it later. For example, a system will be built that allows administrators to review blocked posts. In addition, a function will be introduced that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, a system will be developed that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, a system will be developed that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, a system will be developed that allows the administrator to check detailed information about blocked posts. This will allow the content to be temporarily saved, allowing the administrator to check it later.

[0070] The auto-blocking unit can be strengthened during specific time periods or during specific event periods, allowing for strict monitoring of posts during high-risk periods. The auto-blocking unit, for example, strengthens the auto-blocking function during specific time periods or during specific event periods, allowing for strict monitoring of posts during high-risk periods. For example, it strictly checks post content late at night or during specific event periods. In addition, the generative AI strengthens the auto-blocking function during specific time periods or during event periods, allowing for strict monitoring of posts during high-risk periods. For example, it strictly checks post content during election periods or periods of heightened social tension. In addition, a system can be constructed in which the auto-blocking function is strengthened during specific time periods or during event periods, allowing for strict monitoring of posts during high-risk periods. For example, it strictly checks post content at night or during specific event periods. This allows for the auto-blocking function to be strengthened during specific time periods or during event periods, allowing for strict monitoring of posts during high-risk periods.

[0071] The auto-blocking unit can handle different languages ​​and cultural spheres, and manage risk from a global perspective. The auto-blocking unit, for example, introduces an auto-blocking function that handles different languages ​​and cultural spheres, and manages risk from a global perspective. For example, a multilingual generation AI is used to detect discrimination and defamation in each language. Furthermore, the generation AI introduces an auto-blocking function that handles different languages ​​and cultural spheres, and manages risk from a global perspective. For example, blocking criteria are set that take into account social risks in each cultural sphere. Furthermore, an auto-blocking function that handles different languages ​​and cultural spheres is introduced, and a system that manages risk from a global perspective is constructed. For example, a multilingual generation AI is used to detect defamation in each language. This allows risk management from a global perspective, and manages risk from a global perspective.

[0072] The auto-blocking unit uses the emotion estimation function to collect users' emotional reactions to blocked posts and use the collected information to improve the blocking criteria. The auto-blocking unit, for example, uses the emotion estimation function to collect users' emotional reactions to blocked posts and use the collected information to improve the blocking criteria. For example, it analyzes how users feel about blocked posts. The generation AI also uses the emotion estimation function to collect users' emotional reactions to blocked posts and use the collected information to improve the blocking criteria. For example, it adjusts the blocking criteria based on user feedback. The emotion estimation function is also used to build a system that collects users' emotional reactions to blocked posts and use the collected information to improve the blocking criteria. For example, it optimizes the blocking criteria based on user emotion data. In this way, the emotion estimation function can be used to collect users' emotional reactions to blocked posts and use the collected information to improve the blocking criteria.

[0073] When providing feedback, the post content analysis unit can refer to the user's past posting history and present specific examples of improvement. For example, when the generation AI provides feedback, the post content analysis unit can refer to the user's past posting history and present specific examples of improvement. For example, it can advise the user to avoid expressions that have been problematic in the past. Furthermore, when providing feedback on posted content, the generation AI can refer to the user's past posting history and present specific examples of improvement. For example, it can show how the post should be improved by comparing it with past posts. Furthermore, a system can be constructed in which the generation AI refers to the user's past posting history and presents specific examples of improvement when providing feedback. For example, it can specifically show areas for improvement based on the past posting history. This makes it possible to refer to the user's past posting history and present specific examples of improvement when providing feedback.

[0074] The post content analysis unit customizes the feedback content according to the user's level of understanding, allowing for more effective instruction. The post content analysis unit, for example, customizes the feedback content according to the user's level of understanding, allowing for more effective instruction. For example, it may provide basic advice to beginners and detailed areas for improvement to advanced users. The generation AI also customizes the feedback content according to the user's level of understanding, allowing for more effective instruction. For example, it may adjust the level of advice based on the user's past feedback history. A system may also be built that customizes the feedback content according to the user's level of understanding, allowing for more effective instruction. For example, it may evaluate the user's level of understanding and provide feedback accordingly. This allows for the feedback content to be customized according to the user's level of understanding, allowing for more effective instruction.

[0075] The post content analysis unit can use the emotion estimation function to adjust the tone of the feedback message and provide it in a format that is easy for the user to accept. The post content analysis unit, for example, uses the emotion estimation function to adjust the tone of the feedback message and provide it in a format that is easy for the user to accept. For example, it can point out areas for improvement in a positive tone. Furthermore, the generation AI can use the emotion estimation function to adjust the tone of the feedback message and provide it in a format that is easy for the user to accept. For example, it can provide feedback with words of encouragement. Furthermore, a system can be constructed that uses the emotion estimation function to adjust the tone of the feedback message and provide it in a format that is easy for the user to accept. For example, it can change the tone of the feedback depending on the user's emotional state. In this way, the emotion estimation function can be used to adjust the tone of the feedback message and provide it in a format that is easy for the user to accept.

[0076] The post content analysis unit can share the feedback content with other users and create community guidelines for improving common problems. The post content analysis unit, for example, shares the feedback content with other users and creates community guidelines for improving common problems. For example, it provides guidelines that summarize common problems and how to improve them. The generation AI also shares the feedback content with other users and creates community guidelines for improving common problems. For example, it updates the guidelines based on the feedback content. A system is also constructed that shares the feedback content with other users and creates community guidelines for improving common problems. For example, it aggregates the feedback content and provides it as guidelines. This makes it possible to share the feedback content with other users and create community guidelines for improving common problems.

[0077] The post content analysis unit can automatically translate feedback messages into different languages ​​to accommodate international users. The post content analysis unit, for example, automatically translates feedback messages into different languages ​​to accommodate international users. For example, it translates into multiple languages ​​such as English, French, and Chinese. In addition, the generation AI automatically translates feedback messages into different languages ​​to accommodate international users. For example, it builds a feedback system that supports multiple languages. In addition, it develops a system that automatically translates feedback messages into different languages ​​to accommodate international users. For example, it automatically translates feedback messages according to the user's language settings. This allows feedback messages to be automatically translated into different languages ​​to accommodate international users.

[0078] The post content analysis unit can use the emotion estimation function to monitor the emotional reactions of users who receive feedback and evaluate the effectiveness of the feedback. The post content analysis unit, for example, uses the emotion estimation function to monitor the emotional reactions of users who receive feedback and evaluate the effectiveness of the feedback. For example, it analyzes the user's emotional changes after feedback. The generation AI also uses the emotion estimation function to monitor the emotional reactions of users who receive feedback and evaluate the effectiveness of the feedback. For example, it evaluates whether positive emotions have increased. A system can also be built that uses the emotion estimation function to monitor the emotional reactions of users who receive feedback and evaluate the effectiveness of the feedback. For example, it measures the effectiveness of the feedback based on the user's emotion data. This makes it possible to use the emotion estimation function to monitor the emotional reactions of users who receive feedback and evaluate the effectiveness of the feedback.

[0079] The post content analysis unit integrates data from different social media platforms and can learn more diverse patterns. For example, when the generation AI learns, the post content analysis unit integrates data from different social media platforms and learns more diverse patterns. For example, a learning model is built based on data collected from multiple social media platforms. Data from different social media platforms is also integrated so that the generation AI can learn more diverse patterns. For example, patterns of discrimination and defamation on each platform are learned. Furthermore, when the generation AI learns, data from different social media platforms is integrated to build a system that learns more diverse patterns. For example, data from each platform is collected in real time and reflected in the learning model. This allows data from different social media platforms to be integrated and learn more diverse patterns.

[0080] The post content analysis unit can use the emotion estimation function to analyze the emotional tone of the training data and prioritize learning from data with strong negative emotions. The post content analysis unit, for example, uses the emotion estimation function to analyze the emotional tone of the training data and prioritize learning from data with strong negative emotions. For example, it focuses on learning from data with strong emotions of anger and hatred. Furthermore, the generative AI uses the emotion estimation function to analyze the emotional tone of the training data and prioritize learning from data with strong negative emotions. For example, it focuses on learning from data with strong emotions of sadness and despair. Furthermore, it uses the emotion estimation function to build a system that analyzes the emotional tone of the training data and prioritizes learning from data with strong negative emotions. For example, it focuses on learning from data that includes aggressive language and expressions. This makes it possible to use the emotion estimation function to analyze the emotional tone of the training data and prioritize learning from data with strong negative emotions.

[0081] The post content analysis unit can adapt the learning function to different languages ​​and cultural areas to perform risk assessment from a global perspective. The post content analysis unit, for example, adapts the learning function to different languages ​​and cultural areas to perform risk assessment from a global perspective. For example, a multilingual learning model is constructed to learn risks in each language. Furthermore, the generative AI adapts the learning function to different languages ​​and cultural areas to perform risk assessment from a global perspective. For example, learning data that takes into account social risks in each cultural area is used. Furthermore, the learning function is adapted to different languages ​​and cultural areas to build a system that performs risk assessment from a global perspective. For example, a multilingual learning model is updated in real time to learn risks in each language. This allows the learning function to adapt to different languages ​​and cultural areas to perform risk assessment from a global perspective.

[0082] The post content analysis unit can share learning data with other AI models, thereby mutually enhancing learning effects. The post content analysis unit, for example, shares learning data with other AI models, thereby mutually enhancing learning effects. For example, learning data is exchanged between different AI models, improving judgment accuracy. The generation AI also shares learning data with other AI models, thereby mutually enhancing learning effects. For example, the learning model is updated based on data obtained from other AI models. Furthermore, a system is constructed in which learning data is shared with other AI models, thereby mutually enhancing learning effects. For example, data is shared between different AI models in real time, maximizing learning effects. This allows learning data to be shared with other AI models, thereby mutually enhancing learning effects.

[0083] The post content analysis unit uses the emotion estimation function to collect users' emotional reactions to the learning data and use the collected information to improve the learning content. The post content analysis unit, for example, uses the emotion estimation function to collect users' emotional reactions to the learning data and use the collected information to improve the learning content. For example, it analyzes the emotions users feel toward the learning data. The generation AI also uses the emotion estimation function to collect users' emotional reactions to the learning data and use the collected information to improve the learning content. For example, it adjusts the learning data based on user feedback. The emotion estimation function is also used to collect users' emotional reactions to the learning data and build a system that is useful for improving the learning content. For example, it optimizes the learning data based on user emotion data. In this way, the emotion estimation function can be used to collect users' emotional reactions to the learning data and use the collected information to improve the learning content.

[0084] The post content analysis unit can automatically suggest filtering settings based on a user's past posting history and behavioral patterns. The post content analysis unit, for example, automatically suggests filtering settings based on a user's past posting history and behavioral patterns. For example, it adjusts filtering settings based on post content that has been problematic in the past. In addition, the generation AI automatically suggests filtering settings based on a user's past posting history and behavioral patterns. For example, it analyzes a user's behavioral patterns and suggests optimal filtering settings. In addition, a system is constructed that automatically suggests filtering settings based on a user's past posting history and behavioral patterns. For example, it automatically adjusts filtering settings based on a user's posting history. This makes it possible to automatically suggest filtering settings based on a user's past posting history and behavioral patterns.

[0085] The post content analysis unit can save the change history of filtering settings, allowing the user to refer to past settings. The post content analysis unit, for example, saves the change history of filtering settings, allowing the user to refer to past settings. For example, it displays a list of past filtering settings, allowing the user to select. In addition, the generation AI saves the change history of filtering settings, allowing the user to refer to past settings. For example, it suggests optimal settings based on the change history. In addition, a system is constructed that saves the change history of filtering settings, allowing the user to refer to past settings. For example, it automatically adjusts filtering settings based on past settings. This makes it possible to save the change history of filtering settings, allowing the user to refer to past settings.

[0086] The post content analysis unit can use the emotion estimation function to evaluate the impact of changes in filtering settings on the user's emotions and suggest optimal settings. The post content analysis unit, for example, uses the emotion estimation function to evaluate the impact of changes in filtering settings on the user's emotions and suggest optimal settings. For example, it analyzes changes in the user's emotions after the settings are changed. In addition, the generation AI uses the emotion estimation function to evaluate the impact of changes in filtering settings on the user's emotions and suggest optimal settings. For example, it suggests settings that increase positive emotions. In addition, a system is constructed that uses the emotion estimation function to evaluate the impact of changes in filtering settings on the user's emotions and suggest optimal settings. For example, it optimizes the settings based on the user's emotion data. In this way, it is possible to use the emotion estimation function to evaluate the impact of changes in filtering settings on the user's emotions and suggest optimal settings.

[0087] The post content analysis unit can share filtering settings between different SNS platforms to perform unified risk management. The post content analysis unit, for example, shares filtering settings between different SNS platforms to perform unified risk management. For example, the same filtering settings are applied across multiple SNSs. The generation AI also shares filtering settings between different SNS platforms to perform unified risk management. For example, it unifies risk management standards across each platform. It also builds a system that shares filtering settings between different SNS platforms to perform unified risk management. For example, it synchronizes the settings of each platform in real time. This allows filtering settings to be shared between different SNS platforms to perform unified risk management.

[0088] The post content analysis unit can adapt filtering settings to different languages ​​and cultural spheres and apply them to users globally. The post content analysis unit, for example, adapts filtering settings to different languages ​​and cultural spheres and applies them to users globally. For example, it provides filtering settings that support multiple languages. Furthermore, the generation AI adapts filtering settings to different languages ​​and cultural spheres and applies them to users globally. For example, it provides settings that take into account risk management standards in each cultural sphere. Furthermore, a system is built that adapts filtering settings to different languages ​​and cultural spheres and applies them to users globally. For example, it updates multilingual filtering settings in real time. This allows filtering settings to be adapted to different languages ​​and cultural spheres and applied to users globally.

[0089] The post content analysis unit uses the emotion estimation function to collect users' emotional reactions to filtering settings and use the collected information to improve the settings. The post content analysis unit, for example, uses the emotion estimation function to collect users' emotional reactions to filtering settings and use the collected information to improve the settings. For example, it analyzes changes in the user's emotions after changing the settings. The generation AI also uses the emotion estimation function to collect users' emotional reactions to filtering settings and use the collected information to improve the settings. For example, it adjusts the settings based on user feedback. The emotion estimation function is also used to build a system that collects users' emotional reactions to filtering settings and use the collected information to improve the settings. For example, it optimizes the settings based on the user's emotional data. In this way, the emotion estimation function can be used to collect users' emotional reactions to filtering settings and use the collected information to improve the settings.

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

[0091] The social media platform includes a post content analysis unit that analyzes user posts and an automatic blocking unit that automatically blocks posts. The post content analysis unit analyzes the content of posts posted by users and uses generation AI to detect discriminatory, defamatory, or other socially risky content. For example, the generation AI checks the content of posts using a prompt such as, "Does this post contain discriminatory language?" The generation AI can also analyze the context and keywords of the post content using natural language processing technology. The automatic blocking unit automatically blocks posts analyzed by the post content analysis unit if they contain discriminatory, defamatory, or other socially risky content. For example, if the generation AI detects discriminatory content such as "All people of this kind are bad," it blocks the post. The automatic blocking unit also prevents others from viewing blocked posts. For example, blocked posts are prevented from appearing on users' timelines or feeds. This will enable social media platforms to check the content of articles posted by users in advance and automatically block discriminatory, defamatory, or other content that poses a social risk, preventing others from viewing it.

[0092] The post content analysis unit can improve the accuracy of its judgment by referencing the poster's past posting history and detecting specific patterns. For example, it can prioritize checking posts by users who have made discriminatory posts in the past. It can also learn specific expression and phrasing patterns based on the poster's past posting history, and the generation AI can detect those patterns to improve its judgment accuracy. For example, it can display a warning if a poster uses a previously problematic expression again. The generation AI can also analyze the poster's past posting history and detect specific patterns to evaluate the risk of the post content. For example, it can strictly check posts by users who have made defamatory comments in the past. In this way, it can detect specific patterns by referencing the past posting history, improving its judgment accuracy.

[0093] The post content analysis unit can infer the poster's intention and detect intentional discrimination or slander. For example, it determines whether there is an intention to attack a specific group. In addition, the context of the post content is analyzed, and the generation AI can infer the poster's intention, thereby detecting intentional discrimination or slander. For example, it can read the intention from specific wording and expressions. In addition, the generation AI can analyze the background information of the post content to infer the poster's intention and detect intentional discrimination or slander. For example, it can determine the intention based on the poster's past statements and actions. In this way, it can detect intentional discrimination and slander by inferring the poster's intention.

[0094] The post content analysis unit uses the emotion estimation function to analyze the emotional tone of the post content and can prioritize checking posts with strong negative emotions. For example, it can detect posts with strong emotions of anger or hatred. The emotional tone of the post content can also be analyzed, and the generation AI can prioritize checking posts with strong negative emotions. For example, it can detect posts that contain emotions of sadness or despair. The emotion estimation function can also be used to analyze the emotional tone of the post content and prioritize checking posts with strong negative emotions. For example, it can detect posts that contain offensive language or expressions. This makes it possible to use the emotion estimation function to prioritize checking posts with strong negative emotions.

[0095] The post content analysis unit simultaneously analyzes the content of images and videos, and can detect risks contained in media other than text. For example, it can detect discriminatory images and videos. The generation AI also analyzes the images and videos included in the post content and detects risks contained in media other than text. For example, it can detect violent scenes and inappropriate content. When the generation AI analyzes the post content, it also simultaneously analyzes the content of images and videos and detects risks contained in media other than text. For example, it can detect images and videos containing defamatory content. This allows the content of images and videos to be simultaneously analyzed and risks contained in media other than text to be detected.

[0096] The post content analysis unit cross-checks post content across different social media platforms and can block content that is deemed problematic on other platforms in advance. For example, it blocks posts that are deemed discriminatory on other social media platforms. The generation AI also cross-checks post content across different social media platforms and can block content that is deemed problematic on other platforms in advance. For example, it blocks posts that are deemed defamatory on other platforms. The generation AI also cross-checks post content across different social media platforms and can block content that is deemed problematic on other platforms in advance. For example, it blocks posts that are deemed to pose a high social risk on other social media platforms. This makes it possible to cross-check post content across different social media platforms and block content that is deemed problematic on other platforms in advance.

[0097] The post content analysis unit analyzes the emotions of posters when they enter their post content in real time, and can display a warning if the emotions are strong. For example, a warning is displayed if the emotions of anger or hatred are strong. The emotion analysis unit also analyzes the emotions of posters when they enter their post content in real time, and the generation AI displays a warning if the emotions are strong. For example, a warning is displayed if the emotions of sadness or despair are strong. The emotion estimation function also analyzes the emotions of posters when they enter their post content in real time, and displays a warning if the emotions are strong. For example, a warning is displayed if the content contains offensive language or expressions. This makes it possible to analyze the emotions of posters when they enter their post content in real time, and display a warning if the emotions are strong.

[0098] The auto-blocking unit can analyze the reason for the block in detail and suggest specific improvements to the user. For example, it can display a message such as, "This expression is discriminatory. Please consider using a different expression." In addition, in the auto-blocking function, the generation AI analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it can display a message such as, "This post contains defamatory content. Please change the expression to one that is based on specific facts." In addition, when the generation AI performs an auto-block, it analyzes the reason for the block in detail and suggests specific improvements to the user. For example, it can display a message such as, "This post contains content that poses a high social risk. Please consider using wording that reduces the risk." This allows for a detailed analysis of the reason for the block and suggests specific improvements to the user.

[0099] The auto-blocking unit can temporarily save the content to be blocked, allowing the administrator to check it later. For example, in the auto-blocking function, the generation AI can temporarily save the content to be blocked, allowing the administrator to check it later. For example, we will build a system that allows administrators to review blocked posts. We will also introduce a function that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, we will allow administrators to view the history of blocked posts. We will also develop a system in the auto-blocking function that allows the generation AI to temporarily save the content to be blocked, allowing the administrator to check it later. For example, we will allow administrators to check detailed information about blocked posts. This will allow the content to be temporarily saved, allowing the administrator to check it later.

[0100] The auto-blocking unit can be strengthened during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times. For example, the auto-blocking function can be strengthened during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times. For example, post content can be strictly checked late at night or during specific events. In addition, the generative AI can strengthen the auto-blocking function during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times. For example, post content can be strictly checked during election periods or times of heightened social tension. In addition, the auto-blocking function can be strengthened during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times. For example, post content can be strictly checked late at night or during specific events. This allows for the auto-blocking function to be strengthened during specific time periods or during specific events, allowing for strict monitoring of posts during high-risk times.

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

[0102] Step 1: The post content analysis unit analyzes the content of the article posted by the user. For example, the generation AI receives the text of the article that the user is about to post as input and analyzes its content. The generation AI checks the content of the article using a prompt such as, "Does this post contain discriminatory language?" The generation AI can also use natural language processing technology to analyze the context and keywords of the article content. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze the content of the article. Step 2: The auto-blocking unit automatically blocks articles if the content analyzed by the post content analysis unit is found to be discriminatory, defamatory, or otherwise socially risky. For example, if the generation AI detects discriminatory content such as "all ___ people are bad," the article will be blocked. The auto-blocking unit also prevents others from viewing the blocked article. For example, blocked articles will not appear on users' timelines or feeds.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

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

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0137] 7, 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.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a post content analysis unit that analyzes the content of articles posted by users; and an automatic blocking unit that automatically blocks an article when the article content analyzed by the post content analysis unit includes discriminatory, slanderous, or other content that poses a social risk. A system characterized by:

2. The post content analysis unit Improve accuracy by checking the poster's past posting history and detecting specific patterns 2. The system of claim 1.

3. The post content analysis unit Inferring the poster's intent and detecting intentional discrimination and defamation 2. The system of claim 1.

4. The post content analysis unit Analyze the emotional tone of posts and prioritize posts with strong negative sentiment.

2. The system of claim 1.

5. The post content analysis unit Simultaneously analyzes the content of images and videos to detect risks contained in media other than text.

2. The system of claim 1.

6. The post content analysis unit Cross-checking the content posted on different social media platforms and blocking content that is problematic on other platforms in advance 2. The system of claim 1.

7. The post content analysis unit Analyzes the emotions of users as they post in real time and displays a warning if the emotions are strong and negative.

2. The system of claim 1.

8. The automatic blocking unit is Analyze the reason for the block in detail and suggest specific improvements to the user.

2. The system of claim 1.

Images