system

Abstract

The system according to this embodiment aims to prevent defamation and slander on social media and comment boards, and to promote constructive discussion. [Solution] The system according to the embodiment comprises a conversion unit, a feedback unit, a point accumulation unit, and a filter unit. The conversion unit analyzes posted messages in real time and converts them into kind words. The feedback unit receives feedback from users on the expressions converted by the conversion unit. The point accumulation unit accumulates points when kind words or positive posts are made. The filter unit imports feeds and comments from other social media platforms.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

[0007] The system according to this embodiment can prevent defamation and slander on social media and comment boards, and promote constructive discussion. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The SNS service according to an embodiment of the present invention is a new SNS service designed to prevent defamation and promote constructive discussion on SNS and comment boards. This SNS service aims to provide a safe and secure environment for everyone by automatically converting all posted words into gentler expressions using AI. First, the AI ​​analyzes user-submitted messages in real time and converts aggressive, negative, or extreme expressions into gentler language. For example, a post saying "XX is the worst" might be converted to something like "XX has room for improvement, but it also has its good points!" This conversion system allows users to express their opinions without unconsciously hurting others. Next, after the AI ​​converts the message into a positive expression, it asks the user for feedback, "Are you satisfied with this expression?" This allows for a balance to be struck, respecting what the user wanted to say as much as possible while maintaining gentleness. Furthermore, "gentleness points" are accumulated when gentle words or positive posts are made, and these are displayed on the user's profile as a user evaluation. When points are accumulated, badges and special features are unlocked. This system provides users with an incentive to use gentle language. Users can also set how "gentle" their posts should be. The platform allows for fine-tuning of tone, from gentle expressions and words of encouragement to friendly remarks and slightly firm criticisms. This enables users to choose expressions that match their intentions. Furthermore, by introducing a filter function that incorporates feeds and comments from other social media platforms, aggressive posts seen on other platforms are transformed into gentler language and displayed. This feature allows users to read comments on other social media platforms with peace of mind. Finally, unique hashtags are introduced to spread kindness. By fostering a culture of sharing kind words, such as "#praiseeachother," "#positivedaily," and "#sharekindness," the entire social media platform becomes a positive space. In this way, the social media service provides a stress-free posting environment and a safe community to use. Using AI natural language processing technology, aggressive expressions and nuances are accurately transformed into gentle language, and efforts are made to transform them into appropriate expressions while respecting the user's intentions.This makes it an ideal platform for people tired of online harassment and those seeking a positive community. It allows social media services to prevent online harassment and promote constructive discussion on social media and comment boards.

[0029] The SNS service according to this embodiment comprises a conversion unit, a feedback unit, a point accumulation unit, and a filter unit. The conversion unit analyzes posted messages in real time and converts them into gentle language. For example, the conversion unit converts aggressive, negative, or extreme expressions into gentle language. For example, the conversion unit converts a post that says "XX is the worst" into something like "XX has room for improvement, but it also has good points!" The conversion unit can also use AI to analyze the context of the post and select the most appropriate gentle expression according to the context. For example, in a critical context, it converts it into a constructive suggestion. In a context of gratitude, it converts it into a warmer expression. In a question context, it converts it into a polite answer. The feedback unit receives feedback from users on the expressions converted by the conversion unit. For example, the feedback unit asks users for feedback, such as "Are you satisfied with this expression?" The feedback unit can maintain gentle language while respecting the user's opinion. For example, if the user is dissatisfied, the feedback unit asks for specific areas for improvement. If the user is satisfied, it asks for positive feedback. If the user is neutral, they are asked for their overall opinion. The point accumulation unit accumulates points when kind words or positive posts are made. For example, the point accumulation unit accumulates "kindness points" when kind words or positive posts are made. The point accumulation unit provides an incentive for users to use kind words. For example, the point accumulation unit awards more points if the user has positive emotions. If the user has negative emotions, it awards fewer points. If the user has neutral emotions, it awards a standard number of points. The filter unit takes in feeds and comments from other social media and converts aggressive posts into kind words for display. For example, the filter unit analyzes the content of posts from other social media and selects the optimal filtering method. The filter unit enables appropriate filtering according to the content of posts from other social media. For example, the filter unit analyzes the content of posts from other social media and converts aggressive expressions into kind words. The filter unit classifies the content of posts from other social media by category and applies the appropriate filtering method.The filtering unit analyzes the content of posts on other social networking services (SNS) in real time and selects the optimal filtering method. As a result, the SNS service according to this embodiment can prevent defamation and slander on SNS and comment boards, and promote constructive discussion.

[0030] The translation unit analyzes posted messages in real time and converts them into gentler language. For example, it converts aggressive, negative, or extreme expressions into gentler language. Specifically, it uses natural language processing technology to analyze the context of the post and select appropriate gentle expressions. For example, it converts a post that says "XX is the worst" to something like "XX has room for improvement, but it also has its good points!" The translation unit can also use AI to analyze the context of the post and select the most appropriate gentle expression for that context. The AI ​​utilizes generative AI and large-scale language models (LLMs) to understand the intent and emotions of the post and convert them into appropriate expressions. For example, in a critical context, it converts it into a constructive suggestion. In a context of gratitude, it converts it into a warmer expression. In a question context, it converts it into a polite answer. This allows the translation unit to promote more positive and constructive communication when users post. Furthermore, the translation unit can learn the user's past posting history and preferences and perform individually optimized translations. For example, it can learn the expressions and phrases that a particular user prefers and convert them into gentle language tailored to that user. This allows the conversion unit to provide customized conversions for each user, resulting in more natural and acceptable expressions.

[0031] The feedback unit receives feedback from users on expressions converted by the conversion unit. For example, the feedback unit might ask users, "Are you satisfied with this expression?" Specifically, it provides an interface for users to rate their satisfaction with the converted expression. Users can rate their satisfaction with a star rating or slider, and can also add comments. The feedback unit can maintain gentle expressions while respecting user opinions. For example, if a user is dissatisfied, it will ask for specific areas for improvement. If a user is satisfied, it will ask for positive feedback. If a user is neutral, it will ask for their overall impression. This allows the feedback unit to collect user opinions and continuously improve the conversion unit's algorithm. Furthermore, the feedback unit can analyze the collected feedback and identify trends and patterns. For example, if many users express dissatisfaction with a particular expression, it can take specific measures to improve that expression. In addition, the feedback unit can adjust the conversion unit's algorithm in real time based on user feedback to provide more appropriate conversions. This allows the feedback unit to increase user satisfaction and improve the overall quality of the SNS service.

[0032] The points accumulation system awards points for kind words and positive posts. For example, it accumulates "kindness points" for kind words and positive posts. Specifically, it analyzes the content of posts and awards points if they contain positive expressions or constructive opinions. The points accumulation system provides an incentive for users to use kind words. For example, it awards more points to users with positive emotions, fewer points to users with negative emotions, and a standard number of points to users with neutral emotions. This motivates users to use kind words and improves the overall atmosphere of the social networking service. Furthermore, the points accumulation system can use the accumulated points to offer benefits and rewards to users. For example, it can award special badges or titles to users who reach a certain point total. It can also grant access to exclusive content or special features using points. This allows the points accumulation system to increase user engagement and promote the use of the social networking service.

[0033] The filtering unit incorporates feeds and comments from other social media platforms, transforming offensive posts into gentler language for display. For example, the filtering unit analyzes the content of posts from other social media platforms and selects the optimal filtering method. Specifically, it analyzes post data obtained from other social media platforms in real time to detect offensive language and negative comments. The filtering unit enables appropriate filtering based on the content of posts from other social media platforms. For example, it analyzes the content of posts from other social media platforms and transforms offensive language into gentler language. The filtering unit categorizes the content of posts from other social media platforms and applies the appropriate filtering method. For example, posts related to political discussions or social issues are filtered with particular care to promote constructive discussion. The filtering unit analyzes the content of posts from other social media platforms in real time and selects the optimal filtering method. This allows the filtering unit to effectively filter offensive posts from other social media platforms and display them to users in gentler language. Furthermore, the filtering unit can continuously improve its filtering algorithm based on user feedback. For example, if a user expresses dissatisfaction with a particular filtering result, the algorithm is adjusted to reflect that feedback. This allows the filtering unit to constantly provide optimal filtering based on the latest information and user feedback, thereby improving the overall quality of the SNS service.

[0034] The conversion unit can convert aggressive, negative, or extreme expressions into gentle language. For example, by converting aggressive expressions into gentle language, the conversion unit can facilitate communication on social media. For example, the conversion unit can convert a post that says "XX is the worst" into something like "XX has room for improvement, but it has its good points too!" For example, the conversion unit can convert a post that says "I hate XX" into something like "XX has room for improvement, but let's look at other aspects too!" For example, the conversion unit can convert a post that says "XX is incompetent" into something like "XX has room for improvement, but it is making an effort!" In this way, by converting aggressive expressions into gentle language, communication on social media can be facilitated. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversion unit can input a post containing aggressive expressions into a generative AI, which can then convert it into gentle language.

[0035] The feedback unit can ask the user for feedback, such as, "Are you satisfied with this expression?" The feedback unit can, for example, maintain gentle language while respecting the user's opinion. If the user is dissatisfied, the feedback unit can ask for specific areas for improvement. If the user is satisfied, the feedback unit can ask for positive feedback. If the user is neutral, the feedback unit can ask for their overall impression. This allows the feedback unit to maintain gentle language while respecting the user's opinion. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input the user's feedback into a generative AI, which can analyze the content of the feedback and suggest an appropriate response.

[0036] The point accumulation unit can accumulate "kindness points" when kind words or positive posts are made. The point accumulation unit can, for example, incentivize users to use kind words. For example, the point accumulation unit will award more points if the user has positive emotions. For example, the point accumulation unit will award fewer points if the user has negative emotions. For example, the point accumulation unit will award a standard number of points if the user has neutral emotions. This can incentivize users to use kind words. Some or all of the above processing in the point accumulation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the point accumulation unit can input the user's post content into a generative AI, which can then analyze the post content and award points.

[0037] The filtering unit can take in feeds and comments from other social media platforms and convert aggressive posts into gentler language for display. For example, the filtering unit can analyze the content of posts from other social media platforms and select the optimal filtering method. For example, the filtering unit can analyze the content of posts from other social media platforms and convert aggressive expressions into gentler language. For example, the filtering unit can classify the content of posts from other social media platforms by category and apply the appropriate filtering method. For example, the filtering unit can analyze the content of posts from other social media platforms in real time and select the optimal filtering method. This allows users to read comments on other social media platforms with peace of mind. Some or all of the above processing in the filtering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the filtering unit can input the content of posts from other social media platforms into a generative AI, which can analyze the content and convert it into gentler language.

[0038] The tone setting section allows users to set how "gentle" their posts will be. The tone setting section allows for fine-tuning of the tone, for example, by using soft language, encouraging words, friendly language, or leaving some slightly strict criticism. The tone setting section allows users to choose language that matches their intentions. For example, if the user selects soft language, the tone setting section will convert the post content to a milder tone. For example, if the user selects encouraging words, the tone setting section will convert the post content to an encouraging tone. For example, if the user selects friendly language, the tone setting section will convert the post content to a friendly tone. This allows users to choose language that matches their intentions. Some or all of the above processing in the tone setting section may be performed using, for example, a generating AI, or not using a generating AI. For example, the tone setting section can input the tone setting selected by the user into a generating AI, and the generating AI can convert the post content to an appropriate tone.

[0039] The hashtag section introduces unique hashtags to spread kindness. The hashtag section can foster a culture of sharing kind words, such as "#praiseeachother," "#positivedailylife," and "#sharekindness." The hashtag section can provide users with an incentive to use kind words. For example, if a user has positive emotions, the hashtag section will suggest positive hashtags. For example, if a user has negative emotions, the hashtag section will suggest encouraging hashtags. For example, if a user has neutral emotions, the hashtag section will suggest general hashtags. This can foster a culture of sharing kind words. Some or all of the above processing in the hashtag section may be performed using, for example, a generative AI, or not using a generative AI. For example, the hashtag section can input the user's emotions into a generative AI, which can then suggest appropriate hashtags.

[0040] The conversion unit can analyze the context of the posted content and select the most appropriate gentle expression for that context. For example, in a critical context, the conversion unit converts it into a constructive suggestion. For example, in a context of gratitude, the conversion unit converts it into a warmer expression. For example, in a question context, the conversion unit converts it into a polite answer. This enables appropriate gentle expression depending on the context. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversion unit can input the posted content into a generative AI, which can analyze the context and select the most appropriate gentle expression.

[0041] The conversion unit can refer to the poster's past posting history and convert it into consistent, gentle language. For example, the conversion unit may reuse gentle language used in the past. For example, the conversion unit may convert it to match the tone of past posts. For example, the conversion unit may select the most appropriate language based on past feedback. This makes consistent, gentle language possible. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the conversion unit can input the poster's past posting history into a generative AI, which can then convert it into consistent, gentle language.

[0042] The conversion unit can apply different conversion algorithms depending on the category of the posted content. For example, the conversion unit applies gentle language that includes technical terms to technical posts. For example, the conversion unit applies gentle language that shows empathy to emotional posts. For example, the conversion unit applies gentle language that includes polite answers to question-based posts. This makes it possible to use appropriate gentle language according to the category. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversion unit can input the category of the posted content into a generative AI, and the generative AI can select the most appropriate gentle language according to the category.

[0043] The conversion unit can take into account the regional characteristics of the posted content and convert it into gentle expressions appropriate for the region. For example, the conversion unit can convert it into expressions that match the local culture and customs. For example, the conversion unit can convert it into expressions that take into account the local language and dialect. For example, the conversion unit can convert it into expressions that take into account the local social background. This makes it possible to use appropriate gentle expressions according to the regional characteristics. Some or all of the above processing in the conversion unit may be performed using, for example, a generation AI, or it may be performed without a generation AI. For example, the conversion unit can input the regional characteristics of the posted content into a generation AI, and the generation AI can convert it into gentle expressions appropriate for the region.

[0044] The feedback unit can analyze the feedback history and select the optimal feedback method for each user. For example, the feedback unit can select a question format preferred by the user based on past feedback history. For example, the feedback unit can analyze past feedback content and select topics of interest to the user. For example, the feedback unit can consider the frequency of past feedback and request feedback at an appropriate time. This enables optimal feedback for each user. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the feedback history into a generative AI, which can then select the optimal feedback method.

[0045] The feedback unit can customize the content of the feedback according to the user's posting frequency. For example, the feedback unit may request detailed feedback from users who post frequently, concise feedback from users who post occasionally, and basic feedback from users who are posting for the first time. This enables appropriate feedback tailored to the user's posting frequency. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input user posting frequency data into a generative AI, which can then select the most appropriate feedback content.

[0046] The point accumulation unit can analyze the point history and select the optimal point awarding method for each user. For example, the point accumulation unit can select a point awarding method preferred by the user based on past point history. For example, the point accumulation unit can analyze past point history and award points for topics of interest to the user. For example, the point accumulation unit can consider the frequency of past point history and award points at an appropriate time. This makes it possible to award points optimally for each user. Some or all of the above processing in the point accumulation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the point accumulation unit can input the point history into a generation AI, which can then select the optimal point awarding method.

[0047] The point accumulation unit can customize the awarding of points according to the user's activity time. For example, if the user is active at night, the point accumulation unit will award more points at night. For example, if the user is active during the day, the point accumulation unit will award more points during the day. For example, if the user is active at irregular times, the point accumulation unit will award points according to the activity time. This makes it possible to award points appropriately according to the user's activity time. Some or all of the above processing in the point accumulation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the point accumulation unit can input user activity time data into a generation AI, and the generation AI can select the optimal point awarding method.

[0048] The filtering unit can analyze the content of posts on other social media platforms and select the optimal filtering method. For example, the filtering unit can analyze the content of posts on other social media platforms and convert aggressive language into milder language. For example, the filtering unit can classify the content of posts on other social media platforms into categories and apply an appropriate filtering method. For example, the filtering unit can analyze the content of posts on other social media platforms in real time and select the optimal filtering method. This enables appropriate filtering according to the content of posts on other social media platforms. Some or all of the above processing in the filtering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the filtering unit can input the content of posts on other social media platforms into a generative AI, which can then select the optimal filtering method.

[0049] The filtering unit can apply different filtering algorithms depending on the category of the content posted on other social media platforms. For example, the filtering unit can apply a neutral filtering algorithm to political posts, an empathetic filtering algorithm to emotional posts, and a filtering algorithm that includes technical terms to technical posts. This enables appropriate filtering according to the category. Some or all of the above processing in the filtering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the filtering unit can input the categories of the content posted on other social media platforms into a generative AI, which can then select the most suitable filtering algorithm.

[0050] The tone setting unit can analyze the user's past tone setting history and propose the optimal tone setting. For example, the tone setting unit proposes the optimal tone setting based on previously used tone settings. For example, the tone setting unit analyzes the user's past tone setting history and proposes a tone setting preferred by the user. For example, the tone setting unit considers the frequency of past tone settings and proposes a tone setting at an appropriate time. This enables appropriate tone settings based on the user's past history. Some or all of the above processing in the tone setting unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the tone setting unit can input the user's past tone setting history into a generating AI, which can then propose the optimal tone setting.

[0051] The tone setting unit can customize tone setting options according to the user's post content. For example, the tone setting unit provides a professional tone option for technical posts. For example, the tone setting unit provides an empathetic tone option for emotional posts. For example, the tone setting unit provides a polite tone option for question-based posts. This makes it possible to select an appropriate tone setting option according to the post content. Some or all of the above processing in the tone setting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the tone setting unit can input the user's post content into a generative AI, which can then select the optimal tone setting option.

[0052] The hashtag section can analyze hashtag usage history and suggest the most suitable hashtags for each user. For example, the hashtag section can suggest the most suitable hashtags based on hashtags used in the past. For example, the hashtag section can analyze past hashtag usage history and suggest hashtags that the user prefers. For example, the hashtag section can consider past hashtag usage frequency and suggest hashtags at the appropriate time. This makes it possible to suggest appropriate hashtags based on the user's usage history. Some or all of the above processing in the hashtag section may be performed using, for example, a generation AI, or without a generation AI. For example, the hashtag section can input hashtag usage history into a generation AI, which can then suggest the most suitable hashtags.

[0053] The hashtag section can customize hashtag suggestions according to the user's post content. For example, the hashtag section can suggest specialized hashtags for technical posts, empathetic hashtags for emotional posts, and polite hashtags for question-based posts. This enables appropriate hashtag suggestions based on the post content. Some or all of the above processing in the hashtag section may be performed using, for example, a generative AI, or without a generative AI. For example, the hashtag section can input the user's post content into a generative AI, which can then suggest the most suitable hashtags.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] SNS services can also include a "translation function." This function can translate user posts into other languages. For example, it can translate a user's Japanese post into English. The translation function can also adjust the translated content to make it more polite. For example, when translating a post containing offensive language, it can convert it into gentler language. This enables gentler communication between users who speak different languages. The translation function can perform translations using generative AI, or it can do so without using generative AI. For example, the translation function can input the post content into a generative AI, which then translates it and converts it into gentler language.

[0056] SNS services can also be equipped with an "image analysis unit." This unit can analyze images posted by users and detect text and facial expressions within the images. For example, if the text in an image contains aggressive language, it can be converted into gentler language. If a person's facial expression in an image is angry, it can be converted into a calm and composed expression. This makes gentler expressions possible even in image-based communication. The image analysis unit can perform image analysis using generative AI, or it can do so without using generative AI. For example, the image analysis unit can input an image into a generative AI, which can then analyze the text and facial expressions within the image and convert them into appropriate expressions.

[0057] SNS services can also be equipped with a "voice analysis unit." This unit can analyze voice messages posted by users and detect words and tones within the audio. For example, if the words in the audio contain aggressive expressions, they can be converted into gentler language. If the tone in the audio is angry, it can be converted into a calm and composed tone. This makes it possible to use gentler expressions even in voice communication. The voice analysis unit can perform voice analysis using a generative AI, or it can do so without a generative AI. For example, the voice analysis unit can input the voice message into a generative AI, which can then analyze the words and tones within the audio and convert them into appropriate expressions.

[0058] SNS services can also incorporate a "content recommendation system." This system can recommend appropriate content based on the user's interests and preferences. For example, if a user is feeling positive emotions, it can recommend enjoyable videos and articles. If a user is feeling negative emotions, it can recommend relaxing music and encouraging messages. If a user is feeling neutral emotions, it can recommend general news and information. This enables appropriate content recommendations tailored to the user's emotions. The content recommendation system can recommend content using generative AI, or it can do so without using generative AI. For example, the content recommendation system can input user emotion data into a generative AI, which can then estimate the emotion and recommend appropriate content.

[0059] SNS services can also include a "community management department." This department can manage the communities that users participate in. For example, it can monitor the content of posts within a community and convert posts containing offensive language into gentler language. If a discussion within a community becomes heated, it can send a message encouraging calm and constructive discussion. This enables healthy communication within the community. The community management department can manage communities using generative AI, or it can do so without using generative AI. For example, the community management department can input the content of posts within a community into a generative AI, which can then suggest appropriate responses.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The conversion unit analyzes posted messages in real time and converts them into gentler language. For example, it converts aggressive, negative, or extreme expressions into gentler language. Specifically, it converts a post that says "XX is the worst" into something like "XX has room for improvement, but it also has its good points!" It also uses AI to analyze the context of the post and selects the most appropriate gentle expression for that context. For example, it converts critical contexts into constructive suggestions, grateful contexts into warmer expressions, and question contexts into polite answers. Step 2: The feedback unit receives feedback from the user on the expression converted by the conversion unit. For example, it asks the user for feedback such as, "Are you satisfied with this expression?" The unit maintains a gentle expression while respecting the user's opinion. Specifically, if the user is dissatisfied, it asks for specific areas for improvement; if satisfied, it asks for positive feedback; and if neutral, it asks for an overall impression. Step 3: The points accumulation section accumulates points when kind words or positive posts are made. For example, "kindness points" are accumulated when kind words or positive posts are made. Users feel incentivized to use kind words. Specifically, if a user has positive emotions, more points are awarded; if they have negative emotions, fewer points are awarded; and if they have neutral emotions, standard points are awarded. Step 4: The filter unit takes in feeds and comments from other social media platforms and converts offensive posts into gentler language for display. For example, it analyzes the content of posts from other social media platforms and selects the optimal filtering method. Specifically, it analyzes the content of posts from other social media platforms, converts offensive expressions into gentler language, classifies them by category, and applies the appropriate filtering method. This helps prevent defamation and slander on social media and comment boards, and promotes constructive discussion.

[0062] (Example of form 2) The SNS service according to an embodiment of the present invention is a new SNS service designed to prevent defamation and promote constructive discussion on SNS and comment boards. This SNS service aims to provide a safe and secure environment for everyone by automatically converting all posted words into gentler expressions using AI. First, the AI ​​analyzes user-submitted messages in real time and converts aggressive, negative, or extreme expressions into gentler language. For example, a post saying "XX is the worst" might be converted to something like "XX has room for improvement, but it also has its good points!" This conversion system allows users to express their opinions without unconsciously hurting others. Next, after the AI ​​converts the message into a positive expression, it asks the user for feedback, "Are you satisfied with this expression?" This allows for a balance to be struck, respecting what the user wanted to say as much as possible while maintaining gentleness. Furthermore, "gentleness points" are accumulated when gentle words or positive posts are made, and these are displayed on the user's profile as a user evaluation. When points are accumulated, badges and special features are unlocked. This system provides users with an incentive to use gentle language. Users can also set how "gentle" their posts should be. The platform allows for fine-tuning of tone, from gentle expressions and words of encouragement to friendly remarks and slightly firm criticisms. This enables users to choose expressions that match their intentions. Furthermore, by introducing a filter function that incorporates feeds and comments from other social media platforms, aggressive posts seen on other platforms are transformed into gentler language and displayed. This feature allows users to read comments on other social media platforms with peace of mind. Finally, unique hashtags are introduced to spread kindness. By fostering a culture of sharing kind words, such as "#praiseeachother," "#positivedaily," and "#sharekindness," the entire social media platform becomes a positive space. In this way, the social media service provides a stress-free posting environment and a safe community to use. Using AI natural language processing technology, aggressive expressions and nuances are accurately transformed into gentle language, and efforts are made to transform them into appropriate expressions while respecting the user's intentions.This makes it an ideal platform for people tired of online harassment and those seeking a positive community. It allows social media services to prevent online harassment and promote constructive discussion on social media and comment boards.

[0063] The SNS service according to this embodiment comprises a conversion unit, a feedback unit, a point accumulation unit, and a filter unit. The conversion unit analyzes posted messages in real time and converts them into gentle language. For example, the conversion unit converts aggressive, negative, or extreme expressions into gentle language. For example, the conversion unit converts a post that says "XX is the worst" into something like "XX has room for improvement, but it also has good points!" The conversion unit can also use AI to analyze the context of the post and select the most appropriate gentle expression according to the context. For example, in a critical context, it converts it into a constructive suggestion. In a context of gratitude, it converts it into a warmer expression. In a question context, it converts it into a polite answer. The feedback unit receives feedback from users on the expressions converted by the conversion unit. For example, the feedback unit asks users for feedback, such as "Are you satisfied with this expression?" The feedback unit can maintain gentle language while respecting the user's opinion. For example, if the user is dissatisfied, the feedback unit asks for specific areas for improvement. If the user is satisfied, it asks for positive feedback. If the user is neutral, they are asked for their overall opinion. The point accumulation unit accumulates points when kind words or positive posts are made. For example, the point accumulation unit accumulates "kindness points" when kind words or positive posts are made. The point accumulation unit provides an incentive for users to use kind words. For example, the point accumulation unit awards more points if the user has positive emotions. If the user has negative emotions, it awards fewer points. If the user has neutral emotions, it awards a standard number of points. The filter unit takes in feeds and comments from other social media and converts aggressive posts into kind words for display. For example, the filter unit analyzes the content of posts from other social media and selects the optimal filtering method. The filter unit enables appropriate filtering according to the content of posts from other social media. For example, the filter unit analyzes the content of posts from other social media and converts aggressive expressions into kind words. The filter unit classifies the content of posts from other social media by category and applies the appropriate filtering method.The filtering unit analyzes the content of posts on other social networking services (SNS) in real time and selects the optimal filtering method. As a result, the SNS service according to this embodiment can prevent defamation and slander on SNS and comment boards, and promote constructive discussion.

[0064] The translation unit analyzes posted messages in real time and converts them into gentler language. For example, it converts aggressive, negative, or extreme expressions into gentler language. Specifically, it uses natural language processing technology to analyze the context of the post and select appropriate gentle expressions. For example, it converts a post that says "XX is the worst" to something like "XX has room for improvement, but it also has its good points!" The translation unit can also use AI to analyze the context of the post and select the most appropriate gentle expression for that context. The AI ​​utilizes generative AI and large-scale language models (LLMs) to understand the intent and emotions of the post and convert them into appropriate expressions. For example, in a critical context, it converts it into a constructive suggestion. In a context of gratitude, it converts it into a warmer expression. In a question context, it converts it into a polite answer. This allows the translation unit to promote more positive and constructive communication when users post. Furthermore, the translation unit can learn the user's past posting history and preferences and perform individually optimized translations. For example, it can learn the expressions and phrases that a particular user prefers and convert them into gentle language tailored to that user. This allows the conversion unit to provide customized conversions for each user, resulting in more natural and acceptable expressions.

[0065] The feedback unit receives feedback from users on expressions converted by the conversion unit. For example, the feedback unit might ask users, "Are you satisfied with this expression?" Specifically, it provides an interface for users to rate their satisfaction with the converted expression. Users can rate their satisfaction with a star rating or slider, and can also add comments. The feedback unit can maintain gentle expressions while respecting user opinions. For example, if a user is dissatisfied, it will ask for specific areas for improvement. If a user is satisfied, it will ask for positive feedback. If a user is neutral, it will ask for their overall impression. This allows the feedback unit to collect user opinions and continuously improve the conversion unit's algorithm. Furthermore, the feedback unit can analyze the collected feedback and identify trends and patterns. For example, if many users express dissatisfaction with a particular expression, it can take specific measures to improve that expression. In addition, the feedback unit can adjust the conversion unit's algorithm in real time based on user feedback to provide more appropriate conversions. This allows the feedback unit to increase user satisfaction and improve the overall quality of the SNS service.

[0066] The points accumulation system awards points for kind words and positive posts. For example, it accumulates "kindness points" for kind words and positive posts. Specifically, it analyzes the content of posts and awards points if they contain positive expressions or constructive opinions. The points accumulation system provides an incentive for users to use kind words. For example, it awards more points to users with positive emotions, fewer points to users with negative emotions, and a standard number of points to users with neutral emotions. This motivates users to use kind words and improves the overall atmosphere of the social networking service. Furthermore, the points accumulation system can use the accumulated points to offer benefits and rewards to users. For example, it can award special badges or titles to users who reach a certain point total. It can also grant access to exclusive content or special features using points. This allows the points accumulation system to increase user engagement and promote the use of the social networking service.

[0067] The filtering unit incorporates feeds and comments from other social media platforms, transforming offensive posts into gentler language for display. For example, the filtering unit analyzes the content of posts from other social media platforms and selects the optimal filtering method. Specifically, it analyzes post data obtained from other social media platforms in real time to detect offensive language and negative comments. The filtering unit enables appropriate filtering based on the content of posts from other social media platforms. For example, it analyzes the content of posts from other social media platforms and transforms offensive language into gentler language. The filtering unit categorizes the content of posts from other social media platforms and applies the appropriate filtering method. For example, posts related to political discussions or social issues are filtered with particular care to promote constructive discussion. The filtering unit analyzes the content of posts from other social media platforms in real time and selects the optimal filtering method. This allows the filtering unit to effectively filter offensive posts from other social media platforms and display them to users in gentler language. Furthermore, the filtering unit can continuously improve its filtering algorithm based on user feedback. For example, if a user expresses dissatisfaction with a particular filtering result, the algorithm is adjusted to reflect that feedback. This allows the filtering unit to constantly provide optimal filtering based on the latest information and user feedback, thereby improving the overall quality of the SNS service.

[0068] The conversion unit can convert aggressive, negative, or extreme expressions into gentle language. For example, by converting aggressive expressions into gentle language, the conversion unit can facilitate communication on social media. For example, the conversion unit can convert a post that says "XX is the worst" into something like "XX has room for improvement, but it has its good points too!" For example, the conversion unit can convert a post that says "I hate XX" into something like "XX has room for improvement, but let's look at other aspects too!" For example, the conversion unit can convert a post that says "XX is incompetent" into something like "XX has room for improvement, but it is making an effort!" In this way, by converting aggressive expressions into gentle language, communication on social media can be facilitated. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversion unit can input a post containing aggressive expressions into a generative AI, which can then convert it into gentle language.

[0069] The feedback unit can ask the user for feedback, such as, "Are you satisfied with this expression?" The feedback unit can, for example, maintain gentle language while respecting the user's opinion. If the user is dissatisfied, the feedback unit can ask for specific areas for improvement. If the user is satisfied, the feedback unit can ask for positive feedback. If the user is neutral, the feedback unit can ask for their overall impression. This allows the feedback unit to maintain gentle language while respecting the user's opinion. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input the user's feedback into a generative AI, which can analyze the content of the feedback and suggest an appropriate response.

[0070] The point accumulation unit can accumulate "kindness points" when kind words or positive posts are made. The point accumulation unit can, for example, incentivize users to use kind words. For example, the point accumulation unit will award more points if the user has positive emotions. For example, the point accumulation unit will award fewer points if the user has negative emotions. For example, the point accumulation unit will award a standard number of points if the user has neutral emotions. This can incentivize users to use kind words. Some or all of the above processing in the point accumulation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the point accumulation unit can input the user's post content into a generative AI, which can then analyze the post content and award points.

[0071] The filtering unit can take in feeds and comments from other social media platforms and convert aggressive posts into gentler language for display. For example, the filtering unit can analyze the content of posts from other social media platforms and select the optimal filtering method. For example, the filtering unit can analyze the content of posts from other social media platforms and convert aggressive expressions into gentler language. For example, the filtering unit can classify the content of posts from other social media platforms by category and apply the appropriate filtering method. For example, the filtering unit can analyze the content of posts from other social media platforms in real time and select the optimal filtering method. This allows users to read comments on other social media platforms with peace of mind. Some or all of the above processing in the filtering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the filtering unit can input the content of posts from other social media platforms into a generative AI, which can analyze the content and convert it into gentler language.

[0072] The tone setting section allows users to set how "gentle" their posts will be. The tone setting section allows for fine-tuning of the tone, for example, by using soft language, encouraging words, friendly language, or leaving some slightly strict criticism. The tone setting section allows users to choose language that matches their intentions. For example, if the user selects soft language, the tone setting section will convert the post content to a milder tone. For example, if the user selects encouraging words, the tone setting section will convert the post content to an encouraging tone. For example, if the user selects friendly language, the tone setting section will convert the post content to a friendly tone. This allows users to choose language that matches their intentions. Some or all of the above processing in the tone setting section may be performed using, for example, a generating AI, or not using a generating AI. For example, the tone setting section can input the tone setting selected by the user into a generating AI, and the generating AI can convert the post content to an appropriate tone.

[0073] The hashtag section introduces unique hashtags to spread kindness. The hashtag section can foster a culture of sharing kind words, such as "#praiseeachother," "#positivedailylife," and "#sharekindness." The hashtag section can provide users with an incentive to use kind words. For example, if a user has positive emotions, the hashtag section will suggest positive hashtags. For example, if a user has negative emotions, the hashtag section will suggest encouraging hashtags. For example, if a user has neutral emotions, the hashtag section will suggest general hashtags. This can foster a culture of sharing kind words. Some or all of the above processing in the hashtag section may be performed using, for example, a generative AI, or not using a generative AI. For example, the hashtag section can input the user's emotions into a generative AI, which can then suggest appropriate hashtags.

[0074] The conversion unit can estimate the user's emotions and adjust the tone of the gentle words it converts based on the estimated emotions. For example, if the user is angry, the conversion unit converts to a calm and composed tone. For example, if the user is sad, the conversion unit converts to an encouraging tone. For example, if the user is happy, the conversion unit converts to an empathetic tone. This makes it possible to express emotions in an appropriate tone according to the user's feelings. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the conversion unit may be performed using a generative AI, or not using a generative AI. For example, the conversion unit can input user emotion data into a generative AI, which can estimate the emotion and convert it to an appropriate tone.

[0075] The conversion unit can analyze the context of the posted content and select the most appropriate gentle expression for that context. For example, in a critical context, the conversion unit converts it into a constructive suggestion. For example, in a context of gratitude, the conversion unit converts it into a warmer expression. For example, in a question context, the conversion unit converts it into a polite answer. This enables appropriate gentle expression depending on the context. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversion unit can input the posted content into a generative AI, which can analyze the context and select the most appropriate gentle expression.

[0076] The conversion unit can refer to the poster's past posting history and convert it into consistent, gentle language. For example, the conversion unit may reuse gentle language used in the past. For example, the conversion unit may convert it to match the tone of past posts. For example, the conversion unit may select the most appropriate language based on past feedback. This makes consistent, gentle language possible. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the conversion unit can input the poster's past posting history into a generative AI, which can then convert it into consistent, gentle language.

[0077] The conversion unit can estimate the user's emotions and adjust the length of the converted expression based on the estimated emotions. For example, if the user is in a hurry, the conversion unit converts the expression to a short and concise one. For example, if the user is relaxed, the conversion unit converts the expression to a detailed one. For example, if the user is excited, the conversion unit converts the expression to a moderately long one. This makes it possible to provide an expression of appropriate length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the conversion unit may be performed using a generative AI, or not using a generative AI. For example, the conversion unit can input user emotion data into a generative AI, which can estimate the emotion and convert it to an appropriate length.

[0078] The conversion unit can apply different conversion algorithms depending on the category of the posted content. For example, the conversion unit applies gentle language that includes technical terms to technical posts. For example, the conversion unit applies gentle language that shows empathy to emotional posts. For example, the conversion unit applies gentle language that includes polite answers to question-based posts. This makes it possible to use appropriate gentle language according to the category. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversion unit can input the category of the posted content into a generative AI, and the generative AI can select the most appropriate gentle language according to the category.

[0079] The conversion unit can take into account the regional characteristics of the posted content and convert it into gentle expressions appropriate for the region. For example, the conversion unit can convert it into expressions that match the local culture and customs. For example, the conversion unit can convert it into expressions that take into account the local language and dialect. For example, the conversion unit can convert it into expressions that take into account the local social background. This makes it possible to use appropriate gentle expressions according to the regional characteristics. Some or all of the above processing in the conversion unit may be performed using, for example, a generation AI, or it may be performed without a generation AI. For example, the conversion unit can input the regional characteristics of the posted content into a generation AI, and the generation AI can convert it into gentle expressions appropriate for the region.

[0080] The feedback unit can estimate the user's emotions and adjust the content of the feedback questions based on the estimated emotions. For example, if the user is dissatisfied, the feedback unit will ask for specific areas for improvement. If the user is satisfied, the feedback unit will ask for positive feedback. If the user is neutral, the feedback unit will ask for their overall impression. This enables appropriate feedback tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using a generative AI, or not. For example, the feedback unit can input user emotion data into a generative AI, which can estimate the emotions and suggest appropriate questions.

[0081] The feedback unit can analyze the feedback history and select the optimal feedback method for each user. For example, the feedback unit can select a question format preferred by the user based on past feedback history. For example, the feedback unit can analyze past feedback content and select topics of interest to the user. For example, the feedback unit can consider the frequency of past feedback and request feedback at an appropriate time. This enables optimal feedback for each user. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the feedback history into a generative AI, which can then select the optimal feedback method.

[0082] The feedback unit can estimate the user's emotions and adjust the timing of feedback based on the estimated emotions. For example, if the user is relaxed, the feedback unit will request feedback immediately. If the user is busy, the feedback unit will request feedback later. If the user is dissatisfied, the feedback unit will request feedback at an appropriate time. This enables feedback at the appropriate time according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using a generative AI, or not using a generative AI. For example, the feedback unit can input user emotion data into a generative AI, which can estimate the emotion and request feedback at an appropriate time.

[0083] The feedback unit can customize the content of the feedback according to the user's posting frequency. For example, the feedback unit may request detailed feedback from users who post frequently, concise feedback from users who post occasionally, and basic feedback from users who are posting for the first time. This enables appropriate feedback tailored to the user's posting frequency. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input user posting frequency data into a generative AI, which can then select the most appropriate feedback content.

[0084] The point accumulation unit can estimate the user's emotions and adjust the point awarding criteria based on the estimated emotions. For example, the point accumulation unit awards more points if the user has positive emotions. For example, the point accumulation unit awards fewer points if the user has negative emotions. For example, the point accumulation unit awards standard points if the user has neutral emotions. This enables appropriate point awarding according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the point accumulation unit may be performed using a generative AI, or not using a generative AI. For example, the point accumulation unit can input user emotion data into a generative AI, which can estimate the emotions and set appropriate point awarding criteria.

[0085] The point accumulation unit can analyze the point history and select the optimal point awarding method for each user. For example, the point accumulation unit can select a point awarding method preferred by the user based on past point history. For example, the point accumulation unit can analyze past point history and award points for topics of interest to the user. For example, the point accumulation unit can consider the frequency of past point history and award points at an appropriate time. This makes it possible to award points optimally for each user. Some or all of the above processing in the point accumulation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the point accumulation unit can input the point history into a generation AI, which can then select the optimal point awarding method.

[0086] The point accumulation unit can estimate the user's emotions and adjust the point display method based on the estimated emotions. For example, if the user has positive emotions, the point accumulation unit will display points prominently. For example, if the user has negative emotions, the point accumulation unit will display points more modestly. For example, if the user has neutral emotions, the point accumulation unit will use a standard display method. This enables appropriate point display according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the point accumulation unit may be performed using a generative AI, or not using a generative AI. For example, the point accumulation unit can input user emotion data into a generative AI, which can estimate the emotions and set an appropriate point display method.

[0087] The point accumulation unit can customize the awarding of points according to the user's activity time. For example, if the user is active at night, the point accumulation unit will award more points at night. For example, if the user is active during the day, the point accumulation unit will award more points during the day. For example, if the user is active at irregular times, the point accumulation unit will award points according to the activity time. This makes it possible to award points appropriately according to the user's activity time. Some or all of the above processing in the point accumulation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the point accumulation unit can input user activity time data into a generation AI, and the generation AI can select the optimal point awarding method.

[0088] The filter unit can estimate the user's emotions and adjust the filter strength based on the estimated emotions. For example, if the user is stressed, the filter unit increases the filter strength. For example, if the user is relaxed, the filter unit decreases the filter strength. For example, if the user has neutral emotions, the filter unit applies a standard filter strength. This allows for an appropriate filter strength according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filter unit may be performed using a generative AI, or not using a generative AI. For example, the filter unit can input user emotion data into a generative AI, which can estimate the emotions and set an appropriate filter strength.

[0089] The filtering unit can analyze the content of posts on other social media platforms and select the optimal filtering method. For example, the filtering unit can analyze the content of posts on other social media platforms and convert aggressive language into milder language. For example, the filtering unit can classify the content of posts on other social media platforms into categories and apply an appropriate filtering method. For example, the filtering unit can analyze the content of posts on other social media platforms in real time and select the optimal filtering method. This enables appropriate filtering according to the content of posts on other social media platforms. Some or all of the above processing in the filtering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the filtering unit can input the content of posts on other social media platforms into a generative AI, which can then select the optimal filtering method.

[0090] The filter unit can estimate the user's emotions and adjust the scope of the filter application based on the estimated emotions. For example, if the user is stressed, the filter unit applies a wide range of filters. If the user is relaxed, the filter unit applies a narrow range of filters. If the user has neutral emotions, the filter unit sets a standard scope of application. This allows for an appropriate filter scope according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filter unit may be performed using a generative AI, or not using a generative AI. For example, the filter unit can input user emotion data into a generative AI, which can estimate the emotions and set an appropriate filter scope.

[0091] The filtering unit can apply different filtering algorithms depending on the category of the content posted on other social media platforms. For example, the filtering unit can apply a neutral filtering algorithm to political posts, an empathetic filtering algorithm to emotional posts, and a filtering algorithm that includes technical terms to technical posts. This enables appropriate filtering according to the category. Some or all of the above processing in the filtering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the filtering unit can input the categories of the content posted on other social media platforms into a generative AI, which can then select the most suitable filtering algorithm.

[0092] The tone setting unit can estimate the user's emotions and suggest tone setting options based on the estimated emotions. For example, if the user is relaxed, the tone setting unit suggests a soft tone option. For example, if the user is tense, the tone setting unit suggests a calm tone option. For example, if the user is excited, the tone setting unit suggests a bright tone option. This enables appropriate tone setting options according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the tone setting unit may be performed using a generative AI, or not using a generative AI. For example, the tone setting unit can input user emotion data into a generative AI, which can estimate the emotion and suggest an appropriate tone setting option.

[0093] The tone setting unit can analyze the user's past tone setting history and propose the optimal tone setting. For example, the tone setting unit proposes the optimal tone setting based on previously used tone settings. For example, the tone setting unit analyzes the user's past tone setting history and proposes a tone setting preferred by the user. For example, the tone setting unit considers the frequency of past tone settings and proposes a tone setting at an appropriate time. This enables appropriate tone settings based on the user's past history. Some or all of the above processing in the tone setting unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the tone setting unit can input the user's past tone setting history into a generating AI, which can then propose the optimal tone setting.

[0094] The tone setting unit can estimate the user's emotions and adjust the tone setting interface based on the estimated emotions. For example, if the user is tense, the tone setting unit provides a simple and highly visible interface. For example, if the user is relaxed, the tone setting unit provides a colorful and fun interface. For example, if the user is tired, the tone setting unit provides an interface with calming colors. This enables an appropriate interface according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the tone setting unit may be performed using a generative AI, or not using a generative AI. For example, the tone setting unit can input user emotion data into a generative AI, which can estimate the emotion and provide an appropriate interface.

[0095] The tone setting unit can customize tone setting options according to the user's post content. For example, the tone setting unit provides a professional tone option for technical posts. For example, the tone setting unit provides an empathetic tone option for emotional posts. For example, the tone setting unit provides a polite tone option for question-based posts. This makes it possible to select an appropriate tone setting option according to the post content. Some or all of the above processing in the tone setting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the tone setting unit can input the user's post content into a generative AI, which can then select the optimal tone setting option.

[0096] The hashtag section can estimate the user's emotions and suggest hashtags based on those emotions. For example, if the user has positive emotions, the hashtag section will suggest positive hashtags. If the user has negative emotions, the hashtag section will suggest encouraging hashtags. If the user has neutral emotions, the hashtag section will suggest general hashtags. This enables appropriate hashtag suggestions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the hashtag section may be performed using a generative AI, or not. For example, the hashtag section can input user emotion data into a generative AI, which can estimate the emotions and suggest appropriate hashtags.

[0097] The hashtag section can analyze hashtag usage history and suggest the most suitable hashtags for each user. For example, the hashtag section can suggest the most suitable hashtags based on hashtags used in the past. For example, the hashtag section can analyze past hashtag usage history and suggest hashtags that the user prefers. For example, the hashtag section can consider past hashtag usage frequency and suggest hashtags at the appropriate time. This makes it possible to suggest appropriate hashtags based on the user's usage history. Some or all of the above processing in the hashtag section may be performed using, for example, a generation AI, or without a generation AI. For example, the hashtag section can input hashtag usage history into a generation AI, which can then suggest the most suitable hashtags.

[0098] The hashtag section can estimate the user's emotions and adjust how hashtags are displayed based on the estimated emotions. For example, if the user has positive emotions, the hashtag section will display hashtags prominently. If the user has negative emotions, the hashtag section will display hashtags discreetly. If the user has neutral emotions, the hashtag section will use a standard display method. This enables appropriate hashtag display according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the hashtag section may be performed using a generative AI, or not. For example, the hashtag section can input user emotion data into a generative AI, which can estimate the emotions and set an appropriate hashtag display method.

[0099] The hashtag section can customize hashtag suggestions according to the user's post content. For example, the hashtag section can suggest specialized hashtags for technical posts, empathetic hashtags for emotional posts, and polite hashtags for question-based posts. This enables appropriate hashtag suggestions based on the post content. Some or all of the above processing in the hashtag section may be performed using, for example, a generative AI, or without a generative AI. For example, the hashtag section can input the user's post content into a generative AI, which can then suggest the most suitable hashtags.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] SNS services can also be equipped with a "sentiment analysis unit." The sentiment analysis unit analyzes user posts and feedback to estimate the user's emotions. For example, it can estimate emotions such as anger, sadness, and joy from the context and wording of a user's posted message. Based on the estimated emotion, the sentiment analysis unit can give appropriate instructions to the conversion unit and feedback unit. For example, if the user is angry, the conversion unit will convert it to a calm and composed tone. If the user is sad, the feedback unit will suggest words of encouragement. This enables appropriate responses according to the user's emotions. The sentiment analysis unit can estimate emotions using generative AI, or it can do so without using generative AI. For example, the sentiment analysis unit can input the user's post content into a generative AI, which can then estimate the emotion and suggest an appropriate response.

[0102] SNS services can also be equipped with a "notification unit." This notification unit can customize the content and timing of notifications that users receive. For example, if a user is experiencing positive emotions, the notification unit can send positive feedback or congratulatory messages. If a user is experiencing negative emotions, the notification unit can send encouraging messages or notifications that promote relaxation. If a user is experiencing neutral emotions, a standard notification can be sent. This enables appropriate notifications tailored to the user's emotions. The notification unit can generate notification content using generative AI, or it can do so without using generative AI. For example, the notification unit can input user emotion data into a generative AI, which can then estimate the emotion and generate appropriate notification content.

[0103] SNS services can also include an "avatar function." This function can change the avatar's facial expressions and actions according to the user's emotions. For example, if the user is happy, the avatar will be displayed with a smile. If the user is sad, the avatar will have a sad expression. If the user is angry, the avatar will have an angry expression. This allows for a visual representation of the user's emotions. The avatar function can generate facial expressions and actions using a generative AI, or it can do so without using a generative AI. For example, the avatar function can input the user's emotional data into a generative AI, which can then estimate the emotion and generate appropriate facial expressions and actions for the avatar.

[0104] SNS services can also include a "reminder function." This function can send reminders to users to achieve their set goals and tasks. For example, if a user is experiencing positive emotions, the reminder function can send encouraging messages. If a user is experiencing negative emotions, the reminder function can send messages to help them relax. If a user is experiencing neutral emotions, a standard reminder can be sent. This allows for appropriate reminders tailored to the user's emotions. The reminder function can generate reminder content using generative AI, or it can do so without using generative AI. For example, the reminder function can input user emotion data into a generative AI, which can then estimate the emotion and generate appropriate reminder content.

[0105] SNS services can also be equipped with an "emotional history section." This section records changes in a user's emotions and allows them to refer to past emotional history. For example, it can check what emotions a user has felt in the past. The emotional history section can analyze the user's emotional tendencies and provide appropriate advice and feedback. For example, if a user has felt negative emotions in the past, the emotional history section can suggest encouraging messages. If a user has felt positive emotions in the past, the emotional history section can suggest congratulatory messages. This enables appropriate responses based on the user's emotions. The emotional history section can analyze emotional history using generative AI, or it can do so without using generative AI. For example, the emotional history section can input user emotional data into a generative AI, which can then analyze the emotions and provide appropriate advice and feedback.

[0106] SNS services can also include a "translation function." This function can translate user posts into other languages. For example, it can translate a user's Japanese post into English. The translation function can also adjust the translated content to make it more polite. For example, when translating a post containing offensive language, it can convert it into gentler language. This enables gentler communication between users who speak different languages. The translation function can perform translations using generative AI, or it can do so without using generative AI. For example, the translation function can input the post content into a generative AI, which then translates it and converts it into gentler language.

[0107] SNS services can also be equipped with an "image analysis unit." This unit can analyze images posted by users and detect text and facial expressions within the images. For example, if the text in an image contains aggressive language, it can be converted into gentler language. If a person's facial expression in an image is angry, it can be converted into a calm and composed expression. This makes gentler expressions possible even in image-based communication. The image analysis unit can perform image analysis using generative AI, or it can do so without using generative AI. For example, the image analysis unit can input an image into a generative AI, which can then analyze the text and facial expressions within the image and convert them into appropriate expressions.

[0108] SNS services can also be equipped with a "voice analysis unit." This unit can analyze voice messages posted by users and detect words and tones within the audio. For example, if the words in the audio contain aggressive expressions, they can be converted into gentler language. If the tone in the audio is angry, it can be converted into a calm and composed tone. This makes it possible to use gentler expressions even in voice communication. The voice analysis unit can perform voice analysis using a generative AI, or it can do so without a generative AI. For example, the voice analysis unit can input the voice message into a generative AI, which can then analyze the words and tones within the audio and convert them into appropriate expressions.

[0109] SNS services can also incorporate a "content recommendation system." This system can recommend appropriate content based on the user's interests and preferences. For example, if a user is feeling positive emotions, it can recommend enjoyable videos and articles. If a user is feeling negative emotions, it can recommend relaxing music and encouraging messages. If a user is feeling neutral emotions, it can recommend general news and information. This enables appropriate content recommendations tailored to the user's emotions. The content recommendation system can recommend content using generative AI, or it can do so without using generative AI. For example, the content recommendation system can input user emotion data into a generative AI, which can then estimate the emotion and recommend appropriate content.

[0110] SNS services can also include a "community management department." This department can manage the communities that users participate in. For example, it can monitor the content of posts within a community and convert posts containing offensive language into gentler language. If a discussion within a community becomes heated, it can send a message encouraging calm and constructive discussion. This enables healthy communication within the community. The community management department can manage communities using generative AI, or it can do so without using generative AI. For example, the community management department can input the content of posts within a community into a generative AI, which can then suggest appropriate responses.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The conversion unit analyzes posted messages in real time and converts them into gentler language. For example, it converts aggressive, negative, or extreme expressions into gentler language. Specifically, it converts a post that says "XX is the worst" into something like "XX has room for improvement, but it also has its good points!" It also uses AI to analyze the context of the post and selects the most appropriate gentle expression for that context. For example, it converts critical contexts into constructive suggestions, grateful contexts into warmer expressions, and question contexts into polite answers. Step 2: The feedback unit receives feedback from the user on the expression converted by the conversion unit. For example, it asks the user for feedback such as, "Are you satisfied with this expression?" The unit maintains a gentle expression while respecting the user's opinion. Specifically, if the user is dissatisfied, it asks for specific areas for improvement; if satisfied, it asks for positive feedback; and if neutral, it asks for an overall impression. Step 3: The points accumulation section accumulates points when kind words or positive posts are made. For example, "kindness points" are accumulated when kind words or positive posts are made. Users feel incentivized to use kind words. Specifically, if a user has positive emotions, more points are awarded; if they have negative emotions, fewer points are awarded; and if they have neutral emotions, standard points are awarded. Step 4: The filter unit takes in feeds and comments from other social media platforms and converts offensive posts into gentler language for display. For example, it analyzes the content of posts from other social media platforms and selects the optimal filtering method. Specifically, it analyzes the content of posts from other social media platforms, converts offensive expressions into gentler language, classifies them by category, and applies the appropriate filtering method. This helps prevent defamation and slander on social media and comment boards, and promotes constructive discussion.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0115] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements described above, including the conversion unit, feedback unit, point accumulation unit, filter unit, tone setting unit, and hashtag unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the conversion unit is implemented by the control unit 46A of the smart device 14, which analyzes posted messages in real time and converts them into gentle language. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which receives feedback from the user on the converted expression. The point accumulation unit is implemented, for example, by the control unit 46A of the smart device 14, which accumulates points when gentle language or positive posts are made. The filter unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which takes in feeds and comments from other social networking services and converts aggressive posts into gentle language for display. The tone setting unit is implemented, for example, by the control unit 46A of the smart device 14, which allows the user to set how "gentle" the tone of their posts should be. The hashtag section is implemented, for example, by the specific processing unit 290 of the data processing device 12, and introduces a unique hashtag to spread kindness. The correspondence between each section and the device or control unit is not limited to the example described above and can be modified in various ways.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

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

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0127] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the conversion unit, feedback unit, point accumulation unit, filter unit, tone setting unit, and hashtag unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the conversion unit is implemented by the control unit 46A of the smart glasses 214, which analyzes posted messages in real time and converts them into gentle language. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which receives feedback from the user on the converted expression. The point accumulation unit is implemented by the control unit 46A of the smart glasses 214, which accumulates points when gentle language or positive posts are made. The filter unit is implemented by the specific processing unit 290 of the data processing unit 12, which takes in feeds and comments from other social media and converts aggressive posts into gentle language for display. The tone setting unit is implemented by the control unit 46A of the smart glasses 214, which allows the user to set how "gentle" the tone of their posts should be. The hashtag section is implemented, for example, by the specific processing unit 290 of the data processing device 12, and introduces a unique hashtag to spread kindness. The correspondence between each section and the device or control unit is not limited to the example described above and can be modified in various ways.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0143] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements described above, including the conversion unit, feedback unit, point accumulation unit, filter unit, tone setting unit, and hashtag unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the conversion unit is implemented by the control unit 46A of the headset terminal 314, which analyzes posted messages in real time and converts them into gentle language. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which receives feedback from the user on the converted expression. The point accumulation unit is implemented by the control unit 46A of the headset terminal 314, which accumulates points when gentle language or positive posts are made. The filter unit is implemented by the specific processing unit 290 of the data processing unit 12, which takes in feeds and comments from other social networking services and converts aggressive posts into gentle language for display. The tone setting unit is implemented by the control unit 46A of the headset terminal 314, which allows the user to set how "gentle" the tone of their posts should be. The hashtag section is implemented, for example, by the specific processing unit 290 of the data processing device 12, and introduces a unique hashtag to spread kindness. The correspondence between each section and the device or control unit is not limited to the example described above and can be modified in various ways.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0157] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the conversion unit, feedback unit, point accumulation unit, filter unit, tone setting unit, and hashtag unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the conversion unit is implemented by the control unit 46A of the robot 414, which analyzes posted messages in real time and converts them into gentle language. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which receives feedback from the user on the converted expression. The point accumulation unit is implemented, for example, by the control unit 46A of the robot 414, which accumulates points when gentle language or positive posts are made. The filter unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which takes in feeds and comments from other social media and converts aggressive posts into gentle language for display. The tone setting unit is implemented, for example, by the control unit 46A of the robot 414, which allows the user to set how "gentle" the tone of their posts should be. The hashtag section is implemented, for example, by the specific processing unit 290 of the data processing device 12, and introduces a unique hashtag to spread kindness. The correspondence between each section and the device or control unit is not limited to the example described above and can be modified in various ways.

[0166] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0168] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0169] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0170] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0174] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0175] 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.

[0176] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0177] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0178] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0179] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0181] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0182] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0183] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0184] (Note 1) A conversion unit that analyzes posted messages in real time and converts them into kind words, A feedback unit that receives feedback from the user regarding the expression converted by the conversion unit, There is a points accumulation section where points are accumulated for kind words and positive posts, It includes a filter section that incorporates feeds and comments from other social media platforms. A system characterized by the following features. (Note 2) The conversion unit is Transforming aggressive, negative, or extreme language into gentler terms. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned feedback unit is We ask users for feedback, such as, "Are you satisfied with this expression?" The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned point accumulation unit is Kind words and positive posts accumulate "kindness points." The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned filter section is It incorporates feeds and comments from other social media platforms and transforms offensive posts into gentler language. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a tone setting section where users can adjust how "gentle" their posts will sound. The system described in Appendix 1, characterized by the features described herein. (Note 7) It features a hashtag section that introduces unique hashtags to spread kindness. The system described in Appendix 1, characterized by the features described herein. (Note 8) The conversion unit is It estimates the user's emotions and adjusts the tone of gentle words based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The conversion unit is The system analyzes the context of the post and selects the most appropriate and gentle expression based on that context. The system described in Appendix 1, characterized by the features described herein. (Note 10) The conversion unit is Refer to the poster's past posting history and translate it into consistent and gentle language. The system described in Appendix 1, characterized by the features described herein. (Note 11) The conversion unit is It estimates the user's emotions and adjusts the length of the converted expression based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The conversion unit is Apply different conversion algorithms depending on the category of the post content. The system described in Appendix 1, characterized by the features described herein. (Note 13) The conversion unit is We will take into account the regional characteristics of the post content and translate it into gentle language appropriate for the region. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned feedback unit is The system estimates the user's emotions and adjusts the feedback questions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned feedback unit is Analyze the feedback history and select the optimal feedback method for each user. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned feedback unit is It estimates the user's emotions and adjusts the timing of feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned feedback unit is Customize the content of feedback based on the user's posting frequency. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned point accumulation unit is The system estimates the user's emotions and adjusts the point awarding criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned point accumulation unit is The system analyzes point history and selects the optimal point awarding method for each user. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned point accumulation unit is The system estimates the user's emotions and adjusts how points are displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned point accumulation unit is Customize point allocation based on the user's activity time. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned filter section is It estimates the user's emotions and adjusts the filter strength based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned filter section is Analyze posts from other social media platforms to select the optimal filtering method. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned filter section is It estimates the user's emotions and adjusts the scope of the filter application based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned filter section is Apply different filtering algorithms depending on the category of content posted on other social media platforms. The system described in Appendix 1, characterized by the features described herein. (Note 26) The tone setting unit is, It estimates the user's emotions and suggests tone setting options based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The tone setting unit is, It analyzes the user's past tone setting history and suggests the optimal tone settings. The system described in Appendix 1, characterized by the features described herein. (Note 28) The tone setting unit is, It estimates the user's emotions and adjusts the tone setting interface based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The tone setting unit is, Customize tone settings options according to the user's post content. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned hashtag section is, It estimates the user's emotions and suggests hashtags based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned hashtag section is, We analyze hashtag usage history and suggest the most suitable hashtags for each user. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned hashtag section is, It estimates the user's sentiment and adjusts how hashtags are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned hashtag section is, Customize hashtag suggestions based on the user's post content. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A conversion unit that analyzes posted messages in real time and converts them into kind words, A feedback unit that receives feedback from the user regarding the expression converted by the conversion unit, There is a points accumulation section where points are accumulated for kind words and positive posts, It includes a filter section that incorporates feeds and comments from other social media platforms. A system characterized by the following features.

2. The conversion unit is Transforming aggressive, negative, or extreme language into gentler terms. The system according to feature 1.

3. The aforementioned feedback unit is We ask users for feedback on whether they were satisfied with the presentation. The system according to feature 1.

4. The aforementioned point accumulation unit is Kind words and positive posts accumulate kindness points. The system according to feature 1.

5. The aforementioned filter section is It incorporates feeds and comments from other social media platforms and transforms offensive posts into gentler language. The system according to feature 1.

6. It includes a tone setting section where users can adjust how gentle their posts will sound. The system according to feature 1.

7. It features a hashtag section that introduces unique hashtags to spread kindness. The system according to feature 1.

8. The conversion unit is It estimates the user's emotions and adjusts the tone of gentle words based on those estimated emotions. The system according to feature 1.

9. The conversion unit is The system analyzes the context of the post and selects the most appropriate and gentle expression based on that context. The system according to feature 1.

10. The conversion unit is Refer to the poster's past posting history and translate it into consistent and gentle language. The system according to feature 1.

Images