system

Abstract

The system according to this embodiment aims to promote healthy discourse by allowing users to perform a simulation before posting a comment. [Solution] The system according to this embodiment comprises a reception unit, a simulation unit, and an advice unit. The reception unit receives comments from posters. The simulation unit simulates responses based on past data, using the comments entered by the reception unit. The advice unit provides advice based on the simulation results obtained by the simulation unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, slander and defamation in the comment section of news sites have been a problem, and there has been a problem that many posters recognize it as appropriate criticism.

[0005] The system according to the embodiment aims to promote sound speech by performing a simulation before a poster posts a comment.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a simulation unit, and an advice unit. The reception unit receives comments from posters. The simulation unit simulates responses based on past data, using the comments entered by the reception unit. The advice unit provides advice based on the simulation results obtained by the simulation unit. [Effects of the Invention]

[0007] The system according to this embodiment can promote healthy discourse by allowing users to perform a simulation before posting a comment. [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 controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

[0019] The smart device 14 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 comment simulation system according to an embodiment of the present invention is a system that provides a virtual space for discourse to reduce slander and defamation in the comment sections of news websites. The comment simulation system allows users to simulate and check reactions in this virtual space before actually posting a comment. This is expected to allow for stress relief and promote healthy discourse. For example, in the comment simulation system, a user inputs a comment. Next, a generating AI simulates reactions to that comment based on a vast amount of past posting data. The simulation results include reactions such as empathy, hostility, and indifference. This allows the user to see in advance how their comment will be received. Furthermore, based on the simulation results, the generating AI provides advice to the user. For example, it suggests ways to soften aggressive expressions or ways to offer more constructive criticism. This allows the user to revise their comment and engage in healthier discourse. The comment simulation system is expected not only to reduce slander and defamation in the comment sections of news websites but also to enhance the user's self-awareness and promote a healthy space for discourse. Additionally, the comment simulation system can increase user motivation by incorporating gamification elements. For example, a system could be implemented where users earn points for posting wholesome comments and receive rewards for doing so. This would allow the comment simulation system to encourage healthy discussion by allowing users to simulate their comments and check the reactions before posting them.

[0029] The comment simulation system according to this embodiment comprises a reception unit, a simulation unit, and an advice unit. The reception unit receives comments from posters. The reception unit can receive comments by methods such as text input, voice input, and image input. The reception unit can also use AI to analyze the content of the input comments and convert them into an appropriate format. For example, the reception unit converts voice-input comments into text. The reception unit can also convert image-input comments into text using OCR technology. The simulation unit uses a generation AI to simulate reactions based on past data, using the comments input by the reception unit. For example, the simulation unit simulates reactions such as empathy, hostility, and indifference based on past comment data and user reaction data. The simulation unit can also use a generation AI to simulate reactions to comments in real time. For example, the simulation unit inputs a comment into the generation AI, and the generation AI generates a reaction based on past data. The advice unit provides advice to the poster based on the simulation results obtained by the simulation unit. For example, the advice unit suggests ways to soften aggressive expressions or ways to offer more constructive criticism. The advice unit can also use AI to analyze simulation results and generate appropriate advice. For example, the advice unit inputs the simulation results into a generating AI, which then generates advice. This allows the comment simulation system according to the embodiment to promote healthy discussion by allowing users to simulate and check reactions before posting comments.

[0030] The reception desk receives comments from posters. The reception desk can accept comments via methods such as text input, voice input, and image input. Specifically, for text input, users can directly input comments using a keyboard. For voice input, users input comments using a microphone, and the reception desk converts this into text using speech recognition technology. For image input, users photograph handwritten notes or printed documents with a camera, and the reception desk converts the characters in the image into text using OCR (optical character recognition) technology. Furthermore, the reception desk can use AI to analyze the content of the input comments and convert them into an appropriate format. For example, when converting voice-input comments to text, the speech recognition AI performs noise reduction and speech clarity to ensure accurate text conversion. For image-input comments, OCR technology is used for character recognition, and the AI ​​can perform contextual analysis to reduce misrecognition. This allows the reception desk to support diverse input methods and process comments accurately and quickly as text data, regardless of the format in which the user inputs them. Furthermore, the reception system also has a function to pre-filter the content of submitted comments, detecting and removing inappropriate language and spam. This helps maintain the overall integrity of the system and provides users with an environment where they can enter comments with peace of mind.

[0031] The simulation unit uses a generative AI to simulate reactions based on comments entered by the reception unit, drawing on past data. Specifically, the simulation unit utilizes a generative AI that has learned from a large amount of past comment data and user reaction data to predict various reactions to the entered comment. For example, it simulates reactions such as empathy, dislike, and indifference, and predicts which reaction will be most frequently received. The simulation unit inputs a comment into the generative AI, which generates a reaction based on past data. The generative AI uses natural language processing technology to understand the content and context of the comment and generate an appropriate reaction. For example, it can simulate reactions of empathy and agreement for positive comments, and reactions of dislike and criticism for negative comments. Furthermore, because the simulation unit can simulate reactions in real time, users can see the reaction immediately after entering a comment. This allows users to understand the impact of their comments in advance and review the content before posting. The simulation unit can also set different scenarios and simulate multiple reactions, providing users with reference information to select the most appropriate comment. This allows the simulation unit to support users in engaging in healthy communication and improve the online environment for discourse.

[0032] The advice section provides advice to commenters based on the simulation results obtained by the simulation section. Specifically, the advice section analyzes the simulation results and generates specific advice on the content and expression of comments. For example, it may suggest ways to soften aggressive language or to offer more constructive criticism. The advice section can also use AI to analyze simulation results and generate appropriate advice. The generating AI evaluates the tone and content of comments based on the simulation results and specifically indicates areas for improvement. For example, it may suggest ways to change aggressive comments to more neutral and constructive language, and for positive comments, it may suggest specific expressions to further evoke empathy. The advice section can also provide individually customized advice by considering the user's past comment history and reaction data. This allows users to understand how their comments are received and communicate more effectively. Furthermore, the advice section can present specific examples and scenarios to make the advice easier for users to accept. For example, it may show how similar comments have been received in the past and suggest areas for improvement based on those results. This allows the advice section to provide specific support to promote healthy discourse by enabling users to review their comments before posting them.

[0033] The Points Management Department provides a system where users can earn points and receive rewards by posting healthy comments. For example, the Points Management Department awards points each time a user posts a healthy comment. The Points Management Department can also use AI to analyze the content of comments and determine whether they are healthy. For example, the Points Management Department inputs comments into a generating AI, which then determines whether the comment is healthy. The Points Management Department awards points for healthy comments, and provides rewards when a certain number of points are accumulated. Rewards include, but are not limited to, point exchange items or service usage rights. This allows the system to provide a way for users to earn points and receive rewards by posting healthy comments.

[0034] The simulation unit can simulate reactions based on a vast amount of past posting data. For example, the simulation unit collects past comment data and user reaction data and simulates reactions based on that data. The simulation unit can also use a generative AI to analyze past data and generate reactions to comments. For example, the simulation unit inputs past data into the generative AI, and the generative AI generates reactions. This improves the accuracy of the simulation by simulating reactions based on a vast amount of past posting data. Some or all of the above-described processes in the simulation unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the simulation unit can input past data into the generative AI, and the generative AI can generate reactions.

[0035] The advice unit can suggest ways to mitigate aggressive language or offer more constructive criticism based on the simulation results. For example, the advice unit can analyze the simulation results and suggest ways to mitigate aggressive language. The advice unit can also use generative AI to analyze the simulation results and generate appropriate advice. For example, the advice unit inputs the simulation results into the generative AI, which then generates advice. This promotes healthy discourse by suggesting ways to mitigate aggressive language or offer more constructive criticism based on the simulation results. Some or all of the above-described processes in the advice unit may be performed using or without the generative AI. For example, the advice unit can input the simulation results into the generative AI, which then generates advice.

[0036] The simulation unit can simulate reactions such as empathy, aversion, and indifference. For example, the simulation unit simulates reactions such as empathy, aversion, and indifference based on past comment data and user reaction data. The simulation unit can also use a generative AI to simulate reactions to comments in real time. For example, the simulation unit inputs a comment into the generative AI, and the generative AI generates a reaction based on past data. This allows the poster to check in advance how their comment will be received by simulating reactions such as empathy, aversion, and indifference. Some or all of the above-described processes in the simulation unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the simulation unit can input a comment into the generative AI, and the generative AI can generate a reaction.

[0037] The advice unit can provide posters with advice on posting healthy comments. For example, the advice unit can analyze simulation results and provide advice on posting healthy comments. The advice unit can also use a generative AI to analyze simulation results and generate appropriate advice. For example, the advice unit can input simulation results into a generative AI, which then generates advice. This promotes healthy discourse by providing posters with advice on posting healthy comments. Some or all of the above-described processes in the advice unit may be performed using a generative AI or not. For example, the advice unit can input simulation results into a generative AI, which then generates advice.

[0038] The reception desk can analyze the poster's past comment history and suggest the optimal input method. For example, the reception desk can automatically display expressions and phrases that the poster has frequently used in the past as suggestions. The reception desk can also use a generative AI to analyze the past comment history and suggest an appropriate input method. For example, the reception desk can input the past comment history into the generative AI, which will then suggest the optimal input method. This streamlines comment input by analyzing the poster's past comment history and suggesting the optimal input method. Some or all of the above processing in the reception desk may be performed using a generative AI, or it may be performed without using a generative AI. For example, the reception desk can input the past comment history into the generative AI, which will then suggest the optimal input method.

[0039] The reception desk can provide input assistance based on the commenter's current interests and topics when they enter a comment. For example, the reception desk can automatically suggest keywords related to news articles the commenter is currently interested in. The reception desk can also use a generative AI to analyze the commenter's current interests and topics and provide appropriate input assistance. For example, the reception desk can input the commenter's current interests and topics into the generative AI, which will then provide input assistance. This streamlines the comment entry process by providing input assistance based on the commenter's current interests and topics. Some or all of the above-described processes in the reception desk may be performed using a generative AI, or they may not be performed using a generative AI. For example, the reception desk can input the commenter's current interests and topics into the generative AI, which will then provide input assistance.

[0040] The reception system can prioritize displaying highly relevant topics when a comment is entered, taking into account the poster's geographical location. For example, if the poster is in a specific region, the reception system will prioritize displaying news articles related to that region. The reception system can also use a generative AI to analyze the poster's geographical location and display appropriate topics. For example, the reception system can input geographical location information into the generative AI, which will then display highly relevant topics. This streamlines the comment entry process by prioritizing the display of highly relevant topics based on the poster's geographical location. Some or all of the above processing in the reception system may be performed using a generative AI, or it may be performed without using a generative AI. For example, the reception system can input geographical location information into the generative AI, which will then display highly relevant topics.

[0041] The reception desk can analyze the poster's social media activity when a comment is entered and suggest relevant topics. For example, the reception desk can suggest topics related to posts the poster has recently "liked." The reception desk can also use generative AI to analyze social media activity and suggest appropriate topics. For example, the reception desk can input social media activity data into the generative AI, which then suggests relevant topics. This streamlines the comment entry process by analyzing the poster's social media activity and suggesting relevant topics. Some or all of the above processing in the reception desk may be performed using generative AI, or it may be performed without using generative AI. For example, the reception desk can input social media activity data into the generative AI, which then suggests relevant topics.

[0042] The simulation unit can improve the accuracy of the simulation by considering the relationships between comments during the simulation. For example, if a comment is a reply to another comment, the simulation unit will consider that relationship when performing the simulation. The simulation unit can also use a generation AI to analyze the relationships between comments and perform an appropriate simulation. For example, the simulation unit can input the relationship data of comments into the generation AI, and the generation AI will perform the simulation. This improves the accuracy of the simulation by considering the relationships between comments. Some or all of the above processing in the simulation unit may be performed using the generation AI, or it may be performed without using the generation AI. For example, the simulation unit can input the relationship data of comments into the generation AI, and the generation AI can perform the simulation.

[0043] The simulation unit can perform simulations while considering the attribute information of the commenter. For example, the simulation unit can simulate responses from people of the same age group based on the commenter's age group. The simulation unit can also use a generative AI to analyze the commenter's attribute information and perform an appropriate simulation. For example, the simulation unit inputs the commenter's attribute information data into the generative AI, and the generative AI performs the simulation. This improves the accuracy of the simulation by considering the attribute information of the commenter. Some or all of the above processing in the simulation unit may be performed using the generative AI, or it may be performed without using the generative AI. For example, the simulation unit can input the commenter's attribute information data into the generative AI, and the generative AI can perform the simulation.

[0044] The simulation unit can perform simulations while considering the geographical distribution of comments. For example, if a comment is related to a specific region, the simulation unit will simulate the response in that region. The simulation unit can also use a generative AI to analyze the geographical distribution of comments and perform an appropriate simulation. For example, the simulation unit inputs geographical distribution data into the generative AI, and the generative AI performs the simulation. This improves the accuracy of the simulation by considering the geographical distribution of comments. Some or all of the above-described processes in the simulation unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the simulation unit can input geographical distribution data into the generative AI, and the generative AI can perform the simulation.

[0045] The simulation unit can improve the accuracy of the simulation by referring to relevant literature for the comments during the simulation. For example, if the comment is related to a specific study, the simulation unit will perform the simulation based on past responses to that study. The simulation unit can also use a generative AI to analyze relevant literature and perform an appropriate simulation. For example, the simulation unit can input relevant literature data into the generative AI, and the generative AI will perform the simulation. This improves the accuracy of the simulation by referring to relevant literature for the comments. Some or all of the above processing in the simulation unit may be performed using the generative AI, or it may be performed without the generative AI. For example, the simulation unit can input relevant literature data into the generative AI, and the generative AI can perform the simulation.

[0046] The advice unit can adjust the level of detail of the advice based on the importance of the comment when providing advice. For example, the advice unit will provide detailed advice for comments of high importance. The advice unit can also use a generative AI to analyze the importance of comments and set an appropriate level of detail. For example, the advice unit can input comment importance data into the generative AI, and the generative AI can adjust the level of detail. This ensures that appropriate advice is provided by adjusting the level of detail of the advice based on the importance of the comment. Some or all of the above processing in the advice unit may be performed using a generative AI or not. For example, the advice unit can input comment importance data into the generative AI, and the generative AI can adjust the level of detail.

[0047] The advice unit can apply different advice algorithms depending on the category of the comment when providing advice. For example, the advice unit provides calm and objective advice to comments on politics. The advice unit can also use a generative AI to analyze the category of the comment and apply an appropriate advice algorithm. For example, the advice unit inputs the category data of the comment into the generative AI, and the generative AI applies an advice algorithm. This allows for more appropriate advice to be provided by applying different advice algorithms depending on the category of the comment. Some or all of the above processing in the advice unit may be performed using the generative AI or not. For example, the advice unit can input the category data of the comment into the generative AI, and the generative AI can apply an advice algorithm.

[0048] The advice unit can determine the priority of advice based on when the comments were submitted. For example, the advice unit can prioritize advice for the most recent comments. The advice unit can also use a generative AI to analyze the submission timing of comments and set appropriate priorities. For example, the advice unit inputs the submission timing data of comments into the generative AI, and the generative AI determines the priority. This ensures that advice is provided quickly to the most recent comments by prioritizing advice based on the submission timing of comments. Some or all of the above processing in the advice unit may be performed using a generative AI or not. For example, the advice unit can input the submission timing data of comments into the generative AI, and the generative AI can determine the priority.

[0049] The advice unit can adjust the order of advice based on the relevance of the comments when providing advice. For example, the advice unit will prioritize providing advice to comments with high relevance. The advice unit can also use a generative AI to analyze the relevance of comments and set an appropriate order. For example, the advice unit can input comment relevance data into the generative AI, and the generative AI can adjust the order. This adjusts the order of advice based on the relevance of the comments, thereby prioritizing the provision of advice to highly relevant comments. Some or all of the above processing in the advice unit may be performed using a generative AI or not. For example, the advice unit can input comment relevance data into the generative AI, and the generative AI can adjust the order.

[0050] The point management unit can optimize the point awarding algorithm by referring to past point history during point management. For example, the point management unit can analyze patterns of comments that have previously earned high points from posters and optimize the point awarding algorithm. The point management unit can also use a generation AI to analyze past point history and set an appropriate algorithm. For example, the point management unit can input past point history data into the generation AI, and the generation AI can optimize the algorithm. This improves the accuracy of point awarding by optimizing the point awarding algorithm by referring to past point history. Some or all of the above processes in the point management unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the point management unit can input past point history data into a generation AI, and the generation AI can optimize the algorithm.

[0051] The point management unit can weight points based on the submission date of comments during point management. For example, the point management unit can assign higher points to the most recent comments. The point management unit can also use a generation AI to analyze the submission date of comments and set appropriate weights. For example, the point management unit inputs the comment submission date data into the generation AI, and the generation AI performs the weighting. This weighting of points based on the submission date of comments results in higher points being assigned to the most recent comments. Some or all of the above processing in the point management unit may be performed using the generation AI, or it may be performed without using the generation AI. For example, the point management unit can input the comment submission date data into the generation AI, and the generation AI can perform the weighting.

[0052] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0053] The comment simulation system can also include a feedback unit. The feedback unit collects feedback on the simulation results after the poster receives them. For example, it might ask the poster how they felt about the simulation results, what parts were helpful, and what could be improved. The feedback unit can analyze the collected feedback and use it to improve the algorithms of the simulation and advice units. This improves the overall accuracy and usability of the system. The feedback unit can also use generative AI to analyze the feedback and extract appropriate areas for improvement. For example, the feedback unit can input feedback data into the generative AI, which can then suggest improvements.

[0054] The comment simulation system can also include a learning section. This learning section provides educational content to help commenters post healthy comments. For example, it could offer videos or articles on the importance of healthy speech and how to avoid offensive language. The learning section could also provide individually customized educational content based on the commenter's simulation results and feedback. This allows commenters to learn specific ways to improve the quality of their comments. The learning section could also use generative AI to suggest the most suitable educational content for the commenter. For example, the learning section could input the commenter's simulation results into the generative AI, which could then suggest appropriate educational content.

[0055] The comment simulation system can also include a moderation unit. The moderation unit monitors whether a comment is appropriate after it has been posted. For example, it can analyze posted comments in real time and issue warnings if they contain slander or offensive language. The moderation unit can also use a generative AI to analyze posted comments and suggest appropriate actions. For instance, the moderation unit can input comment data into the generative AI, which can then issue warnings or suggest deletions. This helps maintain a healthy environment for discussion in the comment sections of news websites.

[0056] The comment simulation system can also include a community section. This section helps contributors form communities to promote healthy discourse. For example, it could provide forums or chat rooms to connect users who have posted healthy comments. The community section could also use generative AI to suggest appropriate communities based on the contributor's interests. For instance, the community section could input the contributor's profile data into the generative AI, which would then suggest suitable communities. This would allow contributors to interact with other users and learn about healthy discourse together.

[0057] The comment simulation system can also include a rewards section. The rewards section provides rewards to users who post healthy comments. For example, the rewards section could implement a point system and award points each time a healthy comment is posted. The rewards section could also use a generation AI to analyze the healthiness of comments and award appropriate points. For example, the rewards section could input comment data into the generation AI, which could then award points. The rewards section could also offer gift cards or other benefits once a certain number of points have been accumulated. This would increase the motivation of posters to post healthy comments and promote a healthy online space for discussion.

[0058] The following briefly describes the processing flow for example form 1.

[0059] Step 1: The reception desk receives comments from posters. The reception desk can accept comments via text input, voice input, image input, etc. It can also use AI to analyze the content of the entered comments and convert them into an appropriate format. For example, it can convert voice-input comments into text, or use OCR technology to convert image-input comments into text. Step 2: The simulation unit simulates reactions based on past data, using the comments entered by the reception unit. The simulation unit uses a generation AI to simulate reactions such as empathy, aversion, and indifference, based on past comment data and user reaction data. Furthermore, the simulation unit can also simulate reactions to comments in real time. Step 3: The advice section provides advice to the poster based on the simulation results obtained by the simulation section. The advice section suggests ways to soften aggressive language and offer more constructive criticism. Furthermore, it can use AI to analyze the simulation results and generate appropriate advice.

[0060] (Example of form 2) The comment simulation system according to an embodiment of the present invention is a system that provides a virtual space for discourse to reduce slander and defamation in the comment sections of news websites. The comment simulation system allows users to simulate and check reactions in this virtual space before actually posting a comment. This is expected to allow for stress relief and promote healthy discourse. For example, in the comment simulation system, a user inputs a comment. Next, a generating AI simulates reactions to that comment based on a vast amount of past posting data. The simulation results include reactions such as empathy, hostility, and indifference. This allows the user to see in advance how their comment will be received. Furthermore, based on the simulation results, the generating AI provides advice to the user. For example, it suggests ways to soften aggressive expressions or ways to offer more constructive criticism. This allows the user to revise their comment and engage in healthier discourse. The comment simulation system is expected not only to reduce slander and defamation in the comment sections of news websites but also to enhance the user's self-awareness and promote a healthy space for discourse. Additionally, the comment simulation system can increase user motivation by incorporating gamification elements. For example, a system could be implemented where users earn points for posting wholesome comments and receive rewards for doing so. This would allow the comment simulation system to encourage healthy discussion by allowing users to simulate their comments and check the reactions before posting them.

[0061] The comment simulation system according to this embodiment comprises a reception unit, a simulation unit, and an advice unit. The reception unit receives comments from posters. The reception unit can receive comments by methods such as text input, voice input, and image input. The reception unit can also use AI to analyze the content of the input comments and convert them into an appropriate format. For example, the reception unit converts voice-input comments into text. The reception unit can also convert image-input comments into text using OCR technology. The simulation unit uses a generation AI to simulate reactions based on past data, using the comments input by the reception unit. For example, the simulation unit simulates reactions such as empathy, hostility, and indifference based on past comment data and user reaction data. The simulation unit can also use a generation AI to simulate reactions to comments in real time. For example, the simulation unit inputs a comment into the generation AI, and the generation AI generates a reaction based on past data. The advice unit provides advice to the poster based on the simulation results obtained by the simulation unit. For example, the advice unit suggests ways to soften aggressive expressions or ways to offer more constructive criticism. The advice unit can also use AI to analyze simulation results and generate appropriate advice. For example, the advice unit inputs the simulation results into a generating AI, which then generates advice. This allows the comment simulation system according to the embodiment to promote healthy discussion by allowing users to simulate and check reactions before posting comments.

[0062] The reception desk receives comments from posters. The reception desk can accept comments via methods such as text input, voice input, and image input. Specifically, for text input, users can directly input comments using a keyboard. For voice input, users input comments using a microphone, and the reception desk converts this into text using speech recognition technology. For image input, users photograph handwritten notes or printed documents with a camera, and the reception desk converts the characters in the image into text using OCR (optical character recognition) technology. Furthermore, the reception desk can use AI to analyze the content of the input comments and convert them into an appropriate format. For example, when converting voice-input comments to text, the speech recognition AI performs noise reduction and speech clarity to ensure accurate text conversion. For image-input comments, OCR technology is used for character recognition, and the AI ​​can perform contextual analysis to reduce misrecognition. This allows the reception desk to support diverse input methods and process comments accurately and quickly as text data, regardless of the format in which the user inputs them. Furthermore, the reception system also has a function to pre-filter the content of submitted comments, detecting and removing inappropriate language and spam. This helps maintain the overall integrity of the system and provides users with an environment where they can enter comments with peace of mind.

[0063] The simulation unit uses a generative AI to simulate reactions based on comments entered by the reception unit, drawing on past data. Specifically, the simulation unit utilizes a generative AI that has learned from a large amount of past comment data and user reaction data to predict various reactions to the entered comment. For example, it simulates reactions such as empathy, dislike, and indifference, and predicts which reaction will be most frequently received. The simulation unit inputs a comment into the generative AI, which generates a reaction based on past data. The generative AI uses natural language processing technology to understand the content and context of the comment and generate an appropriate reaction. For example, it can simulate reactions of empathy and agreement for positive comments, and reactions of dislike and criticism for negative comments. Furthermore, because the simulation unit can simulate reactions in real time, users can see the reaction immediately after entering a comment. This allows users to understand the impact of their comments in advance and review the content before posting. The simulation unit can also set different scenarios and simulate multiple reactions, providing users with reference information to select the most appropriate comment. This allows the simulation unit to support users in engaging in healthy communication and improve the online environment for discourse.

[0064] The advice section provides advice to commenters based on the simulation results obtained by the simulation section. Specifically, the advice section analyzes the simulation results and generates specific advice on the content and expression of comments. For example, it may suggest ways to soften aggressive language or to offer more constructive criticism. The advice section can also use AI to analyze simulation results and generate appropriate advice. The generating AI evaluates the tone and content of comments based on the simulation results and specifically indicates areas for improvement. For example, it may suggest ways to change aggressive comments to more neutral and constructive language, and for positive comments, it may suggest specific expressions to further evoke empathy. The advice section can also provide individually customized advice by considering the user's past comment history and reaction data. This allows users to understand how their comments are received and communicate more effectively. Furthermore, the advice section can present specific examples and scenarios to make the advice easier for users to accept. For example, it may show how similar comments have been received in the past and suggest areas for improvement based on those results. This allows the advice section to provide specific support to promote healthy discourse by enabling users to review their comments before posting them.

[0065] The Points Management Department provides a system where users can earn points and receive rewards by posting healthy comments. For example, the Points Management Department awards points each time a user posts a healthy comment. The Points Management Department can also use AI to analyze the content of comments and determine whether they are healthy. For example, the Points Management Department inputs comments into a generating AI, which then determines whether the comment is healthy. The Points Management Department awards points for healthy comments, and provides rewards when a certain number of points are accumulated. Rewards include, but are not limited to, point exchange items or service usage rights. This allows the system to provide a way for users to earn points and receive rewards by posting healthy comments.

[0066] The simulation unit can simulate reactions based on a vast amount of past posting data. For example, the simulation unit collects past comment data and user reaction data and simulates reactions based on that data. The simulation unit can also use a generative AI to analyze past data and generate reactions to comments. For example, the simulation unit inputs past data into the generative AI, and the generative AI generates reactions. This improves the accuracy of the simulation by simulating reactions based on a vast amount of past posting data. Some or all of the above-described processes in the simulation unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the simulation unit can input past data into the generative AI, and the generative AI can generate reactions.

[0067] The advice unit can suggest ways to mitigate aggressive language or offer more constructive criticism based on the simulation results. For example, the advice unit can analyze the simulation results and suggest ways to mitigate aggressive language. The advice unit can also use generative AI to analyze the simulation results and generate appropriate advice. For example, the advice unit inputs the simulation results into the generative AI, which then generates advice. This promotes healthy discourse by suggesting ways to mitigate aggressive language or offer more constructive criticism based on the simulation results. Some or all of the above-described processes in the advice unit may be performed using or without the generative AI. For example, the advice unit can input the simulation results into the generative AI, which then generates advice.

[0068] The simulation unit can simulate reactions such as empathy, aversion, and indifference. For example, the simulation unit simulates reactions such as empathy, aversion, and indifference based on past comment data and user reaction data. The simulation unit can also use a generative AI to simulate reactions to comments in real time. For example, the simulation unit inputs a comment into the generative AI, and the generative AI generates a reaction based on past data. This allows the poster to check in advance how their comment will be received by simulating reactions such as empathy, aversion, and indifference. Some or all of the above-described processes in the simulation unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the simulation unit can input a comment into the generative AI, and the generative AI can generate a reaction.

[0069] The advice unit can provide posters with advice on posting healthy comments. For example, the advice unit can analyze simulation results and provide advice on posting healthy comments. The advice unit can also use a generative AI to analyze simulation results and generate appropriate advice. For example, the advice unit can input simulation results into a generative AI, which then generates advice. This promotes healthy discourse by providing posters with advice on posting healthy comments. Some or all of the above-described processes in the advice unit may be performed using a generative AI or not. For example, the advice unit can input simulation results into a generative AI, which then generates advice.

[0070] The reception unit can estimate the poster's emotions and adjust the comment input interface based on the estimated emotions. For example, if the poster is angry, the reception unit can provide an interface with calming colors to reduce visual stress. The reception unit can also use generative AI to estimate the poster's emotions and provide an appropriate interface. For example, the reception unit inputs the poster's emotion data into the generative AI, which then adjusts the interface. This reduces stress on the poster and promotes healthy comments by adjusting the comment input interface based on the poster'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 reception unit may be performed using or without the generative AI. For example, the reception unit can input the poster's emotion data into the generative AI, which then adjusts the interface.

[0071] The reception desk can analyze the poster's past comment history and suggest the optimal input method. For example, the reception desk can automatically display expressions and phrases that the poster has frequently used in the past as suggestions. The reception desk can also use a generative AI to analyze the past comment history and suggest an appropriate input method. For example, the reception desk can input the past comment history into the generative AI, which will then suggest the optimal input method. This streamlines comment input by analyzing the poster's past comment history and suggesting the optimal input method. Some or all of the above processing in the reception desk may be performed using a generative AI, or it may be performed without using a generative AI. For example, the reception desk can input the past comment history into the generative AI, which will then suggest the optimal input method.

[0072] The reception desk can provide input assistance based on the commenter's current interests and topics when they enter a comment. For example, the reception desk can automatically suggest keywords related to news articles the commenter is currently interested in. The reception desk can also use a generative AI to analyze the commenter's current interests and topics and provide appropriate input assistance. For example, the reception desk can input the commenter's current interests and topics into the generative AI, which will then provide input assistance. This streamlines the comment entry process by providing input assistance based on the commenter's current interests and topics. Some or all of the above-described processes in the reception desk may be performed using a generative AI, or they may not be performed using a generative AI. For example, the reception desk can input the commenter's current interests and topics into the generative AI, which will then provide input assistance.

[0073] The reception unit can estimate the poster's emotions and determine the priority of the submitted comments based on the estimated emotions. For example, if the poster is angry, the reception unit will prioritize simulating that comment. The reception unit can also use generative AI to estimate the poster's emotions and determine appropriate priorities. For example, the reception unit inputs the poster's emotion data into the generative AI, and the generative AI determines the priorities. This ensures that important comments are processed preferentially by prioritizing comments based on the poster'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 reception unit may be performed using or without the generative AI. For example, the reception unit can input the poster's emotion data into the generative AI, and the generative AI can determine the priorities.

[0074] The reception system can prioritize displaying highly relevant topics when a comment is entered, taking into account the poster's geographical location. For example, if the poster is in a specific region, the reception system will prioritize displaying news articles related to that region. The reception system can also use a generative AI to analyze the poster's geographical location and display appropriate topics. For example, the reception system can input geographical location information into the generative AI, which will then display highly relevant topics. This streamlines the comment entry process by prioritizing the display of highly relevant topics based on the poster's geographical location. Some or all of the above processing in the reception system may be performed using a generative AI, or it may be performed without using a generative AI. For example, the reception system can input geographical location information into the generative AI, which will then display highly relevant topics.

[0075] The reception desk can analyze the poster's social media activity when a comment is entered and suggest relevant topics. For example, the reception desk can suggest topics related to posts the poster has recently "liked." The reception desk can also use generative AI to analyze social media activity and suggest appropriate topics. For example, the reception desk can input social media activity data into the generative AI, which then suggests relevant topics. This streamlines the comment entry process by analyzing the poster's social media activity and suggesting relevant topics. Some or all of the above processing in the reception desk may be performed using generative AI, or it may be performed without using generative AI. For example, the reception desk can input social media activity data into the generative AI, which then suggests relevant topics.

[0076] The simulation unit can estimate the poster's emotions and adjust the simulation criteria based on the estimated emotions. For example, if the poster is angry, the simulation unit will perform a simulation that emphasizes the reaction of anger. The simulation unit can also use a generative AI to estimate the poster's emotions and set appropriate simulation criteria. For example, the simulation unit inputs the poster's emotion data into the generative AI, and the generative AI adjusts the simulation criteria. This improves the accuracy of the simulation by adjusting the simulation criteria based on the poster's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 simulation unit may be performed using a generative AI or not. For example, the simulation unit can input the poster's emotion data into a generative AI, and the generative AI can adjust the simulation criteria.

[0077] The simulation unit can improve the accuracy of the simulation by considering the relationships between comments during the simulation. For example, if a comment is a reply to another comment, the simulation unit will consider that relationship when performing the simulation. The simulation unit can also use a generation AI to analyze the relationships between comments and perform an appropriate simulation. For example, the simulation unit can input the relationship data of comments into the generation AI, and the generation AI will perform the simulation. This improves the accuracy of the simulation by considering the relationships between comments. Some or all of the above processing in the simulation unit may be performed using the generation AI, or it may be performed without using the generation AI. For example, the simulation unit can input the relationship data of comments into the generation AI, and the generation AI can perform the simulation.

[0078] The simulation unit can perform simulations while considering the attribute information of the commenter. For example, the simulation unit can simulate responses from people of the same age group based on the commenter's age group. The simulation unit can also use a generative AI to analyze the commenter's attribute information and perform an appropriate simulation. For example, the simulation unit inputs the commenter's attribute information data into the generative AI, and the generative AI performs the simulation. This improves the accuracy of the simulation by considering the attribute information of the commenter. Some or all of the above processing in the simulation unit may be performed using the generative AI, or it may be performed without using the generative AI. For example, the simulation unit can input the commenter's attribute information data into the generative AI, and the generative AI can perform the simulation.

[0079] The simulation unit can estimate the poster's emotions and adjust the display order of the simulation results based on the estimated emotions. For example, if the poster is angry, the simulation unit will display the reaction of aversion first. The simulation unit can also use a generative AI to estimate the poster's emotions and set an appropriate display order. For example, the simulation unit inputs the poster's emotion data into the generative AI, and the generative AI adjusts the display order. This allows for a deeper understanding of the simulation results by adjusting the display order based on the poster's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 simulation unit may be performed using a generative AI or not. For example, the simulation unit can input the poster's emotion data into a generative AI, and the generative AI can adjust the display order.

[0080] The simulation unit can perform simulations while considering the geographical distribution of comments. For example, if a comment is related to a specific region, the simulation unit will simulate the response in that region. The simulation unit can also use a generative AI to analyze the geographical distribution of comments and perform an appropriate simulation. For example, the simulation unit inputs geographical distribution data into the generative AI, and the generative AI performs the simulation. This improves the accuracy of the simulation by considering the geographical distribution of comments. Some or all of the above-described processes in the simulation unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the simulation unit can input geographical distribution data into the generative AI, and the generative AI can perform the simulation.

[0081] The simulation unit can improve the accuracy of the simulation by referring to relevant literature for the comments during the simulation. For example, if the comment is related to a specific study, the simulation unit will perform the simulation based on past responses to that study. The simulation unit can also use a generative AI to analyze relevant literature and perform an appropriate simulation. For example, the simulation unit can input relevant literature data into the generative AI, and the generative AI will perform the simulation. This improves the accuracy of the simulation by referring to relevant literature for the comments. Some or all of the above processing in the simulation unit may be performed using the generative AI, or it may be performed without the generative AI. For example, the simulation unit can input relevant literature data into the generative AI, and the generative AI can perform the simulation.

[0082] The advice unit can estimate the poster's emotions and adjust the way the advice is expressed based on those emotions. For example, if the poster is angry, the advice unit will provide advice in a calm tone. The advice unit can also use generative AI to estimate the poster's emotions and set an appropriate expression. For example, the advice unit can input the poster's emotion data into the generative AI, which will then adjust the expression. This improves the acceptability of the advice by adjusting its expression based on the poster'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 advice unit may be performed using or without the generative AI. For example, the advice unit can input the poster's emotion data into the generative AI, which will then adjust the expression.

[0083] The advice unit can adjust the level of detail of the advice based on the importance of the comment when providing advice. For example, the advice unit will provide detailed advice for comments of high importance. The advice unit can also use a generative AI to analyze the importance of comments and set an appropriate level of detail. For example, the advice unit can input comment importance data into the generative AI, and the generative AI can adjust the level of detail. This ensures that appropriate advice is provided by adjusting the level of detail of the advice based on the importance of the comment. Some or all of the above processing in the advice unit may be performed using a generative AI or not. For example, the advice unit can input comment importance data into the generative AI, and the generative AI can adjust the level of detail.

[0084] The advice unit can apply different advice algorithms depending on the category of the comment when providing advice. For example, the advice unit provides calm and objective advice to comments on politics. The advice unit can also use a generative AI to analyze the category of the comment and apply an appropriate advice algorithm. For example, the advice unit inputs the category data of the comment into the generative AI, and the generative AI applies an advice algorithm. This allows for more appropriate advice to be provided by applying different advice algorithms depending on the category of the comment. Some or all of the above processing in the advice unit may be performed using the generative AI or not. For example, the advice unit can input the category data of the comment into the generative AI, and the generative AI can apply an advice algorithm.

[0085] The advice unit can estimate the poster's emotions and adjust the length of the advice based on the estimated emotions. For example, if the poster is angry, the advice unit will provide short, concise advice. The advice unit can also use generative AI to estimate the poster's emotions and set an appropriate length of advice. For example, the advice unit inputs the poster's emotion data into the generative AI, which then adjusts the length of the advice. This improves the acceptability of the advice by adjusting its length based on the poster'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 advice unit may be performed using or without the generative AI. For example, the advice unit can input the poster's emotion data into the generative AI, which then adjusts the length of the advice.

[0086] The advice unit can determine the priority of advice based on when the comments were submitted. For example, the advice unit can prioritize advice for the most recent comments. The advice unit can also use a generative AI to analyze the submission timing of comments and set appropriate priorities. For example, the advice unit inputs the submission timing data of comments into the generative AI, and the generative AI determines the priority. This ensures that advice is provided quickly to the most recent comments by prioritizing advice based on the submission timing of comments. Some or all of the above processing in the advice unit may be performed using a generative AI or not. For example, the advice unit can input the submission timing data of comments into the generative AI, and the generative AI can determine the priority.

[0087] The advice unit can adjust the order of advice based on the relevance of the comments when providing advice. For example, the advice unit will prioritize providing advice to comments with high relevance. The advice unit can also use a generative AI to analyze the relevance of comments and set an appropriate order. For example, the advice unit can input comment relevance data into the generative AI, and the generative AI can adjust the order. This adjusts the order of advice based on the relevance of the comments, thereby prioritizing the provision of advice to highly relevant comments. Some or all of the above processing in the advice unit may be performed using a generative AI or not. For example, the advice unit can input comment relevance data into the generative AI, and the generative AI can adjust the order.

[0088] The point management unit can estimate the poster's emotions and adjust the point awarding criteria based on the estimated emotions. For example, if a poster is angry, the point management unit will award higher points to calm comments. The point management unit can also use a generative AI to estimate the poster's emotions and set appropriate awarding criteria. For example, the point management unit inputs the poster's emotion data into the generative AI, and the generative AI adjusts the awarding criteria. This promotes healthy comments by adjusting the point awarding criteria based on the poster's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 management unit may be performed using a generative AI or not. For example, the point management unit can input the poster's emotion data into a generative AI, and the generative AI can adjust the awarding criteria.

[0089] The point management unit can optimize the point awarding algorithm by referring to past point history during point management. For example, the point management unit can analyze patterns of comments that have previously earned high points from posters and optimize the point awarding algorithm. The point management unit can also use a generation AI to analyze past point history and set an appropriate algorithm. For example, the point management unit can input past point history data into the generation AI, and the generation AI can optimize the algorithm. This improves the accuracy of point awarding by optimizing the point awarding algorithm by referring to past point history. Some or all of the above processes in the point management unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the point management unit can input past point history data into a generation AI, and the generation AI can optimize the algorithm.

[0090] The point management unit can estimate the poster's emotions and adjust the frequency of point awarding based on the estimated emotions. For example, if a poster is angry, the point management unit will frequently award points to calm comments. The point management unit can also use a generative AI to estimate the poster's emotions and set an appropriate awarding frequency. For example, the point management unit inputs the poster's emotion data into the generative AI, and the generative AI adjusts the awarding frequency. This promotes healthy comments by adjusting the point awarding frequency based on the poster's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 management unit may be performed using a generative AI or not. For example, the point management unit can input the poster's emotion data into a generative AI, and the generative AI can adjust the awarding frequency.

[0091] The point management unit can weight points based on the submission date of comments during point management. For example, the point management unit can assign higher points to the most recent comments. The point management unit can also use a generation AI to analyze the submission date of comments and set appropriate weights. For example, the point management unit inputs the comment submission date data into the generation AI, and the generation AI performs the weighting. This weighting of points based on the submission date of comments results in higher points being assigned to the most recent comments. Some or all of the above processing in the point management unit may be performed using the generation AI, or it may be performed without using the generation AI. For example, the point management unit can input the comment submission date data into the generation AI, and the generation AI can perform the weighting.

[0092] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0093] The comment simulation system can also include a feedback unit. The feedback unit collects feedback on the simulation results after the poster receives them. For example, it might ask the poster how they felt about the simulation results, what parts were helpful, and what could be improved. The feedback unit can analyze the collected feedback and use it to improve the algorithms of the simulation and advice units. This improves the overall accuracy and usability of the system. The feedback unit can also use generative AI to analyze the feedback and extract appropriate areas for improvement. For example, the feedback unit can input feedback data into the generative AI, which can then suggest improvements.

[0094] The comment simulation system can also include a learning section. This learning section provides educational content to help commenters post healthy comments. For example, it could offer videos or articles on the importance of healthy speech and how to avoid offensive language. The learning section could also provide individually customized educational content based on the commenter's simulation results and feedback. This allows commenters to learn specific ways to improve the quality of their comments. The learning section could also use generative AI to suggest the most suitable educational content for the commenter. For example, the learning section could input the commenter's simulation results into the generative AI, which could then suggest appropriate educational content.

[0095] The comment simulation system can also include a moderation unit. The moderation unit monitors whether a comment is appropriate after it has been posted. For example, it can analyze posted comments in real time and issue warnings if they contain slander or offensive language. The moderation unit can also use a generative AI to analyze posted comments and suggest appropriate actions. For instance, the moderation unit can input comment data into the generative AI, which can then issue warnings or suggest deletions. This helps maintain a healthy environment for discussion in the comment sections of news websites.

[0096] The comment simulation system can also include a community section. This section helps contributors form communities to promote healthy discourse. For example, it could provide forums or chat rooms to connect users who have posted healthy comments. The community section could also use generative AI to suggest appropriate communities based on the contributor's interests. For instance, the community section could input the contributor's profile data into the generative AI, which would then suggest suitable communities. This would allow contributors to interact with other users and learn about healthy discourse together.

[0097] The comment simulation system can also include a rewards section. The rewards section provides rewards to users who post healthy comments. For example, the rewards section could implement a point system and award points each time a healthy comment is posted. The rewards section could also use a generation AI to analyze the healthiness of comments and award appropriate points. For example, the rewards section could input comment data into the generation AI, which could then award points. The rewards section could also offer gift cards or other benefits once a certain number of points have been accumulated. This would increase the motivation of posters to post healthy comments and promote a healthy online space for discussion.

[0098] The comment simulation system can also include an emotional feedback unit. The emotional feedback unit collects emotional feedback from the commenter after they receive the simulation results. For example, it might ask how the commenter felt about the simulation results and which parts had an emotional impact. The emotional feedback unit can analyze the collected emotional feedback and use it to improve the algorithms of the simulation and advice units. This improves the overall accuracy and usability of the system. The emotional feedback unit can also analyze the emotional feedback using generative AI and extract appropriate areas for improvement. For example, the emotional feedback unit can input emotional feedback data into the generative AI, which can then suggest areas for improvement.

[0099] The comment simulation system can also include an emotion monitoring unit. This unit monitors the poster's emotional state in real time while they are typing a comment. For example, if the poster is angry, the emotion monitoring unit adjusts the interface's color scheme and font size to reduce visual stress. The emotion monitoring unit can also use a generative AI to estimate the poster's emotions and make appropriate interface adjustments. For instance, the emotion monitoring unit can input emotional data into the generative AI, which can then adjust the interface. This ensures that the interface is adjusted according to the poster's emotional state, promoting healthy commenting.

[0100] The comment simulation system can also include an emotion alert unit. This unit issues alerts based on the poster's emotional state while they are typing a comment. For example, if the poster is feeling intense anger, the emotion alert unit displays messages offering advice to calm down or encouraging deep breathing. The emotion alert unit can also use a generative AI to estimate the poster's emotions and issue appropriate alerts. For instance, the emotion alert unit can input emotional data into the generative AI, which can then issue alerts. This ensures that alerts are issued according to the poster's emotional state, promoting healthy commenting.

[0101] The comment simulation system can also include an emotion history unit. This unit records and analyzes the poster's past emotional states. For example, it records the emotional state the poster was in when they previously entered comments and analyzes their emotional tendencies based on that data. The emotion history unit can also use a generative AI to analyze the emotional data and provide appropriate feedback. For instance, the emotion history unit can input emotional history data into the generative AI, which then analyzes the emotional tendencies. This allows for personalized feedback based on the poster's emotional state, promoting healthy commenting.

[0102] The comment simulation system can also include an emotional training section. This section provides training to improve the emotional management skills of users in posting healthy comments. For example, it could offer videos and articles on how to control anger or techniques for reducing stress. The emotional training section could also provide individually customized training programs based on the user's emotional state. This would allow users to properly manage their emotions and improve their skills in posting healthy comments. The emotional training section could also use generative AI to suggest the most suitable training program for the user. For example, the emotional training section could input emotional data into the generative AI, which could then suggest an appropriate training program.

[0103] The following briefly describes the processing flow for example form 2.

[0104] Step 1: The reception desk receives comments from posters. The reception desk can accept comments via text input, voice input, image input, etc. It can also use AI to analyze the content of the entered comments and convert them into an appropriate format. For example, it can convert voice-input comments into text, or use OCR technology to convert image-input comments into text. Step 2: The simulation unit simulates reactions based on past data, using the comments entered by the reception unit. The simulation unit uses a generation AI to simulate reactions such as empathy, aversion, and indifference, based on past comment data and user reaction data. Furthermore, the simulation unit can also simulate reactions to comments in real time. Step 3: The advice section provides advice to the poster based on the simulation results obtained by the simulation section. The advice section suggests ways to soften aggressive language and offer more constructive criticism. Furthermore, it can use AI to analyze the simulation results and generate appropriate advice.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] Each of the multiple elements described above, including the reception unit, simulation unit, advice unit, and point management unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and inputs the poster's comment. The simulation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and simulates a reaction based on past data. The advice unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides advice based on the simulation results. The point management unit is implemented by, for example, the control unit 46A of the smart device 14 and awards points for posting healthy comments. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0109] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] Each of the multiple elements described above, including the reception unit, simulation unit, advice unit, and point management unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and takes the poster's comment. The simulation unit is implemented by the specific processing unit 290 of the data processing unit 12 and simulates a reaction based on past data. The advice unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides advice based on the simulation results. The point management unit is implemented by the control unit 46A of the smart glasses 214 and awards points for posting healthy comments. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0125] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Each of the multiple elements described above, including the reception unit, simulation unit, advice unit, and point management unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and inputs the poster's comment. The simulation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and simulates a reaction based on past data. The advice unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides advice based on the simulation results. The point management unit is implemented by, for example, the control unit 46A of the headset terminal 314 and awards points for posting healthy comments. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0141] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] Each of the multiple elements described above, including the reception unit, simulation unit, advice unit, and point management unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and inputs the poster's comment. The simulation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and simulates a reaction based on past data. The advice unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides advice based on the simulation results. The point management unit is implemented by, for example, the control unit 46A of the robot 414 and awards points for posting healthy comments. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] (Note 1) The reception area where users enter their comments, Based on the comments entered by the reception unit, a simulation unit simulates the reaction based on past data, The system includes an advice unit that provides advice based on the simulation results obtained by the simulation unit. A system characterized by the following features. (Note 2) It has a points management department that manages points, We offer a system where users can earn points and receive rewards by posting wholesome comments. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned simulation unit, We simulate reactions based on a vast amount of past posting data. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned advice section, Based on the simulation results, we propose ways to soften aggressive language and offer more constructive criticism. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned simulation unit, It simulates reactions such as empathy, aversion, and indifference. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned advice section, Provide posters with advice on how to post healthy comments. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It estimates the poster's emotions and adjusts the comment input interface based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is We analyze the poster's past comment history and suggest the optimal input method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When entering a comment, provide input assistance based on the poster's current interests and topics. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the poster's emotions and prioritizes the comments based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When you enter a comment, the system prioritizes displaying topics that are highly relevant to the poster, taking into account their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When you enter a comment, the system analyzes your social media activity and suggests relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned simulation unit, The system estimates the poster's emotions and adjusts the simulation criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned simulation unit, During simulation, consider the interrelationships of comments to improve the accuracy of the simulation. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned simulation unit, During the simulation, the attribute information of the commenter will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned simulation unit, The system estimates the poster's emotions and adjusts the display order of the simulation results based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned simulation unit, During the simulation, the geographical distribution of comments will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned simulation unit, During simulations, refer to the relevant literature in the comments to improve the accuracy of the simulation. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned advice section, The system estimates the poster's emotions and adjusts the way advice is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned advice section, When providing advice, adjust the level of detail based on the importance of the comment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned advice section, When providing advice, different advice algorithms are applied depending on the category of the comment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned advice section, The system estimates the poster's emotions and adjusts the length of the advice based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned advice section, When providing advice, we prioritize the advice based on when the comments were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned advice section, When providing advice, adjust the order of advice based on the relevance of the comments. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned point management unit, The system estimates the poster's emotions and adjusts the point awarding criteria based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned point management unit, When managing points, the point awarding algorithm is optimized by referring to past point history. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned point management unit, The system estimates the poster's emotions and adjusts the frequency of point awards based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned point management unit, When managing points, weighting of points will be based on when comments were submitted. The system described in Appendix 2, characterized by the features described herein. [Explanation of symbols]

[0177] 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. The reception area where users enter their comments, Based on the comments entered by the reception unit, a simulation unit simulates the reaction based on past data, The system includes an advice unit that provides advice based on the simulation results obtained by the simulation unit. A system characterized by the following features.

2. It has a points management department that manages points, We offer a system where users can earn points and receive rewards by posting wholesome comments. The system according to feature 1.

3. The aforementioned simulation unit, We simulate reactions based on a vast amount of past posting data. The system according to feature 1.

4. The aforementioned advice section, Based on the simulation results, we propose ways to soften aggressive language and offer more constructive criticism. The system according to feature 1.

5. The aforementioned simulation unit, It simulates reactions such as empathy, aversion, and indifference. The system according to feature 1.

6. The aforementioned advice section, Provide posters with advice on how to post healthy comments. The system according to feature 1.

7. The aforementioned reception unit is It estimates the poster's emotions and adjusts the comment input interface based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is We analyze the poster's past comment history and suggest the optimal input method. The system according to feature 1.

9. The aforementioned reception unit is When entering a comment, provide input assistance based on the poster's current interests and topics. The system according to feature 1.

Images