system

Abstract

The system according to the embodiment aims to provide appropriate feedback to abusive comments and suggest alternative comments to the poster. [Solution] A system according to an embodiment includes a detection unit, a generation unit, and a suggestion unit. The detection unit detects abusive comments. The generation unit generates specific words and images for comments detected by the detection unit. The suggestion unit suggests alternative comments based on the specific words and images generated by the generation unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that it is difficult to respond appropriately to abusive comments and to provide effective feedback to the poster.

[0005] The system according to the embodiment aims to provide appropriate feedback to abusive comments and suggest alternative comments to the poster. [Means for solving the problem]

[0006] The system according to the embodiment includes a detection unit, a generation unit, and a suggestion unit. The detection unit detects abusive comments. The generation unit generates specific words and images for the comments detected by the detection unit. The suggestion unit suggests alternative comments based on the specific words and images generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide appropriate feedback to abusive comments and suggest alternative comments to the poster. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention uses humorous words, audio, and images to admonish users who are about to post abusive comments on social networking sites, and suggests alternative comments. This system first detects abusive comments when a user attempts to post them. Next, the system uses humorous words, audio, and images to admonish the poster of the detected comment. A generation AI generates humorous words, audio, and images. An alternative comment is then suggested. The generation AI also generates and presents the alternative comment to the user. This prevents the posting of abusive comments on social networking sites and promotes healthy communication. For example, a system detects abusive comments when a user attempts to post them. The AI ​​analyzes the content of the comment and determines whether it is potentially abusive. For example, if the comment contains words such as "idiot" or "die," it is determined to be abusive. Next, the system uses humorous words, audio, and images to admonish the poster of the detected comment. In this case, the generative AI generates humorous words, sounds, and images. For example, it can generate phrases like, "Don't say that! Let's talk about something more fun!" or an image of a smiling character. This can encourage posters to refrain from posting abusive comments. It also suggests alternative comments. The generative AI generates appropriate alternatives to abusive comments and presents them to users. For example, it can generate alternative comments such as, "I don't agree with that opinion, but here's another way of thinking." This allows users to post constructive comments instead of abusive comments. This mechanism can prevent the posting of abusive comments on social media and promote healthy communication. When users are about to post abusive comments, the generative AI can advise them and suggest alternative comments, leading to better communication. For example, even if a discussion on social media becomes heated and abusive comments are about to be posted, the generative AI can intervene appropriately to maintain a healthy discussion.This will prevent the posting of abusive comments on social media and promote healthy communication.

[0029] An SNS sanitization system according to an embodiment includes a detection unit, a generation unit, and a suggestion unit. The detection unit analyzes comments posted by users in real time and determines whether the comments are likely to be defamatory. For example, the detection unit uses natural language processing technology to analyze the content of the comments and determine that the comments are defamatory if they contain specific words or phrases such as "idiot" or "die." The detection unit can also use context analysis technology to consider the context before and after the comment and more accurately determine the intent of the defamatory comment. The generation unit uses a generation AI to generate humorous words or images in response to the defamatory comment detected by the detection unit. For example, the generation AI uses a text generation AI (e.g., GPT-4 (registered trademark)) to generate humorous words such as "Don't say that. Let's talk about something more fun!" The generation AI can also use an image generation AI to generate images of smiling characters. The generation unit can also generate humorous words and images taking into account multilingual support and cultural differences. For example, the generation AI generates humorous words and images that correspond to different languages ​​and cultures. The suggestion unit uses the generation AI to generate appropriate alternative comments to replace defamatory comments and present them to the user. For example, the generation AI generates alternative comments such as, "I don't agree with that opinion, but here's another way of thinking." The suggestion unit can also present multiple alternative comments for the user to choose from. For example, the generation AI generates alternative comments with different tones and styles and presents them to the user. As a result, the SNS sanitization system according to the embodiment can detect defamatory comments, admonish them with humorous words and images, and suggest alternative comments, thereby promoting healthy communication.

[0030] The generation unit can generate humorous words and images using a generation AI. The generation unit can generate humorous words using, for example, a text generation AI (e.g., GPT-4). For example, the generation unit can generate humorous words such as, "Don't say that, let's talk about something more fun!" The generation unit can also generate humorous images using an image generation AI. For example, the generation unit can generate an image of a smiling character. Furthermore, the generation unit can generate humorous words and images taking into account multilingual support and cultural differences. For example, the generation unit generates humorous words and images that correspond to different languages ​​and cultures. This improves the accuracy of generating humorous words and images by using a generation AI. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input a prompt such as, "Generate a humorous word" to a text generation AI and output the generated word.

[0031] The suggestion unit can generate an alternative comment using a generation AI. The suggestion unit generates an alternative comment using, for example, a text generation AI (e.g., GPT-4). For example, the suggestion unit generates an alternative comment such as, "I don't agree with that opinion, but there is also this way of thinking." The suggestion unit can also present multiple alternative comments for the user to choose from. For example, the suggestion unit generates alternative comments with different tones and styles and presents them to the user. This improves the accuracy of generating alternative comments by using the generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input a prompt to the text generation AI, such as "Please generate an alternative comment," and output the generated comment.

[0032] The generation unit can generate specific words and images taking into account multilingual support and cultural differences. The generation unit, for example, uses a text generation AI (e.g., GPT-4) to generate humorous words that are multilingual. For example, the generation unit generates humorous words in different languages, such as English, Japanese, and French. The generation unit can also use an image generation AI to generate humorous images that take cultural differences into account. For example, the generation unit generates images of smiling characters that correspond to different cultures. This allows for the generation of more appropriate humorous words and images by taking into account multilingual support and cultural differences. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input a prompt to the text generation AI, such as "Generate humorous words that are multilingual," and output the generated words.

[0033] The suggestion unit can present multiple alternative comments to the user to select from. The suggestion unit generates multiple alternative comments using, for example, a text generation AI (e.g., GPT-4). For example, the suggestion unit generates an alternative comment such as, "I don't agree with that opinion, but here's another way of thinking." The suggestion unit can also generate alternative comments with different tones or styles and present them to the user. For example, the suggestion unit presents multiple options, such as alternative comments that include light humor and alternative comments that are gentle. By presenting multiple alternative comments, the user can select the most appropriate comment. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input a prompt to the text generation AI, such as, "Generate multiple alternative comments," and output the generated comments.

[0034] The detection unit instantly detects abusive comments, allowing the generation unit and suggestion unit to intervene immediately. The detection unit, for example, uses natural language processing technology to analyze comments that users are about to post in real time and instantly determine whether they are potentially abusive. For example, the detection unit may determine that a comment is abusive if it contains specific words or phrases such as "idiot" or "die." The detection unit can also use context analysis technology to consider the context before and after the comment to more accurately determine the intent of the comment. The generation unit instantly generates humorous words or images in response to abusive comments detected by the detection unit. For example, the generation unit uses text generation AI (e.g., GPT-4) to instantly generate humorous words such as "Don't say that. Let's talk about something more fun!" The generation unit can also instantly generate images of smiling characters using image generation AI. The suggestion unit instantly generates an alternative comment based on the humorous words and images generated by the generation unit and presents it to the user. For example, the suggestion unit uses a text generation AI to instantly generate an alternative comment such as, "I don't agree with that opinion, but here's another way of thinking." This enables real-time detection and intervention to quickly prevent abusive comments. Some or all of the above-described processing in the detection unit, generation unit, and suggestion unit may be performed using, or without, the generation AI. For example, the detection unit analyzes the comment using natural language processing technology, the generation unit inputs a prompt to the text generation AI such as, "Please generate some humorous words," and the suggestion unit generates an alternative comment based on the generated words.

[0035] The SNS sanitization system includes a flow diagram creation unit that illustrates the overall system flow. The flow diagram creation unit generates a flow diagram that visually shows the operation of each unit of the system. For example, the flow diagram creation unit sequentially illustrates the operation of each element of the detection unit, generation unit, and suggestion unit, showing the system operation flow when a user attempts to post an abusive comment. The flow diagram creation unit can also generate an optimal flow diagram by referencing the system's operation history. For example, the flow diagram creation unit generates an efficient flow diagram based on the system's past operation history. Furthermore, the flow diagram creation unit can estimate the user's emotions and adjust the display method of the flow diagram based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible flow diagram is displayed, and if the user is relaxed, a flow diagram containing detailed information is displayed. This allows the flow diagram creation unit to visually facilitate understanding of the system's operation. Some or all of the above-described processing in the flow diagram creation unit may be performed using, or without, a generation AI. For example, the flow diagram creation unit inputs the system's operation history into the generation AI to generate an optimal flow diagram.

[0036] The detection unit can improve detection accuracy by analyzing past posting history and learning patterns of defamatory comments against a specific user. The detection unit, for example, analyzes past posting history and learns patterns of defamatory comments against a specific user. For example, the detection unit collects past defamatory comments against a specific user and analyzes the patterns. The detection unit can also detect similar defamatory comments in real time based on the learned patterns. For example, the detection unit extracts characteristics of defamatory comments against a specific user based on the past posting history and uses them for real-time detection. Furthermore, when a new defamatory pattern is discovered, the detection unit can update the learning data to improve detection accuracy. For example, the detection unit adds the newly discovered pattern of defamatory comments to the learning data to improve detection accuracy. In this way, by analyzing past posting history, the detection unit can learn patterns of defamatory comments against a specific user and improve detection accuracy. Some or all of the above-described processing in the detection unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the detection unit may input past posting history into the generation AI and have it learn patterns of defamation.

[0037] The detection unit analyzes the context of the comment during detection, thereby enabling more accurate determination of the intent to be defamatory. The detection unit analyzes the context of the comment using, for example, natural language processing technology. For example, the detection unit considers the context before and after the comment to determine the intent to be defamatory. The detection unit can also detect defamation by considering not only keywords in the comment but the entire context. For example, the detection unit analyzes the context before and after the comment to more accurately determine the intent to be defamatory. Furthermore, the detection unit can reduce false positives and accurately detect defamatory comments through context analysis. For example, the detection unit uses context analysis technology to analyze the context before and after the comment to determine the intent to be defamatory. In this way, by analyzing the context of the comment, the intent to be defamatory can be more accurately determined. Some or all of the above-described processing in the detection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the detection unit can use natural language processing technology to analyze the context of the comment, input a prompt to the generation AI such as "Please determine the intent of the comment as defamatory," and output the generated determination result.

[0038] During detection, the detection unit can detect region-specific defamatory expressions by taking into account the user's geographical location information. The detection unit acquires the user's geographical location information using, for example, GPS data or an IP address. For example, the detection unit detects region-specific defamatory expressions based on the user's geographical location information. The detection unit can also improve detection accuracy by referring to a database of defamatory expressions for each region. For example, the detection unit detects defamatory expressions commonly used in a specific region using a database of defamatory expressions for each region. Furthermore, the detection unit can update the geographical location information in real time to detect region-specific defamatory expressions. For example, the detection unit acquires the user's geographical location information in real time and detects region-specific defamatory expressions. In this way, region-specific defamatory expressions can be accurately detected by taking the geographical location information into account. Some or all of the above-described processing in the detection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the detection unit can input GPS data and IP addresses into the generation AI to detect defamatory language specific to a region.

[0039] During detection, the detection unit can analyze the user's social media activity and detect related abusive comments. The detection unit, for example, analyzes the user's past social media activity and learns patterns of abusive comments. For example, the detection unit collects the user's past posts and followers' reactions and analyzes the patterns. The detection unit can also detect related abusive comments in real time based on the learned patterns. For example, the detection unit extracts characteristics of abusive comments based on the user's past social media activity and uses them for real-time detection. Furthermore, when new social media activity is discovered, the detection unit can update the learning data to improve detection accuracy. For example, the detection unit adds newly discovered patterns of abusive comments to the learning data to improve detection accuracy. This allows related abusive comments to be accurately detected by analyzing social media activity. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generation AI or without a generation AI. For example, the detection unit can input a user's social media activity into the generation AI to detect abusive comments.

[0040] The generation unit can apply different humor styles depending on the content of the comment during generation. The generation unit can apply different humor styles depending on the content of the comment, for example, using a text generation AI (e.g., GPT-4). For example, the generation unit can apply a light humor style to mildly abusive comments and a mild humor style to seriously abusive comments. The generation unit can also apply a general humor style to neutral comments. This allows for more effective humor to be provided by applying a humor style depending on the content of the comment. Some or all of the above-described processing in the generation unit can be performed using, or without, the generation AI. For example, the generation unit can input a prompt to the text generation AI, such as "Please apply different humor styles depending on the content of the comment," and output the generated style.

[0041] During generation, the generation unit can select an optimal humorous expression by referring to the user's past reactions. The generation unit, for example, analyzes the user's past social media activities to select an optimal humorous expression. For example, the generation unit selects an optimal humorous expression based on the user's previously preferred style of humor. The generation unit can also analyze the user's past reactions to select the most effective humorous expression. Furthermore, the generation unit can update the user's past reaction data to always provide the optimal humorous expression. For example, the generation unit selects and generates an optimal humorous expression based on the user's past reaction data. In this way, the optimal humorous expression can be provided by referring to the user's past reactions. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's past reaction data into the generation AI to select the optimal humorous expression.

[0042] The generation unit can generate appropriate humor by taking into account the user's cultural background. For example, the generation unit generates humorous words and images by taking into account the user's cultural background. For example, the generation unit selects an appropriate humor style by taking into account the user's national culture and religious background. The generation unit can also generate humor that does not lead to misunderstandings by taking into account the user's cultural background. For example, the generation unit generates humorous words and images that correspond to different cultures. Furthermore, the generation unit can generate region-specific humor according to the user's cultural background. For example, the generation unit generates humorous words and images that take into account regional expressions and customs. This allows the user's cultural background to be taken into account, thereby providing appropriate humor that does not lead to misunderstandings. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the user's cultural background into the generation AI to generate appropriate humor.

[0043] During generation, the generation unit can analyze the user's social media activity and generate relevant humorous words and images. The generation unit, for example, analyzes the user's past social media activity and generates relevant humorous words and images. For example, the generation unit collects the user's past posts and followers' reactions and analyzes their patterns. The generation unit can also select optimal humorous expressions based on the user's social media activity. Furthermore, the generation unit can analyze the user's social media activity in real time and generate relevant humorous words and images. For example, the generation unit generates relevant humorous words and images based on the user's past social media activity and uses them for real-time generation. In this way, relevant humorous words and images can be provided by analyzing the user's social media activity. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's social media activity into a generation AI and generate relevant humorous words and images.

[0044] When making a suggestion, the suggestion unit can apply different alternative comment styles depending on the content of the comment. The suggestion unit can apply different alternative comment styles depending on the content of the comment, for example, using a text generation AI (e.g., GPT-4). For example, the suggestion unit can suggest an alternative comment that includes light humor for a mildly abusive comment, and a milder alternative comment for a seriously abusive comment. The suggestion unit can also suggest a general alternative comment for a neutral comment. This allows for more effective alternative comments to be provided by applying an alternative comment style depending on the content of the comment. Some or all of the above-described processing in the suggestion unit can be performed using, or without, a generation AI. For example, the suggestion unit can input a prompt to the text generation AI, such as "Please apply different alternative comment styles depending on the content of the comment," and output the generated style.

[0045] When making a suggestion, the suggestion unit can select an optimal alternative comment by referring to the user's past reactions. The suggestion unit, for example, analyzes the user's past social media activities to select an optimal alternative comment. For example, the suggestion unit selects an optimal alternative comment based on the style of alternative comments that the user has previously preferred. The suggestion unit can also analyze the user's past reactions to select the most effective alternative comment. Furthermore, the suggestion unit can update the user's past reaction data to always provide the optimal alternative comment. For example, the suggestion unit selects and generates an optimal alternative comment based on the user's past reaction data. In this way, the optimal alternative comment can be provided by referring to the user's past reactions. Some or all of the above-described processing in the suggestion unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the suggestion unit can input the user's past reaction data into a generation AI to select an optimal alternative comment.

[0046] When making a suggestion, the suggestion unit can suggest an appropriate alternative comment by taking into account the user's cultural background. The suggestion unit, for example, generates an alternative comment by taking into account the user's cultural background. For example, the suggestion unit selects an appropriate alternative comment by taking into account the user's national culture and religious background. The suggestion unit can also suggest an alternative comment that does not lead to misunderstandings by taking into account the user's cultural background. For example, the suggestion unit generates an alternative comment that corresponds to a different culture. Furthermore, the suggestion unit can also suggest an alternative comment that is specific to a region according to the user's cultural background. For example, the suggestion unit generates an alternative comment that takes into account expressions and customs specific to a region. This makes it possible to provide an appropriate alternative comment that does not lead to misunderstandings by taking into account the user's cultural background. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the user's cultural background into a generation AI to generate an appropriate alternative comment.

[0047] When making a suggestion, the suggestion unit can analyze the user's social media activity and suggest a related alternative comment. The suggestion unit, for example, analyzes the user's past social media activity and suggests a related alternative comment. For example, the suggestion unit collects the user's past posts and followers' reactions and analyzes their patterns. The suggestion unit can also select an optimal alternative comment based on the user's social media activity. Furthermore, the suggestion unit can analyze the user's social media activity in real time and suggest a related alternative comment. For example, the suggestion unit generates a related alternative comment based on the user's past social media activity and uses it for real-time suggestions. In this way, the user's social media activity can be analyzed to provide a related alternative comment. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the user's social media activity into a generation AI and generate a related alternative comment.

[0048] When creating a flow diagram, the flow diagram creation unit can generate an optimal flow diagram by referring to the operation history of each part of the system. The flow diagram creation unit generates an optimal flow diagram, for example, based on the past operation history of the system. For example, the flow diagram creation unit collects the operation history of each part of the system and analyzes its patterns. The flow diagram creation unit can also analyze the operation history of each part to generate an efficient flow diagram. Furthermore, the flow diagram creation unit can update the operation history in real time to always provide the latest flow diagram. For example, the flow diagram creation unit generates an optimal flow diagram based on the system's operation history and uses it for real-time generation. In this way, the optimal flow diagram can be provided by referring to the system's operation history. Some or all of the above-mentioned processing in the flow diagram creation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the flow diagram creation unit can input the system's operation history into a generation AI to generate an optimal flow diagram.

[0049] When creating a flow diagram, the flow diagram creation unit can generate an optimal flow diagram by taking into account the user's device information. The flow diagram creation unit, for example, generates a flow diagram by taking into account the user's device information. For example, the flow diagram creation unit acquires the screen size and OS type of the device used by the user and generates an optimal flow diagram based on that information. Furthermore, if the user is using a smartphone, the flow diagram creation unit can generate a flow diagram that matches the screen size, and if the user is using a tablet, the flow diagram creation unit can generate a flow diagram optimized for a larger screen. Furthermore, if the user is using a desktop, the flow diagram creation unit can generate a flow diagram that includes detailed information. This allows the optimal flow diagram to be provided by taking into account the user's device information. Some or all of the above-described processing in the flow diagram creation unit may be performed using, or without, a generation AI. For example, the flow diagram creation unit may input the user's device information into a generation AI to generate an optimal flow diagram.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The SNS sanitization system can further include a history analysis unit that analyzes a user's past posting history. The history analysis unit collects the user's past posting content and reactions and analyzes their patterns. For example, the history analysis unit can grasp trends in abusive comments by analyzing what kind of comments a user has posted in the past and what kind of reactions they have received. The history analysis unit can also predict when a user is likely to post abusive comments based on the past posting history. Furthermore, the history analysis unit can provide data for generating optimal humorous words and images based on the user's past reactions. This allows the history analysis unit to utilize a user's past posting history to more effectively prevent abusive comments.

[0052] The suggestion unit can further generate an alternative comment taking into account the user's cultural background. For example, the suggestion unit selects an appropriate alternative comment taking into account the user's national culture and religious background. The suggestion unit can also suggest an alternative comment that does not lead to misunderstandings by taking into account the user's cultural background. For example, the suggestion unit generates alternative comments that correspond to different cultures. Furthermore, the suggestion unit can suggest alternative comments that are specific to a region according to the user's cultural background. In this way, an appropriate alternative comment that does not lead to misunderstandings can be provided by taking into account the user's cultural background.

[0053] The generation unit can further analyze the user's social media activity and generate relevant humorous words and images. For example, the generation unit collects the user's past posts and followers' reactions and analyzes the patterns. The generation unit can also select the most appropriate humorous expression based on the user's social media activity. Furthermore, the generation unit can analyze the user's social media activity in real time and generate relevant humorous words and images. In this way, relevant humorous words and images can be provided by analyzing the user's social media activity.

[0054] The detection unit can further detect region-specific abusive language by taking into account the user's geographic location information. For example, the detection unit can obtain the user's geographic location information using GPS data or an IP address and detect region-specific abusive language. The detection unit can also improve detection accuracy by referencing a database of abusive language for each region. Furthermore, the detection unit can update the geographic location information in real time and detect region-specific abusive language. In this way, by taking into account the geographic location information, region-specific abusive language can be accurately detected.

[0055] The detection unit can further analyze the user's social media activity to detect related abusive comments. For example, the detection unit can analyze the user's past social media activity to learn patterns of abusive comments. The detection unit can also detect related abusive comments in real time based on the learned patterns. Furthermore, when new social media activity is discovered, the detection unit can update the learning data to improve detection accuracy. This allows related abusive comments to be accurately detected by analyzing social media activity.

[0056] The generation unit can further select the most appropriate humorous expression by referring to the user's past reactions. For example, the generation unit can analyze the user's past social media activities and select the most appropriate humorous expression based on the user's previously preferred humor style. The generation unit can also analyze the user's past reactions and select the most effective humorous expression. Furthermore, the generation unit can update the user's past reaction data and always provide the most appropriate humorous expression. In this way, the most appropriate humorous expression can be provided by referring to the user's past reactions.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The detection unit analyzes in real time the comments that users are about to post and determines whether they are potentially defamatory. For example, the detection unit uses natural language processing technology to analyze the content of the comment and determines that it is a defamatory comment if it contains specific words or phrases such as "idiot" or "die." The detection unit can also use context analysis technology to consider the context before and after the comment to more accurately determine the intent of the comment as defamatory. Step 2: The generation unit uses a generation AI to generate humorous words and images in response to the abusive comments detected by the detection unit. For example, the generation AI uses a text generation AI (e.g., GPT-4) to generate humorous words such as, "Don't say that, let's talk about something more fun!" The generation AI can also use an image generation AI to generate images of smiling characters. Furthermore, the generation unit can generate humorous words and images taking into account multilingual support and cultural differences. For example, the generation AI generates humorous words and images that are compatible with different languages ​​and cultures. Step 3: The suggestion unit uses the generation AI to generate an appropriate alternative comment to replace the abusive comment and present it to the user. For example, the generation AI may generate an alternative comment such as, "I don't agree with that opinion, but here's another way of thinking." The suggestion unit may also present multiple alternative comments for the user to choose from. For example, the generation AI may generate alternative comments with different tones and styles and present them to the user.

[0059] (Example 2) A system according to an embodiment of the present invention uses humorous words, audio, and images to admonish users who are about to post abusive comments on social networking sites, and suggests alternative comments. This system first detects abusive comments when a user attempts to post them. Next, the system uses humorous words, audio, and images to admonish the poster of the detected comment. A generation AI generates humorous words, audio, and images. An alternative comment is then suggested. The generation AI also generates and presents the alternative comment to the user. This prevents the posting of abusive comments on social networking sites and promotes healthy communication. For example, a system detects abusive comments when a user attempts to post them. The AI ​​analyzes the content of the comment and determines whether it is potentially abusive. For example, if the comment contains words such as "idiot" or "die," it is determined to be abusive. Next, the system uses humorous words, audio, and images to admonish the poster of the detected comment. In this case, the generative AI generates humorous words, sounds, and images. For example, it can generate phrases like, "Don't say that! Let's talk about something more fun!" or an image of a smiling character. This can encourage posters to refrain from posting abusive comments. It also suggests alternative comments. The generative AI generates appropriate alternatives to abusive comments and presents them to users. For example, it can generate alternative comments such as, "I don't agree with that opinion, but here's another way of thinking." This allows users to post constructive comments instead of abusive comments. This mechanism can prevent the posting of abusive comments on social media and promote healthy communication. When users are about to post abusive comments, the generative AI can advise them and suggest alternative comments, leading to better communication. For example, even if a discussion on social media becomes heated and abusive comments are about to be posted, the generative AI can intervene appropriately to maintain a healthy discussion.This will prevent the posting of abusive comments on social media and promote healthy communication.

[0060] An SNS sanitization system according to an embodiment includes a detection unit, a generation unit, and a suggestion unit. The detection unit analyzes comments posted by users in real time and determines whether the comments are likely to be defamatory. For example, the detection unit uses natural language processing technology to analyze the content of the comments and determine that the comments are defamatory if they contain specific words or phrases such as "idiot" or "die." The detection unit can also use context analysis technology to consider the context before and after the comment and more accurately determine the intent of the defamatory comment. The generation unit uses a generation AI to generate humorous words or images in response to the defamatory comment detected by the detection unit. For example, the generation AI uses a text generation AI (e.g., GPT-4) to generate humorous words such as "Don't say that. Let's talk about something more fun!" The generation AI can also use an image generation AI to generate images of smiling characters. The generation unit can also generate humorous words and images taking into account multilingual support and cultural differences. For example, the generation AI generates humorous words and images that correspond to different languages ​​and cultures. The suggestion unit uses the generation AI to generate appropriate alternative comments to replace defamatory comments and present them to the user. For example, the generation AI generates alternative comments such as, "I don't agree with that opinion, but here's another way of thinking." The suggestion unit can also present multiple alternative comments for the user to choose from. For example, the generation AI generates alternative comments with different tones and styles and presents them to the user. As a result, the SNS sanitization system according to the embodiment can detect defamatory comments, admonish them with humorous words and images, and suggest alternative comments, thereby promoting healthy communication.

[0061] The generation unit can generate humorous words and images using a generation AI. The generation unit can generate humorous words using, for example, a text generation AI (e.g., GPT-4). For example, the generation unit can generate humorous words such as, "Don't say that, let's talk about something more fun!" The generation unit can also generate humorous images using an image generation AI. For example, the generation unit can generate an image of a smiling character. Furthermore, the generation unit can generate humorous words and images taking into account multilingual support and cultural differences. For example, the generation unit generates humorous words and images that correspond to different languages ​​and cultures. This improves the accuracy of generating humorous words and images by using a generation AI. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input a prompt such as, "Generate a humorous word" to a text generation AI and output the generated word.

[0062] The suggestion unit can generate an alternative comment using a generation AI. The suggestion unit generates an alternative comment using, for example, a text generation AI (e.g., GPT-4). For example, the suggestion unit generates an alternative comment such as, "I don't agree with that opinion, but there is also this way of thinking." The suggestion unit can also present multiple alternative comments for the user to choose from. For example, the suggestion unit generates alternative comments with different tones and styles and presents them to the user. This improves the accuracy of generating alternative comments by using the generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can input a prompt to the text generation AI, such as "Please generate an alternative comment," and output the generated comment.

[0063] The generation unit can generate specific words and images taking into account multilingual support and cultural differences. The generation unit, for example, uses a text generation AI (e.g., GPT-4) to generate humorous words that are multilingual. For example, the generation unit generates humorous words in different languages, such as English, Japanese, and French. The generation unit can also use an image generation AI to generate humorous images that take cultural differences into account. For example, the generation unit generates images of smiling characters that correspond to different cultures. This allows for the generation of more appropriate humorous words and images by taking into account multilingual support and cultural differences. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input a prompt to the text generation AI, such as "Generate humorous words that are multilingual," and output the generated words.

[0064] The suggestion unit can present multiple alternative comments to the user to select from. The suggestion unit generates multiple alternative comments using, for example, a text generation AI (e.g., GPT-4). For example, the suggestion unit generates an alternative comment such as, "I don't agree with that opinion, but here's another way of thinking." The suggestion unit can also generate alternative comments with different tones or styles and present them to the user. For example, the suggestion unit presents multiple options, such as alternative comments that include light humor and alternative comments that are gentle. By presenting multiple alternative comments, the user can select the most appropriate comment. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input a prompt to the text generation AI, such as, "Generate multiple alternative comments," and output the generated comments.

[0065] The detection unit instantly detects abusive comments, allowing the generation unit and suggestion unit to intervene immediately. The detection unit, for example, uses natural language processing technology to analyze comments that users are about to post in real time and instantly determine whether they are potentially abusive. For example, the detection unit may determine that a comment is abusive if it contains specific words or phrases such as "idiot" or "die." The detection unit can also use context analysis technology to consider the context before and after the comment to more accurately determine the intent of the comment. The generation unit instantly generates humorous words or images in response to abusive comments detected by the detection unit. For example, the generation unit uses text generation AI (e.g., GPT-4) to instantly generate humorous words such as "Don't say that. Let's talk about something more fun!" The generation unit can also instantly generate images of smiling characters using image generation AI. The suggestion unit instantly generates an alternative comment based on the humorous words and images generated by the generation unit and presents it to the user. For example, the suggestion unit uses a text generation AI to instantly generate an alternative comment such as, "I don't agree with that opinion, but here's another way of thinking." This enables real-time detection and intervention to quickly prevent abusive comments. Some or all of the above-described processing in the detection unit, generation unit, and suggestion unit may be performed using, or without, the generation AI. For example, the detection unit analyzes the comment using natural language processing technology, the generation unit inputs a prompt to the text generation AI such as, "Please generate some humorous words," and the suggestion unit generates an alternative comment based on the generated words.

[0066] The SNS sanitization system includes a flow diagram creation unit that illustrates the overall system flow. The flow diagram creation unit generates a flow diagram that visually shows the operation of each unit of the system. For example, the flow diagram creation unit sequentially illustrates the operation of each element of the detection unit, generation unit, and suggestion unit, showing the system operation flow when a user attempts to post an abusive comment. The flow diagram creation unit can also generate an optimal flow diagram by referencing the system's operation history. For example, the flow diagram creation unit generates an efficient flow diagram based on the system's past operation history. Furthermore, the flow diagram creation unit can estimate the user's emotions and adjust the display method of the flow diagram based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible flow diagram is displayed, and if the user is relaxed, a flow diagram containing detailed information is displayed. This allows the flow diagram creation unit to visually facilitate understanding of the system's operation. Some or all of the above-described processing in the flow diagram creation unit may be performed using, or without, a generation AI. For example, the flow diagram creation unit inputs the system's operation history into the generation AI to generate an optimal flow diagram.

[0067] The detection unit can estimate the user's emotions and adjust the detection accuracy of abusive comments based on the estimated user emotions. The detection unit estimates the user's emotions using, for example, facial expression recognition technology. For example, the detection unit analyzes facial expression data of the user captured by a camera to estimate whether the user is angry, sad, or relaxed. The detection unit can also estimate the user's emotions using text analysis technology. For example, the detection unit analyzes the content of a comment the user is about to post and calculates an emotion score. Furthermore, the detection unit adjusts the detection accuracy of abusive comments based on the estimated user emotions. For example, if the user is angry, the detection accuracy is increased to more accurately detect abusive comments, and if the user is sad, the detection accuracy is adjusted to avoid false detection of emotional comments. In this way, adjusting the detection accuracy according to the user's emotions reduces false detections and enables accurate detection. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the detection unit can use facial expression recognition technology to estimate the user's emotions, input a prompt to the generation AI saying, "Please adjust the detection accuracy of defamatory comments," and output the generated adjustment results.

[0068] The detection unit can improve detection accuracy by analyzing past posting history and learning patterns of defamatory comments against a specific user. The detection unit, for example, analyzes past posting history and learns patterns of defamatory comments against a specific user. For example, the detection unit collects past defamatory comments against a specific user and analyzes the patterns. The detection unit can also detect similar defamatory comments in real time based on the learned patterns. For example, the detection unit extracts characteristics of defamatory comments against a specific user based on the past posting history and uses them for real-time detection. Furthermore, when a new defamatory pattern is discovered, the detection unit can update the learning data to improve detection accuracy. For example, the detection unit adds the newly discovered pattern of defamatory comments to the learning data to improve detection accuracy. In this way, by analyzing past posting history, the detection unit can learn patterns of defamatory comments against a specific user and improve detection accuracy. Some or all of the above-described processing in the detection unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the detection unit may input past posting history into the generation AI and have it learn patterns of defamation.

[0069] The detection unit analyzes the context of the comment during detection, thereby enabling more accurate determination of the intent to be defamatory. The detection unit analyzes the context of the comment using, for example, natural language processing technology. For example, the detection unit considers the context before and after the comment to determine the intent to be defamatory. The detection unit can also detect defamation by considering not only keywords in the comment but the entire context. For example, the detection unit analyzes the context before and after the comment to more accurately determine the intent to be defamatory. Furthermore, the detection unit can reduce false positives and accurately detect defamatory comments through context analysis. For example, the detection unit uses context analysis technology to analyze the context before and after the comment to determine the intent to be defamatory. In this way, by analyzing the context of the comment, the intent to be defamatory can be more accurately determined. Some or all of the above-described processing in the detection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the detection unit can use natural language processing technology to analyze the context of the comment, input a prompt to the generation AI such as "Please determine the intent of the comment as defamatory," and output the generated determination result.

[0070] The detection unit can estimate the user's emotions and prioritize the detected comments based on the estimated user emotions. The detection unit estimates the user's emotions using, for example, facial expression recognition technology. For example, the detection unit analyzes facial expression data of the user captured by a camera and estimates whether the user is angry, sad, or relaxed. The detection unit can also estimate the user's emotions using text analysis technology. For example, the detection unit analyzes the content of a comment the user is about to post and calculates an emotion score. Furthermore, the detection unit prioritizes the detected comments based on the estimated user emotions. For example, if the user is angry, the detection unit can prioritize abusive comments, and if the user is sad, the detection unit can adjust the priority of emotional comments. This allows important comments to be prioritized by prioritizing comments according to the user's emotions. Some or all of the above-described processing in the detection unit can be performed using, for example, a generation AI, or without a generation AI. For example, the detection unit can use facial expression recognition technology to estimate the user's emotions, input a prompt to the generation AI such as "Please determine the priority of the comments," and output the generated priorities.

[0071] During detection, the detection unit can detect region-specific defamatory expressions by taking into account the user's geographical location information. The detection unit acquires the user's geographical location information using, for example, GPS data or an IP address. For example, the detection unit detects region-specific defamatory expressions based on the user's geographical location information. The detection unit can also improve detection accuracy by referring to a database of defamatory expressions for each region. For example, the detection unit detects defamatory expressions commonly used in a specific region using a database of defamatory expressions for each region. Furthermore, the detection unit can update the geographical location information in real time to detect region-specific defamatory expressions. For example, the detection unit acquires the user's geographical location information in real time and detects region-specific defamatory expressions. In this way, region-specific defamatory expressions can be accurately detected by taking the geographical location information into account. Some or all of the above-described processing in the detection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the detection unit can input GPS data and IP addresses into the generation AI to detect defamatory language specific to a region.

[0072] During detection, the detection unit can analyze the user's social media activity and detect related abusive comments. The detection unit, for example, analyzes the user's past social media activity and learns patterns of abusive comments. For example, the detection unit collects the user's past posts and followers' reactions and analyzes the patterns. The detection unit can also detect related abusive comments in real time based on the learned patterns. For example, the detection unit extracts characteristics of abusive comments based on the user's past social media activity and uses them for real-time detection. Furthermore, when new social media activity is discovered, the detection unit can update the learning data to improve detection accuracy. For example, the detection unit adds newly discovered patterns of abusive comments to the learning data to improve detection accuracy. This allows related abusive comments to be accurately detected by analyzing social media activity. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generation AI or without a generation AI. For example, the detection unit can input a user's social media activity into the generation AI to detect abusive comments.

[0073] The generation unit can estimate the user's emotions and adjust the generation method of humorous words and images based on the estimated user's emotions. The generation unit estimates the user's emotions using, for example, facial expression recognition technology. For example, the generation unit analyzes facial expression data of the user captured by a camera and estimates whether the user is angry, sad, or relaxed. The generation unit can also estimate the user's emotions using text analysis technology. For example, the generation unit analyzes the content of a comment the user is about to post and calculates an emotion score. Furthermore, the generation unit adjusts the generation method of humorous words and images based on the estimated user's emotions. For example, if the user is relaxed, the generation unit generates lightly humorous words and images, and if the user is angry, the generation unit generates mildly humorous words and images. This allows the generation method of humorous words and images to be adjusted according to the user's emotions, thereby providing more appropriate humor. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can use facial expression recognition technology to estimate the user's emotions, input a prompt to the generation AI such as "Please adjust the way humorous words and images are generated," and output the generated adjustment results.

[0074] The generation unit can apply different humor styles depending on the content of the comment during generation. The generation unit can apply different humor styles depending on the content of the comment, for example, using a text generation AI (e.g., GPT-4). For example, the generation unit can apply a light humor style to mildly abusive comments and a mild humor style to seriously abusive comments. The generation unit can also apply a general humor style to neutral comments. This allows for more effective humor to be provided by applying a humor style depending on the content of the comment. Some or all of the above-described processing in the generation unit can be performed using, or without, the generation AI. For example, the generation unit can input a prompt to the text generation AI, such as "Please apply different humor styles depending on the content of the comment," and output the generated style.

[0075] During generation, the generation unit can select an optimal humorous expression by referring to the user's past reactions. The generation unit, for example, analyzes the user's past social media activities to select an optimal humorous expression. For example, the generation unit selects an optimal humorous expression based on the user's previously preferred style of humor. The generation unit can also analyze the user's past reactions to select the most effective humorous expression. Furthermore, the generation unit can update the user's past reaction data to always provide the optimal humorous expression. For example, the generation unit selects and generates an optimal humorous expression based on the user's past reaction data. In this way, the optimal humorous expression can be provided by referring to the user's past reactions. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's past reaction data into the generation AI to select the optimal humorous expression.

[0076] The generation unit can estimate the user's emotions and prioritize humorous words and images to be generated based on the estimated user's emotions. The generation unit estimates the user's emotions using, for example, facial expression recognition technology. For example, the generation unit analyzes facial expression data of the user captured by a camera and estimates whether the user is angry, sad, or relaxed. The generation unit can also estimate the user's emotions using text analysis technology. For example, the generation unit analyzes the content of a comment the user intends to post and calculates an emotion score. Furthermore, the generation unit prioritizes humorous words and images to be generated based on the estimated user's emotions. For example, if the user is angry, the generation unit prioritizes mildly humorous words and images, and if the user is relaxed, the generation unit prioritizes lightly humorous words and images. This allows for more effective humor to be provided by prioritizing humorous words and images according to the user's emotions. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can estimate the user's emotions using facial expression recognition technology, input a prompt to the generation AI such as "Please prioritize humorous words and images," and output the generated priorities.

[0077] The generation unit can generate appropriate humor by taking into account the user's cultural background. For example, the generation unit generates humorous words and images by taking into account the user's cultural background. For example, the generation unit selects an appropriate humor style by taking into account the user's national culture and religious background. The generation unit can also generate humor that does not lead to misunderstandings by taking into account the user's cultural background. For example, the generation unit generates humorous words and images that correspond to different cultures. Furthermore, the generation unit can generate region-specific humor according to the user's cultural background. For example, the generation unit generates humorous words and images that take into account regional expressions and customs. This allows the user's cultural background to be taken into account, thereby providing appropriate humor that does not lead to misunderstandings. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the user's cultural background into the generation AI to generate appropriate humor.

[0078] During generation, the generation unit can analyze the user's social media activity and generate relevant humorous words and images. The generation unit, for example, analyzes the user's past social media activity and generates relevant humorous words and images. For example, the generation unit collects the user's past posts and followers' reactions and analyzes their patterns. The generation unit can also select optimal humorous expressions based on the user's social media activity. Furthermore, the generation unit can analyze the user's social media activity in real time and generate relevant humorous words and images. For example, the generation unit generates relevant humorous words and images based on the user's past social media activity and uses them for real-time generation. In this way, relevant humorous words and images can be provided by analyzing the user's social media activity. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's social media activity into a generation AI and generate relevant humorous words and images.

[0079] The suggestion unit can estimate the user's emotions and adjust the method for suggesting alternative comments based on the estimated user's emotions. The suggestion unit can estimate the user's emotions using, for example, facial expression recognition technology. For example, the suggestion unit can analyze the user's facial expression data captured by a camera and estimate whether the user is angry, sad, or relaxed. The suggestion unit can also estimate the user's emotions using text analysis technology. For example, the suggestion unit can analyze the content of a comment the user is about to post and calculate an emotion score. The suggestion unit can also adjust the method for suggesting alternative comments based on the estimated user's emotions. For example, if the user is angry, the suggestion unit can suggest a calm alternative comment, and if the user is relaxed, the suggestion unit can suggest an alternative comment that includes light humor. This allows for adjusting the method for suggesting alternative comments according to the user's emotions, thereby providing more appropriate alternative comments. Some or all of the above-described processing in the suggestion unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the suggestion unit can estimate the user's emotions using facial expression recognition technology, input a prompt to the generation AI saying, "Please adjust the method for suggesting alternative comments," and output the generated adjustment result.

[0080] When making a suggestion, the suggestion unit can apply different alternative comment styles depending on the content of the comment. The suggestion unit can apply different alternative comment styles depending on the content of the comment, for example, using a text generation AI (e.g., GPT-4). For example, the suggestion unit can suggest an alternative comment that includes light humor for a mildly abusive comment, and a milder alternative comment for a seriously abusive comment. The suggestion unit can also suggest a general alternative comment for a neutral comment. This allows for more effective alternative comments to be provided by applying an alternative comment style depending on the content of the comment. Some or all of the above-described processing in the suggestion unit can be performed using, or without, a generation AI. For example, the suggestion unit can input a prompt to the text generation AI, such as "Please apply different alternative comment styles depending on the content of the comment," and output the generated style.

[0081] When making a suggestion, the suggestion unit can select an optimal alternative comment by referring to the user's past reactions. The suggestion unit, for example, analyzes the user's past social media activities to select an optimal alternative comment. For example, the suggestion unit selects an optimal alternative comment based on the style of alternative comments that the user has previously preferred. The suggestion unit can also analyze the user's past reactions to select the most effective alternative comment. Furthermore, the suggestion unit can update the user's past reaction data to always provide the optimal alternative comment. For example, the suggestion unit selects and generates an optimal alternative comment based on the user's past reaction data. In this way, the optimal alternative comment can be provided by referring to the user's past reactions. Some or all of the above-described processing in the suggestion unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the suggestion unit can input the user's past reaction data into a generation AI to select an optimal alternative comment.

[0082] The suggestion unit can estimate the user's emotions and determine the priority of alternative comments to be suggested based on the estimated user's emotions. The suggestion unit estimates the user's emotions using, for example, facial expression recognition technology. For example, the suggestion unit analyzes facial expression data of the user captured by a camera and estimates whether the user is angry, sad, or relaxed. The suggestion unit can also estimate the user's emotions using text analysis technology. For example, the suggestion unit analyzes the content of a comment the user intends to post and calculates an emotion score. Furthermore, the suggestion unit determines the priority of alternative comments to be suggested based on the estimated user's emotions. For example, if the user is angry, the suggestion unit prioritizes calm alternative comments, and if the user is relaxed, the suggestion unit prioritizes alternative comments containing light humor. This allows for more effective alternative comments to be provided by prioritizing alternative comments according to the user's emotions. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can estimate the user's emotions using facial expression recognition technology, input a prompt to the generation AI such as "Please determine the priority of alternative comments," and output the generated priority.

[0083] When making a suggestion, the suggestion unit can suggest an appropriate alternative comment by taking into account the user's cultural background. The suggestion unit, for example, generates an alternative comment by taking into account the user's cultural background. For example, the suggestion unit selects an appropriate alternative comment by taking into account the user's national culture and religious background. The suggestion unit can also suggest an alternative comment that does not lead to misunderstandings by taking into account the user's cultural background. For example, the suggestion unit generates an alternative comment that corresponds to a different culture. Furthermore, the suggestion unit can also suggest an alternative comment that is specific to a region according to the user's cultural background. For example, the suggestion unit generates an alternative comment that takes into account expressions and customs specific to a region. This makes it possible to provide an appropriate alternative comment that does not lead to misunderstandings by taking into account the user's cultural background. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the user's cultural background into a generation AI to generate an appropriate alternative comment.

[0084] When making a suggestion, the suggestion unit can analyze the user's social media activity and suggest a related alternative comment. The suggestion unit, for example, analyzes the user's past social media activity and suggests a related alternative comment. For example, the suggestion unit collects the user's past posts and followers' reactions and analyzes their patterns. The suggestion unit can also select an optimal alternative comment based on the user's social media activity. Furthermore, the suggestion unit can analyze the user's social media activity in real time and suggest a related alternative comment. For example, the suggestion unit generates a related alternative comment based on the user's past social media activity and uses it for real-time suggestions. In this way, the user's social media activity can be analyzed to provide a related alternative comment. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input the user's social media activity into a generation AI and generate a related alternative comment.

[0085] The flow diagram creation unit can estimate a user's emotions and adjust the display method of the flow diagram based on the estimated user's emotions. The flow diagram creation unit estimates the user's emotions using, for example, facial expression recognition technology. For example, the flow diagram creation unit analyzes facial expression data of the user captured by a camera to estimate whether the user is nervous, relaxed, or in a hurry. The flow diagram creation unit can also estimate the user's emotions using text analysis technology. For example, the flow diagram creation unit analyzes the content the user is viewing and calculates an emotion score. Furthermore, the flow diagram creation unit adjusts the display method of the flow diagram based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible flow diagram is displayed, and if the user is relaxed, a flow diagram containing detailed information is displayed. This allows the display method of the flow diagram to be adjusted according to the user's emotions, thereby providing a more visible flow diagram. Some or all of the above-described processing in the flow diagram creation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the flow diagram creation unit can use facial expression recognition technology to estimate the user's emotions, input a prompt to the generation AI such as "Please adjust the way the flow diagram is displayed," and output the generated adjustment results.

[0086] When creating a flow diagram, the flow diagram creation unit can generate an optimal flow diagram by referring to the operation history of each part of the system. The flow diagram creation unit generates an optimal flow diagram, for example, based on the past operation history of the system. For example, the flow diagram creation unit collects the operation history of each part of the system and analyzes its patterns. The flow diagram creation unit can also analyze the operation history of each part to generate an efficient flow diagram. Furthermore, the flow diagram creation unit can update the operation history in real time to always provide the latest flow diagram. For example, the flow diagram creation unit generates an optimal flow diagram based on the system's operation history and uses it for real-time generation. In this way, the optimal flow diagram can be provided by referring to the system's operation history. Some or all of the above-mentioned processing in the flow diagram creation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the flow diagram creation unit can input the system's operation history into a generation AI to generate an optimal flow diagram.

[0087] The flow diagram creation unit can estimate a user's emotions and prioritize flow diagrams based on the estimated user emotions. The flow diagram creation unit estimates the user's emotions using, for example, facial expression recognition technology. For example, the flow diagram creation unit analyzes facial expression data of the user captured by a camera to estimate whether the user is nervous, relaxed, or in a hurry. The flow diagram creation unit can also estimate the user's emotions using text analysis technology. For example, the flow diagram creation unit analyzes the content the user is viewing and calculates an emotion score. Furthermore, the flow diagram creation unit prioritizes flow diagrams based on the estimated user emotions. For example, if the user is nervous, important flow diagrams are displayed preferentially, and if the user is relaxed, detailed flow diagrams are displayed preferentially. By prioritizing flow diagrams according to the user's emotions, important information can be provided preferentially. Some or all of the above-described processing in the flow diagram creation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the flow diagram creation unit can use facial expression recognition technology to estimate the user's emotions, input a prompt to the generation AI such as "Please determine the priority of the flow diagram," and output the generated priorities.

[0088] When creating a flow diagram, the flow diagram creation unit can generate an optimal flow diagram by taking into account the user's device information. The flow diagram creation unit, for example, generates a flow diagram by taking into account the user's device information. For example, the flow diagram creation unit acquires the screen size and OS type of the device used by the user and generates an optimal flow diagram based on that information. Furthermore, if the user is using a smartphone, the flow diagram creation unit can generate a flow diagram that matches the screen size, and if the user is using a tablet, the flow diagram creation unit can generate a flow diagram optimized for a larger screen. Furthermore, if the user is using a desktop, the flow diagram creation unit can generate a flow diagram that includes detailed information. This allows the optimal flow diagram to be provided by taking into account the user's device information. Some or all of the above-described processing in the flow diagram creation unit may be performed using, or without, a generation AI. For example, the flow diagram creation unit may input the user's device information into a generation AI to generate an optimal flow diagram. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned detection unit, generation unit, suggestion unit, and flow diagram creation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the detection unit is realized by the control unit 46A of the smart device 14 and analyzes comments that users intend to post in real time. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates humorous words and images. The suggestion unit is realized by the control unit 46A of the smart device 14 and generates alternative comments and presents them to the user. The flow diagram creation unit is realized by the specific processing unit 290 of the data processing device 12 and visually shows the operation flow of the system. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned detection unit, generation unit, suggestion unit, and flow diagram creation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the detection unit is realized by the control unit 46A of the smart glasses 214 and analyzes comments that users intend to post in real time. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates humorous words and images. The suggestion unit is realized, for example, by the control unit 46A of the smart glasses 214 and generates alternative comments and presents them to the user. The flow diagram creation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and visually shows the operation flow of the system. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned detection unit, generation unit, suggestion unit, and flow diagram creation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the detection unit is realized by the control unit 46A of the headset type terminal 314 and analyzes in real time comments that users are about to post. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates humorous words and images. The suggestion unit is realized, for example, by the control unit 46A of the headset type terminal 314 and generates alternative comments and presents them to the user. The flow diagram creation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and visually shows the operation flow of the system. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned detection unit, generation unit, suggestion unit, and flow diagram creation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the detection unit is realized by the control unit 46A of the robot 414 and analyzes in real time comments that users are about to post. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates humorous words and images. The suggestion unit is realized, for example, by the control unit 46A of the robot 414 and generates alternative comments and presents them to the user. The flow diagram creation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and visually shows the operation flow of the system.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The SNS sanitization system can further include a history analysis unit that analyzes a user's past posting history. The history analysis unit collects the user's past posting content and reactions and analyzes their patterns. For example, the history analysis unit can grasp trends in abusive comments by analyzing what kind of comments a user has posted in the past and what kind of reactions they have received. The history analysis unit can also predict when a user is likely to post abusive comments based on the past posting history. Furthermore, the history analysis unit can provide data for generating optimal humorous words and images based on the user's past reactions. This allows the history analysis unit to utilize a user's past posting history to more effectively prevent abusive comments.

[0091] The generation unit can further estimate the user's emotion and adjust the method of generating humorous words and images based on the estimated user's emotion. For example, the generation unit can estimate the user's emotion using facial expression recognition technology and generate mildly humorous words and images when the user is angry, and generate lightly humorous words and images when the user is relaxed. The generation unit can also estimate the user's emotion using text analysis technology and adjust the style of humor to be generated based on the emotion score. This makes it possible to provide optimal humorous words and images according to the user's emotion.

[0092] The suggestion unit can further generate an alternative comment taking into account the user's cultural background. For example, the suggestion unit selects an appropriate alternative comment taking into account the user's national culture and religious background. The suggestion unit can also suggest an alternative comment that does not lead to misunderstandings by taking into account the user's cultural background. For example, the suggestion unit generates alternative comments that correspond to different cultures. Furthermore, the suggestion unit can suggest alternative comments that are specific to a region according to the user's cultural background. In this way, an appropriate alternative comment that does not lead to misunderstandings can be provided by taking into account the user's cultural background.

[0093] The generation unit can further analyze the user's social media activity and generate relevant humorous words and images. For example, the generation unit collects the user's past posts and followers' reactions and analyzes the patterns. The generation unit can also select the most appropriate humorous expression based on the user's social media activity. Furthermore, the generation unit can analyze the user's social media activity in real time and generate relevant humorous words and images. In this way, relevant humorous words and images can be provided by analyzing the user's social media activity.

[0094] The suggestion unit can further estimate the user's emotion and adjust the method of suggesting alternative comments based on the estimated user's emotion. For example, the suggestion unit can estimate the user's emotion using facial expression recognition technology and suggest a calm alternative comment if the user is angry, or suggest an alternative comment containing light humor if the user is relaxed. The suggestion unit can also estimate the user's emotion using text analysis technology and adjust the style of the suggested alternative comment based on the emotion score. This makes it possible to provide an optimal alternative comment according to the user's emotion.

[0095] The detection unit can further detect region-specific abusive language by taking into account the user's geographic location information. For example, the detection unit can obtain the user's geographic location information using GPS data or an IP address and detect region-specific abusive language. The detection unit can also improve detection accuracy by referencing a database of abusive language for each region. Furthermore, the detection unit can update the geographic location information in real time and detect region-specific abusive language. In this way, by taking into account the geographic location information, region-specific abusive language can be accurately detected.

[0096] The SNS sanitization system may further include an emotion adjustment unit that estimates the user's emotion and adjusts the system's operation based on the estimated user's emotion. The emotion adjustment unit may estimate the user's emotion using, for example, facial expression recognition technology, and calm the system's response when the user is angry, and lighten the system's response when the user is relaxed. The emotion adjustment unit may also estimate the user's emotion using text analysis technology and adjust the system's operation based on the emotion score. This allows the system's operation to be optimized according to the user's emotion.

[0097] The detection unit can further analyze the user's social media activity to detect related abusive comments. For example, the detection unit can analyze the user's past social media activity to learn patterns of abusive comments. The detection unit can also detect related abusive comments in real time based on the learned patterns. Furthermore, when new social media activity is discovered, the detection unit can update the learning data to improve detection accuracy. This allows related abusive comments to be accurately detected by analyzing social media activity.

[0098] The generation unit can further select the most appropriate humorous expression by referring to the user's past reactions. For example, the generation unit can analyze the user's past social media activities and select the most appropriate humorous expression based on the user's previously preferred humor style. The generation unit can also analyze the user's past reactions and select the most effective humorous expression. Furthermore, the generation unit can update the user's past reaction data and always provide the most appropriate humorous expression. In this way, the most appropriate humorous expression can be provided by referring to the user's past reactions.

[0099] The suggestion unit can further estimate the user's emotion and determine the priority of alternative comments to be suggested based on the estimated user's emotion. For example, the suggestion unit can estimate the user's emotion using facial expression recognition technology, and prioritize suggesting calm alternative comments when the user is angry, and prioritize suggesting alternative comments containing light humor when the user is relaxed. The suggestion unit can also estimate the user's emotion using text analysis technology and prioritize suggesting alternative comments to be suggested based on emotion scores. This makes it possible to provide optimal alternative comments according to the user's emotion.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The detection unit analyzes in real time the comments that users are about to post and determines whether they are potentially defamatory. For example, the detection unit uses natural language processing technology to analyze the content of the comment and determines that it is a defamatory comment if it contains specific words or phrases such as "idiot" or "die." The detection unit can also use context analysis technology to consider the context before and after the comment to more accurately determine the intent of the comment as defamatory. Step 2: The generation unit uses a generation AI to generate humorous words and images in response to the abusive comments detected by the detection unit. For example, the generation AI uses a text generation AI (e.g., GPT-4) to generate humorous words such as, "Don't say that, let's talk about something more fun!" The generation AI can also use an image generation AI to generate images of smiling characters. Furthermore, the generation unit can generate humorous words and images taking into account multilingual support and cultural differences. For example, the generation AI generates humorous words and images that are compatible with different languages ​​and cultures. Step 3: The suggestion unit uses the generation AI to generate an appropriate alternative comment to replace the abusive comment and present it to the user. For example, the generation AI may generate an alternative comment such as, "I don't agree with that opinion, but here's another way of thinking." The suggestion unit may also present multiple alternative comments for the user to choose from. For example, the generation AI may generate alternative comments with different tones and styles and present them to the user.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0104] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0105] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

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

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

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

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

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

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

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

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

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

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

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

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

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

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 7, a 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.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0157] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0158] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0159] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0162] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0163] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0164] 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.

[0165] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0166] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0167] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0168] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0170] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0171] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0172] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0173] [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a detection unit that detects defamatory comments; a generation unit that generates specific words or images for the comments detected by the detection unit; a suggestion unit that suggests alternative comments based on the specific words and images generated by the generation unit; Equipped with A system characterized by:

2. The generation unit Generate humorous words and images using generative AI The system of claim 1 .

3. The proposal unit Generate alternative comments using generative AI The system of claim 1 .

4. The generation unit Generate specific words and images that take multilingual and cultural differences into account The system of claim 1 .

5. The proposal unit Present multiple alternative comments for the user to choose from The system of claim 1 .

6. The detection unit Immediately detects abusive comments, and the generation unit and suggestion unit intervene immediately. The system of claim 1 .

7. Equipped with a flow diagram creation section that illustrates the flow of the entire system The system of claim 1 .

8. The detection unit Estimate user emotions and adjust the accuracy of detecting abusive comments based on the estimated user emotions. The system of claim 1 .

Images