System

Abstract

An object of a system according to an embodiment is to detect a defamatory comment and change the comment to an appropriate expression.SOLUTION: A system according to an embodiment includes an analysis unit, a detection unit, and a change unit. The analysis unit analyzes the comment. The detection unit detects slander and defamation from the comment analyzed by the analysis unit. The change unit changes the content of the slander detected by the detection unit to an appropriate expression.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have not adequately detected abusive comments on the Internet and have not adequately modified the wording, so there is room for improvement.

[0005] The system according to the embodiment aims to detect abusive comments and change them to appropriate expressions. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a detection unit, and a modification unit. The analysis unit analyzes comments. The detection unit detects defamatory comments from the comments analyzed by the analysis unit. The modification unit modifies the defamatory comments detected by the detection unit into appropriate expressions. [Effects of the Invention]

[0007] The system according to the embodiment can detect abusive comments and change them to appropriate expressions. [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) An AI system according to an embodiment of the present invention is a system for preventing content creators from suffering from slander. This system analyzes comments posted in a comment section, detects slanderous content, and naturally changes the content to a kinder, more harmless expression. This allows content creators to protect themselves from slander while leaving the comment section intact. This allows content creators to continue their activities without worrying about slander. It also enables the comment section to function as a place for healthy communication. For example, the AI ​​system analyzes comments posted in a comment section. For example, the AI ​​system understands the content of the comments using natural language processing technology. Next, the AI ​​system detects slanderous content. For example, the AI ​​system identifies parts of the comments that are slanderous and changes those parts to a kinder, more harmless expression. This allows the AI ​​system to protect content creators from slander while leaving the comment section intact. Furthermore, the AI ​​system not only detects abusive content but also takes into account the tone and context of the comment when making changes. This allows the comment to be changed to a more natural expression without losing its overall meaning. For example, the AI ​​system could change a comment such as "Your video is boring" to "Your video has room for improvement, but keep up the good work." This reduces the mental burden on content creators and allows them to provide better content.

[0029] The AI ​​system according to the embodiment includes an analysis unit, a detection unit, and a modification unit. The analysis unit analyzes comments. The analysis unit understands the content of the comments using, for example, natural language processing technology. For example, the analysis unit can break down words in the comments using morphological analysis and analyze sentence structure using grammatical analysis. The analysis unit can also understand the meaning of the comments using semantic analysis. For example, the analysis unit can analyze the intention of the comments by taking into account the context of the comments. The detection unit detects defamation from the comments analyzed by the analysis unit. The detection unit detects defamation by taking into account, for example, the tone and context of the comments. For example, the detection unit can detect an offensive tone or discriminatory language. The detection unit can also detect the intent of defamation by taking into account the context before and after the comment. For example, the detection unit can analyze the relevance of the comments and identify the intent of defamation. The modification unit changes the defamatory content detected by the detection unit to an appropriate expression. The modification unit, for example, modifies the comment to a more natural expression without compromising the overall meaning. For example, the modification unit can modify slanderous content to a more gentle, harmless expression by using grammatically correct expressions and everyday phrases. The modification unit can also modify the comment by taking into consideration the tone and context of the comment. For example, the modification unit can change the tone of the comment to a more friendly one and modify the expression to a more natural one by taking the context into consideration. This allows the AI ​​system according to the embodiment to protect content creators from slander while leaving the comment section intact. This allows content creators to continue their activities with peace of mind, without suffering from slander. Furthermore, the comment section can function as a place for healthy communication.

[0030] The analysis unit can understand the content of the comment using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit can break down the words of the comment using morphological analysis and analyze the structure of the sentence using grammatical analysis. The analysis unit can also understand the meaning of the comment using semantic analysis. For example, the analysis unit can analyze the intention of the comment by taking into account the context of the comment. This allows the analysis unit to accurately understand the content of the comment. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the comment to a generation AI and have the generation AI analyze the content of the comment.

[0031] The detection unit can detect slander based on the tone or context of a comment. For example, the detection unit can analyze the tone of a comment to detect an offensive tone or discriminatory language. The detection unit can also analyze the context of a comment to detect a slanderous intent. For example, the detection unit can identify a slanderous intent by considering the context before and after the comment. Furthermore, the detection unit can analyze the relevance of comments to detect a slanderous intent. For example, when multiple comments are posted in succession, the detection unit can detect slander by considering the relevance of those comments. As a result, the detection unit can improve the accuracy of detecting slander by considering the tone and context of the comments. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the tone and context of a comment into a generation AI, which can then detect slander.

[0032] The modification unit can modify the comment to a more natural expression without losing the overall meaning. For example, the modification unit can modify the abusive content to a more gentle, non-offensive expression by using grammatically correct expressions and everyday phrases. The modification unit can also modify the comment by taking into account the tone and context of the comment. For example, the modification unit can change the tone of the comment to a more friendly one and modify the comment to a more natural expression by taking the context into account. Furthermore, the modification unit can modify the abusive content to a more gentle one while maintaining the overall meaning of the comment. For example, the modification unit can modify a comment such as "Your videos are boring" to a comment such as "Your videos have room for improvement, but please keep up the good work." In this way, the modification unit can modify the abusive content to a more gentle one while maintaining the overall meaning of the comment. Some or all of the above-described processing by the modification unit may be performed using, for example, AI, or may be performed without AI. For example, the modification unit can input the abusive content into a generation AI, which then modifies the content to a more gentle, non-offensive one.

[0033] The modification unit can change the content of defamatory comments to appropriate expressions. For example, the modification unit can change the content of defamatory comments to gentler, more harmless expressions using grammatically correct expressions and everyday phrases. For example, the modification unit can change a comment such as "You should disappear" to "I don't agree with your opinion, but other perspectives are important." The modification unit can also make changes taking into account the tone and context of the comment. For example, the modification unit can change the tone of the comment to a more friendly one and change the expression to a more natural one taking the context into account. In this way, the modification unit can protect content creators by changing the content of defamatory comments to a gentler one. Some or all of the above-described processing by the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the content of defamatory comments into a generation AI, which then changes the content to a gentler, more harmless expression.

[0034] The modification unit can modify the comment based on its tone or context. For example, the modification unit can change the comment's tone to a more friendly one and consider the context to modify the comment to a more natural expression. For example, the modification unit can change a comment such as "Your video is boring" to "Your video has room for improvement, but please keep up the good work." The modification unit can also modify abusive comments to a more gentle one while preserving the overall meaning of the comment. For example, the modification unit can change a comment such as "You should just disappear" to "I don't agree with your opinion, but other perspectives are important." In this way, the modification unit can modify the comment to a more natural expression by considering the tone and context of the comment. Some or all of the above-described processing by the modification unit may be performed using, or without, AI. For example, the modification unit can input the tone and context of the comment into a generation AI, which can then modify the comment to a more natural expression.

[0035] When analyzing comments, the analysis unit can improve the accuracy of the analysis by referring to the user's past comment history. For example, the analysis unit can analyze the trends of comments posted by the user in the past and analyze the intent of the current comment more accurately. The analysis unit can also learn specific expressions and phrases from the user's past comment history and reflect them in the analysis. Furthermore, the analysis unit can adjust the comment analysis method by referring to feedback the user has received in the past. For example, the analysis unit can analyze the trends of comments posted by the user in the past and analyze the intent of the current comment more accurately. In this way, the analysis unit can improve the accuracy of the analysis by referring to the user's past comment history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past comment history into a generation AI and use the generation AI to improve the analysis accuracy.

[0036] When analyzing comments, the analysis unit can take into account the time period and frequency of comment posting. For example, the analysis unit can analyze comments posted late at night by determining that they have a strong emotional element. The analysis unit can also analyze comments posted in rapid succession by determining that they may be spam. Furthermore, the analysis unit can analyze comments posted in a concentrated period of time by taking into account trends and topicality. For example, the analysis unit can analyze comments posted late at night by determining that they have a strong emotional element. In this way, the analysis unit improves analysis accuracy by taking into account the time period and frequency of comment posting. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time period and frequency of comment posting into a generation AI, and have the generation AI perform the analysis.

[0037] When analyzing comments, the analysis unit can take into account the language of the comment and regional expressions. The analysis unit can, for example, take into account slang and dialects used in a specific region during analysis. The analysis unit can also perform multilingual analysis and detect slander in different languages. Furthermore, the analysis unit can accurately analyze the intent of the comment by taking into account regional culture and customs. For example, the analysis unit can take into account slang and dialects used in a specific region during analysis. This improves the analysis accuracy by taking into account the language of the comment and regional expressions. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the language of the comment and regional expressions into a generation AI, which can then perform the analysis.

[0038] When analyzing comments, the analysis unit can take into account the user's geographical location information. For example, if the user is in a specific region, the analysis unit can take into account the culture and customs of that region when analyzing. Furthermore, if the user is traveling, the analysis unit can take into account the language and culture of the destination when analyzing. Furthermore, if the user is participating in a specific event, the analysis unit can take into account information related to the event when analyzing. For example, if the user is in a specific region, the analysis unit can take into account the culture and customs of that region when analyzing. This allows the analysis unit to improve analysis accuracy by taking into account the user's geographical location information. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's geographical location information into a generation AI and have the generation AI perform the analysis.

[0039] When analyzing comments, the analysis unit can analyze the user's social media activity and prioritize analysis of related comments. The analysis unit can, for example, reflect expressions frequently used by the user on social media in the analysis. The analysis unit can also analyze the intent of the comment by referring to the user's social media activity. Furthermore, the analysis unit can analyze comments taking into account the user's friendships on social media. For example, the analysis unit can reflect expressions frequently used by the user on social media in the analysis. This allows the analysis unit to analyze the user's social media activity and prioritize analysis of related comments. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or without AI. For example, the analysis unit can input the user's social media activity into a generation AI and have the generation AI perform the analysis.

[0040] When analyzing comments, the analysis unit can customize the analysis method by reflecting the user's past feedback. The analysis unit can, for example, adjust the analysis method based on feedback provided by the user in the past. The analysis unit can also improve the analysis accuracy by taking into account problems pointed out by the user in the past. Furthermore, the analysis unit can learn specific analysis patterns from the user's past feedback and reflect them in the analysis. For example, the analysis unit can adjust the analysis method based on feedback provided by the user in the past. In this way, the analysis unit can customize the analysis method by reflecting the user's past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past feedback into a generation AI and have the generation AI customize the analysis method.

[0041] The detection unit can improve detection accuracy when detecting slander by taking into account the interrelationships between comments. For example, when multiple comments are posted in succession, the detection unit can detect them by taking into account the relevance of those comments. The detection unit can also analyze the reply relationships between comments to detect slanderous intent. Furthermore, the detection unit can analyze the entire comment exchange and understand the context of the slander to detect it. For example, when multiple comments are posted in succession, the detection unit can detect them by taking into account the relevance of those comments. As a result, the detection unit improves the detection accuracy of slander by taking into account the interrelationships between comments. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the interrelationships between comments into a generation AI, which can then detect slander.

[0042] When detecting slander, the detection unit can perform the detection by taking into account attribute information of the comment poster. For example, if the comment poster has a history of making slanderous comments in the past, the detection unit can tighten the detection criteria. The detection unit can also detect the slanderous intent by taking into account the age and gender of the comment poster. Furthermore, the detection unit can detect slander by referring to the comment poster's social media activity history. For example, the detection unit can tighten the detection criteria if the comment poster has a history of making slanderous comments in the past. As a result, the detection unit improves the accuracy of detecting slander by taking into account the attribute information of the comment poster. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input attribute information of the comment poster into a generation AI, and the generation AI can detect slander.

[0043] When detecting slander, the detection unit can weight the detection based on the frequency of comment posting. For example, the detection unit can prioritize detection of comments by users who post a large number of comments in a short period of time. The detection unit can also prioritize detection of comments posted in a concentrated manner during a specific time period. Furthermore, the detection unit can weight and detect comments by users who have made slanderous remarks in the past. For example, the detection unit can prioritize detection of comments by users who post a large number of comments in a short period of time. This allows the detection unit to weight the detection based on the frequency of comment posting, thereby improving detection accuracy. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the frequency of comment posting into a generation AI, and the generation AI can detect slander.

[0044] When detecting defamation, the detection unit can perform the detection by taking into account the geographical distribution of comments. For example, the detection unit can focus on comments posted in a concentrated manner from a specific region. The detection unit can also analyze comments posted from geographically distant locations to detect defamation. Furthermore, the detection unit can detect defamation by taking into account expressions and slang specific to the region. For example, the detection unit can focus on comments posted in a concentrated manner from a specific region. As a result, the detection unit can improve the accuracy of detecting defamation by taking the geographical distribution of comments into account. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the geographical distribution of comments into a generation AI, and the generation AI can detect defamation.

[0045] When detecting defamation, the detection unit can improve detection accuracy by referring to literature related to the comment. For example, if the content of the comment matches past defamation cases, the detection unit can tighten detection standards. The detection unit can also detect defamatory intent by referring to related academic papers and reports. Furthermore, if the content of the comment is related to a specific topic, the detection unit can detect defamation by referring to literature related to the topic. For example, if the content of the comment matches past defamation cases, the detection unit can tighten detection standards. As a result, the detection unit can improve the detection accuracy of defamation by referring to literature related to the comment. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input literature related to the comment into a generation AI, which can then detect defamation.

[0046] The detection unit can detect slander by taking into account the market value of the comment. For example, the detection unit can prioritize detecting comments with high market value. Furthermore, if the content of a comment is related to a specific product or service, the detection unit can also detect the comment by taking into account its market value. Furthermore, if the comment poster is an influential person, the detection unit can also prioritize detecting the comment. For example, the detection unit can prioritize detecting comments with high market value. As a result, the detection unit can improve the accuracy of detecting slander by taking the market value of the comment into account. Some or all of the above-mentioned processing in the detection unit can be performed using, for example, AI, or without AI. For example, the detection unit can input the market value of the comment into a generation AI, and the generation AI can detect slander.

[0047] When changing a comment, the modification unit can adjust the level of detail of the change based on the importance of the comment. For example, the modification unit can change a comment with high importance to be more detailed. The modification unit can also change a comment with low importance to be more concise. Furthermore, the modification unit can determine the priority of the change according to the importance of the comment. For example, the modification unit can change a comment with high importance to be more detailed. As a result, the modification unit can adjust the level of detail of the change based on the importance of the comment, thereby enabling more appropriate changes. Some or all of the above-mentioned processing in the modification unit may be performed using, or without, AI, for example. For example, the modification unit can input the importance of the comment to a generation AI, and the generation AI can adjust the level of detail of the change.

[0048] When modifying a comment, the modification unit can apply different modification algorithms depending on the category of the comment. For example, the modification unit can modify comments related to politics by applying a specific algorithm. Furthermore, the modification unit can modify comments related to entertainment by applying a different algorithm. Furthermore, the modification unit can modify comments related to sports by applying yet another algorithm. For example, the modification unit can modify comments related to politics by applying a specific algorithm. In this way, the modification unit can apply different modification algorithms depending on the category of the comment, thereby enabling more appropriate modification. Some or all of the above-mentioned processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the category of the comment into a generation AI and apply different modification algorithms using the generation AI.

[0049] When changing a comment, the modification unit can improve the accuracy of the modification by referring to the results of past modifications made by the user. For example, the modification unit can make current modifications based on the results of modifications made by the user in the past. The modification unit can also learn specific patterns from the user's past modification history and reflect them in the modifications. Furthermore, the modification unit can improve the accuracy of the modifications by referring to feedback provided by the user in the past. For example, the modification unit can make current modifications based on the results of modifications made by the user in the past. In this way, the modification unit improves the accuracy of the modifications by referring to the results of past modifications made by the user. Some or all of the above-described processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the results of past modifications made by the user into a generation AI, and the generation AI can improve the accuracy of the modifications.

[0050] When modifying a comment, the modification unit can determine the priority of the modification based on the time the comment was posted. For example, the modification unit can prioritize modifying the most recent comment. The modification unit can also prioritize modifying comments related to a specific event or topic. Furthermore, the modification unit can determine the priority of the modification based on the importance of past comments as well. For example, the modification unit can prioritize modifying the most recent comment. This allows the modification unit to determine the priority of the modification based on the time the comment was posted, thereby enabling more appropriate modifications. Some or all of the above-described processing by the modification unit may be performed using AI, for example, or may be performed without using AI. For example, the modification unit can input the time the comment was posted to a generation AI, and the generation AI can determine the priority of the modification.

[0051] When modifying comments, the modification unit can adjust the order of modification based on the relevance of the comments. For example, the modification unit can prioritize modifying highly relevant comments. Furthermore, if the content of a comment is related to a specific topic, the modification unit can also prioritize modifying comments related to the topic. Furthermore, the modification unit can prioritize modifying highly relevant comments by taking into account the entire comment exchange. For example, the modification unit can prioritize modifying highly relevant comments. This enables the modification unit to adjust the order of modification based on the relevance of the comments, thereby enabling more appropriate modification. Some or all of the above-described processing in the modification unit may be performed using AI, for example, or may be performed without using AI. For example, the modification unit can input the relevance of the comments to a generation AI and allow the generation AI to adjust the order of modification.

[0052] When modifying a comment, the modification unit may adjust the use of technical terms in the modification depending on the user's level of expertise. For example, if the user has technical expertise, the modification unit may modify the comment using technical terms. Furthermore, if the user has general knowledge, the modification unit may modify the comment by avoiding technical terms. Furthermore, the modification unit may modify the comment by selecting appropriate terms depending on the user's level of expertise. For example, if the user has technical expertise, the modification unit may modify the comment using technical terms. This allows the modification unit to adjust the use of technical terms depending on the user's level of expertise, thereby enabling more appropriate modification. Some or all of the above-described processing by the modification unit may be performed using AI, for example, or may be performed without using AI. For example, the modification unit may input the user's level of expertise into the generation AI, and the generation AI may adjust the use of technical terms.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] When analyzing comments, the analysis unit can improve the accuracy of the analysis by referring to the user's past browsing history. For example, the analysis unit can analyze the trends of content viewed by the user in the past and more accurately analyze the intent of the current comment. The analysis unit can also learn specific interests and concerns from the user's past browsing history and reflect them in the analysis. Furthermore, the analysis unit can adjust the comment analysis method by referring to feedback from the user on content viewed in the past. In this way, the analysis unit can improve the accuracy of the analysis by referring to the user's past browsing history.

[0055] When detecting comments, the detection unit can improve detection accuracy by taking into account the user's social media activity history. For example, the detection unit can reflect expressions frequently used by the user on social media in the analysis. The detection unit can also analyze the intent of the comment by referring to the user's social media activity. Furthermore, the detection unit can detect comments by taking into account the user's friendships on social media. This allows the detection unit to preferentially detect related comments by analyzing the user's social media activity.

[0056] The modification unit can customize the modification method by reflecting the user's past feedback when modifying a comment. For example, the modification unit can adjust the modification method based on feedback provided by the user in the past. The modification unit can also improve the accuracy of the modification by taking into account problems pointed out by the user in the past. Furthermore, the modification unit can learn specific modification patterns from the user's past feedback and reflect them in the modification. In this way, the modification unit can customize the modification method by reflecting the user's past feedback.

[0057] When analyzing comments, the analysis unit can take into account the user's geographical location information. For example, if the user is in a specific region, the analysis unit can take into account the culture and customs of that region in its analysis. Also, if the user is traveling, the analysis unit can take into account the language and culture of the destination in its analysis. Furthermore, if the user is participating in a specific event, the analysis unit can take into account information related to the event in its analysis. In this way, the analysis unit can improve the accuracy of its analysis by taking into account the user's geographical location information.

[0058] When detecting slander, the detection unit can weight the detection based on the frequency of comment posting. For example, it can prioritize detection of comments by users who post a large number of comments in a short period of time. The detection unit can also focus on detecting comments posted in a concentrated manner during a specific time period. Furthermore, the detection unit can weight and detect comments by users who have made slanderous comments in the past. In this way, the detection unit can weight detection based on the frequency of comment posting, thereby improving detection accuracy.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The analysis unit analyzes the comment. The analysis unit understands the content of the comment using, for example, natural language processing technology. Specifically, it uses morphological analysis to break down the words in the comment and grammatical analysis to analyze the structure of the sentence. It also uses semantic analysis to understand the meaning of the comment and analyze the intent of the comment by taking the context into account. Step 2: The detection unit detects defamatory comments from the comments analyzed by the analysis unit. The detection unit detects defamatory comments by taking into account the tone and context of the comments. Specifically, it detects offensive tones and discriminatory language, and identifies the intent behind the defamatory comments by taking into account the context before and after the comments. Step 3: The modification unit changes the abusive content detected by the detection unit to appropriate expressions. The modification unit changes the expression to a natural one without losing the overall meaning of the comment. Specifically, the modification unit changes the abusive content to a kinder, more harmless expression using grammatically correct expressions and everyday phrases. The modification unit also takes into account the tone and context of the comment, changing it to a more friendly tone and making it more natural in context.

[0061] (Example 2) An AI system according to an embodiment of the present invention is a system for preventing content creators from suffering from slander. This system analyzes comments posted in a comment section, detects slanderous content, and naturally changes the content to a kinder, more harmless expression. This allows content creators to protect themselves from slander while leaving the comment section intact. This allows content creators to continue their activities without worrying about slander. It also enables the comment section to function as a place for healthy communication. For example, the AI ​​system analyzes comments posted in a comment section. For example, the AI ​​system understands the content of the comments using natural language processing technology. Next, the AI ​​system detects slanderous content. For example, the AI ​​system identifies parts of the comments that are slanderous and changes those parts to a kinder, more harmless expression. This allows the AI ​​system to protect content creators from slander while leaving the comment section intact. Furthermore, the AI ​​system not only detects abusive content but also takes into account the tone and context of the comment when making changes. This allows the comment to be changed to a more natural expression without losing its overall meaning. For example, the AI ​​system could change a comment such as "Your video is boring" to "Your video has room for improvement, but keep up the good work." This reduces the mental burden on content creators and allows them to provide better content.

[0062] The AI ​​system according to the embodiment includes an analysis unit, a detection unit, and a modification unit. The analysis unit analyzes comments. The analysis unit understands the content of the comments using, for example, natural language processing technology. For example, the analysis unit can break down words in the comments using morphological analysis and analyze sentence structure using grammatical analysis. The analysis unit can also understand the meaning of the comments using semantic analysis. For example, the analysis unit can analyze the intention of the comments by taking into account the context of the comments. The detection unit detects defamation from the comments analyzed by the analysis unit. The detection unit detects defamation by taking into account, for example, the tone and context of the comments. For example, the detection unit can detect an offensive tone or discriminatory language. The detection unit can also detect the intent of defamation by taking into account the context before and after the comment. For example, the detection unit can analyze the relevance of the comments and identify the intent of defamation. The modification unit changes the defamatory content detected by the detection unit to an appropriate expression. The modification unit, for example, modifies the comment to a more natural expression without compromising the overall meaning. For example, the modification unit can modify slanderous content to a more gentle, harmless expression by using grammatically correct expressions and everyday phrases. The modification unit can also modify the comment by taking into consideration the tone and context of the comment. For example, the modification unit can change the tone of the comment to a more friendly one and modify the expression to a more natural one by taking the context into consideration. This allows the AI ​​system according to the embodiment to protect content creators from slander while leaving the comment section intact. This allows content creators to continue their activities with peace of mind, without suffering from slander. Furthermore, the comment section can function as a place for healthy communication.

[0063] The analysis unit can understand the content of the comment using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit can break down the words of the comment using morphological analysis and analyze the structure of the sentence using grammatical analysis. The analysis unit can also understand the meaning of the comment using semantic analysis. For example, the analysis unit can analyze the intention of the comment by taking into account the context of the comment. This allows the analysis unit to accurately understand the content of the comment. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the comment to a generation AI and have the generation AI analyze the content of the comment.

[0064] The detection unit can detect slander based on the tone or context of a comment. For example, the detection unit can analyze the tone of a comment to detect an offensive tone or discriminatory language. The detection unit can also analyze the context of a comment to detect a slanderous intent. For example, the detection unit can identify a slanderous intent by considering the context before and after the comment. Furthermore, the detection unit can analyze the relevance of comments to detect a slanderous intent. For example, when multiple comments are posted in succession, the detection unit can detect slander by considering the relevance of those comments. As a result, the detection unit can improve the accuracy of detecting slander by considering the tone and context of the comments. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the tone and context of a comment into a generation AI, which can then detect slander.

[0065] The modification unit can modify the comment to a more natural expression without losing the overall meaning. For example, the modification unit can modify the abusive content to a more gentle, non-offensive expression by using grammatically correct expressions and everyday phrases. The modification unit can also modify the comment by taking into account the tone and context of the comment. For example, the modification unit can change the tone of the comment to a more friendly one and modify the comment to a more natural expression by taking the context into account. Furthermore, the modification unit can modify the abusive content to a more gentle one while maintaining the overall meaning of the comment. For example, the modification unit can modify a comment such as "Your videos are boring" to a comment such as "Your videos have room for improvement, but please keep up the good work." In this way, the modification unit can modify the abusive content to a more gentle one while maintaining the overall meaning of the comment. Some or all of the above-described processing by the modification unit may be performed using, for example, AI, or may be performed without AI. For example, the modification unit can input the abusive content into a generation AI, which then modifies the content to a more gentle, non-offensive one.

[0066] The modification unit can change the content of defamatory comments to appropriate expressions. For example, the modification unit can change the content of defamatory comments to gentler, more harmless expressions using grammatically correct expressions and everyday phrases. For example, the modification unit can change a comment such as "You should disappear" to "I don't agree with your opinion, but other perspectives are important." The modification unit can also make changes taking into account the tone and context of the comment. For example, the modification unit can change the tone of the comment to a more friendly one and change the expression to a more natural one taking the context into account. In this way, the modification unit can protect content creators by changing the content of defamatory comments to a gentler one. Some or all of the above-described processing by the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the content of defamatory comments into a generation AI, which then changes the content to a gentler, more harmless expression.

[0067] The modification unit can modify the comment based on its tone or context. For example, the modification unit can change the comment's tone to a more friendly one and consider the context to modify the comment to a more natural expression. For example, the modification unit can change a comment such as "Your video is boring" to "Your video has room for improvement, but please keep up the good work." The modification unit can also modify abusive comments to a more gentle one while preserving the overall meaning of the comment. For example, the modification unit can change a comment such as "You should just disappear" to "I don't agree with your opinion, but other perspectives are important." In this way, the modification unit can modify the comment to a more natural expression by considering the tone and context of the comment. Some or all of the above-described processing by the modification unit may be performed using, or without, AI. For example, the modification unit can input the tone and context of the comment into a generation AI, which can then modify the comment to a more natural expression.

[0068] The analysis unit can estimate the user's emotions and adjust the comment analysis method based on the estimated user's emotions. The analysis unit can use, for example, facial expression analysis or text analysis to estimate the user's emotions. For example, the analysis unit can capture the user's facial expressions with a camera and estimate the emotions using an facial expression analysis algorithm. The analysis unit can also perform text analysis of the user's comments to estimate the emotions. For example, the analysis unit can analyze emotional expressions in the comments to estimate the user's emotions. Next, the analysis unit adjusts the comment analysis method based on the estimated user's emotions. For example, if the user is feeling angry, the analysis unit can analyze the comments by emphasizing their aggressiveness. If the user is feeling sad, the analysis unit can analyze the comments by emphasizing their emotional aspects. Furthermore, if the user is feeling happy, the analysis unit can analyze the comments by emphasizing their positive elements. This allows the analysis unit to adjust the comment analysis method according to the user's emotions, enabling more appropriate analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's emotions into the generation AI, which can then adjust how the comment is analyzed.

[0069] When analyzing comments, the analysis unit can improve the accuracy of the analysis by referring to the user's past comment history. For example, the analysis unit can analyze the trends of comments posted by the user in the past and analyze the intent of the current comment more accurately. The analysis unit can also learn specific expressions and phrases from the user's past comment history and reflect them in the analysis. Furthermore, the analysis unit can adjust the comment analysis method by referring to feedback the user has received in the past. For example, the analysis unit can analyze the trends of comments posted by the user in the past and analyze the intent of the current comment more accurately. In this way, the analysis unit can improve the accuracy of the analysis by referring to the user's past comment history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past comment history into a generation AI and use the generation AI to improve the analysis accuracy.

[0070] When analyzing comments, the analysis unit can take into account the time period and frequency of comment posting. For example, the analysis unit can analyze comments posted late at night by determining that they have a strong emotional element. The analysis unit can also analyze comments posted in rapid succession by determining that they may be spam. Furthermore, the analysis unit can analyze comments posted in a concentrated period of time by taking into account trends and topicality. For example, the analysis unit can analyze comments posted late at night by determining that they have a strong emotional element. In this way, the analysis unit improves analysis accuracy by taking into account the time period and frequency of comment posting. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time period and frequency of comment posting into a generation AI, and have the generation AI perform the analysis.

[0071] When analyzing comments, the analysis unit can take into account the language of the comment and regional expressions. The analysis unit can, for example, take into account slang and dialects used in a specific region during analysis. The analysis unit can also perform multilingual analysis and detect slander in different languages. Furthermore, the analysis unit can accurately analyze the intent of the comment by taking into account regional culture and customs. For example, the analysis unit can take into account slang and dialects used in a specific region during analysis. This improves the analysis accuracy by taking into account the language of the comment and regional expressions. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the language of the comment and regional expressions into a generation AI, which can then perform the analysis.

[0072] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user's emotions. The analysis unit can use, for example, facial expression analysis or text analysis to estimate the user's emotions. For example, the analysis unit can capture the user's facial expressions with a camera and estimate the emotions using an facial expression analysis algorithm. The analysis unit can also perform text analysis of the user's comments to estimate the emotions. For example, the analysis unit can analyze emotional expressions in the comments to estimate the user's emotions. Next, the analysis unit adjusts the display method of the analysis results based on the estimated user's emotions. For example, if the user is feeling angry, the analysis unit can display the analysis results calmly. If the user is feeling sad, the analysis unit can display the analysis results gently. Furthermore, if the user is feeling happy, the analysis unit can display the analysis results brightly. In this way, the analysis unit can adjust the display method of the analysis results according to the user's emotions, thereby enabling more appropriate display. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's emotions into the generation AI, which can then adjust how the analysis results are displayed.

[0073] When analyzing comments, the analysis unit can take into account the user's geographical location information. For example, if the user is in a specific region, the analysis unit can take into account the culture and customs of that region when analyzing. Furthermore, if the user is traveling, the analysis unit can take into account the language and culture of the destination when analyzing. Furthermore, if the user is participating in a specific event, the analysis unit can take into account information related to the event when analyzing. For example, if the user is in a specific region, the analysis unit can take into account the culture and customs of that region when analyzing. This allows the analysis unit to improve analysis accuracy by taking into account the user's geographical location information. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's geographical location information into a generation AI and have the generation AI perform the analysis.

[0074] When analyzing comments, the analysis unit can analyze the user's social media activity and prioritize analysis of related comments. The analysis unit can, for example, reflect expressions frequently used by the user on social media in the analysis. The analysis unit can also analyze the intent of the comment by referring to the user's social media activity. Furthermore, the analysis unit can analyze comments taking into account the user's friendships on social media. For example, the analysis unit can reflect expressions frequently used by the user on social media in the analysis. This allows the analysis unit to analyze the user's social media activity and prioritize analysis of related comments. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or without AI. For example, the analysis unit can input the user's social media activity into a generation AI and have the generation AI perform the analysis.

[0075] When analyzing comments, the analysis unit can customize the analysis method by reflecting the user's past feedback. The analysis unit can, for example, adjust the analysis method based on feedback provided by the user in the past. The analysis unit can also improve the analysis accuracy by taking into account problems pointed out by the user in the past. Furthermore, the analysis unit can learn specific analysis patterns from the user's past feedback and reflect them in the analysis. For example, the analysis unit can adjust the analysis method based on feedback provided by the user in the past. In this way, the analysis unit can customize the analysis method by reflecting the user's past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past feedback into a generation AI and have the generation AI customize the analysis method.

[0076] The detection unit can estimate the user's emotions and adjust the detection criteria for slander based on the estimated user's emotions. The detection unit can use, for example, facial expression analysis or text analysis to estimate the user's emotions. For example, the detection unit can capture the user's facial expression with a camera and estimate the emotion using an facial expression analysis algorithm. The detection unit can also perform text analysis of the user's comments to estimate the emotion. For example, the detection unit can analyze emotional expressions in the comments to estimate the user's emotions. Next, the detection unit adjusts the detection criteria for slander based on the estimated user's emotions. For example, if the user is feeling angry, the detection unit can tighten the detection criteria for slander. Furthermore, if the user is feeling sad, the detection unit can focus on emotional expressions when detecting slander. Furthermore, if the user is feeling happy, the detection unit can focus on positive expressions when detecting slander. In this way, the detection unit can adjust the detection criteria for slander based on the user's emotions, thereby improving detection accuracy. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit may input the user's emotions into the generation AI, and the generation AI may adjust the detection criteria for slander.

[0077] The detection unit can improve detection accuracy when detecting slander by taking into account the interrelationships between comments. For example, when multiple comments are posted in succession, the detection unit can detect them by taking into account the relevance of those comments. The detection unit can also analyze the reply relationships between comments to detect slanderous intent. Furthermore, the detection unit can analyze the entire comment exchange and understand the context of the slander to detect it. For example, when multiple comments are posted in succession, the detection unit can detect them by taking into account the relevance of those comments. As a result, the detection unit improves the detection accuracy of slander by taking into account the interrelationships between comments. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the interrelationships between comments into a generation AI, which can then detect slander.

[0078] When detecting slander, the detection unit can perform the detection by taking into account attribute information of the comment poster. For example, if the comment poster has a history of making slanderous comments in the past, the detection unit can tighten the detection criteria. The detection unit can also detect the slanderous intent by taking into account the age and gender of the comment poster. Furthermore, the detection unit can detect slander by referring to the comment poster's social media activity history. For example, the detection unit can tighten the detection criteria if the comment poster has a history of making slanderous comments in the past. As a result, the detection unit improves the accuracy of detecting slander by taking into account the attribute information of the comment poster. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input attribute information of the comment poster into a generation AI, and the generation AI can detect slander.

[0079] When detecting slander, the detection unit can weight the detection based on the frequency of comment posting. For example, the detection unit can prioritize detection of comments by users who post a large number of comments in a short period of time. The detection unit can also prioritize detection of comments posted in a concentrated manner during a specific time period. Furthermore, the detection unit can weight and detect comments by users who have made slanderous remarks in the past. For example, the detection unit can prioritize detection of comments by users who post a large number of comments in a short period of time. This allows the detection unit to weight the detection based on the frequency of comment posting, thereby improving detection accuracy. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the frequency of comment posting into a generation AI, and the generation AI can detect slander.

[0080] The detection unit can estimate the user's emotion and adjust the display method of the detection result based on the estimated user's emotion. The detection unit can use, for example, facial expression analysis or text analysis to estimate the user's emotion. For example, the detection unit can capture the user's facial expression with a camera and estimate the emotion using a facial expression analysis algorithm. The detection unit can also perform text analysis of the user's comments to estimate the emotion. For example, the detection unit can analyze emotional expressions in the comments to estimate the user's emotion. Next, the detection unit adjusts the display method of the detection result based on the estimated user's emotion. For example, if the user is feeling angry, the detection unit can display the detection result calmly. If the user is feeling sad, the detection unit can display the detection result gently. Furthermore, if the user is feeling happy, the detection unit can display the detection result brightly. In this way, the detection unit can adjust the display method of the detection result according to the user's emotion, thereby enabling a more appropriate display. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the user's emotions into the generation AI, which can then adjust how the detection results are displayed.

[0081] When detecting defamation, the detection unit can perform the detection by taking into account the geographical distribution of comments. For example, the detection unit can focus on comments posted in a concentrated manner from a specific region. The detection unit can also analyze comments posted from geographically distant locations to detect defamation. Furthermore, the detection unit can detect defamation by taking into account expressions and slang specific to the region. For example, the detection unit can focus on comments posted in a concentrated manner from a specific region. As a result, the detection unit can improve the accuracy of detecting defamation by taking the geographical distribution of comments into account. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the geographical distribution of comments into a generation AI, and the generation AI can detect defamation.

[0082] When detecting defamation, the detection unit can improve detection accuracy by referring to literature related to the comment. For example, if the content of the comment matches past defamation cases, the detection unit can tighten detection standards. The detection unit can also detect defamatory intent by referring to related academic papers and reports. Furthermore, if the content of the comment is related to a specific topic, the detection unit can detect defamation by referring to literature related to the topic. For example, if the content of the comment matches past defamation cases, the detection unit can tighten detection standards. As a result, the detection unit can improve the detection accuracy of defamation by referring to literature related to the comment. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input literature related to the comment into a generation AI, which can then detect defamation.

[0083] The detection unit can detect slander by taking into account the market value of the comment. For example, the detection unit can prioritize detecting comments with high market value. Furthermore, if the content of a comment is related to a specific product or service, the detection unit can also detect the comment by taking into account its market value. Furthermore, if the comment poster is an influential person, the detection unit can also prioritize detecting the comment. For example, the detection unit can prioritize detecting comments with high market value. As a result, the detection unit can improve the accuracy of detecting slander by taking the market value of the comment into account. Some or all of the above-mentioned processing in the detection unit can be performed using, for example, AI, or without AI. For example, the detection unit can input the market value of the comment into a generation AI, and the generation AI can detect slander.

[0084] The modification unit can estimate the user's emotion and adjust the expression method to be changed based on the estimated user's emotion. The modification unit can use, for example, facial expression analysis or text analysis to estimate the user's emotion. For example, the modification unit can capture the user's facial expression with a camera and estimate the emotion using an expression analysis algorithm. The modification unit can also perform text analysis of the user's comments to estimate the emotion. For example, the modification unit can analyze emotional expressions in the comments to estimate the user's emotion. Next, the modification unit adjusts the expression method to be changed based on the estimated user's emotion. For example, if the user is feeling angry, the modification unit can change the expression to a calm and neutral expression. If the user is feeling sad, the modification unit can change the expression to a gentle and encouraging expression. Furthermore, if the user is feeling happy, the modification unit can change the expression to a positive expression. This allows the modification unit to adjust the expression method according to the user's emotion, thereby enabling more appropriate modification. Some or all of the above-mentioned processing by the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the user's emotions into the generation AI and adjust the expression method to be modified by the generation AI.

[0085] When changing a comment, the modification unit can adjust the level of detail of the change based on the importance of the comment. For example, the modification unit can change a comment with high importance to be more detailed. The modification unit can also change a comment with low importance to be more concise. Furthermore, the modification unit can determine the priority of the change according to the importance of the comment. For example, the modification unit can change a comment with high importance to be more detailed. As a result, the modification unit can adjust the level of detail of the change based on the importance of the comment, thereby enabling more appropriate changes. Some or all of the above-mentioned processing in the modification unit may be performed using, or without, AI, for example. For example, the modification unit can input the importance of the comment to a generation AI, and the generation AI can adjust the level of detail of the change.

[0086] When modifying a comment, the modification unit can apply different modification algorithms depending on the category of the comment. For example, the modification unit can modify comments related to politics by applying a specific algorithm. Furthermore, the modification unit can modify comments related to entertainment by applying a different algorithm. Furthermore, the modification unit can modify comments related to sports by applying yet another algorithm. For example, the modification unit can modify comments related to politics by applying a specific algorithm. In this way, the modification unit can apply different modification algorithms depending on the category of the comment, thereby enabling more appropriate modification. Some or all of the above-mentioned processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the category of the comment into a generation AI and apply different modification algorithms using the generation AI.

[0087] When changing a comment, the modification unit can improve the accuracy of the modification by referring to the results of past modifications made by the user. For example, the modification unit can make current modifications based on the results of modifications made by the user in the past. The modification unit can also learn specific patterns from the user's past modification history and reflect them in the modifications. Furthermore, the modification unit can improve the accuracy of the modifications by referring to feedback provided by the user in the past. For example, the modification unit can make current modifications based on the results of modifications made by the user in the past. In this way, the modification unit improves the accuracy of the modifications by referring to the results of past modifications made by the user. Some or all of the above-described processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the results of past modifications made by the user into a generation AI, and the generation AI can improve the accuracy of the modifications.

[0088] The modification unit can estimate the user's emotions and adjust the length of the comment to be modified based on the estimated user's emotions. The modification unit can use, for example, facial expression analysis or text analysis to estimate the user's emotions. For example, the modification unit can capture the user's facial expressions with a camera and estimate the emotions using an facial expression analysis algorithm. The modification unit can also perform text analysis of the user's comments to estimate the emotions. For example, the modification unit can analyze emotional expressions in the comments to estimate the user's emotions. Next, the modification unit adjusts the length of the comment to be modified based on the estimated user's emotions. For example, if the user is feeling angry, the modification unit can modify the comment to a short, to-the-point comment. If the user is feeling sad, the modification unit can modify the comment to a longer, gentle, encouraging comment. Furthermore, if the user is feeling happy, the modification unit can modify the comment to an appropriate length that includes positive elements. This allows the modification unit to adjust the length of the comment according to the user's emotions, thereby enabling more appropriate modification. Some or all of the above-described processing by the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the user's emotions into the generation AI and adjust the length of the comment to be modified by the generation AI.

[0089] When modifying a comment, the modification unit can determine the priority of the modification based on the time the comment was posted. For example, the modification unit can prioritize modifying the most recent comment. The modification unit can also prioritize modifying comments related to a specific event or topic. Furthermore, the modification unit can determine the priority of the modification based on the importance of past comments as well. For example, the modification unit can prioritize modifying the most recent comment. This allows the modification unit to determine the priority of the modification based on the time the comment was posted, thereby enabling more appropriate modifications. Some or all of the above-described processing by the modification unit may be performed using AI, for example, or may be performed without using AI. For example, the modification unit can input the time the comment was posted to a generation AI, and the generation AI can determine the priority of the modification.

[0090] When modifying comments, the modification unit can adjust the order of modification based on the relevance of the comments. For example, the modification unit can prioritize modifying highly relevant comments. Furthermore, if the content of a comment is related to a specific topic, the modification unit can also prioritize modifying comments related to the topic. Furthermore, the modification unit can prioritize modifying highly relevant comments by taking into account the entire comment exchange. For example, the modification unit can prioritize modifying highly relevant comments. This enables the modification unit to adjust the order of modification based on the relevance of the comments, thereby enabling more appropriate modification. Some or all of the above-described processing in the modification unit may be performed using AI, for example, or may be performed without using AI. For example, the modification unit can input the relevance of the comments to a generation AI and allow the generation AI to adjust the order of modification.

[0091] When modifying a comment, the modification unit may adjust the use of technical terms in the modification depending on the user's level of expertise. For example, if the user has technical expertise, the modification unit may modify the comment using technical terms. Furthermore, if the user has general knowledge, the modification unit may modify the comment by avoiding technical terms. Furthermore, the modification unit may modify the comment by selecting appropriate terms depending on the user's level of expertise. For example, if the user has technical expertise, the modification unit may modify the comment using technical terms. This allows the modification unit to adjust the use of technical terms depending on the user's level of expertise, thereby enabling more appropriate modification. Some or all of the above-described processing by the modification unit may be performed using AI, for example, or may be performed without using AI. For example, the modification unit may input the user's level of expertise into the generation AI, and the generation AI may adjust the use of technical terms. === Hard Collateral 1-1 === Each of the multiple elements including the above-described analysis unit, detection unit, and change unit may be realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit may be realized by the processor 46 of the smart device 14 and analyze comments. The detection unit may be realized by the specific processing unit 290 of the data processing device 12 and detect abusive content. The change unit may be realized by the control unit 46A of the smart device 14 and change the abusive content to a more gentle and harmless expression. The analysis unit may be realized by the specific processing unit 290 of the data processing device 12, and the detection unit and change unit may be realized by the control unit 46A of the smart device 14, for example. === Hard Collateral 1-2 === Each of the multiple elements including the above-described analysis unit, detection unit, and change unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes comments. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects abusive content. The change unit is realized, for example, by the control unit 46A of the smart glasses 214 and changes the abusive content to a kinder, less malicious expression. The analysis unit may be realized, for example, by the specific processing unit 290 of the data processing device 12, and the detection unit and change unit may be realized, for example, by the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, detection unit, and change unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 and analyzes comments. The detection unit is realized by the specific processing unit 290 of the data processing device 12 and detects abusive content. The change unit is realized by the control unit 46A of the headset type terminal 314 and changes the abusive content to a kinder, less malicious expression. The analysis unit may be realized, for example, by the specific processing unit 290 of the data processing device 12, and the detection unit and change unit may be realized, for example, by the control unit 46A of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, detection unit, and change unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes comments. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects abusive content. The change unit is realized, for example, by the control unit 46A of the robot 414 and changes the abusive content to a kinder, less malicious expression. The analysis unit may be realized, for example, by the specific processing unit 290 of the data processing device 12, and the detection unit and change unit may be realized, for example, by the control unit 46A of the robot 414.

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

[0093] When analyzing comments, the analysis unit can improve the accuracy of the analysis by referring to the user's past browsing history. For example, the analysis unit can analyze the trends of content viewed by the user in the past and more accurately analyze the intent of the current comment. The analysis unit can also learn specific interests and concerns from the user's past browsing history and reflect them in the analysis. Furthermore, the analysis unit can adjust the comment analysis method by referring to feedback from the user on content viewed in the past. In this way, the analysis unit can improve the accuracy of the analysis by referring to the user's past browsing history.

[0094] When detecting comments, the detection unit can improve detection accuracy by taking into account the user's social media activity history. For example, the detection unit can reflect expressions frequently used by the user on social media in the analysis. The detection unit can also analyze the intent of the comment by referring to the user's social media activity. Furthermore, the detection unit can detect comments by taking into account the user's friendships on social media. This allows the detection unit to preferentially detect related comments by analyzing the user's social media activity.

[0095] The modification unit can customize the modification method by reflecting the user's past feedback when modifying a comment. For example, the modification unit can adjust the modification method based on feedback provided by the user in the past. The modification unit can also improve the accuracy of the modification by taking into account problems pointed out by the user in the past. Furthermore, the modification unit can learn specific modification patterns from the user's past feedback and reflect them in the modification. In this way, the modification unit can customize the modification method by reflecting the user's past feedback.

[0096] When analyzing comments, the analysis unit can take into account the user's geographical location information. For example, if the user is in a specific region, the analysis unit can take into account the culture and customs of that region in its analysis. Also, if the user is traveling, the analysis unit can take into account the language and culture of the destination in its analysis. Furthermore, if the user is participating in a specific event, the analysis unit can take into account information related to the event in its analysis. In this way, the analysis unit can improve the accuracy of its analysis by taking into account the user's geographical location information.

[0097] When detecting slander, the detection unit can weight the detection based on the frequency of comment posting. For example, it can prioritize detection of comments by users who post a large number of comments in a short period of time. The detection unit can also focus on detecting comments posted in a concentrated manner during a specific time period. Furthermore, the detection unit can weight and detect comments by users who have made slanderous comments in the past. In this way, the detection unit can weight detection based on the frequency of comment posting, thereby improving detection accuracy.

[0098] The analysis unit can estimate the user's emotions and adjust the comment analysis method based on the estimated user's emotions. For example, the analysis unit can use facial expression analysis or text analysis to estimate the user's emotions. Next, the analysis unit adjusts the comment analysis method based on the estimated user's emotions. For example, if the user is feeling angry, the analysis unit can analyze the comments by emphasizing their aggressiveness. Furthermore, if the user is feeling sad, the analysis unit can analyze the comments by emphasizing their emotional aspects. Furthermore, if the user is feeling happy, the analysis unit can analyze the comments by emphasizing their positive elements. This allows the analysis unit to adjust the comment analysis method according to the user's emotions, enabling more appropriate analysis.

[0099] The detection unit can estimate the user's emotions and adjust the detection criteria for slander based on the estimated user's emotions. For example, the detection unit can use facial expression analysis or text analysis to estimate the user's emotions. Next, the detection unit adjusts the detection criteria for slander based on the estimated user's emotions. For example, if the user is feeling angry, the detection unit can tighten the detection criteria for slander. Furthermore, if the user is feeling sad, the detection unit can focus on emotional expressions when detecting slander. Furthermore, if the user is feeling happy, the detection unit can focus on positive expressions when detecting slander. In this way, the detection unit can adjust the detection criteria for slander according to the user's emotions, thereby improving detection accuracy.

[0100] The modification unit can estimate the user's emotion and adjust the expression method to be changed based on the estimated user's emotion. For example, the modification unit can use facial expression analysis or text analysis to estimate the user's emotion. Next, the modification unit adjusts the expression method to be changed based on the estimated user's emotion. For example, if the user is feeling angry, the modification unit can change the expression to a calm and neutral expression. Furthermore, if the user is feeling sad, the modification unit can change the expression to a gentle and encouraging expression. Furthermore, if the user is feeling happy, the modification unit can change the expression to a positive expression. In this way, the modification unit can adjust the expression method according to the user's emotion, thereby enabling more appropriate changes.

[0101] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user's emotions. For example, the analysis unit can use facial expression analysis or text analysis to estimate the user's emotions. Next, the analysis unit adjusts the display method of the analysis results based on the estimated user's emotions. For example, if the user is feeling angry, the analysis unit can display the analysis results calmly. Furthermore, if the user is feeling sad, the analysis unit can display the analysis results gently. Furthermore, if the user is feeling happy, the analysis unit can display the analysis results brightly. In this way, the analysis unit can adjust the display method of the analysis results according to the user's emotions, thereby enabling more appropriate display.

[0102] The modification unit can estimate the user's emotion and adjust the length of the comment to be modified based on the estimated user's emotion. For example, the modification unit can use facial expression analysis or text analysis to estimate the user's emotion. Next, the modification unit adjusts the length of the comment to be modified based on the estimated user's emotion. For example, if the user is feeling angry, the modification unit can modify the comment to a short, to-the-point comment. If the user is feeling sad, the modification unit can modify the comment to a longer, gentle, encouraging comment. Furthermore, if the user is feeling happy, the modification unit can modify the comment to an appropriate length that includes positive elements. This allows the modification unit to adjust the length of the comment according to the user's emotion, thereby enabling more appropriate modification.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The analysis unit analyzes the comment. The analysis unit understands the content of the comment using, for example, natural language processing technology. Specifically, it uses morphological analysis to break down the words in the comment and grammatical analysis to analyze the structure of the sentence. It also uses semantic analysis to understand the meaning of the comment and analyze the intent of the comment by taking the context into account. Step 2: The detection unit detects defamatory comments from the comments analyzed by the analysis unit. The detection unit detects defamatory comments by taking into account the tone and context of the comments. Specifically, it detects offensive tones and discriminatory language, and identifies the intent behind the defamatory comments by taking into account the context before and after the comments. Step 3: The modification unit changes the abusive content detected by the detection unit to appropriate expressions. The modification unit changes the expression to a natural one without losing the overall meaning of the comment. Specifically, the modification unit changes the abusive content to a kinder, more harmless expression using grammatically correct expressions and everyday phrases. The modification unit also takes into account the tone and context of the comment, changing it to a more friendly tone and making it more natural in context.

[0105] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating 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.

[0106] 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 generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] 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.

[0108] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

[0110] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating 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.

[0122] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0123] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is 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.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

[0126] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0139] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

[0142] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0143] The data processing device 12 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the 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.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is 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.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] [Explanation of symbols]

[0177] 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. an analysis unit that analyzes comments; a detection unit that detects slander from the comments analyzed by the analysis unit; a change unit that changes the content of the slander detected by the detection unit to an appropriate expression. A system characterized by:

2. The analysis unit Understanding the content of comments using natural language processing technology 2. The system of claim 1.

3. The detection unit Detect abusive comments based on their tone or context 2. The system of claim 1.

4. The change unit Change the comment to a more natural expression without losing the overall meaning 2. The system of claim 1.

5. The change unit Change the defamatory content to appropriate language 2. The system of claim 1.

6. The change unit Make changes based on the tone or context of the comment 2. The system of claim 1.

7. The analysis unit Estimate user sentiment and adjust comment analysis methods based on the estimated user sentiment 2. The system of claim 1.

8. The analysis unit When analyzing comments, improve the accuracy of the analysis by referring to the user's past comment history.

2. The system of claim 1.

Images