system

Abstract

The system according to the embodiment aims to effectively remove negative comments on SNS and reduce the mental burden on users. [Solution] A system according to an embodiment includes a scanning unit, an analyzing unit, and a removing unit. The scanning unit scans comments on a social networking site. The analyzing unit analyzes the comments scanned by the scanning unit. The removing unit removes comments containing sarcasm or irony detected by the analyzing unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it is difficult to completely remove negative comments on social media, which can be a mental burden for users.

[0005] The system according to the embodiment aims to effectively remove negative comments on SNS and reduce the mental burden on users. [Means for solving the problem]

[0006] The system according to the embodiment includes a scanning unit, an analyzing unit, and a removing unit. The scanning unit scans comments on the social networking site. The analyzing unit analyzes the comments scanned by the scanning unit. The removing unit removes comments containing sarcasm or irony detected by the analyzing unit. [Effects of the Invention]

[0007] The system according to the embodiment can effectively remove negative comments on SNS and reduce the mental burden on users. [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 SNS comment filtering system according to an embodiment of the present invention uses a generation AI to scan SNS comments, detect sarcasm and sarcasm, and block them. In the SNS comment filtering system, the generation AI scans SNS comments by context and detects and blocks sarcasm and sarcasm. For example, the SNS comment filtering system scans comments by considering not only the content of the comment but also the context. This allows it to detect sarcasm and sarcasm that cannot be detected by a simple keyword filter. Next, the SNS comment filtering system analyzes the comments scanned by the generation AI and identifies comments that contain sarcasm and sarcasm. For example, it not only checks whether a specific keyword is included, but also analyzes the context in which the keyword is used. This allows it to detect sarcasm and sarcasm that cannot be detected by a simple keyword filter. Next, the SNS comment filtering system blocks detected comments before they are displayed to users. This allows users to use SNS without being distracted by negative comments. For example, if a comment containing sarcasm and sarcasm is detected, the comment is blocked and not displayed to users. This reduces SNS fatigue and allows users to use SNS more comfortably. This allows the SNS comment filtering system to allow users to use SNS without worrying about negative comments. For example, by blocking comments containing sarcasm or irony, users can use SNS without worrying about negative comments. In addition, by scanning comments by context, the generation AI can detect sarcasm and irony that cannot be detected by a simple keyword filter. This allows users to use SNS more comfortably.

[0029] An SNS comment filtering system according to an embodiment includes a scanning unit, an analysis unit, and a shutout unit. The scanning unit scans SNS comments. For example, the scanning unit uses a generation AI to scan comments by context. The scanning unit can also perform scanning while taking into account previous and subsequent comments and the poster's past comment history. For example, the scanning unit not only checks whether a specific keyword is included but also analyzes the context in which the keyword is used. The analysis unit analyzes the comments scanned by the scanning unit. For example, the analysis unit uses a generation AI to analyze comments and identify comments containing sarcasm or irony. The analysis unit can also analyze not only whether a specific keyword is included but also the context in which the keyword is used. For example, the analysis unit uses a generation AI to perform analysis while taking into account not only the content of the comment but also the context before and after the comment. The shutout unit shuts out comments containing sarcasm or irony detected by the analysis unit. For example, the shutout unit shuts out comments detected using the generation AI before they are displayed to the user. The shutout unit can also notify the user of the detected comments. For example, if a comment containing sarcasm or irony is detected, the shutout unit shuts out the comment without displaying it to the user. This allows the SNS comment filtering system according to the embodiment to allow users to use SNS without being bothered by negative comments. Some or all of the above-described processing in the scanning unit, analysis unit, and shutout unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the scanning unit inputs SNS comments to the generation AI, which then scans the comments. The analysis unit inputs the comments scanned by the scanning unit to the generation AI, which then analyzes the comments. The shutout unit inputs the comments detected by the analysis unit to the generation AI, which then shuts out the comments.

[0030] The scanning unit can perform a scan based on previous and following comments or the poster's past comment history. The scanning unit, for example, performs a scan taking into account previous and following comments. For example, the scanning unit can perform a scan by referring to comments immediately before and after, or comments within a certain period of time. The scanning unit can also perform a scan by considering the poster's past comment history. For example, the scanning unit can perform a scan by referring to comments within a certain period of time or comments on a specific topic. This improves the accuracy of the scan by taking into account previous and following comments and the poster's past comment history. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs previous and following comments and the poster's past comment history into the generation AI, and the generation AI performs the scan.

[0031] The shutout unit can notify the user of the detected comment. The shutout unit, for example, notifies the user of the detected comment. For example, the shutout unit can notify the user of the detected comment by email or an in-app notification. The shutout unit can also notify the user of the detected comment in real time. For example, the shutout unit immediately notifies the user of the detected comment. In this way, by notifying the user of the detected comment, the user can confirm the shutout comment. Some or all of the above-mentioned processing in the shutout unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the shutout unit inputs the detected comment into the generation AI, and the generation AI notifies the user.

[0032] The analysis unit can analyze not only whether a specific keyword is included but also the context in which the keyword is used. For example, the analysis unit can analyze not only whether a specific keyword is included but also the context in which the keyword is used. For example, the analysis unit can analyze the surrounding sentences, related topics, and the meanings of the words used. The analysis unit can also analyze not only whether a specific keyword is included but also the context in which the keyword is used. For example, the analysis unit can analyze the surrounding sentences and related topics to identify the context in which the keyword is used. In this way, by analyzing the context of the specific keyword, comments containing sarcasm or irony can be more accurately detected. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit inputs comments containing specific keywords into the generation AI, and the generation AI analyzes the context.

[0033] The scanning unit can improve the accuracy of the scan based on the past behavioral history of the comment poster. For example, the scanning unit improves the accuracy of the scan by referring to the past behavioral history of the comment poster. For example, if a poster has posted many negative comments in the past, the scanning unit prioritizes scanning of the poster's comments. Also, if a poster has frequently used a specific keyword in the past, the scanning unit can focus on scanning comments containing that keyword. Furthermore, the scanning unit can analyze the poster's past behavioral history to predict negative comments and improve the accuracy of the scan. In this way, negative comments can be detected more accurately by referring to the poster's past behavioral history. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs the poster's past behavioral history into the generation AI, which then improves the accuracy of the scan.

[0034] The scanning unit can adjust the scanning method based on the time or location of the comment posting. For example, the scanning unit adjusts the scanning method taking into account the time and location of the comment posting. For example, the scanning unit predicts that comments posted late at night will have a high percentage of negative content and improves the accuracy of the scan. The scanning unit can also scan comments posted from specific locations by taking into account slang and expressions specific to the region. Furthermore, the scanning unit can adjust the scanning algorithm according to the time of posting to improve accuracy. In this way, the accuracy of the scan is improved by taking into account the time and location of posting. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs data on the time and location of the comment posting into the generation AI, and the generation AI adjusts the scanning method.

[0035] The scanning unit can optimize the scanning algorithm based on the language or cultural background of the comment. For example, the scanning unit optimizes the scanning algorithm by taking into account the language and cultural background of the comment. For example, if the comment is posted in English, the scanning unit scans the comment taking into account slang and expressions specific to English. Also, if the comment is posted in Japanese, the scanning unit can apply an algorithm that detects sarcasm and sarcasm that are specific to Japanese. Furthermore, the scanning unit can optimize the algorithm that detects sarcasm and sarcasm in a specific culture by taking into account the cultural background of the comment. In this way, by taking the language and cultural background into account, comments containing sarcasm and sarcasm can be more accurately detected. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs data on the language and cultural background of the comment into the generation AI, and the generation AI optimizes the scanning algorithm.

[0036] The scanning unit can analyze the social media activity of the comment poster and prioritize scanning related comments. For example, the scanning unit analyzes the social media activity of the comment poster and prioritize scanning related comments. For example, if the poster has posted many negative comments on other social media platforms, the scanning unit prioritizes scanning the poster's comments. The scanning unit can also analyze the poster's social media activity and predict negative comments to improve the accuracy of the scan. Furthermore, if the poster has posted many comments on a particular topic, the scanning unit can prioritize scanning comments related to that topic. This allows for more accurate detection of negative comments by analyzing the poster's social media activity. Some or all of the above-described processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs data on the poster's social media activity into the generation AI, which then prioritizes scanning related comments.

[0037] The scanning unit can apply different scanning algorithms based on the content of the comments. For example, the scanning unit applies different scanning algorithms based on the content of the comments. For example, the scanning unit can apply a stricter scanning algorithm to comments containing negative keywords. The scanning unit can also apply a normal scanning algorithm to comments containing positive keywords. Furthermore, the scanning unit can apply a balanced scanning algorithm to comments containing neutral keywords. This improves the accuracy of the scan by adjusting the scanning algorithm according to the content of the comments. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs comment content data into the generation AI, and the generation AI applies different scanning algorithms.

[0038] The scanning unit can adjust the scanning method based on the length or format of the comment. For example, the scanning unit adjusts the scanning method according to the length and format of the comment. For example, the scanning unit applies a detailed scanning algorithm to long comments. The scanning unit can also apply a quick scanning algorithm to short comments. Furthermore, the scanning unit can apply a scanning algorithm suitable for a specific format (e.g., list format or bullet points) to comments. In this way, by adjusting the scanning method according to the length and format of the comment, the accuracy of the scan is improved. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs data on the length and format of the comment into the generation AI, and the generation AI adjusts the scanning method.

[0039] The analysis unit can improve the accuracy of the analysis based on the past commentary tendency of the comment poster. The analysis unit improves the accuracy of the analysis, for example, by referring to the past commentary tendency of the comment poster. For example, if the poster has posted many negative comments in the past, the analysis unit can focus on analyzing the poster's comments. Also, if the poster has frequently used a specific keyword in the past, the analysis unit can focus on analyzing comments containing that keyword. Furthermore, the analysis unit can analyze the poster's past commentary tendency and predict negative comments to improve the accuracy of the analysis. In this way, by referring to the poster's past commentary tendency, negative comments can be analyzed more accurately. Some or all of the above-mentioned processing in the analysis unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the analysis unit inputs data on the poster's past commentary tendency into the generation AI, which then improves the accuracy of the analysis.

[0040] The analysis unit can refer to related external data to gain a deeper understanding of the context of the comment. For example, the analysis unit can refer to related external data to gain a deeper understanding of the context of the comment. For example, the analysis unit can refer to related news articles to gain a deeper understanding of the context of the comment. The analysis unit can also refer to related social media posts to gain a deeper understanding of the context of the comment. Furthermore, the analysis unit can refer to related forum posts to gain a deeper understanding of the context of the comment. By referencing related external data, the context of the comment can be more deeply understood, improving the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit inputs related external data into the generation AI, which then understands the context of the comment.

[0041] The analysis unit can evaluate the emotional tone of the comments to improve the accuracy of detecting sarcasm and sarcasm. For example, the analysis unit evaluates the emotional tone of the comments to improve the accuracy of detecting sarcasm and sarcasm. For example, the analysis unit evaluates the emotional tone of the comments and focuses on analyzing comments with a negative tone. The analysis unit can also evaluate the emotional tone of the comments to identify comments containing sarcasm and sarcasm. Furthermore, the analysis unit can evaluate the emotional tone of the comments and exclude comments with a positive tone to improve the accuracy of the analysis. In this way, by evaluating the emotional tone of the comments, comments containing sarcasm and sarcasm can be more accurately detected. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit inputs data on the emotional tone of the comments into the generation AI, and the generation AI evaluates the emotional tone.

[0042] The analysis unit can improve the accuracy of the analysis based on the geographical information of the comment poster. The analysis unit, for example, improves the accuracy of the analysis by taking into account the geographical information of the comment poster. For example, the analysis unit takes into account the geographical information of the poster and reflects slang and expressions specific to the region in the analysis. The analysis unit can also take into account the geographical information of the poster and reflect a cultural background specific to the region in the analysis. Furthermore, the analysis unit can take into account the geographical information of the poster and reflect topics specific to the region in the analysis. In this way, by taking into account the geographical information of the poster, slang and expressions specific to the region are reflected in the analysis, improving the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the analysis unit inputs data on the poster's geographical information into the generation AI, and the generation AI improves the accuracy of the analysis.

[0043] The analysis unit can determine the priority of analysis by taking into account the relevance of the comments. The analysis unit, for example, evaluates the relevance of the comments and prioritizes the analysis of important comments. For example, the analysis unit evaluates the relevance of the comments and prioritizes the analysis of negative comments. The analysis unit can also evaluate the relevance of the comments and prioritize the analysis of positive comments, improving the accuracy of the analysis. In this way, by evaluating the relevance of the comments, important comments can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit inputs comment relevance data into the generation AI, and the generation AI determines the priority of analysis.

[0044] The analysis unit can apply different analysis algorithms based on the category of the comment. For example, the analysis unit applies different analysis algorithms depending on the category of the comment. For example, the analysis unit applies a stricter analysis algorithm to comments in a negative category. The analysis unit can also apply a normal analysis algorithm to comments in a positive category. Furthermore, the analysis unit can apply a balanced analysis algorithm to comments in a neutral category. In this way, the analysis accuracy is improved by adjusting the analysis algorithm depending on the category of the comment. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit inputs comment category data into the generation AI, and the generation AI applies different analysis algorithms.

[0045] The shutout unit can improve the accuracy of shutting out comments based on the past behavioral history of the comment poster. The shutout unit, for example, improves the accuracy of shutting out comments by referring to the past behavioral history of the comment poster. For example, if a poster has posted many negative comments in the past, the shutout unit will prioritize shutting out comments by that poster. Also, if a poster has frequently used a specific keyword in the past, the shutout unit can prioritize shutting out comments containing that keyword. Furthermore, the shutout unit can analyze the poster's past behavioral history and predict negative comments to improve the accuracy of shutting out comments. In this way, by referring to the poster's past behavioral history, negative comments can be shut out more accurately. Some or all of the above-described processing in the shutout unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the shutout unit inputs data on the poster's past behavioral history into the generation AI, which then improves the accuracy of shutting out comments.

[0046] The shut-out unit can apply different shut-out methods taking into account the content of the comment. For example, the shut-out unit applies different shut-out methods based on the content of the comment. For example, the shut-out unit applies a strict shut-out method to comments containing negative keywords. The shut-out unit can also apply a normal shut-out method to comments containing positive keywords. Furthermore, the shut-out unit can also apply a balanced shut-out method to comments containing neutral keywords. This improves the accuracy of shut-out by adjusting the shut-out method according to the content of the comment. Some or all of the above-mentioned processing in the shut-out unit may be performed using or without the generation AI. For example, the shut-out unit inputs comment content data into the generation AI, and the generation AI applies different shut-out methods.

[0047] The shutout unit can take into account the impact of a comment and determine the priority of shutting out based on its importance. The shutout unit, for example, evaluates the impact of a comment and prioritizes shutting out important comments. For example, the shutout unit quickly shuts out comments with high impact. The shutout unit can also apply a normal shutout method to comments with low impact. Furthermore, the shutout unit can evaluate the impact of a comment and determine the priority of shutting out based on its importance. In this way, important comments can be prioritized by evaluating the impact of a comment. Some or all of the above-described processing in the shutout unit may be performed using or without the generation AI. For example, the shutout unit inputs comment impact data into the generation AI, and the generation AI determines the priority of shutting out.

[0048] The shutout unit can prioritize shutting out related comments based on the social media activity of the comment poster. For example, the shutout unit analyzes the social media activity of the comment poster and prioritizes shutting out related comments. For example, if the poster has posted many negative comments on other social media platforms, the shutout unit prioritizes shutting out the poster's comments. The shutout unit can also analyze the poster's social media activity to predict negative comments and improve the accuracy of the shutout. Furthermore, if the poster has posted many comments on a specific topic, the shutout unit can prioritize shutting out comments related to that topic. This allows for more accurate shutout of negative comments by analyzing the poster's social media activity. Some or all of the above-described processing in the shutout unit may be performed using or without the generation AI. For example, the shutout unit inputs data on the poster's social media activity into the generation AI, which then prioritizes shutting out related comments.

[0049] The shutout unit can optimize the shutout algorithm based on the language or cultural background of the comment. The shutout unit, for example, optimizes the shutout algorithm by taking into account the language and cultural background of the comment. For example, if a comment is posted in English, the shutout unit takes into account slang and expressions specific to English and shuts out the comment. Also, if a comment is posted in Japanese, the shutout unit can apply an algorithm that detects sarcasm and sarcasm specific to Japanese. Furthermore, the shutout unit can optimize the algorithm that detects sarcasm and sarcasm in a specific culture by taking into account the cultural background of the comment. In this way, by taking the language and cultural background into consideration, comments containing sarcasm and sarcasm can be more accurately shut out. Some or all of the above-mentioned processing in the shutout unit may be performed using or without the generation AI. For example, the shutout unit inputs data on the language and cultural background of the comment into the generation AI, and the generation AI optimizes the shutout algorithm.

[0050] The shut-out unit can adjust the shut-out method based on the length or format of the comment. The shut-out unit adjusts the shut-out method according to, for example, the length or format of the comment. For example, the shut-out unit applies a detailed shut-out algorithm to long comments. The shut-out unit can also apply a quick shut-out algorithm to short comments. Furthermore, the shut-out unit can also apply a shut-out algorithm suitable for a specific format (e.g., list format or bullet points) of a comment. In this way, adjusting the shut-out method according to the length or format of the comment improves the accuracy of the shut-out. Some or all of the above-described processing in the shut-out unit may be performed using or without the generation AI. For example, the shut-out unit inputs data on the length and format of the comment into the generation AI, and the generation AI adjusts the shut-out method.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The SNS comment filtering system can further include a customization unit that customizes the filtering criteria based on the user's preferences. For example, if the user dislikes a particular keyword or phrase, the customization unit can preferentially block comments containing that keyword or phrase. Also, if the user likes comments on a particular topic, the customization unit can preferentially display comments related to that topic. Furthermore, the customization unit can automatically adjust the filtering criteria by referencing the history of comments that the user has previously filtered. This enables filtering according to the user's preferences, making SNS use more comfortable.

[0053] The SNS comment filtering system may further include a reliability evaluation unit that evaluates the reliability of the poster of a comment and adjusts the filtering criteria based on the reliability. For example, if a poster has posted many reliable comments in the past, the reliability evaluation unit may preferentially display the poster's comments. Also, if a poster has posted many negative comments in the past, the reliability evaluation unit may preferentially block the poster's comments. Furthermore, the reliability evaluation unit may evaluate the poster's reliability in real time and dynamically adjust the filtering criteria. This enables filtering according to the poster's reliability, resulting in the display of more reliable comments.

[0054] The SNS comment filtering system may further include a content evaluation unit that applies different filtering algorithms based on the content of the comment. For example, the content evaluation unit may apply a stricter filtering algorithm to comments containing negative keywords. The content evaluation unit may also apply a normal filtering algorithm to comments containing positive keywords. The content evaluation unit may also apply a balanced filtering algorithm to comments containing neutral keywords. This enables filtering according to the content of the comment, resulting in more accurate filtering.

[0055] The SNS comment filtering system can further include a behavioral history evaluation unit that adjusts filtering criteria based on the past behavioral history of the comment poster. For example, if a poster has posted many negative comments in the past, the behavioral history evaluation unit can prioritize blocking comments from that poster. Also, if a poster has frequently used a specific keyword in the past, the behavioral history evaluation unit can prioritize filtering comments containing that keyword. Furthermore, the behavioral history evaluation unit can analyze the poster's past behavioral history, predict negative comments, and adjust filtering criteria accordingly. This enables filtering based on the poster's past behavioral history, resulting in more accurate filtering.

[0056] The SNS comment filtering system can further include a time and location evaluation unit that adjusts filtering criteria based on the time and location of the comment posting. For example, the time and location evaluation unit predicts that comments posted late at night will contain more negative content and sets stricter filtering criteria. The time and location evaluation unit can also filter comments posted from specific locations by taking into account local slang and expressions. Furthermore, the time and location evaluation unit can adjust the filtering algorithm according to the time of posting to improve accuracy. This enables filtering based on the time and location of posting, resulting in more accurate filtering.

[0057] The SNS comment filtering system can further include a language and culture evaluation unit that optimizes the filtering algorithm based on the language and cultural background of the comment. For example, if the comment is posted in English, the language and culture evaluation unit may filter the comment taking into account slang and expressions specific to English. In addition, if the comment is posted in Japanese, the language and culture evaluation unit may apply an algorithm that detects sarcasm and irony specific to Japanese. Furthermore, the language and culture evaluation unit may optimize the algorithm that detects sarcasm and irony in a specific culture by taking into account the cultural background of the comment. This enables filtering based on language and cultural background, resulting in more accurate filtering.

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

[0059] Step 1: The scanning unit scans comments on social media. Using generative AI, the scanning unit scans comments by context, taking into account the comments before and after and the poster's past comment history. For example, it analyzes not only whether a specific keyword is included, but also the context in which that keyword is used. Step 2: The analysis unit analyzes the comments scanned by the scanning unit. The analysis unit uses generative AI to analyze the comments and identify comments that contain sarcasm or irony. The analysis unit can not only determine whether specific keywords are included, but also analyze the context in which those keywords are used. For example, the analysis takes into account not only the content of the comment, but also the context before and after it. Step 3: The removal unit removes comments containing sarcasm or irony detected by the analysis unit. The removal unit uses the generation AI to remove detected comments before they are displayed to the user. For example, if a comment containing sarcasm or irony is detected, the comment is removed without being displayed to the user.

[0060] (Example 2) An SNS comment filtering system according to an embodiment of the present invention uses a generation AI to scan SNS comments, detect sarcasm and sarcasm, and block them. In the SNS comment filtering system, the generation AI scans SNS comments by context and detects and blocks sarcasm and sarcasm. For example, the SNS comment filtering system scans comments by considering not only the content of the comment but also the context. This allows it to detect sarcasm and sarcasm that cannot be detected by a simple keyword filter. Next, the SNS comment filtering system analyzes the comments scanned by the generation AI and identifies comments that contain sarcasm and sarcasm. For example, it not only checks whether a specific keyword is included, but also analyzes the context in which the keyword is used. This allows it to detect sarcasm and sarcasm that cannot be detected by a simple keyword filter. Next, the SNS comment filtering system blocks detected comments before they are displayed to users. This allows users to use SNS without being distracted by negative comments. For example, if a comment containing sarcasm and sarcasm is detected, the comment is blocked and not displayed to users. This reduces SNS fatigue and allows users to use SNS more comfortably. This allows the SNS comment filtering system to allow users to use SNS without worrying about negative comments. For example, by blocking comments containing sarcasm or irony, users can use SNS without worrying about negative comments. In addition, by scanning comments by context, the generation AI can detect sarcasm and irony that cannot be detected by a simple keyword filter. This allows users to use SNS more comfortably.

[0061] An SNS comment filtering system according to an embodiment includes a scanning unit, an analysis unit, and a shutout unit. The scanning unit scans SNS comments. For example, the scanning unit uses a generation AI to scan comments by context. The scanning unit can also perform scanning while taking into account previous and subsequent comments and the poster's past comment history. For example, the scanning unit not only checks whether a specific keyword is included but also analyzes the context in which the keyword is used. The analysis unit analyzes the comments scanned by the scanning unit. For example, the analysis unit uses a generation AI to analyze comments and identify comments containing sarcasm or irony. The analysis unit can also analyze not only whether a specific keyword is included but also the context in which the keyword is used. For example, the analysis unit uses a generation AI to perform analysis while taking into account not only the content of the comment but also the context before and after the comment. The shutout unit shuts out comments containing sarcasm or irony detected by the analysis unit. For example, the shutout unit shuts out comments detected using the generation AI before they are displayed to the user. The shutout unit can also notify the user of the detected comments. For example, if a comment containing sarcasm or irony is detected, the shutout unit shuts out the comment without displaying it to the user. This allows the SNS comment filtering system according to the embodiment to allow users to use SNS without being bothered by negative comments. Some or all of the above-described processing in the scanning unit, analysis unit, and shutout unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the scanning unit inputs SNS comments to the generation AI, which then scans the comments. The analysis unit inputs the comments scanned by the scanning unit to the generation AI, which then analyzes the comments. The shutout unit inputs the comments detected by the analysis unit to the generation AI, which then shuts out the comments.

[0062] The scanning unit can perform a scan based on previous and following comments or the poster's past comment history. The scanning unit, for example, performs a scan taking into account previous and following comments. For example, the scanning unit can perform a scan by referring to comments immediately before and after, or comments within a certain period of time. The scanning unit can also perform a scan by considering the poster's past comment history. For example, the scanning unit can perform a scan by referring to comments within a certain period of time or comments on a specific topic. This improves the accuracy of the scan by taking into account previous and following comments and the poster's past comment history. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs previous and following comments and the poster's past comment history into the generation AI, and the generation AI performs the scan.

[0063] The shutout unit can notify the user of the detected comment. The shutout unit, for example, notifies the user of the detected comment. For example, the shutout unit can notify the user of the detected comment by email or an in-app notification. The shutout unit can also notify the user of the detected comment in real time. For example, the shutout unit immediately notifies the user of the detected comment. In this way, by notifying the user of the detected comment, the user can confirm the shutout comment. Some or all of the above-mentioned processing in the shutout unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the shutout unit inputs the detected comment into the generation AI, and the generation AI notifies the user.

[0064] The analysis unit can analyze not only whether a specific keyword is included but also the context in which the keyword is used. For example, the analysis unit can analyze not only whether a specific keyword is included but also the context in which the keyword is used. For example, the analysis unit can analyze the surrounding sentences, related topics, and the meanings of the words used. The analysis unit can also analyze not only whether a specific keyword is included but also the context in which the keyword is used. For example, the analysis unit can analyze the surrounding sentences and related topics to identify the context in which the keyword is used. In this way, by analyzing the context of the specific keyword, comments containing sarcasm or irony can be more accurately detected. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit inputs comments containing specific keywords into the generation AI, and the generation AI analyzes the context.

[0065] The scanning unit can estimate the user's emotions and adjust the frequency of scanning based on the estimated user emotions. For example, the scanning unit estimates the user's emotions and adjusts the frequency of scanning based on the estimated user emotions. For example, if the user is feeling stressed, the scanning unit can increase the frequency of scanning to quickly detect negative comments. Also, if the user is relaxed, the scanning unit can decrease the frequency of scanning to reduce the load on the system. Furthermore, if the user is in a hurry, the scanning unit can increase the frequency of scanning to quickly detect negative comments. In this way, negative comments can be quickly detected by adjusting the frequency of scanning according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the scanning unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the scanning unit inputs the user's emotion data into the generation AI, which then estimates the emotion and adjusts the frequency of scanning.

[0066] The scanning unit can improve the accuracy of the scan based on the past behavioral history of the comment poster. For example, the scanning unit improves the accuracy of the scan by referring to the past behavioral history of the comment poster. For example, if a poster has posted many negative comments in the past, the scanning unit prioritizes scanning of the poster's comments. Also, if a poster has frequently used a specific keyword in the past, the scanning unit can focus on scanning comments containing that keyword. Furthermore, the scanning unit can analyze the poster's past behavioral history to predict negative comments and improve the accuracy of the scan. In this way, negative comments can be detected more accurately by referring to the poster's past behavioral history. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs the poster's past behavioral history into the generation AI, which then improves the accuracy of the scan.

[0067] The scanning unit can adjust the scanning method based on the time or location of the comment posting. For example, the scanning unit adjusts the scanning method taking into account the time and location of the comment posting. For example, the scanning unit predicts that comments posted late at night will have a high percentage of negative content and improves the accuracy of the scan. The scanning unit can also scan comments posted from specific locations by taking into account slang and expressions specific to the region. Furthermore, the scanning unit can adjust the scanning algorithm according to the time of posting to improve accuracy. In this way, the accuracy of the scan is improved by taking into account the time and location of posting. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs data on the time and location of the comment posting into the generation AI, and the generation AI adjusts the scanning method.

[0068] The scanning unit can optimize the scanning algorithm based on the language or cultural background of the comment. For example, the scanning unit optimizes the scanning algorithm by taking into account the language and cultural background of the comment. For example, if the comment is posted in English, the scanning unit scans the comment taking into account slang and expressions specific to English. Also, if the comment is posted in Japanese, the scanning unit can apply an algorithm that detects sarcasm and sarcasm that are specific to Japanese. Furthermore, the scanning unit can optimize the algorithm that detects sarcasm and sarcasm in a specific culture by taking into account the cultural background of the comment. In this way, by taking the language and cultural background into account, comments containing sarcasm and sarcasm can be more accurately detected. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs data on the language and cultural background of the comment into the generation AI, and the generation AI optimizes the scanning algorithm.

[0069] The scanning unit can estimate the user's emotions and determine the priority of comments to scan based on the estimated user emotions. For example, the scanning unit estimates the user's emotions and determines the priority of comments to scan based on the estimated user emotions. For example, if the user is stressed, the scanning unit prioritizes scanning negative comments. Also, if the user is relaxed, the scanning unit can scan all comments evenly. Furthermore, if the user is in a hurry, the scanning unit can prioritize scanning important comments. This allows important comments to be scanned preferentially by determining the priority of comments to scan based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the scanning unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the scanning unit inputs the user's emotion data into the generation AI, which then estimates the emotion and determines the priority of comments to scan.

[0070] The scanning unit can analyze the social media activity of the comment poster and prioritize scanning related comments. For example, the scanning unit analyzes the social media activity of the comment poster and prioritize scanning related comments. For example, if the poster has posted many negative comments on other social media platforms, the scanning unit prioritizes scanning the poster's comments. The scanning unit can also analyze the poster's social media activity and predict negative comments to improve the accuracy of the scan. Furthermore, if the poster has posted many comments on a particular topic, the scanning unit can prioritize scanning comments related to that topic. This allows for more accurate detection of negative comments by analyzing the poster's social media activity. Some or all of the above-described processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs data on the poster's social media activity into the generation AI, which then prioritizes scanning related comments.

[0071] The scanning unit can apply different scanning algorithms based on the content of the comments. For example, the scanning unit applies different scanning algorithms based on the content of the comments. For example, the scanning unit can apply a stricter scanning algorithm to comments containing negative keywords. The scanning unit can also apply a normal scanning algorithm to comments containing positive keywords. Furthermore, the scanning unit can apply a balanced scanning algorithm to comments containing neutral keywords. This improves the accuracy of the scan by adjusting the scanning algorithm according to the content of the comments. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs comment content data into the generation AI, and the generation AI applies different scanning algorithms.

[0072] The scanning unit can adjust the scanning method based on the length or format of the comment. For example, the scanning unit adjusts the scanning method according to the length and format of the comment. For example, the scanning unit applies a detailed scanning algorithm to long comments. The scanning unit can also apply a quick scanning algorithm to short comments. Furthermore, the scanning unit can apply a scanning algorithm suitable for a specific format (e.g., list format or bullet points) to comments. In this way, by adjusting the scanning method according to the length and format of the comment, the accuracy of the scan is improved. Some or all of the above-mentioned processing in the scanning unit may be performed using or without the generation AI. For example, the scanning unit inputs data on the length and format of the comment into the generation AI, and the generation AI adjusts the scanning method.

[0073] The analysis unit can estimate the user's emotions and adjust the level of analysis detail based on the estimated user emotions. For example, the analysis unit estimates the user's emotions and adjusts the level of analysis detail based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit performs a detailed analysis to quickly identify negative comments. Alternatively, if the user is relaxed, the analysis unit can perform a normal analysis to analyze all comments evenly. Furthermore, if the user is in a hurry, the analysis unit can perform a quick analysis to prioritize important comments. This allows for the rapid identification of negative comments by adjusting the level of analysis detail based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without the generation AI. For example, the analysis unit inputs the user's emotion data into the generation AI, which then estimates the emotion and adjusts the level of analysis detail.

[0074] The analysis unit can improve the accuracy of the analysis based on the past commentary tendency of the comment poster. The analysis unit improves the accuracy of the analysis, for example, by referring to the past commentary tendency of the comment poster. For example, if the poster has posted many negative comments in the past, the analysis unit can focus on analyzing the poster's comments. Also, if the poster has frequently used a specific keyword in the past, the analysis unit can focus on analyzing comments containing that keyword. Furthermore, the analysis unit can analyze the poster's past commentary tendency and predict negative comments to improve the accuracy of the analysis. In this way, by referring to the poster's past commentary tendency, negative comments can be analyzed more accurately. Some or all of the above-mentioned processing in the analysis unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the analysis unit inputs data on the poster's past commentary tendency into the generation AI, which then improves the accuracy of the analysis.

[0075] The analysis unit can refer to related external data to gain a deeper understanding of the context of the comment. For example, the analysis unit can refer to related external data to gain a deeper understanding of the context of the comment. For example, the analysis unit can refer to related news articles to gain a deeper understanding of the context of the comment. The analysis unit can also refer to related social media posts to gain a deeper understanding of the context of the comment. Furthermore, the analysis unit can refer to related forum posts to gain a deeper understanding of the context of the comment. By referencing related external data, the context of the comment can be more deeply understood, improving the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit inputs related external data into the generation AI, which then understands the context of the comment.

[0076] The analysis unit can evaluate the emotional tone of the comments to improve the accuracy of detecting sarcasm and sarcasm. For example, the analysis unit evaluates the emotional tone of the comments to improve the accuracy of detecting sarcasm and sarcasm. For example, the analysis unit evaluates the emotional tone of the comments and focuses on analyzing comments with a negative tone. The analysis unit can also evaluate the emotional tone of the comments to identify comments containing sarcasm and sarcasm. Furthermore, the analysis unit can evaluate the emotional tone of the comments and exclude comments with a positive tone to improve the accuracy of the analysis. In this way, by evaluating the emotional tone of the comments, comments containing sarcasm and sarcasm can be more accurately detected. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit inputs data on the emotional tone of the comments into the generation AI, and the generation AI evaluates the emotional tone.

[0077] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, the analysis unit estimates the user's emotions and adjusts the display method of the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit displays concise, highly visible analysis results. Furthermore, if the user is relaxed, the analysis unit can display detailed analysis results. Furthermore, if the user is in a hurry, the analysis unit can display analysis results that focus on the main points. By adjusting the display method of the analysis results according to the user's emotions, it is possible to provide analysis results that are easy for the user to read. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit inputs the user's emotion data into the generation AI, which then estimates the emotion and adjusts the display method of the analysis results.

[0078] The analysis unit can improve the accuracy of the analysis based on the geographical information of the comment poster. The analysis unit, for example, improves the accuracy of the analysis by taking into account the geographical information of the comment poster. For example, the analysis unit takes into account the geographical information of the poster and reflects slang and expressions specific to the region in the analysis. The analysis unit can also take into account the geographical information of the poster and reflect a cultural background specific to the region in the analysis. Furthermore, the analysis unit can take into account the geographical information of the poster and reflect topics specific to the region in the analysis. In this way, by taking into account the geographical information of the poster, slang and expressions specific to the region are reflected in the analysis, improving the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the analysis unit inputs data on the poster's geographical information into the generation AI, and the generation AI improves the accuracy of the analysis.

[0079] The analysis unit can determine the priority of analysis by taking into account the relevance of the comments. The analysis unit, for example, evaluates the relevance of the comments and prioritizes the analysis of important comments. For example, the analysis unit evaluates the relevance of the comments and prioritizes the analysis of negative comments. The analysis unit can also evaluate the relevance of the comments and prioritize the analysis of positive comments, improving the accuracy of the analysis. In this way, by evaluating the relevance of the comments, important comments can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit inputs comment relevance data into the generation AI, and the generation AI determines the priority of analysis.

[0080] The analysis unit can apply different analysis algorithms based on the category of the comment. For example, the analysis unit applies different analysis algorithms depending on the category of the comment. For example, the analysis unit applies a stricter analysis algorithm to comments in a negative category. The analysis unit can also apply a normal analysis algorithm to comments in a positive category. Furthermore, the analysis unit can apply a balanced analysis algorithm to comments in a neutral category. In this way, the analysis accuracy is improved by adjusting the analysis algorithm depending on the category of the comment. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit inputs comment category data into the generation AI, and the generation AI applies different analysis algorithms.

[0081] The shut-out unit can estimate the user's emotions and adjust the shut-out criteria based on the estimated user emotions. For example, the shut-out unit can estimate the user's emotions and adjust the shut-out criteria based on the estimated user emotions. For example, the shut-out unit can apply strict shut-out criteria when the user is stressed. The shut-out unit can also apply normal shut-out criteria when the user is relaxed. Furthermore, the shut-out unit can quickly apply shut-out criteria when the user is in a hurry. This allows for more appropriate comment shut-out by adjusting the shut-out criteria according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the shut-out unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the shut-out unit inputs the user's emotional data into the generation AI, which then estimates the emotion and adjusts the shut-out criteria.

[0082] The shutout unit can improve the accuracy of shutting out comments based on the past behavioral history of the comment poster. The shutout unit, for example, improves the accuracy of shutting out comments by referring to the past behavioral history of the comment poster. For example, if a poster has posted many negative comments in the past, the shutout unit will prioritize shutting out comments by that poster. Also, if a poster has frequently used a specific keyword in the past, the shutout unit can prioritize shutting out comments containing that keyword. Furthermore, the shutout unit can analyze the poster's past behavioral history and predict negative comments to improve the accuracy of shutting out comments. In this way, by referring to the poster's past behavioral history, negative comments can be shut out more accurately. Some or all of the above-described processing in the shutout unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the shutout unit inputs data on the poster's past behavioral history into the generation AI, which then improves the accuracy of shutting out comments.

[0083] The shut-out unit can apply different shut-out methods taking into account the content of the comment. For example, the shut-out unit applies different shut-out methods based on the content of the comment. For example, the shut-out unit applies a strict shut-out method to comments containing negative keywords. The shut-out unit can also apply a normal shut-out method to comments containing positive keywords. Furthermore, the shut-out unit can also apply a balanced shut-out method to comments containing neutral keywords. This improves the accuracy of shut-out by adjusting the shut-out method according to the content of the comment. Some or all of the above-mentioned processing in the shut-out unit may be performed using or without the generation AI. For example, the shut-out unit inputs comment content data into the generation AI, and the generation AI applies different shut-out methods.

[0084] The shutout unit can take into account the impact of a comment and determine the priority of shutting out based on its importance. The shutout unit, for example, evaluates the impact of a comment and prioritizes shutting out important comments. For example, the shutout unit quickly shuts out comments with high impact. The shutout unit can also apply a normal shutout method to comments with low impact. Furthermore, the shutout unit can evaluate the impact of a comment and determine the priority of shutting out based on its importance. In this way, important comments can be prioritized by evaluating the impact of a comment. Some or all of the above-described processing in the shutout unit may be performed using or without the generation AI. For example, the shutout unit inputs comment impact data into the generation AI, and the generation AI determines the priority of shutting out.

[0085] The shutout unit can estimate the user's emotions and adjust the display method of the shut-out comments based on the estimated user emotions. The shutout unit, for example, estimates the user's emotions and adjusts the display method of the shut-out comments based on the estimated user emotions. For example, the shutout unit hides the shut-out comments when the user is stressed. The shutout unit can also notify the user of the shut-out comments when the user is relaxed. Furthermore, the shutout unit can briefly display the shut-out comments when the user is in a hurry. This allows for a user-friendly display by adjusting the display method of the shut-out comments according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the shutout unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the shut-out unit inputs the user's emotional data into the generation AI, which then estimates the emotion and adjusts the display method for the comments to be shut out.

[0086] The shutout unit can prioritize shutting out related comments based on the social media activity of the comment poster. For example, the shutout unit analyzes the social media activity of the comment poster and prioritizes shutting out related comments. For example, if the poster has posted many negative comments on other social media platforms, the shutout unit prioritizes shutting out the poster's comments. The shutout unit can also analyze the poster's social media activity to predict negative comments and improve the accuracy of the shutout. Furthermore, if the poster has posted many comments on a specific topic, the shutout unit can prioritize shutting out comments related to that topic. This allows for more accurate shutout of negative comments by analyzing the poster's social media activity. Some or all of the above-described processing in the shutout unit may be performed using or without the generation AI. For example, the shutout unit inputs data on the poster's social media activity into the generation AI, which then prioritizes shutting out related comments.

[0087] The shutout unit can optimize the shutout algorithm based on the language or cultural background of the comment. The shutout unit, for example, optimizes the shutout algorithm by taking into account the language and cultural background of the comment. For example, if a comment is posted in English, the shutout unit takes into account slang and expressions specific to English and shuts out the comment. Also, if a comment is posted in Japanese, the shutout unit can apply an algorithm that detects sarcasm and sarcasm specific to Japanese. Furthermore, the shutout unit can optimize the algorithm that detects sarcasm and sarcasm in a specific culture by taking into account the cultural background of the comment. In this way, by taking the language and cultural background into consideration, comments containing sarcasm and sarcasm can be more accurately shut out. Some or all of the above-mentioned processing in the shutout unit may be performed using or without the generation AI. For example, the shutout unit inputs data on the language and cultural background of the comment into the generation AI, and the generation AI optimizes the shutout algorithm.

[0088] The shut-out unit can adjust the shut-out method based on the length or format of the comment. The shut-out unit adjusts the shut-out method according to, for example, the length or format of the comment. For example, the shut-out unit applies a detailed shut-out algorithm to long comments. The shut-out unit can also apply a quick shut-out algorithm to short comments. Furthermore, the shut-out unit can also apply a shut-out algorithm suitable for a specific format (e.g., list format or bullet points) of a comment. In this way, adjusting the shut-out method according to the length or format of the comment improves the accuracy of the shut-out. Some or all of the above-described processing in the shut-out unit may be performed using or without the generation AI. For example, the shut-out unit inputs data on the length and format of the comment into the generation AI, and the generation AI adjusts the shut-out method. === Hard Collateral 1-1 === Each of the multiple elements including the scanning unit, the analyzing unit, and the shutting out unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the scanning unit is realized by the processor 46 of the smart device 14 and scans comments on the SNS for each context. The analyzing unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the scanned comments to identify comments containing sarcasm or irony. The shutting out unit is realized, for example, by the control unit 46A of the smart device 14 and shuts out detected comments before they are displayed to the user. === Hard Collateral 1-2 === Each of the multiple elements, including the scanning unit, the analyzing unit, and the shutting out unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the scanning unit is realized by the processor 46 of the smart glasses 214 and scans comments on the social networking site for each context. The analyzing unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the scanned comments to identify comments containing sarcasm or irony. The shutting out unit is realized, for example, by the control unit 46A of the smart glasses 214 and shuts out detected comments before they are displayed to the user. === Hard Collateral 1-3 === Each of the multiple elements including the scanning unit, analyzing unit, and shutting out unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the scanning unit is realized by the processor 46 of the headset type terminal 314 and scans comments on SNS for each context. The analyzing unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the scanned comments to identify comments containing sarcasm or irony. The shutting out unit is realized, for example, by the control unit 46A of the headset type terminal 314 and shuts out detected comments before they are displayed to the user. === Hard Collateral 1-4 === Each of the multiple elements including the scanning unit, analyzing unit, and shutting out unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the scanning unit is realized by the processor 46 of the robot 414 and scans comments on the SNS for each context. The analyzing unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the scanned comments to identify comments containing sarcasm or irony. The shutting out unit is realized, for example, by the control unit 46A of the robot 414 and shuts out detected comments before they are displayed to the user.

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

[0090] The SNS comment filtering system can further include a customization unit that customizes the filtering criteria based on the user's preferences. For example, if the user dislikes a particular keyword or phrase, the customization unit can preferentially block comments containing that keyword or phrase. Also, if the user likes comments on a particular topic, the customization unit can preferentially display comments related to that topic. Furthermore, the customization unit can automatically adjust the filtering criteria by referencing the history of comments that the user has previously filtered. This enables filtering according to the user's preferences, making SNS use more comfortable.

[0091] The SNS comment filtering system can further include an emotion evaluation unit that evaluates the emotional tone of comments and adjusts filtering criteria based on the emotional tone. For example, the emotion evaluation unit may preferentially block comments that have a negative tone. The emotion evaluation unit may also preferentially display comments that have a positive tone. Furthermore, the emotion evaluation unit may filter comments that have a neutral tone using the normal criteria. This enables filtering according to the emotional tone of comments, enabling SNS use that takes users' emotions into consideration.

[0092] The SNS comment filtering system may further include a reliability evaluation unit that evaluates the reliability of the poster of a comment and adjusts the filtering criteria based on the reliability. For example, if a poster has posted many reliable comments in the past, the reliability evaluation unit may preferentially display the poster's comments. Also, if a poster has posted many negative comments in the past, the reliability evaluation unit may preferentially block the poster's comments. Furthermore, the reliability evaluation unit may evaluate the poster's reliability in real time and dynamically adjust the filtering criteria. This enables filtering according to the poster's reliability, resulting in the display of more reliable comments.

[0093] The SNS comment filtering system may further include an activity status evaluation unit that adjusts filtering criteria based on the user's current activity status. For example, when the user is at work, the activity status evaluation unit may tighten the filtering criteria and prioritize blocking negative comments. Furthermore, when the user is relaxed, the activity status evaluation unit may loosen the filtering criteria and prioritize displaying positive comments. Furthermore, when the user is in a hurry, the activity status evaluation unit may prioritize displaying important comments. This enables filtering according to the user's activity status, resulting in more appropriate comments being displayed.

[0094] The SNS comment filtering system may further include a content evaluation unit that applies different filtering algorithms based on the content of the comment. For example, the content evaluation unit may apply a stricter filtering algorithm to comments containing negative keywords. The content evaluation unit may also apply a normal filtering algorithm to comments containing positive keywords. The content evaluation unit may also apply a balanced filtering algorithm to comments containing neutral keywords. This enables filtering according to the content of the comment, resulting in more accurate filtering.

[0095] The SNS comment filtering system may further include an emotion estimation unit that estimates the user's emotion and adjusts filtering criteria based on the estimated user emotion. For example, if the user is feeling stressed, the emotion estimation unit may tighten the filtering criteria and prioritize blocking negative comments. Also, if the user is relaxed, the emotion estimation unit may loosen the filtering criteria and prioritize displaying positive comments. Furthermore, if the user is in a hurry, the emotion estimation unit may prioritize displaying important comments. This enables filtering according to the user's emotion, resulting in more appropriate comments being displayed.

[0096] The SNS comment filtering system can further include a behavioral history evaluation unit that adjusts filtering criteria based on the past behavioral history of the comment poster. For example, if a poster has posted many negative comments in the past, the behavioral history evaluation unit can prioritize blocking comments from that poster. Also, if a poster has frequently used a specific keyword in the past, the behavioral history evaluation unit can prioritize filtering comments containing that keyword. Furthermore, the behavioral history evaluation unit can analyze the poster's past behavioral history, predict negative comments, and adjust filtering criteria accordingly. This enables filtering based on the poster's past behavioral history, resulting in more accurate filtering.

[0097] The SNS comment filtering system can further include a time and location evaluation unit that adjusts filtering criteria based on the time and location of the comment posting. For example, the time and location evaluation unit predicts that comments posted late at night will contain more negative content and sets stricter filtering criteria. The time and location evaluation unit can also filter comments posted from specific locations by taking into account local slang and expressions. Furthermore, the time and location evaluation unit can adjust the filtering algorithm according to the time of posting to improve accuracy. This enables filtering based on the time and location of posting, resulting in more accurate filtering.

[0098] The SNS comment filtering system can further include a language and culture evaluation unit that optimizes the filtering algorithm based on the language and cultural background of the comment. For example, if the comment is posted in English, the language and culture evaluation unit may filter the comment taking into account slang and expressions specific to English. In addition, if the comment is posted in Japanese, the language and culture evaluation unit may apply an algorithm that detects sarcasm and irony specific to Japanese. Furthermore, the language and culture evaluation unit may optimize the algorithm that detects sarcasm and irony in a specific culture by taking into account the cultural background of the comment. This enables filtering based on language and cultural background, resulting in more accurate filtering.

[0099] The SNS comment filtering system may further include an emotion display unit that estimates a user's emotion and adjusts the display method of the filtering results based on the estimated user emotion. For example, the emotion display unit may hide filtered comments when the user is stressed. The emotion display unit may also notify the user of filtered comments when the user is relaxed. Furthermore, the emotion display unit may briefly display filtered comments when the user is in a hurry. This allows the filtering results to be displayed according to the user's emotion, thereby providing more appropriate information.

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

[0101] Step 1: The scanning unit scans comments on social media. Using generative AI, the scanning unit scans comments by context, taking into account the comments before and after and the poster's past comment history. For example, it analyzes not only whether a specific keyword is included, but also the context in which that keyword is used. Step 2: The analysis unit analyzes the comments scanned by the scanning unit. The analysis unit uses generative AI to analyze the comments and identify comments that contain sarcasm or irony. The analysis unit can not only determine whether specific keywords are included, but also analyze the context in which those keywords are used. For example, the analysis takes into account not only the content of the comment, but also the context before and after it. Step 3: The removal unit removes comments containing sarcasm or irony detected by the analysis unit. The removal unit uses the generation AI to remove detected comments before they are displayed to the user. For example, if a comment containing sarcasm or irony is detected, the comment is removed without being displayed to the user.

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

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of 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.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt 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.

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

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

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

[0139] 7, 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.

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

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

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

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

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

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

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

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

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

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

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

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

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt 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.

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

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

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

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

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

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

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

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

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

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

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

[0164] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

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

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

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

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

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

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

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

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

[0173] [Explanation of symbols]

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

Claims

1. A scanning section that scans SNS comments, an analysis unit that analyzes the comments scanned by the scanning unit; a removal unit that removes comments containing sarcasm or irony detected by the analysis unit. A system characterized by:

2. The scanning unit Scanning based on previous and following comments or the poster's past comment history 2. The system of claim 1.

3. The shutout portion is Notify the user of detected comments 2. The system of claim 1.

4. The analysis unit Analyze not only the presence of specific keywords, but also the context in which those keywords are used 2. The system of claim 1.

5. The scanning unit Inferring user emotions and adjusting scan frequency based on the estimated user emotions 2. The system of claim 1.

6. The scanning unit Improve scan accuracy based on commenters' past behavior 2. The system of claim 1.

7. The scanning unit Adjust scanning based on the time or location of comments 2. The system of claim 1.

8. The scanning unit Optimize scanning algorithms based on the language or cultural context of comments 2. The system of claim 1.

Images