system

Abstract

An object of a system according to an embodiment is to detect a fire risk or a discriminative / offensive expression of a post content in an SNS or a chat tool in real time and take appropriate measures.SOLUTION: A system includes a contribution content analysis part, a burning risk warning part, an expression candidate presentation part, a discriminative / offensive expression detection part, and a pre-contribution check part. The posted content analysis unit analyzes the posted content in real time. A fire risk warning part warns of a fire risk on the basis of a result analyzed by the contribution content analysis part. The expression candidate presentation part presents appropriate expression candidates based on the burning risk warned by the burning risk warning part. The discriminatory and offensive expression detection unit automatically detects discriminatory and offensive expressions based on words predicted from learned data and predefined rules and guidelines. The pre-posting check unit checks the posted content before posting.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to detect in real time whether posts on social media or chat tools were at risk of causing an uproar or contained discriminatory or offensive language, and to take appropriate measures.

[0005] The system according to the embodiment aims to detect in real time whether posts on social media or chat tools are at risk of causing an uproar or contain discriminatory or offensive language, and to take appropriate measures. [Means for solving the problem]

[0006] The system according to the embodiment includes a post content analysis unit, a flame war risk warning unit, a candidate expression presentation unit, a discriminatory / offensive expression detection unit, and a pre-post check unit. The post content analysis unit analyzes post content in real time. The flame war risk warning unit warns of a flame war risk based on the results of the analysis by the post content analysis unit. The candidate expression presentation unit presents appropriate candidate expressions based on the flame war risk warned by the flame war risk warning unit. The discriminatory / offensive expression detection unit automatically detects discriminatory / offensive expressions based on words predicted from learned data and predefined rules and guidelines. The pre-post check unit checks post content before posting. [Effects of the Invention]

[0007] The system according to the embodiment can detect in real time whether posts on social media or chat tools are at risk of causing an uproar or contain discriminatory or offensive language, and can take appropriate measures. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) A real-time analysis system for SNS posts and chat tools according to an embodiment of the present invention is a system that warns users of the risk of a controversy before they post and presents suggestions for appropriate expressions. This allows users to avoid the risk of a controversy and communicate safely without using discriminatory or offensive expressions.

[0029] According to an embodiment, a real-time analysis system for social media posts and chat tools includes a post content analysis unit, a flame war risk warning unit, a candidate expression presentation unit, a discriminatory / offensive expression detection unit, and a pre-post check unit. The post content analysis unit analyzes the post content entered by a user in real time. For example, the generation AI uses natural language processing technology to understand the meaning and context of the post content. The generation AI also performs analysis based on the text the user is about to post. The flame war risk warning unit warns of the risk of a flame war based on the analysis results. For example, the generation AI evaluates the risk based on the frequency of occurrence of specific keywords and similarity to past flame war cases. The candidate expression presentation unit presents appropriate candidate expressions based on the risk of a flame war. For example, in response to a post saying "This product is really terrible," the generation AI suggests a phrase such as "This product has room for improvement." The discriminatory / offensive expression detection unit automatically detects discriminatory / offensive expressions based on words predicted from learned data and predefined rules and guidelines. For example, the generation AI detects discriminatory language such as "This expression is inappropriate" and displays a warning. The pre-post checker checks the content of posts before users post them. For example, the generation AI re-analyzes the content of posts before users press the post button to check for any problems. This allows real-time analysis systems for social media posts and chat tools to help users avoid the risk of flame wars and communicate safely without using discriminatory or offensive language. For example, by analyzing users' posts in real time and suggesting appropriate language, flame wars can be prevented. Furthermore, by automatically detecting discriminatory or offensive language and prompting users to correct it, a healthy communication environment can be provided.

[0030] The post content analysis unit takes into account the poster's past posting history and behavioral patterns, enabling more accurate analysis. For example, when the generation AI analyzes the content of a post, the post content analysis unit references the poster's past posting history and takes into account past posting patterns and frequently used words. For example, it can learn the patterns of posts that have caused controversy in the past and detect posts that pose similar risks with high accuracy. In this way, by taking into account the poster's past posting history and behavioral patterns, the accuracy of the analysis is improved.

[0031] The post content analysis unit can perform a more comprehensive risk assessment by combining the analysis results of the post content with predicted reactions from the poster's followers and friends. The post content analysis unit, for example, performs risk assessment based on the analysis results of the post content and by referring to past reaction data from followers and friends. For example, the unit learns posting patterns in which a specific follower has previously shown negative reactions, and detects posts that pose similar risks with high accuracy. This improves the accuracy of risk assessment by taking into account predicted reactions from followers and friends.

[0032] The post content analysis unit analyzes not only text but also the content of images and videos, making it possible to assess the risk of multimedia posts. For example, when the generation AI analyzes post content, the post content analysis unit analyzes not only text but also the content of images and videos. For example, it uses image recognition technology to detect inappropriate elements contained in posted images. This makes it possible to assess the risk of multimedia posts.

[0033] The post content analysis unit can share the analysis results of post content between different SNS platforms and provide a unified risk assessment. The post content analysis unit, for example, builds a system that shares the analysis results of post content between different SNS platforms and provides a unified risk assessment. For example, it can simultaneously analyze post content on Facebook and Twitter and provide a consistent risk assessment. This makes it possible to provide a unified risk assessment between different SNS platforms.

[0034] The flaming risk warning unit can refer to past flaming cases and perform risk assessment based on cases with high similarity. For example, when the generation AI warns of the risk of a flaming case, the flaming risk warning unit refers to past flaming cases from a database and performs risk assessment based on cases with high similarity. For example, it compares the content of posts that have caused flaming in the past with the content of current posts to assess risk. This makes it possible to perform risk assessment based on past flaming cases.

[0035] The Flame Risk Warning Unit can understand the poster's intention and suggest appropriate expressions that do not undermine that intention. For example, the Flame Risk Warning Unit uses a generative AI to analyze the poster's intention and suggest appropriate expressions that do not undermine that intention. For example, the intention "This product is really terrible" can be changed to "This product has room for improvement." This makes it possible to suggest appropriate expressions that do not undermine the poster's intention.

[0036] The flame risk warning unit can provide customized risk assessments and appropriate language based on the attributes of the poster's followers and friends. The flame risk warning unit customizes the flame risk warning and appropriate language presentation based on, for example, attribute data (age, gender, interests, etc.) of the poster's followers and friends. For example, if there are many followers with a specific attribute, the risk of a post containing content that is sensitive to that attribute is highly rated. This makes it possible to provide customized risk assessments and appropriate language presentation based on the attributes of followers and friends.

[0037] The flame risk warning unit can also perform risk assessment for specific groups or communities selected by the poster. The flame risk warning unit builds a system that issues flame risk warnings for specific groups or communities selected by the poster. For example, it performs risk assessment within a specific group and suggests appropriate wording. This makes it possible to perform risk assessment for specific groups or communities.

[0038] The flaming risk warning unit can present appropriate expressions corresponding to different languages ​​and cultural spheres. The flaming risk warning unit, for example, builds a system that presents appropriate expressions corresponding to different languages ​​and cultural spheres. For example, it proposes expressions corresponding to multiple languages, such as English, French, and Chinese. This makes it possible to present appropriate expressions corresponding to different languages ​​and cultural spheres.

[0039] The discriminatory / offensive language detection unit takes into account the poster's past posting history and behavioral patterns, enabling more accurate detection. For example, when the generation AI detects discriminatory / offensive language, the discriminatory / offensive language detection unit refers to the poster's past posting history and takes into account past posting patterns and frequently used words. For example, it particularly carefully analyzes the current posting content of a poster who has used discriminatory language in the past. This improves the accuracy of detection by taking into account the poster's past posting history and behavioral patterns.

[0040] The discriminatory and offensive expression detection unit can perform a more comprehensive risk assessment by combining detection results with predicted reactions from the poster's followers and friends. For example, the discriminatory and offensive expression detection unit performs risk assessment by referring to past reaction data from followers and friends based on the detection results of discriminatory and offensive expressions. For example, it can learn the posting patterns in which a specific follower has previously shown negative reactions, and detect posts that pose a similar risk with high accuracy. This improves the accuracy of risk assessment by taking into account predicted reactions from followers and friends.

[0041] The discriminatory / offensive expression detection unit analyzes not only text but also the content of images and videos, making it possible to assess the risk of multimedia posts. For example, when the generative AI detects discriminatory / offensive expressions, the discriminatory / offensive expression detection unit analyzes not only text but also the content of images and videos. For example, it uses image recognition technology to detect inappropriate elements contained in posted images. This makes it possible to assess the risk of multimedia posts.

[0042] The discriminatory and offensive language detection unit can share the detection results of discriminatory and offensive language across different social media platforms and provide a unified risk assessment. For example, the discriminatory and offensive language detection unit can build a system that shares the detection results of discriminatory and offensive language across different social media platforms and provide a unified risk assessment. For example, it can simultaneously analyze the content of posts on Facebook and Twitter and provide a consistent risk assessment. This makes it possible to provide a unified risk assessment across different social media platforms.

[0043] The pre-post check section takes into account the poster's past posting history and behavioral patterns, enabling more accurate checks. For example, when the generation AI performs a pre-post check, the pre-post check section references the poster's past posting history and takes into account past posting patterns and frequently used words. For example, it learns the patterns of posts that have caused controversy in the past and detects posts that pose similar risks with high accuracy. This improves the accuracy of the check by taking into account the poster's past posting history and behavioral patterns.

[0044] The pre-post check unit can perform a more comprehensive risk assessment by combining the check results with predicted reactions from the poster's followers and friends. The pre-post check unit, for example, performs risk assessment by referring to past reaction data from followers and friends based on the pre-post check results. For example, it can learn posting patterns in which a specific follower has previously shown negative reactions, and detect posts that pose similar risks with high accuracy. This improves the accuracy of risk assessment by taking into account predicted reactions from followers and friends.

[0045] The pre-post check unit analyzes not only text but also the content of images and videos, and can perform risk assessments of multimedia posts. For example, when the generation AI performs a pre-post check, the pre-post check unit analyzes not only text but also the content of images and videos. For example, it uses image recognition technology to detect inappropriate elements contained in posted images. This makes it possible to perform risk assessments of multimedia posts.

[0046] The pre-post check unit can share the results of pre-post checks between different SNS platforms and provide a unified risk assessment. For example, the pre-post check unit can build a system that shares the results of pre-post checks between different SNS platforms and provide a unified risk assessment. For example, it can simultaneously analyze the content of posts on Facebook and Twitter and perform a consistent risk assessment. This makes it possible to provide a unified risk assessment across different SNS platforms.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] A real-time analysis system for SNS posts and chat tools can further include a reaction prediction unit that predicts follower reactions to user posts. The reaction prediction unit presents predicted reactions to posts based on past follower reaction data. For example, it can learn from past posting patterns in which specific followers have shown negative reactions and display a warning for posts that pose a similar risk. The reaction prediction unit can also make customized reaction predictions taking into account follower attributes (age, gender, interests, etc.). This allows users to predict follower reactions and select appropriate expressions before posting.

[0049] The real-time analysis system for social media posts and chat tools can further include a social impact assessment unit that evaluates the social impact of the content posted by users. The social impact assessment unit evaluates the social impact of the content posted and displays a warning to the user. For example, if a specific keyword or phrase is related to a socially sensitive topic, the unit evaluates the impact and warns of the risk. The social impact assessment unit can also evaluate the impact the content posted will have on a specific community or group. This allows users to consider the social impact before posting and select appropriate expressions.

[0050] The real-time analysis system for social media posts and chat tools can further include a legal risk assessment unit that evaluates the legal risks of the content posted by users. The legal risk assessment unit evaluates whether the content posted poses a legal problem and displays a warning to the user. For example, if a specific expression may constitute defamation or a violation of privacy, the legal risk assessment unit evaluates the risk and displays a warning. The legal risk assessment unit can also evaluate whether the content posted violates specific laws or regulations. This allows users to consider legal risks before posting and select appropriate expressions.

[0051] The real-time analysis system for SNS posts and chat tools can further include a brand image evaluation unit that evaluates the impact of user posts on brand image. The brand image evaluation unit evaluates how the posts will affect brand image and displays a warning to the user. For example, if a specific expression could potentially damage brand image, it evaluates the risk and displays a warning. The brand image evaluation unit can also evaluate how the posts will affect brand value and credibility. This allows users to consider the impact on brand image before posting and select appropriate expressions.

[0052] The real-time analysis system for social media posts and chat tools can further include a cultural impact assessment unit that evaluates the cultural impact of user posts. The cultural impact assessment unit evaluates how the post content will affect different cultural spheres and displays a warning to the user. For example, if a particular expression could be misleading in a different cultural sphere, it evaluates the risk and displays a warning. The cultural impact assessment unit can also evaluate how the post content will affect a particular culture or religion. This allows users to consider cultural impact before posting and select appropriate expressions.

[0053] The real-time analysis system for social media posts and chat tools can further include an ethical impact assessment unit that evaluates the ethical impact of the content posted by users. The ethical impact assessment unit evaluates whether the content posted is ethically problematic and displays a warning to the user. For example, if a specific expression is ethically inappropriate, it evaluates the risk and displays a warning. The ethical impact assessment unit can also evaluate whether the content posted is appropriate in light of societal ethical standards. This allows users to consider the ethical impact before posting and select appropriate expressions.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The post content analysis unit analyzes the post content entered by the user in real time. For example, the generation AI uses natural language processing technology to understand the meaning and context of the post content and performs analysis based on the text the user is about to post. Step 2: The Flaming Risk Warning Unit warns of the risk of a flaming incident based on the results of the analysis by the post content analysis unit. For example, the generation AI assesses the risk based on the frequency of occurrence of specific keywords and similarities with past flaming incidents. Step 3: The candidate expression suggestion unit suggests appropriate candidate expressions based on the risk of a controversy. For example, in response to a post saying "This product is really terrible," the generation AI would suggest expressions such as "This product has room for improvement." Step 4: The discriminatory / offensive expression detection unit automatically detects discriminatory / offensive expressions based on predicted words from the learned data and predefined rules and guidelines. For example, the generation AI detects discriminatory expressions such as "This expression is inappropriate" and displays a warning. Step 5: The pre-post checker checks the content of the post before the user posts it. For example, the generation AI re-analyzes the content of the post before the user presses the post button to check for any problems.

[0056] (Example 2) A real-time analysis system for SNS posts and chat tools according to an embodiment of the present invention is a system that warns users of the risk of a controversy before they post and presents suggestions for appropriate expressions. This allows users to avoid the risk of a controversy and communicate safely without using discriminatory or offensive expressions.

[0057] According to an embodiment, a real-time analysis system for social media posts and chat tools includes a post content analysis unit, a flame war risk warning unit, a candidate expression presentation unit, a discriminatory / offensive expression detection unit, and a pre-post check unit. The post content analysis unit analyzes the post content entered by a user in real time. For example, the generation AI uses natural language processing technology to understand the meaning and context of the post content. The generation AI also performs analysis based on the text the user is about to post. The flame war risk warning unit warns of the risk of a flame war based on the analysis results. For example, the generation AI evaluates the risk based on the frequency of occurrence of specific keywords and similarity to past flame war cases. The candidate expression presentation unit presents appropriate candidate expressions based on the risk of a flame war. For example, in response to a post saying "This product is really terrible," the generation AI suggests a phrase such as "This product has room for improvement." The discriminatory / offensive expression detection unit automatically detects discriminatory / offensive expressions based on words predicted from learned data and predefined rules and guidelines. For example, the generation AI detects discriminatory language such as "This expression is inappropriate" and displays a warning. The pre-post checker checks the content of posts before users post them. For example, the generation AI re-analyzes the content of posts before users press the post button to check for any problems. This allows real-time analysis systems for social media posts and chat tools to help users avoid the risk of flame wars and communicate safely without using discriminatory or offensive language. For example, by analyzing users' posts in real time and suggesting appropriate language, flame wars can be prevented. Furthermore, by automatically detecting discriminatory or offensive language and prompting users to correct it, a healthy communication environment can be provided.

[0058] The post content analysis unit takes into account the poster's past posting history and behavioral patterns, enabling more accurate analysis. For example, when the generation AI analyzes the content of a post, the post content analysis unit references the poster's past posting history and takes into account past posting patterns and frequently used words. For example, it can learn the patterns of posts that have caused controversy in the past and detect posts that pose similar risks with high accuracy. In this way, by taking into account the poster's past posting history and behavioral patterns, the accuracy of the analysis is improved.

[0059] The post content analysis unit can estimate the poster's current psychological state and emotions and adjust the analysis results based on that. For example, the post content analysis unit analyzes the poster's input speed and typing strength to estimate the poster's current psychological state. For example, posts entered hastily may contain emotional content, so the risk assessment is increased. This improves the accuracy of the analysis results by taking the poster's psychological state and emotions into consideration.

[0060] The post content analysis unit can perform a more comprehensive risk assessment by combining the analysis results of the post content with predicted reactions from the poster's followers and friends. The post content analysis unit, for example, performs risk assessment based on the analysis results of the post content and by referring to past reaction data from followers and friends. For example, the unit learns posting patterns in which a specific follower has previously shown negative reactions, and detects posts that pose similar risks with high accuracy. This improves the accuracy of risk assessment by taking into account predicted reactions from followers and friends.

[0061] The post content analysis unit analyzes not only text but also the content of images and videos, making it possible to assess the risk of multimedia posts. For example, when the generation AI analyzes post content, the post content analysis unit analyzes not only text but also the content of images and videos. For example, it uses image recognition technology to detect inappropriate elements contained in posted images. This makes it possible to assess the risk of multimedia posts.

[0062] The post content analysis unit can share the analysis results of post content between different SNS platforms and provide a unified risk assessment. The post content analysis unit, for example, builds a system that shares the analysis results of post content between different SNS platforms and provides a unified risk assessment. For example, it can simultaneously analyze post content on Facebook and Twitter and provide a consistent risk assessment. This makes it possible to provide a unified risk assessment between different SNS platforms.

[0063] The post content analysis unit uses the emotion estimation function to analyze in real time the emotions of the poster when he or she enters the post content, and can perform a risk assessment based on the emotions. The post content analysis unit, for example, uses the emotion estimation function to analyze in real time the emotions of the poster when he or she enters the post content. For example, it uses a camera or microphone to analyze the poster's facial expression and tone of voice and calculates an emotion score. This makes it possible to perform a risk assessment based on the poster's emotions.

[0064] The flaming risk warning unit can refer to past flaming cases and perform risk assessment based on cases with high similarity. For example, when the generation AI warns of the risk of a flaming case, the flaming risk warning unit refers to past flaming cases from a database and performs risk assessment based on cases with high similarity. For example, it compares the content of posts that have caused flaming in the past with the content of current posts to assess risk. This makes it possible to perform risk assessment based on past flaming cases.

[0065] The Flame Risk Warning Unit can understand the poster's intention and suggest appropriate expressions that do not undermine that intention. For example, the Flame Risk Warning Unit uses a generative AI to analyze the poster's intention and suggest appropriate expressions that do not undermine that intention. For example, the intention "This product is really terrible" can be changed to "This product has room for improvement." This makes it possible to suggest appropriate expressions that do not undermine the poster's intention.

[0066] The flame risk warning unit can provide customized risk assessments and appropriate language based on the attributes of the poster's followers and friends. The flame risk warning unit customizes the flame risk warning and appropriate language presentation based on, for example, attribute data (age, gender, interests, etc.) of the poster's followers and friends. For example, if there are many followers with a specific attribute, the risk of a post containing content that is sensitive to that attribute is highly rated. This makes it possible to provide customized risk assessments and appropriate language presentation based on the attributes of followers and friends.

[0067] The flame risk warning unit can also perform risk assessment for specific groups or communities selected by the poster. The flame risk warning unit builds a system that issues flame risk warnings for specific groups or communities selected by the poster. For example, it performs risk assessment within a specific group and suggests appropriate wording. This makes it possible to perform risk assessment for specific groups or communities.

[0068] The flaming risk warning unit can present appropriate expressions corresponding to different languages ​​and cultural spheres. The flaming risk warning unit, for example, builds a system that presents appropriate expressions corresponding to different languages ​​and cultural spheres. For example, it proposes expressions corresponding to multiple languages, such as English, French, and Chinese. This makes it possible to present appropriate expressions corresponding to different languages ​​and cultural spheres.

[0069] The flaming risk warning unit can use the emotion estimation function to suggest appropriate expressions based on the poster's emotions. The flaming risk warning unit, for example, uses the emotion estimation function to build a system that suggests appropriate expressions based on the poster's emotions. For example, if the poster is feeling anger or sadness, it suggests positive expressions. This makes it possible to suggest appropriate expressions based on the poster's emotions.

[0070] The discriminatory / offensive language detection unit takes into account the poster's past posting history and behavioral patterns, enabling more accurate detection. For example, when the generation AI detects discriminatory / offensive language, the discriminatory / offensive language detection unit refers to the poster's past posting history and takes into account past posting patterns and frequently used words. For example, it particularly carefully analyzes the current posting content of a poster who has used discriminatory language in the past. This improves the accuracy of detection by taking into account the poster's past posting history and behavioral patterns.

[0071] The discriminatory and offensive expression detection unit can estimate the poster's current mental state and emotions and adjust the detection results based on that. For example, the discriminatory and offensive expression detection unit analyzes the poster's typing speed and typing strength to estimate their current mental state. For example, posts typed hastily may contain emotional content, so the risk assessment is increased. This improves the accuracy of detection results by taking into account the poster's mental state and emotions.

[0072] The discriminatory and offensive expression detection unit can perform a more comprehensive risk assessment by combining detection results with predicted reactions from the poster's followers and friends. For example, the discriminatory and offensive expression detection unit performs risk assessment by referring to past reaction data from followers and friends based on the detection results of discriminatory and offensive expressions. For example, it can learn the posting patterns in which a specific follower has previously shown negative reactions, and detect posts that pose a similar risk with high accuracy. This improves the accuracy of risk assessment by taking into account predicted reactions from followers and friends.

[0073] The discriminatory / offensive expression detection unit analyzes not only text but also the content of images and videos, making it possible to assess the risk of multimedia posts. For example, when the generative AI detects discriminatory / offensive expressions, the discriminatory / offensive expression detection unit analyzes not only text but also the content of images and videos. For example, it uses image recognition technology to detect inappropriate elements contained in posted images. This makes it possible to assess the risk of multimedia posts.

[0074] The discriminatory and offensive language detection unit can share the detection results of discriminatory and offensive language across different social media platforms and provide a unified risk assessment. For example, the discriminatory and offensive language detection unit can build a system that shares the detection results of discriminatory and offensive language across different social media platforms and provide a unified risk assessment. For example, it can simultaneously analyze the content of posts on Facebook and Twitter and provide a consistent risk assessment. This makes it possible to provide a unified risk assessment across different social media platforms.

[0075] The discriminatory / offensive expression detection unit uses an emotion estimation function to analyze in real time the emotions felt by posters when they use discriminatory / offensive expressions, and is able to perform risk assessment based on those emotions. The discriminatory / offensive expression detection unit, for example, uses an emotion estimation function to analyze in real time the emotions felt by posters when they use discriminatory / offensive expressions. For example, it may use a camera or microphone to analyze the poster's facial expressions and tone of voice and calculate an emotion score. This makes it possible to perform risk assessment based on the poster's emotions.

[0076] The pre-post check section takes into account the poster's past posting history and behavioral patterns, enabling more accurate checks. For example, when the generation AI performs a pre-post check, the pre-post check section references the poster's past posting history and takes into account past posting patterns and frequently used words. For example, it learns the patterns of posts that have caused controversy in the past and detects posts that pose similar risks with high accuracy. This improves the accuracy of the check by taking into account the poster's past posting history and behavioral patterns.

[0077] The pre-post check unit can estimate the poster's current psychological state and emotions and adjust the check results based on that. For example, the pre-post check unit analyzes the poster's input speed and typing strength to estimate the poster's current psychological state. For example, posts entered hastily may contain emotional content, so the risk assessment is increased. This improves the accuracy of the check results by taking the poster's psychological state and emotions into consideration.

[0078] The pre-post check unit can perform a more comprehensive risk assessment by combining the check results with predicted reactions from the poster's followers and friends. The pre-post check unit, for example, performs risk assessment by referring to past reaction data from followers and friends based on the pre-post check results. For example, it can learn posting patterns in which a specific follower has previously shown negative reactions, and detect posts that pose similar risks with high accuracy. This improves the accuracy of risk assessment by taking into account predicted reactions from followers and friends.

[0079] The pre-post check unit analyzes not only text but also the content of images and videos, and can perform risk assessments of multimedia posts. For example, when the generation AI performs a pre-post check, the pre-post check unit analyzes not only text but also the content of images and videos. For example, it uses image recognition technology to detect inappropriate elements contained in posted images. This makes it possible to perform risk assessments of multimedia posts.

[0080] The pre-post check unit can share the results of pre-post checks between different SNS platforms and provide a unified risk assessment. For example, the pre-post check unit can build a system that shares the results of pre-post checks between different SNS platforms and provide a unified risk assessment. For example, it can simultaneously analyze the content of posts on Facebook and Twitter and perform a consistent risk assessment. This makes it possible to provide a unified risk assessment across different SNS platforms.

[0081] The pre-post check unit uses the emotion estimation function to analyze in real time the emotions of the poster when entering the content to post, and can perform a risk assessment based on the emotions. The pre-post check unit, for example, uses the emotion estimation function to analyze in real time the emotions of the poster when entering the content to post. For example, it uses a camera or microphone to analyze the poster's facial expression and tone of voice and calculates an emotion score. This makes it possible to perform a risk assessment based on the poster's emotions.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] A real-time analysis system for SNS posts and chat tools can further include a reaction prediction unit that predicts follower reactions to user posts. The reaction prediction unit presents predicted reactions to posts based on past follower reaction data. For example, it can learn from past posting patterns in which specific followers have shown negative reactions and display a warning for posts that pose a similar risk. The reaction prediction unit can also make customized reaction predictions taking into account follower attributes (age, gender, interests, etc.). This allows users to predict follower reactions and select appropriate expressions before posting.

[0084] A real-time analysis system for social media posts and chat tools can further include an emotional response prediction unit that predicts the emotional response of users to the content of their posts. The emotional response prediction unit presents predicted emotions for the content of posts based on past emotional response data from followers. For example, it can learn the posting patterns in which a specific follower has previously expressed emotions such as anger or sadness, and display a warning for posts that pose a similar risk. The emotional response prediction unit can also calculate an emotional score for each follower and perform a risk assessment based on their emotions. This allows users to predict their followers' emotional responses before posting and select appropriate expressions.

[0085] The real-time analysis system for social media posts and chat tools can further include a social impact assessment unit that evaluates the social impact of the content posted by users. The social impact assessment unit evaluates the social impact of the content posted and displays a warning to the user. For example, if a specific keyword or phrase is related to a socially sensitive topic, the unit evaluates the impact and warns of the risk. The social impact assessment unit can also evaluate the impact the content posted will have on a specific community or group. This allows users to consider the social impact before posting and select appropriate expressions.

[0086] The real-time analysis system for social media posts and chat tools can further include a legal risk assessment unit that evaluates the legal risks of the content posted by users. The legal risk assessment unit evaluates whether the content posted poses a legal problem and displays a warning to the user. For example, if a specific expression may constitute defamation or a violation of privacy, the legal risk assessment unit evaluates the risk and displays a warning. The legal risk assessment unit can also evaluate whether the content posted violates specific laws or regulations. This allows users to consider legal risks before posting and select appropriate expressions.

[0087] The real-time analysis system for SNS posts and chat tools can further include a brand image evaluation unit that evaluates the impact of user posts on brand image. The brand image evaluation unit evaluates how the posts will affect brand image and displays a warning to the user. For example, if a specific expression could potentially damage brand image, it evaluates the risk and displays a warning. The brand image evaluation unit can also evaluate how the posts will affect brand value and credibility. This allows users to consider the impact on brand image before posting and select appropriate expressions.

[0088] The real-time analysis system for SNS posts and chat tools can further include an emotional impact assessment unit that evaluates the emotional impact of the content posted by a user. The emotional impact assessment unit evaluates the emotional impact that the content posted will have on other users and displays a warning to the user. For example, if a particular expression is likely to cause anger or sadness in other users, the system evaluates the risk and displays a warning. The emotional impact assessment unit can also evaluate whether the content posted will cause positive emotions in other users. This allows users to consider the emotional impact on other users and select appropriate expressions before posting.

[0089] The real-time analysis system for SNS posts and chat tools can further include a psychological impact assessment unit that evaluates the psychological impact of the content posted by a user. The psychological impact assessment unit evaluates the psychological impact that the content posted will have on other users and displays a warning to the user. For example, if a particular expression has the potential to cause stress or anxiety to other users, the unit evaluates the risk and displays a warning. The psychological impact assessment unit can also evaluate whether the content posted will have a positive psychological impact on other users. This allows users to consider the psychological impact on other users and select appropriate expressions before posting.

[0090] The real-time analysis system for social media posts and chat tools can further include a cultural impact assessment unit that evaluates the cultural impact of user posts. The cultural impact assessment unit evaluates how the post content will affect different cultural spheres and displays a warning to the user. For example, if a particular expression could be misleading in a different cultural sphere, it evaluates the risk and displays a warning. The cultural impact assessment unit can also evaluate how the post content will affect a particular culture or religion. This allows users to consider cultural impact before posting and select appropriate expressions.

[0091] The real-time analysis system for SNS posts and chat tools can further include an emotional support unit that provides emotional support for the content posted by the user. The emotional support unit provides an appropriate support message when the user is in an emotionally difficult situation. For example, if the user is feeling sad or angry, the emotional support unit displays a message of encouragement or comfort. The emotional support unit can also provide advice to help the user post in an emotionally stable state. This allows the user to communicate safely while receiving emotional support.

[0092] The real-time analysis system for social media posts and chat tools can further include an ethical impact assessment unit that evaluates the ethical impact of the content posted by users. The ethical impact assessment unit evaluates whether the content posted is ethically problematic and displays a warning to the user. For example, if a specific expression is ethically inappropriate, it evaluates the risk and displays a warning. The ethical impact assessment unit can also evaluate whether the content posted is appropriate in light of societal ethical standards. This allows users to consider the ethical impact before posting and select appropriate expressions.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The post content analysis unit analyzes the post content entered by the user in real time. For example, the generation AI uses natural language processing technology to understand the meaning and context of the post content and performs analysis based on the text the user is about to post. Step 2: The Flaming Risk Warning Unit warns of the risk of a flaming incident based on the results of the analysis by the post content analysis unit. For example, the generation AI assesses the risk based on the frequency of occurrence of specific keywords and similarities with past flaming incidents. Step 3: The candidate expression suggestion unit suggests appropriate candidate expressions based on the risk of a controversy. For example, in response to a post saying "This product is really terrible," the generation AI would suggest expressions such as "This product has room for improvement." Step 4: The discriminatory / offensive expression detection unit automatically detects discriminatory / offensive expressions based on predicted words from the learned data and predefined rules and guidelines. For example, the generation AI detects discriminatory expressions such as "This expression is inappropriate" and displays a warning. Step 5: The pre-post checker checks the content of the post before the user posts it. For example, the generation AI re-analyzes the content of the post before the user presses the post button to check for any problems.

[0095] 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.

[0096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0097] 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.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0108] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0123] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0139] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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."

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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. [Explanation of symbols]

[0162] 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 post content analysis unit that analyzes post content in real time; a flaming risk warning unit that warns of a flaming risk based on the results of the analysis by the post content analysis unit; a candidate expression presentation unit that presents candidates for appropriate expressions based on the risk of a controversy warned by the controversy risk warning unit; A discriminatory / offensive expression detection unit that automatically detects discriminatory / offensive expressions based on words predicted from learned data and predefined rules and guidelines; A pre-posting check unit that checks the content of a post before it is posted. A system characterized by:

2. The post content analysis unit Analyze not only text but also images and videos to assess the risk of multimedia posts 2. The system of claim 1.

3. The flaming risk warning unit Refer to past cases of online outrage and conduct risk assessments based on similar cases 2. The system of claim 1.

4. The discriminatory / offensive expression detection unit It takes into account the poster's past posting history and behavioral patterns to achieve more accurate detection.

2. The system of claim 1.

5. The pre-posting check unit Conduct more accurate checks by taking into account the poster's past posting history and behavioral patterns 2. The system of claim 1.

6. The post content analysis unit Estimate the poster's current mental state and emotions and adjust the analysis results accordingly 2. The system of claim 1.

7. The flaming risk warning unit Using emotion estimation function, we suggest appropriate expressions based on the poster's emotions.

2. The system of claim 1.

8. The discriminatory / offensive expression detection unit Using an emotion estimation function, the emotions expressed by posters when they use discriminatory or offensive expressions are analyzed in real time, and risk assessment is performed based on those emotions.

2. The system of claim 1.

Images