System

Abstract

An object of the system according to the embodiment is to automatically detect whether the content of the text is inappropriate and warn the user.SOLUTION: A system according to an embodiment includes a text analysis unit, an ethics evaluation unit, an inappropriate text detection unit, a warning message generation unit, and an alert display unit. A text analysis part analyzes the use pattern of words by using the generation AI. The ethics evaluator evaluates the text based on general ethical principles. The inappropriate text detection unit detects inappropriate content from the text analyzed and evaluated by the text analysis unit and the ethics evaluation unit. The warning message generation unit generates a warning message based on the inappropriate content detected by the inappropriate text detection unit. The alert display unit displays the warning message generated by the warning message generation unit to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques do not adequately automatically detect whether text content is inappropriate and warn the user, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically detect whether the content of the text is inappropriate and to warn the user. [Means for solving the problem]

[0006] The system according to the embodiment includes a text analysis unit, an ethics evaluation unit, an inappropriate text detection unit, a warning message generation unit, and an alert display unit. The text analysis unit analyzes word usage patterns using a generative AI. The ethics evaluation unit evaluates text based on general ethical principles. The inappropriate text detection unit detects inappropriate content from the text analyzed and evaluated by the text analysis unit and the ethics evaluation unit. The warning message generation unit generates a warning message based on the inappropriate content detected by the inappropriate text detection unit. The alert display unit displays the warning message generated by the warning message generation unit to a user. [Effects of the Invention]

[0007] The system according to the embodiment can automatically detect if the content of the text is inappropriate and warn the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The inappropriate text detection system according to the embodiment of the present invention is a system that uses a generation AI to detect inappropriate text or interactions and issues an alert to the user as a warning message. As a result, the inappropriate text detection system warns the user of inappropriate text or interactions, and can be useful in preventing damage.

[0029] The inappropriate text detection system according to the embodiment includes a text analysis unit, an ethics evaluation unit, an inappropriate text detection unit, a warning message generation unit, and an alert display unit. The text analysis unit allows the generation AI to analyze word usage patterns. For example, the generation AI analyzes word usage patterns in input text to detect offensive language, discriminatory expressions, violent content, and the like. The generation AI can also identify word usage patterns using frequency analysis and co-occurrence analysis. The ethics evaluation unit allows the generation AI to evaluate text based on general ethical principles. For example, the generation AI detects content that may harm others or violate their privacy. The generation AI can also evaluate text based on AI ethics guidelines and legal regulations. The inappropriate text detection unit detects inappropriate content from the text analyzed and evaluated by the text analysis unit and the ethics evaluation unit. For example, the generation AI detects offensive comments, discriminatory remarks, violent messages, and the like. The generation AI can also reference a database of past inappropriate text to detect similar patterns. The warning message generation unit generates a warning message based on the inappropriate content detected by the inappropriate text detection unit. For example, the generation AI generates a message such as, "This message contains inappropriate content. Please check the content before sending." The generation AI can also refer to the user's past behavioral history and generate individually customized warning messages. The alert display unit displays the warning message generated by the warning message generation unit to the user. For example, the generation AI displays the warning message using a pop-up display or a notification message. The generation AI can also apply the warning message to voice input and video chat content and generate multimodal alerts. As a result, the inappropriate text detection system according to the embodiment can detect inappropriate text and interactions and alert the user as a warning message, thereby helping to prevent damage.

[0030] The text analysis unit analyzes a user's past speech history and learns patterns of specific word usage to perform individually customized analysis. For example, the generation AI collects a user's past speech history and identifies frequently used words and phrases. For example, if a particular user tends to frequently use offensive language, the system learns that pattern and predicts future speech. The text analysis unit also analyzes patterns of words used in specific situations and contexts based on the user's speech history. For example, the system identifies a tendency for aggressive language to increase in stressful situations and learns that pattern. The generation AI also analyzes a user's speech history and learns the frequency and combination of specific words. For example, if a particular phrase is used frequently, the system increases the likelihood that the phrase contains inappropriate content. This enables individually customized analysis based on the user's past speech history, enabling more accurate detection of inappropriate text.

[0031] The text analysis unit can understand the context of text in real time and analyze word usage patterns according to the context. For example, the text analysis unit analyzes the context of text input by the generative AI in real time and identifies word usage patterns according to the context. For example, it predicts the possibility of offensive language being used based on the flow of conversation or topic. The text analysis unit also analyzes the context of text in real time and learns patterns of language used in specific contexts. For example, it identifies a tendency for offensive language to increase in situations where discussions become heated and learns that pattern. The text analysis unit also allows the generative AI to understand the context of text in real time and analyze word usage patterns according to the context. For example, it identifies patterns of language used in specific topics or situations and learns that pattern. This allows the system to understand the context of text in real time and analyze word usage patterns according to the context, making it possible to more accurately detect inappropriate text.

[0032] The text analysis unit can also be applied to the content of voice input or video chat to analyze multimodal language usage patterns. The text analysis unit, for example, analyzes the content of voice input or video chat to identify language usage patterns. For example, it uses voice recognition technology to convert voice data into text in real time and analyzes language usage patterns. The text analysis unit also analyzes the content of video chat to identify language usage patterns. For example, it uses video analysis technology to analyze a user's facial expressions and gestures to identify language usage patterns. The text analysis unit also analyzes the content of voice input or video chat to identify multimodal language usage patterns. For example, it integrates voice data and video data to analyze language usage patterns. This makes it possible to detect a wider range of inappropriate text by applying it to the content of voice input or video chat to analyze multimodal language usage patterns.

[0033] The text analysis unit can analyze word usage patterns in different languages ​​and cultural spheres to detect inappropriate text from a global perspective. For example, the text analysis unit analyzes word usage patterns in different languages ​​and cultural spheres to detect inappropriate text from a global perspective. For example, multilingual generative AI is used to identify inappropriate expressions in different languages. The text analysis unit also analyzes word usage patterns in different cultural spheres to detect inappropriate text taking cultural background into consideration. For example, expressions that are considered offensive in a particular cultural sphere are identified and those patterns are learned. The text analysis unit also analyzes word usage patterns in different languages ​​and cultural spheres to detect inappropriate text from a global perspective. For example, discriminatory expressions and violent content in different languages ​​are identified. This enables the detection of a wider range of inappropriate text by analyzing word usage patterns in different languages ​​and cultural spheres to detect inappropriate text from a global perspective.

[0034] The ethical evaluation unit automatically updates the latest ethical principles and laws and regulations, allowing it to always evaluate text using the latest standards. For example, the ethical evaluation unit could build a system in which the generation AI automatically collects and updates the latest ethical principles and laws and regulations. For example, it could periodically check laws and regulations and ethical guidelines and update the generation AI's evaluation criteria. The ethical evaluation unit could also automatically update the latest ethical principles and laws and regulations, allowing the generation AI to always evaluate text using the latest standards. For example, when new laws and regulations come into effect, their contents could be reflected immediately. The ethical evaluation unit could also develop a system in which the generation AI automatically updates the latest ethical principles and laws and regulations, allowing it to always evaluate text using the latest standards. For example, it could reference a database of laws and regulations that is publicly available online. This would allow the latest ethical principles and laws and regulations to be automatically updated, allowing text to be evaluated using the latest standards, enabling more appropriate detection of inappropriate text.

[0035] The ethical evaluation unit can learn the user's individual ethics and values ​​and perform an individually customized ethical evaluation. For example, the ethical evaluation unit constructs a system in which a generation AI learns the user's individual ethics and values ​​and performs an individually customized ethical evaluation. For example, it identifies ethics based on the user's past actions and statements. The ethical evaluation unit also learns the user's individual ethics and values ​​and the generation AI performs an individually customized ethical evaluation. For example, it identifies the ethical principles that the user values ​​and evaluates based on those standards. The ethical evaluation unit also develops a system in which a generation AI learns the user's individual ethics and values ​​and performs an individually customized ethical evaluation. For example, it adjusts the ethics based on user feedback. In this way, by learning the user's individual ethics and values ​​and performing an individually customized ethical evaluation, it becomes possible to more appropriately detect inappropriate text.

[0036] The inappropriate text detection unit can refer to a database of past inappropriate text and detect similar patterns. For example, the generation AI of the inappropriate text detection unit references a database of past inappropriate text and builds a system to detect similar patterns. For example, it identifies offensive words and phrases based on past data. The inappropriate text detection unit also references a database of inappropriate text and the generation AI detects similar patterns. For example, it identifies similar content based on past discriminatory remarks or violent messages. The inappropriate text detection unit also develops a system in which the generation AI references a database of past inappropriate text and detects similar patterns. For example, it identifies inappropriate content based on past data and displays a warning. This makes it possible to detect inappropriate text with greater accuracy by referring to a database of past inappropriate text and detecting similar patterns.

[0037] The inappropriate text detection unit has a deep understanding of the context of the text and is able to detect inappropriate content based on the context. For example, the inappropriate text detection unit constructs a system in which the generation AI has a deep understanding of the context of the text and detects inappropriate content based on the context. For example, it identifies inappropriate content based on the flow of the conversation or topic. The inappropriate text detection unit also analyzes the context of the text and the generation AI detects inappropriate content based on the context. For example, it identifies offensive words and phrases used in a specific context. The inappropriate text detection unit also develops a system in which the generation AI has a deep understanding of the context of the text and detects inappropriate content based on the context. For example, it identifies inappropriate content by taking into account the background and situation of the conversation. This enables more accurate detection of inappropriate text by having a deep understanding of the context of the text and detecting inappropriate content based on the context.

[0038] The inappropriate text detection unit can also be applied to the content of voice input and video chat, allowing for multimodal inappropriate text detection. The inappropriate text detection unit, for example, analyzes the content of voice input and video chat to build a system that detects inappropriate text. For example, voice data is converted into text in real time using voice recognition technology, and inappropriate content is identified. The inappropriate text detection unit also analyzes the content of video chat to detect inappropriate text. For example, video analysis technology is used to analyze a user's facial expressions and gestures to identify inappropriate content. The inappropriate text detection unit also analyzes the content of voice input and video chat to perform multimodal inappropriate text detection. For example, voice data and video data are integrated to identify inappropriate content. This allows for multimodal inappropriate text detection by also applying the inappropriate text detection unit to the content of voice input and video chat, enabling a wider range of inappropriate text to be detected.

[0039] The inappropriate text detection unit can detect inappropriate text in different languages ​​and cultural spheres and perform detection from a global perspective. For example, the inappropriate text detection unit builds a system that detects inappropriate text in different languages ​​and cultural spheres and performs detection from a global perspective. For example, a multilingual generation AI is used to identify inappropriate expressions in different languages. The inappropriate text detection unit also detects inappropriate text in different cultural spheres and performs detection taking cultural background into consideration. For example, it identifies expressions that are considered offensive in a specific cultural sphere and learns those patterns. The inappropriate text detection unit also detects inappropriate text in different languages ​​and cultural spheres and performs detection from a global perspective. For example, it identifies discriminatory expressions and violent content in different languages. This makes it possible to detect inappropriate text in different languages ​​and cultural spheres and perform detection from a global perspective, making it possible to detect a wider range of inappropriate text.

[0040] The warning message generation unit can refer to a user's past behavioral history and generate individually customized warning messages. The warning message generation unit, for example, builds a system in which a generation AI refers to a user's past behavioral history and generates individually customized warning messages. For example, a special warning is displayed for users who have made offensive remarks in the past. The warning message generation unit also generates individually customized warning messages based on the user's behavioral history. For example, a user who frequently uses specific words or phrases is encouraged to refrain from using those words. The warning message generation unit also develops a system in which a generation AI refers to a user's past behavioral history and generates individually customized warning messages. For example, an appropriate warning is displayed based on past behavior patterns. This makes it possible to display more appropriate warnings by referencing a user's past behavioral history and generating individually customized warning messages.

[0041] The warning message generation unit can understand the context of the text in real time and generate a warning message that is appropriate for the context. For example, the warning message generation unit builds a system in which a generation AI understands the context of the text in real time and generates a warning message that is appropriate for the context. For example, an appropriate warning is displayed based on the flow of the conversation or the topic. The warning message generation unit also analyzes the context of the text in real time and the generation AI generates a warning message that is appropriate for the context. For example, a warning is displayed for offensive language used in a specific context. The warning message generation unit also develops a system in which a generation AI understands the context of the text in real time and generates a warning message that is appropriate for the context. For example, an appropriate warning is displayed taking into account the background and situation of the conversation. This makes it possible to display more appropriate warnings by understanding the context of the text in real time and generating a warning message that is appropriate for the context.

[0042] The warning message generation unit can also be applied to the content of voice input and video chat, allowing for multimodal warnings. The warning message generation unit, for example, analyzes the content of voice input and video chat and builds a system that generates a warning message. For example, it uses voice recognition technology to convert voice data into text in real time and display an appropriate warning. The warning message generation unit also analyzes the content of video chat and generates a warning message. For example, it uses video analysis technology to analyze a user's facial expressions and gestures and display an appropriate warning. The warning message generation unit also analyzes the content of voice input and video chat and generates a multimodal warning message. For example, it integrates voice data and video data and displays an appropriate warning. This allows for the generation of a multimodal warning message that can also be applied to the content of voice input and video chat, making it possible to display a wider range of warnings.

[0043] The warning message generation unit generates warning messages that are compatible with different languages ​​and cultural spheres, allowing for warnings from a global perspective. The warning message generation unit, for example, generates warning messages that are compatible with different languages ​​and cultural spheres, building a system that provides warnings from a global perspective. For example, a multilingual generation AI is used to display warnings in different languages. The warning message generation unit also generates warning messages that are compatible with different cultural spheres, providing warnings that take cultural backgrounds into consideration. For example, it displays appropriate warnings for expressions that are problematic in specific cultural spheres. The warning message generation unit also generates warning messages that are compatible with different languages ​​and cultural spheres, providing warnings from a global perspective. For example, it displays warnings for discriminatory expressions or violent content in different languages. In this way, by generating warning messages that are compatible with different languages ​​and cultural spheres and providing warnings from a global perspective, it becomes possible to display a wider range of warnings.

[0044] The alert display unit can reference a user's past behavioral history and generate individually customized alerts. For example, the alert display unit builds a system in which a generation AI references a user's past behavioral history and generates individually customized alerts. For example, a special warning is displayed for users who have made offensive remarks in the past. The alert display unit also builds a system in which the generation AI generates individually customized alerts based on the user's behavioral history. For example, a user who frequently uses specific words or phrases is encouraged to refrain from using those words. The alert display unit also develops a system in which the generation AI references a user's past behavioral history and generates individually customized alerts. For example, an appropriate warning is displayed based on past behavior patterns. This makes it possible to display more appropriate alerts by referencing a user's past behavioral history and generating individually customized alerts.

[0045] The alert display unit is capable of understanding the context of text in real time and generating alerts appropriate to the context. For example, the alert display unit constructs a system in which a generation AI understands the context of text in real time and generates alerts appropriate to the context. For example, it displays an appropriate alert based on the flow of conversation or topic. The alert display unit also analyzes the context of text in real time and the generation AI generates an alert appropriate to the context. For example, it displays a warning for offensive language used in a specific context. The alert display unit also develops a system in which a generation AI understands the context of text in real time and generates alerts appropriate to the context. For example, it displays an appropriate alert taking into account the background and situation of the conversation. This makes it possible to display more appropriate alerts by understanding the context of text in real time and generating alerts appropriate to the context.

[0046] The alert display unit can also be applied to the content of voice input and video chat, allowing for multimodal alerts. The alert display unit, for example, builds a system that analyzes the content of voice input and video chat and generates alerts. For example, it uses voice recognition technology to convert voice data into text in real time and display an appropriate alert. The alert display unit also analyzes the content of video chat and generates an alert. For example, it uses video analysis technology to analyze a user's facial expressions and gestures and display an appropriate alert. The alert display unit also analyzes the content of voice input and video chat and generates a multimodal alert. For example, it integrates voice data and video data and displays an appropriate alert. This allows for application to the content of voice input and video chat, allowing for the generation of multimodal alerts, making it possible to display a wider range of alerts.

[0047] The alert display unit generates alerts that correspond to different languages ​​and cultural spheres, and can provide alerts from a global perspective. The alert display unit, for example, builds a system that generates alerts that correspond to different languages ​​and cultural spheres, and provides alerts from a global perspective. For example, a multilingual generation AI is used to display alerts in different languages. The alert display unit also generates alerts that correspond to different cultural spheres, and provides alerts that take cultural background into consideration. For example, it displays appropriate alerts for expressions that are problematic in a particular cultural sphere. The alert display unit also generates alerts that correspond to different languages ​​and cultural spheres, and provides alerts from a global perspective. For example, it displays alerts for discriminatory expressions or violent content in different languages. In this way, by generating alerts that correspond to different languages ​​and cultural spheres, and providing alerts from a global perspective, it becomes possible to display a wider range of alerts.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The inappropriate text detection system can also provide personalized feedback based on a user's behavioral history. For example, it can record the inappropriate comments a user has made in the past and analyze those trends to provide specific advice to prevent similar comments in the future. Furthermore, if a user improves, it can provide feedback on their progress and provide positive reinforcement. Furthermore, it can analyze the types of comments a user is likely to make in specific situations and provide specific advice tailored to those situations. This allows users to reflect on their behavior and receive specific help to improve.

[0050] The inappropriate text detection system can also provide real-time feedback on user comments. For example, when a user types an offensive word, it can immediately display a warning and suggest alternative expressions. Also, when a user makes a positive comment, it can immediately display a message of praise to encourage positive behavior. Furthermore, when a user comments on a specific topic, it can also suggest appropriate expressions related to that topic. This allows users to review and improve their comments in real time.

[0051] The inappropriate text detection system can also provide long-term feedback on user comments. For example, it can record what users have said in the past and analyze those trends to provide specific advice for long-term improvement. Furthermore, if a user improves, it can provide feedback on their progress and provide positive reinforcement. Furthermore, it can analyze what comments a user is likely to make in specific situations and provide specific advice tailored to those situations. This allows users to reflect on their own behavior and receive specific help for long-term improvement.

[0052] The inappropriate text detection system can also provide context-based feedback to a user's comments. For example, when a user makes a comment about a specific topic, the system can suggest appropriate expressions related to that topic. It can also provide specific advice to a user when the user makes a comment in a specific situation. This allows the user to receive specific help to review and improve their comments.

[0053] The inappropriate text detection system can also have a feedback function that takes into account the cultural background of the user's utterances. For example, when a user communicates with people from a different culture, the system can suggest appropriate expressions that are appropriate for that culture. Also, when a user communicates with people from a particular cultural background, the system can provide specific advice that is appropriate for that background. Furthermore, when a user communicates with people from a different culture, the system can provide specific advice that is appropriate for that culture. This allows the user to receive specific help in communicating appropriately with people from different cultures.

[0054] The inappropriate text detection system can also be equipped with a feedback function that takes into account the long-term cultural background of a user's utterances. For example, when a user communicates with people from a different culture, the system can suggest appropriate expressions for that culture. It can also provide specific advice tailored to a user's cultural background when the user communicates with people from a specific cultural background. In this way, the user can receive specific help in communicating appropriately with people from different cultures.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The text analysis unit uses generative AI to analyze word usage patterns. For example, it analyzes word usage patterns in the input text to detect offensive language, discriminatory expressions, violent content, etc. It can also identify word usage patterns using frequency analysis and co-occurrence analysis. Step 2: The ethical evaluation unit uses generative AI to evaluate the text based on general ethical principles, such as detecting content that may harm others or violate their privacy. It can also evaluate the text based on AI ethical guidelines and legal regulations. Step 3: The inappropriate text detection unit detects inappropriate content from the text analyzed and evaluated by the text analysis unit and the ethical evaluation unit. For example, it detects offensive comments, discriminatory remarks, violent messages, etc. It can also refer to a database of past inappropriate text to detect similar patterns. Step 4: The warning message generator generates a warning message based on the inappropriate content detected by the inappropriate text detector. For example, it generates a message such as "This message contains inappropriate content. Please check the content before sending." It can also generate individually customized warning messages by referring to the user's past behavior history. Step 5: The alert display unit displays the warning message generated by the warning message generation unit to the user. For example, the warning message may be displayed using a pop-up display or a notification message. It is also possible to apply the warning message to voice input and video chat content, thereby generating a multimodal alert.

[0057] (Example 2) The inappropriate text detection system according to the embodiment of the present invention is a system that uses a generation AI to detect inappropriate text or interactions and issues an alert to the user as a warning message. As a result, the inappropriate text detection system warns the user of inappropriate text or interactions, and can be useful in preventing damage.

[0058] The inappropriate text detection system according to the embodiment includes a text analysis unit, an ethics evaluation unit, an inappropriate text detection unit, a warning message generation unit, and an alert display unit. The text analysis unit allows the generation AI to analyze word usage patterns. For example, the generation AI analyzes word usage patterns in input text to detect offensive language, discriminatory expressions, violent content, and the like. The generation AI can also identify word usage patterns using frequency analysis and co-occurrence analysis. The ethics evaluation unit allows the generation AI to evaluate text based on general ethical principles. For example, the generation AI detects content that may harm others or violate their privacy. The generation AI can also evaluate text based on AI ethics guidelines and legal regulations. The inappropriate text detection unit detects inappropriate content from the text analyzed and evaluated by the text analysis unit and the ethics evaluation unit. For example, the generation AI detects offensive comments, discriminatory remarks, violent messages, and the like. The generation AI can also reference a database of past inappropriate text to detect similar patterns. The warning message generation unit generates a warning message based on the inappropriate content detected by the inappropriate text detection unit. For example, the generation AI generates a message such as, "This message contains inappropriate content. Please check the content before sending." The generation AI can also refer to the user's past behavioral history and generate individually customized warning messages. The alert display unit displays the warning message generated by the warning message generation unit to the user. For example, the generation AI displays the warning message using a pop-up display or a notification message. The generation AI can also apply the warning message to voice input and video chat content and generate multimodal alerts. As a result, the inappropriate text detection system according to the embodiment can detect inappropriate text and interactions and alert the user as a warning message, thereby helping to prevent damage.

[0059] The text analysis unit analyzes a user's past speech history and learns patterns of specific word usage to perform individually customized analysis. For example, the generation AI collects a user's past speech history and identifies frequently used words and phrases. For example, if a particular user tends to frequently use offensive language, the system learns that pattern and predicts future speech. The text analysis unit also analyzes patterns of words used in specific situations and contexts based on the user's speech history. For example, the system identifies a tendency for aggressive language to increase in stressful situations and learns that pattern. The generation AI also analyzes a user's speech history and learns the frequency and combination of specific words. For example, if a particular phrase is used frequently, the system increases the likelihood that the phrase contains inappropriate content. This enables individually customized analysis based on the user's past speech history, enabling more accurate detection of inappropriate text.

[0060] The text analysis unit can understand the context of text in real time and analyze word usage patterns according to the context. For example, the text analysis unit analyzes the context of text input by the generative AI in real time and identifies word usage patterns according to the context. For example, it predicts the possibility of offensive language being used based on the flow of conversation or topic. The text analysis unit also analyzes the context of text in real time and learns patterns of language used in specific contexts. For example, it identifies a tendency for offensive language to increase in situations where discussions become heated and learns that pattern. The text analysis unit also allows the generative AI to understand the context of text in real time and analyze word usage patterns according to the context. For example, it identifies patterns of language used in specific topics or situations and learns that pattern. This allows the system to understand the context of text in real time and analyze word usage patterns according to the context, making it possible to more accurately detect inappropriate text.

[0061] The text analysis unit can use the emotion estimation function to analyze the user's emotional state and identify patterns of emotion-based word usage. The text analysis unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and identify patterns of emotion-based word usage. For example, it identifies a tendency for aggressive language to increase in situations of increased anger or stress. The text analysis unit also analyzes the user's emotional state and learns patterns of emotion-based word usage. For example, it identifies a tendency for calm language to be used in positive emotional states and learns this pattern. The text analysis unit also uses the emotion estimation function to analyze the user's emotional state and identify patterns of emotion-based word usage. For example, it identifies a tendency for aggressive language to increase in negative emotional states and learns this pattern. In this way, by using the emotion estimation function to analyze the user's emotional state and identify patterns of emotion-based word usage, it is possible to detect inappropriate text with higher accuracy.

[0062] The text analysis unit can also be applied to the content of voice input or video chat to analyze multimodal language usage patterns. The text analysis unit, for example, analyzes the content of voice input or video chat to identify language usage patterns. For example, it uses voice recognition technology to convert voice data into text in real time and analyzes language usage patterns. The text analysis unit also analyzes the content of video chat to identify language usage patterns. For example, it uses video analysis technology to analyze a user's facial expressions and gestures to identify language usage patterns. The text analysis unit also analyzes the content of voice input or video chat to identify multimodal language usage patterns. For example, it integrates voice data and video data to analyze language usage patterns. This makes it possible to detect a wider range of inappropriate text by applying it to the content of voice input or video chat to analyze multimodal language usage patterns.

[0063] The text analysis unit can analyze word usage patterns in different languages ​​and cultural spheres to detect inappropriate text from a global perspective. For example, the text analysis unit analyzes word usage patterns in different languages ​​and cultural spheres to detect inappropriate text from a global perspective. For example, multilingual generative AI is used to identify inappropriate expressions in different languages. The text analysis unit also analyzes word usage patterns in different cultural spheres to detect inappropriate text taking cultural background into consideration. For example, expressions that are considered offensive in a particular cultural sphere are identified and those patterns are learned. The text analysis unit also analyzes word usage patterns in different languages ​​and cultural spheres to detect inappropriate text from a global perspective. For example, discriminatory expressions and violent content in different languages ​​are identified. This enables the detection of a wider range of inappropriate text by analyzing word usage patterns in different languages ​​and cultural spheres to detect inappropriate text from a global perspective.

[0064] The ethical evaluation unit automatically updates the latest ethical principles and laws and regulations, allowing it to always evaluate text using the latest standards. For example, the ethical evaluation unit could build a system in which the generation AI automatically collects and updates the latest ethical principles and laws and regulations. For example, it could periodically check laws and regulations and ethical guidelines and update the generation AI's evaluation criteria. The ethical evaluation unit could also automatically update the latest ethical principles and laws and regulations, allowing the generation AI to always evaluate text using the latest standards. For example, when new laws and regulations come into effect, their contents could be reflected immediately. The ethical evaluation unit could also develop a system in which the generation AI automatically updates the latest ethical principles and laws and regulations, allowing it to always evaluate text using the latest standards. For example, it could reference a database of laws and regulations that is publicly available online. This would allow the latest ethical principles and laws and regulations to be automatically updated, allowing text to be evaluated using the latest standards, enabling more appropriate detection of inappropriate text.

[0065] The ethical evaluation unit can learn the user's individual ethics and values ​​and perform an individually customized ethical evaluation. For example, the ethical evaluation unit constructs a system in which a generation AI learns the user's individual ethics and values ​​and performs an individually customized ethical evaluation. For example, it identifies ethics based on the user's past actions and statements. The ethical evaluation unit also learns the user's individual ethics and values ​​and the generation AI performs an individually customized ethical evaluation. For example, it identifies the ethical principles that the user values ​​and evaluates based on those standards. The ethical evaluation unit also develops a system in which a generation AI learns the user's individual ethics and values ​​and performs an individually customized ethical evaluation. For example, it adjusts the ethics based on user feedback. In this way, by learning the user's individual ethics and values ​​and performing an individually customized ethical evaluation, it becomes possible to more appropriately detect inappropriate text.

[0066] The ethical evaluation unit can use the emotion estimation function to consider the emotional state of the user and perform an emotion-based ethical evaluation. The ethical evaluation unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and perform an emotion-based ethical evaluation. For example, it particularly carefully evaluates statements made in situations where anger or stress is high. The ethical evaluation unit also builds a system that considers the user's emotional state and performs an emotion-based ethical evaluation. For example, it identifies ethically questionable statements made when negative emotions are strong. The ethical evaluation unit also uses the emotion estimation function to consider the user's emotional state and perform an emotion-based ethical evaluation. For example, it identifies a tendency for ethically acceptable statements to be more common when the emotional state is positive. As a result, by using the emotion estimation function to consider the user's emotional state and perform an emotion-based ethical evaluation, more appropriate detection of inappropriate text is possible.

[0067] The inappropriate text detection unit can refer to a database of past inappropriate text and detect similar patterns. For example, the generation AI of the inappropriate text detection unit references a database of past inappropriate text and builds a system to detect similar patterns. For example, it identifies offensive words and phrases based on past data. The inappropriate text detection unit also references a database of inappropriate text and the generation AI detects similar patterns. For example, it identifies similar content based on past discriminatory remarks or violent messages. The inappropriate text detection unit also develops a system in which the generation AI references a database of past inappropriate text and detects similar patterns. For example, it identifies inappropriate content based on past data and displays a warning. This makes it possible to detect inappropriate text with greater accuracy by referring to a database of past inappropriate text and detecting similar patterns.

[0068] The inappropriate text detection unit has a deep understanding of the context of the text and is able to detect inappropriate content based on the context. For example, the inappropriate text detection unit constructs a system in which the generation AI has a deep understanding of the context of the text and detects inappropriate content based on the context. For example, it identifies inappropriate content based on the flow of the conversation or topic. The inappropriate text detection unit also analyzes the context of the text and the generation AI detects inappropriate content based on the context. For example, it identifies offensive words and phrases used in a specific context. The inappropriate text detection unit also develops a system in which the generation AI has a deep understanding of the context of the text and detects inappropriate content based on the context. For example, it identifies inappropriate content by taking into account the background and situation of the conversation. This enables more accurate detection of inappropriate text by having a deep understanding of the context of the text and detecting inappropriate content based on the context.

[0069] The inappropriate text detection unit can use the emotion estimation function to analyze the emotional state of a user and detect emotion-based inappropriate text. The inappropriate text detection unit, for example, uses the emotion estimation function to analyze the emotional state of a user in real time and build a system to detect emotion-based inappropriate text. For example, it particularly carefully evaluates statements made in situations where anger or stress is high. The inappropriate text detection unit also analyzes the emotional state of a user and detects emotion-based inappropriate text. For example, it identifies inappropriate content when negative emotions are strong. The inappropriate text detection unit also uses the emotion estimation function to analyze the emotional state of a user and detect emotion-based inappropriate text. For example, it identifies a tendency for inappropriate content to be less prevalent in positive emotional states. This enables more accurate detection of inappropriate text by using the emotion estimation function to analyze the emotional state of a user and detect emotion-based inappropriate text.

[0070] The inappropriate text detection unit can also be applied to the content of voice input and video chat, allowing for multimodal inappropriate text detection. The inappropriate text detection unit, for example, analyzes the content of voice input and video chat to build a system that detects inappropriate text. For example, voice data is converted into text in real time using voice recognition technology, and inappropriate content is identified. The inappropriate text detection unit also analyzes the content of video chat to detect inappropriate text. For example, video analysis technology is used to analyze a user's facial expressions and gestures to identify inappropriate content. The inappropriate text detection unit also analyzes the content of voice input and video chat to perform multimodal inappropriate text detection. For example, voice data and video data are integrated to identify inappropriate content. This allows for multimodal inappropriate text detection by also applying the inappropriate text detection unit to the content of voice input and video chat, enabling a wider range of inappropriate text to be detected.

[0071] The inappropriate text detection unit can detect inappropriate text in different languages ​​and cultural spheres and perform detection from a global perspective. For example, the inappropriate text detection unit builds a system that detects inappropriate text in different languages ​​and cultural spheres and performs detection from a global perspective. For example, a multilingual generation AI is used to identify inappropriate expressions in different languages. The inappropriate text detection unit also detects inappropriate text in different cultural spheres and performs detection taking cultural background into consideration. For example, it identifies expressions that are considered offensive in a specific cultural sphere and learns those patterns. The inappropriate text detection unit also detects inappropriate text in different languages ​​and cultural spheres and performs detection from a global perspective. For example, it identifies discriminatory expressions and violent content in different languages. This makes it possible to detect inappropriate text in different languages ​​and cultural spheres and perform detection from a global perspective, making it possible to detect a wider range of inappropriate text.

[0072] The inappropriate text detection unit uses the emotion estimation function to analyze the emotion of the user when entering text in real time, thereby preventing the entry of inappropriate text. For example, the inappropriate text detection unit uses the emotion estimation function to analyze the emotion of the user when entering text in real time, thereby building a system that prevents the entry of inappropriate text. For example, a warning is displayed when a negative emotion is detected. The inappropriate text detection unit also analyzes the user's emotional state in real time and prevents the entry of inappropriate text. For example, if the emotion score is low, inappropriate content is identified and a warning is displayed. The inappropriate text detection unit also uses the emotion estimation function to analyze the emotion of the user when entering text in real time, thereby preventing the entry of inappropriate text. For example, it suggests word choices that enhance positive emotions. In this way, by using the emotion estimation function to analyze the emotion of the user when entering text in real time and preventing the entry of inappropriate text, more accurate detection of inappropriate text is possible.

[0073] The warning message generation unit can refer to a user's past behavioral history and generate individually customized warning messages. The warning message generation unit, for example, builds a system in which a generation AI refers to a user's past behavioral history and generates individually customized warning messages. For example, a special warning is displayed for users who have made offensive remarks in the past. The warning message generation unit also generates individually customized warning messages based on the user's behavioral history. For example, a user who frequently uses specific words or phrases is encouraged to refrain from using those words. The warning message generation unit also develops a system in which a generation AI refers to a user's past behavioral history and generates individually customized warning messages. For example, an appropriate warning is displayed based on past behavior patterns. This makes it possible to display more appropriate warnings by referencing a user's past behavioral history and generating individually customized warning messages.

[0074] The warning message generation unit can understand the context of the text in real time and generate a warning message that is appropriate for the context. For example, the warning message generation unit builds a system in which a generation AI understands the context of the text in real time and generates a warning message that is appropriate for the context. For example, an appropriate warning is displayed based on the flow of the conversation or the topic. The warning message generation unit also analyzes the context of the text in real time and the generation AI generates a warning message that is appropriate for the context. For example, a warning is displayed for offensive language used in a specific context. The warning message generation unit also develops a system in which a generation AI understands the context of the text in real time and generates a warning message that is appropriate for the context. For example, an appropriate warning is displayed taking into account the background and situation of the conversation. This makes it possible to display more appropriate warnings by understanding the context of the text in real time and generating a warning message that is appropriate for the context.

[0075] The warning message generation unit can use the emotion estimation function to analyze the emotional state of the user and generate a warning message based on the emotion. The warning message generation unit, for example, uses the emotion estimation function to build a system that analyzes the emotional state of the user in real time and generates a warning message based on the emotion. For example, a special warning is displayed for statements made in situations that increase anger or stress. The warning message generation unit also analyzes the emotional state of the user and generates a warning message based on the emotion. For example, a message urging the user to stay calm when negative emotions are strong is displayed. The warning message generation unit also uses the emotion estimation function to analyze the emotional state of the user and generate a warning message based on the emotion. For example, an encouraging message that strengthens positive emotions is displayed. In this way, by using the emotion estimation function to analyze the emotional state of the user and generate a warning message based on the emotion, it is possible to display a more appropriate warning.

[0076] The warning message generation unit can also be applied to the content of voice input and video chat, allowing for multimodal warnings. The warning message generation unit, for example, analyzes the content of voice input and video chat and builds a system that generates a warning message. For example, it uses voice recognition technology to convert voice data into text in real time and display an appropriate warning. The warning message generation unit also analyzes the content of video chat and generates a warning message. For example, it uses video analysis technology to analyze a user's facial expressions and gestures and display an appropriate warning. The warning message generation unit also analyzes the content of voice input and video chat and generates a multimodal warning message. For example, it integrates voice data and video data and displays an appropriate warning. This allows for the generation of a multimodal warning message that can also be applied to the content of voice input and video chat, making it possible to display a wider range of warnings.

[0077] The warning message generation unit generates warning messages that are compatible with different languages ​​and cultural spheres, allowing for warnings from a global perspective. The warning message generation unit, for example, generates warning messages that are compatible with different languages ​​and cultural spheres, building a system that provides warnings from a global perspective. For example, a multilingual generation AI is used to display warnings in different languages. The warning message generation unit also generates warning messages that are compatible with different cultural spheres, providing warnings that take cultural backgrounds into consideration. For example, it displays appropriate warnings for expressions that are problematic in specific cultural spheres. The warning message generation unit also generates warning messages that are compatible with different languages ​​and cultural spheres, providing warnings from a global perspective. For example, it displays warnings for discriminatory expressions or violent content in different languages. In this way, by generating warning messages that are compatible with different languages ​​and cultural spheres and providing warnings from a global perspective, it becomes possible to display a wider range of warnings.

[0078] The warning message generation unit can use the emotion estimation function to analyze the emotion of the user when entering input in real time and generate a warning message that encourages positive behavior. The warning message generation unit, for example, uses the emotion estimation function to build a system that analyzes the emotion of the user when entering input in real time and generates a warning message that encourages positive behavior. For example, an encouraging message is displayed when a negative emotion is detected. The warning message generation unit also analyzes the user's emotional state in real time and generates a warning message that encourages positive behavior. For example, a message that encourages positive behavior is displayed when the emotion score is low. The warning message generation unit also uses the emotion estimation function to analyze the emotion of the user when entering input in real time and generate a warning message that encourages positive behavior. For example, an encouraging message that strengthens positive emotions is displayed. In this way, by using the emotion estimation function to analyze the emotion of the user when entering input in real time and generating a warning message that encourages positive behavior, it is possible to display a more appropriate warning.

[0079] The alert display unit can reference a user's past behavioral history and generate individually customized alerts. For example, the alert display unit builds a system in which a generation AI references a user's past behavioral history and generates individually customized alerts. For example, a special warning is displayed for users who have made offensive remarks in the past. The alert display unit also builds a system in which the generation AI generates individually customized alerts based on the user's behavioral history. For example, a user who frequently uses specific words or phrases is encouraged to refrain from using those words. The alert display unit also develops a system in which the generation AI references a user's past behavioral history and generates individually customized alerts. For example, an appropriate warning is displayed based on past behavior patterns. This makes it possible to display more appropriate alerts by referencing a user's past behavioral history and generating individually customized alerts.

[0080] The alert display unit is capable of understanding the context of text in real time and generating alerts appropriate to the context. For example, the alert display unit constructs a system in which a generation AI understands the context of text in real time and generates alerts appropriate to the context. For example, it displays an appropriate alert based on the flow of conversation or topic. The alert display unit also analyzes the context of text in real time and the generation AI generates an alert appropriate to the context. For example, it displays a warning for offensive language used in a specific context. The alert display unit also develops a system in which a generation AI understands the context of text in real time and generates alerts appropriate to the context. For example, it displays an appropriate alert taking into account the background and situation of the conversation. This makes it possible to display more appropriate alerts by understanding the context of text in real time and generating alerts appropriate to the context.

[0081] The alert display unit can use the emotion estimation function to analyze the user's emotional state and generate an alert based on the emotion. The alert display unit, for example, uses the emotion estimation function to build a system that analyzes the user's emotional state in real time and generates an alert based on the emotion. For example, a special alert is displayed for statements made in situations that increase anger or stress. The alert display unit also analyzes the user's emotional state and generates an alert based on the emotion. For example, a message urging the user to stay calm when negative emotions are strong is displayed. The alert display unit also uses the emotion estimation function to analyze the user's emotional state and generate an alert based on the emotion. For example, an encouraging message that strengthens positive emotions is displayed. In this way, by using the emotion estimation function to analyze the user's emotional state and generate an alert based on the emotion, it is possible to display more appropriate alerts.

[0082] The alert display unit can also be applied to the content of voice input and video chat, allowing for multimodal alerts. The alert display unit, for example, builds a system that analyzes the content of voice input and video chat and generates alerts. For example, it uses voice recognition technology to convert voice data into text in real time and display an appropriate alert. The alert display unit also analyzes the content of video chat and generates an alert. For example, it uses video analysis technology to analyze a user's facial expressions and gestures and display an appropriate alert. The alert display unit also analyzes the content of voice input and video chat and generates a multimodal alert. For example, it integrates voice data and video data and displays an appropriate alert. This allows for application to the content of voice input and video chat, allowing for the generation of multimodal alerts, making it possible to display a wider range of alerts.

[0083] The alert display unit generates alerts that correspond to different languages ​​and cultural spheres, and can provide alerts from a global perspective. The alert display unit, for example, builds a system that generates alerts that correspond to different languages ​​and cultural spheres, and provides alerts from a global perspective. For example, a multilingual generation AI is used to display alerts in different languages. The alert display unit also generates alerts that correspond to different cultural spheres, and provides alerts that take cultural background into consideration. For example, it displays appropriate alerts for expressions that are problematic in a particular cultural sphere. The alert display unit also generates alerts that correspond to different languages ​​and cultural spheres, and provides alerts from a global perspective. For example, it displays alerts for discriminatory expressions or violent content in different languages. In this way, by generating alerts that correspond to different languages ​​and cultural spheres, and providing alerts from a global perspective, it becomes possible to display a wider range of alerts.

[0084] The alert display unit can use the emotion estimation function to analyze the emotion of the user when entering data in real time and generate an alert that promotes positive behavior. The alert display unit, for example, uses the emotion estimation function to build a system that analyzes the emotion of the user when entering data in real time and generates an alert that promotes positive behavior. For example, an encouraging message is displayed when a negative emotion is detected. The alert display unit also analyzes the user's emotional state in real time and generates an alert that promotes positive behavior. For example, a message that promotes positive behavior is displayed when the emotion score is low. The alert display unit also uses the emotion estimation function to analyze the emotion of the user when entering data in real time and generate an alert that promotes positive behavior. For example, an encouraging message that strengthens positive emotions is displayed. This makes it possible to display more appropriate warnings by using the emotion estimation function to analyze the emotion of the user when entering data in real time and generate an alert that promotes positive behavior.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] The inappropriate text detection system can also provide personalized feedback based on a user's behavioral history. For example, it can record the inappropriate comments a user has made in the past and analyze those trends to provide specific advice to prevent similar comments in the future. Furthermore, if a user improves, it can provide feedback on their progress and provide positive reinforcement. Furthermore, it can analyze the types of comments a user is likely to make in specific situations and provide specific advice tailored to those situations. This allows users to reflect on their behavior and receive specific help to improve.

[0087] The inappropriate text detection system can also provide real-time feedback on user comments. For example, when a user types an offensive word, it can immediately display a warning and suggest alternative expressions. Also, when a user makes a positive comment, it can immediately display a message of praise to encourage positive behavior. Furthermore, when a user comments on a specific topic, it can also suggest appropriate expressions related to that topic. This allows users to review and improve their comments in real time.

[0088] The inappropriate text detection system can also provide feedback that takes into account the user's emotional state. For example, if the user is feeling stressed, the system can provide advice on how to relax. If the user is feeling angry, the system can suggest specific ways to control those emotions. Furthermore, if the user is feeling positive, the system can provide advice on how to maintain those positive emotions. This allows the user to understand their emotional state and receive specific help to deal with it appropriately.

[0089] The inappropriate text detection system can also provide long-term feedback on user comments. For example, it can record what users have said in the past and analyze those trends to provide specific advice for long-term improvement. Furthermore, if a user improves, it can provide feedback on their progress and provide positive reinforcement. Furthermore, it can analyze what comments a user is likely to make in specific situations and provide specific advice tailored to those situations. This allows users to reflect on their own behavior and receive specific help for long-term improvement.

[0090] The inappropriate text detection system can also analyze the user's emotional state in real time and provide feedback based on that emotion. For example, if the user is feeling negative emotions, the system can provide specific advice to alleviate those emotions. Alternatively, if the user is feeling positive emotions, the system can provide advice to maintain those emotions. Furthermore, if the user is feeling a specific emotion, the system can provide specific advice according to that emotion. This allows the user to understand their emotional state and receive specific help to deal with it appropriately.

[0091] The inappropriate text detection system can also provide context-based feedback to a user's comments. For example, when a user makes a comment about a specific topic, the system can suggest appropriate expressions related to that topic. It can also provide specific advice to a user when the user makes a comment in a specific situation. This allows the user to receive specific help to review and improve their comments.

[0092] The inappropriate text detection system can also provide context-based feedback that takes into account the user's emotional state. For example, if the user is feeling stressed, the system can provide advice on how to relax. If the user is feeling angry, the system can suggest specific ways to control those emotions. Furthermore, if the user is feeling positive emotions, the system can provide advice on how to maintain those emotions. This allows the user to understand their emotional state and receive specific help to deal with it appropriately.

[0093] The inappropriate text detection system can also have a feedback function that takes into account the cultural background of the user's utterances. For example, when a user communicates with people from a different culture, the system can suggest appropriate expressions that are appropriate for that culture. Also, when a user communicates with people from a particular cultural background, the system can provide specific advice that is appropriate for that background. Furthermore, when a user communicates with people from a different culture, the system can provide specific advice that is appropriate for that culture. This allows the user to receive specific help in communicating appropriately with people from different cultures.

[0094] The inappropriate text detection system can also analyze the user's emotional state in real time and provide feedback based on that emotion, taking into account cultural background. For example, if the user is feeling negative emotions, the system can provide specific advice to alleviate those emotions. Alternatively, if the user is feeling positive emotions, the system can provide advice to maintain those emotions. Furthermore, if the user is feeling a specific emotion, the system can provide specific advice that takes into account the cultural background of that emotion. This allows the user to understand their emotional state and receive specific help to deal with it appropriately.

[0095] The inappropriate text detection system can also be equipped with a feedback function that takes into account the long-term cultural background of a user's utterances. For example, when a user communicates with people from a different culture, the system can suggest appropriate expressions for that culture. It can also provide specific advice tailored to a user's cultural background when the user communicates with people from a specific cultural background. In this way, the user can receive specific help in communicating appropriately with people from different cultures.

[0096] The processing flow of the second embodiment will be briefly explained below.

[0097] Step 1: The text analysis unit uses generative AI to analyze word usage patterns. For example, it analyzes word usage patterns in the input text to detect offensive language, discriminatory expressions, violent content, etc. It can also identify word usage patterns using frequency analysis and co-occurrence analysis. Step 2: The ethical evaluation unit uses generative AI to evaluate the text based on general ethical principles, such as detecting content that may harm others or violate their privacy. It can also evaluate the text based on AI ethical guidelines and legal regulations. Step 3: The inappropriate text detection unit detects inappropriate content from the text analyzed and evaluated by the text analysis unit and the ethical evaluation unit. For example, it detects offensive comments, discriminatory remarks, violent messages, etc. It can also refer to a database of past inappropriate text to detect similar patterns. Step 4: The warning message generator generates a warning message based on the inappropriate content detected by the inappropriate text detector. For example, it generates a message such as "This message contains inappropriate content. Please check the content before sending." It can also generate individually customized warning messages by referring to the user's past behavior history. Step 5: The alert display unit displays the warning message generated by the warning message generation unit to the user. For example, the warning message may be displayed using a pop-up display or a notification message. It is also possible to apply the warning message to voice input and video chat content, thereby generating a multimodal alert.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] 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.

[0109] 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.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0111] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0126] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0142] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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."

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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]

[0165] 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. Using generative AI, a text analysis unit that analyzes word usage patterns; an ethical evaluation section that evaluates texts based on general ethical principles; an inappropriate text detection unit that detects inappropriate content from the text analyzed and evaluated by the text analysis unit and the ethical evaluation unit; a warning message generating unit that generates a warning message based on the inappropriate content detected by the inappropriate text detecting unit; an alert display unit that displays the warning message generated by the warning message generation unit to a user. A system characterized by:

2. The text analysis unit Analyze the user's past speech history, learn specific word usage patterns, and perform individually customized analysis.

2. The system of claim 1.

3. The text analysis unit Understand the context of the text in real time and analyze contextual word usage patterns 2. The system of claim 1.

4. The text analysis unit Analyzing the emotional state of the user and identifying emotion-based word usage patterns.

2. The system of claim 1.

5. The text analysis unit It will also be applied to voice input and video chat content to analyze multimodal language usage patterns.

2. The system of claim 1.

6. The text analysis unit Analyzes word usage patterns across different languages ​​and cultures to detect inappropriate text from a global perspective 2. The system of claim 1.

7. The ethical evaluation department Automatically updates the latest ethical principles and regulations, ensuring the text is always evaluated against the latest standards 2. The system of claim 1.

8. The ethical evaluation department Learn the user's individual ethics and values ​​and provide a personalized ethical assessment 2. The system of claim 1.

Images