System

Abstract

To provide a system which detects an aggressive posted message and urges a poster to take an appropriate action.SOLUTION: A system includes a detection section, a specification section, and a notification section. The detection section detects an aggressive posted message. The specification section specifies a user who posted the aggressive message detected by the detection section. The notification section performs notification to the user specified by the specification.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have not been effective in detecting offensive posted messages and encouraging posters to take appropriate action, and there is room for improvement.

[0005] The system according to the embodiment aims to detect offensive posted messages and prompt the poster to take appropriate action. [Means for solving the problem]

[0006] The system according to the embodiment includes a detection unit, a specification unit, and a notification unit. The detection unit detects an offensive posted message. The specification unit specifies a user who posted the offensive message detected by the detection unit. The notification unit issues a notification to the user specified by the specification unit. Effect of the Invention

[0007] The system according to the embodiment can detect offensive posted messages and prompt the poster to take appropriate action. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A system according to an embodiment of the present invention is a system that uses AI to detect aggressive posted messages, notifies the user, and recommends milder text. In this system, first, AI analyzes the posted message and determines whether it contains aggressive content. Next, if an aggressive message is detected, the user who posted the message is identified and notified to the user. This notification includes specific parts of the aggressive message and advice on how to correct it. Furthermore, a process that can be selected by the receiver can be performed. For example, the receiver can select whether to filter the aggressive message or convert it into milder text. This provides an opportunity for the user to correct the aggressive message before posting it, and allows the receiver to respond flexibly. For example, AI analyzes the posted message and determines whether it contains aggressive content. If an aggressive message is detected, the user who posted the message is identified and notified to the user. This notification includes specific parts of the aggressive message and advice on how to correct it. Furthermore, a process that can be selected by the receiver can be performed. For example, the receiver can select whether to filter the aggressive message or convert it into milder text. This provides users with an opportunity to correct their offensive messages before they are posted, and allows the recipient to respond flexibly. This allows the system to detect offensive posted messages, notify users, and recommend milder versions.

[0029] The system according to the embodiment includes a detection unit, an identification unit, and a notification unit. The detection unit detects an aggressive posted message. For example, the detection unit uses AI to analyze the posted message and determine whether it contains aggressive content. The AI ​​uses natural language processing technology to analyze the content of the posted message and detect aggressive words and phrases. For example, the AI ​​can detect aggressive messages using keyword matching or machine learning algorithms. The identification unit identifies a user who posted an aggressive message detected by the detection unit. For example, the identification unit analyzes a user ID or IP address to identify a user who posted an aggressive message. The identification unit can also use AI to analyze a user's posting history and behavioral patterns to identify a user who posted an aggressive message. The notification unit notifies the user identified by the identification unit. For example, the notification unit notifies the user of the aggressive message posting by using an email notification or an in-app notification. The notification unit can also use AI to indicate specific parts of the aggressive message and provide advice on how to correct it. For example, the notification unit highlights specific parts of offensive messages and provides correction examples and guidelines, allowing the system to detect offensive posted messages, notify users, and recommend milder language.

[0030] The detection unit detects offensive posted messages. For example, the detection unit uses AI to analyze posted messages and determine whether they contain offensive content. The AI ​​uses natural language processing technology to analyze the content of posted messages and detect offensive words and phrases. Specifically, the AI ​​can detect offensive messages using keyword matching or machine learning algorithms. In keyword matching, a predefined list of offensive words and phrases is used to detect matching parts in posted messages. In machine learning algorithms, a large amount of data is used to train a model and learn the characteristics of offensive messages. This enables detection that takes into account subtle nuances and context that cannot be detected by simple keyword matching. In addition, the AI ​​can perform context analysis and sentiment analysis to evaluate the overall tone and intention of the posted message. For example, even if a posted message is written as sarcasm or a joke, it can detect the offensive intention behind it. This allows the detection unit to detect offensive messages with higher accuracy and improve the reliability of the entire system.

[0031] The identification unit identifies the user who posted the offensive message detected by the detection unit. For example, the identification unit analyzes the user ID and IP address to identify the user who posted the offensive message. Specifically, the identification unit collects metadata related to the posted message and extracts the user's identification information. This includes the user's account information, IP address, device information, posting history, etc. Furthermore, the identification unit can use AI to analyze the user's posting history and behavioral patterns to identify the user who posted the offensive message. The AI ​​learns the user's past posting content and behavioral patterns to identify users who tend to post offensive messages. For example, the identification unit preferentially investigates users who have a history of posting offensive messages in the past and evaluates the risk of recurrence. In addition, the identification unit can use an anomaly detection algorithm to detect unusual behavioral patterns and identify users who may have posted offensive messages. This allows the identification unit to quickly and accurately identify users who have posted offensive messages and take appropriate measures.

[0032] The notification unit notifies the user identified by the identification unit. For example, the notification unit notifies the user of the posting of an offensive message by using an email notification or an in-app notification. Specifically, the notification unit indicates the specific part of the offensive message to the user and provides advice on how to correct it. For example, the notification unit highlights the specific part of the offensive message and provides correction examples and guidelines. Furthermore, the notification unit can use AI to indicate the specific part of the offensive message and provide advice on how to correct it. The AI ​​analyzes the content of the offensive message and generates appropriate correction examples and guidelines. For example, the AI ​​suggests replacing offensive words and phrases with milder expressions. In addition, the notification unit can provide educational content to the user and conduct awareness-raising activities to prevent the posting of offensive messages. In this way, the notification unit can encourage the user to take appropriate action and reduce the posting of offensive messages. Furthermore, the notification unit can collect feedback from users and continuously improve the accuracy and effectiveness of the notification content. For example, based on the feedback provided by the user, the notification unit can review the notification content and examples of corrections to provide more effective notifications. This allows the notification unit to provide prompt and appropriate notifications to the user, thereby improving the reliability and safety of the entire system.

[0033] The notification unit can indicate specific parts of the offensive message and provide advice on how to correct it. The notification unit can, for example, highlight specific parts of the offensive message and provide correction examples and guidelines. For example, the notification unit can identify offensive phrases or contexts and provide specific advice for correcting them. The notification unit can also use AI to identify specific parts of the offensive message and provide advice on how to correct it. For example, the notification unit can use AI to analyze specific parts of the offensive message and generate correction examples and guidelines. This can encourage the user to correct the offensive message by providing a specific correction method to the user.

[0034] The processing unit can perform processing that can be selected by the receiver based on the aggressive message. The processing unit can select, for example, whether the receiver filters the aggressive message or converts it into a mild sentence. For example, the processing unit uses AI to filter the aggressive message. The AI ​​can detect the aggressive message and filter it using natural language processing technology. The processing unit can also use AI to convert the aggressive message into a mild sentence. For example, the AI ​​converts the aggressive message into a mild sentence by replacing aggressive words and phrases and adjusting the tone of the sentence. This allows the receiver to respond flexibly to the aggressive message. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can use a rule-based system for filtering aggressive messages.

[0035] The detection unit can estimate the poster's emotion and improve the detection accuracy of aggressive messages based on the estimated poster's emotion. The detection unit can, for example, use AI to analyze the poster's emotion in real time and improve the detection accuracy of aggressive messages when the poster has strong emotions such as anger or irritation. The AI ​​can use an emotion analysis algorithm to analyze the poster's emotion and calculate an emotion score. The detection unit can also use AI to learn the poster's past emotion patterns and improve the detection accuracy by taking into account that aggressive messages are likely to be posted when the poster is in a specific emotional state. For example, the AI ​​analyzes the poster's past posting history and learns the emotion change pattern. Furthermore, the detection unit can also use AI to track changes in the poster's emotion and enhance the detection of aggressive messages when there is a sudden change in emotion. As a result, the detection of aggressive messages becomes more accurate by improving the detection accuracy based on the poster's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0036] The detection unit can improve detection accuracy by analyzing the past posting history and learning the pattern of aggressive messages of a specific user. The detection unit can, for example, use AI to analyze the past posting history of a specific user and learn the pattern of aggressive messages. The AI ​​can learn from the user's posting history that aggressive messages are likely to be posted in a specific time period or situation, and improve detection accuracy. The detection unit can also detect a message as aggressive if it contains a specific keyword or phrase based on the user's posting history using AI. This improves the detection accuracy of aggressive messages of a specific user by analyzing the past posting history. Part or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can analyze the past posting history using a rule-based system.

[0037] The detection unit can analyze the context of the posted message and identify a portion that may contain aggressive content. The detection unit can, for example, use AI to analyze the context of the posted message and identify a portion that may contain aggressive content. The AI ​​can use natural language processing technology to analyze the context of the posted message and identify phrases or words that may contain aggressive content. The detection unit can also highlight a portion that may contain aggressive content based on the context of the posted message using AI. This makes it possible to identify aggressive content by analyzing the context of the posted message. A part or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can also analyze the context of the posted message using a context analysis algorithm.

[0038] The detection unit can estimate the poster's emotion and adjust the detection timing of aggressive messages based on the estimated poster's emotion. The detection unit can, for example, use AI to analyze the poster's emotion in real time and enhance the detection of aggressive messages when the poster is emotionally excited. The AI ​​can analyze the poster's emotion and calculate an emotion score using an emotion analysis algorithm. The detection unit can also use AI to track changes in the poster's emotion and prioritize the detection of aggressive messages when the emotion changes rapidly. Furthermore, the detection unit can also use AI to adjust the detection timing of aggressive messages when the poster is in a specific emotional state based on the poster's emotion. This makes the detection of aggressive messages more effective by adjusting the detection timing based on the poster's emotion. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0039] The detection unit can adjust the detection criteria for offensive content by taking into account the language and cultural background of the posted message. The detection unit, for example, uses AI to analyze the language of the posted message and detects aggressive expressions in a specific language. The AI ​​can use natural language processing technology to analyze the language of the posted message and identify aggressive expressions. The detection unit can also use AI to consider the cultural background of the posted message and detect aggressive expressions in a specific culture. Furthermore, the detection unit can also adjust the detection criteria for offensive content based on the language and cultural background of the posted message by using AI. As a result, by taking into account the language and cultural background, the detection criteria for offensive content are adjusted and the detection accuracy is improved. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can detect aggressive content by using a rule-based system that takes into account the language and cultural background.

[0040] The detection unit can integrate data from social media and other online platforms to improve the detection accuracy of aggressive messages. The detection unit can, for example, use AI to analyze data from social media and learn patterns of aggressive messages. The AI ​​can collect social media posting data and identify patterns of aggressive messages. The detection unit can also integrate data from other online platforms using AI to improve the detection accuracy of aggressive messages. Furthermore, the detection unit can also use AI to adjust the detection criteria for aggressive messages based on data from multiple platforms. This improves the detection accuracy of aggressive messages by integrating multiple data sources. Some or all of the above-mentioned processing in the detection unit can be performed, for example, using AI or without using AI. For example, the detection unit can use API integration to integrate data from social media and other online platforms.

[0041] The identification unit can estimate the poster's emotions and improve the accuracy of identifying aggressive messages based on the estimated emotions of the poster. The identification unit can, for example, use AI to analyze the poster's emotions in real time and improve the accuracy of identification when the emotions are high. The AI ​​can use an emotion analysis algorithm to analyze the poster's emotions and calculate an emotion score. The identification unit can also use AI to learn the poster's past emotion patterns and improve the accuracy of identification when the poster is in a specific emotional state. Furthermore, the identification unit can also use AI to track changes in the poster's emotions and improve the accuracy of identification when there is a sudden change in emotion. This allows for more accurate identification by improving the accuracy of identification based on the poster's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0042] The identification unit can analyze the poster's past behavioral history and improve the accuracy of identifying aggressive messages. The identification unit can, for example, use AI to analyze the poster's past behavioral history and improve the accuracy of identification. The AI ​​can learn the poster's behavioral patterns and improve the accuracy of identification. The identification unit can also use AI to improve the accuracy of identification based on the poster's past behavioral history. As a result, the accuracy of identification is improved by analyzing the past behavioral history. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can analyze the past behavioral history using a rule-based system.

[0043] The identification unit can improve the accuracy of identifying an offensive message by using the poster's IP address and device information. The identification unit can, for example, use AI to analyze the poster's IP address and improve the accuracy of identification. The AI ​​can analyze the poster's location information and network information based on the IP address. The identification unit can also use AI to analyze the poster's device information and improve the accuracy of identification. Furthermore, the identification unit can also use AI to improve the accuracy of identification based on the poster's IP address and device information. As a result, the accuracy of identification is improved by using the IP address and device information. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can analyze the IP address and device information using a rule-based system.

[0044] The identification unit can estimate the poster's emotions and determine the specific priority of aggressive messages based on the estimated emotions of the poster. The identification unit can, for example, use AI to analyze the poster's emotions in real time and increase the specific priority when the emotions are high. The AI ​​can analyze the poster's emotions and calculate an emotion score using an emotion analysis algorithm. The identification unit can also use AI to learn the poster's past emotion patterns and determine the specific priority when the poster is in a specific emotional state. Furthermore, the identification unit can also use AI to track changes in the poster's emotions and increase the specific priority when there is a sudden change in emotion. In this way, important identification is prioritized by determining the specific priority based on the poster's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0045] The identification unit can improve the accuracy of identifying an offensive message by taking into account the poster's geographic location information. The identification unit can, for example, use AI to analyze the poster's geographic location information and improve the identification accuracy. The AI ​​can analyze the poster's geographic location information by using GPS data or a location information service. The identification unit can also improve the identification accuracy based on the poster's geographic location information by using AI. Furthermore, the identification unit can also improve the identification accuracy by taking into account the poster's geographic location information by using AI. As a result, the identification accuracy is improved by taking into account the geographic location information. A part or all of the above-mentioned processing in the identification unit may be performed by using AI, for example, or may be performed without using AI. For example, the identification unit can analyze the geographic location information by using a rule-based system.

[0046] The identification unit can analyze the poster's social media activity and improve the accuracy of identifying offensive messages. The identification unit can, for example, use AI to analyze the poster's social media activity and improve the accuracy of identification. The AI ​​can collect social media posting data and identify the poster's behavioral pattern. The identification unit can also use AI to improve the accuracy of identification based on the poster's social media activity. Furthermore, the identification unit can also use AI to improve the accuracy of identification by taking into account the poster's social media activity. In this way, the accuracy of identification is improved by analyzing social media activity. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can analyze social media activity using a rule-based system.

[0047] The notification unit can estimate the poster's emotions and adjust the expression method of the aggressive message notification based on the estimated emotions of the poster. The notification unit can, for example, use AI to analyze the poster's emotions in real time and make a notification in a calmer expression when the poster is emotionally excited. The AI ​​can use an emotion analysis algorithm to analyze the poster's emotions and calculate an emotion score. The notification unit can also use AI to learn the poster's past emotion patterns and make a notification in an appropriate expression method when the poster is in a specific emotional state. Furthermore, the notification unit can also use AI to track changes in the poster's emotions and make a notification in an appropriate expression method when there is a sudden change in emotions. This allows for more effective notification by adjusting the expression method of the notification based on the poster's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0048] The notification unit can select the optimal notification method for an aggressive message by referring to past notification history. The notification unit, for example, uses AI to analyze past notification history and select the optimal notification method. The AI ​​can select the optimal notification method in a specific situation based on the past notification history. The notification unit can also use AI to refer to past notification history and select the optimal notification method. As a result, the optimal notification method is selected by referring to the past notification history. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can analyze past notification history using a rule-based system.

[0049] The notification unit can estimate the poster's emotions and adjust the timing of the notification of an aggressive message based on the estimated emotions of the poster. The notification unit can, for example, use AI to analyze the poster's emotions in real time and adjust the timing of the notification when the poster is emotionally excited. The AI ​​can use an emotion analysis algorithm to analyze the poster's emotions and calculate an emotion score. The notification unit can also use AI to learn the poster's past emotion patterns and adjust the timing of the notification when the poster is in a specific emotional state. Furthermore, the notification unit can also use AI to track changes in the poster's emotions and adjust the timing of the notification when there is a sudden change in emotions. As a result, the notification is made at a more appropriate time by adjusting the timing of the notification based on the poster's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0050] The notification unit can adjust the content of the notification of an offensive message by taking into account the language and cultural background of the poster. The notification unit can, for example, use AI to analyze the language of the poster and make the notification in an appropriate language. The AI ​​can use natural language processing technology to analyze the language of the poster and make the notification in an appropriate language. The notification unit can also use AI to consider the cultural background of the poster and make the notification in an appropriate expression. Furthermore, the notification unit can also adjust the content of the notification based on the language and cultural background of the poster by using AI. As a result, a more appropriate notification is made by taking into account the language and cultural background. A part or all of the above-mentioned processing in the notification unit may be performed by using AI, for example, or may be performed without using AI. For example, the notification unit can adjust the content of the notification by using a rule-based system that takes into account the language and cultural background.

[0051] The notification unit can analyze the poster's social media activity and select the optimal notification method for the offensive message. The notification unit can, for example, use AI to analyze the poster's social media activity and select the optimal notification method. The AI ​​can collect social media posting data and identify the poster's behavioral pattern. The notification unit can also use AI to select the optimal notification method in a specific situation based on the poster's social media activity. Furthermore, the notification unit can also use AI to refer to the poster's social media activity and select the optimal notification method. In this way, the optimal notification method is selected by analyzing the social media activity. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can analyze the social media activity using a rule-based system and select the optimal notification method.

[0052] The processing unit can estimate the emotion of the receiver and provide a selectable processing method for aggressive messages based on the estimated emotion of the receiver. The processing unit can, for example, use AI to analyze the emotion of the receiver in real time and prioritize filtering when the emotion is heightened. The AI ​​can use an emotion analysis algorithm to analyze the emotion of the receiver and calculate an emotion score. The processing unit can also use AI to learn the past emotion patterns of the receiver and provide an optimal processing method when the receiver is in a specific emotional state. Furthermore, the processing unit can also use AI to track changes in the emotion of the receiver and provide an optimal processing method when there is a sudden change in emotion. This improves the satisfaction of the receiver by providing an optimal processing method based on the emotion of the receiver. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0053] The processing unit can filter the aggressive message on the receiver side or convert it to milder sentences based on the content of the aggressive message. The processing unit, for example, uses AI to analyze the content of the aggressive message and filter it on the receiver side. The AI ​​can detect the aggressive message and filter it using natural language processing technology. The processing unit can also convert the aggressive message into milder sentences based on the content of the aggressive message using AI. For example, the AI ​​replaces aggressive words and phrases and adjusts the tone of the sentence to convert it into milder sentences. This reduces the stress of the receiver by filtering the aggressive message or converting it into milder sentences. Some or all of the above-mentioned processing in the processing unit may be performed using AI, for example, or may be performed without using AI. For example, the processing unit can use a rule-based system for filtering aggressive messages.

[0054] The processing unit can analyze the receiver's past message reception history and select the optimal processing method for the aggressive message. The processing unit can, for example, use AI to analyze the receiver's past message reception history and select the optimal processing method. The AI ​​can select the optimal processing method in a specific situation based on the past message reception history. The processing unit can also use AI to refer to the receiver's past message reception history and select the optimal processing method. In this way, the optimal processing method is selected by analyzing the past message reception history. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can analyze the past message reception history using a rule-based system.

[0055] The processing unit can estimate the emotion of the receiver and determine the priority of processing aggressive messages based on the estimated emotion of the receiver. The processing unit can, for example, use AI to analyze the emotion of the receiver in real time and increase the priority of processing when the emotion is heightened. The AI ​​can use an emotion analysis algorithm to analyze the emotion of the receiver and calculate an emotion score. The processing unit can also use AI to learn the past emotion patterns of the receiver and determine the priority of processing when the receiver is in a specific emotional state. Furthermore, the processing unit can also use AI to track changes in the emotion of the receiver and increase the priority of processing when there is a sudden change in emotion. In this way, important processing is prioritized by determining the priority of processing based on the emotion of the receiver. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0056] The processing unit can select the optimal processing method for the aggressive message by taking into account the geographic location information of the receiver. The processing unit, for example, uses AI to analyze the geographic location information of the receiver and selects the optimal processing method. The AI ​​can analyze the geographic location information of the receiver by using GPS data or a location information service. The processing unit can also use AI to select the optimal processing method based on the geographic location information of the receiver. Furthermore, the processing unit can also use AI to select the optimal processing method by taking into account the geographic location information of the receiver. In this way, the optimal processing method is selected by taking into account the geographic location information. A part or all of the above-mentioned processing in the processing unit may be performed by using AI, for example, or may be performed without using AI. For example, the processing unit can analyze the geographic location information by using a rule-based system and select the optimal processing method.

[0057] The processing unit can analyze the social media activity of the recipient and select the optimal processing method for the offensive message. The processing unit can, for example, use AI to analyze the social media activity of the recipient and select the optimal processing method. The AI ​​can collect social media posting data and identify the behavioral pattern of the recipient. The processing unit can also use AI to select the optimal processing method in a specific situation based on the social media activity of the recipient. Furthermore, the processing unit can also use AI to refer to the social media activity of the recipient and select the optimal processing method. In this way, the optimal processing method is selected by analyzing the social media activity. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can analyze the social media activity using a rule-based system and select the optimal processing method.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The detection unit can also analyze the image and video content of the posted message to determine whether it contains offensive content. For example, it can use AI to analyze the content of the image or video to detect offensive symbols or gestures. Furthermore, the identification unit can analyze the metadata of the image or video to identify the poster. For example, it can identify the poster based on the location information of the image or the date and time of shooting. The notification unit can also indicate the specific parts of the offensive image or video and provide advice on how to correct it. This makes it possible to detect and respond to offensive content not only in text but also in multimedia content.

[0060] The detection unit can also analyze the audio content of the posted message to determine whether it contains offensive content. For example, it can use AI to convert the audio data into text and analyze the text to detect offensive words or phrases. The identification unit can analyze the metadata of the audio data to identify the poster. For example, it can identify the poster based on the location and time of the audio recording. The notification unit can also indicate the specific parts of the offensive audio and provide advice on how to correct them. This makes it possible to detect and respond to offensive content in audio content as well.

[0061] The detection unit can analyze the context of a posted message and identify parts that may contain offensive content. For example, the context of a posted message can be analyzed using AI to identify phrases or words that may contain offensive content. The detection unit can also use AI to highlight parts that may contain offensive content based on the context of a posted message. In this way, by analyzing the context of a posted message, it is possible to identify offensive content.

[0062] The detection unit can adjust the detection criteria for offensive content by taking into account the language and cultural background of the posted message. For example, AI can be used to analyze the language of the posted message and detect offensive expressions in a specific language. The AI ​​can use natural language processing technology to analyze the language of the posted message and identify the offensive expressions. The detection unit can also use AI to take into account the cultural background of the posted message and detect offensive expressions in a specific culture. As a result, by taking into account the language and cultural background, the detection criteria for offensive content are adjusted, improving detection accuracy.

[0063] The identification unit can improve the accuracy of identifying offensive messages by using the poster's IP address and device information. For example, AI can be used to analyze the poster's IP address to improve the accuracy of identification. AI can analyze the poster's location information and network information based on the IP address. The identification unit can also use AI to analyze the poster's device information to improve the accuracy of identification. In this way, the accuracy of identification is improved by using the IP address and device information.

[0064] The processing unit can analyze the receiver's past message reception history and select the optimal processing method for the offensive message. For example, AI is used to analyze the receiver's past message reception history and select the optimal processing method. AI can select the optimal processing method in a specific situation based on the past message reception history. The processing unit can also use AI to refer to the receiver's past message reception history and select the optimal processing method. In this way, the optimal processing method is selected by analyzing the past message reception history.

[0065] The process flow of the first embodiment will be briefly described below.

[0066] Step 1: The detection unit detects offensive posted messages. For example, the detection unit uses AI to analyze posted messages and determine whether they contain offensive content. The AI ​​uses natural language processing techniques to analyze the content of the posted messages and detect offensive words or phrases. For example, the AI ​​can use keyword matching or machine learning algorithms to detect offensive messages. Step 2: The identification unit identifies the user who posted the offensive message detected by the detection unit. For example, the identification unit analyzes the user ID or IP address to identify the user who posted the offensive message. The identification unit can also use AI to analyze the user's posting history and behavioral patterns to identify the user who posted the offensive message. Step 3: The notification unit notifies the user identified by the identification unit. For example, the notification unit notifies the user of the posting of an offensive message by using an email notification or an in-app notification. The notification unit can also use AI to indicate specific parts of the offensive message and provide advice on how to correct it. For example, the notification unit highlights specific parts of the offensive message and provides examples and guidelines for correction.

[0067] (Example 2) A system according to an embodiment of the present invention is a system that uses AI to detect aggressive posted messages, notifies the user, and recommends milder text. In this system, first, AI analyzes the posted message and determines whether it contains aggressive content. Next, if an aggressive message is detected, the user who posted the message is identified and notified to the user. This notification includes specific parts of the aggressive message and advice on how to correct it. Furthermore, a process that can be selected by the receiver can be performed. For example, the receiver can select whether to filter the aggressive message or convert it into milder text. This provides an opportunity for the user to correct the aggressive message before posting it, and allows the receiver to respond flexibly. For example, AI analyzes the posted message and determines whether it contains aggressive content. If an aggressive message is detected, the user who posted the message is identified and notified to the user. This notification includes specific parts of the aggressive message and advice on how to correct it. Furthermore, a process that can be selected by the receiver can be performed. For example, the receiver can select whether to filter the aggressive message or convert it into milder text. This provides users with an opportunity to correct their offensive messages before they are posted, and allows the recipient to respond flexibly. This allows the system to detect offensive posted messages, notify users, and recommend milder versions.

[0068] The system according to the embodiment includes a detection unit, an identification unit, and a notification unit. The detection unit detects an aggressive posted message. For example, the detection unit uses AI to analyze the posted message and determine whether it contains aggressive content. The AI ​​uses natural language processing technology to analyze the content of the posted message and detect aggressive words and phrases. For example, the AI ​​can detect aggressive messages using keyword matching or machine learning algorithms. The identification unit identifies a user who posted an aggressive message detected by the detection unit. For example, the identification unit analyzes a user ID or IP address to identify a user who posted an aggressive message. The identification unit can also use AI to analyze a user's posting history and behavioral patterns to identify a user who posted an aggressive message. The notification unit notifies the user identified by the identification unit. For example, the notification unit notifies the user of the aggressive message posting by using an email notification or an in-app notification. The notification unit can also use AI to indicate specific parts of the aggressive message and provide advice on how to correct it. For example, the notification unit highlights specific parts of offensive messages and provides correction examples and guidelines, allowing the system to detect offensive posted messages, notify users, and recommend milder language.

[0069] The detection unit detects offensive posted messages. For example, the detection unit uses AI to analyze posted messages and determine whether they contain offensive content. The AI ​​uses natural language processing technology to analyze the content of posted messages and detect offensive words and phrases. Specifically, the AI ​​can detect offensive messages using keyword matching or machine learning algorithms. In keyword matching, a predefined list of offensive words and phrases is used to detect matching parts in posted messages. In machine learning algorithms, a large amount of data is used to train a model and learn the characteristics of offensive messages. This enables detection that takes into account subtle nuances and context that cannot be detected by simple keyword matching. In addition, the AI ​​can perform context analysis and sentiment analysis to evaluate the overall tone and intention of the posted message. For example, even if a posted message is written as sarcasm or a joke, it can detect the offensive intention behind it. This allows the detection unit to detect offensive messages with higher accuracy and improve the reliability of the entire system.

[0070] The identification unit identifies the user who posted the offensive message detected by the detection unit. For example, the identification unit analyzes the user ID and IP address to identify the user who posted the offensive message. Specifically, the identification unit collects metadata related to the posted message and extracts the user's identification information. This includes the user's account information, IP address, device information, posting history, etc. Furthermore, the identification unit can use AI to analyze the user's posting history and behavioral patterns to identify the user who posted the offensive message. The AI ​​learns the user's past posting content and behavioral patterns to identify users who tend to post offensive messages. For example, the identification unit preferentially investigates users who have a history of posting offensive messages in the past and evaluates the risk of recurrence. In addition, the identification unit can use an anomaly detection algorithm to detect unusual behavioral patterns and identify users who may have posted offensive messages. This allows the identification unit to quickly and accurately identify users who have posted offensive messages and take appropriate measures.

[0071] The notification unit notifies the user identified by the identification unit. For example, the notification unit notifies the user of the posting of an offensive message by using an email notification or an in-app notification. Specifically, the notification unit indicates the specific part of the offensive message to the user and provides advice on how to correct it. For example, the notification unit highlights the specific part of the offensive message and provides correction examples and guidelines. Furthermore, the notification unit can use AI to indicate the specific part of the offensive message and provide advice on how to correct it. The AI ​​analyzes the content of the offensive message and generates appropriate correction examples and guidelines. For example, the AI ​​suggests replacing offensive words and phrases with milder expressions. In addition, the notification unit can provide educational content to the user and conduct awareness-raising activities to prevent the posting of offensive messages. In this way, the notification unit can encourage the user to take appropriate action and reduce the posting of offensive messages. Furthermore, the notification unit can collect feedback from users and continuously improve the accuracy and effectiveness of the notification content. For example, based on the feedback provided by the user, the notification unit can review the notification content and examples of corrections to provide more effective notifications. This allows the notification unit to provide prompt and appropriate notifications to the user, thereby improving the reliability and safety of the entire system.

[0072] The notification unit can indicate specific parts of the offensive message and provide advice on how to correct it. The notification unit can, for example, highlight specific parts of the offensive message and provide correction examples and guidelines. For example, the notification unit can identify offensive phrases or contexts and provide specific advice for correcting them. The notification unit can also use AI to identify specific parts of the offensive message and provide advice on how to correct it. For example, the notification unit can use AI to analyze specific parts of the offensive message and generate correction examples and guidelines. This can encourage the user to correct the offensive message by providing a specific correction method to the user.

[0073] The processing unit can perform processing that can be selected by the receiver based on the aggressive message. The processing unit can select, for example, whether the receiver filters the aggressive message or converts it into a mild sentence. For example, the processing unit uses AI to filter the aggressive message. The AI ​​can detect the aggressive message and filter it using natural language processing technology. The processing unit can also use AI to convert the aggressive message into a mild sentence. For example, the AI ​​converts the aggressive message into a mild sentence by replacing aggressive words and phrases and adjusting the tone of the sentence. This allows the receiver to respond flexibly to the aggressive message. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can use a rule-based system for filtering aggressive messages.

[0074] The detection unit can estimate the poster's emotion and improve the detection accuracy of aggressive messages based on the estimated poster's emotion. The detection unit can, for example, use AI to analyze the poster's emotion in real time and improve the detection accuracy of aggressive messages when the poster has strong emotions such as anger or irritation. The AI ​​can use an emotion analysis algorithm to analyze the poster's emotion and calculate an emotion score. The detection unit can also use AI to learn the poster's past emotion patterns and improve the detection accuracy by taking into account that aggressive messages are likely to be posted when the poster is in a specific emotional state. For example, the AI ​​analyzes the poster's past posting history and learns the emotion change pattern. Furthermore, the detection unit can also use AI to track changes in the poster's emotion and enhance the detection of aggressive messages when there is a sudden change in emotion. As a result, the detection of aggressive messages becomes more accurate by improving the detection accuracy based on the poster's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0075] The detection unit can improve detection accuracy by analyzing the past posting history and learning the pattern of aggressive messages of a specific user. The detection unit can, for example, use AI to analyze the past posting history of a specific user and learn the pattern of aggressive messages. The AI ​​can learn from the user's posting history that aggressive messages are likely to be posted in a specific time period or situation, and improve detection accuracy. The detection unit can also detect a message as aggressive if it contains a specific keyword or phrase based on the user's posting history using AI. This improves the detection accuracy of aggressive messages of a specific user by analyzing the past posting history. Part or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can analyze the past posting history using a rule-based system.

[0076] The detection unit can analyze the context of the posted message and identify a portion that may contain aggressive content. The detection unit can, for example, use AI to analyze the context of the posted message and identify a portion that may contain aggressive content. The AI ​​can use natural language processing technology to analyze the context of the posted message and identify phrases or words that may contain aggressive content. The detection unit can also highlight a portion that may contain aggressive content based on the context of the posted message using AI. This makes it possible to identify aggressive content by analyzing the context of the posted message. A part or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can also analyze the context of the posted message using a context analysis algorithm.

[0077] The detection unit can estimate the poster's emotion and adjust the detection timing of aggressive messages based on the estimated poster's emotion. The detection unit can, for example, use AI to analyze the poster's emotion in real time and enhance the detection of aggressive messages when the poster is emotionally excited. The AI ​​can analyze the poster's emotion and calculate an emotion score using an emotion analysis algorithm. The detection unit can also use AI to track changes in the poster's emotion and prioritize the detection of aggressive messages when the emotion changes rapidly. Furthermore, the detection unit can also use AI to adjust the detection timing of aggressive messages when the poster is in a specific emotional state based on the poster's emotion. This makes the detection of aggressive messages more effective by adjusting the detection timing based on the poster's emotion. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0078] The detection unit can adjust the detection criteria for offensive content by taking into account the language and cultural background of the posted message. The detection unit, for example, uses AI to analyze the language of the posted message and detects aggressive expressions in a specific language. The AI ​​can use natural language processing technology to analyze the language of the posted message and identify aggressive expressions. The detection unit can also use AI to consider the cultural background of the posted message and detect aggressive expressions in a specific culture. Furthermore, the detection unit can also adjust the detection criteria for offensive content based on the language and cultural background of the posted message by using AI. As a result, by taking into account the language and cultural background, the detection criteria for offensive content are adjusted and the detection accuracy is improved. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI, or may be performed without using AI. For example, the detection unit can detect aggressive content by using a rule-based system that takes into account the language and cultural background.

[0079] The detection unit can integrate data from social media and other online platforms to improve the detection accuracy of aggressive messages. The detection unit can, for example, use AI to analyze data from social media and learn patterns of aggressive messages. The AI ​​can collect social media posting data and identify patterns of aggressive messages. The detection unit can also integrate data from other online platforms using AI to improve the detection accuracy of aggressive messages. Furthermore, the detection unit can also use AI to adjust the detection criteria for aggressive messages based on data from multiple platforms. This improves the detection accuracy of aggressive messages by integrating multiple data sources. Some or all of the above-mentioned processing in the detection unit can be performed, for example, using AI or without using AI. For example, the detection unit can use API integration to integrate data from social media and other online platforms.

[0080] The identification unit can estimate the poster's emotions and improve the accuracy of identifying aggressive messages based on the estimated emotions of the poster. The identification unit can, for example, use AI to analyze the poster's emotions in real time and improve the accuracy of identification when the emotions are high. The AI ​​can use an emotion analysis algorithm to analyze the poster's emotions and calculate an emotion score. The identification unit can also use AI to learn the poster's past emotion patterns and improve the accuracy of identification when the poster is in a specific emotional state. Furthermore, the identification unit can also use AI to track changes in the poster's emotions and improve the accuracy of identification when there is a sudden change in emotion. This allows for more accurate identification by improving the accuracy of identification based on the poster's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0081] The identification unit can analyze the poster's past behavioral history and improve the accuracy of identifying aggressive messages. The identification unit can, for example, use AI to analyze the poster's past behavioral history and improve the accuracy of identification. The AI ​​can learn the poster's behavioral patterns and improve the accuracy of identification. The identification unit can also use AI to improve the accuracy of identification based on the poster's past behavioral history. As a result, the accuracy of identification is improved by analyzing the past behavioral history. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can analyze the past behavioral history using a rule-based system.

[0082] The identification unit can improve the accuracy of identifying an offensive message by using the poster's IP address and device information. The identification unit can, for example, use AI to analyze the poster's IP address and improve the accuracy of identification. The AI ​​can analyze the poster's location information and network information based on the IP address. The identification unit can also use AI to analyze the poster's device information and improve the accuracy of identification. Furthermore, the identification unit can also use AI to improve the accuracy of identification based on the poster's IP address and device information. As a result, the accuracy of identification is improved by using the IP address and device information. A part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can analyze the IP address and device information using a rule-based system.

[0083] The identification unit can estimate the poster's emotions and determine the specific priority of aggressive messages based on the estimated emotions of the poster. The identification unit can, for example, use AI to analyze the poster's emotions in real time and increase the specific priority when the emotions are high. The AI ​​can analyze the poster's emotions and calculate an emotion score using an emotion analysis algorithm. The identification unit can also use AI to learn the poster's past emotion patterns and determine the specific priority when the poster is in a specific emotional state. Furthermore, the identification unit can also use AI to track changes in the poster's emotions and increase the specific priority when there is a sudden change in emotion. In this way, important identification is prioritized by determining the specific priority based on the poster's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0084] The identification unit can improve the accuracy of identifying an offensive message by taking into account the poster's geographic location information. The identification unit can, for example, use AI to analyze the poster's geographic location information and improve the identification accuracy. The AI ​​can analyze the poster's geographic location information by using GPS data or a location information service. The identification unit can also improve the identification accuracy based on the poster's geographic location information by using AI. Furthermore, the identification unit can also improve the identification accuracy by taking into account the poster's geographic location information by using AI. As a result, the identification accuracy is improved by taking into account the geographic location information. A part or all of the above-mentioned processing in the identification unit may be performed by using AI, for example, or may be performed without using AI. For example, the identification unit can analyze the geographic location information by using a rule-based system.

[0085] The identification unit can analyze the poster's social media activity and improve the accuracy of identifying offensive messages. The identification unit can, for example, use AI to analyze the poster's social media activity and improve the accuracy of identification. The AI ​​can collect social media posting data and identify the poster's behavioral pattern. The identification unit can also use AI to improve the accuracy of identification based on the poster's social media activity. Furthermore, the identification unit can also use AI to improve the accuracy of identification by taking into account the poster's social media activity. In this way, the accuracy of identification is improved by analyzing social media activity. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can analyze social media activity using a rule-based system.

[0086] The notification unit can estimate the poster's emotions and adjust the expression method of the aggressive message notification based on the estimated emotions of the poster. The notification unit can, for example, use AI to analyze the poster's emotions in real time and make a notification in a calmer expression when the poster is emotionally excited. The AI ​​can use an emotion analysis algorithm to analyze the poster's emotions and calculate an emotion score. The notification unit can also use AI to learn the poster's past emotion patterns and make a notification in an appropriate expression method when the poster is in a specific emotional state. Furthermore, the notification unit can also use AI to track changes in the poster's emotions and make a notification in an appropriate expression method when there is a sudden change in emotions. This allows for more effective notification by adjusting the expression method of the notification based on the poster's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0087] The notification unit can select the optimal notification method for an aggressive message by referring to past notification history. The notification unit, for example, uses AI to analyze past notification history and select the optimal notification method. The AI ​​can select the optimal notification method in a specific situation based on the past notification history. The notification unit can also use AI to refer to past notification history and select the optimal notification method. As a result, the optimal notification method is selected by referring to the past notification history. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can analyze past notification history using a rule-based system.

[0088] The notification unit can estimate the poster's emotions and adjust the timing of the notification of an aggressive message based on the estimated emotions of the poster. The notification unit can, for example, use AI to analyze the poster's emotions in real time and adjust the timing of the notification when the poster is emotionally excited. The AI ​​can use an emotion analysis algorithm to analyze the poster's emotions and calculate an emotion score. The notification unit can also use AI to learn the poster's past emotion patterns and adjust the timing of the notification when the poster is in a specific emotional state. Furthermore, the notification unit can also use AI to track changes in the poster's emotions and adjust the timing of the notification when there is a sudden change in emotions. As a result, the notification is made at a more appropriate time by adjusting the timing of the notification based on the poster's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0089] The notification unit can adjust the content of the notification of an offensive message by taking into account the language and cultural background of the poster. The notification unit can, for example, use AI to analyze the language of the poster and make the notification in an appropriate language. The AI ​​can use natural language processing technology to analyze the language of the poster and make the notification in an appropriate language. The notification unit can also use AI to consider the cultural background of the poster and make the notification in an appropriate expression. Furthermore, the notification unit can also adjust the content of the notification based on the language and cultural background of the poster by using AI. As a result, a more appropriate notification is made by taking into account the language and cultural background. A part or all of the above-mentioned processing in the notification unit may be performed by using AI, for example, or may be performed without using AI. For example, the notification unit can adjust the content of the notification by using a rule-based system that takes into account the language and cultural background.

[0090] The notification unit can analyze the poster's social media activity and select the optimal notification method for the offensive message. The notification unit can, for example, use AI to analyze the poster's social media activity and select the optimal notification method. The AI ​​can collect social media posting data and identify the poster's behavioral pattern. The notification unit can also use AI to select the optimal notification method in a specific situation based on the poster's social media activity. Furthermore, the notification unit can also use AI to refer to the poster's social media activity and select the optimal notification method. In this way, the optimal notification method is selected by analyzing the social media activity. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can analyze the social media activity using a rule-based system and select the optimal notification method.

[0091] The processing unit can estimate the emotion of the receiver and provide a selectable processing method for aggressive messages based on the estimated emotion of the receiver. The processing unit can, for example, use AI to analyze the emotion of the receiver in real time and prioritize filtering when the emotion is heightened. The AI ​​can use an emotion analysis algorithm to analyze the emotion of the receiver and calculate an emotion score. The processing unit can also use AI to learn the past emotion patterns of the receiver and provide an optimal processing method when the receiver is in a specific emotional state. Furthermore, the processing unit can also use AI to track changes in the emotion of the receiver and provide an optimal processing method when there is a sudden change in emotion. This improves the satisfaction of the receiver by providing an optimal processing method based on the emotion of the receiver. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0092] The processing unit can filter the aggressive message on the receiver side or convert it to milder sentences based on the content of the aggressive message. The processing unit, for example, uses AI to analyze the content of the aggressive message and filter it on the receiver side. The AI ​​can detect the aggressive message and filter it using natural language processing technology. The processing unit can also convert the aggressive message into milder sentences based on the content of the aggressive message using AI. For example, the AI ​​replaces aggressive words and phrases and adjusts the tone of the sentence to convert it into milder sentences. This reduces the stress of the receiver by filtering the aggressive message or converting it into milder sentences. Some or all of the above-mentioned processing in the processing unit may be performed using AI, for example, or may be performed without using AI. For example, the processing unit can use a rule-based system for filtering aggressive messages.

[0093] The processing unit can analyze the receiver's past message reception history and select the optimal processing method for the aggressive message. The processing unit can, for example, use AI to analyze the receiver's past message reception history and select the optimal processing method. The AI ​​can select the optimal processing method in a specific situation based on the past message reception history. The processing unit can also use AI to refer to the receiver's past message reception history and select the optimal processing method. In this way, the optimal processing method is selected by analyzing the past message reception history. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can analyze the past message reception history using a rule-based system.

[0094] The processing unit can estimate the emotion of the receiver and determine the priority of processing aggressive messages based on the estimated emotion of the receiver. The processing unit can, for example, use AI to analyze the emotion of the receiver in real time and increase the priority of processing when the emotion is heightened. The AI ​​can use an emotion analysis algorithm to analyze the emotion of the receiver and calculate an emotion score. The processing unit can also use AI to learn the past emotion patterns of the receiver and determine the priority of processing when the receiver is in a specific emotional state. Furthermore, the processing unit can also use AI to track changes in the emotion of the receiver and increase the priority of processing when there is a sudden change in emotion. In this way, important processing is prioritized by determining the priority of processing based on the emotion of the receiver. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0095] The processing unit can select the optimal processing method for the aggressive message by taking into account the geographic location information of the receiver. The processing unit, for example, uses AI to analyze the geographic location information of the receiver and selects the optimal processing method. The AI ​​can analyze the geographic location information of the receiver by using GPS data or a location information service. The processing unit can also use AI to select the optimal processing method based on the geographic location information of the receiver. Furthermore, the processing unit can also use AI to select the optimal processing method by taking into account the geographic location information of the receiver. In this way, the optimal processing method is selected by taking into account the geographic location information. A part or all of the above-mentioned processing in the processing unit may be performed by using AI, for example, or may be performed without using AI. For example, the processing unit can analyze the geographic location information by using a rule-based system and select the optimal processing method.

[0096] The processing unit can analyze the social media activity of the recipient and select the optimal processing method for the offensive message. The processing unit can, for example, use AI to analyze the social media activity of the recipient and select the optimal processing method. The AI ​​can collect social media posting data and identify the behavioral pattern of the recipient. The processing unit can also use AI to select the optimal processing method in a specific situation based on the social media activity of the recipient. Furthermore, the processing unit can also use AI to refer to the social media activity of the recipient and select the optimal processing method. In this way, the optimal processing method is selected by analyzing the social media activity. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can analyze the social media activity using a rule-based system and select the optimal processing method.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] The detection unit can also analyze the image and video content of the posted message to determine whether it contains offensive content. For example, it can use AI to analyze the content of the image or video to detect offensive symbols or gestures. Furthermore, the identification unit can analyze the metadata of the image or video to identify the poster. For example, it can identify the poster based on the location information of the image or the date and time of shooting. The notification unit can also indicate the specific parts of the offensive image or video and provide advice on how to correct it. This makes it possible to detect and respond to offensive content not only in text but also in multimedia content.

[0099] The detection unit can also analyze the audio content of the posted message to determine whether it contains offensive content. For example, it can use AI to convert the audio data into text and analyze the text to detect offensive words or phrases. The identification unit can analyze the metadata of the audio data to identify the poster. For example, it can identify the poster based on the location and time of the audio recording. The notification unit can also indicate the specific parts of the offensive audio and provide advice on how to correct them. This makes it possible to detect and respond to offensive content in audio content as well.

[0100] The detection unit can analyze the context of a posted message and identify parts that may contain offensive content. For example, the context of a posted message can be analyzed using AI to identify phrases or words that may contain offensive content. The detection unit can also use AI to highlight parts that may contain offensive content based on the context of a posted message. In this way, by analyzing the context of a posted message, it is possible to identify offensive content.

[0101] The detection unit can estimate the poster's emotions and improve the detection accuracy of aggressive messages based on the estimated emotions of the poster. For example, the emotions of the poster can be analyzed in real time using AI, and the detection accuracy of aggressive messages can be improved when emotions of anger or irritation are strong. The AI ​​can analyze the emotions of the poster using an emotion analysis algorithm and calculate an emotion score. The detection unit can also use AI to learn the poster's past emotion patterns and improve the detection accuracy by taking into account that aggressive messages are more likely to be posted when the poster is in a certain emotional state. In this way, detection of aggressive messages becomes more accurate by improving the detection accuracy based on the poster's emotions.

[0102] The identification unit can estimate the poster's emotions and improve the accuracy of identifying offensive messages based on the estimated emotions of the poster. For example, the AI ​​can be used to analyze the poster's emotions in real time and improve the accuracy of identification when the poster is emotional. The AI ​​can analyze the poster's emotions and calculate an emotion score using an emotion analysis algorithm. The identification unit can also use AI to learn the poster's past emotion patterns and improve the accuracy of identification when the poster is in a specific emotional state. This allows for more accurate identification by improving the accuracy of identification based on the poster's emotions.

[0103] The notification unit can estimate the poster's emotions and adjust the way in which the notification of an aggressive message is expressed based on the estimated emotions of the poster. For example, the emotions of the poster can be analyzed in real time using AI, and the notification can be made in a calmer way when the poster is emotional. The AI ​​can analyze the emotions of the poster using an emotion analysis algorithm and calculate an emotion score. The notification unit can also learn the poster's past emotion patterns using AI, and make the notification in an appropriate way when the poster is in a specific emotional state. This allows for more effective notifications by adjusting the way in which the notification is expressed based on the poster's emotions.

[0104] The processing unit can estimate the emotion of the recipient and provide selectable processing methods for aggressive messages based on the estimated emotion of the recipient. For example, the AI ​​can be used to analyze the emotion of the recipient in real time and prioritize filtering when the emotion is heightened. The AI ​​can use an emotion analysis algorithm to analyze the emotion of the recipient and calculate an emotion score. The processing unit can also use the AI ​​to learn the past emotion patterns of the recipient and provide an optimal processing method when the recipient is in a particular emotional state. This improves the satisfaction of the recipient by providing an optimal processing method based on the emotion of the recipient.

[0105] The detection unit can adjust the detection criteria for offensive content by taking into account the language and cultural background of the posted message. For example, AI can be used to analyze the language of the posted message and detect offensive expressions in a specific language. The AI ​​can use natural language processing technology to analyze the language of the posted message and identify the offensive expressions. The detection unit can also use AI to take into account the cultural background of the posted message and detect offensive expressions in a specific culture. As a result, by taking into account the language and cultural background, the detection criteria for offensive content are adjusted, improving detection accuracy.

[0106] The identification unit can improve the accuracy of identifying offensive messages by using the poster's IP address and device information. For example, AI can be used to analyze the poster's IP address to improve the accuracy of identification. AI can analyze the poster's location information and network information based on the IP address. The identification unit can also use AI to analyze the poster's device information to improve the accuracy of identification. In this way, the accuracy of identification is improved by using the IP address and device information.

[0107] The processing unit can analyze the receiver's past message reception history and select the optimal processing method for the offensive message. For example, AI is used to analyze the receiver's past message reception history and select the optimal processing method. AI can select the optimal processing method in a specific situation based on the past message reception history. The processing unit can also use AI to refer to the receiver's past message reception history and select the optimal processing method. In this way, the optimal processing method is selected by analyzing the past message reception history.

[0108] The process flow of the second embodiment will be briefly described below.

[0109] Step 1: The detection unit detects offensive posted messages. For example, the detection unit uses AI to analyze posted messages and determine whether they contain offensive content. The AI ​​uses natural language processing techniques to analyze the content of the posted messages and detect offensive words or phrases. For example, the AI ​​can use keyword matching or machine learning algorithms to detect offensive messages. Step 2: The identification unit identifies the user who posted the offensive message detected by the detection unit. For example, the identification unit analyzes the user ID or IP address to identify the user who posted the offensive message. The identification unit can also use AI to analyze the user's posting history and behavioral patterns to identify the user who posted the offensive message. Step 3: The notification unit notifies the user identified by the identification unit. For example, the notification unit notifies the user of the posting of an offensive message by using an email notification or an in-app notification. The notification unit can also use AI to indicate specific parts of the offensive message and provide advice on how to correct it. For example, the notification unit highlights specific parts of the offensive message and provides examples and guidelines for correction.

[0110] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0112] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0113] For example, the detection unit is realized by acquiring a message posted by a user using the camera 42 or microphone 38B of the smart device 14, and performing AI analysis by the identification processing unit 290 of the data processing device 12. The identification unit, for example, analyzes a user ID or IP address by the identification processing unit 290 of the data processing device 12, and identifies a user who posted an offensive message. The notification unit, for example, issues an email notification or an in-app notification by the control unit 46A of the smart device 14, indicates specific parts of the offensive message, and provides correction examples and guidelines. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] 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, the RAM 30, and the 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.

[0117] 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.

[0118] 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 the voice according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0120] 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 performed in a secure state.

[0121] Fig. 4 shows an example of 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.

[0122] 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.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0125] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0126] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0127] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0128] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0129] For example, the detection unit is realized by acquiring a message posted by a user using the camera 42 and microphone 238 of the smart glasses 214, and performing AI analysis by the identification processing unit 290 of the data processing device 12. The identification unit, for example, analyzes a user ID or IP address by the identification processing unit 290 of the data processing device 12, and identifies a user who posted an offensive message. The notification unit, for example, issues an email notification or an in-app notification by the control unit 46A of the smart glasses 214, indicates specific parts of the offensive message, and provides correction examples and guidelines. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 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.

[0132] 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, the RAM 30, and the 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.

[0133] 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.

[0134] 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 the voice according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0136] 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 performed in a secure state.

[0137] 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.

[0138] 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.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0140] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0141] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0142] 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 voice indicating a user input for 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.

[0143] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0144] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0145] For example, the detection unit is realized by acquiring messages posted by users using the camera 42 and microphone 238 of the headset type terminal 314, and performing AI analysis by the identification processing unit 290 of the data processing device 12. The identification unit, for example, analyzes a user ID or IP address by the identification processing unit 290 of the data processing device 12, and identifies the user who posted the offensive message. The notification unit, for example, issues an email notification or an in-app notification by the control unit 46A of the headset type terminal 314, indicates specific parts of the offensive message, and provides correction examples and guidelines. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] 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, the RAM 30, and the 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.

[0149] 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.

[0150] 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 the voice according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0152] 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 performed in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0154] 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.

[0155] 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.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0158] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] 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 a voice indicating a user input for 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.

[0160] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0161] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0162] For example, the detection unit is realized by acquiring messages posted by users using the camera 42 and microphone 238 of the robot 414, and performing AI analysis by the identification processing unit 290 of the data processing device 12. The identification unit, for example, analyzes a user ID or IP address by the identification processing unit 290 of the data processing device 12, and identifies the user who posted the offensive message. The notification unit, for example, issues an email notification or an in-app notification by the control unit 46A of the robot 414, indicates specific parts of the offensive message, and provides correction examples and guidelines. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0163] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0164] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0166] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0167] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0168] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0170] 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.

[0171] 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 Universal Serial Bus (USB) 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.

[0172] In addition, 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 upon request from the data processing device 12.

[0173] 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.

[0174] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0175] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0176] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0177] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0179] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0181] (Appendix 1) A system comprising: a detection unit that detects offensive posted messages; an identification unit that identifies users who have posted the offensive messages detected by the detection unit; and a notification unit that notifies the users identified by the identification unit. (Appendix 2) The system of claim 1, wherein the notification unit indicates specific parts of the offensive message and provides advice on how to modify it. (Appendix 3) The system described in Appendix 1, further comprising a processing unit that performs selectable processing on the recipient side based on the offensive message. (Appendix 4) The system described in Appendix 1, characterized in that the detection unit estimates the poster's emotions and improves the accuracy of detecting offensive messages based on the estimated poster's emotions. (Appendix 5) The system described in Appendix 1, characterized in that the detection unit analyzes past posting history and learns patterns of aggressive messages from specific users to improve detection accuracy. (Appendix 6) The system described in Appendix 1, characterized in that the detection unit analyzes the context of a posted message and identifies parts that may contain offensive content. (Appendix 7) The system described in Appendix 1, wherein the detection unit estimates the poster's emotions and adjusts the timing of detecting aggressive messages based on the estimated poster's emotions. (Appendix 8) The system described in Appendix 1, characterized in that the detection unit adjusts detection criteria for offensive content taking into account the language and cultural background of the posted message. (Appendix 9) The system of claim 1, wherein the detection unit integrates data from social media and other online platforms to improve accuracy in detecting offensive messages. (Appendix 10) The system described in Appendix 1, wherein the identification unit estimates the poster's emotions and improves the accuracy of identifying offensive messages based on the estimated poster's emotions. (Appendix 11) The system described in Appendix 1, wherein the identification unit analyzes the poster's past behavioral history to improve the accuracy of identifying offensive messages. (Appendix 12) The system described in Appendix 1, characterized in that the identification unit improves the accuracy of identifying offensive messages by utilizing the poster's IP address and device information. (Appendix 13) The system described in Appendix 1, wherein the identification unit estimates the poster's emotions and determines the identification priority of offensive messages based on the estimated poster's emotions. (Appendix 14) The system of claim 1, wherein the identification unit improves the accuracy of identifying offensive messages by taking into account the geographic location information of the poster. (Appendix 15) The system of claim 1, wherein the identification unit analyzes the poster's social media activity to improve accuracy in identifying offensive messages. (Appendix 16) The system described in Appendix 1, wherein the notification unit estimates the poster's emotions and adjusts the manner in which the aggressive message is notified based on the estimated emotions of the poster. (Appendix 17) The system according to claim 1, wherein the notification unit refers to past notification history and selects the optimal notification method for an offensive message. (Appendix 18) The system described in claim 1, wherein the notification unit estimates the poster's emotions and adjusts the timing of notification of aggressive messages based on the estimated poster's emotions. (Appendix 19) The system according to claim 1, wherein the notification unit adjusts the content of the notification of an offensive message taking into account the language and cultural background of the poster. (Appendix 20) The system described in Appendix 1, wherein the notification unit analyzes the poster's social media activity and selects the optimal method of notifying the offensive message. (Appendix 21) 3. The system of claim 2, wherein the processing unit estimates a recipient's emotion and provides selectable handling of aggressive messages based on the estimated recipient's emotion. (Appendix 22) The system described in Appendix 2, characterized in that the processing unit filters aggressive messages on the recipient's side or converts them into milder text based on the content of the messages. (Appendix 23) The system described in Appendix 2, characterized in that the processing unit analyzes the recipient's past message receiving history and selects the optimal method for handling offensive messages. (Appendix 24) The system according to claim 2, wherein the processing unit estimates a recipient's emotions and determines a priority for processing offensive messages based on the estimated recipient's emotions. (Appendix 25) The system according to claim 2, wherein the processing unit selects an optimal method for processing an offensive message taking into account the geographic location information of the recipient. (Appendix 26) The system of claim 2, wherein the processing unit analyzes the recipient's social media activity and selects an optimal way to handle offensive messages. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A detection unit for detecting offensive posted messages; an identification unit that identifies a user who posted an offensive message detected by the detection unit; a notification unit that notifies the user identified by the identification unit. A system characterized by:

2. The notification unit is Identify specific parts of the offensive message and provide advice on how to modify it 2. The system of claim 1 .

3. a processing unit that performs a process selectable by a recipient based on the offensive message detected by the detection unit; 2. The system of claim 1 .

4. The detection unit is Estimate the poster's emotions and improve the accuracy of detecting offensive messages based on the estimated emotions of the poster.

2. The system of claim 1 .

5. The detection unit is Analyze past posting history and learn the patterns of abusive messages from specific users to improve detection accuracy 2. The system of claim 1 .

6. The detection unit is Analyze the context of posted messages to identify potentially offensive content 2. The system of claim 1 .

7. The detection unit is Estimate the poster's emotions and adjust the timing of detecting offensive messages based on the estimated emotions of the poster.

2. The system of claim 1 .

8. The detection unit is Adjusting criteria for detecting offensive content by taking into account the language and cultural context of the message 2. The system of claim 1 .

9. The detection unit is Integrating data from social media and other online platforms to improve detection of offensive messages 2. The system of claim 1 .

Images