system

Abstract

An object of a system according to an embodiment is to enable adolescents to work safely on an SNS.SOLUTION: A system includes an analysis unit, a warning unit, and a notification unit. The analysis unit analyzes a message or content on the SNS. The warning unit displays a warning message based on the inappropriate content detected by the analysis unit. The notification unit notifies the protector of the warning message generated by the warning unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, young people are at risk of encountering inappropriate messages or dangerous content on social media, making it difficult for parents to respond appropriately.

[0005] The system according to the embodiment aims to enable young people to safely engage in social networking services. [Means for solving the problem]

[0006] A system according to an embodiment includes an analysis unit, a warning unit, and a notification unit. The analysis unit analyzes messages or content on an SNS. The warning unit displays a warning message based on inappropriate content detected by the analysis unit. The notification unit notifies a parent or guardian of the warning message generated by the warning unit. [Effects of the Invention]

[0007] The system according to the embodiment can enable young people to safely engage in activities on SNS. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention is a tool for preventing young people from becoming involved in crimes on social media. The system uses generative AI to analyze messages and content on social media to detect inappropriate or dangerous content. It then displays a warning message to young people based on the detected inappropriate content. Furthermore, if a problem occurs, it notifies parents of a summary while protecting the user's privacy. For example, the system analyzes messages and content on social media to detect violent language, sexual content, or potentially fraudulent messages. Based on the detected inappropriate content, the system then displays a warning message to young people, such as "This message contains dangerous content. Please do not reply." It also displays educational messages to young people, such as "Please be careful when handling personal information on social media." Furthermore, if a problem occurs, the system notifies parents, such as "The message your child received contained dangerous content. Please discuss the details with your child." The specific content is concealed to protect the young person's privacy. This allows the system to keep young people's social media use safe and allows parents to monitor their activities with peace of mind. For example, young people can learn how to use social media and enjoy social media safely while their privacy is protected. In addition, parents can safely monitor their children's social media activities while maintaining a reasonable distance from them, regardless of whether they are online literate or not.

[0029] An SNS safety management system according to an embodiment includes an analysis unit, a warning unit, and a notification unit. The analysis unit analyzes messages and content on SNS to detect inappropriate content or dangerous elements. For example, the analysis unit detects violent language or discriminatory remarks using text analysis. The analysis unit can also detect sexual content using image analysis. The analysis unit can also detect potentially fraudulent messages using audio analysis. The warning unit displays a warning message to a minor based on the detected inappropriate content. For example, the warning unit displays a text message such as "This message contains dangerous content. Please do not reply." The warning unit can also display the warning message using a pop-up notification. The warning unit can also display the warning message using an audio alert. When a problem occurs, the notification unit notifies a parent or guardian of a summary while protecting the user's privacy. For example, the notification unit sends an email notification such as "The message your child received contains dangerous content. Please discuss the details with your child." The notification unit can also notify a parent or guardian of a summary using an SMS notification. The notification unit can also notify a parent or guardian of a summary using an in-app notification. As a result, the SNS safety management system according to the embodiment keeps young people's use of SNS safe, allowing parents to watch over them with peace of mind.

[0030] The analysis unit can analyze messages or content on SNS to detect inappropriate or dangerous content. Examples of inappropriate or dangerous content include, but are not limited to, violent content, fraudulent content, and the leakage of personal information. The analysis unit can, for example, use text analysis to detect violent language or discriminatory remarks. The analysis unit can also use image analysis to detect sexual content. The analysis unit can also use audio analysis to detect potentially fraudulent messages. This helps ensure the safety of young people by detecting inappropriate or dangerous content on SNS. Some or all of the above-described processing by the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input messages or content on SNS into a generation AI and have the generation AI detect inappropriate content or dangerous elements.

[0031] The warning unit can display a warning message to the minor based on the detected inappropriate content. Examples of inappropriate content include, but are not limited to, violent content, discriminatory remarks, and sexual content. Examples of warning messages include, but are not limited to, a text message, a pop-up notification, and an audio alert. For example, the warning unit can display a text message such as, "This message contains dangerous content. Please do not reply." The warning unit can also display the warning message using a pop-up notification. The warning unit can also display the warning message using an audio alert. Displaying the warning message to the minor can alert them to the inappropriate content. Some or all of the above-described processing by the warning unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the warning unit can cause the generation AI to execute a warning message based on the inappropriate content detected by the generation AI.

[0032] When a problem occurs, the notification unit can notify the parent or guardian of a summary while protecting the user's privacy. Examples of privacy protection methods include, but are not limited to, anonymizing personal information and encrypting data. Examples of the summary notification include, but are not limited to, the type of problem, the date and time of occurrence, and the scope of the impact. The notification unit can send an email notification stating, for example, "A message received by your child contained dangerous content. Please discuss the details with your child." The notification unit can also notify the parent or guardian of the summary using an SMS notification. The notification unit can also notify the parent or guardian of the summary using an in-app notification. This allows the parent or guardian to take appropriate action while protecting the user's privacy. Some or all of the above-described processing by the notification unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the notification unit can cause the generation AI to execute a summary of the problem detected by the generation AI.

[0033] The warning unit can display educational messages to encourage appropriate behavior among young people. Examples of content encouraging appropriate behavior include, but are not limited to, specific guidelines for behavior and educational message content. For example, the warning unit can display educational messages such as, "Be careful when handling personal information on social networking sites." The warning unit can also display specific guidelines for behavior such as, "Do not reply to messages from unknown people." The warning unit can also display advice such as, "If a message contains dangerous content, consult your parents immediately." By displaying educational messages encouraging appropriate behavior among young people, safe use of social networking sites can be promoted. Some or all of the above-described processing by the warning unit can be performed, for example, using or without a generation AI. For example, the warning unit can cause the generation AI to execute educational messages based on inappropriate content detected by the generation AI.

[0034] The notification unit can conceal specific details when notifying a parent of an overview of a problem detected by the generation AI. Methods for concealing specific details include, but are not limited to, masking specific keywords and omitting detailed information. For example, the notification unit may conceal specific details when sending an email notification such as, "The message your child received contained dangerous content. Please discuss the details with your child." The notification unit can also mask specific keywords when notifying a parent of the overview via SMS notification. The notification unit can also omit detailed information when notifying a parent of the overview via in-app notification. By concealing specific details, the notification unit can notify a parent while protecting the privacy of the minor. Some or all of the above-described processing by the notification unit may be performed using, or without, the generation AI. For example, the notification unit can cause the generation AI to execute a summary of the problem detected by the generation AI.

[0035] The analysis unit can more accurately detect inappropriate content by taking into account the context of the message during analysis. Methods for taking the context into account include, but are not limited to, analyzing preceding and following messages and extracting related topics. For example, the analysis unit can analyze the context of the message and detect inappropriate content based on the context. The analysis unit can also consider the continuity of messages and detect content that is acceptable when used alone but inappropriate when used consecutively. The analysis unit can also analyze the tone and nuance of the message and detect inappropriate content based on the context. Thus, by taking the context of the message into account, inappropriate content can be more accurately detected. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input message context data into the generation AI and have the generation AI detect inappropriate content.

[0036] During analysis, the analysis unit can evaluate the risk level by referring to the sender's past behavioral history. Methods for referring to the past behavioral history include, but are not limited to, analyzing past message history and behavioral patterns. For example, the analysis unit may evaluate the risk level as high if the sender has a history of sending inappropriate messages in the past. The analysis unit may also evaluate the risk level as high if the sender has a history of receiving warnings in the past. The analysis unit may also evaluate the risk level as low if the sender has no history of engaging in problematic behavior in the past. This allows for a more accurate evaluation of the risk level by referring to the sender's past behavioral history. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI or without a generation AI. For example, the analysis unit may input the sender's past behavioral history data into the generation AI and have the generation AI evaluate the risk level.

[0037] During analysis, the analysis unit can improve the accuracy of the analysis by taking into account the time period during which the message was sent. Methods for taking into account the time period during which the message was sent include, but are not limited to, analyzing behavioral patterns by time period and assessing risk according to the time period. For example, the analysis unit may evaluate a message sent late at night as being highly dangerous. The analysis unit may also evaluate a message sent during school hours as containing content requiring caution. The analysis unit may also evaluate messages sent on holidays with normal analysis accuracy. In this way, the accuracy of the analysis can be improved by taking into account the time period during which the message was sent. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit may input data on the time period during which the message was sent into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0038] During analysis, the analysis unit can detect inappropriate content by taking into account the geographical source of the message. Methods for taking into account the geographical source include, but are not limited to, analyzing IP addresses and using location information. For example, the analysis unit may evaluate messages from specific regions as being highly dangerous. The analysis unit may also evaluate messages from overseas as requiring caution. The analysis unit may also evaluate messages from the user's residential area with normal analysis accuracy. By taking into account the geographical source of the message, inappropriate content can be detected more accurately. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI. For example, the analysis unit may input the geographical source data of the message into the generation AI and cause the generation AI to detect inappropriate content.

[0039] During analysis, the analysis unit can analyze images and videos related to the message to detect inappropriate content. Methods for analyzing related images and videos include, but are not limited to, image recognition technology and video analysis algorithms. For example, the analysis unit can analyze images attached to the message to detect inappropriate content. The analysis unit can also analyze videos attached to the message to detect inappropriate content. The analysis unit can also comprehensively analyze images and videos related to the message text to detect inappropriate content. This allows for more accurate detection of inappropriate content by analyzing images and videos related to the message. Some or all of the above-described processing by the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input image and video data attached to the message into the generation AI and have the generation AI detect inappropriate content.

[0040] During analysis, the analysis unit can adjust the analysis algorithm taking into account the language and slang of the message. Methods for taking language and slang into account include, but are not limited to, applying a language model or using a slang dictionary. For example, the analysis unit can analyze the language of the message and evaluate it as inappropriate if it contains specific slang. The analysis unit can also apply an appropriate analysis algorithm if the message is written in a different language. The analysis unit can also analyze the slang of the message and detect inappropriate content based on the context. This allows the analysis algorithm to be appropriately adjusted by taking into account the language and slang of the message. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the language and slang data of the message into the generation AI and have the generation AI adjust the analysis algorithm.

[0041] When displaying a warning message, the warning unit can adjust the level of detail of the warning based on the importance of the message. Methods for evaluating the importance of a message include, but are not limited to, the urgency of the content and the scope of impact. Methods for adjusting the level of detail of the warning include, but are not limited to, displaying detailed information according to the importance or providing a simplified warning. For example, the warning unit can display a detailed warning message for a message of high importance. The warning unit can also display a concise warning message for a message of medium importance. The warning unit can also display a light warning message for a message of low importance. In this way, adjusting the level of detail of the warning based on the importance of the message enables appropriate warnings. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input message importance data into the generation AI and cause the generation AI to adjust the level of detail of the warning.

[0042] When displaying a warning message, the warning unit can apply different warning algorithms depending on the message category. Methods for classifying message categories include, but are not limited to, a category classification algorithm or a predefined category list. Specific types and implementation methods of the warning algorithm include, but are not limited to, a rule-based algorithm or a machine learning algorithm. For example, the warning unit can display a strong warning message for a violent message. The warning unit can also display an appropriate warning message for a message containing sexual content. The warning unit can also display a warning message urging caution for a message that may be fraudulent. This allows for appropriate warnings by applying different warning algorithms depending on the message category. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input message category data into the generation AI and have the generation AI apply the warning algorithm.

[0043] When displaying a warning message, the warning unit can improve the accuracy of the warning by referring to the user's past warning history. Methods for referring to the past warning history include, but are not limited to, using a warning history database and analyzing history data. For example, the warning unit displays an appropriate warning message based on the user's past warning history. The warning unit can also display an emphasized warning message based on the user's past ignored warning history. The warning unit can also display a normal warning message based on the user's past obeyed warning history. In this way, the accuracy of the warning can be improved by referring to the user's past warning history. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input the user's past warning history data into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0044] When displaying a warning message, the warning unit can determine the priority of the warning based on the time the message was sent. Methods for considering the time the message was sent include, but are not limited to, risk assessment by time period and prioritization according to the time the message was sent. Methods for determining the priority of the warning include, but are not limited to, prioritization based on risk assessment and prioritization according to urgency. For example, the warning unit can prioritize displaying a warning message for messages sent late at night. The warning unit can also display a warning message that calls attention to messages sent during school hours. The warning unit can also display a regular warning message for messages sent on holidays. This enables appropriate warnings by determining the priority of the warning based on the time the message was sent. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input message sending time data into the generation AI and have the generation AI determine the priority of the warning.

[0045] When displaying warning messages, the warning unit can adjust the order of warnings based on the relevance of the messages. Methods for evaluating the relevance of messages include, but are not limited to, content similarity and extraction of related topics. Methods for adjusting the order of warnings include, but are not limited to, ordering based on relevance and changing the display order according to priority. For example, the warning unit can display a warning message first for important messages. The warning unit can also display a warning message second for messages of medium importance. The warning unit can also display a warning message last for messages of low importance. This allows for appropriate warnings by adjusting the order of warnings based on the relevance of messages. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input message relevance data into the generation AI and cause the generation AI to adjust the order of warnings.

[0046] When displaying a warning message, the warning unit can adjust the use of technical terms in the warning depending on the user's age and level of comprehension. Methods for evaluating the user's age and level of comprehension include, but are not limited to, evaluation criteria based on age groups and the results of comprehension tests. Methods for adjusting the use of technical terms include, but are not limited to, selecting terms based on age and level of comprehension and using simple expressions. For example, the warning unit can display a warning message in simple language to younger users. The warning unit can also display a warning message in easy-to-understand language to older users. The warning unit can also display a detailed warning message to users who can understand technical terms. This allows for appropriate warnings by adjusting the use of technical terms in the warning depending on the user's age and level of comprehension. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input the user's age and level of comprehension data into the generation AI and cause the generation AI to adjust the use of technical terms in the warning.

[0047] The notification unit can adjust the level of detail of the notification based on the importance of the problem when sending a notification. Methods for evaluating the importance of the problem include, but are not limited to, the urgency of the content and the scope of the impact. Methods for adjusting the level of detail of the notification include, but are not limited to, displaying detailed information according to the importance or providing a simplified notification. For example, the notification unit can display detailed notification content for problems of high importance. The notification unit can also display concise notification content for problems of medium importance. The notification unit can also display brief notification content for problems of low importance. This allows for appropriate notification by adjusting the level of detail of the notification based on the importance of the problem. Some or all of the above-described processing in the notification unit can be performed using, or without, a generation AI. For example, the notification unit can input problem importance data into the generation AI and cause the generation AI to adjust the level of detail of the notification.

[0048] The notification unit can apply different notification algorithms depending on the problem category when notifying. Methods for classifying problem categories include, but are not limited to, category classification algorithms and predefined category lists. Specific types and implementation methods of the notification algorithm include, but are not limited to, rule-based algorithms and machine learning algorithms. For example, the notification unit can display strong notification content for violent problems. The notification unit can also display appropriate notification content for problems containing sexual content. The notification unit can also display warning content for problems that may be fraudulent. This allows for appropriate notification by applying different notification algorithms depending on the problem category. Some or all of the above-mentioned processing in the notification unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the notification unit can input problem category data into the generation AI and have the generation AI apply the notification algorithm.

[0049] The notification unit can improve the accuracy of notifications by referring to the guardian's past notification history when notifying the guardian. Methods for referring to the past notification history include, but are not limited to, using a notification history database and analyzing history data. The notification unit, for example, displays appropriate notification content based on the guardian's past notification history. The notification unit can also display emphasized notification content based on the guardian's past ignored notification history. The notification unit can also display regular notification content based on the guardian's past notification history. In this way, the accuracy of notifications can be improved by referring to the guardian's past notification history. Some or all of the above-described processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input the guardian's past notification history data into the generation AI and cause the generation AI to improve the accuracy of notifications.

[0050] The notification unit can determine the priority of notifications based on the time when the problem occurred when notifying the user. Methods for considering the time when the problem occurred include, but are not limited to, risk assessment by time period and prioritization according to the time of occurrence. Methods for determining the priority of notifications include, but are not limited to, prioritization based on risk assessment and setting priorities according to urgency. For example, the notification unit can prioritize displaying notification content for problems that occurred late at night. The notification unit can also display notification content that calls attention to problems that occurred during school hours. The notification unit can also display regular notification content for problems that occurred on holidays. This enables appropriate notification by determining the priority of notifications based on the time when the problem occurred. Some or all of the above-described processing by the notification unit can be performed using, for example, a generation AI, or without using a generation AI. For example, the notification unit can input data on the time when the problem occurred into the generation AI and have the generation AI determine the priority of notifications.

[0051] The notification unit can adjust the order of notifications based on the relevance of the questions when notifying the user. Methods for evaluating the relevance of questions include, but are not limited to, content similarity and extraction of related topics. Methods for adjusting the order of notifications include, but are not limited to, ordering based on relevance and changing the display order according to priority. For example, the notification unit can display notification content first for important questions. The notification unit can also display notification content second for questions of medium importance. The notification unit can also display notification content last for questions of low importance. This allows for appropriate notifications by adjusting the order of notifications based on the relevance of the questions. Some or all of the above-described processing in the notification unit can be performed using, or without, a generation AI. For example, the notification unit can input question relevance data into the generation AI and have the generation AI adjust the order of notifications.

[0052] The notification unit can adjust the use of technical terms in the notification depending on the parent's internet literacy when providing the notification. Methods for assessing internet literacy include, but are not limited to, survey results and past behavioral history. Methods for adjusting the use of technical terms include, but are not limited to, selecting terms appropriate for the parent's internet literacy and using simple expressions. For example, the notification unit can display notification content in simple language to parents with low internet literacy. The notification unit can also display detailed notification content to parents with high internet literacy. The notification unit can also display notification content including technical terms to parents who can understand technical terms. This allows for appropriate notification by adjusting the use of technical terms in the notification depending on the parent's internet literacy. Some or all of the above-described processing in the notification unit can be performed using, or without, a generation AI. For example, the notification unit can input the parent's internet literacy data into the generation AI and cause the generation AI to adjust the use of technical terms in the notification.

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

[0054] When analyzing messages and content on social media, the analysis unit can improve the accuracy of the analysis by taking into account the user's past behavioral patterns. For example, by analyzing what kind of messages the user has responded to in the past and what kind of content they prefer to view, it is possible to detect inappropriate content with greater accuracy. The analysis unit can also refer to the history of warning messages the user has received in the past and adjust the strength of the warning if a similar pattern is observed. Furthermore, the analysis unit can evaluate the risk for specific time periods and situations based on the user's past behavioral patterns and adjust the priority of the analysis. This allows for more effective analysis and warnings by taking into account the user's behavioral patterns.

[0055] When analyzing messages and content on social media, the analysis unit can evaluate the trustworthiness of the message sender. For example, if the sender has a history of sending inappropriate messages in the past, the unit can evaluate the sender's trustworthiness low and prioritize the display of a warning message. Also, if the sender is a trustworthy person, the unit can refrain from displaying a warning message. Furthermore, the analysis priority can be adjusted based on the sender's trustworthiness. This allows for more effective analysis and warnings by taking the sender's trustworthiness into consideration.

[0056] The notification unit can adjust the way the notification content is expressed depending on the parent's internet literacy. For example, for parents with low internet literacy, the notification content can be displayed in simple language to make it easier to understand. For parents with high internet literacy, detailed notification content can be displayed to encourage deeper understanding. Furthermore, notification content including technical terms can be displayed to parents who can understand technical terms. This makes it possible to provide appropriate notifications by adjusting the way the notification content is expressed depending on the parent's internet literacy.

[0057] When analyzing messages and content on social media, the analysis unit can improve the accuracy of the analysis by taking into account the geographic location information of the message sender. For example, messages from a specific region can be evaluated as being highly dangerous. Messages from overseas can also be evaluated as containing content requiring caution. Furthermore, messages from the user's residential area can be evaluated with normal analysis accuracy. This allows for more accurate detection of inappropriate content by taking into account the geographical source of the message.

[0058] The notification unit can adjust the priority of notification content by referring to the guardian's past notification history. For example, if the guardian has a history of ignoring notifications in the past, notifications with similar content can be displayed with priority to attract their attention. Also, if the guardian has a history of following notifications in the past, notifications with similar content can be displayed with normal priority. Furthermore, based on the history of notifications received by the guardian in the past, notifications with high importance can also be displayed with priority. In this way, by referring to the guardian's past notification history, the priority of notification content can be adjusted, enabling more effective notifications.

[0059] When analyzing messages and content on social media, the analysis unit takes into account the context of the message to more accurately detect inappropriate content. For example, it can analyze the context of the message and detect inappropriate content based on the context. It can also take into account the continuity of messages to detect content that is acceptable when used alone but inappropriate when used in succession. It can also analyze the tone and nuance of the message to detect inappropriate content based on the context. This allows for more accurate detection of inappropriate content by taking into account the context of the message.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The analysis unit analyzes messages and content on social media to detect inappropriate or dangerous content. For example, text analysis can be used to detect violent or discriminatory language, image analysis to detect sexual content, and audio analysis to detect potentially fraudulent messages. Step 2: The warning unit displays a warning message to the minor based on the inappropriate content detected by the analysis unit. For example, the warning message may be a text message such as "This message contains dangerous content. Please do not reply.", or a pop-up notification or a voice alert. Step 3: The notification unit notifies the parent of the warning message generated by the warning unit. For example, the notification unit notifies the parent of an overview via email, SMS, or in-app notification, such as "The message your child received contained dangerous content. Please discuss the details with your child."

[0062] (Example 2) A system according to an embodiment of the present invention is a tool for preventing young people from becoming involved in crimes on social media. The system uses generative AI to analyze messages and content on social media to detect inappropriate or dangerous content. It then displays a warning message to young people based on the detected inappropriate content. Furthermore, if a problem occurs, it notifies parents of a summary while protecting the user's privacy. For example, the system analyzes messages and content on social media to detect violent language, sexual content, or potentially fraudulent messages. Based on the detected inappropriate content, the system then displays a warning message to young people, such as "This message contains dangerous content. Please do not reply." It also displays educational messages to young people, such as "Please be careful when handling personal information on social media." Furthermore, if a problem occurs, the system notifies parents, such as "The message your child received contained dangerous content. Please discuss the details with your child." The specific content is concealed to protect the young person's privacy. This allows the system to keep young people's social media use safe and allows parents to monitor their activities with peace of mind. For example, young people can learn how to use social media and enjoy social media safely while their privacy is protected. In addition, parents can safely monitor their children's social media activities while maintaining a reasonable distance from them, regardless of whether they are online literate or not.

[0063] An SNS safety management system according to an embodiment includes an analysis unit, a warning unit, and a notification unit. The analysis unit analyzes messages and content on SNS to detect inappropriate content or dangerous elements. For example, the analysis unit detects violent language or discriminatory remarks using text analysis. The analysis unit can also detect sexual content using image analysis. The analysis unit can also detect potentially fraudulent messages using audio analysis. The warning unit displays a warning message to a minor based on the detected inappropriate content. For example, the warning unit displays a text message such as "This message contains dangerous content. Please do not reply." The warning unit can also display the warning message using a pop-up notification. The warning unit can also display the warning message using an audio alert. When a problem occurs, the notification unit notifies a parent or guardian of a summary while protecting the user's privacy. For example, the notification unit sends an email notification such as "The message your child received contains dangerous content. Please discuss the details with your child." The notification unit can also notify a parent or guardian of a summary using an SMS notification. The notification unit can also notify a parent or guardian of a summary using an in-app notification. As a result, the SNS safety management system according to the embodiment keeps young people's use of SNS safe, allowing parents to watch over them with peace of mind.

[0064] The analysis unit can analyze messages or content on SNS to detect inappropriate or dangerous content. Examples of inappropriate or dangerous content include, but are not limited to, violent content, fraudulent content, and the leakage of personal information. The analysis unit can, for example, use text analysis to detect violent language or discriminatory remarks. The analysis unit can also use image analysis to detect sexual content. The analysis unit can also use audio analysis to detect potentially fraudulent messages. This helps ensure the safety of young people by detecting inappropriate or dangerous content on SNS. Some or all of the above-described processing by the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input messages or content on SNS into a generation AI and have the generation AI detect inappropriate content or dangerous elements.

[0065] The warning unit can display a warning message to the minor based on the detected inappropriate content. Examples of inappropriate content include, but are not limited to, violent content, discriminatory remarks, and sexual content. Examples of warning messages include, but are not limited to, a text message, a pop-up notification, and an audio alert. For example, the warning unit can display a text message such as, "This message contains dangerous content. Please do not reply." The warning unit can also display the warning message using a pop-up notification. The warning unit can also display the warning message using an audio alert. Displaying the warning message to the minor can alert them to the inappropriate content. Some or all of the above-described processing by the warning unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the warning unit can cause the generation AI to execute a warning message based on the inappropriate content detected by the generation AI.

[0066] When a problem occurs, the notification unit can notify the parent or guardian of a summary while protecting the user's privacy. Examples of privacy protection methods include, but are not limited to, anonymizing personal information and encrypting data. Examples of the summary notification include, but are not limited to, the type of problem, the date and time of occurrence, and the scope of the impact. The notification unit can send an email notification stating, for example, "A message received by your child contained dangerous content. Please discuss the details with your child." The notification unit can also notify the parent or guardian of the summary using an SMS notification. The notification unit can also notify the parent or guardian of the summary using an in-app notification. This allows the parent or guardian to take appropriate action while protecting the user's privacy. Some or all of the above-described processing by the notification unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the notification unit can cause the generation AI to execute a summary of the problem detected by the generation AI.

[0067] The warning unit can display educational messages to encourage appropriate behavior among young people. Examples of content encouraging appropriate behavior include, but are not limited to, specific guidelines for behavior and educational message content. For example, the warning unit can display educational messages such as, "Be careful when handling personal information on social networking sites." The warning unit can also display specific guidelines for behavior such as, "Do not reply to messages from unknown people." The warning unit can also display advice such as, "If a message contains dangerous content, consult your parents immediately." By displaying educational messages encouraging appropriate behavior among young people, safe use of social networking sites can be promoted. Some or all of the above-described processing by the warning unit can be performed, for example, using or without a generation AI. For example, the warning unit can cause the generation AI to execute educational messages based on inappropriate content detected by the generation AI.

[0068] The notification unit can conceal specific details when notifying a parent of an overview of a problem detected by the generation AI. Methods for concealing specific details include, but are not limited to, masking specific keywords and omitting detailed information. For example, the notification unit may conceal specific details when sending an email notification such as, "The message your child received contained dangerous content. Please discuss the details with your child." The notification unit can also mask specific keywords when notifying a parent of the overview via SMS notification. The notification unit can also omit detailed information when notifying a parent of the overview via in-app notification. By concealing specific details, the notification unit can notify a parent while protecting the privacy of the minor. Some or all of the above-described processing by the notification unit may be performed using, or without, the generation AI. For example, the notification unit can cause the generation AI to execute a summary of the problem detected by the generation AI.

[0069] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated user emotions. Methods for estimating the user's emotions include, but are not limited to, emotion analysis algorithms and facial expression recognition technology. Methods for adjusting the analysis priority include, but are not limited to, prioritizing based on emotion scores and applying real-time analysis. For example, if the user is feeling anxious, the analysis unit can cause the generation AI to prioritize analyzing inappropriate content. Furthermore, if the user is relaxed, the analysis unit can also cause the generation AI to proceed in the normal analysis order. Furthermore, if the user is excited, the analysis unit can cause the generation AI to prioritize analyzing content with high urgency. This allows for more appropriate analysis by adjusting the analysis priority based on the user's emotions. Some or all of the above-described processing in the analysis unit can be performed using, or without, the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the analysis priority.

[0070] The analysis unit can more accurately detect inappropriate content by taking into account the context of the message during analysis. Methods for taking the context into account include, but are not limited to, analyzing preceding and following messages and extracting related topics. For example, the analysis unit can analyze the context of the message and detect inappropriate content based on the context. The analysis unit can also consider the continuity of messages and detect content that is acceptable when used alone but inappropriate when used consecutively. The analysis unit can also analyze the tone and nuance of the message and detect inappropriate content based on the context. Thus, by taking the context of the message into account, inappropriate content can be more accurately detected. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input message context data into the generation AI and have the generation AI detect inappropriate content.

[0071] During analysis, the analysis unit can evaluate the risk level by referring to the sender's past behavioral history. Methods for referring to the past behavioral history include, but are not limited to, analyzing past message history and behavioral patterns. For example, the analysis unit may evaluate the risk level as high if the sender has a history of sending inappropriate messages in the past. The analysis unit may also evaluate the risk level as high if the sender has a history of receiving warnings in the past. The analysis unit may also evaluate the risk level as low if the sender has no history of engaging in problematic behavior in the past. This allows for a more accurate evaluation of the risk level by referring to the sender's past behavioral history. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI or without a generation AI. For example, the analysis unit may input the sender's past behavioral history data into the generation AI and have the generation AI evaluate the risk level.

[0072] During analysis, the analysis unit can improve the accuracy of the analysis by taking into account the time period during which the message was sent. Methods for taking into account the time period during which the message was sent include, but are not limited to, analyzing behavioral patterns by time period and assessing risk according to the time period. For example, the analysis unit may evaluate a message sent late at night as being highly dangerous. The analysis unit may also evaluate a message sent during school hours as containing content requiring caution. The analysis unit may also evaluate messages sent on holidays with normal analysis accuracy. In this way, the accuracy of the analysis can be improved by taking into account the time period during which the message was sent. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit may input data on the time period during which the message was sent into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0073] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. Methods for estimating the user's emotions include, but are not limited to, emotion analysis algorithms and facial expression recognition technology. Methods for adjusting the display method of the analysis results include, but are not limited to, changing the display format according to the emotion and customizing the display content. For example, the analysis unit can display the analysis results concisely when the user is feeling anxious. The analysis unit can also display detailed analysis results when the user is relaxed. The analysis unit can also highlight important analysis results when the user is excited. This allows for more appropriate display by adjusting the display method of the analysis results based on the user's emotions. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the display method of the analysis results.

[0074] During analysis, the analysis unit can detect inappropriate content by taking into account the geographical source of the message. Methods for taking into account the geographical source include, but are not limited to, analyzing IP addresses and using location information. For example, the analysis unit may evaluate messages from specific regions as being highly dangerous. The analysis unit may also evaluate messages from overseas as requiring caution. The analysis unit may also evaluate messages from the user's residential area with normal analysis accuracy. By taking into account the geographical source of the message, inappropriate content can be detected more accurately. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI. For example, the analysis unit may input the geographical source data of the message into the generation AI and cause the generation AI to detect inappropriate content.

[0075] During analysis, the analysis unit can analyze images and videos related to the message to detect inappropriate content. Methods for analyzing related images and videos include, but are not limited to, image recognition technology and video analysis algorithms. For example, the analysis unit can analyze images attached to the message to detect inappropriate content. The analysis unit can also analyze videos attached to the message to detect inappropriate content. The analysis unit can also comprehensively analyze images and videos related to the message text to detect inappropriate content. This allows for more accurate detection of inappropriate content by analyzing images and videos related to the message. Some or all of the above-described processing by the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input image and video data attached to the message into the generation AI and have the generation AI detect inappropriate content.

[0076] During analysis, the analysis unit can adjust the analysis algorithm taking into account the language and slang of the message. Methods for taking language and slang into account include, but are not limited to, applying a language model or using a slang dictionary. For example, the analysis unit can analyze the language of the message and evaluate it as inappropriate if it contains specific slang. The analysis unit can also apply an appropriate analysis algorithm if the message is written in a different language. The analysis unit can also analyze the slang of the message and detect inappropriate content based on the context. This allows the analysis algorithm to be appropriately adjusted by taking into account the language and slang of the message. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the language and slang data of the message into the generation AI and have the generation AI adjust the analysis algorithm.

[0077] The warning unit can estimate the user's emotions and adjust the way the warning message is expressed based on the estimated user's emotions. Methods for estimating the user's emotions include, but are not limited to, emotion analysis algorithms and facial expression recognition technology. Methods for adjusting the way the warning message is expressed include, but are not limited to, changing the expression based on the user's emotions and adjusting the tone of the message. For example, if the user is feeling anxious, the warning unit can display a warning message in gentle language. If the user is relaxed, the warning unit can also display a normal warning message. If the user is excited, the warning unit can also display an emphasized warning message. This allows for more appropriate warnings by adjusting the way the warning message is expressed based on the user's emotions. Some or all of the above-described processing in the warning unit can be performed using, or without, a generation AI. For example, the warning unit can input user emotion data into the generation AI and cause the generation AI to adjust the way the warning message is expressed.

[0078] When displaying a warning message, the warning unit can adjust the level of detail of the warning based on the importance of the message. Methods for evaluating the importance of a message include, but are not limited to, the urgency of the content and the scope of impact. Methods for adjusting the level of detail of the warning include, but are not limited to, displaying detailed information according to the importance or providing a simplified warning. For example, the warning unit can display a detailed warning message for a message of high importance. The warning unit can also display a concise warning message for a message of medium importance. The warning unit can also display a light warning message for a message of low importance. In this way, adjusting the level of detail of the warning based on the importance of the message enables appropriate warnings. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input message importance data into the generation AI and cause the generation AI to adjust the level of detail of the warning.

[0079] When displaying a warning message, the warning unit can apply different warning algorithms depending on the message category. Methods for classifying message categories include, but are not limited to, a category classification algorithm or a predefined category list. Specific types and implementation methods of the warning algorithm include, but are not limited to, a rule-based algorithm or a machine learning algorithm. For example, the warning unit can display a strong warning message for a violent message. The warning unit can also display an appropriate warning message for a message containing sexual content. The warning unit can also display a warning message urging caution for a message that may be fraudulent. This allows for appropriate warnings by applying different warning algorithms depending on the message category. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input message category data into the generation AI and have the generation AI apply the warning algorithm.

[0080] When displaying a warning message, the warning unit can improve the accuracy of the warning by referring to the user's past warning history. Methods for referring to the past warning history include, but are not limited to, using a warning history database and analyzing history data. For example, the warning unit displays an appropriate warning message based on the user's past warning history. The warning unit can also display an emphasized warning message based on the user's past ignored warning history. The warning unit can also display a normal warning message based on the user's past obeyed warning history. In this way, the accuracy of the warning can be improved by referring to the user's past warning history. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input the user's past warning history data into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0081] The warning unit can estimate the user's emotions and adjust the length of the warning message based on the estimated user emotions. Methods for estimating the user's emotions include, but are not limited to, emotion analysis algorithms and facial expression recognition technology. Methods for adjusting the length of the warning message include, but are not limited to, shortening the message based on the emotion or adding detailed information. For example, if the user is feeling anxious, the warning unit can display a short and concise warning message. Furthermore, if the user is relaxed, the warning unit can display a detailed warning message. Furthermore, if the user is excited, the warning unit can display an emphasized warning message. This allows for more appropriate warnings by adjusting the length of the warning message based on the user's emotions. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input user emotion data into the generation AI and have the generation AI adjust the length of the warning message.

[0082] When displaying a warning message, the warning unit can determine the priority of the warning based on the time the message was sent. Methods for considering the time the message was sent include, but are not limited to, risk assessment by time period and prioritization according to the time the message was sent. Methods for determining the priority of the warning include, but are not limited to, prioritization based on risk assessment and prioritization according to urgency. For example, the warning unit can prioritize displaying a warning message for messages sent late at night. The warning unit can also display a warning message that calls attention to messages sent during school hours. The warning unit can also display a regular warning message for messages sent on holidays. This enables appropriate warnings by determining the priority of the warning based on the time the message was sent. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input message sending time data into the generation AI and have the generation AI determine the priority of the warning.

[0083] When displaying warning messages, the warning unit can adjust the order of warnings based on the relevance of the messages. Methods for evaluating the relevance of messages include, but are not limited to, content similarity and extraction of related topics. Methods for adjusting the order of warnings include, but are not limited to, ordering based on relevance and changing the display order according to priority. For example, the warning unit can display a warning message first for important messages. The warning unit can also display a warning message second for messages of medium importance. The warning unit can also display a warning message last for messages of low importance. This allows for appropriate warnings by adjusting the order of warnings based on the relevance of messages. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input message relevance data into the generation AI and cause the generation AI to adjust the order of warnings.

[0084] When displaying a warning message, the warning unit can adjust the use of technical terms in the warning depending on the user's age and level of comprehension. Methods for evaluating the user's age and level of comprehension include, but are not limited to, evaluation criteria based on age groups and the results of comprehension tests. Methods for adjusting the use of technical terms include, but are not limited to, selecting terms based on age and level of comprehension and using simple expressions. For example, the warning unit can display a warning message in simple language to younger users. The warning unit can also display a warning message in easy-to-understand language to older users. The warning unit can also display a detailed warning message to users who can understand technical terms. This allows for appropriate warnings by adjusting the use of technical terms in the warning depending on the user's age and level of comprehension. Some or all of the above-described processing in the warning unit may be performed using, or without, a generation AI. For example, the warning unit can input the user's age and level of comprehension data into the generation AI and cause the generation AI to adjust the use of technical terms in the warning.

[0085] The notification unit can estimate the user's emotions and adjust the way the notification content is presented based on the estimated user's emotions. Methods for estimating the user's emotions include, but are not limited to, emotion analysis algorithms and facial expression recognition technology. Methods for adjusting the way the notification content is presented include, but are not limited to, changing the expression based on the user's emotions and customizing the notification content. For example, if the user is feeling anxious, the notification unit can display the notification content in gentle language. If the user is relaxed, the notification unit can also display normal notification content. If the user is excited, the notification unit can also display emphasized notification content. This allows for more appropriate notification by adjusting the way the notification content is presented based on the user's emotions. Some or all of the above-described processing in the notification unit can be performed using, or without, a generation AI. For example, the notification unit can input the user's emotion data into the generation AI and have the generation AI adjust the way the notification content is presented.

[0086] The notification unit can adjust the level of detail of the notification based on the importance of the problem when sending a notification. Methods for evaluating the importance of the problem include, but are not limited to, the urgency of the content and the scope of the impact. Methods for adjusting the level of detail of the notification include, but are not limited to, displaying detailed information according to the importance or providing a simplified notification. For example, the notification unit can display detailed notification content for problems of high importance. The notification unit can also display concise notification content for problems of medium importance. The notification unit can also display brief notification content for problems of low importance. This allows for appropriate notification by adjusting the level of detail of the notification based on the importance of the problem. Some or all of the above-described processing in the notification unit can be performed using, or without, a generation AI. For example, the notification unit can input problem importance data into the generation AI and cause the generation AI to adjust the level of detail of the notification.

[0087] The notification unit can apply different notification algorithms depending on the problem category when notifying. Methods for classifying problem categories include, but are not limited to, category classification algorithms and predefined category lists. Specific types and implementation methods of the notification algorithm include, but are not limited to, rule-based algorithms and machine learning algorithms. For example, the notification unit can display strong notification content for violent problems. The notification unit can also display appropriate notification content for problems containing sexual content. The notification unit can also display warning content for problems that may be fraudulent. This allows for appropriate notification by applying different notification algorithms depending on the problem category. Some or all of the above-mentioned processing in the notification unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the notification unit can input problem category data into the generation AI and have the generation AI apply the notification algorithm.

[0088] The notification unit can improve the accuracy of notifications by referring to the guardian's past notification history when notifying the guardian. Methods for referring to the past notification history include, but are not limited to, using a notification history database and analyzing history data. The notification unit, for example, displays appropriate notification content based on the guardian's past notification history. The notification unit can also display emphasized notification content based on the guardian's past ignored notification history. The notification unit can also display regular notification content based on the guardian's past notification history. In this way, the accuracy of notifications can be improved by referring to the guardian's past notification history. Some or all of the above-described processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input the guardian's past notification history data into the generation AI and cause the generation AI to improve the accuracy of notifications.

[0089] The notification unit can estimate the user's emotions and adjust the length of the notification based on the estimated user emotions. Methods for estimating the user's emotions include, but are not limited to, emotion analysis algorithms and facial expression recognition technology. Methods for adjusting the length of the notification include, but are not limited to, shortening the notification based on the emotion or adding more detailed information. For example, if the user is feeling anxious, the notification unit can display a short, concise notification. If the user is feeling relaxed, the notification unit can also display detailed notification content. If the user is excited, the notification unit can also display emphasized notification content. This allows for more appropriate notification by adjusting the length of the notification based on the user's emotions. Some or all of the above-described processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the notification.

[0090] The notification unit can determine the priority of notifications based on the time when the problem occurred when notifying the user. Methods for considering the time when the problem occurred include, but are not limited to, risk assessment by time period and prioritization according to the time of occurrence. Methods for determining the priority of notifications include, but are not limited to, prioritization based on risk assessment and setting priorities according to urgency. For example, the notification unit can prioritize displaying notification content for problems that occurred late at night. The notification unit can also display notification content that calls attention to problems that occurred during school hours. The notification unit can also display regular notification content for problems that occurred on holidays. This enables appropriate notification by determining the priority of notifications based on the time when the problem occurred. Some or all of the above-described processing by the notification unit can be performed using, for example, a generation AI, or without using a generation AI. For example, the notification unit can input data on the time when the problem occurred into the generation AI and have the generation AI determine the priority of notifications.

[0091] The notification unit can adjust the order of notifications based on the relevance of the questions when notifying the user. Methods for evaluating the relevance of questions include, but are not limited to, content similarity and extraction of related topics. Methods for adjusting the order of notifications include, but are not limited to, ordering based on relevance and changing the display order according to priority. For example, the notification unit can display notification content first for important questions. The notification unit can also display notification content second for questions of medium importance. The notification unit can also display notification content last for questions of low importance. This allows for appropriate notifications by adjusting the order of notifications based on the relevance of the questions. Some or all of the above-described processing in the notification unit can be performed using, or without, a generation AI. For example, the notification unit can input question relevance data into the generation AI and have the generation AI adjust the order of notifications.

[0092] The notification unit can adjust the use of technical terms in the notification depending on the parent's internet literacy when providing the notification. Methods for assessing internet literacy include, but are not limited to, survey results and past behavioral history. Methods for adjusting the use of technical terms include, but are not limited to, selecting terms appropriate for the parent's internet literacy and using simple expressions. For example, the notification unit can display notification content in simple language to parents with low internet literacy. The notification unit can also display detailed notification content to parents with high internet literacy. The notification unit can also display notification content including technical terms to parents who can understand technical terms. This allows for appropriate notification by adjusting the use of technical terms in the notification depending on the parent's internet literacy. Some or all of the above-described processing in the notification unit can be performed using, or without, a generation AI. For example, the notification unit can input the parent's internet literacy data into the generation AI and cause the generation AI to adjust the use of technical terms in the notification. === Hard Collateral 1-1 === Each of the multiple elements including the above-described analysis unit, warning unit, and notification unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes messages and content on the SNS to detect inappropriate content or dangerous elements. For example, the warning unit is realized by the control unit 46A of the smart device 14 and displays a warning message to young people based on the detected inappropriate content. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12 and notifies parents of a summary of a problem when it occurs while protecting the user's privacy. === Hard Collateral 1-2 === Each of the multiple elements including the above-described analysis unit, warning unit, and notification unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes messages and content on the SNS to detect inappropriate content or dangerous elements. For example, the warning unit is realized by the control unit 46A of the smart glasses 214 and displays a warning message to the minor based on the detected inappropriate content. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12 and notifies the guardian of a summary of the problem when it occurs while protecting the user's privacy. === Hard Collateral 1-3 === Each of the multiple elements including the above-described analysis unit, warning unit, and notification unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes messages and content on the SNS to detect inappropriate content or dangerous elements. For example, the warning unit is realized by the control unit 46A of the headset type terminal 314, and displays a warning message to young people based on the detected inappropriate content. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12, and when a problem occurs, notifies parents of an overview while protecting the user's privacy. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, warning unit, and notification unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes messages and content on the SNS to detect inappropriate content or dangerous elements. For example, the warning unit is realized by the control unit 46A of the robot 414, and displays a warning message to the minor based on the detected inappropriate content. For example, the notification unit is realized by the specific processing unit 290 of the data processing device 12, and when a problem occurs, notifies the parent or guardian of an overview while protecting the user's privacy.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] When analyzing messages and content on social media, the analysis unit can improve the accuracy of the analysis by taking into account the user's past behavioral patterns. For example, by analyzing what kind of messages the user has responded to in the past and what kind of content they prefer to view, it is possible to detect inappropriate content with greater accuracy. The analysis unit can also refer to the history of warning messages the user has received in the past and adjust the strength of the warning if a similar pattern is observed. Furthermore, the analysis unit can evaluate the risk for specific time periods and situations based on the user's past behavioral patterns and adjust the priority of the analysis. This allows for more effective analysis and warnings by taking into account the user's behavioral patterns.

[0095] The warning unit can estimate the user's emotions and adjust the timing of displaying the warning message based on the estimated user emotions. For example, if the user is feeling stressed, the burden on the user can be reduced by temporarily delaying the display of the warning message. Furthermore, if the user is relaxed, the warning message can be displayed immediately to prompt a prompt response. Furthermore, if the user is excited, the warning message can be displayed in stages to attract the user's attention. Thus, by adjusting the timing of displaying the warning message based on the user's emotions, more effective warnings can be provided.

[0096] The notification unit can estimate the parent's emotions and adjust the level of detail of the notification content based on the estimated parent's emotions. For example, if the parent is feeling anxious, detailed notification content can be displayed to provide a sense of security. If the parent is relaxed, concise notification content can be displayed to avoid providing excessive information. Furthermore, if the parent is excited, important information can be highlighted to encourage a prompt response. Thus, by adjusting the level of detail of the notification content based on the parent's emotions, more appropriate notifications can be provided.

[0097] When analyzing messages and content on social media, the analysis unit can evaluate the trustworthiness of the message sender. For example, if the sender has a history of sending inappropriate messages in the past, the unit can evaluate the sender's trustworthiness low and prioritize the display of a warning message. Also, if the sender is a trustworthy person, the unit can refrain from displaying a warning message. Furthermore, the analysis priority can be adjusted based on the sender's trustworthiness. This allows for more effective analysis and warnings by taking the sender's trustworthiness into consideration.

[0098] The warning unit can estimate the user's emotions and adjust the display format of the warning message based on the estimated user's emotions. For example, if the user is feeling anxious, a visually friendly warning message can be displayed to reduce the burden on the user. If the user is relaxed, a normal warning message can be displayed. Furthermore, if the user is excited, a visually emphasized warning message can be displayed to attract the user's attention. Thus, by adjusting the display format of the warning message based on the user's emotions, more effective warnings can be provided.

[0099] The notification unit can adjust the way the notification content is expressed depending on the parent's internet literacy. For example, for parents with low internet literacy, the notification content can be displayed in simple language to make it easier to understand. For parents with high internet literacy, detailed notification content can be displayed to encourage deeper understanding. Furthermore, notification content including technical terms can be displayed to parents who can understand technical terms. This makes it possible to provide appropriate notifications by adjusting the way the notification content is expressed depending on the parent's internet literacy.

[0100] When analyzing messages and content on social media, the analysis unit can improve the accuracy of the analysis by taking into account the geographic location information of the message sender. For example, messages from a specific region can be evaluated as being highly dangerous. Messages from overseas can also be evaluated as containing content requiring caution. Furthermore, messages from the user's residential area can be evaluated with normal analysis accuracy. This allows for more accurate detection of inappropriate content by taking into account the geographical source of the message.

[0101] The warning unit can estimate the user's emotions and customize the content of the warning message based on the estimated user's emotions. For example, if the user feels anxious, a warning message including specific measures and advice can be displayed to provide a sense of security. If the user feels relaxed, a concise warning message can be displayed. Furthermore, if the user feels excited, an emphasized warning message calling for caution can be displayed. This allows for more effective warnings by customizing the content of the warning message based on the user's emotions.

[0102] The notification unit can adjust the priority of notification content by referring to the guardian's past notification history. For example, if the guardian has a history of ignoring notifications in the past, notifications with similar content can be displayed with priority to attract their attention. Also, if the guardian has a history of following notifications in the past, notifications with similar content can be displayed with normal priority. Furthermore, based on the history of notifications received by the guardian in the past, notifications with high importance can also be displayed with priority. In this way, by referring to the guardian's past notification history, the priority of notification content can be adjusted, enabling more effective notifications.

[0103] When analyzing messages and content on social media, the analysis unit takes into account the context of the message to more accurately detect inappropriate content. For example, it can analyze the context of the message and detect inappropriate content based on the context. It can also take into account the continuity of messages to detect content that is acceptable when used alone but inappropriate when used in succession. It can also analyze the tone and nuance of the message to detect inappropriate content based on the context. This allows for more accurate detection of inappropriate content by taking into account the context of the message.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The analysis unit analyzes messages and content on social media to detect inappropriate or dangerous content. For example, text analysis can be used to detect violent or discriminatory language, image analysis to detect sexual content, and audio analysis to detect potentially fraudulent messages. Step 2: The warning unit displays a warning message to the minor based on the inappropriate content detected by the analysis unit. For example, the warning message may be a text message such as "This message contains dangerous content. Please do not reply.", or a pop-up notification or a voice alert. Step 3: The notification unit notifies the parent of the warning message generated by the warning unit. For example, the notification unit notifies the parent of an overview via email, SMS, or in-app notification, such as "The message your child received contained dangerous content. Please discuss the details with your child."

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0108] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 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.

[0112] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0113] 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.

[0114] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0116] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0117] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] 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.

[0119] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0120] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] 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.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] 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.

[0134] 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.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 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.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] 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.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0150] 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.

[0151] 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.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0157] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0161] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0162] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0166] 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.

[0167] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0168] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0169] 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.

[0170] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0171] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0172] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0174] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0175] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0176] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0177] [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes messages or content on the SNS; a warning unit that displays a warning message based on the inappropriate content detected by the analysis unit; a notification unit that notifies a parent or guardian of the warning message generated by the warning unit; Equipped with A system characterized by:

2. The analysis unit Analyze messages or content on social media to detect inappropriate or dangerous content 2. The system of claim 1.

3. The warning unit Display warning messages to young people based on inappropriate content detected 2. The system of claim 1.

4. The notification unit Provide parents with a summary of issues when they occur while preserving user privacy 2. The system of claim 1.

5. The warning unit Display educational messages to encourage appropriate behavior among young people 2. The system of claim 1.

6. The notification unit When notifying parents of an overview of the problems detected by the AI, the specific details are hidden.

2. The system of claim 1.

7. The analysis unit Estimate user emotions and adjust analysis priorities based on the estimated user emotions 2. The system of claim 1.

8. The analysis unit During analysis, the context of the message is taken into account to more accurately detect inappropriate content.

2. The system of claim 1.

Images