System

Abstract

An object of a system according to an embodiment is to detect content related to bullying in a mobile messenger and prompt an appropriate response.SOLUTION: A system includes an analysis unit, a warning unit, an advice unit, and an image generation unit. The analysis unit analyzes the text of the message and detects a keyword or a phrase related to bullying. The warning unit transmits a warning to the protector based on the content detected by the analysis unit. The advice unit provides advice such as a response based on the warning transmitted by the warning unit. The image generation unit generates the content of the message as an image based on the warning transmitted 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] Conventional technology has faced the challenge of making it difficult to quickly and accurately detect bullying-related content on mobile messengers and take appropriate action.

[0005] The system according to the embodiment aims to detect bullying-related content on mobile messengers and encourage appropriate responses. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a warning unit, an advice unit, and an image generation unit. The analysis unit analyzes the text of the message and detects keywords or phrases related to bullying. The warning unit sends a warning to parents based on the content detected by the analysis unit. The advice unit provides advice on how to respond, etc., based on the warning sent by the warning unit. The image generation unit generates an image of the content of the message based on the warning sent by the warning unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect bullying-related content on mobile messengers and prompt appropriate responses. [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 detects content likely related to bullying from a series of messages in a mobile messenger and sends a warning and advice on how to respond to the message to parents. This system uses AI to analyze the content of the mobile messenger and detects content likely related to bullying. The system then sends the detected content as a warning to parents and provides advice on how to respond. The system also sends the mobile messenger content as an image. This enables the system to detect bullying early and take appropriate action, thereby protecting the safety of children. For example, the system uses AI to analyze the content of the mobile messenger and detects keywords and phrases likely related to bullying. The system then sends the detected content as a warning to parents and provides advice on how to respond. The system also sends the mobile messenger content as an image, making it easier for parents to check the content. Furthermore, the system provides advice on how to respond to the message to parents. For example, the system helps parents take appropriate action by providing specific countermeasures against bullying and information on where to seek help.

[0029] A bullying detection system according to an embodiment includes an analysis unit, a warning unit, an advice unit, and an image generation unit. The analysis unit analyzes the text of a message to detect keywords or phrases related to bullying. For example, the analysis unit detects messages containing keywords or phrases related to bullying. The analysis unit can also use natural language processing technology to analyze the context of the message and detect signs of bullying. The analysis unit can also use AI to analyze the emotions in the message and detect signs of bullying. The warning unit sends a warning to a guardian based on the content detected by the analysis unit. For example, the warning unit sends a message related to the detected bullying to the guardian's email address or mobile messenger. The warning unit can also send the warning message as a text message or an alert sound. The warning unit can also generate the content of the warning message using AI. The advice unit provides advice on how to respond based on the warning sent by the warning unit. For example, the advice unit provides information on specific countermeasures against bullying and where to seek advice. The advice unit can also provide information on psychological support and counseling. The advice unit can also generate the content of the advice using AI. The image generation unit generates the message content as an image based on the warning sent by the warning unit. For example, the image generation unit generates the message content as an image to make it easier for parents to check the content. The image generation unit can also use AI to generate the image content. This enables the bullying detection system according to the embodiment to detect bullying early and take appropriate measures. For example, the system uses AI to analyze the content of a mobile messenger and detect keywords and phrases that may be related to bullying. Next, the system sends the detected content to parents as a warning and provides advice on how to respond. At this time, the mobile messenger content is also sent as an image to make it easier for parents to check the content. Furthermore, advice on how to respond is provided to parents. For example, specific measures against bullying and information on where to seek advice can be provided to help parents take appropriate measures.

[0030] The analysis unit analyzes not only the text of the message but also images and audio data. For example, the analysis unit may use AI to analyze images attached to the message and detect visual elements related to bullying. The analysis unit may also use AI to analyze audio data included in the message and detect the tone and content of the audio related to bullying. The analysis unit may also comprehensively analyze text, images, and audio data to detect complex elements related to bullying. This allows for a broader detection of signs of bullying by analyzing not only text but also image and audio data. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit may input image and audio data into a generation AI and have the generation AI detect elements related to bullying.

[0031] During analysis, the analysis unit optimizes the analysis algorithm by referring to past bullying-related data. For example, the analysis unit optimizes the analysis algorithm by learning past bullying-related data using AI. The analysis unit can also improve the accuracy of detecting specific keywords and phrases by referring to past bullying-related data. The analysis unit can also analyze bullying patterns based on past bullying-related data and detect new signs of bullying. In this way, the accuracy of the analysis algorithm can be improved by referring to past bullying-related data. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input past bullying-related data into the generation AI and have the generation AI optimize the analysis algorithm.

[0032] During analysis, the analysis unit corrects the analysis results based on the relationship between the sender and receiver of the message. For example, if the sender and receiver of the message are friends, the analysis unit corrects the analysis results so that jokes or light-hearted words are not mistaken for bullying. Furthermore, if the sender and receiver of the message are in a hostile relationship, the analysis unit can also detect subtle aggressive expressions as bullying. The analysis unit can also use AI to learn the relationship between the sender and receiver of the message and appropriately correct the analysis results. This reduces the chance of misidentification of bullying by taking the relationship between the sender and receiver into consideration. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the relationship between the sender and receiver into the generation AI and have the generation AI correct the analysis results.

[0033] During analysis, the analysis unit corrects the analysis results by taking into account the time period and frequency of message transmission. For example, the analysis unit uses AI to analyze messages sent late at night and determine that there is a high possibility of bullying. The analysis unit can also use AI to analyze messages sent frequently in a short period of time and detect signs of bullying. The analysis unit can also appropriately correct the analysis results by taking into account the time period and frequency of transmission. In this way, signs of bullying can be detected more accurately by taking into account the time period and frequency of transmission. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time period and frequency of transmission into the generation AI and have the generation AI correct the analysis results.

[0034] During analysis, the analysis unit takes into account the context of the message to improve the accuracy of keyword detection. For example, the analysis unit uses AI to analyze the context before and after the message to improve the accuracy of detecting keywords related to bullying. The analysis unit can also take the context into account to accurately detect keywords that are difficult to determine as bullying on their own. The analysis unit can also more accurately detect signs of bullying through context analysis. In this way, by taking the context into account, signs of bullying can be detected more accurately. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input context data of the message into the generation AI and cause the generation AI to improve the accuracy of keyword detection.

[0035] During analysis, the analysis unit corrects the analysis results by referring to the message sender's past behavioral history. For example, if the sender has engaged in bullying behavior in the past, the analysis unit can detect even subtle aggressive language as bullying. Furthermore, if the sender has previously sent friendly messages, the analysis unit can correct the analysis results so that jokes or light-hearted words are not mistaken for bullying. Furthermore, the analysis unit can use AI to learn the sender's past behavioral history and appropriately correct the analysis results. Thus, by referring to the sender's past behavioral history, it is possible to reduce false positives of bullying. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the sender's past behavioral history data into the generation AI and have the generation AI correct the analysis results.

[0036] When sending a warning, the warning unit adjusts the urgency of the warning by referring to the guardian's past reaction history. For example, if the guardian has responded quickly in the past, the warning unit sends a warning with a high level of urgency. Furthermore, if the guardian has responded slowly in the past, the warning unit can also send a warning including detailed information. Furthermore, the warning unit can use AI to learn the guardian's past reaction history and appropriately adjust the urgency of the warning. In this way, the urgency of the warning can be appropriately adjusted by referring to the guardian's past reaction history. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input the guardian's past reaction history data into the generation AI and cause the generation AI to adjust the urgency of the warning.

[0037] When sending a warning, the warning unit uses different warning templates depending on the content of the message. For example, if the content of bullying is serious, the warning unit uses a high-urgency warning template. Alternatively, if there are signs of mild bullying, the warning unit can use a milder warning template. The warning unit can also use AI to select an appropriate warning template depending on the content of the message. This allows for more effective warnings to be sent by using an appropriate warning template depending on the content of the message. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input message content data into a generation AI and have the generation AI select a warning template.

[0038] The warning unit adds a function to automatically update the guardian's contact information when sending a warning. For example, if the guardian's contact information is changed, the warning unit automatically updates it using AI. The warning unit can also periodically check the guardian's contact information and update it to the latest information. The warning unit can also have AI learn the guardian's contact information and update it appropriately. By automatically updating the guardian's contact information, the latest contact information can always be used. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input the guardian's contact information data into the generation AI and have the generation AI update the contact information.

[0039] When sending a warning, the warning unit selects the optimal means of contact taking into account the guardian's geographical location information. For example, if the guardian is at home, the warning unit sends the warning by phone. If the guardian is out, the warning unit can also send the warning by email or message. The warning unit can also use AI to learn the guardian's geographical location information and select the optimal means of contact. This makes it possible to select the optimal means of contact by taking the guardian's geographical location information into consideration. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input the guardian's geographical location information data into the generation AI and have the generation AI select the optimal means of contact.

[0040] When sending a warning, the warning unit makes the warning content multilingual according to the parent's language setting. The warning unit automatically translates the warning content based on, for example, the language setting of the parent's device. The warning unit can also provide a language switching function if the parent uses multiple languages. If the parent selects a specific language, the warning unit can also provide the warning content in that language. By making the warning content multilingual according to the parent's language setting, it is possible to send a warning that is easier to understand. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the parent's language setting data into a generation AI and cause the generation AI to translate the warning content into multiple languages.

[0041] When sending a warning, the warning unit selects the optimal display method by taking into account the parent's device information. For example, if the parent is using a smartphone, the warning unit provides a display method that matches the screen size. Furthermore, if the parent is using a tablet, the warning unit can also provide a display method optimized for a large screen. Furthermore, if the parent is using a smartwatch, the warning unit can also provide a simple and highly visible display method. In this way, the optimal display method can be provided by taking into account the parent's device information. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the parent's device information data into the generation AI and cause the generation AI to select the optimal display method.

[0042] When providing advice, the advice unit improves the accuracy of the advice by referring to past cases of how bullying was dealt with. For example, the advice unit uses AI to learn from past cases of how bullying was dealt with and provides optimal advice. The advice unit can also refer to past cases of how bullying was dealt with and suggest specific countermeasures. The advice unit can also provide effective advice based on past cases of how bullying was dealt with. In this way, by referring to past cases of how bullying was dealt with, the accuracy of the advice can be improved. Some or all of the above-mentioned processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input data on past cases of how bullying was dealt with into the generation AI and have the generation AI improve the accuracy of the advice.

[0043] When providing advice, the advice unit selects the most appropriate advice by referring to the guardian's past response history. For example, if the guardian has responded effectively in the past, the advice unit provides similar advice. Furthermore, if the guardian has responded late in the past, the advice unit can also provide advice encouraging a prompt response. Furthermore, the advice unit can use AI to learn the guardian's past response history and select the most appropriate advice. In this way, optimal advice can be provided by referring to the guardian's past response history. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the guardian's past response history data into the generation AI and have the generation AI select the most appropriate advice.

[0044] When providing advice, the advice unit uses different advice templates depending on the type of bullying. For example, in the case of physical bullying, the advice unit uses an advice template that includes specific countermeasures and information on where to seek advice. In the case of mental bullying, the advice unit can also use an advice template that includes information on psychological support and counseling. In the case of cyberbullying, the advice unit can also use an advice template that includes online countermeasures and legal advice. This allows more effective advice to be provided by using an appropriate advice template depending on the type of bullying. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input data on the type of bullying into the generation AI and have the generation AI select an advice template.

[0045] When providing advice, the advice unit considers the guardian's geographical location information to suggest the most appropriate consultation destination. For example, if the guardian is at home, the advice unit considers the geographical location information of the guardian and suggests a nearby consultation destination. Furthermore, if the guardian is out, the advice unit can also consider the closest consultation destination to the guardian's current location. Furthermore, the advice unit can use AI to learn the guardian's geographical location information and suggest the most appropriate consultation destination. In this way, the most appropriate consultation destination can be suggested by considering the guardian's geographical location information. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the guardian's geographical location information data into the generation AI and have the generation AI suggest the most appropriate consultation destination.

[0046] When providing advice, the advice unit makes the advice content multilingual according to the parent's language setting. The advice unit automatically translates the advice content based on, for example, the language setting of the parent's device. The advice unit can also provide a language switching function if the parent speaks multiple languages. If the parent selects a specific language, the advice unit can also provide the advice content in that language. By making the advice content multilingual according to the parent's language setting, it is possible to provide advice that is easier to understand. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the parent's language setting data into a generation AI and cause the generation AI to translate the advice content into multiple languages.

[0047] When providing advice, the advice unit selects the optimal display method by taking into account the parent's device information. For example, if the parent is using a smartphone, the advice unit provides a display method that matches the screen size. Furthermore, if the parent is using a tablet, the advice unit can also provide a display method optimized for a large screen. Furthermore, if the parent is using a smartwatch, the advice unit can also provide a simple and highly visible display method. In this way, the optimal display method can be provided by taking into account the parent's device information. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the parent's device information data into the generation AI and cause the generation AI to select the optimal display method.

[0048] When generating an image, the image generation unit adjusts the level of detail of the image based on the importance of the message. For example, in the case of a message with high importance, the image generation unit generates an image containing detailed information. Furthermore, in the case of a message with low importance, the image generation unit can also generate an image containing concise information. Furthermore, the image generation unit can also use AI to adjust the level of detail of the image according to the importance of the message. In this way, by adjusting the level of detail of the image according to the importance of the message, a more appropriate image can be generated. Some or all of the above-described processing in the image generation unit may be performed using AI, for example, or may be performed without using AI. For example, the image generation unit can input message importance data to the generation AI and cause the generation AI to adjust the level of detail of the image.

[0049] When generating an image, the image generation unit applies different image generation algorithms depending on the message category. For example, in the case of physical bullying, the image generation unit generates an image that includes specific countermeasures and information on where to seek advice. In addition, in the case of mental bullying, the image generation unit can also generate an image that includes information on psychological support and counseling. In addition, in the case of cyberbullying, the image generation unit can also generate an image that includes online countermeasures and legal advice. In this way, by applying an appropriate image generation algorithm depending on the message category, more effective images can be generated. Some or all of the above-mentioned processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input message category data into the generation AI and have the generation AI apply the image generation algorithm.

[0050] When generating an image, the image generation unit corrects the content of the image taking into account the relationship between the message sender and recipient. For example, if the message sender and recipient are friends, the image generation unit corrects the content of the image so that jokes or light-hearted words are not mistaken for bullying. Furthermore, if the message sender and recipient are in a hostile relationship, the image generation unit can also detect subtle aggressive expressions as bullying. Furthermore, the image generation unit can use AI to learn the relationship between the message sender and recipient and appropriately correct the content of the image. This reduces the chance of misidentification as bullying by taking the relationship between the sender and recipient into consideration. Some or all of the above-mentioned processing in the image generation unit may be performed using AI, for example, or may be performed without using AI. For example, the image generation unit can input data on the relationship between the sender and recipient into the generation AI and have the generation AI correct the image content.

[0051] When generating an image, the image generation unit corrects the content of the image by taking into account the time and frequency of message transmission. For example, the image generation unit uses AI to analyze messages sent late at night and determine that there is a high possibility of bullying. The image generation unit can also use AI to analyze messages sent frequently in a short period of time and detect signs of bullying. The image generation unit can also appropriately correct the content of the image by taking into account the time and frequency of transmission. In this way, by taking into account the time and frequency of transmission, signs of bullying can be detected more accurately. Some or all of the above-mentioned processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input data on the time and frequency of transmission into the generation AI and have the generation AI correct the image content.

[0052] When generating an image, the image generation unit corrects the content of the image by taking into account the context of the message. For example, the image generation unit uses AI to analyze the context before and after the message, improving the accuracy of detecting keywords related to bullying. The image generation unit can also take the context into account and accurately detect keywords that are difficult to determine as bullying on their own. The image generation unit can also more accurately detect signs of bullying through context analysis. As a result, by taking the context into account, signs of bullying can be detected more accurately. Some or all of the above-mentioned processing in the image generation unit may be performed using AI, for example, or may be performed without using AI. For example, the image generation unit can input the context data of the message into the generation AI and have the generation AI correct the image content.

[0053] When generating an image, the image generation unit corrects the content of the image by referring to the message sender's past behavioral history. For example, if the sender has engaged in bullying behavior in the past, the image generation unit can detect even subtle aggressive language as bullying. Furthermore, if the sender has previously sent friendly messages, the image generation unit can also correct the content of the image so that jokes or light-hearted words are not mistaken for bullying. Furthermore, the image generation unit can use AI to learn the sender's past behavioral history and appropriately correct the content of the image. By referring to the sender's past behavioral history, it is possible to reduce the chance of misidentifying bullying. Some or all of the above-described processing in the image generation unit may be performed using, for example, AI, or may be performed without AI. For example, the image generation unit can input the sender's past behavioral history data into the generation AI and have the generation AI correct the image content.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The analysis unit can analyze not only the text of messages but also the user's behavioral patterns. For example, if a user frequently sends messages during a specific time period, the analysis unit can analyze that behavioral pattern to detect signs of bullying. Furthermore, if a user sends messages from a specific location, the analysis unit can analyze the location information to evaluate the possibility of bullying. Furthermore, the analysis unit can analyze changes in the frequency of a user's message sending and the recipients of those messages to detect signs of bullying early on. Thus, by analyzing a user's behavioral patterns, signs of bullying can be detected more broadly.

[0056] The analysis unit can analyze not only the text of messages but also the user's social media activity. For example, if a user frequently uses a specific keyword on social media, the analysis unit can analyze that keyword to detect signs of bullying. Also, if a user is a member of a specific group on social media, the analysis unit can analyze the activity of that group to evaluate the possibility of bullying. Furthermore, the analysis unit can analyze the user's friendships on social media to detect signs of bullying at an early stage. This allows for a more widespread detection of signs of bullying by analyzing social media activity.

[0057] During analysis, the analysis unit can optimize the analysis algorithm by referring to the user's past message history. For example, if the user has sent messages related to bullying in the past, the analysis unit can optimize the analysis algorithm by referring to the message history. In addition, if the user has sent friendly messages in the past, the analysis unit can also adjust the analysis algorithm by referring to the message history. Furthermore, the analysis unit can analyze bullying patterns based on the user's past message history and detect new signs of bullying. In this way, by referring to the past message history, the accuracy of the analysis algorithm can be improved.

[0058] During analysis, the analysis unit can correct the analysis results by taking into account the user's message sending patterns. For example, if a user frequently sends messages during a specific time period, the analysis unit can correct the analysis results by taking into account that sending pattern, thereby more accurately detecting signs of bullying. In addition, if a user frequently sends messages to a specific person, the analysis unit can also correct the analysis results by taking into account that sending pattern. Furthermore, the analysis unit can use AI to learn the user's message sending patterns and appropriately correct the analysis results. In this way, by taking into account the user's message sending patterns, it is possible to reduce false positives of bullying.

[0059] During analysis, the analysis unit can correct the analysis results by taking into account the destination of the user's message. For example, if a user sends a message to a specific group, the analysis results can be corrected by taking into account the destination, allowing for more accurate detection of signs of bullying. In addition, if a user sends a message to a specific individual, the analysis unit can also correct the analysis results by taking into account the destination. Furthermore, the analysis unit can use AI to learn the destination of the user's messages and appropriately correct the analysis results. In this way, by taking into account the destination of the user's messages, it is possible to reduce false positives of bullying.

[0060] During analysis, the analysis unit can correct the analysis results by taking into account the content of the user's messages. For example, if a user frequently uses a specific keyword, the analysis results can be corrected by taking into account the content of the messages, allowing for more accurate detection of signs of bullying. In addition, if a user frequently uses a specific phrase, the analysis unit can correct the analysis results by taking into account the content of the messages. Furthermore, the analysis unit can use AI to learn the content of the user's messages and appropriately correct the analysis results. This makes it possible to reduce false positives of bullying by taking into account the content of the user's messages.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The analysis unit analyzes the text of the message to detect keywords or phrases related to bullying. For example, the analysis unit may use natural language processing technology or AI to analyze the context and sentiment of the message to detect signs of bullying. Step 2: The warning unit sends a warning to parents based on the content detected by the analysis unit. For example, the warning unit can send a message related to the detected bullying to the parent's email address or mobile messenger, or can send a warning as a text message or an alert sound. The content of the warning message can also be generated using AI. Step 3: The advice unit provides advice on how to respond based on the warning sent by the warning unit. For example, it provides specific countermeasures against bullying, information on where to seek advice, and information on psychological support and counseling. It is also possible to generate the content of advice using AI. Step 4: The image generation unit generates the message content as an image based on the warning sent by the warning unit. For example, the image generation unit generates the message content as an image to make it easier for parents to check the content. The image content can also be generated using AI.

[0063] (Example 2) A system according to an embodiment of the present invention detects content likely related to bullying from a series of messages in a mobile messenger and sends a warning and advice on how to respond to the message to parents. This system uses AI to analyze the content of the mobile messenger and detects content likely related to bullying. The system then sends the detected content as a warning to parents and provides advice on how to respond. The system also sends the mobile messenger content as an image. This enables the system to detect bullying early and take appropriate action, thereby protecting the safety of children. For example, the system uses AI to analyze the content of the mobile messenger and detects keywords and phrases likely related to bullying. The system then sends the detected content as a warning to parents and provides advice on how to respond. The system also sends the mobile messenger content as an image, making it easier for parents to check the content. Furthermore, the system provides advice on how to respond to the message to parents. For example, the system helps parents take appropriate action by providing specific countermeasures against bullying and information on where to seek help.

[0064] A bullying detection system according to an embodiment includes an analysis unit, a warning unit, an advice unit, and an image generation unit. The analysis unit analyzes the text of a message to detect keywords or phrases related to bullying. For example, the analysis unit detects messages containing keywords or phrases related to bullying. The analysis unit can also use natural language processing technology to analyze the context of the message and detect signs of bullying. The analysis unit can also use AI to analyze the emotions in the message and detect signs of bullying. The warning unit sends a warning to a guardian based on the content detected by the analysis unit. For example, the warning unit sends a message related to the detected bullying to the guardian's email address or mobile messenger. The warning unit can also send the warning message as a text message or an alert sound. The warning unit can also generate the content of the warning message using AI. The advice unit provides advice on how to respond based on the warning sent by the warning unit. For example, the advice unit provides information on specific countermeasures against bullying and where to seek advice. The advice unit can also provide information on psychological support and counseling. The advice unit can also generate the content of the advice using AI. The image generation unit generates the message content as an image based on the warning sent by the warning unit. For example, the image generation unit generates the message content as an image to make it easier for parents to check the content. The image generation unit can also use AI to generate the image content. This enables the bullying detection system according to the embodiment to detect bullying early and take appropriate measures. For example, the system uses AI to analyze the content of a mobile messenger and detect keywords and phrases that may be related to bullying. Next, the system sends the detected content to parents as a warning and provides advice on how to respond. At this time, the mobile messenger content is also sent as an image to make it easier for parents to check the content. Furthermore, advice on how to respond is provided to parents. For example, specific measures against bullying and information on where to seek advice can be provided to help parents take appropriate measures.

[0065] The analysis unit estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. For example, if the user is feeling stressed, the AI ​​in the analysis unit increases the accuracy of the analysis and detects subtle keywords and phrases related to bullying. Furthermore, if the user is relaxed, the analysis unit can set the accuracy of the analysis to a normal level and detect general keywords and phrases. Furthermore, if the user is excited, the AI ​​in the analysis unit can adjust the accuracy of the analysis and detect messages containing emotional expressions. This allows for more appropriate analysis results by adjusting the analysis accuracy according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or without an AI. For example, the analysis unit may input the user's emotion data into the generation AI and cause the generation AI to adjust the analysis accuracy based on the emotion.

[0066] The analysis unit analyzes not only the text of the message but also images and audio data. For example, the analysis unit may use AI to analyze images attached to the message and detect visual elements related to bullying. The analysis unit may also use AI to analyze audio data included in the message and detect the tone and content of the audio related to bullying. The analysis unit may also comprehensively analyze text, images, and audio data to detect complex elements related to bullying. This allows for a broader detection of signs of bullying by analyzing not only text but also image and audio data. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit may input image and audio data into a generation AI and have the generation AI detect elements related to bullying.

[0067] During analysis, the analysis unit optimizes the analysis algorithm by referring to past bullying-related data. For example, the analysis unit optimizes the analysis algorithm by learning past bullying-related data using AI. The analysis unit can also improve the accuracy of detecting specific keywords and phrases by referring to past bullying-related data. The analysis unit can also analyze bullying patterns based on past bullying-related data and detect new signs of bullying. In this way, the accuracy of the analysis algorithm can be improved by referring to past bullying-related data. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input past bullying-related data into the generation AI and have the generation AI optimize the analysis algorithm.

[0068] During analysis, the analysis unit corrects the analysis results based on the relationship between the sender and receiver of the message. For example, if the sender and receiver of the message are friends, the analysis unit corrects the analysis results so that jokes or light-hearted words are not mistaken for bullying. Furthermore, if the sender and receiver of the message are in a hostile relationship, the analysis unit can also detect subtle aggressive expressions as bullying. The analysis unit can also use AI to learn the relationship between the sender and receiver of the message and appropriately correct the analysis results. This reduces the chance of misidentification of bullying by taking the relationship between the sender and receiver into consideration. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the relationship between the sender and receiver into the generation AI and have the generation AI correct the analysis results.

[0069] The analysis unit estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit may prioritize bullying-related messages as analysis results. Furthermore, if the user is relaxed, the analysis unit may display a balanced mix of normal and bullying-related messages. Furthermore, if the user is excited, the analysis unit may prioritize messages containing emotional expressions as analysis results. This allows important messages to be prioritized by prioritizing the analysis results according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without an AI. For example, the analysis unit may input the user's emotion data into the generation AI and cause the generation AI to prioritize the analysis results based on the emotions.

[0070] During analysis, the analysis unit corrects the analysis results by taking into account the time period and frequency of message transmission. For example, the analysis unit uses AI to analyze messages sent late at night and determine that there is a high possibility of bullying. The analysis unit can also use AI to analyze messages sent frequently in a short period of time and detect signs of bullying. The analysis unit can also appropriately correct the analysis results by taking into account the time period and frequency of transmission. In this way, signs of bullying can be detected more accurately by taking into account the time period and frequency of transmission. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time period and frequency of transmission into the generation AI and have the generation AI correct the analysis results.

[0071] During analysis, the analysis unit takes into account the context of the message to improve the accuracy of keyword detection. For example, the analysis unit uses AI to analyze the context before and after the message to improve the accuracy of detecting keywords related to bullying. The analysis unit can also take the context into account to accurately detect keywords that are difficult to determine as bullying on their own. The analysis unit can also more accurately detect signs of bullying through context analysis. In this way, by taking the context into account, signs of bullying can be detected more accurately. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input context data of the message into the generation AI and cause the generation AI to improve the accuracy of keyword detection.

[0072] During analysis, the analysis unit corrects the analysis results by referring to the message sender's past behavioral history. For example, if the sender has engaged in bullying behavior in the past, the analysis unit can detect even subtle aggressive language as bullying. Furthermore, if the sender has previously sent friendly messages, the analysis unit can correct the analysis results so that jokes or light-hearted words are not mistaken for bullying. Furthermore, the analysis unit can use AI to learn the sender's past behavioral history and appropriately correct the analysis results. Thus, by referring to the sender's past behavioral history, it is possible to reduce false positives of bullying. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the sender's past behavioral history data into the generation AI and have the generation AI correct the analysis results.

[0073] The warning unit estimates the user's emotions and adjusts the way the warning is expressed based on the estimated user emotions. For example, if the user is nervous, the warning unit transmits a warning in a calm manner. Furthermore, if the user is relaxed, the warning unit can transmit a warning with detailed information. Furthermore, if the user is excited, the warning unit can transmit a quick and concise warning. This allows for more appropriate warnings to be sent by adjusting the way the warning is expressed based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the warning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the warning unit may input the user's emotion data into the generation AI and cause the generation AI to adjust the way the warning is expressed based on the emotion.

[0074] When sending a warning, the warning unit adjusts the urgency of the warning by referring to the guardian's past reaction history. For example, if the guardian has responded quickly in the past, the warning unit sends a warning with a high level of urgency. Furthermore, if the guardian has responded slowly in the past, the warning unit can also send a warning including detailed information. Furthermore, the warning unit can use AI to learn the guardian's past reaction history and appropriately adjust the urgency of the warning. In this way, the urgency of the warning can be appropriately adjusted by referring to the guardian's past reaction history. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input the guardian's past reaction history data into the generation AI and cause the generation AI to adjust the urgency of the warning.

[0075] When sending a warning, the warning unit uses different warning templates depending on the content of the message. For example, if the content of bullying is serious, the warning unit uses a high-urgency warning template. Alternatively, if there are signs of mild bullying, the warning unit can use a milder warning template. The warning unit can also use AI to select an appropriate warning template depending on the content of the message. This allows for more effective warnings to be sent by using an appropriate warning template depending on the content of the message. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input message content data into a generation AI and have the generation AI select a warning template.

[0076] The warning unit adds a function to automatically update the guardian's contact information when sending a warning. For example, if the guardian's contact information is changed, the warning unit automatically updates it using AI. The warning unit can also periodically check the guardian's contact information and update it to the latest information. The warning unit can also have AI learn the guardian's contact information and update it appropriately. By automatically updating the guardian's contact information, the latest contact information can always be used. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input the guardian's contact information data into the generation AI and have the generation AI update the contact information.

[0077] The warning unit estimates the user's emotions and adjusts the timing of sending the warning based on the estimated user emotions. For example, if the user is nervous, the warning unit sends a gentle warning. Furthermore, if the user is relaxed, the warning unit can also send a warning with detailed information. Furthermore, if the user is excited, the warning unit can also send a quick and concise warning. By adjusting the timing of sending the warning according to the user's emotions, the warning can be sent at a more appropriate time. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the warning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the warning unit may input the user's emotion data into the generation AI and cause the generation AI to adjust the timing of sending the warning based on the emotion.

[0078] When sending a warning, the warning unit selects the optimal means of contact taking into account the guardian's geographical location information. For example, if the guardian is at home, the warning unit sends the warning by phone. If the guardian is out, the warning unit can also send the warning by email or message. The warning unit can also use AI to learn the guardian's geographical location information and select the optimal means of contact. This makes it possible to select the optimal means of contact by taking the guardian's geographical location information into consideration. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input the guardian's geographical location information data into the generation AI and have the generation AI select the optimal means of contact.

[0079] When sending a warning, the warning unit makes the warning content multilingual according to the parent's language setting. The warning unit automatically translates the warning content based on, for example, the language setting of the parent's device. The warning unit can also provide a language switching function if the parent uses multiple languages. If the parent selects a specific language, the warning unit can also provide the warning content in that language. By making the warning content multilingual according to the parent's language setting, it is possible to send a warning that is easier to understand. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the parent's language setting data into a generation AI and cause the generation AI to translate the warning content into multiple languages.

[0080] When sending a warning, the warning unit selects the optimal display method by taking into account the parent's device information. For example, if the parent is using a smartphone, the warning unit provides a display method that matches the screen size. Furthermore, if the parent is using a tablet, the warning unit can also provide a display method optimized for a large screen. Furthermore, if the parent is using a smartwatch, the warning unit can also provide a simple and highly visible display method. In this way, the optimal display method can be provided by taking into account the parent's device information. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the parent's device information data into the generation AI and cause the generation AI to select the optimal display method.

[0081] The advice unit estimates the user's emotions and adjusts the content of the advice based on the estimated user emotions. For example, if the user is nervous, the advice unit provides advice in a calm manner. Furthermore, if the user is relaxed, the advice unit can also provide advice including detailed information. Furthermore, if the user is excited, the advice unit can also provide quick and concise advice. By adjusting the content of the advice according to the user's emotions, more appropriate advice can be provided. The emotion estimation is realized using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the advice unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the advice unit may input the user's emotion data into the generation AI and cause the generation AI to adjust the content of the advice based on the emotion.

[0082] When providing advice, the advice unit improves the accuracy of the advice by referring to past cases of how bullying was dealt with. For example, the advice unit uses AI to learn from past cases of how bullying was dealt with and provides optimal advice. The advice unit can also refer to past cases of how bullying was dealt with and suggest specific countermeasures. The advice unit can also provide effective advice based on past cases of how bullying was dealt with. In this way, by referring to past cases of how bullying was dealt with, the accuracy of the advice can be improved. Some or all of the above-mentioned processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input data on past cases of how bullying was dealt with into the generation AI and have the generation AI improve the accuracy of the advice.

[0083] When providing advice, the advice unit selects the most appropriate advice by referring to the guardian's past response history. For example, if the guardian has responded effectively in the past, the advice unit provides similar advice. Furthermore, if the guardian has responded late in the past, the advice unit can also provide advice encouraging a prompt response. Furthermore, the advice unit can use AI to learn the guardian's past response history and select the most appropriate advice. In this way, optimal advice can be provided by referring to the guardian's past response history. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the guardian's past response history data into the generation AI and have the generation AI select the most appropriate advice.

[0084] When providing advice, the advice unit uses different advice templates depending on the type of bullying. For example, in the case of physical bullying, the advice unit uses an advice template that includes specific countermeasures and information on where to seek advice. In the case of mental bullying, the advice unit can also use an advice template that includes information on psychological support and counseling. In the case of cyberbullying, the advice unit can also use an advice template that includes online countermeasures and legal advice. This allows more effective advice to be provided by using an appropriate advice template depending on the type of bullying. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input data on the type of bullying into the generation AI and have the generation AI select an advice template.

[0085] The advice unit estimates the user's emotions and determines the priority of advice based on the estimated user emotions. For example, if the user is nervous, the advice unit prioritizes providing advice with a high level of urgency. Furthermore, if the user is relaxed, the advice unit can also provide advice with detailed information. Furthermore, if the user is excited, the advice unit can also prioritize providing quick and concise advice. Thus, by determining the priority of advice according to the user's emotions, important advice can be provided preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the advice unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the advice unit may input the user's emotion data into the generation AI and cause the generation AI to determine the priority of advice based on emotions.

[0086] When providing advice, the advice unit considers the guardian's geographical location information to suggest the most appropriate consultation destination. For example, if the guardian is at home, the advice unit considers the geographical location information of the guardian and suggests a nearby consultation destination. Furthermore, if the guardian is out, the advice unit can also consider the closest consultation destination to the guardian's current location. Furthermore, the advice unit can use AI to learn the guardian's geographical location information and suggest the most appropriate consultation destination. In this way, the most appropriate consultation destination can be suggested by considering the guardian's geographical location information. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the guardian's geographical location information data into the generation AI and have the generation AI suggest the most appropriate consultation destination.

[0087] When providing advice, the advice unit makes the advice content multilingual according to the parent's language setting. The advice unit automatically translates the advice content based on, for example, the language setting of the parent's device. The advice unit can also provide a language switching function if the parent speaks multiple languages. If the parent selects a specific language, the advice unit can also provide the advice content in that language. By making the advice content multilingual according to the parent's language setting, it is possible to provide advice that is easier to understand. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the parent's language setting data into a generation AI and cause the generation AI to translate the advice content into multiple languages.

[0088] When providing advice, the advice unit selects the optimal display method by taking into account the parent's device information. For example, if the parent is using a smartphone, the advice unit provides a display method that matches the screen size. Furthermore, if the parent is using a tablet, the advice unit can also provide a display method optimized for a large screen. Furthermore, if the parent is using a smartwatch, the advice unit can also provide a simple and highly visible display method. In this way, the optimal display method can be provided by taking into account the parent's device information. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the parent's device information data into the generation AI and cause the generation AI to select the optimal display method.

[0089] The image generation unit estimates the user's emotions and adjusts the image generation method based on the estimated user emotions. For example, if the user is nervous, the image generation unit generates an image with calm colors. Furthermore, if the user is relaxed, the image generation unit can also generate an image containing detailed information. Furthermore, if the user is excited, the image generation unit can also generate an image with a visually stimulating effect. This allows for adjusting the image generation method according to the user's emotions to generate more appropriate images. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the image generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the image generation unit may input the user's emotion data into the generation AI and cause the generation AI to adjust the image generation method based on the emotion.

[0090] When generating an image, the image generation unit adjusts the level of detail of the image based on the importance of the message. For example, in the case of a message with high importance, the image generation unit generates an image containing detailed information. Furthermore, in the case of a message with low importance, the image generation unit can also generate an image containing concise information. Furthermore, the image generation unit can also use AI to adjust the level of detail of the image according to the importance of the message. In this way, by adjusting the level of detail of the image according to the importance of the message, a more appropriate image can be generated. Some or all of the above-described processing in the image generation unit may be performed using AI, for example, or may be performed without using AI. For example, the image generation unit can input message importance data to the generation AI and cause the generation AI to adjust the level of detail of the image.

[0091] When generating an image, the image generation unit applies different image generation algorithms depending on the message category. For example, in the case of physical bullying, the image generation unit generates an image that includes specific countermeasures and information on where to seek advice. In addition, in the case of mental bullying, the image generation unit can also generate an image that includes information on psychological support and counseling. In addition, in the case of cyberbullying, the image generation unit can also generate an image that includes online countermeasures and legal advice. In this way, by applying an appropriate image generation algorithm depending on the message category, more effective images can be generated. Some or all of the above-mentioned processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input message category data into the generation AI and have the generation AI apply the image generation algorithm.

[0092] When generating an image, the image generation unit corrects the content of the image taking into account the relationship between the message sender and recipient. For example, if the message sender and recipient are friends, the image generation unit corrects the content of the image so that jokes or light-hearted words are not mistaken for bullying. Furthermore, if the message sender and recipient are in a hostile relationship, the image generation unit can also detect subtle aggressive expressions as bullying. Furthermore, the image generation unit can use AI to learn the relationship between the message sender and recipient and appropriately correct the content of the image. This reduces the chance of misidentification as bullying by taking the relationship between the sender and recipient into consideration. Some or all of the above-mentioned processing in the image generation unit may be performed using AI, for example, or may be performed without using AI. For example, the image generation unit can input data on the relationship between the sender and recipient into the generation AI and have the generation AI correct the image content.

[0093] The image generation unit estimates the user's emotions and adjusts the image display method based on the estimated user emotions. For example, if the user is nervous, the image generation unit displays an image with calm colors. Furthermore, if the user is relaxed, the image generation unit can also display an image containing detailed information. Furthermore, if the user is excited, the image generation unit can also display an image with a visually stimulating effect. This allows for adjusting the image display method according to the user's emotions, thereby displaying a more appropriate image. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the image generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the image generation unit may input the user's emotion data into the generation AI and cause the generation AI to adjust the image display method based on the emotion.

[0094] When generating an image, the image generation unit corrects the content of the image by taking into account the time and frequency of message transmission. For example, the image generation unit uses AI to analyze messages sent late at night and determine that there is a high possibility of bullying. The image generation unit can also use AI to analyze messages sent frequently in a short period of time and detect signs of bullying. The image generation unit can also appropriately correct the content of the image by taking into account the time and frequency of transmission. In this way, by taking into account the time and frequency of transmission, signs of bullying can be detected more accurately. Some or all of the above-mentioned processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input data on the time and frequency of transmission into the generation AI and have the generation AI correct the image content.

[0095] When generating an image, the image generation unit corrects the content of the image by taking into account the context of the message. For example, the image generation unit uses AI to analyze the context before and after the message, improving the accuracy of detecting keywords related to bullying. The image generation unit can also take the context into account and accurately detect keywords that are difficult to determine as bullying on their own. The image generation unit can also more accurately detect signs of bullying through context analysis. As a result, by taking the context into account, signs of bullying can be detected more accurately. Some or all of the above-mentioned processing in the image generation unit may be performed using AI, for example, or may be performed without using AI. For example, the image generation unit can input the context data of the message into the generation AI and have the generation AI correct the image content.

[0096] When generating an image, the image generation unit corrects the content of the image by referring to the message sender's past behavioral history. For example, if the sender has engaged in bullying behavior in the past, the image generation unit can detect even subtle aggressive language as bullying. Furthermore, if the sender has previously sent friendly messages, the image generation unit can also correct the content of the image so that jokes or light-hearted words are not mistaken for bullying. Furthermore, the image generation unit can use AI to learn the sender's past behavioral history and appropriately correct the content of the image. By referring to the sender's past behavioral history, it is possible to reduce the chance of misidentifying bullying. Some or all of the above-described processing in the image generation unit may be performed using, for example, AI, or may be performed without AI. For example, the image generation unit can input the sender's past behavioral history data into the generation AI and have the generation AI correct the image content. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, warning unit, advice unit, and image generation 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 processor 46 of the smart device 14 and analyzes the text of the message to detect keywords and phrases related to bullying. The warning unit is realized by the specific processing unit 290 of the data processing device 12 and sends a warning to the parent or guardian based on the detected content. The advice unit is realized by the control unit 46A of the smart device 14 and provides advice on how to respond, etc. The image generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an image of the content of the message. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, warning unit, advice unit, and image generation 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 processor 46 of the smart glasses 214 and analyzes the text of the message to detect keywords and phrases related to bullying. The warning unit is realized by the specific processing unit 290 of the data processing device 12 and sends a warning to parents based on the detected content. The advice unit is realized by the control unit 46A of the smart glasses 214 and provides advice on how to respond. The image generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an image of the content of the message. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, warning unit, advice unit, and image generation 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 processor 46 of the headset type terminal 314 and analyzes the text of the message to detect keywords and phrases related to bullying. The warning unit is realized by the specific processing unit 290 of the data processing device 12 and sends a warning to the parent or guardian based on the detected content. The advice unit is realized by the control unit 46A of the headset type terminal 314 and provides advice on how to respond, etc. The image generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates the content of the message as an image. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, warning unit, advice unit, and image generation 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 processor 46 of the robot 414 and analyzes the text of the message to detect keywords and phrases related to bullying. The warning unit is realized by the specific processing unit 290 of the data processing device 12 and sends a warning to the parent or guardian based on the detected content. The advice unit is realized by the control unit 46A of the robot 414 and provides advice on how to respond, etc. The image generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates the content of the message as an image.

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

[0098] The analysis unit can analyze not only the text of messages but also the user's behavioral patterns. For example, if a user frequently sends messages during a specific time period, the analysis unit can analyze that behavioral pattern to detect signs of bullying. Furthermore, if a user sends messages from a specific location, the analysis unit can analyze the location information to evaluate the possibility of bullying. Furthermore, the analysis unit can analyze changes in the frequency of a user's message sending and the recipients of those messages to detect signs of bullying early on. Thus, by analyzing a user's behavioral patterns, signs of bullying can be detected more broadly.

[0099] The analysis unit can estimate the user's emotions and evaluate the importance of a message based on the estimated user's emotions. For example, if the user is feeling highly stressed, the message can be evaluated as having a high importance level and a prompt response can be made. Alternatively, if the user is relaxed, the message can be evaluated as having a normal importance level. Furthermore, if the user is excited, the message can be evaluated as having a level of importance that requires special attention. In this way, by evaluating the importance of a message based on the user's emotions, an appropriate response can be made.

[0100] The analysis unit can analyze not only the text of messages but also the user's social media activity. For example, if a user frequently uses a specific keyword on social media, the analysis unit can analyze that keyword to detect signs of bullying. Also, if a user is a member of a specific group on social media, the analysis unit can analyze the activity of that group to evaluate the possibility of bullying. Furthermore, the analysis unit can analyze the user's friendships on social media to detect signs of bullying at an early stage. This allows for a more widespread detection of signs of bullying by analyzing social media activity.

[0101] During analysis, the analysis unit can optimize the analysis algorithm by referring to the user's past message history. For example, if the user has sent messages related to bullying in the past, the analysis unit can optimize the analysis algorithm by referring to the message history. In addition, if the user has sent friendly messages in the past, the analysis unit can also adjust the analysis algorithm by referring to the message history. Furthermore, the analysis unit can analyze bullying patterns based on the user's past message history and detect new signs of bullying. In this way, by referring to the past message history, the accuracy of the analysis algorithm can be improved.

[0102] During analysis, the analysis unit can correct the analysis results by taking into account the user's psychological state. For example, if the user is in a psychologically unstable state, the analysis results can be corrected by taking that state into account, allowing for more accurate detection of signs of bullying. Furthermore, if the user is psychologically stable, the analysis unit can provide analysis results with normal accuracy by taking that state into account. Furthermore, the analysis unit can use AI to learn the user's psychological state and appropriately correct the analysis results. This makes it possible to reduce false positives of bullying by taking the user's psychological state into account.

[0103] The analysis unit can estimate the user's emotions and adjust the message analysis method based on the estimated user emotions. For example, if the user is feeling highly stressed, the analysis method can be set to a more detailed setting to more accurately detect signs of bullying. Alternatively, if the user is relaxed, the analysis method can be set to a normal setting to detect general keywords and phrases. Furthermore, if the user is excited, the analysis method can be adjusted to detect messages containing emotional expressions. This allows for more appropriate analysis results to be obtained by adjusting the analysis method according to the user's emotions.

[0104] During analysis, the analysis unit can correct the analysis results by taking into account the user's message sending patterns. For example, if a user frequently sends messages during a specific time period, the analysis unit can correct the analysis results by taking into account that sending pattern, thereby more accurately detecting signs of bullying. In addition, if a user frequently sends messages to a specific person, the analysis unit can also correct the analysis results by taking into account that sending pattern. Furthermore, the analysis unit can use AI to learn the user's message sending patterns and appropriately correct the analysis results. In this way, by taking into account the user's message sending patterns, it is possible to reduce false positives of bullying.

[0105] During analysis, the analysis unit can correct the analysis results by taking into account the destination of the user's message. For example, if a user sends a message to a specific group, the analysis results can be corrected by taking into account the destination, allowing for more accurate detection of signs of bullying. In addition, if a user sends a message to a specific individual, the analysis unit can also correct the analysis results by taking into account the destination. Furthermore, the analysis unit can use AI to learn the destination of the user's messages and appropriately correct the analysis results. In this way, by taking into account the destination of the user's messages, it is possible to reduce false positives of bullying.

[0106] During analysis, the analysis unit can correct the analysis results by taking into account the content of the user's messages. For example, if a user frequently uses a specific keyword, the analysis results can be corrected by taking into account the content of the messages, allowing for more accurate detection of signs of bullying. In addition, if a user frequently uses a specific phrase, the analysis unit can correct the analysis results by taking into account the content of the messages. Furthermore, the analysis unit can use AI to learn the content of the user's messages and appropriately correct the analysis results. This makes it possible to reduce false positives of bullying by taking into account the content of the user's messages.

[0107] The warning unit can estimate the user's emotions and adjust the content of the warning based on the estimated user's emotions. For example, if the user is feeling highly stressed, the warning unit can send a warning in a calm manner. If the user is relaxed, the warning unit can send a warning with detailed information. Furthermore, if the user is excited, the warning unit can send a quick and concise warning. In this way, by adjusting the content of the warning according to the user's emotions, more appropriate warnings can be sent.

[0108] The processing flow of the second embodiment will be briefly explained below.

[0109] Step 1: The analysis unit analyzes the text of the message to detect keywords or phrases related to bullying. For example, the analysis unit may use natural language processing technology or AI to analyze the context and sentiment of the message to detect signs of bullying. Step 2: The warning unit sends a warning to parents based on the content detected by the analysis unit. For example, the warning unit can send a message related to the detected bullying to the parent's email address or mobile messenger, or can send a warning as a text message or an alert sound. The content of the warning message can also be generated using AI. Step 3: The advice unit provides advice on how to respond based on the warning sent by the warning unit. For example, it provides specific countermeasures against bullying, information on where to seek advice, and information on psychological support and counseling. It is also possible to generate the content of advice using AI. Step 4: The image generation unit generates the message content as an image based on the warning sent by the warning unit. For example, the image generation unit generates the message content as an image to make it easier for parents to check the content. The image content can also be generated using AI.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires 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.

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search 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.

[0112] 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.

[0113] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0119] 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).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0121] 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.

[0122] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0124] 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.

[0125] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires 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.

[0127] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may 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.

[0129] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

[0133] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0134] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0135] 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).

[0136] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0137] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0138] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0140] 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.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires 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.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may 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.

[0145] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] 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).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0153] 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.

[0154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0157] 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.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires 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.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may 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.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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."

[0169] 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.

[0170] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0171] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a 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.

[0172] 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.

[0173] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] [Explanation of symbols]

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

Claims

1. an analysis unit that analyzes the text of the message to detect keywords or phrases related to bullying; a warning unit that sends a warning to a parent or guardian based on the content detected by the analysis unit; an advice unit that provides advice on how to respond based on the warning sent by the warning unit; an image generating unit that generates an image of the content of the message based on the warning sent by the warning unit; A system characterized by:

2. The analysis unit Estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions.

2. The system of claim 1.

3. The analysis unit Analyze not only the text of messages but also images and audio data 2. The system of claim 1.

4. The analysis unit During analysis, the analysis algorithm is optimized by referencing past bullying-related data.

2. The system of claim 1.

5. The analysis unit During analysis, the analysis results are adjusted based on the relationship between the message sender and receiver.

2. The system of claim 1.

6. The analysis unit Estimate the user's emotions and prioritize the analysis results based on the estimated user emotions.

2. The system of claim 1.

7. The analysis unit During analysis, the analysis results are corrected taking into account the time and frequency of message transmission.

2. The system of claim 1.

8. The analysis unit During analysis, the context of the message is taken into account to improve keyword detection accuracy.

2. The system of claim 1.

Images