system

Abstract

The system according to the embodiment aims to identify children's mental health conditions and stress factors and provide appropriate advice. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, an identification unit, and a provision unit. The reception unit receives speech from a child. The analysis unit analyzes the content of the conversation received by the reception unit. The identification unit identifies the mental health condition and stress factors based on the content of the conversation analyzed by the analysis unit. The provision unit provides advice to the child or their parents based on the results identified by the identification unit.

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 the drawback of making it difficult to quickly and accurately grasp a child's mental health and stress factors.

[0005] The system according to the embodiment aims to identify children's mental health conditions and stress factors and provide appropriate advice. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, an identification unit, and a provision unit. The reception unit receives speech from the child. The analysis unit analyzes the content of the conversation received by the reception unit. The identification unit identifies the mental health condition and stress factors based on the content of the conversation analyzed by the analysis unit. The provision unit provides advice to the child or their parents based on the results identified by the identification unit. [Effects of the Invention]

[0007] The system according to the embodiment can identify a child's mental health condition and stress factors and provide appropriate advice. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention is a system that uses a conversational AI character installed on a device for children, and that performs stress checks using the AI. When a child speaks to the device, the AI ​​character initiates a conversation, analyzes the conversation, identifies the child's mental health status and stress factors, and provides advice to the child or their parents based on the analysis results. For example, when a child speaks to the device, the AI ​​character initiates a conversation. For example, if the child asks, "What happened at school today?", the AI ​​character responds, "What happened today?" In this way, a natural conversation takes place between the child and the AI ​​character. Next, the AI ​​analyzes the conversation content and identifies the child's mental health status and stress factors. For example, if a child says, "I had a fight with my friend today," the AI ​​analyzes the content and identifies that the cause of stress is a fight with a friend. It can also assess the child's mental health status from the child's tone of voice and speaking style. Finally, the AI ​​provides advice to the child or their parents based on the analysis results. For example, the AI ​​might advise, "You had a fight with your friend. Why don't you apologize the next time you see each other?" The system can also provide advice to parents, such as, "Your child had a fight with a friend and is feeling stressed. Please listen to him." This allows the system to grasp the child's mental health state and provide appropriate advice. For example, if a child is feeling stressed, the system can identify the cause early on and take appropriate measures to maintain mental health. It also makes it easier for parents to understand their children's mental state and provide appropriate support.

[0029] A stress check system according to an embodiment includes a reception unit, an analysis unit, an identification unit, and a providing unit. The reception unit receives speech from a child. The speech from the child may include, but is not limited to, voice, text, or gesture. The reception unit receives speech from the child using, for example, voice recognition technology. The reception unit may also generate an appropriate response to the child's speech using natural language processing technology. For example, if a child asks, "What happened at school today?", the reception unit replies, "What happened today?" The analysis unit analyzes the content of the conversation received by the reception unit. The analysis may be performed using, for example, voice analysis, text analysis, or emotion analysis, but is not limited to these examples. For example, the analysis unit may use voice recognition technology to analyze the child's tone of voice and speaking style to estimate emotions. The identification unit identifies a mental health condition and stress factors based on the content of the conversation analyzed by the analysis unit. The identification may be performed based on, for example, evaluation criteria such as stress level, happiness level, and psychological stability, but is not limited to these examples. For example, when a child says, "I had a fight with my friend today," the identification unit analyzes the content of the speech and identifies that the cause of stress is a fight with a friend. The provision unit provides advice to the child or their parents based on the results identified by the identification unit. The advice may include, but is not limited to, psychological support, behavioral guidance, and the provision of resources. For example, the provision unit may advise the child, "I see you had a fight with your friend. Why don't you apologize the next time you see each other?" The provision unit may also advise the parent, "Your child has had a fight with a friend and is feeling stressed. Please listen to him / her." In this way, the stress check system according to the embodiment can identify the child's mental health condition and the cause of stress and provide appropriate advice.

[0030] The providing unit includes a notification unit that sends notifications to parents. The notification unit sends notifications to parents by, for example, email, SMS, app notification, or other methods. For example, the notification unit can notify parents of information about their child's mental health condition and stress factors. The notification unit can also notify parents of specific advice. For example, the notification unit can notify parents of advice such as, "Your child had a fight with a friend and is feeling stressed. Please listen to him." This allows the providing unit to quickly notify parents of their child's condition.

[0031] The reception unit includes a scenario unit that uses natural language processing technology to generate appropriate responses to the child's utterances. The scenario unit analyzes the child's utterances using, for example, morphological analysis technology and generates appropriate responses. For example, the scenario unit analyzes the grammar and meaning of the child's utterances and generates responses based on the context. The scenario unit can also analyze the emotions in the child's utterances using emotion analysis technology and generate responses based on the emotions. For example, when a child asks, "What happened at school today?" the scenario unit replies, "What happened today?" This allows the reception unit to have a natural conversation with the child.

[0032] The providing unit includes a database unit that generates advice based on past conversation data. The database unit, for example, stores past conversation data as text data or voice data and uses it to generate advice. For example, the database unit searches past conversation histories and provides advice for similar situations. The database unit can also analyze past conversation data using a machine learning algorithm and generate optimal advice. For example, the database unit provides advice appropriate to the current situation based on the past conversation data. This allows the providing unit to provide more appropriate advice by utilizing past data.

[0033] The reception unit can analyze the child's past conversation history and select the optimal way to start a conversation. For example, if the child has previously preferred happy topics, the reception unit can have the AI ​​character start the conversation by talking about a happy topic. Also, if the child has previously confided their worries, the reception unit can start the conversation by having the AI ​​character listen to their worries. Also, if the child has often spoken at a particular time of day in the past, the reception unit can start the conversation at that time of day. This allows the reception unit to select the optimal way to start a conversation by utilizing the past conversation history.

[0034] When receiving a conversation, the reception unit can perform filtering based on the child's current activity status and areas of interest. For example, if the child is studying, the reception unit can start a conversation by prioritizing topics related to studying. Also, if the child is playing, the reception unit can start a conversation by prioritizing topics related to playing. Also, if the child is interested in a particular anime or game, the reception unit can start a conversation by prioritizing that topic. In this way, the reception unit can provide a conversation that suits the child's current situation and interests.

[0035] The reception unit can select a reception means according to the child's input method when receiving a conversation. For example, if the child speaks by voice, the reception unit can start a conversation by prioritizing the voice input. Also, if the child inputs by text, the reception unit can start a conversation by prioritizing the text input. Also, if the child sends an image, the reception unit can perform image analysis and start a conversation based on the content of the image. This allows the reception unit to provide the optimal reception means according to the child's input method.

[0036] When receiving a conversation, the reception unit can prioritize receiving a highly relevant conversation in consideration of the child's geographical location information. For example, when the child is at school, the reception unit can prioritize receiving a topic related to school. Furthermore, when the child is at a park, the reception unit can also prioritize receiving a topic related to the park. Furthermore, when the child is at home, the reception unit can also prioritize receiving a topic related to home. In this way, the reception unit can provide a highly relevant conversation based on the child's geographical location information.

[0037] The reception unit can analyze the child's social media activity and receive related conversations when receiving a conversation. For example, the reception unit receives related topics based on content posted by the child on social media. The reception unit can also receive related topics based on content of accounts the child follows on social media. The reception unit can also receive related topics based on content of groups the child participates in on social media. This allows the reception unit to provide highly relevant conversations based on the child's social media activity.

[0038] The reception unit can customize the reception method by reflecting the child's past feedback when receiving a conversation. For example, the reception unit can prioritize reception of conversation topics that the child has previously liked. The reception unit can also accept conversations by excluding conversation topics that the child has previously avoided. The reception unit can also prioritize reception of conversation styles that the child has previously given high ratings. This allows the reception unit to provide the optimal reception method based on the child's past feedback.

[0039] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the conversation. For example, the analysis unit performs a detailed analysis when the conversation content is important. The analysis unit can also perform a concise analysis when the conversation content is general. The analysis unit can also perform a quick analysis when the conversation content is highly urgent. This allows the analysis unit to provide analysis results according to the importance of the conversation.

[0040] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the conversation. For example, if the conversation is about school, the analysis unit applies a school-related analysis algorithm. Also, if the conversation is about home, the analysis unit can apply a home-related analysis algorithm. Also, if the conversation is about friendships, the analysis unit can apply a friendship-related analysis algorithm. This allows the analysis unit to provide optimal analysis results depending on the category of the conversation.

[0041] During analysis, the analysis unit can improve the accuracy of the analysis by referring to past analysis results of the child. For example, the analysis unit can identify current stress factors by referring to past stress factors of the child. The analysis unit can also estimate current emotional states by referring to past emotional states of the child. The analysis unit can also analyze current conversation content by referring to past conversation content of the child. In this way, the analysis unit can improve the accuracy of the analysis by utilizing past analysis results.

[0042] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the conversation. For example, the analysis unit prioritizes analysis of the most recent conversation content. The analysis unit can also postpone analysis of past conversation content. The analysis unit can also prioritize analysis of conversation content with high urgency. This allows the analysis unit to provide an analysis priority according to the time of submission of the conversation.

[0043] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the conversation. For example, the analysis unit prioritizes analysis of highly relevant conversation content. The analysis unit can also postpone analysis of less relevant conversation content. The analysis unit can also group and analyze relevant conversation content. This allows the analysis unit to provide an analysis order according to the relevance of the conversation.

[0044] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the child's level of expertise. For example, if the child has technical knowledge, the analysis unit can provide the analysis results using technical terms. Alternatively, if the child does not have technical knowledge, the analysis unit can provide the analysis results in simple language. Alternatively, the analysis unit can select appropriate terms according to the child's level of expertise to provide the analysis results. This allows the analysis unit to provide appropriate analysis results according to the child's level of expertise.

[0045] The identification unit can improve the accuracy of identification by taking into account the interrelationships of conversations during identification. The identification unit can identify stress factors by taking into account, for example, the context of the conversation. The identification unit can also identify stress factors by taking into account the relevance of the content of the conversation. The identification unit can also identify stress factors by taking into account the frequency of the conversation. This allows the identification unit to provide accuracy of identification that takes into account the interrelationships of conversations.

[0046] When identifying, the identification unit can perform the identification by taking into consideration attribute information of the person who submitted the conversation. For example, the identification unit can identify the stress factor by taking into consideration the age of the child. The identification unit can also identify the stress factor by taking into consideration the gender of the child. The identification unit can also identify the stress factor by taking into consideration the interests and concerns of the child. This allows the identification unit to provide an identification based on the attribute information of the person who submitted the conversation.

[0047] At the time of identification, the identification unit can assign a specific weight based on the frequency of submission of the conversation. For example, the identification unit assigns a weight to conversation content that is frequently submitted for identification. The identification unit can also assign a light weight to conversation content that is submitted only once for identification. The identification unit can also adjust the specific weight according to the frequency of submission. In this way, the identification unit can provide a specific weight based on the frequency of submission of the conversation.

[0048] The identification unit can perform the identification by taking into consideration the geographical distribution of the conversation. For example, the identification unit can identify stress factors specific to a region based on what the child said in a specific region. The identification unit can also compare what the child said in different regions to identify common stress factors. The identification unit can also identify stress factors at a travel destination based on what the child said while traveling. This allows the identification unit to provide an identification based on the geographical distribution of the conversation.

[0049] During identification, the identification unit can improve the accuracy of the identification by referring to literature related to the conversation. For example, the identification unit can identify stress factors by referring to academic papers related to the content of the conversation. The identification unit can also identify stress factors by referring to books related to the content of the conversation. The identification unit can also identify stress factors by referring to online articles related to the content of the conversation. This allows the identification unit to provide accuracy of identification based on literature related to the conversation.

[0050] The identification unit can perform identification taking into consideration the market value of the conversation. For example, if the content of the conversation has a high market value, the identification unit prioritizes the content for identification. Also, if the content of the conversation has a low market value, the identification unit can postpone the content for identification. Also, the identification unit can adjust the priority of identification according to the market value of the content of the conversation. This allows the identification unit to provide identification based on the market value of the conversation.

[0051] When providing advice, the providing unit can adjust the level of detail of the advice based on the importance of the conversation. For example, the providing unit provides detailed advice in the case of important conversation content. The providing unit can also provide concise advice in the case of general conversation content. The providing unit can also provide quick advice in the case of highly urgent conversation content. In this way, the providing unit can provide the level of detail of advice according to the importance of the conversation.

[0052] When providing advice, the providing unit can apply different advice algorithms depending on the category of the conversation. For example, in the case of a conversation about school, the providing unit applies a school-related advice algorithm. In addition, in the case of a conversation about home, the providing unit can also apply a home-related advice algorithm. In addition, in the case of a conversation about friendships, the providing unit can also apply a friendship-related advice algorithm. This allows the providing unit to provide optimal advice according to the category of the conversation.

[0053] When providing advice, the providing unit can improve the accuracy of the advice by referring to past advice results for the child. The providing unit, for example, adjusts the current advice based on the past advice results for the child. The providing unit can also analyze the past advice results for the child and provide optimal advice. The providing unit can also improve the accuracy of the advice by referring to the past advice results for the child. In this way, the providing unit can improve the accuracy of the advice by utilizing the past advice results.

[0054] When providing advice, the providing unit can determine the priority of the advice based on the time of submission of the conversation. The providing unit can provide advice preferentially based on, for example, the content of the most recent conversation. The providing unit can also provide advice later based on the content of the past conversation. The providing unit can also provide advice with the highest priority based on the content of the conversation with the highest urgency. This allows the providing unit to provide the priority of advice according to the time of submission of the conversation.

[0055] The providing unit can adjust the order of advice based on the relevance of the conversation when providing advice. For example, the providing unit provides advice preferentially based on highly relevant conversation content. The providing unit can also provide advice later based on less relevant conversation content. The providing unit can also provide advice by grouping relevant conversation content. This allows the providing unit to provide the order of advice according to the relevance of the conversation.

[0056] When providing advice, the providing unit may adjust the use of technical terms in the advice depending on the child's level of expertise. For example, if the child has technical knowledge, the providing unit may provide the advice using technical terms. Also, if the child does not have technical knowledge, the providing unit may provide the advice in simple language. Also, the providing unit may provide the advice by selecting appropriate terms depending on the child's level of expertise. In this way, the providing unit can provide appropriate advice depending on the child's level of expertise.

[0057] The estimation unit can improve the accuracy of estimation by taking into account the interrelationships of conversations during estimation. The estimation unit estimates stress factors by taking into account, for example, the context of the conversation. The estimation unit can also estimate stress factors by taking into account the relevance of the content of the conversation. The estimation unit can also estimate stress factors by taking into account the frequency of the conversation. In this way, the estimation unit can provide accuracy of estimation that takes into account the interrelationships of conversations.

[0058] The estimation unit can make an estimation by taking into account attribute information of the person who submitted the conversation. For example, the estimation unit estimates the stress factor by taking into account the age of the child. The estimation unit can also estimate the stress factor by taking into account the gender of the child. The estimation unit can also estimate the stress factor by taking into account the interests and concerns of the child. This allows the estimation unit to provide an estimation based on the attribute information of the person who submitted the conversation.

[0059] The estimation unit can make the estimation by taking into account the geographical distribution of the conversation. For example, the estimation unit estimates region-specific stress factors based on what the child said in a particular region. The estimation unit can also compare what the child said in different regions and estimate common stress factors. The estimation unit can also estimate stress factors at a travel destination based on what the child said while traveling. This allows the estimation unit to provide estimations based on the geographical distribution of the conversation.

[0060] The estimation unit can improve the accuracy of the estimation by referring to literature related to the conversation during estimation. For example, the estimation unit can refer to academic papers related to the content of the conversation to estimate stress factors. The estimation unit can also refer to books related to the content of the conversation to estimate stress factors. The estimation unit can also refer to online articles related to the content of the conversation to estimate stress factors. This allows the estimation unit to provide accuracy of estimation based on literature related to the conversation.

[0061] The estimation unit can make an estimation taking into account the market value of the conversation. For example, if the content of the conversation has a high value in the market, the estimation unit prioritizes that content in its estimation. Also, if the content of the conversation has a low value in the market, the estimation unit can postpone its estimation. Also, the estimation unit can adjust the priority of estimation according to the market value of the content of the conversation. This allows the estimation unit to provide an estimation based on the market value of the conversation.

[0062] The notification unit can determine the priority of notification based on the importance of the conversation when making a notification. For example, if the conversation content is important, the notification unit notifies the parent first. Also, if the conversation content is general, the notification unit can notify the parent later. Also, if the conversation content is highly urgent, the notification unit can notify the parent with the highest priority. In this way, the notification unit can provide notification priorities according to the importance of the conversation.

[0063] The notification unit can apply different notification methods depending on the category of the conversation when making a notification. For example, in the case of a conversation about school, the notification unit applies a school-related notification method to the parent. In addition, in the case of a conversation about home, the notification unit can also apply a home-related notification method to the parent. In addition, in the case of a conversation about friendship, the notification unit can also apply a friendship-related notification method to the parent. This allows the notification unit to provide the optimal notification method depending on the category of the conversation.

[0064] The notification unit can adjust the content of the notification based on the time of submission of the conversation when notifying. The notification unit can notify the parent of the latest information based on the content of the most recent conversation, for example. The notification unit can also notify the parent of reference information based on the content of past conversations. The notification unit can also immediately notify the parent based on the content of conversations with high urgency. This allows the notification unit to provide the content of the notification according to the time of submission of the conversation.

[0065] The notification unit can adjust the order of notifications based on the relevance of the conversations when notifying. For example, the notification unit can notify the parent preferentially based on highly relevant conversation content. The notification unit can also notify the parent later based on less relevant conversation content. The notification unit can also group relevant conversation content and notify the parent. This allows the notification unit to provide an order of notifications according to the relevance of the conversations.

[0066] When generating a scenario, the scenario unit can adjust the level of detail of the scenario based on the importance of the conversation. For example, the scenario unit provides a detailed scenario for important conversation content. The scenario unit can also provide a concise scenario for general conversation content. The scenario unit can also provide a quick scenario for urgent conversation content. This allows the scenario unit to provide a level of detail of the scenario according to the importance of the conversation.

[0067] When generating a scenario, the scenario unit can apply different scenario algorithms depending on the category of the conversation. For example, if the conversation is about school, the scenario unit can apply a school-related scenario algorithm. Also, if the conversation is about home, the scenario unit can apply a home-related scenario algorithm. Also, if the conversation is about friendships, the scenario unit can apply a friendship-related scenario algorithm. This allows the scenario unit to provide an optimal scenario according to the category of the conversation.

[0068] When generating a scenario, the scenario unit can determine the priority of the scenario based on the time of submission of the conversation. The scenario unit can provide a scenario with priority based on, for example, the content of the most recent conversation. The scenario unit can also provide a scenario later based on the content of the past conversation. The scenario unit can also provide a scenario with the highest priority based on the content of the conversation with the highest urgency. This allows the scenario unit to provide a priority of the scenario according to the time of submission of the conversation.

[0069] When generating a scenario, the scenario unit can adjust the order of scenarios based on the relevance of the conversations. For example, the scenario unit provides a scenario with priority based on highly relevant conversation content. The scenario unit can also provide a scenario later based on less relevant conversation content. The scenario unit can also provide a scenario by grouping related conversation content. This allows the scenario unit to provide an order of scenarios according to the relevance of the conversations.

[0070] When updating the database, the database unit can improve the accuracy of the database by referring to past data. For example, the database unit scrutinizes current data based on past data and adds it to the database. The database unit can also analyze past data to improve the accuracy of the database. The database unit can also update the contents of the database by referring to past data. In this way, the database unit can improve the accuracy of the database by utilizing past data.

[0071] When updating the database, the database unit can apply different database algorithms depending on the category of the conversation. For example, in the case of a conversation about school, the database unit applies a school-related database algorithm. In addition, in the case of a conversation about home, the database unit can also apply a home-related database algorithm. In addition, in the case of a conversation about friendship, the database unit can also apply a friendship-related database algorithm. In this way, the database unit can provide an optimal database according to the category of the conversation.

[0072] When updating the database, the database unit can adjust the contents of the database based on the time of submission of the conversation. For example, the database unit can add recent conversation contents to the database with priority. The database unit can also add older conversation contents to the database later. The database unit can also add conversation contents with high urgency to the database with top priority. This allows the database unit to provide database contents according to the time of submission of the conversation.

[0073] The database unit can adjust the order of the database based on the relevance of the conversations when updating the database. For example, the database unit adds highly relevant conversation content to the database with priority. The database unit can also add less relevant conversation content to the database later. The database unit can also group related conversation content and add it to the database. In this way, the database unit can provide an order of the database according to the relevance of the conversations.

[0074] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0075] When accepting a child's message, the reception unit can adjust the content of the conversation taking into account the child's current physical condition information. For example, if the child has a cold, the AI ​​character will prioritize conversations that show concern for the child's health. Also, if the child is tired, the AI ​​character can offer topics that will help the child relax. Furthermore, if the child is in good health, the AI ​​character can offer lively topics. This allows the reception unit to provide appropriate conversations according to the child's physical condition.

[0076] When sending a notification to a parent, the providing unit can adjust the content of the notification taking into account the parent's current situation. For example, if the parent is at work, a brief notification can be sent. If the parent is at home, a detailed notification can be sent. Furthermore, if the parent is traveling, the notification can be delayed. This allows the providing unit to provide an appropriate notification according to the parent's situation.

[0077] When generating an appropriate response to a child's comments, the reception unit can adjust the content of the response taking into account the child's learning progress. For example, if a child asks a question related to the content they are studying, the AI ​​character will respond based on that content. Also, if a child talks about worries about their studies, the AI ​​character can provide study advice. Furthermore, if a child talks about a successful experience with their studies, the AI ​​character can respond by praising them. This allows the reception unit to provide appropriate responses according to the child's learning progress.

[0078] When generating advice based on past conversation data, the providing unit can adjust the content of the advice taking into account the child's developmental stage. For example, simple and easy-to-understand advice can be provided to a toddler. Specific and practical advice can also be provided to an elementary school child. Furthermore, more advanced advice can be provided to a junior high school child. This allows the providing unit to provide appropriate advice according to the child's developmental stage.

[0079] The reception unit can analyze the child's past conversation history and select the optimal way to start a conversation. For example, if the child has previously preferred happy topics, the AI ​​character can start the conversation by talking about happy topics. Also, if the child has previously confided their worries, the reception unit can start the conversation by having the AI ​​character listen to their worries. Also, if the child has often spoken at a certain time of day in the past, the reception unit can start the conversation at that time of day. This allows the reception unit to select the optimal way to start a conversation by utilizing past conversation history.

[0080] When receiving a conversation, the reception unit can filter the conversation based on the child's current activity status and areas of interest. For example, if the child is studying, the reception unit can start a conversation by prioritizing topics related to studying. Also, if the child is playing, the reception unit can start a conversation by prioritizing topics related to playing. Also, if the child is interested in a particular anime or game, the reception unit can start a conversation by prioritizing that topic. In this way, the reception unit can provide a conversation that suits the child's current situation and interests.

[0081] When accepting a conversation, the reception unit can select a reception means according to the child's input method. For example, if the child speaks by voice, the reception unit can start the conversation by prioritizing the voice input. Also, if the child inputs by text, the reception unit can start the conversation by prioritizing the text input. Also, if the child sends an image, the reception unit can perform image analysis and start the conversation based on the content of the image. This allows the reception unit to provide the optimal reception means according to the child's input method.

[0082] The processing flow of the first embodiment will be briefly explained below.

[0083] Step 1: The reception unit accepts what the child is saying. The child's speech may include voice, text, gestures, etc. The reception unit accepts what the child is saying using voice recognition technology, and can also generate an appropriate response using natural language processing technology. For example, if a child asks, "What happened at school today?", the reception unit will respond with, "What happened today?" Step 2: The analysis unit analyzes the conversation content received by the reception unit. The analysis is performed using methods such as voice analysis, text analysis, and emotion analysis. For example, the analysis unit can use voice recognition technology to analyze the child's tone of voice and speaking style to estimate their emotion. Step 3: The identification unit identifies mental health conditions and stress factors based on the conversation content analyzed by the analysis unit. Identification is based on evaluation criteria such as stress level, happiness, and psychological stability. For example, if a child says, "I had a fight with my friend today," the identification unit analyzes the content and identifies that the cause of stress is a fight with a friend. Step 4: The provider provides advice to the child or their parents based on the results identified by the identifyr. The advice may include psychological support, behavioral guidance, or the provision of resources. For example, the provider might advise a child, "You had a fight with your friend. Why don't you apologize the next time you see each other?" The provider can also advise parents, "Your child had a fight with a friend and is feeling stressed. Please listen to him."

[0084] (Example 2) A system according to an embodiment of the present invention is a system that uses a conversational AI character installed on a device for children, and that performs stress checks using the AI. When a child speaks to the device, the AI ​​character initiates a conversation, analyzes the conversation, identifies the child's mental health status and stress factors, and provides advice to the child or their parents based on the analysis results. For example, when a child speaks to the device, the AI ​​character initiates a conversation. For example, if the child asks, "What happened at school today?", the AI ​​character responds, "What happened today?" In this way, a natural conversation takes place between the child and the AI ​​character. Next, the AI ​​analyzes the conversation content and identifies the child's mental health status and stress factors. For example, if a child says, "I had a fight with my friend today," the AI ​​analyzes the content and identifies that the cause of stress is a fight with a friend. It can also assess the child's mental health status from the child's tone of voice and speaking style. Finally, the AI ​​provides advice to the child or their parents based on the analysis results. For example, the AI ​​might advise, "You had a fight with your friend. Why don't you apologize the next time you see each other?" The system can also provide advice to parents, such as, "Your child had a fight with a friend and is feeling stressed. Please listen to him." This allows the system to grasp the child's mental health state and provide appropriate advice. For example, if a child is feeling stressed, the system can identify the cause early on and take appropriate measures to maintain mental health. It also makes it easier for parents to understand their children's mental state and provide appropriate support.

[0085] A stress check system according to an embodiment includes a reception unit, an analysis unit, an identification unit, and a providing unit. The reception unit receives speech from a child. The speech from the child may include, but is not limited to, voice, text, or gesture. The reception unit receives speech from the child using, for example, voice recognition technology. The reception unit may also generate an appropriate response to the child's speech using natural language processing technology. For example, if a child asks, "What happened at school today?", the reception unit replies, "What happened today?" The analysis unit analyzes the content of the conversation received by the reception unit. The analysis may be performed using, for example, voice analysis, text analysis, or emotion analysis, but is not limited to these examples. For example, the analysis unit may use voice recognition technology to analyze the child's tone of voice and speaking style to estimate emotions. The identification unit identifies a mental health condition and stress factors based on the content of the conversation analyzed by the analysis unit. The identification may be performed based on, for example, evaluation criteria such as stress level, happiness level, and psychological stability, but is not limited to these examples. For example, when a child says, "I had a fight with my friend today," the identification unit analyzes the content of the speech and identifies that the cause of stress is a fight with a friend. The provision unit provides advice to the child or their parents based on the results identified by the identification unit. The advice may include, but is not limited to, psychological support, behavioral guidance, and the provision of resources. For example, the provision unit may advise the child, "I see you had a fight with your friend. Why don't you apologize the next time you see each other?" The provision unit may also advise the parent, "Your child has had a fight with a friend and is feeling stressed. Please listen to him / her." In this way, the stress check system according to the embodiment can identify the child's mental health condition and the cause of stress and provide appropriate advice.

[0086] The analysis unit includes an estimation unit that uses voice recognition technology to analyze the child's tone of voice and speaking style to estimate emotions. The estimation unit analyzes the child's tone of voice using, for example, voice tone analysis technology. For example, the estimation unit analyzes pitch, intensity, rhythm, etc. to estimate emotions. The estimation unit can also analyze the child's speaking style using voice pattern recognition technology. For example, the estimation unit analyzes speaking speed, pauses, word choice, etc. to estimate emotions. The estimation unit can also comprehensively analyze the child's tone of voice and speaking style using voice recognition technology to estimate emotions. For example, the estimation unit analyzes a combination of pitch, intensity, speaking speed, etc. to estimate emotions. This allows the analysis unit to more accurately estimate the child's emotions. Emotion estimation is achieved using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0087] The providing unit includes a notification unit that sends notifications to parents. The notification unit sends notifications to parents by, for example, email, SMS, app notification, or other methods. For example, the notification unit can notify parents of information about their child's mental health condition and stress factors. The notification unit can also notify parents of specific advice. For example, the notification unit can notify parents of advice such as, "Your child had a fight with a friend and is feeling stressed. Please listen to him." This allows the providing unit to quickly notify parents of their child's condition.

[0088] The reception unit includes a scenario unit that uses natural language processing technology to generate appropriate responses to the child's utterances. The scenario unit analyzes the child's utterances using, for example, morphological analysis technology and generates appropriate responses. For example, the scenario unit analyzes the grammar and meaning of the child's utterances and generates responses based on the context. The scenario unit can also analyze the emotions in the child's utterances using emotion analysis technology and generate responses based on the emotions. For example, when a child asks, "What happened at school today?" the scenario unit replies, "What happened today?" This allows the reception unit to have a natural conversation with the child.

[0089] The providing unit includes a database unit that generates advice based on past conversation data. The database unit, for example, stores past conversation data as text data or voice data and uses it to generate advice. For example, the database unit searches past conversation histories and provides advice for similar situations. The database unit can also analyze past conversation data using a machine learning algorithm and generate optimal advice. For example, the database unit provides advice appropriate to the current situation based on the past conversation data. This allows the providing unit to provide more appropriate advice by utilizing past data.

[0090] The reception unit can estimate the child's emotions and adjust the timing of starting the conversation based on the estimated child's emotions. For example, if the child is feeling stressed, the reception unit can have the AI ​​character speak to the child in a gentle voice and delay the timing of starting the conversation. If the child is relaxed, the reception unit can have the AI ​​character speak to the child in a cheerful voice and start the conversation immediately. If the child is excited, the reception unit can have the AI ​​character speak to the child in a calm voice and start the conversation slowly. This allows the reception unit to start the conversation at an appropriate time depending on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0091] The reception unit can analyze the child's past conversation history and select the optimal way to start a conversation. For example, if the child has previously preferred happy topics, the reception unit can have the AI ​​character start the conversation by talking about a happy topic. Also, if the child has previously confided their worries, the reception unit can start the conversation by having the AI ​​character listen to their worries. Also, if the child has often spoken at a particular time of day in the past, the reception unit can start the conversation at that time of day. This allows the reception unit to select the optimal way to start a conversation by utilizing the past conversation history.

[0092] When receiving a conversation, the reception unit can perform filtering based on the child's current activity status and areas of interest. For example, if the child is studying, the reception unit can start a conversation by prioritizing topics related to studying. Also, if the child is playing, the reception unit can start a conversation by prioritizing topics related to playing. Also, if the child is interested in a particular anime or game, the reception unit can start a conversation by prioritizing that topic. In this way, the reception unit can provide a conversation that suits the child's current situation and interests.

[0093] The reception unit can select a reception means according to the child's input method when receiving a conversation. For example, if the child speaks by voice, the reception unit can start a conversation by prioritizing the voice input. Also, if the child inputs by text, the reception unit can start a conversation by prioritizing the text input. Also, if the child sends an image, the reception unit can perform image analysis and start a conversation based on the content of the image. This allows the reception unit to provide the optimal reception means according to the child's input method.

[0094] The reception unit can estimate the child's emotions and determine the priority of conversations to be received based on the estimated child's emotions. For example, if the child is feeling stressed, the reception unit can prioritize receiving conversations related to stress. Furthermore, if the child is relaxed, the reception unit can also prioritize receiving conversations related to relaxation. Furthermore, if the child is excited, the reception unit can also prioritize receiving conversations related to excitement. This allows the reception unit to determine the priority of conversations according to the child's emotions. Emotion estimation is achieved using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0095] When receiving a conversation, the reception unit can prioritize receiving a highly relevant conversation in consideration of the child's geographical location information. For example, when the child is at school, the reception unit can prioritize receiving a topic related to school. Furthermore, when the child is at a park, the reception unit can also prioritize receiving a topic related to the park. Furthermore, when the child is at home, the reception unit can also prioritize receiving a topic related to home. In this way, the reception unit can provide a highly relevant conversation based on the child's geographical location information.

[0096] The reception unit can analyze the child's social media activity and receive related conversations when receiving a conversation. For example, the reception unit receives related topics based on content posted by the child on social media. The reception unit can also receive related topics based on content of accounts the child follows on social media. The reception unit can also receive related topics based on content of groups the child participates in on social media. This allows the reception unit to provide highly relevant conversations based on the child's social media activity.

[0097] The reception unit can customize the reception method by reflecting the child's past feedback when receiving a conversation. For example, the reception unit can prioritize reception of conversation topics that the child has previously liked. The reception unit can also accept conversations by excluding conversation topics that the child has previously avoided. The reception unit can also prioritize reception of conversation styles that the child has previously given high ratings. This allows the reception unit to provide the optimal reception method based on the child's past feedback.

[0098] The analysis unit can estimate the child's emotions and adjust the way the analysis is presented based on the estimated child's emotions. For example, if the child is feeling stressed, the analysis unit expresses the analysis results in gentle words. If the child is relaxed, the analysis unit can also explain the analysis results in detail. If the child is excited, the analysis unit can also summarize the analysis results concisely. This allows the analysis unit to provide analysis results that correspond to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0099] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the conversation. For example, the analysis unit performs a detailed analysis when the conversation content is important. The analysis unit can also perform a concise analysis when the conversation content is general. The analysis unit can also perform a quick analysis when the conversation content is highly urgent. This allows the analysis unit to provide analysis results according to the importance of the conversation.

[0100] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the conversation. For example, if the conversation is about school, the analysis unit applies a school-related analysis algorithm. Also, if the conversation is about home, the analysis unit can apply a home-related analysis algorithm. Also, if the conversation is about friendships, the analysis unit can apply a friendship-related analysis algorithm. This allows the analysis unit to provide optimal analysis results depending on the category of the conversation.

[0101] During analysis, the analysis unit can improve the accuracy of the analysis by referring to past analysis results of the child. For example, the analysis unit can identify current stress factors by referring to past stress factors of the child. The analysis unit can also estimate current emotional states by referring to past emotional states of the child. The analysis unit can also analyze current conversation content by referring to past conversation content of the child. In this way, the analysis unit can improve the accuracy of the analysis by utilizing past analysis results.

[0102] The analysis unit can estimate the child's emotion and adjust the length of the analysis based on the estimated emotion of the child. For example, if the child is stressed, the analysis unit provides a short analysis result. If the child is relaxed, the analysis unit can also provide a detailed analysis result. If the child is excited, the analysis unit can also provide a concise analysis result. This allows the analysis unit to provide the length of the analysis result according to the child's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0103] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the conversation. For example, the analysis unit prioritizes analysis of the most recent conversation content. The analysis unit can also postpone analysis of past conversation content. The analysis unit can also prioritize analysis of conversation content with high urgency. This allows the analysis unit to provide an analysis priority according to the time of submission of the conversation.

[0104] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the conversation. For example, the analysis unit prioritizes analysis of highly relevant conversation content. The analysis unit can also postpone analysis of less relevant conversation content. The analysis unit can also group and analyze relevant conversation content. This allows the analysis unit to provide an analysis order according to the relevance of the conversation.

[0105] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the child's level of expertise. For example, if the child has technical knowledge, the analysis unit can provide the analysis results using technical terms. Alternatively, if the child does not have technical knowledge, the analysis unit can provide the analysis results in simple language. Alternatively, the analysis unit can select appropriate terms according to the child's level of expertise to provide the analysis results. This allows the analysis unit to provide appropriate analysis results according to the child's level of expertise.

[0106] The identification unit can estimate the child's emotions and adjust the specific criteria based on the estimated child's emotions. For example, if the child is feeling stressed, the identification unit can tighten the criteria for identifying stressors. Also, if the child is relaxed, the identification unit can loosen the criteria for identifying stressors. Also, if the child is excited, the identification unit can set the criteria for identifying stressors to a moderate level. This allows the identification unit to provide specific criteria according to the child's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0107] The identification unit can improve the accuracy of identification by taking into account the interrelationships of conversations during identification. The identification unit can identify stress factors by taking into account, for example, the context of the conversation. The identification unit can also identify stress factors by taking into account the relevance of the content of the conversation. The identification unit can also identify stress factors by taking into account the frequency of the conversation. This allows the identification unit to provide accuracy of identification that takes into account the interrelationships of conversations.

[0108] When identifying, the identification unit can perform the identification by taking into consideration attribute information of the person who submitted the conversation. For example, the identification unit can identify the stress factor by taking into consideration the age of the child. The identification unit can also identify the stress factor by taking into consideration the gender of the child. The identification unit can also identify the stress factor by taking into consideration the interests and concerns of the child. This allows the identification unit to provide an identification based on the attribute information of the person who submitted the conversation.

[0109] At the time of identification, the identification unit can assign a specific weight based on the frequency of submission of the conversation. For example, the identification unit assigns a weight to conversation content that is frequently submitted for identification. The identification unit can also assign a light weight to conversation content that is submitted only once for identification. The identification unit can also adjust the specific weight according to the frequency of submission. In this way, the identification unit can provide a specific weight based on the frequency of submission of the conversation.

[0110] The identification unit can estimate the child's emotion and adjust the order in which specific results are displayed based on the estimated emotion of the child. For example, if the child is feeling stressed, the identification unit can display the stressor first. Also, if the child is relaxed, the identification unit can display the stressor later. Also, if the child is excited, the identification unit can display the stressor in the middle. In this way, the identification unit can provide a display order of specific results according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0111] The identification unit can perform the identification by taking into consideration the geographical distribution of the conversation. For example, the identification unit can identify stress factors specific to a region based on what the child said in a specific region. The identification unit can also compare what the child said in different regions to identify common stress factors. The identification unit can also identify stress factors at a travel destination based on what the child said while traveling. This allows the identification unit to provide an identification based on the geographical distribution of the conversation.

[0112] During identification, the identification unit can improve the accuracy of the identification by referring to literature related to the conversation. For example, the identification unit can identify stress factors by referring to academic papers related to the content of the conversation. The identification unit can also identify stress factors by referring to books related to the content of the conversation. The identification unit can also identify stress factors by referring to online articles related to the content of the conversation. This allows the identification unit to provide accuracy of identification based on literature related to the conversation.

[0113] The identification unit can perform identification taking into consideration the market value of the conversation. For example, if the content of the conversation has a high market value, the identification unit prioritizes the content for identification. Also, if the content of the conversation has a low market value, the identification unit can postpone the content for identification. Also, the identification unit can adjust the priority of identification according to the market value of the content of the conversation. This allows the identification unit to provide identification based on the market value of the conversation.

[0114] The providing unit can estimate the child's emotions and adjust the way in which advice is expressed based on the estimated child's emotions. For example, if the child is feeling stressed, the providing unit can provide advice in gentle words. If the child is relaxed, the providing unit can also provide detailed advice. If the child is excited, the providing unit can also provide concise advice. This allows the providing unit to provide a way of expressing advice according to the child's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0115] When providing advice, the providing unit can adjust the level of detail of the advice based on the importance of the conversation. For example, the providing unit provides detailed advice in the case of important conversation content. The providing unit can also provide concise advice in the case of general conversation content. The providing unit can also provide quick advice in the case of highly urgent conversation content. In this way, the providing unit can provide the level of detail of advice according to the importance of the conversation.

[0116] When providing advice, the providing unit can apply different advice algorithms depending on the category of the conversation. For example, in the case of a conversation about school, the providing unit applies a school-related advice algorithm. In addition, in the case of a conversation about home, the providing unit can also apply a home-related advice algorithm. In addition, in the case of a conversation about friendships, the providing unit can also apply a friendship-related advice algorithm. This allows the providing unit to provide optimal advice according to the category of the conversation.

[0117] When providing advice, the providing unit can improve the accuracy of the advice by referring to past advice results for the child. The providing unit, for example, adjusts the current advice based on the past advice results for the child. The providing unit can also analyze the past advice results for the child and provide optimal advice. The providing unit can also improve the accuracy of the advice by referring to the past advice results for the child. In this way, the providing unit can improve the accuracy of the advice by utilizing the past advice results.

[0118] The providing unit can estimate the child's emotion and adjust the length of advice based on the estimated emotion of the child. For example, if the child is stressed, the providing unit can provide short advice. If the child is relaxed, the providing unit can also provide detailed advice. If the child is excited, the providing unit can also provide concise advice. This allows the providing unit to provide the length of advice according to the child's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0119] When providing advice, the providing unit can determine the priority of the advice based on the time of submission of the conversation. The providing unit can provide advice preferentially based on, for example, the content of the most recent conversation. The providing unit can also provide advice later based on the content of the past conversation. The providing unit can also provide advice with the highest priority based on the content of the conversation with the highest urgency. This allows the providing unit to provide the priority of advice according to the time of submission of the conversation.

[0120] The providing unit can adjust the order of advice based on the relevance of the conversation when providing advice. For example, the providing unit provides advice preferentially based on highly relevant conversation content. The providing unit can also provide advice later based on less relevant conversation content. The providing unit can also provide advice by grouping relevant conversation content. This allows the providing unit to provide the order of advice according to the relevance of the conversation.

[0121] When providing advice, the providing unit may adjust the use of technical terms in the advice depending on the child's level of expertise. For example, if the child has technical knowledge, the providing unit may provide the advice using technical terms. Also, if the child does not have technical knowledge, the providing unit may provide the advice in simple language. Also, the providing unit may provide the advice by selecting appropriate terms depending on the child's level of expertise. In this way, the providing unit can provide appropriate advice depending on the child's level of expertise.

[0122] The estimation unit can estimate the child's emotion and adjust the estimation standard based on the estimated emotion of the child. For example, if the child is feeling stressed, the estimation unit can tighten the standard for estimating stress factors. Also, if the child is relaxed, the estimation unit can loosen the standard for estimating stress factors. Also, if the child is excited, the estimation unit can set the standard for estimating stress factors to a moderate level. This allows the estimation unit to provide estimation standards according to the child's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0123] The estimation unit can improve the accuracy of estimation by taking into account the interrelationships of conversations during estimation. The estimation unit estimates stress factors by taking into account, for example, the context of the conversation. The estimation unit can also estimate stress factors by taking into account the relevance of the content of the conversation. The estimation unit can also estimate stress factors by taking into account the frequency of the conversation. In this way, the estimation unit can provide accuracy of estimation that takes into account the interrelationships of conversations.

[0124] The estimation unit can make an estimation by taking into account attribute information of the person who submitted the conversation. For example, the estimation unit estimates the stress factor by taking into account the age of the child. The estimation unit can also estimate the stress factor by taking into account the gender of the child. The estimation unit can also estimate the stress factor by taking into account the interests and concerns of the child. This allows the estimation unit to provide an estimation based on the attribute information of the person who submitted the conversation.

[0125] The estimation unit can estimate the child's emotion and adjust the order in which the estimation results are displayed based on the estimated emotion of the child. For example, if the child is feeling stressed, the estimation unit can display the stressor first. Also, if the child is relaxed, the estimation unit can display the stressor later. Also, if the child is excited, the estimation unit can display the stressor in the middle. This allows the estimation unit to provide a display order for the estimation results according to the child's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0126] The estimation unit can make the estimation by taking into account the geographical distribution of the conversation. For example, the estimation unit estimates region-specific stress factors based on what the child said in a particular region. The estimation unit can also compare what the child said in different regions and estimate common stress factors. The estimation unit can also estimate stress factors at a travel destination based on what the child said while traveling. This allows the estimation unit to provide estimations based on the geographical distribution of the conversation.

[0127] The estimation unit can improve the accuracy of the estimation by referring to literature related to the conversation during estimation. For example, the estimation unit can refer to academic papers related to the content of the conversation to estimate stress factors. The estimation unit can also refer to books related to the content of the conversation to estimate stress factors. The estimation unit can also refer to online articles related to the content of the conversation to estimate stress factors. This allows the estimation unit to provide accuracy of estimation based on literature related to the conversation.

[0128] The estimation unit can make an estimation taking into account the market value of the conversation. For example, if the content of the conversation has a high value in the market, the estimation unit prioritizes that content in its estimation. Also, if the content of the conversation has a low value in the market, the estimation unit can postpone its estimation. Also, the estimation unit can adjust the priority of estimation according to the market value of the content of the conversation. This allows the estimation unit to provide an estimation based on the market value of the conversation.

[0129] The notification unit can estimate the child's emotion and adjust the content of the notification based on the estimated emotion of the child. For example, if the child is feeling stressed, the notification unit notifies the parent of the cause of the stress and measures to address it. Furthermore, if the child is relaxed, the notification unit can also notify the parent of the child's relaxed state. Furthermore, if the child is excited, the notification unit can also notify the parent of the child's excited state. This allows the notification unit to provide notification content according to the child's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0130] The notification unit can determine the priority of notification based on the importance of the conversation when making a notification. For example, if the conversation content is important, the notification unit notifies the parent first. Also, if the conversation content is general, the notification unit can notify the parent later. Also, if the conversation content is highly urgent, the notification unit can notify the parent with the highest priority. In this way, the notification unit can provide notification priorities according to the importance of the conversation.

[0131] The notification unit can apply different notification methods depending on the category of the conversation when making a notification. For example, in the case of a conversation about school, the notification unit applies a school-related notification method to the parent. In addition, in the case of a conversation about home, the notification unit can also apply a home-related notification method to the parent. In addition, in the case of a conversation about friendship, the notification unit can also apply a friendship-related notification method to the parent. This allows the notification unit to provide the optimal notification method depending on the category of the conversation.

[0132] The notification unit can estimate the child's emotion and adjust the timing of notification based on the estimated emotion of the child. For example, if the child is feeling stressed, the notification unit can provide an immediate notification so that the parent can respond immediately. Furthermore, if the child is relaxed, the notification unit can also provide periodic notifications to the parent. Furthermore, if the child is excited, the notification unit can also provide notifications to the parent at an appropriate time. This allows the notification unit to provide timing of notifications according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0133] The notification unit can adjust the content of the notification based on the time of submission of the conversation when notifying. The notification unit can notify the parent of the latest information based on the content of the most recent conversation, for example. The notification unit can also notify the parent of reference information based on the content of past conversations. The notification unit can also immediately notify the parent based on the content of conversations with high urgency. This allows the notification unit to provide the content of the notification according to the time of submission of the conversation.

[0134] The notification unit can adjust the order of notifications based on the relevance of the conversations when notifying. For example, the notification unit can notify the parent preferentially based on highly relevant conversation content. The notification unit can also notify the parent later based on less relevant conversation content. The notification unit can also group relevant conversation content and notify the parent. This allows the notification unit to provide an order of notifications according to the relevance of the conversations.

[0135] The scenario unit can estimate the child's emotions and adjust the way the scenario is expressed based on the estimated child's emotions. For example, if the child is feeling stressed, the scenario unit can progress the scenario using gentle words. Furthermore, if the child is relaxed, the scenario unit can provide a detailed scenario. Furthermore, if the child is excited, the scenario unit can provide a concise scenario. In this way, the scenario unit can provide a way of expressing the scenario according to the child's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0136] When generating a scenario, the scenario unit can adjust the level of detail of the scenario based on the importance of the conversation. For example, the scenario unit provides a detailed scenario for important conversation content. The scenario unit can also provide a concise scenario for general conversation content. The scenario unit can also provide a quick scenario for urgent conversation content. This allows the scenario unit to provide a level of detail of the scenario according to the importance of the conversation.

[0137] When generating a scenario, the scenario unit can apply different scenario algorithms depending on the category of the conversation. For example, if the conversation is about school, the scenario unit can apply a school-related scenario algorithm. Also, if the conversation is about home, the scenario unit can apply a home-related scenario algorithm. Also, if the conversation is about friendships, the scenario unit can apply a friendship-related scenario algorithm. This allows the scenario unit to provide an optimal scenario according to the category of the conversation.

[0138] The scenario unit can estimate the child's emotions and adjust the length of the scenario based on the estimated child's emotions. For example, if the child is feeling stressed, the scenario unit can provide a short scenario. If the child is relaxed, the scenario unit can also provide a detailed scenario. If the child is excited, the scenario unit can also provide a concise scenario. This allows the scenario unit to provide a scenario length that corresponds to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0139] When generating a scenario, the scenario unit can determine the priority of the scenario based on the time of submission of the conversation. The scenario unit can provide a scenario with priority based on, for example, the content of the most recent conversation. The scenario unit can also provide a scenario later based on the content of the past conversation. The scenario unit can also provide a scenario with the highest priority based on the content of the conversation with the highest urgency. This allows the scenario unit to provide a priority of the scenario according to the time of submission of the conversation.

[0140] When generating a scenario, the scenario unit can adjust the order of scenarios based on the relevance of the conversations. For example, the scenario unit provides a scenario with priority based on highly relevant conversation content. The scenario unit can also provide a scenario later based on less relevant conversation content. The scenario unit can also provide a scenario by grouping related conversation content. This allows the scenario unit to provide an order of scenarios according to the relevance of the conversations.

[0141] The database unit can estimate the child's emotions and adjust the contents of the database based on the estimated child's emotions. For example, if the child is feeling stressed, the database unit can prioritize adding stress-related data to the database. Also, if the child is relaxed, the database unit can prioritize adding relaxation-related data to the database. Also, if the child is excited, the database unit can prioritize adding excitement-related data to the database. This allows the database unit to provide database contents according to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0142] When updating the database, the database unit can improve the accuracy of the database by referring to past data. For example, the database unit scrutinizes current data based on past data and adds it to the database. The database unit can also analyze past data to improve the accuracy of the database. The database unit can also update the contents of the database by referring to past data. In this way, the database unit can improve the accuracy of the database by utilizing past data.

[0143] When updating the database, the database unit can apply different database algorithms depending on the category of the conversation. For example, in the case of a conversation about school, the database unit applies a school-related database algorithm. In addition, in the case of a conversation about home, the database unit can also apply a home-related database algorithm. In addition, in the case of a conversation about friendship, the database unit can also apply a friendship-related database algorithm. In this way, the database unit can provide an optimal database according to the category of the conversation.

[0144] The database unit can estimate the child's emotion and adjust the update frequency of the database based on the estimated emotion of the child. For example, if the child is feeling stressed, the database unit updates the database frequently. Also, if the child is relaxed, the database unit can update the database periodically. Also, if the child is excited, the database unit can update the database appropriately. This allows the database unit to provide an update frequency of the database according to the child's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0145] When updating the database, the database unit can adjust the contents of the database based on the time of submission of the conversation. For example, the database unit can add recent conversation contents to the database with priority. The database unit can also add older conversation contents to the database later. The database unit can also add conversation contents with high urgency to the database with top priority. This allows the database unit to provide database contents according to the time of submission of the conversation.

[0146] The database unit can adjust the order of the database based on the relevance of the conversations when updating the database. For example, the database unit adds highly relevant conversation content to the database with priority. The database unit can also add less relevant conversation content to the database later. The database unit can also group related conversation content and add it to the database. In this way, the database unit can provide an order of the database according to the relevance of the conversations. === Hard Collateral 1-1 === Each of the multiple elements, including the reception unit, analysis unit, identification unit, and provision unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit receives a child's speech using the microphone 38B of the smart device 14 and analyzes it using voice recognition technology via the control unit 46A. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and performs voice analysis and emotion analysis. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies stress factors. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides advice to the child and / or parent. The estimation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes voice tone and speaking style to estimate emotions. The notification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and sends emails or app notifications. The scenario unit is realized, for example, by the control unit 46A of the smart device 14 and generates an appropriate response using natural language processing technology. The database unit is realized by, for example, the database 24 of the data processing device 12, and stores past conversation data, which is used to generate advice. === Hard Collateral 1-2 === Each of the multiple elements, including the reception unit, analysis unit, identification unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives speech from a child using the microphone 238 of the smart glasses 214 and analyzes the speech using voice recognition technology via the control unit 46A. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and performs voice analysis and emotion analysis. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies stress factors. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides advice to the child and / or parent. The estimation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes voice tone and speaking style to estimate emotions. The notification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and sends emails or app notifications. The scenario unit is realized, for example, by the control unit 46A of the smart glasses 214, and generates appropriate responses using natural language processing technology. The database unit is realized, for example, by the database 24 of the data processing device 12, and stores past conversation data and uses it to generate advice. === Hard Collateral 1-3 === Each of the multiple elements, including the above-described reception unit, analysis unit, identification unit, and provision unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit receives speech from a child using the microphone 238 of the headset-type terminal 314 and analyzes the speech using voice recognition technology via the control unit 46A. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and performs voice analysis and emotion analysis. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies stress factors. The provision unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and provides advice to the child and / or parent. The estimation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes voice tone and speaking style to estimate emotions. The notification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and sends emails or app notifications. The scenario unit is realized, for example, by the control unit 46A of the headset terminal 314, and generates appropriate responses using natural language processing technology. The database unit is realized, for example, by the database 24 of the data processing device 12, and stores past conversation data and uses it to generate advice. === Hard Collateral 1-4 === Each of the multiple elements, including the reception unit, analysis unit, identification unit, and provision unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives a child's speech using the microphone 238 of the robot 414 and analyzes it using voice recognition technology via the control unit 46A. The analysis unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and performs voice analysis and emotion analysis. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies stress factors. The provision unit is realized, for example, by the control unit 46A of the robot 414 and provides advice to the child and / or parent. The estimation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes voice tone and speaking style to estimate emotions. The notification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and sends emails or app notifications. The scenario unit is realized, for example, by the control unit 46A of the robot 414 and generates an appropriate response using natural language processing technology. The database unit is realized by, for example, the database 24 of the data processing device 12, and stores past conversation data, which is used to generate advice.

[0147] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0148] When accepting a child's message, the reception unit can adjust the content of the conversation taking into account the child's current physical condition information. For example, if the child has a cold, the AI ​​character will prioritize conversations that show concern for the child's health. Also, if the child is tired, the AI ​​character can offer topics that will help the child relax. Furthermore, if the child is in good health, the AI ​​character can offer lively topics. This allows the reception unit to provide appropriate conversations according to the child's physical condition.

[0149] The analysis unit can estimate the child's emotions and adjust the accuracy of the analysis based on the estimated child's emotions. For example, if the child is feeling very stressed, the analysis unit can perform a more detailed analysis to accurately identify the cause of the stress. If the child is relaxed, the analysis unit can perform a brief analysis to identify the cause of the relaxation. Furthermore, if the child is excited, the analysis unit can perform a quick analysis to identify the cause of the excitement. This allows the analysis unit to provide analysis accuracy according to the child's emotions.

[0150] When sending a notification to a parent, the providing unit can adjust the content of the notification taking into account the parent's current situation. For example, if the parent is at work, a brief notification can be sent. If the parent is at home, a detailed notification can be sent. Furthermore, if the parent is traveling, the notification can be delayed. This allows the providing unit to provide an appropriate notification according to the parent's situation.

[0151] When generating an appropriate response to a child's comments, the reception unit can adjust the content of the response taking into account the child's learning progress. For example, if a child asks a question related to the content they are studying, the AI ​​character will respond based on that content. Also, if a child talks about worries about their studies, the AI ​​character can provide study advice. Furthermore, if a child talks about a successful experience with their studies, the AI ​​character can respond by praising them. This allows the reception unit to provide appropriate responses according to the child's learning progress.

[0152] When generating advice based on past conversation data, the providing unit can adjust the content of the advice taking into account the child's developmental stage. For example, simple and easy-to-understand advice can be provided to a toddler. Specific and practical advice can also be provided to an elementary school child. Furthermore, more advanced advice can be provided to a junior high school child. This allows the providing unit to provide appropriate advice according to the child's developmental stage.

[0153] The reception unit can estimate the child's emotions and adjust the timing of starting the conversation based on the estimated child's emotions. For example, if the child is feeling stressed, the AI ​​character can speak to the child in a gentle voice and delay the timing of starting the conversation. Alternatively, if the child is relaxed, the AI ​​character can speak to the child in a cheerful voice and start the conversation immediately. Alternatively, if the child is excited, the AI ​​character can speak to the child in a calm voice and start the conversation slowly. This allows the reception unit to start the conversation at an appropriate time depending on the child's emotions.

[0154] The reception unit can analyze the child's past conversation history and select the optimal way to start a conversation. For example, if the child has previously preferred happy topics, the AI ​​character can start the conversation by talking about happy topics. Also, if the child has previously confided their worries, the reception unit can start the conversation by having the AI ​​character listen to their worries. Also, if the child has often spoken at a certain time of day in the past, the reception unit can start the conversation at that time of day. This allows the reception unit to select the optimal way to start a conversation by utilizing past conversation history.

[0155] When receiving a conversation, the reception unit can filter the conversation based on the child's current activity status and areas of interest. For example, if the child is studying, the reception unit can start a conversation by prioritizing topics related to studying. Also, if the child is playing, the reception unit can start a conversation by prioritizing topics related to playing. Also, if the child is interested in a particular anime or game, the reception unit can start a conversation by prioritizing that topic. In this way, the reception unit can provide a conversation that suits the child's current situation and interests.

[0156] When accepting a conversation, the reception unit can select a reception means according to the child's input method. For example, if the child speaks by voice, the reception unit can start the conversation by prioritizing the voice input. Also, if the child inputs by text, the reception unit can start the conversation by prioritizing the text input. Also, if the child sends an image, the reception unit can perform image analysis and start the conversation based on the content of the image. This allows the reception unit to provide the optimal reception means according to the child's input method.

[0157] The reception unit can estimate the child's emotions and determine the priority of conversations to be received based on the estimated child's emotions. For example, if the child is feeling stressed, conversations related to stress can be given priority in receiving conversations. Also, if the child is relaxed, conversations related to relaxation can be given priority in receiving conversations. Also, if the child is excited, conversations related to excitement can be given priority in receiving conversations. In this way, the reception unit can determine the priority of conversations according to the child's emotions.

[0158] The processing flow of the second embodiment will be briefly explained below.

[0159] Step 1: The reception unit accepts what the child is saying. The child's speech may include voice, text, gestures, etc. The reception unit accepts what the child is saying using voice recognition technology, and can also generate an appropriate response using natural language processing technology. For example, if a child asks, "What happened at school today?", the reception unit will respond with, "What happened today?" Step 2: The analysis unit analyzes the conversation content received by the reception unit. The analysis is performed using methods such as voice analysis, text analysis, and emotion analysis. For example, the analysis unit can use voice recognition technology to analyze the child's tone of voice and speaking style to estimate their emotion. Step 3: The identification unit identifies mental health conditions and stress factors based on the conversation content analyzed by the analysis unit. Identification is based on evaluation criteria such as stress level, happiness, and psychological stability. For example, if a child says, "I had a fight with my friend today," the identification unit analyzes the content and identifies that the cause of stress is a fight with a friend. Step 4: The provider provides advice to the child or their parents based on the results identified by the identifyr. The advice may include psychological support, behavioral guidance, or the provision of resources. For example, the provider might advise a child, "You had a fight with your friend. Why don't you apologize the next time you see each other?" The provider can also advise parents, "Your child had a fight with a friend and is feeling stressed. Please listen to him."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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).

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0178] 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.

[0179] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0180] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0181] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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).

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0194] 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.

[0195] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0196] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0197] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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).

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0211] 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.

[0212] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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).

[0217] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0218] 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."

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] [Explanation of symbols]

[0232] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception desk where children can talk to each other, an analysis unit that analyzes the conversation content received by the reception unit; an identification unit that identifies a mental health condition and a cause of stress based on the conversation content analyzed by the analysis unit; a providing unit that provides advice to the person or a parent based on the result identified by the identifying unit; Equipped with A system characterized by:

2. The analysis unit It has an estimation unit that uses voice recognition technology to analyze the child's tone of voice and speaking style to estimate their emotions.

2. The system of claim 1.

3. The providing unit Equipped with a notification section that sends notifications to parents 2. The system of claim 1.

4. The reception unit It has a scenario section that uses natural language processing technology to generate appropriate responses to children's comments.

2. The system of claim 1.

5. The providing unit Equipped with a database that generates advice based on past conversation data 2. The system of claim 1.

6. The reception unit Estimate the child's emotions and adjust the timing of conversation start based on the estimated emotions of the child.

2. The system of claim 1.

7. The reception unit Analyze your child's past conversation history and choose how to start a conversation 2. The system of claim 1.

8. The reception unit Filter incoming conversations based on your child's current activity and interests 2. The system of claim 1.

9. The reception unit When accepting a conversation, select the acceptance method according to the child's input method 2. The system of claim 1.

Images