system

Abstract

The system according to the embodiment aims to help children develop the ability to express their feelings and thoughts in words. According to an embodiment, the system includes a reception unit, an analysis unit, and a feedback unit. The reception unit receives a child's story. The analysis unit analyzes the story received by the reception unit. The feedback unit generates feedback based on the analysis result by the analysis 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 technologies do not provide sufficient opportunities for children to effectively develop the ability to express their feelings and thoughts in words, and there is room for improvement.

[0005] The system according to the embodiment aims to help children develop the ability to express their feelings and thoughts in words. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, and a feedback unit. The reception unit receives a child's story. The analysis unit analyzes the story received by the reception unit. The feedback unit generates feedback based on the analysis result by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can help children develop the ability to express their feelings and thoughts in words. [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 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) An emotional expression training system according to an embodiment of the present invention uses AI to provide a place for children to practice expressing emotions and stories in words. This system allows children to interact with AI, organize their emotions and thoughts, and develop their ability to express them. Specifically, the system consists of the following steps: First, a child talks to the AI ​​about their emotions and thoughts. Next, the AI ​​analyzes the content and returns appropriate feedback and questions. This allows children to gain a deeper understanding of their emotions and thoughts and practice expressing them in words. For example, if a child says, "I had a fight with my friends at school today and I'm sad," the AI ​​responds with questions such as, "Why did the fight happen?" and "How were you feeling at the time?" This allows children to organize their emotions and develop their ability to express them in words. The AI ​​can also generate stories based on what the child says. For example, if a child says, "I played at the park today," the AI ​​responds with questions such as, "What games did you play at the park?" and "Who did you play with?" and generates a story based on the child's answers. This allows children to practice expressing their experiences as stories. This system will enable children to develop the ability to express their feelings and thoughts in words, which is expected to improve their communication skills. As a result, the emotional expression practice system will enable children to develop the ability to express their feelings and thoughts in words.

[0029] An emotional expression training system according to an embodiment includes a reception unit, an analysis unit, and a feedback unit. The reception unit receives a child's story. The child's story may include, but is not limited to, everyday events, emotional expressions, and original stories. The reception unit may receive the child's story using, for example, voice input. The reception unit may also receive the child's story using text input. The reception unit may also receive the child's story using video input. For example, the reception unit may record the child's story using a microphone and save it as audio data. In the case of text input, the child may input the story using a keyboard. In the case of video input, the child's story may be recorded using a camera and saved as video data. The analysis unit analyzes the story received by the reception unit. The analysis may be performed using, for example, emotion analysis, content analysis, keyword extraction, or other methods, but is not limited to these examples. For example, the analysis unit may analyze the emotion of the child's story using an emotion analysis algorithm. The analysis unit may also analyze the content of the child's story using a content analysis algorithm. The analysis unit may also extract important keywords from the child's story using a keyword extraction algorithm. For example, the analysis unit uses an emotion analysis algorithm to identify emotions expressed in the child's story and evaluate the intensity of those emotions. The content analysis algorithm understands the content of the story and extracts important information. The keyword extraction algorithm identifies frequently occurring words and phrases in the story and performs analysis based on those. The feedback unit generates feedback based on the results of the analysis by the analysis unit. The feedback may be provided in the form of, for example, text, audio, or video, but is not limited to these examples. For example, the feedback unit provides appropriate advice or words of encouragement to the child based on the analysis results. The feedback unit may also return questions to the child based on the analysis results. The feedback unit may also generate stories for the child based on the analysis results. For example, the feedback unit may return questions to the child such as, "Why did you fight?" or "How were you feeling at the time?" based on the analysis results.As a result, the emotional expression training system according to the embodiment can help children develop the ability to express their own emotions and thoughts in words.

[0030] The feedback unit includes a generation unit that generates a story based on the child's speech. The generation unit generates the story based on the child's speech. Story generation is performed by, for example, constructing a plot, setting characters, selecting a theme, and the like, but is not limited to these examples. For example, the generation unit generates a story based on the construction of a plot. The generation unit can also generate a story based on character settings. The generation unit can also generate a story based on theme selection. For example, the generation unit constructs a plot based on what the child has said and generates a story based on the plot. The character settings involve setting characters in the story based on what the child has said. The theme selection involves selecting a theme for the story based on what the child has said. This allows the child to practice expressing their own experiences as a story. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the child's speech as a prompt to the generation AI, which then generates a story. This allows the generation unit to generate a story based on the child's speech, allowing the child to practice expressing their own experiences as a story.

[0031] The reception unit includes a recording unit that records the child's speech. The recording unit records the child's speech. The recording may be in the form of text, audio, video, or the like, but is not limited to these examples. For example, the recording unit records the child's speech as text data. The recording unit may also record the child's speech as audio data. The recording unit may also record the child's speech as video data. For example, the recording unit saves speech entered by the child using a keyboard as text data. In the case of audio data, the recording unit records the child's speech using a microphone and saves it as audio data. In the case of video data, the recording unit records the child's speech using a camera and saves it as video data. By recording the child's speech, it is possible to look back on it later and check the child's growth process. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input the child's speech into AI, which may convert it into text data, audio data, or video data and record it. By recording the child's speech, it is possible to look back on it later and check the child's growth process.

[0032] The feedback unit includes an advice unit that provides advice and words of encouragement to the child. The advice unit provides the advice and words of encouragement to the child. The advice and words of encouragement are provided in the form of, for example, positive feedback, suggestions for specific improvements, etc., but are not limited to these examples. For example, the advice unit provides positive feedback to the child. The advice unit can also suggest specific improvements to the child. The advice unit can also provide words of encouragement to the child. For example, the advice unit provides positive feedback such as "You did a good job" or "Try this next time" based on what the child has said. Suggesting specific improvements is specific advice such as "If you do this next time, you'll do better" based on what the child has said. The words of encouragement are encouraging words such as "It's okay, do your best" based on what the child has said. In this way, by providing appropriate advice and words of encouragement to the child, the child's ability to express himself can be improved. Some or all of the above-described processing by the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input what a child says into the AI, which can then generate and provide appropriate advice or words of encouragement. By providing appropriate advice and words of encouragement to the child, the advice unit can improve the child's ability to express themselves.

[0033] The reception unit can analyze the child's past conversation history and select a reception method. The reception unit, for example, can suggest topics that the child is comfortable talking about based on the content of the child's past conversations. The reception unit can also analyze the time periods in which the child talked in the past and set the optimal conversation reception time. The reception unit can also adjust the frequency of conversation reception based on the frequency with which the child talked in the past. For example, the reception unit stores the past conversation history in a database and analyzes the data. Based on the analysis results, it can suggest topics and time periods that the child is comfortable talking about. For example, if the child has talked a lot about "school events" in the past, the reception unit can prioritize suggesting that topic. Also, if the child has talked a lot in the evening in the past, the reception unit can prioritize that time period. In this way, by analyzing the past conversation history, it is possible to suggest topics and time periods that the child is comfortable talking about. The history analysis can be performed, for example, using AI or without AI. For example, the reception unit can input past conversation history data into AI, have the AI ​​perform analysis, and select a reception method based on the results. In this way, the reception unit can suggest topics and time periods that the child is comfortable talking about by analyzing the past conversation history.

[0034] When receiving a conversation, the reception unit can filter the conversation based on the child's current situation and areas of interest. For example, immediately after a child returns home from school, the reception unit can prioritize receiving conversations about events at school. If a child is interested in a particular anime, the reception unit can prioritize receiving conversations related to that anime. If a child plays a sport, the reception unit can prioritize receiving conversations about that sport. For example, the reception unit can grasp the child's current situation using sensors or GPS data and filter the conversations according to the situation. Areas of interest can be extracted from the child's past conversations or social media activity. For example, by preferentially receiving conversations about events at school immediately after a child returns home from school, it is possible to prioritize receiving conversations that are easy for the child to talk about. In this way, by filtering conversations based on the child's current situation and areas of interest, it is possible to prioritize receiving conversations that are easy for the child to talk about. Filtering may be performed using, for example, AI or without AI. For example, the reception unit can input data on the child's current situation and areas of interest data into AI, which can perform filtering and accept conversations based on the results. This allows the reception unit to filter conversations based on the child's current situation and areas of interest, allowing it to preferentially receive content that the child is comfortable talking about.

[0035] When receiving a message, the reception unit can prioritize receiving a message that is highly relevant by taking into account the child's geographical location information. For example, if the child is at a park, the reception unit can prioritize receiving a message about events that occurred in the park. Furthermore, if the child is at home, the reception unit can prioritize receiving a message about events that occurred at home. Furthermore, if the child is at school, the reception unit can prioritize receiving a message about events that occurred at school. For example, the reception unit acquires the child's geographical location information using GPS data and filters the message based on the information. For example, if the child is at a park, the reception unit can prioritize receiving a message about events that occurred in the park, thereby prioritizing receiving content that the child is comfortable talking about. In this way, by taking the child's geographical location information into account, it is possible to prioritize receiving content that the child is comfortable talking about. The acquisition of the geographical location information may be performed using, for example, AI or without AI. For example, the reception unit can input the child's geographical location information data into AI, have the AI ​​analyze the information, and accept a message based on the results. In this way, by taking the child's geographical location information into account, the reception unit can prioritize receiving content that the child is comfortable talking about.

[0036] When receiving a story, the reception unit can analyze the child's social media activity and receive related stories. For example, the reception unit can prioritize receiving related stories based on content shared by the child on social media. The reception unit can also prioritize receiving related stories based on accounts the child follows on social media. The reception unit can also prioritize receiving related stories based on posts the child has "liked" on social media. For example, the reception unit can analyze the child's social media activity and filter stories based on the activity. For example, by preferentially receiving stories related to posts the child has "liked" on social media, it is possible to prioritize receiving content that the child is comfortable talking about. In this way, by analyzing the child's social media activity, it is possible to prioritize receiving content that the child is comfortable talking about. The analysis of social media activity may be performed using, for example, AI or without AI. For example, the reception unit can input the child's social media activity data into AI, have the AI ​​analyze the data, and receive stories based on the results. In this way, by analyzing the child's social media activity, it is possible to prioritize receiving content that the child is comfortable talking about.

[0037] 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 on important topics. The analysis unit can also perform a simplified analysis on everyday topics. The analysis unit can also focus on topics that the child particularly wants to emphasize. For example, the analysis unit analyzes the content of the conversation and adjusts the level of detail of the analysis based on its importance. For important topics, a detailed analysis is performed to extract important information. For everyday topics, a simplified analysis is performed to extract the minimum necessary information. For topics that the child particularly wants to emphasize, a focused analysis is performed to extract detailed information. In this way, by adjusting the level of detail of the analysis based on the importance of the conversation, more detailed analysis can be performed on important topics. Adjustment of the level of detail of the analysis can be performed using, for example, AI or without AI. For example, the analysis unit can input content data of the conversation into AI, have the AI ​​evaluate the importance, and adjust the level of detail of the analysis based on the result. In this way, by adjusting the level of detail of the analysis based on the importance of the conversation, more detailed analysis can be performed on important topics.

[0038] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the story. For example, the analysis unit applies an emotion analysis algorithm to stories about emotions. The analysis unit can also apply a story analysis algorithm to stories about stories. The analysis unit can also apply an education-related analysis algorithm to stories about school events. For example, the analysis unit identifies a story category and applies an analysis algorithm according to the category. For stories about emotions, an emotion analysis algorithm is applied to analyze the intensity and type of emotions. For stories about stories, a story analysis algorithm is applied to analyze the structure and development of the story. For stories about school events, an education-related analysis algorithm is applied to analyze the content of the story from an educational perspective. In this way, by applying different analysis algorithms depending on the story category, more appropriate analysis results can be obtained. The application of analysis algorithms can be performed using, for example, AI or without AI. For example, the analysis unit can input story category data into AI, and the AI ​​can apply an analysis algorithm according to the category. In this way, by applying different analysis algorithms depending on the story category, more appropriate analysis results can be obtained.

[0039] During analysis, the analysis unit can adjust the order of analysis based on the time the story was submitted. For example, the analysis unit prioritizes analyzing the most recent story. The analysis unit can also sequentially analyze past stories. The analysis unit can also prioritize analyzing content that was discussed intensively during a specific period. For example, the analysis unit records the time the story was submitted in a database and adjusts the order of analysis based on that data. For the most recent story, analysis is prioritized to quickly provide the latest information. For past stories, analysis is performed sequentially to provide necessary information. For content that was discussed intensively during a specific period, stories from that period are analyzed together to provide highly relevant information. In this way, by adjusting the order of analysis based on the time the story was submitted, the most recent topic can be analyzed preferentially. Adjusting the order of analysis may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time the story was submitted into AI, have the AI ​​analyze the data, and adjust the order of analysis based on the results. In this way, by adjusting the order of analysis based on the time the story was submitted, the analysis unit can prioritize analyzing the most recent topic.

[0040] The analysis unit can adjust the order of analysis based on the relevance of the stories during analysis. For example, the analysis unit prioritizes analysis of highly relevant stories. The analysis unit can also postpone analysis of less relevant stories. The analysis unit can also analyze stories on the same topic together. For example, the analysis unit records the relevance of stories in a database and adjusts the order of analysis based on that data. Highly relevant stories are analyzed preferentially to quickly provide highly relevant information. Less relevant stories are analyzed later to provide necessary information. For stories on the same topic, stories related to that theme are analyzed together to provide highly relevant information. In this way, by adjusting the order of analysis based on the relevance of the stories, highly relevant topics can be analyzed preferentially. Adjustment of the order of analysis may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input story relevance data into AI, have the AI ​​analyze the data, and adjust the order of analysis based on the results. In this way, by adjusting the order of analysis based on the relevance of the stories, highly relevant topics can be analyzed preferentially.

[0041] When generating feedback, the feedback unit can adjust the level of detail of the feedback based on the importance of the conversation. For example, the feedback unit provides detailed feedback for important topics. The feedback unit can also provide brief feedback for everyday topics. The feedback unit can also provide focused feedback for topics that the child particularly wants to emphasize. For example, the feedback unit analyzes the content of the conversation and adjusts the level of detail of the feedback based on its importance. For important topics, detailed feedback is provided to convey important information. For everyday topics, brief feedback is provided to convey the minimum necessary information. For topics that the child particularly wants to emphasize, focused feedback is provided to convey detailed information. In this way, by adjusting the level of detail of the feedback based on the importance of the conversation, more detailed feedback can be provided for important topics. Adjustment of the level of detail of the feedback can be performed, for example, using AI or without using AI. For example, the feedback unit can input content data of the conversation into AI, have the AI ​​evaluate the importance of the conversation, and adjust the level of detail of the feedback based on the result. In this way, by adjusting the level of detail of the feedback based on the importance of the conversation, more detailed feedback can be provided for important topics.

[0042] The feedback unit can apply different feedback algorithms depending on the category of the story when generating feedback. For example, the feedback unit can apply an emotion feedback algorithm to stories about emotions. The feedback unit can also apply a story feedback algorithm to stories about stories. The feedback unit can also apply an education-related feedback algorithm to stories about school events. For example, the feedback unit identifies a category of the story and applies a feedback algorithm according to the category. For stories about emotions, an emotion feedback algorithm is applied to provide feedback according to the intensity and type of emotion. For stories about stories, a story feedback algorithm is applied to provide feedback according to the structure and development of the story. For stories about school events, an education-related feedback algorithm is applied to provide feedback on the content of the story from an educational perspective. In this way, by applying different feedback algorithms depending on the category of the story, more appropriate feedback can be provided. The application of the feedback algorithm can be performed using, for example, AI or without AI. For example, the feedback unit can input story category data into AI, and the AI ​​can apply a feedback algorithm according to the category. In this way, by applying different feedback algorithms depending on the category of the story, more appropriate feedback can be provided.

[0043] When generating feedback, the feedback unit can determine the priority of feedback based on the time when the story was submitted. For example, the feedback unit can provide feedback preferentially to the most recent story. The feedback unit can also provide feedback sequentially to past stories. The feedback unit can also provide feedback preferentially to content that was discussed intensively during a specific period. For example, the feedback unit records the time when the story was submitted in a database and determines the priority of feedback based on the data. For the most recent story, feedback is provided preferentially, and the latest information is quickly provided. For past stories, feedback is provided sequentially, and necessary information is provided. For content that was discussed intensively during a specific period, feedback is provided in a consolidated manner, and highly relevant information is provided. In this way, by determining the priority of feedback based on the time when the story was submitted, it is possible to provide feedback preferentially to the most recent topic. Determining the priority of feedback may be performed, for example, using AI or without AI. For example, the feedback unit can input data on the time when the story was submitted into AI, have the AI ​​analyze the data, and determine the priority of feedback based on the results. In this way, by determining the priority of feedback based on the time when the story was submitted, it is possible to provide feedback preferentially to the most recent topic.

[0044] The feedback unit can adjust the order of feedback based on the relevance of the stories when generating feedback. For example, the feedback unit provides feedback preferentially to highly relevant stories. The feedback unit can also provide feedback later to less relevant stories. The feedback unit can also provide feedback collectively to stories on the same topic. For example, the feedback unit records the relevance of the stories in a database and adjusts the order of feedback based on the data. For highly relevant stories, feedback is provided preferentially, and highly relevant information is quickly provided. For less relevant stories, feedback is provided later, and necessary information is provided. For stories on the same topic, feedback is collectively provided on stories related to the topic, and highly relevant information is provided. In this way, by adjusting the order of feedback based on the relevance of the stories, feedback can be provided preferentially to highly relevant topics. Adjustment of the order of feedback can be performed, for example, using AI or without using AI. For example, the feedback unit can input story relevance data into AI, have the AI ​​analyze the data, and adjust the order of feedback based on the results. In this way, by adjusting the order of feedback based on the relevance of the stories, feedback can be provided preferentially to highly relevant topics.

[0045] When generating a story, the generation unit can adjust the level of detail of the generated story based on the importance of the story. For example, the generation unit generates a detailed story for an important topic. The generation unit can also generate a simplified story for an everyday topic. The generation unit can also generate a story that focuses on a topic that the child particularly wants to emphasize. For example, the generation unit analyzes the content of the story and adjusts the level of detail of the generated story based on its importance. For an important topic, a detailed story is generated to convey important information. For an everyday topic, a simplified story is generated to convey the minimum necessary information. For a topic that the child particularly wants to emphasize, a story is generated that focuses on detailed information. In this way, by adjusting the level of detail of the generated story based on the importance of the story, a more detailed story can be generated for an important topic. The adjustment of the level of detail of the generated story can be performed, for example, using AI or without AI. For example, the generation unit can input content data of the story into AI, have the AI ​​evaluate the importance of the story, and adjust the level of detail of the generated story based on the result. In this way, by adjusting the level of detail of the generated story based on the importance of the story, a more detailed story can be generated for an important topic.

[0046] The generation unit can apply different generation algorithms depending on the category of the story when generating the story. For example, the generation unit applies an emotion story generation algorithm to a story about emotions. The generation unit can also apply a story generation algorithm to a story about stories. The generation unit can also apply an education-related generation algorithm to a story about school events. For example, the generation unit identifies a category of the story and applies a generation algorithm depending on the category. For a story about emotions, an emotion story generation algorithm is applied to generate a story depending on the intensity and type of emotion. For a story about stories, a story generation algorithm is applied to generate a story depending on the structure and development of the story. For a story about school events, an education-related generation algorithm is applied to generate a story based on the content of the story from an educational perspective. In this way, by applying different generation algorithms depending on the category of the story, more appropriate stories can be generated. The application of the generation algorithm can be performed using, for example, AI or without AI. For example, the generation unit can input story category data into AI, and the AI ​​can apply a generation algorithm depending on the category. In this way, the generation unit can generate more appropriate stories by applying different generation algorithms depending on the category of the story.

[0047] When generating stories, the generation unit can determine the generation priority based on the time the stories were submitted. For example, the generation unit can generate stories preferentially based on the most recent stories. The generation unit can also generate stories sequentially based on past stories. The generation unit can also generate stories preferentially based on content that was discussed intensively during a specific period. For example, the generation unit records the time the stories were submitted in a database and determines the generation priority based on that data. For the most recent stories, stories are generated preferentially to quickly provide the latest information. For past stories, stories are generated sequentially to provide necessary information. For content that was discussed intensively during a specific period, stories from that period are summarized to generate a story and provide highly relevant information. In this way, by determining the generation priority based on the time the stories were submitted, stories can be generated preferentially for the most recent topics. The generation priority can be determined using, for example, AI or without AI. For example, the generation unit can input story submission time data into AI, have the AI ​​analyze the data, and determine the generation priority based on the results. This allows the generation unit to determine the priority of generation based on the time of submission of the story, thereby allowing the generation unit to generate stories with priority given to the latest topics.

[0048] The generation unit can adjust the order of generation based on the relevance of stories when generating stories. For example, the generation unit prioritizes generating stories based on highly relevant stories. The generation unit can also postpone generating stories based on less relevant stories. The generation unit can also generate stories collectively based on stories related to the same theme. For example, the generation unit records the relevance of stories in a database and adjusts the order of generation based on that data. For highly relevant stories, the generation unit prioritizes generating stories and quickly provides highly relevant information. For less relevant stories, the generation unit postpones generating stories and provides necessary information. For stories related to the same theme, the generation unit collectively generates stories related to the theme and provides highly relevant information. In this way, by adjusting the order of generation based on the relevance of stories, it is possible to generate stories with priority for highly relevant topics. The adjustment of the order of generation may be performed, for example, using AI or without using AI. For example, the generation unit can input story relevance data into AI, have the AI ​​analyze the data, and adjust the order of generation based on the results. This allows the generation unit to generate stories with priority given to highly related topics by adjusting the order of generation based on the relevance of the stories.

[0049] The recording unit can adjust the level of detail of the recording based on the importance of the conversation during recording. For example, the recording unit performs detailed recording for important topics. The recording unit can also perform brief recording for everyday topics. The recording unit can also perform focused recording for topics that the child particularly wants to emphasize. For example, the recording unit analyzes the content of the conversation and adjusts the level of detail of the recording based on its importance. For important topics, detailed recording is performed and important information is saved. For everyday topics, brief recording is performed and the minimum necessary information is saved. For topics that the child particularly wants to emphasize, focused recording is performed and detailed information is saved. In this way, by adjusting the level of detail of the recording based on the importance of the conversation, more detailed recording can be performed for important topics. The adjustment of the level of detail of the recording can be performed using, for example, AI or without AI. For example, the recording unit can input content data of the conversation into AI, have the AI ​​evaluate the importance, and adjust the level of detail of the recording based on the result. In this way, by adjusting the level of detail of the recording based on the importance of the conversation, more detailed recording can be performed for important topics.

[0050] The recording unit can adjust the order of recording based on the time of submission of the story during recording. For example, the recording unit prioritizes recording the most recent story. The recording unit can also sequentially record past stories. The recording unit can also prioritize recording content that was discussed intensively during a specific period. For example, the recording unit records the time of submission of the story in a database and adjusts the order of recording based on that data. For the most recent story, recording is prioritized and the latest information is quickly saved. For past stories, recording is sequential and necessary information is saved. For content that was discussed intensively during a specific period, stories from that period are recorded together and highly relevant information is saved. In this way, by adjusting the order of recording based on the time of submission of the story, the most recent topic can be prioritized and recorded. The adjustment of the order of recording may be performed, for example, using AI or without AI. For example, the recording unit can input data on the time of submission of the story into AI, have the AI ​​analyze the data, and adjust the order of recording based on the results. In this way, the recording unit can prioritize recording the most recent topic by adjusting the order of recording based on the time of submission of the story.

[0051] When providing advice, the advice unit can adjust the level of detail of the advice based on the importance of the conversation. For example, the advice unit provides detailed advice for important topics. The advice unit can also provide brief advice for everyday topics. The advice unit can also provide focused advice for topics that the child particularly wants to emphasize. For example, the advice unit analyzes the content of the conversation and adjusts the level of detail of the advice based on its importance. For important topics, detailed advice is provided and important information is conveyed. For everyday topics, brief advice is provided and the minimum necessary information is conveyed. For topics that the child particularly wants to emphasize, focused advice is provided and detailed information is conveyed. In this way, by adjusting the level of detail of the advice based on the importance of the conversation, more detailed advice can be provided for important topics. Adjustment of the level of detail of the advice can be performed, for example, using AI or without AI. For example, the advice unit can input content data of the conversation into AI, have the AI ​​evaluate the importance of the conversation, and adjust the level of detail of the advice based on the result. In this way, the advice unit can provide more detailed advice for important topics by adjusting the level of detail of the advice based on the importance of the conversation.

[0052] When providing advice, the advice unit can adjust the order of advice based on the time the story was submitted. For example, the advice unit can prioritize providing advice for the most recent story. The advice unit can also provide advice for older stories in order. The advice unit can also prioritize providing advice for content that was discussed intensively during a specific period. For example, the advice unit records the time the story was submitted in a database and adjusts the order of advice based on the data. For the most recent story, advice is provided preferentially and the latest information is quickly provided. For older stories, advice is provided sequentially and necessary information is provided. For content that was discussed intensively during a specific period, advice is provided by summarizing the stories from that period and providing highly relevant information. In this way, by adjusting the order of advice based on the time the story was submitted, it is possible to prioritize advice on the most recent topic. Adjusting the order of advice may be performed, for example, using AI or without AI. For example, the advice unit can input data on the time the story was submitted into AI, have the AI ​​analyze the data, and adjust the order of advice based on the results. In this way, the advice unit can prioritize advice on the most recent topic by adjusting the order of advice based on the time the story was submitted.

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

[0054] When receiving a child's story, the reception unit can add interactive elements to attract the child's interest and attention. For example, the reception unit can provide a simple quiz or game to attract the child's attention before the child starts speaking. The reception unit can also use background music or sound effects to create an environment in which the child feels comfortable speaking. Furthermore, the reception unit can display animations or visual effects according to what the child is saying. This allows the child to speak in a fun environment, making self-expression practice more effective.

[0055] The generator can generate an interactive storybook based on what the child says. For example, the generator can generate a storybook that includes animations of characters moving based on what the child says. The generator can also add interactive elements that provide choices and allow the child to choose how the story unfolds, depending on what the child says. The generator can also add audio narration based on what the child says. This allows the child to visually see how their story unfolds as a story, making practicing self-expression more enjoyable.

[0056] When recording a child's story, the recording unit can automatically tag the story based on the content of the story. For example, the recording unit can automatically assign tags such as "school," "friends," and "family" based on what the child said. The recording unit can also tag the emotional tone of the story (e.g., "happy," "sad," "excited," etc.) based on what the child said. Furthermore, the recording unit can assign tags according to the length and level of detail of the story based on what the child said. This makes it easy to search for stories related to a specific topic or emotion when reviewing the stories later.

[0057] The advice section can provide specific action plans based on what a child has said. For example, if a child talks about a fight they had with a friend, the advice section can provide specific advice on how to talk to their friend the next time they talk. If a child talks about a school assignment, the advice section can provide a step-by-step guide on how to efficiently complete the assignment. Furthermore, if a child talks about a new hobby or interest, the advice section can provide specific resources and reference materials for starting that hobby. This allows children to improve their self-expression skills through concrete actions.

[0058] The reception unit can analyze the child's past story history and provide personalized questions when receiving a story. For example, if a child has talked a lot about "school events" in the past, the reception unit will prioritize questions such as "What happened at school today?". Also, if a child has talked about "spending time with family" in the past, the reception unit can provide questions such as "What did you do with your family recently?". Furthermore, if a child talks about a particular hobby, the reception unit can provide questions related to that hobby. This makes it easier for children to talk based on their own interests and allows them to practice self-expression more effectively.

[0059] When receiving a message, the reception unit can filter the message based on the child's current situation and areas of interest. For example, immediately after a child returns home from school, the reception unit can prioritize receiving messages about events at school. If a child is interested in a particular anime, the reception unit can prioritize receiving messages related to that anime. If a child is playing sports, the reception unit can prioritize receiving messages about that sport. For example, the reception unit can grasp the child's current situation using sensors or GPS data and filter the message based on that situation. Areas of interest can be extracted from past conversations by the child, social media activity, and the like. By filtering messages based on the child's current situation and areas of interest, it is possible to prioritize receiving messages that the child is comfortable talking about.

[0060] When receiving a conversation, the reception unit can prioritize receiving a conversation that is highly relevant by taking into account the child's geographical location information. For example, if the child is at a park, the reception unit can prioritize receiving a conversation about events that occurred in the park. Furthermore, if the child is at home, the reception unit can prioritize receiving a conversation about events that occurred at home. Furthermore, if the child is at school, the reception unit can prioritize receiving a conversation about events that occurred at school. For example, the reception unit acquires the child's geographical location information using GPS data and filters the conversation based on that information. For example, if the child is at a park, by preferentially receiving a conversation about events that occurred in the park, it is possible to preferentially receive content that the child is comfortable talking about. In this way, it is possible to preferentially receive content that the child is comfortable talking about by taking the child's geographical location information into account.

[0061] When receiving a story, the reception unit can analyze the child's social media activity and receive related stories. For example, the reception unit can prioritize receiving related stories based on content shared by the child on social media. The reception unit can also prioritize receiving related stories based on accounts the child follows on social media. The reception unit can also prioritize receiving related stories based on posts the child has "liked" on social media. For example, the reception unit analyzes the child's social media activity and filters stories based on the activity. For example, by preferentially receiving stories related to posts the child has "liked" on social media, it is possible to preferentially receive content that the child is comfortable talking about. In this way, by analyzing the child's social media activity, it is possible to preferentially receive content that the child is comfortable talking about.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The reception unit receives the child's story. The child's story may include everyday events, expressions of emotions, and original stories. The reception unit can receive the child's story using voice input, text input, or video input. For example, the child's story is recorded using a microphone and saved as voice data. In the case of text input, the child can input the story using a keyboard. In the case of video input, the child's story is recorded using a camera and saved as video data. Step 2: The analysis unit analyzes the story received by the reception unit. Analysis is performed using methods such as sentiment analysis, content analysis, and keyword extraction. For example, a sentiment analysis algorithm is used to analyze the emotions in a child's story and evaluate the intensity of those emotions. A content analysis algorithm understands the content of the story and extracts important information. A keyword extraction algorithm identifies frequently occurring words and phrases in the story and performs analysis based on them. Step 3: The feedback unit generates feedback based on the results of the analysis by the analysis unit. The feedback is provided in the form of text, audio, video, etc. For example, the feedback unit may provide the child with appropriate advice or words of encouragement based on the analysis results. It may also be able to return questions to the child based on the analysis results. It may also be able to generate stories for the child based on the analysis results.

[0064] (Example 2) An emotional expression training system according to an embodiment of the present invention uses AI to provide a place for children to practice expressing emotions and stories in words. This system allows children to interact with AI, organize their emotions and thoughts, and develop their ability to express them. Specifically, the system consists of the following steps: First, a child talks to the AI ​​about their emotions and thoughts. Next, the AI ​​analyzes the content and returns appropriate feedback and questions. This allows children to gain a deeper understanding of their emotions and thoughts and practice expressing them in words. For example, if a child says, "I had a fight with my friends at school today and I'm sad," the AI ​​responds with questions such as, "Why did the fight happen?" and "How were you feeling at the time?" This allows children to organize their emotions and develop their ability to express them in words. The AI ​​can also generate stories based on what the child says. For example, if a child says, "I played at the park today," the AI ​​responds with questions such as, "What games did you play at the park?" and "Who did you play with?" and generates a story based on the child's answers. This allows children to practice expressing their experiences as stories. This system will enable children to develop the ability to express their feelings and thoughts in words, which is expected to improve their communication skills. As a result, the emotional expression practice system will enable children to develop the ability to express their feelings and thoughts in words.

[0065] An emotional expression training system according to an embodiment includes a reception unit, an analysis unit, and a feedback unit. The reception unit receives a child's story. The child's story may include, but is not limited to, everyday events, emotional expressions, and original stories. The reception unit may receive the child's story using, for example, voice input. The reception unit may also receive the child's story using text input. The reception unit may also receive the child's story using video input. For example, the reception unit may record the child's story using a microphone and save it as audio data. In the case of text input, the child may input the story using a keyboard. In the case of video input, the child's story may be recorded using a camera and saved as video data. The analysis unit analyzes the story received by the reception unit. The analysis may be performed using, for example, emotion analysis, content analysis, keyword extraction, or other methods, but is not limited to these examples. For example, the analysis unit may analyze the emotion of the child's story using an emotion analysis algorithm. The analysis unit may also analyze the content of the child's story using a content analysis algorithm. The analysis unit may also extract important keywords from the child's story using a keyword extraction algorithm. For example, the analysis unit uses an emotion analysis algorithm to identify emotions expressed in the child's story and evaluate the intensity of those emotions. The content analysis algorithm understands the content of the story and extracts important information. The keyword extraction algorithm identifies frequently occurring words and phrases in the story and performs analysis based on those. The feedback unit generates feedback based on the results of the analysis by the analysis unit. The feedback may be provided in the form of, for example, text, audio, or video, but is not limited to these examples. For example, the feedback unit provides appropriate advice or words of encouragement to the child based on the analysis results. The feedback unit may also return questions to the child based on the analysis results. The feedback unit may also generate stories for the child based on the analysis results. For example, the feedback unit may return questions to the child such as, "Why did you fight?" or "How were you feeling at the time?" based on the analysis results.As a result, the emotional expression training system according to the embodiment can help children develop the ability to express their own emotions and thoughts in words.

[0066] The feedback unit includes a generation unit that generates a story based on the child's speech. The generation unit generates the story based on the child's speech. Story generation is performed by, for example, constructing a plot, setting characters, selecting a theme, and the like, but is not limited to these examples. For example, the generation unit generates a story based on the construction of a plot. The generation unit can also generate a story based on character settings. The generation unit can also generate a story based on theme selection. For example, the generation unit constructs a plot based on what the child has said and generates a story based on the plot. The character settings involve setting characters in the story based on what the child has said. The theme selection involves selecting a theme for the story based on what the child has said. This allows the child to practice expressing their own experiences as a story. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the child's speech as a prompt to the generation AI, which then generates a story. This allows the generation unit to generate a story based on the child's speech, allowing the child to practice expressing their own experiences as a story.

[0067] The reception unit includes a recording unit that records the child's speech. The recording unit records the child's speech. The recording may be in the form of text, audio, video, or the like, but is not limited to these examples. For example, the recording unit records the child's speech as text data. The recording unit may also record the child's speech as audio data. The recording unit may also record the child's speech as video data. For example, the recording unit saves speech entered by the child using a keyboard as text data. In the case of audio data, the recording unit records the child's speech using a microphone and saves it as audio data. In the case of video data, the recording unit records the child's speech using a camera and saves it as video data. By recording the child's speech, it is possible to look back on it later and check the child's growth process. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input the child's speech into AI, which may convert it into text data, audio data, or video data and record it. By recording the child's speech, it is possible to look back on it later and check the child's growth process.

[0068] The feedback unit includes an advice unit that provides advice and words of encouragement to the child. The advice unit provides the advice and words of encouragement to the child. The advice and words of encouragement are provided in the form of, for example, positive feedback, suggestions for specific improvements, etc., but are not limited to these examples. For example, the advice unit provides positive feedback to the child. The advice unit can also suggest specific improvements to the child. The advice unit can also provide words of encouragement to the child. For example, the advice unit provides positive feedback such as "You did a good job" or "Try this next time" based on what the child has said. Suggesting specific improvements is specific advice such as "If you do this next time, you'll do better" based on what the child has said. The words of encouragement are encouraging words such as "It's okay, do your best" based on what the child has said. In this way, by providing appropriate advice and words of encouragement to the child, the child's ability to express himself can be improved. Some or all of the above-described processing by the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input what a child says into the AI, which can then generate and provide appropriate advice or words of encouragement. By providing appropriate advice and words of encouragement to the child, the advice unit can improve the child's ability to express themselves.

[0069] The reception unit can estimate the child's emotions and adjust the timing of speech reception based on the estimated emotions. For example, if the child is excited, the reception unit can delay speech reception for a while, waiting for the child to calm down. Furthermore, if the child is sad, the reception unit can immediately receive speech, allowing the child to express their emotions quickly. Furthermore, if the child is tired, the reception unit can quickly receive speech, allowing the child to speak comfortably. For example, the reception unit captures the child's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on changes in facial expression and adjusts the timing of speech reception based on the result. Emotions can also be estimated by analyzing the tone and speed of the child's voice using voice analysis technology. For example, if the child's voice tone is high, it is determined that the child is excited, and the timing of speech reception is delayed. Conversely, if the voice tone is low, it is determined that the child is sad, and the timing of speech reception is immediately adjusted. This allows the timing of speech reception to be adjusted according to the child's emotions, providing an environment in which children can speak more easily. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input a child's facial expression data into the generation AI, which then estimates the child's emotion, and adjust the timing of speech reception based on the result. In this way, the reception unit can provide an environment in which the child is more comfortable speaking by adjusting the timing of speech reception according to the child's emotion.

[0070] The reception unit can analyze the child's past conversation history and select a reception method. The reception unit, for example, can suggest topics that the child is comfortable talking about based on the content of the child's past conversations. The reception unit can also analyze the time periods in which the child talked in the past and set the optimal conversation reception time. The reception unit can also adjust the frequency of conversation reception based on the frequency with which the child talked in the past. For example, the reception unit stores the past conversation history in a database and analyzes the data. Based on the analysis results, it can suggest topics and time periods that the child is comfortable talking about. For example, if the child has talked a lot about "school events" in the past, the reception unit can prioritize suggesting that topic. Also, if the child has talked a lot in the evening in the past, the reception unit can prioritize that time period. In this way, by analyzing the past conversation history, it is possible to suggest topics and time periods that the child is comfortable talking about. The history analysis can be performed, for example, using AI or without AI. For example, the reception unit can input past conversation history data into AI, have the AI ​​perform analysis, and select a reception method based on the results. In this way, the reception unit can suggest topics and time periods that the child is comfortable talking about by analyzing the past conversation history.

[0071] When receiving a conversation, the reception unit can filter the conversation based on the child's current situation and areas of interest. For example, immediately after a child returns home from school, the reception unit can prioritize receiving conversations about events at school. If a child is interested in a particular anime, the reception unit can prioritize receiving conversations related to that anime. If a child plays a sport, the reception unit can prioritize receiving conversations about that sport. For example, the reception unit can grasp the child's current situation using sensors or GPS data and filter the conversations according to the situation. Areas of interest can be extracted from the child's past conversations or social media activity. For example, by preferentially receiving conversations about events at school immediately after a child returns home from school, it is possible to prioritize receiving conversations that are easy for the child to talk about. In this way, by filtering conversations based on the child's current situation and areas of interest, it is possible to prioritize receiving conversations that are easy for the child to talk about. Filtering may be performed using, for example, AI or without AI. For example, the reception unit can input data on the child's current situation and areas of interest data into AI, which can perform filtering and accept conversations based on the results. This allows the reception unit to filter conversations based on the child's current situation and areas of interest, allowing it to preferentially receive content that the child is comfortable talking about.

[0072] The reception unit can estimate the child's emotions and prioritize the conversations to be received based on the estimated emotions. For example, if the child is angry, the reception unit can prioritize conversations related to that emotion. Also, if the child is happy, the reception unit can prioritize conversations related to that emotion. Also, if the child is anxious, the reception unit can prioritize conversations related to that emotion. For example, the reception unit captures the child's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on changes in facial expression and prioritizes conversations based on the results. Emotions can also be estimated by analyzing the tone and speed of the child's voice using voice analysis technology. For example, if the child's voice tone is high, it is determined that the child is angry, and conversations related to that emotion are prioritized. Conversely, if the voice tone is low, it is determined that the child is sad, and conversations related to that emotion are prioritized. By prioritizing conversations based on the child's emotions, it is possible to prioritize conversations that the child finds easy to talk about. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input a child's facial expression data into the generation AI, which may estimate the child's emotions, and determine the priority of the conversation based on the result. In this way, the reception unit can prioritize conversations that are easy for the child to talk about by determining the priority of the conversation based on the child's emotions, and can preferentially accept conversations that are easy for the child to talk about.

[0073] When receiving a message, the reception unit can prioritize receiving a message that is highly relevant by taking into account the child's geographical location information. For example, if the child is at a park, the reception unit can prioritize receiving a message about events that occurred in the park. Furthermore, if the child is at home, the reception unit can prioritize receiving a message about events that occurred at home. Furthermore, if the child is at school, the reception unit can prioritize receiving a message about events that occurred at school. For example, the reception unit acquires the child's geographical location information using GPS data and filters the message based on the information. For example, if the child is at a park, the reception unit can prioritize receiving a message about events that occurred in the park, thereby prioritizing receiving content that the child is comfortable talking about. In this way, by taking the child's geographical location information into account, it is possible to prioritize receiving content that the child is comfortable talking about. The acquisition of the geographical location information may be performed using, for example, AI or without AI. For example, the reception unit can input the child's geographical location information data into AI, have the AI ​​analyze the information, and accept a message based on the results. In this way, by taking the child's geographical location information into account, the reception unit can prioritize receiving content that the child is comfortable talking about.

[0074] When receiving a story, the reception unit can analyze the child's social media activity and receive related stories. For example, the reception unit can prioritize receiving related stories based on content shared by the child on social media. The reception unit can also prioritize receiving related stories based on accounts the child follows on social media. The reception unit can also prioritize receiving related stories based on posts the child has "liked" on social media. For example, the reception unit can analyze the child's social media activity and filter stories based on the activity. For example, by preferentially receiving stories related to posts the child has "liked" on social media, it is possible to prioritize receiving content that the child is comfortable talking about. In this way, by analyzing the child's social media activity, it is possible to prioritize receiving content that the child is comfortable talking about. The analysis of social media activity may be performed using, for example, AI or without AI. For example, the reception unit can input the child's social media activity data into AI, have the AI ​​analyze the data, and receive stories based on the results. In this way, by analyzing the child's social media activity, it is possible to prioritize receiving content that the child is comfortable talking about.

[0075] The analysis unit can estimate the child's emotions and adjust the analysis method based on the estimated emotions. For example, if the child is sad, the analysis unit selects an analysis method that soothes the child's emotions. Furthermore, if the child is excited, the analysis unit can select an analysis method that helps organize the child's emotions. Furthermore, if the child is anxious, the analysis unit can select an analysis method that provides a sense of security. For example, the analysis unit captures the child's facial expression with a camera and estimates the child's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates the child's emotions based on changes in facial expressions and adjusts the analysis method based on the results. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate emotions. For example, if the child's voice tone is high, it is determined that the child is excited, and an analysis method that helps organize the child's emotions is selected. Conversely, if the voice tone is low, it is determined that the child is sad, and an analysis method that helps soothe the child's emotions is selected. By adjusting the analysis method according to the child's emotions, more appropriate analysis results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input a child's facial expression data into the generation AI, which may infer the child's emotions and adjust the analysis method based on the result. In this way, the analysis unit can obtain more appropriate analysis results by adjusting the analysis method according to the child's emotions.

[0076] 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 on important topics. The analysis unit can also perform a simplified analysis on everyday topics. The analysis unit can also focus on topics that the child particularly wants to emphasize. For example, the analysis unit analyzes the content of the conversation and adjusts the level of detail of the analysis based on its importance. For important topics, a detailed analysis is performed to extract important information. For everyday topics, a simplified analysis is performed to extract the minimum necessary information. For topics that the child particularly wants to emphasize, a focused analysis is performed to extract detailed information. In this way, by adjusting the level of detail of the analysis based on the importance of the conversation, more detailed analysis can be performed on important topics. Adjustment of the level of detail of the analysis can be performed using, for example, AI or without AI. For example, the analysis unit can input content data of the conversation into AI, have the AI ​​evaluate the importance, and adjust the level of detail of the analysis based on the result. In this way, by adjusting the level of detail of the analysis based on the importance of the conversation, more detailed analysis can be performed on important topics.

[0077] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the story. For example, the analysis unit applies an emotion analysis algorithm to stories about emotions. The analysis unit can also apply a story analysis algorithm to stories about stories. The analysis unit can also apply an education-related analysis algorithm to stories about school events. For example, the analysis unit identifies a story category and applies an analysis algorithm according to the category. For stories about emotions, an emotion analysis algorithm is applied to analyze the intensity and type of emotions. For stories about stories, a story analysis algorithm is applied to analyze the structure and development of the story. For stories about school events, an education-related analysis algorithm is applied to analyze the content of the story from an educational perspective. In this way, by applying different analysis algorithms depending on the story category, more appropriate analysis results can be obtained. The application of analysis algorithms can be performed using, for example, AI or without AI. For example, the analysis unit can input story category data into AI, and the AI ​​can apply an analysis algorithm according to the category. In this way, by applying different analysis algorithms depending on the story category, more appropriate analysis results can be obtained.

[0078] The analysis unit can estimate the child's emotions and determine analysis priorities based on the estimated emotions. For example, the analysis unit prioritizes analysis of speech in which the child expresses strong emotions. The analysis unit can also prioritize analysis of content that the child repeatedly speaks. The analysis unit can also prioritize analysis of content that the child has recently spoken. For example, the analysis unit captures the child's facial expressions with a camera and estimates the child's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates emotions based on changes in facial expressions and determines analysis priorities based on the results. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate emotions. For example, if the child's voice tone is high, it is determined that the child is expressing strong emotions, and that speech is prioritized for analysis. Conversely, if the voice tone is low, it is determined that the child is sad, and that speech is prioritized for analysis. This allows important topics to be prioritized for analysis by determining analysis priorities based on 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, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input data on a child's facial expression into a generation AI, which may infer the child's emotions, and determine the analysis priority based on the result. This allows the analysis unit to prioritize important topics by determining the analysis priority according to the child's emotions.

[0079] During analysis, the analysis unit can adjust the order of analysis based on the time the story was submitted. For example, the analysis unit prioritizes analyzing the most recent story. The analysis unit can also sequentially analyze past stories. The analysis unit can also prioritize analyzing content that was discussed intensively during a specific period. For example, the analysis unit records the time the story was submitted in a database and adjusts the order of analysis based on that data. For the most recent story, analysis is prioritized to quickly provide the latest information. For past stories, analysis is performed sequentially to provide necessary information. For content that was discussed intensively during a specific period, stories from that period are analyzed together to provide highly relevant information. In this way, by adjusting the order of analysis based on the time the story was submitted, the most recent topic can be analyzed preferentially. Adjusting the order of analysis may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time the story was submitted into AI, have the AI ​​analyze the data, and adjust the order of analysis based on the results. In this way, by adjusting the order of analysis based on the time the story was submitted, the analysis unit can prioritize analyzing the most recent topic.

[0080] The analysis unit can adjust the order of analysis based on the relevance of the stories during analysis. For example, the analysis unit prioritizes analysis of highly relevant stories. The analysis unit can also postpone analysis of less relevant stories. The analysis unit can also analyze stories on the same topic together. For example, the analysis unit records the relevance of stories in a database and adjusts the order of analysis based on that data. Highly relevant stories are analyzed preferentially to quickly provide highly relevant information. Less relevant stories are analyzed later to provide necessary information. For stories on the same topic, stories related to that theme are analyzed together to provide highly relevant information. In this way, by adjusting the order of analysis based on the relevance of the stories, highly relevant topics can be analyzed preferentially. Adjustment of the order of analysis may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input story relevance data into AI, have the AI ​​analyze the data, and adjust the order of analysis based on the results. In this way, by adjusting the order of analysis based on the relevance of the stories, highly relevant topics can be analyzed preferentially.

[0081] The feedback unit can estimate the child's emotions and adjust the way the feedback is expressed based on the estimated emotions. For example, if the child is sad, the feedback unit can provide gentle feedback. If the child is excited, the feedback unit can also provide calm feedback. If the child is anxious, the feedback unit can also provide reassuring feedback. For example, the feedback unit captures the child's facial expression with a camera and estimates the child's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on changes in facial expression and adjusts the way the feedback is expressed based on the results. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate the emotion. For example, if the child's voice tone is high, the system determines that the child is excited and provides calm feedback. Conversely, if the voice tone is low, the system determines that the child is sad and provides gentle feedback. This allows the system to provide more appropriate feedback by adjusting the way the feedback is expressed based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI. For example, the feedback unit may input facial expression data of a child into the generation AI, which may estimate the child's emotions and adjust the feedback expression method based on the result. This allows the feedback unit to provide more appropriate feedback by adjusting the feedback expression method according to the child's emotions.

[0082] When generating feedback, the feedback unit can adjust the level of detail of the feedback based on the importance of the conversation. For example, the feedback unit provides detailed feedback for important topics. The feedback unit can also provide brief feedback for everyday topics. The feedback unit can also provide focused feedback for topics that the child particularly wants to emphasize. For example, the feedback unit analyzes the content of the conversation and adjusts the level of detail of the feedback based on its importance. For important topics, detailed feedback is provided to convey important information. For everyday topics, brief feedback is provided to convey the minimum necessary information. For topics that the child particularly wants to emphasize, focused feedback is provided to convey detailed information. In this way, by adjusting the level of detail of the feedback based on the importance of the conversation, more detailed feedback can be provided for important topics. Adjustment of the level of detail of the feedback can be performed, for example, using AI or without using AI. For example, the feedback unit can input content data of the conversation into AI, have the AI ​​evaluate the importance of the conversation, and adjust the level of detail of the feedback based on the result. In this way, by adjusting the level of detail of the feedback based on the importance of the conversation, more detailed feedback can be provided for important topics.

[0083] The feedback unit can apply different feedback algorithms depending on the category of the story when generating feedback. For example, the feedback unit can apply an emotion feedback algorithm to stories about emotions. The feedback unit can also apply a story feedback algorithm to stories about stories. The feedback unit can also apply an education-related feedback algorithm to stories about school events. For example, the feedback unit identifies a category of the story and applies a feedback algorithm according to the category. For stories about emotions, an emotion feedback algorithm is applied to provide feedback according to the intensity and type of emotion. For stories about stories, a story feedback algorithm is applied to provide feedback according to the structure and development of the story. For stories about school events, an education-related feedback algorithm is applied to provide feedback on the content of the story from an educational perspective. In this way, by applying different feedback algorithms depending on the category of the story, more appropriate feedback can be provided. The application of the feedback algorithm can be performed using, for example, AI or without AI. For example, the feedback unit can input story category data into AI, and the AI ​​can apply a feedback algorithm according to the category. In this way, by applying different feedback algorithms depending on the category of the story, more appropriate feedback can be provided.

[0084] The feedback unit can estimate the child's emotion and adjust the length of the feedback based on the estimated emotion. For example, if the child is sad, the feedback unit can provide short, gentle feedback. If the child is excited, the feedback unit can provide calm, detailed feedback. If the child is anxious, the feedback unit can provide longer, reassuring feedback. For example, the feedback unit captures the child's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on changes in facial expression and adjusts the length of the feedback based on the result. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate the emotion. For example, if the child's voice tone is high, it is determined that the child is excited, and calm, detailed feedback is provided. Conversely, if the voice tone is low, it is determined that the child is sad, and short, gentle feedback is provided. By adjusting the length of the feedback according to the child's emotion, more appropriate feedback can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using 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. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input facial expression data of the child into a generation AI, which may estimate the child's emotion, and adjust the length of the feedback based on the estimation result. This allows the feedback unit to provide more appropriate feedback by adjusting the length of the feedback according to the child's emotion.

[0085] When generating feedback, the feedback unit can determine the priority of feedback based on the time when the story was submitted. For example, the feedback unit can provide feedback preferentially to the most recent story. The feedback unit can also provide feedback sequentially to past stories. The feedback unit can also provide feedback preferentially to content that was discussed intensively during a specific period. For example, the feedback unit records the time when the story was submitted in a database and determines the priority of feedback based on the data. For the most recent story, feedback is provided preferentially, and the latest information is quickly provided. For past stories, feedback is provided sequentially, and necessary information is provided. For content that was discussed intensively during a specific period, feedback is provided in a consolidated manner, and highly relevant information is provided. In this way, by determining the priority of feedback based on the time when the story was submitted, it is possible to provide feedback preferentially to the most recent topic. Determining the priority of feedback may be performed, for example, using AI or without AI. For example, the feedback unit can input data on the time when the story was submitted into AI, have the AI ​​analyze the data, and determine the priority of feedback based on the results. In this way, by determining the priority of feedback based on the time when the story was submitted, it is possible to provide feedback preferentially to the most recent topic.

[0086] The feedback unit can adjust the order of feedback based on the relevance of the stories when generating feedback. For example, the feedback unit provides feedback preferentially to highly relevant stories. The feedback unit can also provide feedback later to less relevant stories. The feedback unit can also provide feedback collectively to stories on the same topic. For example, the feedback unit records the relevance of the stories in a database and adjusts the order of feedback based on the data. For highly relevant stories, feedback is provided preferentially, and highly relevant information is quickly provided. For less relevant stories, feedback is provided later, and necessary information is provided. For stories on the same topic, feedback is collectively provided on stories related to the topic, and highly relevant information is provided. In this way, by adjusting the order of feedback based on the relevance of the stories, feedback can be provided preferentially to highly relevant topics. Adjustment of the order of feedback can be performed, for example, using AI or without using AI. For example, the feedback unit can input story relevance data into AI, have the AI ​​analyze the data, and adjust the order of feedback based on the results. In this way, by adjusting the order of feedback based on the relevance of the stories, feedback can be provided preferentially to highly relevant topics.

[0087] The generation unit can estimate the child's emotions and adjust the content of the generated story based on the estimated emotions. For example, if a child is sad, the generation unit generates a story that soothes the child's emotions. Furthermore, if a child is excited, the generation unit can generate a story to help the child organize their emotions. Furthermore, if a child is anxious, the generation unit can generate a story that provides a sense of security. For example, the generation unit captures the child's facial expression with a camera and estimates the child's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates the child's emotions based on changes in facial expressions and adjusts the content of the story based on the results. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate emotions. For example, if a child's voice has a high tone, it is determined that the child is excited, and a story to help the child organize their emotions is generated. Conversely, if the voice has a low tone, it is determined that the child is sad, and a story to help the child organize their emotions is generated. This allows the generation of a more appropriate story by adjusting the content of the story according to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input a child's facial expression data into the generation AI, which may infer the child's emotions and adjust the content of the story based on the results. This allows the generation unit to generate a more appropriate story by adjusting the content of the story according to the child's emotions.

[0088] When generating a story, the generation unit can adjust the level of detail of the generated story based on the importance of the story. For example, the generation unit generates a detailed story for an important topic. The generation unit can also generate a simplified story for an everyday topic. The generation unit can also generate a story that focuses on a topic that the child particularly wants to emphasize. For example, the generation unit analyzes the content of the story and adjusts the level of detail of the generated story based on its importance. For an important topic, a detailed story is generated to convey important information. For an everyday topic, a simplified story is generated to convey the minimum necessary information. For a topic that the child particularly wants to emphasize, a story is generated that focuses on detailed information. In this way, by adjusting the level of detail of the generated story based on the importance of the story, a more detailed story can be generated for an important topic. The adjustment of the level of detail of the generated story can be performed, for example, using AI or without AI. For example, the generation unit can input content data of the story into AI, have the AI ​​evaluate the importance of the story, and adjust the level of detail of the generated story based on the result. In this way, by adjusting the level of detail of the generated story based on the importance of the story, a more detailed story can be generated for an important topic.

[0089] The generation unit can apply different generation algorithms depending on the category of the story when generating the story. For example, the generation unit applies an emotion story generation algorithm to a story about emotions. The generation unit can also apply a story generation algorithm to a story about stories. The generation unit can also apply an education-related generation algorithm to a story about school events. For example, the generation unit identifies a category of the story and applies a generation algorithm depending on the category. For a story about emotions, an emotion story generation algorithm is applied to generate a story depending on the intensity and type of emotion. For a story about stories, a story generation algorithm is applied to generate a story depending on the structure and development of the story. For a story about school events, an education-related generation algorithm is applied to generate a story based on the content of the story from an educational perspective. In this way, by applying different generation algorithms depending on the category of the story, more appropriate stories can be generated. The application of the generation algorithm can be performed using, for example, AI or without AI. For example, the generation unit can input story category data into AI, and the AI ​​can apply a generation algorithm depending on the category. In this way, the generation unit can generate more appropriate stories by applying different generation algorithms depending on the category of the story.

[0090] The generation unit can estimate the child's emotions and adjust the length of the story to be generated based on the estimated emotions. For example, if the child is sad, the generation unit can generate a short, soothing story. If the child is excited, the generation unit can generate a longer story to calm the child down. If the child is anxious, the generation unit can generate a longer story to reassure the child. For example, the generation unit can capture the child's facial expression with a camera and estimate the child's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates the child's emotions based on changes in facial expressions and adjusts the length of the story based on the results. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate emotions. For example, if the child's voice tone is high, it can be determined that the child is excited, and a longer story to calm the child down can be generated. Conversely, if the voice tone is low, it can be determined that the child is sad, and a short, soothing story can be generated. This allows the length of the story to be adjusted according to the child's emotions, thereby generating a more appropriate story. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input a child's facial expression data into the generation AI, which may estimate the child's emotions and adjust the length of the story based on the results. This allows the generation unit to generate a more appropriate story by adjusting the length of the story according to the child's emotions.

[0091] When generating stories, the generation unit can determine the generation priority based on the time the stories were submitted. For example, the generation unit can generate stories preferentially based on the most recent stories. The generation unit can also generate stories sequentially based on past stories. The generation unit can also generate stories preferentially based on content that was discussed intensively during a specific period. For example, the generation unit records the time the stories were submitted in a database and determines the generation priority based on that data. For the most recent stories, stories are generated preferentially to quickly provide the latest information. For past stories, stories are generated sequentially to provide necessary information. For content that was discussed intensively during a specific period, stories from that period are summarized to generate a story and provide highly relevant information. In this way, by determining the generation priority based on the time the stories were submitted, stories can be generated preferentially for the most recent topics. The generation priority can be determined using, for example, AI or without AI. For example, the generation unit can input story submission time data into AI, have the AI ​​analyze the data, and determine the generation priority based on the results. This allows the generation unit to determine the priority of generation based on the time of submission of the story, thereby allowing the generation unit to generate stories with priority given to the latest topics.

[0092] The generation unit can adjust the order of generation based on the relevance of stories when generating stories. For example, the generation unit prioritizes generating stories based on highly relevant stories. The generation unit can also postpone generating stories based on less relevant stories. The generation unit can also generate stories collectively based on stories related to the same theme. For example, the generation unit records the relevance of stories in a database and adjusts the order of generation based on that data. For highly relevant stories, the generation unit prioritizes generating stories and quickly provides highly relevant information. For less relevant stories, the generation unit postpones generating stories and provides necessary information. For stories related to the same theme, the generation unit collectively generates stories related to the theme and provides highly relevant information. In this way, by adjusting the order of generation based on the relevance of stories, it is possible to generate stories with priority for highly relevant topics. The adjustment of the order of generation may be performed, for example, using AI or without using AI. For example, the generation unit can input story relevance data into AI, have the AI ​​analyze the data, and adjust the order of generation based on the results. This allows the generation unit to generate stories with priority given to highly related topics by adjusting the order of generation based on the relevance of the stories.

[0093] The recording unit can estimate the child's emotions and adjust the recording method based on the estimated emotions. For example, if the child is sad, the recording unit selects a recording method that soothes the child's emotions. Furthermore, if the child is excited, the recording unit can select a recording method that helps the child organize their emotions. Furthermore, if the child is anxious, the recording unit can select a recording method that gives the child a sense of security. For example, the recording unit captures the child's facial expressions with a camera and estimates the child's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates the child's emotions based on changes in facial expressions and adjusts the recording method based on the results. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate emotions. For example, if the child's voice tone is high, it is determined that the child is excited, and a recording method that helps the child organize their emotions is selected. Conversely, if the voice tone is low, it is determined that the child is sad, and a recording method that helps the child organize their emotions is selected. This allows for more appropriate recording by adjusting the recording method according to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input facial expression data of a child into the generation AI, which may infer the child's emotions and adjust the recording method based on the result. This allows the recording unit to adjust the recording method according to the child's emotions, thereby enabling more appropriate recording.

[0094] The recording unit can adjust the level of detail of the recording based on the importance of the conversation during recording. For example, the recording unit performs detailed recording for important topics. The recording unit can also perform brief recording for everyday topics. The recording unit can also perform focused recording for topics that the child particularly wants to emphasize. For example, the recording unit analyzes the content of the conversation and adjusts the level of detail of the recording based on its importance. For important topics, detailed recording is performed and important information is saved. For everyday topics, brief recording is performed and the minimum necessary information is saved. For topics that the child particularly wants to emphasize, focused recording is performed and detailed information is saved. In this way, by adjusting the level of detail of the recording based on the importance of the conversation, more detailed recording can be performed for important topics. The adjustment of the level of detail of the recording can be performed using, for example, AI or without AI. For example, the recording unit can input content data of the conversation into AI, have the AI ​​evaluate the importance, and adjust the level of detail of the recording based on the result. In this way, by adjusting the level of detail of the recording based on the importance of the conversation, more detailed recording can be performed for important topics.

[0095] The recording unit can estimate the child's emotions and determine recording priorities based on the estimated emotions. For example, the recording unit prioritizes recording conversations in which the child expresses strong emotions. The recording unit can also prioritize recording content that the child repeatedly speaks. The recording unit can also prioritize recording content that the child newly speaks. For example, the recording unit captures the child's facial expressions with a camera and estimates the child's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates emotions based on changes in facial expressions and determines recording priorities based on the results. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate emotions. For example, if the child's voice tone is high, it is determined that the child is expressing strong emotions, and that conversation is prioritized for recording. Conversely, if the voice tone is low, it is determined that the child is sad, and that conversation is prioritized for recording. This allows important topics to be prioritized for recording by determining recording priorities based on 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, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input data of a child's facial expression into a generating AI, which may then estimate the child's emotions and determine the recording priority based on the estimation result. This allows the recording unit to prioritize recording important topics by determining the recording priority according to the child's emotions.

[0096] The recording unit can adjust the order of recording based on the time of submission of the story during recording. For example, the recording unit prioritizes recording the most recent story. The recording unit can also sequentially record past stories. The recording unit can also prioritize recording content that was discussed intensively during a specific period. For example, the recording unit records the time of submission of the story in a database and adjusts the order of recording based on that data. For the most recent story, recording is prioritized and the latest information is quickly saved. For past stories, recording is sequential and necessary information is saved. For content that was discussed intensively during a specific period, stories from that period are recorded together and highly relevant information is saved. In this way, by adjusting the order of recording based on the time of submission of the story, the most recent topic can be prioritized and recorded. The adjustment of the order of recording may be performed, for example, using AI or without AI. For example, the recording unit can input data on the time of submission of the story into AI, have the AI ​​analyze the data, and adjust the order of recording based on the results. In this way, the recording unit can prioritize recording the most recent topic by adjusting the order of recording based on the time of submission of the story.

[0097] The advice unit can estimate the child's emotions and adjust the way the advice is expressed based on the estimated emotions. For example, if the child is sad, the advice unit can provide gentle advice. If the child is excited, the advice unit can provide calm advice. If the child is anxious, the advice unit can provide reassuring advice. For example, the advice unit captures the child's facial expression with a camera and estimates the child's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates the child's emotions based on changes in facial expressions and adjusts the way the advice is expressed based on the results. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate emotions. For example, if the child's voice tone is high, the system determines that the child is excited and provides calm advice. Conversely, if the voice tone is low, the system determines that the child is sad and provides gentle advice. This allows the system to provide more appropriate advice by adjusting the way the advice is expressed based on the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit may input a child's facial expression data into the generation AI, which may estimate the child's emotions, and adjust the way the advice is expressed based on the results. This allows the advice unit to provide more appropriate advice by adjusting the way the advice is expressed according to the child's emotions.

[0098] When providing advice, the advice unit can adjust the level of detail of the advice based on the importance of the conversation. For example, the advice unit provides detailed advice for important topics. The advice unit can also provide brief advice for everyday topics. The advice unit can also provide focused advice for topics that the child particularly wants to emphasize. For example, the advice unit analyzes the content of the conversation and adjusts the level of detail of the advice based on its importance. For important topics, detailed advice is provided and important information is conveyed. For everyday topics, brief advice is provided and the minimum necessary information is conveyed. For topics that the child particularly wants to emphasize, focused advice is provided and detailed information is conveyed. In this way, by adjusting the level of detail of the advice based on the importance of the conversation, more detailed advice can be provided for important topics. Adjustment of the level of detail of the advice can be performed, for example, using AI or without AI. For example, the advice unit can input content data of the conversation into AI, have the AI ​​evaluate the importance of the conversation, and adjust the level of detail of the advice based on the result. In this way, the advice unit can provide more detailed advice for important topics by adjusting the level of detail of the advice based on the importance of the conversation.

[0099] The advice unit can estimate the child's emotions and prioritize advice based on the estimated emotions. For example, the advice unit can prioritize providing advice for topics that the child expresses strong emotions about. The advice unit can also prioritize providing advice for topics that the child repeatedly talks about. The advice unit can also prioritize providing advice for topics that the child has recently started talking about. For example, the advice unit can capture the child's facial expressions with a camera and estimate the child's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on changes in facial expressions and prioritizes advice based on the results. Voice analysis technology can also be used to analyze the tone and speed of the child's voice to estimate emotions. For example, if the child's voice tone is high, it can be determined that the child is expressing strong emotions, and advice can be prioritized for that topic. Conversely, if the voice tone is low, it can be determined that the child is sad, and advice can be prioritized for that topic. In this way, by prioritizing advice based on the child's emotions, advice can be prioritized for important topics. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit may input a child's facial expression data into the generation AI, which may estimate the child's emotions, and determine the priority of advice based on the result. In this way, the advice unit can prioritize advice on important topics by determining the priority of advice according to the child's emotions.

[0100] When providing advice, the advice unit can adjust the order of advice based on the time the story was submitted. For example, the advice unit can prioritize providing advice for the most recent story. The advice unit can also provide advice for older stories in order. The advice unit can also prioritize providing advice for content that was discussed intensively during a specific period. For example, the advice unit records the time the story was submitted in a database and adjusts the order of advice based on the data. For the most recent story, advice is provided preferentially and the latest information is quickly provided. For older stories, advice is provided sequentially and necessary information is provided. For content that was discussed intensively during a specific period, advice is provided by summarizing the stories from that period and providing highly relevant information. In this way, by adjusting the order of advice based on the time the story was submitted, it is possible to prioritize advice on the most recent topic. Adjusting the order of advice may be performed, for example, using AI or without AI. For example, the advice unit can input data on the time the story was submitted into AI, have the AI ​​analyze the data, and adjust the order of advice based on the results. In this way, the advice unit can prioritize advice on the most recent topic by adjusting the order of advice based on the time the story was submitted. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, feedback unit, generation unit, recording unit, and advice unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit can receive the child's story using the microphone 38B or the camera 42 of the smart device 14. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the child's story. The feedback unit is realized by the specific processing unit 290 of the data processing device 12 and generates feedback based on the analysis results. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a story based on the child's story. The recording unit records the child's story in the storage 50 of the smart device 14. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides the child with appropriate advice or words of encouragement. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, feedback unit, generation unit, recording unit, and advice unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit can receive the child's speech using the microphone 238 or the camera 42 of the smart glasses 214. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the child's speech. The feedback unit is realized by the specific processing unit 290 of the data processing device 12 and generates feedback based on the analysis results. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a story based on the child's speech. The recording unit records the child's speech in the storage 50 of the smart glasses 214. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides the child with appropriate advice or words of encouragement. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, feedback unit, generation unit, recording unit, and advice 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 can receive the child's speech using the microphone 238 or the camera 42 of the headset-type terminal 314. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the child's speech. The feedback unit is realized by the specific processing unit 290 of the data processing device 12 and generates feedback based on the analysis results. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a story based on the child's speech. The recording unit records the child's speech in the storage 50 of the headset-type terminal 314. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides the child with appropriate advice or words of encouragement. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, feedback unit, generation unit, recording unit, and advice unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit can receive the child's story using the microphone 238 or the camera 42 of the robot 414. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the child's story. The feedback unit is realized by the specific processing unit 290 of the data processing device 12 and generates feedback based on the analysis results. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a story based on the child's story. The recording unit records the child's story in the storage 50 of the robot 414. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides the child with appropriate advice or words of encouragement.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] When receiving a child's story, the reception unit can add interactive elements to attract the child's interest and attention. For example, the reception unit can provide a simple quiz or game to attract the child's attention before the child starts speaking. The reception unit can also use background music or sound effects to create an environment in which the child feels comfortable speaking. Furthermore, the reception unit can display animations or visual effects according to what the child is saying. This allows the child to speak in a fun environment, making self-expression practice more effective.

[0103] The generator can generate an interactive storybook based on what the child says. For example, the generator can generate a storybook that includes animations of characters moving based on what the child says. The generator can also add interactive elements that provide choices and allow the child to choose how the story unfolds, depending on what the child says. The generator can also add audio narration based on what the child says. This allows the child to visually see how their story unfolds as a story, making practicing self-expression more enjoyable.

[0104] When recording a child's story, the recording unit can automatically tag the story based on the content of the story. For example, the recording unit can automatically assign tags such as "school," "friends," and "family" based on what the child said. The recording unit can also tag the emotional tone of the story (e.g., "happy," "sad," "excited," etc.) based on what the child said. Furthermore, the recording unit can assign tags according to the length and level of detail of the story based on what the child said. This makes it easy to search for stories related to a specific topic or emotion when reviewing the stories later.

[0105] The advice section can provide specific action plans based on what a child has said. For example, if a child talks about a fight they had with a friend, the advice section can provide specific advice on how to talk to their friend the next time they talk. If a child talks about a school assignment, the advice section can provide a step-by-step guide on how to efficiently complete the assignment. Furthermore, if a child talks about a new hobby or interest, the advice section can provide specific resources and reference materials for starting that hobby. This allows children to improve their self-expression skills through concrete actions.

[0106] The reception unit can estimate the child's emotions and customize the way it receives their conversation based on the estimated emotions. For example, if a child is nervous, the reception unit can play relaxing music to provide an environment that makes it easier for them to talk. If a child is excited, the reception unit can adjust the pace of the conversation to help the child speak calmly. Furthermore, if a child is sad, the reception unit can speak to the child in kind words to help the child feel at ease. This makes it possible to respond appropriately to a child's emotions, making self-expression practice more effective.

[0107] The reception unit can analyze the child's past story history and provide personalized questions when receiving a story. For example, if a child has talked a lot about "school events" in the past, the reception unit will prioritize questions such as "What happened at school today?". Also, if a child has talked about "spending time with family" in the past, the reception unit can provide questions such as "What did you do with your family recently?". Furthermore, if a child talks about a particular hobby, the reception unit can provide questions related to that hobby. This makes it easier for children to talk based on their own interests and allows them to practice self-expression more effectively.

[0108] When receiving a message, the reception unit can filter the message based on the child's current situation and areas of interest. For example, immediately after a child returns home from school, the reception unit can prioritize receiving messages about events at school. If a child is interested in a particular anime, the reception unit can prioritize receiving messages related to that anime. If a child is playing sports, the reception unit can prioritize receiving messages about that sport. For example, the reception unit can grasp the child's current situation using sensors or GPS data and filter the message based on that situation. Areas of interest can be extracted from past conversations by the child, social media activity, and the like. By filtering messages based on the child's current situation and areas of interest, it is possible to prioritize receiving messages that the child is comfortable talking about.

[0109] The reception unit can estimate the child's emotions and determine the priority of the conversations to be received based on the estimated emotions. For example, if the child is angry, the reception unit can prioritize conversations related to that emotion. Also, if the child is happy, the reception unit can prioritize conversations related to that emotion. Also, if the child is feeling anxious, the reception unit can prioritize conversations related to that emotion. For example, the reception unit captures the child's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on changes in facial expression and determines the priority of the conversations based on the result. Voice analysis technology can also be used to analyze the tone and speed of the child's voice and estimate the emotion. In this way, by determining the priority of conversations based on the child's emotions, it is possible to prioritize conversations that are easy for the child to talk about.

[0110] When receiving a conversation, the reception unit can prioritize receiving a conversation that is highly relevant by taking into account the child's geographical location information. For example, if the child is at a park, the reception unit can prioritize receiving a conversation about events that occurred in the park. Furthermore, if the child is at home, the reception unit can prioritize receiving a conversation about events that occurred at home. Furthermore, if the child is at school, the reception unit can prioritize receiving a conversation about events that occurred at school. For example, the reception unit acquires the child's geographical location information using GPS data and filters the conversation based on that information. For example, if the child is at a park, by preferentially receiving a conversation about events that occurred in the park, it is possible to preferentially receive content that the child is comfortable talking about. In this way, it is possible to preferentially receive content that the child is comfortable talking about by taking the child's geographical location information into account.

[0111] When receiving a story, the reception unit can analyze the child's social media activity and receive related stories. For example, the reception unit can prioritize receiving related stories based on content shared by the child on social media. The reception unit can also prioritize receiving related stories based on accounts the child follows on social media. The reception unit can also prioritize receiving related stories based on posts the child has "liked" on social media. For example, the reception unit analyzes the child's social media activity and filters stories based on the activity. For example, by preferentially receiving stories related to posts the child has "liked" on social media, it is possible to preferentially receive content that the child is comfortable talking about. In this way, by analyzing the child's social media activity, it is possible to preferentially receive content that the child is comfortable talking about.

[0112] The processing flow of the second embodiment will be briefly explained below.

[0113] Step 1: The reception unit receives the child's story. The child's story may include everyday events, expressions of emotions, and original stories. The reception unit can receive the child's story using voice input, text input, or video input. For example, the child's story is recorded using a microphone and saved as voice data. In the case of text input, the child can input the story using a keyboard. In the case of video input, the child's story is recorded using a camera and saved as video data. Step 2: The analysis unit analyzes the story received by the reception unit. Analysis is performed using methods such as sentiment analysis, content analysis, and keyword extraction. For example, a sentiment analysis algorithm is used to analyze the emotions in a child's story and evaluate the intensity of those emotions. A content analysis algorithm understands the content of the story and extracts important information. A keyword extraction algorithm identifies frequently occurring words and phrases in the story and performs analysis based on them. Step 3: The feedback unit generates feedback based on the results of the analysis by the analysis unit. The feedback is provided in the form of text, audio, video, etc. For example, the feedback unit may provide the child with appropriate advice or words of encouragement based on the analysis results. It may also be able to return questions to the child based on the analysis results. It may also be able to generate stories for the child based on the analysis results.

[0114] 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.

[0115] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0116] 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.

[0117] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0132] 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.

[0133] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0134] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0148] 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.

[0149] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0150] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0151] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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, in order to avoid confusion and to 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.

[0184] 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.

[0185] [Explanation of symbols]

[0186] 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 that listens to children's stories, an analysis unit that analyzes the story received by the reception unit; a feedback unit that generates feedback based on the results of the analysis by the analysis unit; Equipped with A system characterized by:

2. The feedback unit It has a generator that generates stories based on children's stories.

2. The system of claim 1.

3. The reception unit Equipped with a recording section to record children's stories 2. The system of claim 1.

4. The feedback unit Have an advice department that offers advice and words of encouragement to children 2. The system of claim 1.

5. The reception unit Estimates the child's emotions and adjusts the timing of conversations based on the estimated emotions 2. The system of claim 1.

6. The reception unit Analyze the child's past history and select the reception method 2. The system of claim 1.

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

8. The reception unit Estimate the child's emotions and prioritize the conversations to be accepted based on the estimated emotions 2. The system of claim 1.

Images