system

Abstract

The system according to this embodiment aims to leverage children's natural curiosity and promote their active participation. [Solution] The system according to the embodiment comprises an analysis unit, a prompt creation unit, and a motivation unit. The analysis unit analyzes the child's browsing history and interests. The prompt creation unit creates personalized prompts based on the analysis results obtained by the analysis unit. The motivation unit encourages the child's behavior based on the prompts created by the prompt creation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is mainstream to restrict children's use of the Internet and SNS, and there is room for improvement in ways to make use of children's natural curiosity.

[0005] The system according to the embodiment aims to make use of children's natural curiosity and promote active participation.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a prompt creation unit, and a motivation unit. The analysis unit analyzes the child's browsing history and interests. The prompt creation unit creates personalized prompts based on the analysis results obtained by the analysis unit. The motivation unit encourages the child's behavior based on the prompts created by the prompt creation unit. [Effects of the Invention]

[0007] The system according to this embodiment can leverage children's natural curiosity and encourage their active participation. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The system according to the embodiment of the present invention aims not to restrict children's use of the internet and social media, but rather to leverage their natural curiosity and subtly guide them to interest-based activities that require active participation. This promotes children to develop spontaneous thinking, explore and develop their passions through hands-on activities. Specifically, it utilizes generative AI to analyze a child's browsing history, interests, and behavior, and creates personalized prompts that resonate with that child. For example, if a child frequently visits websites about soccer, the system might estimate how much and in what way they would improve if they spent that time playing soccer instead of browsing, and calculate their chances of becoming a professional soccer player, thereby encouraging them to play soccer instead. Furthermore, it can use videos of the child playing to show how different types of practice improve their skills, how that changes their play, and how it can lead to success in matches, thereby motivating children. In this way, the system can leverage children's natural curiosity and promote active participation.

[0029] The system according to this embodiment comprises an analysis unit, a prompt creation unit, and a motivation unit. The analysis unit analyzes the child's browsing history and interests. For example, the analysis unit collects the history of websites visited by the child and analyzes the child's interest trends. The analysis unit can also evaluate the depth of the child's interest based on the history of videos the child has watched. Furthermore, the analysis unit can analyze the keywords the child has searched for and track the changes in their interests. For example, the analysis unit analyzes the website browsing history in chronological order and visualizes changes in interests. The prompt creation unit creates personalized prompts based on the analysis results obtained by the analysis unit. For example, the prompt creation unit generates prompts that suggest specific activities based on the child's interests. The prompt creation unit can also provide prompts at the optimal timing based on the child's behavioral history. Furthermore, the prompt creation unit can adjust the level of detail of the prompts according to the depth of the child's interest. For example, if the prompt creation unit has a strong interest in a particular topic, it will create a prompt that includes detailed information. The motivation unit encourages the children's behavior based on the prompts created by the prompt creation unit. The motivation unit can, for example, use videos of children playing to show how different types of practice lead to improvement. It can also use generative AI to provide specific advice to encourage children's behavior. Furthermore, the motivation unit can estimate a child's emotions and adjust its motivational approach based on those emotions. For instance, if a child is excited, it will provide energetic and positive motivation. This allows the system to leverage children's natural curiosity and encourage active participation.

[0030] The analytics department analyzes children's browsing history and interests. Specifically, it collects the history of websites visited by children and analyzes their interest trends. For example, if a child frequently visits educational websites or views a lot of information on a particular theme, it can be determined that they have a high level of interest in that theme. The analytics department can also evaluate the depth of interest based on the history of videos children watch. By analyzing viewing time, number of views, and genres of videos watched, it can be assessed how interested the child is in a particular theme. Furthermore, the analytics department can analyze the keywords children search for and track changes in their interests. For example, if a particular keyword is frequently searched, it can be determined that a new interest related to that keyword has emerged. The analytics department analyzes this data over time to visualize changes in interests. This allows for a detailed understanding of children's interest trends and changes, which can be used to create prompts for the next steps. In addition, the analytics department can use AI to analyze the data and perform more advanced pattern recognition and prediction. For example, machine learning algorithms can be used to predict changes in children's interests and estimate what themes they are likely to be interested in in the future. This allows the analytics department to gain a deeper understanding of children's interests and contribute to creating personalized prompts.

[0031] The prompt generation unit creates personalized prompts based on the analysis results obtained by the analysis unit. Specifically, it generates prompts that suggest specific activities based on the child's interests. For example, if a child is interested in science, it will create prompts that suggest ideas for science experiments or watching related videos. The prompt generation unit can also provide prompts at the optimal time based on the child's behavioral history. For example, if a child is active during a particular time of day, providing prompts at that time can more effectively capture their interest. Furthermore, the prompt generation unit can adjust the level of detail of prompts according to the depth of the child's interest. For example, if a child has a strong interest in a particular topic, it will create prompts with detailed information, while providing concise prompts if their interest is shallow. The prompt generation unit can also automatically generate prompts using generative AI. The generative AI takes the child's interests and behavioral history as input and generates optimal prompts. For example, it uses natural language processing technology to generate sentences and questions related to the child's interests and provide prompts that capture the child's interest. This allows the prompt generation unit to efficiently create personalized prompts tailored to the child's interests and support their learning and activities.

[0032] The motivation unit promotes children's behavior based on prompts created by the prompt generation unit. Specifically, it uses videos of children playing to show how to improve through practice. For example, it advises children who have watched sports practice videos on specific practice methods and tips for improvement based on the content of the videos. The motivation unit can also use generative AI to provide specific advice to promote children's behavior. The generative AI analyzes children's interests and behavioral history to generate optimal advice. For example, if a child is interested in a particular theme, it suggests new information and activities related to that theme. The motivation unit can also estimate children's emotions and adjust its motivational methods based on those emotions. For example, if a child is excited, it provides energetic and positive motivation; conversely, if a child is depressed, it offers words of encouragement and comfort. The motivation unit uses emotion recognition technology to analyze children's facial expressions and tone of voice to estimate their emotions. This allows the motivation unit to provide appropriate motivation according to the child's emotions. Furthermore, the motivation unit can collect children's feedback and continuously evaluate and improve the effectiveness of the motivation. For example, the team can analyze which advice elicited the best response from children and use that information to improve future motivation. This allows the motivation department to leverage children's natural curiosity and encourage active participation.

[0033] The analysis unit can analyze a child's browsing history and interests using generative AI. For example, the analysis unit can use generative AI to analyze a child's website visit history and identify trends in their interests. It can also use generative AI to analyze a child's video viewing history and evaluate the depth of their interest. Furthermore, the analysis unit can use generative AI to analyze keywords a child has searched for and track changes in their interests. For example, the analysis unit can input website browsing history into the generative AI and visualize changes in interests. This allows for accurate analysis of a child's interests using generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using generative AI or not. For example, the analysis unit can input a child's browsing history into the generative AI and have the generative AI perform an analysis to identify trends in their interests.

[0034] The prompt generation unit can create personalized prompts using generative AI. For example, the prompt generation unit can use generative AI to generate prompts that suggest specific activities based on the child's interests. The prompt generation unit can also use generative AI to provide prompts at the optimal timing based on the child's behavioral history. Furthermore, the prompt generation unit can use generative AI to adjust the level of detail of the prompts according to the depth of the child's interest. For example, the prompt generation unit can input the child's interest data into the generative AI and generate personalized prompts. This allows the system to provide the child with the most appropriate prompts by using generative AI. The generative AI is, for example, 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 processes in the prompt generation unit may be performed using generative AI or not. For example, the prompt generation unit can input the child's interest data into the generative AI and have the generative AI generate personalized prompts.

[0035] The motivation unit can use videos of children playing to show them what kind of practice will help them improve. For example, the motivation unit can analyze a video of a child playing soccer and show them what kind of practice they should do. It can also analyze a video of a child playing the piano and show them what kind of practice they should do. Furthermore, it can analyze a video of a child drawing and show them what kind of practice they should do. For example, the motivation unit can analyze a video of a child playing soccer and suggest practice methods to improve a specific skill. This can increase the child's motivation by showing them specific practice methods. Some or all of the above processing in the motivation unit may be performed using generative AI or not. For example, the motivation unit can input a video of a child playing into a generative AI and have the generative AI suggest practice methods.

[0036] The motivation unit can use generative AI to provide specific advice to encourage children's behavior. For example, the motivation unit can use generative AI to provide specific advice when a child plays soccer. It can also use generative AI to provide specific advice when a child plays the piano. Furthermore, it can use generative AI to provide specific advice when a child draws pictures. For example, the motivation unit inputs the child's behavioral data into the generative AI and generates specific advice. This allows for the provision of effective advice to children using generative AI. The generative AI is, for example, 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 processes in the motivation unit may be performed using generative AI or not. For example, the motivation unit can input the child's behavioral data into the generative AI and have the generative AI generate specific advice.

[0037] The analytics unit can analyze a child's past browsing history and track changes in their interests. For example, the analytics unit can analyze patterns of websites a child has frequently visited in the past and visualize changes in their interests. The analytics unit can also identify topics a child was interested in at a specific time from their browsing history. Furthermore, the analytics unit can analyze a child's browsing history chronologically and graph changes in their interests. For example, the analytics unit can input past browsing history into a generative AI and have the generative AI perform an analysis to track changes in interests. This allows for the provision of more personalized prompts by understanding the changes in the child's interests. The generative AI is, for example, 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 processing in the analytics unit may be performed using a generative AI or not. For example, the analytics unit can input past browsing history into a generative AI and have the generative AI perform an analysis to track changes in interests.

[0038] The analysis unit can assess the depth of a child's interest and measure their level of engagement with specific interests. For example, the analysis unit can assess the depth of interest based on the time a child spends on a particular topic. It can also measure engagement based on how thoroughly a child researches information about a particular topic. Furthermore, the analysis unit can assess engagement based on a child's activities (comments, shares, etc.) related to a particular topic. For example, the analysis unit can input data on a particular topic into a generative AI and have the generative AI perform an analysis to assess the depth of interest and engagement. This allows for more effective prompts by measuring the child's level of engagement. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the processing described above in the analysis unit may be performed using a generative AI or not. For example, the analysis unit can input data on a particular topic into a generative AI and have the generative AI perform an analysis to assess the depth of interest and engagement.

[0039] The analysis unit can analyze region-specific interests based on children's geographical location information. For example, the analysis unit can analyze region-specific events and activities based on children's residential areas. It can also identify region-specific interests based on children's school and community information. Furthermore, the analysis unit can analyze local trends and popular activities based on children's geographical location information. For example, the analysis unit can input geographical location information into a generating AI and have the generating AI perform an analysis to analyze region-specific interests. This allows for the provision of more personalized prompts by analyzing region-specific interests. The generating AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using or without a generating AI. For example, the analysis unit can input geographical location information into a generating AI and have the generating AI perform an analysis to analyze region-specific interests.

[0040] The analysis unit can analyze children's social media activity and correlate their online interests with their offline behavior. For example, the analysis unit can analyze the content of children's social media posts to identify topics of interest. It can also analyze children's social media friendships to identify common interests. Furthermore, the analysis unit can predict offline behavior patterns based on children's social media activity. For example, the analysis unit can input social media data into a generative AI and have the generative AI perform an analysis that correlates online and offline behavior. This allows for more effective prompts by correlating online and offline behavior. The generative AI is, for example, 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 processing in the analysis unit may be performed using a generative AI or not. For example, the analysis unit can input social media data into a generative AI and have the generative AI perform an analysis that correlates online and offline behavior.

[0041] The prompt generation unit can adjust the level of detail of prompts based on the depth of the child's interest. For example, if a child has a strong interest in a particular topic, the prompt generation unit will create a prompt containing detailed information. It can also create a prompt containing basic information if the child is beginning to show interest in a new topic. Furthermore, if the child is interested in multiple topics, the prompt generation unit can create prompts that include an overview of each topic. For example, the prompt generation unit can have the generating AI perform an analysis to adjust the level of detail of prompts based on the depth of interest. This allows for more effective motivation by providing prompts tailored to the child's level of interest. The generating 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 processes in the prompt generation unit may be performed using or without the generating AI. For example, the prompt generation unit can input the child's interest data into the generating AI and have the generating AI adjust the level of detail of prompts.

[0042] The prompt generation unit can apply different prompt generation algorithms depending on the child's age and grade level when creating prompts. For example, the prompt generation unit can create simple and visual prompts for preschoolers. It can also create concrete and practical prompts for elementary school students. Furthermore, it can create abstract and challenging prompts for middle and high school students. For example, the prompt generation unit can have a generation AI execute a prompt generation algorithm appropriate to the child's age and grade level. This allows for more effective motivation by providing prompts tailored to the child's age and grade level. 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 processes in the prompt generation unit may be performed using the generation AI or not. For example, the prompt generation unit can input the child's age and grade level data into the generation AI and have the generation AI execute the application of a prompt generation algorithm.

[0043] The prompt generation unit can determine prompt priorities based on the child's past response history when creating prompts. For example, the prompt generation unit may prioritize prompts to which the child has responded favorably in the past. It can also postpone prompts to which the child has been indifferent in the past. Furthermore, the prompt generation unit can analyze the child's past response history and prioritize the most effective prompts. For example, the prompt generation unit can input past response history into a generating AI and have the generating AI perform an analysis to determine prompt priorities. This enables more effective motivation by providing prompts based on the child's past response history. The generating AI is, for example, a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the above processing in the prompt generation unit may be performed using a generating AI or not using a generating AI. For example, the prompt generation unit can input past response history into a generating AI and have the generating AI perform an analysis to determine prompt priorities.

[0044] The prompt generation unit can adjust the order of prompts based on the relevance of the child's interests when creating prompts. For example, the prompt generation unit can first provide the prompt most relevant to the child's current interests. It can also then provide prompts related to the child's past interests. Furthermore, the prompt generation unit can dynamically adjust the order of prompts based on the changes in the child's interests. For example, the prompt generation unit can have the generating AI perform an analysis to adjust the order of prompts based on the relevance of interests. This enables more effective motivation by providing prompts based on the relevance of the child's interests. The generating AI is, for example, 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 processing in the prompt generation unit may be performed using the generating AI or not. For example, the prompt generation unit can input interest relevance data into the generating AI and have the generating AI perform an analysis to adjust the order of prompts.

[0045] The motivation unit can analyze a child's past behavioral history to select the optimal motivation method during the motivation process. For example, the motivation unit can select a similar motivation method based on the child's past successful experiences. It can also select a different motivation method based on the child's past failures. Furthermore, the motivation unit can analyze the child's past behavioral history to select the most effective motivation method. For example, the motivation unit can input past behavioral history into a generating AI and have the generating AI perform an analysis to select the optimal motivation method. This enables more effective motivation by providing motivation methods based on the child's past behavioral history. The generating AI is, for example, a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to these examples. Some or all of the above-described processes in the motivation unit may be performed using a generating AI or not. For example, the motivation unit can input past behavioral history into a generating AI and have the generating AI perform an analysis to select the optimal motivation method.

[0046] The motivation unit can customize the means of motivation based on the child's current living situation during the motivation process. For example, if the child is in the middle of school exams, the motivation unit will provide academically related motivation. It can also provide sports-related motivation if the child is participating in a sports event. Furthermore, the motivation unit can select the most appropriate motivational means considering the child's current living situation. For example, the motivation unit can input living situation data into a generating AI and have the generating AI perform an analysis to customize the motivational means. This allows for more effective motivation by providing motivational means tailored to the child's current living situation. The generating AI is, for example, a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to these examples. Some or all of the above-described processes in the motivation unit may be performed using the generating AI or not. For example, the motivation unit can input living situation data into a generating AI and have the generating AI perform an analysis to customize the motivational means.

[0047] The motivation unit can select the optimal motivation method based on the child's geographical location information during the motivation process. For example, the motivation unit can suggest local events and activities based on the child's residential area. It can also select local motivation methods based on information about the child's school and community. Furthermore, the motivation unit can suggest local trends and popular activities based on the child's geographical location information. For example, the motivation unit can input geographical location information into a generating AI and have the generating AI perform an analysis to select the optimal motivation method. This enables more effective motivation by providing motivation methods based on the child's geographical location information. The generating AI is, for example, a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to these examples. Some or all of the above-described processes in the motivation unit may be performed using a generating AI or not. For example, the motivation unit can input geographical location information into a generating AI and have the generating AI perform an analysis to select the optimal motivation method.

[0048] The motivation unit can analyze a child's social media activity and propose motivational strategies during the motivation process. For example, the motivation unit can analyze the content of a child's social media posts and propose motivations related to topics of interest. It can also analyze a child's social media friendships and propose motivations based on shared interests. Furthermore, the motivation unit can propose optimal motivational strategies based on the child's social media activity. For example, the motivation unit can input social media data into a generating AI and have the generating AI perform an analysis to propose motivational strategies. This allows for more effective motivation by providing motivational strategies based on the child's social media activity. The generating AI may be, but is not limited to, a text generating AI (e.g., LLM) or a multimodal generating AI. Some or all of the above-described processes in the motivation unit may be performed using or without a generating AI. For example, the motivation unit can input social media data into a generating AI and have the generating AI perform an analysis to propose motivational strategies.

[0049] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0050] The system can also be equipped with a feedback section to leverage children's natural curiosity and encourage active participation. The feedback section provides feedback on activities performed by children. For example, if a child practices soccer, it provides specific feedback on areas for improvement and successes based on the practice. The feedback section can also provide technical advice and comments evaluating the creativity of drawings created by children. Furthermore, the feedback section can provide scientific evaluations and suggestions for the next steps in experiments and projects undertaken by children. This allows children to have their efforts recognized and receive concrete guidance for moving forward.

[0051] The system can be equipped with an exploration section to further deepen children's interests. The exploration section suggests new information and activities related to topics that children are interested in. For example, if a child is interested in dinosaurs, the exploration section will provide information on the latest dinosaur research and museum exhibits. If a child is interested in space, the exploration section can also suggest space-related events and online courses. Furthermore, if a child is interested in music, the exploration section can suggest introductions to new instruments or music production workshops. This gives children opportunities to further deepen their interests and acquire new knowledge and skills.

[0052] The system can include a rewards section to maintain children's interest. The rewards section provides rewards when children complete specific activities. For example, if a child completes a reading assignment, the rewards section might offer a digital badge or points. If a child successfully completes a science experiment, the rewards section could offer a special title or access to the next level. Furthermore, if a child continues practicing a sport, the rewards section could offer a trophy or medal. This allows children to feel their efforts are recognized and increases their motivation to move on to the next step.

[0053] The system can include a collaboration section to further broaden children's interests. The collaboration section provides opportunities for children to engage in activities together with other children. For example, if children work on a science project together, the collaboration section supports the project's progress and facilitates role-sharing and communication. If children create artwork together, the collaboration section can also support idea sharing and skill exchange. Furthermore, if children form a sports team together, the collaboration section can support teamwork and strategy development. This allows children to acquire new skills and develop social skills while collaborating with other children.

[0054] The system can include a resources section to deepen children's interests. The resources section provides resources related to topics that children are interested in. For example, if a child is interested in history, the resources section can provide historical documentaries and books. If a child is interested in science, the resources section can also provide science experiment kits and online courses. Furthermore, if a child is interested in art, the resources section can provide art materials and workshops. This gives children opportunities to further deepen their interests and acquire new knowledge and skills.

[0055] The system can include a Challenge Department to further broaden children's interests. The Challenge Department provides challenges for children to acquire new skills and knowledge. For example, if a child is interested in programming, the Challenge Department can suggest programming contests or hackathons. If a child is interested in cooking, the Challenge Department can suggest cooking contests or recipe development challenges. Furthermore, if a child is interested in sports, the Challenge Department can suggest sports tournaments or training challenges. This allows children to acquire new skills and knowledge and deepen their interests.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The analysis department analyzes the child's browsing history and interests. Specifically, it collects the history of websites the child has visited and analyzes their interest trends. It can also evaluate the depth of interest based on the history of videos the child has watched. Furthermore, it can analyze the keywords the child has searched for and track changes in their interests. For example, it can analyze website browsing history chronologically to visualize changes in interests. Step 2: The prompt creation unit creates personalized prompts based on the analysis results obtained by the analysis unit. Specifically, it generates prompts that suggest specific activities based on the child's interests. It can also provide prompts at the optimal timing based on the child's behavioral history. Furthermore, it can adjust the level of detail of the prompts according to the depth of the child's interest. For example, if the child has a strong interest in a particular topic, it will create a prompt that includes detailed information. Step 3: The motivation unit encourages children's behavior based on prompts created by the prompt generation unit. Specifically, it uses videos of the children playing to show what kind of practice will lead to improvement. It can also use generative AI to provide specific advice to encourage children's behavior. Furthermore, it can estimate the children's emotions and adjust the motivational methods based on those emotions. For example, if the child is excited, it will provide energetic and positive motivation.

[0058] (Example of form 2) The system according to the embodiment of the present invention aims not to restrict children's use of the internet and social media, but rather to leverage their natural curiosity and subtly guide them to interest-based activities that require active participation. This promotes children to develop spontaneous thinking, explore and develop their passions through hands-on activities. Specifically, it utilizes generative AI to analyze a child's browsing history, interests, and behavior, and creates personalized prompts that resonate with that child. For example, if a child frequently visits websites about soccer, the system might estimate how much and in what way they would improve if they spent that time playing soccer instead of browsing, and calculate their chances of becoming a professional soccer player, thereby encouraging them to play soccer instead. Furthermore, it can use videos of the child playing to show how different types of practice improve their skills, how that changes their play, and how it can lead to success in matches, thereby motivating children. In this way, the system can leverage children's natural curiosity and promote active participation.

[0059] The system according to this embodiment comprises an analysis unit, a prompt creation unit, and a motivation unit. The analysis unit analyzes the child's browsing history and interests. For example, the analysis unit collects the history of websites visited by the child and analyzes the child's interest trends. The analysis unit can also evaluate the depth of the child's interest based on the history of videos the child has watched. Furthermore, the analysis unit can analyze the keywords the child has searched for and track the changes in their interests. For example, the analysis unit analyzes the website browsing history in chronological order and visualizes changes in interests. The prompt creation unit creates personalized prompts based on the analysis results obtained by the analysis unit. For example, the prompt creation unit generates prompts that suggest specific activities based on the child's interests. The prompt creation unit can also provide prompts at the optimal timing based on the child's behavioral history. Furthermore, the prompt creation unit can adjust the level of detail of the prompts according to the depth of the child's interest. For example, if the prompt creation unit has a strong interest in a particular topic, it will create a prompt that includes detailed information. The motivation unit encourages the children's behavior based on the prompts created by the prompt creation unit. The motivation unit can, for example, use videos of children playing to show how different types of practice lead to improvement. It can also use generative AI to provide specific advice to encourage children's behavior. Furthermore, the motivation unit can estimate a child's emotions and adjust its motivational approach based on those emotions. For instance, if a child is excited, it will provide energetic and positive motivation. This allows the system to leverage children's natural curiosity and encourage active participation.

[0060] The analytics department analyzes children's browsing history and interests. Specifically, it collects the history of websites visited by children and analyzes their interest trends. For example, if a child frequently visits educational websites or views a lot of information on a particular theme, it can be determined that they have a high level of interest in that theme. The analytics department can also evaluate the depth of interest based on the history of videos children watch. By analyzing viewing time, number of views, and genres of videos watched, it can be assessed how interested the child is in a particular theme. Furthermore, the analytics department can analyze the keywords children search for and track changes in their interests. For example, if a particular keyword is frequently searched, it can be determined that a new interest related to that keyword has emerged. The analytics department analyzes this data over time to visualize changes in interests. This allows for a detailed understanding of children's interest trends and changes, which can be used to create prompts for the next steps. In addition, the analytics department can use AI to analyze the data and perform more advanced pattern recognition and prediction. For example, machine learning algorithms can be used to predict changes in children's interests and estimate what themes they are likely to be interested in in the future. This allows the analytics department to gain a deeper understanding of children's interests and contribute to creating personalized prompts.

[0061] The prompt generation unit creates personalized prompts based on the analysis results obtained by the analysis unit. Specifically, it generates prompts that suggest specific activities based on the child's interests. For example, if a child is interested in science, it will create prompts that suggest ideas for science experiments or watching related videos. The prompt generation unit can also provide prompts at the optimal time based on the child's behavioral history. For example, if a child is active during a particular time of day, providing prompts at that time can more effectively capture their interest. Furthermore, the prompt generation unit can adjust the level of detail of prompts according to the depth of the child's interest. For example, if a child has a strong interest in a particular topic, it will create prompts with detailed information, while providing concise prompts if their interest is shallow. The prompt generation unit can also automatically generate prompts using generative AI. The generative AI takes the child's interests and behavioral history as input and generates optimal prompts. For example, it uses natural language processing technology to generate sentences and questions related to the child's interests and provide prompts that capture the child's interest. This allows the prompt generation unit to efficiently create personalized prompts tailored to the child's interests and support their learning and activities.

[0062] The motivation unit promotes children's behavior based on prompts created by the prompt generation unit. Specifically, it uses videos of children playing to show how to improve through practice. For example, it advises children who have watched sports practice videos on specific practice methods and tips for improvement based on the content of the videos. The motivation unit can also use generative AI to provide specific advice to promote children's behavior. The generative AI analyzes children's interests and behavioral history to generate optimal advice. For example, if a child is interested in a particular theme, it suggests new information and activities related to that theme. The motivation unit can also estimate children's emotions and adjust its motivational methods based on those emotions. For example, if a child is excited, it provides energetic and positive motivation; conversely, if a child is depressed, it offers words of encouragement and comfort. The motivation unit uses emotion recognition technology to analyze children's facial expressions and tone of voice to estimate their emotions. This allows the motivation unit to provide appropriate motivation according to the child's emotions. Furthermore, the motivation unit can collect children's feedback and continuously evaluate and improve the effectiveness of the motivation. For example, the team can analyze which advice elicited the best response from children and use that information to improve future motivation. This allows the motivation department to leverage children's natural curiosity and encourage active participation.

[0063] The analysis unit can analyze a child's browsing history and interests using generative AI. For example, the analysis unit can use generative AI to analyze a child's website visit history and identify trends in their interests. It can also use generative AI to analyze a child's video viewing history and evaluate the depth of their interest. Furthermore, the analysis unit can use generative AI to analyze keywords a child has searched for and track changes in their interests. For example, the analysis unit can input website browsing history into the generative AI and visualize changes in interests. This allows for accurate analysis of a child's interests using generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using generative AI or not. For example, the analysis unit can input a child's browsing history into the generative AI and have the generative AI perform an analysis to identify trends in their interests.

[0064] The prompt generation unit can create personalized prompts using generative AI. For example, the prompt generation unit can use generative AI to generate prompts that suggest specific activities based on the child's interests. The prompt generation unit can also use generative AI to provide prompts at the optimal timing based on the child's behavioral history. Furthermore, the prompt generation unit can use generative AI to adjust the level of detail of the prompts according to the depth of the child's interest. For example, the prompt generation unit can input the child's interest data into the generative AI and generate personalized prompts. This allows the system to provide the child with the most appropriate prompts by using generative AI. The generative AI is, for example, 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 processes in the prompt generation unit may be performed using generative AI or not. For example, the prompt generation unit can input the child's interest data into the generative AI and have the generative AI generate personalized prompts.

[0065] The motivation unit can use videos of children playing to show them what kind of practice will help them improve. For example, the motivation unit can analyze a video of a child playing soccer and show them what kind of practice they should do. It can also analyze a video of a child playing the piano and show them what kind of practice they should do. Furthermore, it can analyze a video of a child drawing and show them what kind of practice they should do. For example, the motivation unit can analyze a video of a child playing soccer and suggest practice methods to improve a specific skill. This can increase the child's motivation by showing them specific practice methods. Some or all of the above processing in the motivation unit may be performed using generative AI or not. For example, the motivation unit can input a video of a child playing into a generative AI and have the generative AI suggest practice methods.

[0066] The motivation unit can use generative AI to provide specific advice to encourage children's behavior. For example, the motivation unit can use generative AI to provide specific advice when a child plays soccer. It can also use generative AI to provide specific advice when a child plays the piano. Furthermore, it can use generative AI to provide specific advice when a child draws pictures. For example, the motivation unit inputs the child's behavioral data into the generative AI and generates specific advice. This allows for the provision of effective advice to children using generative AI. The generative AI is, for example, 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 processes in the motivation unit may be performed using generative AI or not. For example, the motivation unit can input the child's behavioral data into the generative AI and have the generative AI generate specific advice.

[0067] The analysis unit can estimate a child's emotions and adjust the analysis method of browsing history based on the estimated emotions. For example, the analysis unit can capture a child's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The analysis unit can also record a child's voice and estimate their emotions using voice analysis technology. Furthermore, the analysis unit can collect a child's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, the analysis unit can input the child's facial expression data into a generative AI and have the generative AI perform emotion estimation. This allows for more appropriate feedback by providing an analysis method that corresponds to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using a generative AI or not. For example, the analysis department can input children's emotional data into a generating AI and have the AI ​​adjust the analysis method based on those emotions.

[0068] The analytics unit can analyze a child's past browsing history and track changes in their interests. For example, the analytics unit can analyze patterns of websites a child has frequently visited in the past and visualize changes in their interests. The analytics unit can also identify topics a child was interested in at a specific time from their browsing history. Furthermore, the analytics unit can analyze a child's browsing history chronologically and graph changes in their interests. For example, the analytics unit can input past browsing history into a generative AI and have the generative AI perform an analysis to track changes in interests. This allows for the provision of more personalized prompts by understanding the changes in the child's interests. The generative AI is, for example, 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 processing in the analytics unit may be performed using a generative AI or not. For example, the analytics unit can input past browsing history into a generative AI and have the generative AI perform an analysis to track changes in interests.

[0069] The analysis unit can assess the depth of a child's interest and measure their level of engagement with specific interests. For example, the analysis unit can assess the depth of interest based on the time a child spends on a particular topic. It can also measure engagement based on how thoroughly a child researches information about a particular topic. Furthermore, the analysis unit can assess engagement based on a child's activities (comments, shares, etc.) related to a particular topic. For example, the analysis unit can input data on a particular topic into a generative AI and have the generative AI perform an analysis to assess the depth of interest and engagement. This allows for more effective prompts by measuring the child's level of engagement. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the processing described above in the analysis unit may be performed using a generative AI or not. For example, the analysis unit can input data on a particular topic into a generative AI and have the generative AI perform an analysis to assess the depth of interest and engagement.

[0070] The analysis unit can estimate a child's emotions and determine the priority of the analysis results based on the estimated emotions. For example, the analysis unit can capture a child's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The analysis unit can also record a child's voice and estimate their emotions using voice analysis technology. Furthermore, the analysis unit can collect a child's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, the analysis unit can input a child's facial expression data into a generating AI and have the generating AI perform emotion estimation. This allows for more appropriate feedback by setting priorities according to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using a generating AI or not using a generating AI. For example, the analysis unit can input a child's emotion data into a generating AI and have the generating AI perform emotion-based priority setting.

[0071] The analysis unit can analyze region-specific interests based on children's geographical location information. For example, the analysis unit can analyze region-specific events and activities based on children's residential areas. It can also identify region-specific interests based on children's school and community information. Furthermore, the analysis unit can analyze local trends and popular activities based on children's geographical location information. For example, the analysis unit can input geographical location information into a generating AI and have the generating AI perform an analysis to analyze region-specific interests. This allows for the provision of more personalized prompts by analyzing region-specific interests. The generating AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using or without a generating AI. For example, the analysis unit can input geographical location information into a generating AI and have the generating AI perform an analysis to analyze region-specific interests.

[0072] The analysis unit can analyze children's social media activity and correlate their online interests with their offline behavior. For example, the analysis unit can analyze the content of children's social media posts to identify topics of interest. It can also analyze children's social media friendships to identify common interests. Furthermore, the analysis unit can predict offline behavior patterns based on children's social media activity. For example, the analysis unit can input social media data into a generative AI and have the generative AI perform an analysis that correlates online and offline behavior. This allows for more effective prompts by correlating online and offline behavior. The generative AI is, for example, 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 processing in the analysis unit may be performed using a generative AI or not. For example, the analysis unit can input social media data into a generative AI and have the generative AI perform an analysis that correlates online and offline behavior.

[0073] The prompt generation unit can estimate a child's emotions and adjust the way prompts are expressed based on the estimated emotions. For example, the prompt generation unit can capture a child's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. It can also record a child's voice and estimate the emotion using voice analysis technology. Furthermore, the prompt generation unit can collect a child's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. For example, the prompt generation unit can input the child's facial expression data into a generating AI and have the generating AI perform emotion estimation. This enables more effective motivation by providing prompts that correspond to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is 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 processes in the prompt generation unit may be performed using a generating AI or not using a generating AI. For example, the prompt generation unit can input child emotional data into a generating AI and have the generating AI adjust the way prompts are expressed based on those emotions.

[0074] The prompt generation unit can adjust the level of detail of prompts based on the depth of the child's interest. For example, if a child has a strong interest in a particular topic, the prompt generation unit will create a prompt containing detailed information. It can also create a prompt containing basic information if the child is beginning to show interest in a new topic. Furthermore, if the child is interested in multiple topics, the prompt generation unit can create prompts that include an overview of each topic. For example, the prompt generation unit can have the generating AI perform an analysis to adjust the level of detail of prompts based on the depth of interest. This allows for more effective motivation by providing prompts tailored to the child's level of interest. The generating 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 processes in the prompt generation unit may be performed using or without the generating AI. For example, the prompt generation unit can input the child's interest data into the generating AI and have the generating AI adjust the level of detail of prompts.

[0075] The prompt generation unit can apply different prompt generation algorithms depending on the child's age and grade level when creating prompts. For example, the prompt generation unit can create simple and visual prompts for preschoolers. It can also create concrete and practical prompts for elementary school students. Furthermore, it can create abstract and challenging prompts for middle and high school students. For example, the prompt generation unit can have a generation AI execute a prompt generation algorithm appropriate to the child's age and grade level. This allows for more effective motivation by providing prompts tailored to the child's age and grade level. 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 processes in the prompt generation unit may be performed using the generation AI or not. For example, the prompt generation unit can input the child's age and grade level data into the generation AI and have the generation AI execute the application of a prompt generation algorithm.

[0076] The prompt generation unit can estimate a child's emotions and adjust the length of the prompt based on the estimated emotions. For example, the prompt generation unit can capture a child's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. It can also record a child's voice and estimate the emotion using voice analysis technology. Furthermore, the prompt generation unit can collect a child's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. For example, the prompt generation unit can input the child's facial expression data into a generating AI and have the generating AI perform emotion estimation. This allows for more effective motivation by providing prompt lengths that correspond to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the prompt generation unit may be performed using a generating AI or not using a generating AI. For example, the prompt generation unit can input child emotion data into a generating AI, which can then adjust the length of the prompt based on the child's emotions.

[0077] The prompt generation unit can determine prompt priorities based on the child's past response history when creating prompts. For example, the prompt generation unit may prioritize prompts to which the child has responded favorably in the past. It can also postpone prompts to which the child has been indifferent in the past. Furthermore, the prompt generation unit can analyze the child's past response history and prioritize the most effective prompts. For example, the prompt generation unit can input past response history into a generating AI and have the generating AI perform an analysis to determine prompt priorities. This enables more effective motivation by providing prompts based on the child's past response history. The generating AI is, for example, a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the above processing in the prompt generation unit may be performed using a generating AI or not using a generating AI. For example, the prompt generation unit can input past response history into a generating AI and have the generating AI perform an analysis to determine prompt priorities.

[0078] The prompt generation unit can adjust the order of prompts based on the relevance of the child's interests when creating prompts. For example, the prompt generation unit can first provide the prompt most relevant to the child's current interests. It can also then provide prompts related to the child's past interests. Furthermore, the prompt generation unit can dynamically adjust the order of prompts based on the changes in the child's interests. For example, the prompt generation unit can have the generating AI perform an analysis to adjust the order of prompts based on the relevance of interests. This enables more effective motivation by providing prompts based on the relevance of the child's interests. The generating AI is, for example, 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 processing in the prompt generation unit may be performed using the generating AI or not. For example, the prompt generation unit can input interest relevance data into the generating AI and have the generating AI perform an analysis to adjust the order of prompts.

[0079] The motivation unit can estimate a child's emotions and adjust the motivation method based on the estimated emotions. For example, the motivation unit can capture a child's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. It can also record a child's voice and estimate their emotions using voice analysis technology. Furthermore, the motivation unit can collect a child's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, the motivation unit can input the child's facial expression data into a generating AI and have the generating AI perform emotion estimation. This enables more effective motivation by providing a motivation method that corresponds to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the motivation unit may be performed using a generating AI or not using a generating AI. For example, the motivation unit can input child emotional data into a generating AI and have the generating AI adjust the motivation method based on those emotions.

[0080] The motivation unit can analyze a child's past behavioral history to select the optimal motivation method during the motivation process. For example, the motivation unit can select a similar motivation method based on the child's past successful experiences. It can also select a different motivation method based on the child's past failures. Furthermore, the motivation unit can analyze the child's past behavioral history to select the most effective motivation method. For example, the motivation unit can input past behavioral history into a generating AI and have the generating AI perform an analysis to select the optimal motivation method. This enables more effective motivation by providing motivation methods based on the child's past behavioral history. The generating AI is, for example, a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to these examples. Some or all of the above-described processes in the motivation unit may be performed using a generating AI or not. For example, the motivation unit can input past behavioral history into a generating AI and have the generating AI perform an analysis to select the optimal motivation method.

[0081] The motivation unit can customize the means of motivation based on the child's current living situation during the motivation process. For example, if the child is in the middle of school exams, the motivation unit will provide academically related motivation. It can also provide sports-related motivation if the child is participating in a sports event. Furthermore, the motivation unit can select the most appropriate motivational means considering the child's current living situation. For example, the motivation unit can input living situation data into a generating AI and have the generating AI perform an analysis to customize the motivational means. This allows for more effective motivation by providing motivational means tailored to the child's current living situation. The generating AI is, for example, a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to these examples. Some or all of the above-described processes in the motivation unit may be performed using the generating AI or not. For example, the motivation unit can input living situation data into a generating AI and have the generating AI perform an analysis to customize the motivational means.

[0082] The motivation unit can estimate a child's emotions and determine motivational priorities based on the estimated emotions. For example, the motivation unit can capture a child's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. It can also record a child's voice and estimate their emotions using voice analysis technology. Furthermore, the motivation unit can collect a child's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, the motivation unit can input the child's facial expression data into a generative AI and have the generative AI perform emotion estimation. This allows for more effective motivation by setting motivational priorities according to the child's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the motivation unit may be performed using a generative AI or not. For example, the motivation unit can input child emotional data into a generating AI and have the AI ​​prioritize motivations based on those emotions.

[0083] The motivation unit can select the optimal motivation method based on the child's geographical location information during the motivation process. For example, the motivation unit can suggest local events and activities based on the child's residential area. It can also select local motivation methods based on information about the child's school and community. Furthermore, the motivation unit can suggest local trends and popular activities based on the child's geographical location information. For example, the motivation unit can input geographical location information into a generating AI and have the generating AI perform an analysis to select the optimal motivation method. This enables more effective motivation by providing motivation methods based on the child's geographical location information. The generating AI is, for example, a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to these examples. Some or all of the above-described processes in the motivation unit may be performed using a generating AI or not. For example, the motivation unit can input geographical location information into a generating AI and have the generating AI perform an analysis to select the optimal motivation method.

[0084] The motivation unit can analyze a child's social media activity and propose motivational strategies during the motivation process. For example, the motivation unit can analyze the content of a child's social media posts and propose motivations related to topics of interest. It can also analyze a child's social media friendships and propose motivations based on shared interests. Furthermore, the motivation unit can propose optimal motivational strategies based on the child's social media activity. For example, the motivation unit can input social media data into a generating AI and have the generating AI perform an analysis to propose motivational strategies. This allows for more effective motivation by providing motivational strategies based on the child's social media activity. The generating AI may be, but is not limited to, a text generating AI (e.g., LLM) or a multimodal generating AI. Some or all of the above-described processes in the motivation unit may be performed using or without a generating AI. For example, the motivation unit can input social media data into a generating AI and have the generating AI perform an analysis to propose motivational strategies.

[0085] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0086] The system can also be equipped with a feedback section to leverage children's natural curiosity and encourage active participation. The feedback section provides feedback on activities performed by children. For example, if a child practices soccer, it provides specific feedback on areas for improvement and successes based on the practice. The feedback section can also provide technical advice and comments evaluating the creativity of drawings created by children. Furthermore, the feedback section can provide scientific evaluations and suggestions for the next steps in experiments and projects undertaken by children. This allows children to have their efforts recognized and receive concrete guidance for moving forward.

[0087] The system can be equipped with an exploration section to further deepen children's interests. The exploration section suggests new information and activities related to topics that children are interested in. For example, if a child is interested in dinosaurs, the exploration section will provide information on the latest dinosaur research and museum exhibits. If a child is interested in space, the exploration section can also suggest space-related events and online courses. Furthermore, if a child is interested in music, the exploration section can suggest introductions to new instruments or music production workshops. This gives children opportunities to further deepen their interests and acquire new knowledge and skills.

[0088] The system can estimate children's emotions and adjust the difficulty of activities based on those estimates. For example, if a child is stressed, the system can suggest relaxing activities. If a child is excited, the system can suggest challenging activities. Furthermore, if a child is depressed, the system can suggest fun activities to lift their spirits. This allows children to engage in activities appropriate to their emotions, leading to more effective engagement and deeper engagement.

[0089] The system can include a rewards section to maintain children's interest. The rewards section provides rewards when children complete specific activities. For example, if a child completes a reading assignment, the rewards section might offer a digital badge or points. If a child successfully completes a science experiment, the rewards section could offer a special title or access to the next level. Furthermore, if a child continues practicing a sport, the rewards section could offer a trophy or medal. This allows children to feel their efforts are recognized and increases their motivation to move on to the next step.

[0090] The system can estimate children's emotions and adjust the content of the feedback based on those estimates. For example, if a child is feeling anxious, the system will provide words of encouragement and positive feedback. If a child is confident, the system can also provide challenging feedback. Furthermore, if a child is excited, the system can provide energetic feedback. This allows children to receive appropriate feedback that matches their emotions, enabling them to grow more effectively.

[0091] The system can include a collaboration section to further broaden children's interests. The collaboration section provides opportunities for children to engage in activities together with other children. For example, if children work on a science project together, the collaboration section supports the project's progress and facilitates role-sharing and communication. If children create artwork together, the collaboration section can also support idea sharing and skill exchange. Furthermore, if children form a sports team together, the collaboration section can support teamwork and strategy development. This allows children to acquire new skills and develop social skills while collaborating with other children.

[0092] The system can estimate children's emotions and adjust the type of reward based on those estimates. For example, if a child is happy, the system can offer fun activities or games as rewards. If a child is tired, the system can offer relaxing activities or breaks as rewards. Furthermore, if a child is excited, the system can offer energetic activities or sports as rewards. This allows children to receive appropriate rewards according to their emotions and maintain their motivation.

[0093] The system can include a resources section to deepen children's interests. The resources section provides resources related to topics that children are interested in. For example, if a child is interested in history, the resources section can provide historical documentaries and books. If a child is interested in science, the resources section can also provide science experiment kits and online courses. Furthermore, if a child is interested in art, the resources section can provide art materials and workshops. This gives children opportunities to further deepen their interests and acquire new knowledge and skills.

[0094] The system can estimate children's emotions and adjust the way they collaborate based on those estimates. For example, if a child is nervous, the system can suggest collaboration in a relaxing environment. If a child is excited, the system can suggest collaboration in an energetic activity. Furthermore, if a child is depressed, the system can suggest collaboration that involves mutual encouragement. This allows children to collaborate appropriately according to their emotions, deepening their interest more effectively.

[0095] The system can include a Challenge Department to further broaden children's interests. The Challenge Department provides challenges for children to acquire new skills and knowledge. For example, if a child is interested in programming, the Challenge Department can suggest programming contests or hackathons. If a child is interested in cooking, the Challenge Department can suggest cooking contests or recipe development challenges. Furthermore, if a child is interested in sports, the Challenge Department can suggest sports tournaments or training challenges. This allows children to acquire new skills and knowledge and deepen their interests.

[0096] The following briefly describes the processing flow for example form 2.

[0097] Step 1: The analysis department analyzes the child's browsing history and interests. Specifically, it collects the history of websites the child has visited and analyzes their interest trends. It can also evaluate the depth of interest based on the history of videos the child has watched. Furthermore, it can analyze the keywords the child has searched for and track changes in their interests. For example, it can analyze website browsing history chronologically to visualize changes in interests. Step 2: The prompt creation unit creates personalized prompts based on the analysis results obtained by the analysis unit. Specifically, it generates prompts that suggest specific activities based on the child's interests. It can also provide prompts at the optimal timing based on the child's behavioral history. Furthermore, it can adjust the level of detail of the prompts according to the depth of the child's interest. For example, if the child has a strong interest in a particular topic, it will create a prompt that includes detailed information. Step 3: The motivation unit encourages children's behavior based on prompts created by the prompt generation unit. Specifically, it uses videos of the children playing to show what kind of practice will lead to improvement. It can also use generative AI to provide specific advice to encourage children's behavior. Furthermore, it can estimate the children's emotions and adjust the motivational methods based on those emotions. For example, if the child is excited, it will provide energetic and positive motivation.

[0098] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0099] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0100] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0101] Each of the multiple elements described above, including the analysis unit, prompt generation unit, and motivation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 and analyzes the child's browsing history and interests. The prompt generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates personalized prompts. The motivation unit is implemented by the control unit 46A of the smart device 14 and provides specific advice to encourage the child's behavior. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0102] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0103] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0104] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0105] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0106] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0108] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0109] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0110] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0111] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0112] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0113] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0114] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0116] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0117] Each of the multiple elements described above, including the analysis unit, prompt generation unit, and motivation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 and analyzes the child's browsing history and interests. The prompt generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates personalized prompts. The motivation unit is implemented by the control unit 46A of the smart glasses 214 and provides specific advice to encourage the child's behavior. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0118] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0119] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0120] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0121] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0122] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the 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 image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0124] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0125] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0126] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0127] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0128] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0130] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 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 a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0132] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0133] Each of the multiple elements described above, including the analysis unit, prompt generation unit, and motivation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 and analyzes the child's browsing history and interests. The prompt generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates personalized prompts. The motivation unit is implemented by the control unit 46A of the headset terminal 314 and provides specific advice to encourage the child's behavior. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0134] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0135] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0136] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0137] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0138] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the 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 image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0140] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0141] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0142] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0143] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0144] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0145] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0147] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0149] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the analysis unit, prompt generation unit, and motivation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 and analyzes the child's browsing history and interests. The prompt generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates personalized prompts. The motivation unit is implemented by the control unit 46A of the robot 414 and provides specific advice to encourage the child's behavior. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0151] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0152] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0153] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0154] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0155] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0156] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0157] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0158] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0159] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0160] 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.

[0161] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0162] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0163] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0164] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0165] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0166] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0167] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0168] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0169] (Note 1) The analytics department analyzes children's browsing history and interests, A prompt creation unit creates a personalized prompt based on the analysis results obtained by the aforementioned analysis unit, The system includes a motivation unit that promotes children's behavior based on prompts created by the prompt generation unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit is Using generative AI to analyze children's browsing history and interests The system described in Appendix 1, characterized by the features described herein. (Note 3) The prompt generation unit, Create personalized prompts using generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned motivation unit is, Using videos of children playing, we demonstrate what kind of practice leads to improvement. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned motivation unit is, Using generated AI, we provide specific advice to encourage children's behavior. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit is We estimate the child's emotions and adjust the analysis method of browsing history based on the estimated emotions of the child. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit is Analyze a child's past browsing history to track changes in their interests. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit is To assess the depth of a child's interest and measure their level of engagement with specific interests. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit is The system estimates the child's emotions and prioritizes the analysis results based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit is Analyzing region-specific interests based on children's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit is Analyze children's social media activity and correlate their online interests with their offline behavior. The system described in Appendix 1, characterized by the features described herein. (Note 12) The prompt generation unit, The system estimates the child's emotions and adjusts the way prompts are phrased based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 13) The prompt generation unit, When creating prompts, adjust the level of detail based on the child's level of interest. The system described in Appendix 1, characterized by the features described herein. (Note 14) The prompt generation unit, When creating prompts, different prompt generation algorithms are applied depending on the child's age and grade level. The system described in Appendix 1, characterized by the features described herein. (Note 15) The prompt generation unit, The system estimates the child's emotions and adjusts the prompt length based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The prompt generation unit, When creating prompts, prioritize prompts based on the child's past response history. The system described in Appendix 1, characterized by the features described herein. (Note 17) The prompt generation unit, When creating prompts, adjust the order of prompts based on the relevance of the child's interests. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned motivation unit is, Estimate the child's emotions and adjust the motivational methods based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned motivation unit is, When motivating a child, analyze their past behavioral history to select the most suitable motivational method. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned motivation unit is, When providing motivation, customize the motivational methods based on the child's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned motivation unit is, The system estimates the child's emotions and determines motivational priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned motivation unit is, When providing motivation, the most suitable motivational method is selected based on the child's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned motivation unit is, When providing motivation, we analyze children's social media activity and propose motivational strategies. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analytics department analyzes children's browsing history and interests, A prompt creation unit creates a personalized prompt based on the analysis results obtained by the aforementioned analysis unit, The system includes a motivation unit that promotes children's behavior based on prompts created by the prompt generation unit. A system characterized by the following features.

2. The aforementioned analysis unit is Using generative AI to analyze children's browsing history and interests. The system according to feature 1.

3. The prompt generation unit, Create personalized prompts using generative AI. The system according to feature 1.

4. The aforementioned motivation unit is, Using videos of children playing, we demonstrate what kind of practice leads to improvement. The system according to feature 1.

5. The aforementioned motivation unit is, Using generative AI, we provide specific advice to encourage children's behavior. The system according to feature 1.

6. The aforementioned analysis unit is We estimate the child's emotions and adjust the method of analyzing browsing history based on the estimated emotions. The system according to feature 1.

7. The aforementioned analysis unit is Analyze a child's past browsing history to track changes in their interests. The system according to feature 1.

8. The aforementioned analysis unit is To assess the depth of a child's interest and measure their level of engagement with specific interests. The system according to feature 1.

Images