system

Abstract

The system according to the embodiment aims to effectively convey the hobbies and special skills of elderly people to the younger generation. [Solution] The system according to the embodiment includes a collection unit, a learning unit, and a providing unit. The collection unit collects information about the hobbies and special skills of elderly people. The learning unit studies the collected information. The providing unit acts as a lecturer at an online cram school based on the learned knowledge.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately provide a means for elderly people to effectively share their hobbies and special skills with younger generations, and there is room for improvement.

[0005] The system according to the embodiment aims to effectively convey the hobbies and special skills of elderly people to the younger generation. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a learning unit, and a providing unit. The collection unit collects information about the hobbies and special skills of elderly people. The learning unit studies the collected information. The providing unit acts as a lecturer at an online cram school based on the learned knowledge. [Effects of the Invention]

[0007] The system according to the embodiment can effectively convey the hobbies and special skills of elderly people to younger generations. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An online tutoring system according to an embodiment of the present invention uses an AI avatar to collect hobbies and special skills that seniors can teach to younger generations. This online tutoring system first collects information about seniors' hobbies and special skills. The AI ​​avatar then learns the collected information. Once the AI ​​avatar has completed the learning process, it acts as a tutor for the online tutoring system. Users can access the AI ​​avatar through a smartphone app and receive lessons on hobbies and special skills. This service allows seniors to pass on their knowledge and experience to younger generations, promoting intergenerational exchange. It also allows younger generations to learn new hobbies and special skills, promoting self-improvement. For example, information about seniors' hobbies and special skills is collected. Examples include handicrafts, cooking, gardening, and playing music. This information is collected through interviews, questionnaires, audio recordings, videos, and so on. The AI ​​avatar then learns the collected information. The AI ​​avatar analyzes the collected data and acquires knowledge about seniors' hobbies and special skills. For example, it learns handicraft techniques, cooking recipes, and gardening tips. Once the AI ​​avatar has completed its training, it will act as a teacher at an online cram school. Users can access the AI ​​avatar through a smartphone app and receive lessons on hobbies and special skills. For example, in a handicraft lesson, the AI ​​avatar will explain the steps and show a video of the actual handicraft being performed. In a cooking lesson, the AI ​​avatar will explain the recipe and show a video of the cooking steps. This service allows the knowledge and experience of the elderly to be passed on to the younger generation, promoting intergenerational exchange. It also allows the younger generation to learn new hobbies and special skills, helping them to grow. In this way, the online cram school system can pass on the knowledge and experience of the elderly to the younger generation, promoting intergenerational exchange. It also allows the younger generation to learn new hobbies and special skills, helping them to grow.

[0029] An online tutoring system according to an embodiment includes a collection unit, a learning unit, and a providing unit. The collection unit collects information about the hobbies and special skills of elderly people. The collection unit collects information through, for example, interviews, questionnaires, audio recordings, videos, etc. For example, the collection unit can collect information about elderly people's hobbies and special skills, such as handicrafts, cooking, gardening, and playing music. The collection unit can collect detailed information about elderly people's hobbies and special skills through, for example, interviews. The collection unit can also collect information about elderly people's hobbies and special skills through questionnaires. Furthermore, the collection unit can collect information about elderly people's hobbies and special skills through audio recordings and videos. The learning unit studies the information collected by the collection unit. For example, the learning unit analyzes the collected data to acquire knowledge about elderly people's hobbies and special skills. For example, the learning unit can learn handicraft techniques, cooking recipes, gardening tips, etc. For example, the learning unit can analyze the collected data to acquire handicraft techniques. The learning unit can also analyze the collected data to acquire cooking recipes. Furthermore, the learning unit can analyze the collected data and teach gardening tips. The providing unit acts as an instructor for an online cram school based on the knowledge learned by the learning unit. For example, the providing unit allows a user to access an AI avatar through a smartphone app and provides lessons on hobbies and special skills. For example, the providing unit can explain the steps in a handicraft lesson and show a video of the actual handicraft being performed. Furthermore, the providing unit can explain recipes in a cooking lesson and show a video of the cooking steps. Furthermore, the providing unit can explain tips in a gardening lesson and show a video of the actual gardening. In this way, the online cram school system according to the embodiment collects, learns, and provides information about the hobbies and special skills of the elderly, promoting intergenerational exchange and allowing younger generations to learn new hobbies and special skills. Some or all of the above-described processing by the providing unit may be performed using, or without, AI. For example, the providing unit can input the information collected by the collecting unit into a generation AI and provide lessons based on the knowledge learned by the generation AI.

[0030] The collection unit can collect information through interviews or questionnaires, audio recordings, and videos. For example, the collection unit can collect detailed information about the elderly's hobbies and special skills through interviews. For example, the collection unit can ask the elderly questions about their hobbies and special skills and record the responses. The collection unit can also collect information about the elderly's hobbies and special skills through questionnaires. For example, the collection unit can administer a questionnaire about the elderly's hobbies and special skills to the elderly and collect the responses. The collection unit can also collect information about the elderly's hobbies and special skills through audio recordings and videos. For example, the collection unit can audio or video record the elderly demonstrating their hobbies or special skills and collect the data. This allows for more accurate and extensive information to be obtained by collecting information in a variety of ways. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit can input interview or questionnaire response data into a generation AI and collect information analyzed by the generation AI.

[0031] The learning unit can analyze the collected data and acquire knowledge about the elderly person's hobbies and special skills. The learning unit can, for example, analyze the collected data and acquire handicraft techniques. For example, the learning unit can analyze the collected handicraft-related data and acquire handicraft techniques. The learning unit can also analyze the collected data and acquire cooking recipes. For example, the learning unit can analyze the collected cooking-related data and acquire cooking recipes. The learning unit can also analyze the collected data and acquire gardening tips. For example, the learning unit can analyze the collected gardening-related data and acquire gardening tips. In this way, by analyzing the collected data, the AI ​​avatar can accurately acquire knowledge about the elderly person's hobbies and special skills. Some or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can input the collected data into a generation AI and learn the information analyzed by the generation AI.

[0032] The providing unit allows a user to access an AI avatar through a smartphone app and provides lessons related to hobbies or special skills. For example, in a handicraft lesson, the providing unit can explain the steps and show a video of the handicraft being performed. For example, the providing unit can explain the steps of the handicraft in detail and show a video of the handicraft being performed according to the steps. In a cooking lesson, the providing unit can also explain a recipe and show a video of the cooking steps. For example, the providing unit can explain a cooking recipe in detail and show a video of the cooking being performed according to the recipe. In a gardening lesson, the providing unit can also explain tips and show a video of the gardening being performed. For example, the providing unit can explain gardening tips in detail and show a video of the gardening being performed according to the tips. This allows a user to easily access the AI ​​avatar through the smartphone app and receive lessons. Some or all of the above-mentioned processing by the providing unit may be performed using AI, for example, or without AI. For example, the providing unit can input information collected by the collecting unit into the generating AI and provide lessons based on the knowledge learned by the generating AI.

[0033] The providing unit can explain the steps in a handicraft lesson and show a video of how the handicraft is performed. For example, the providing unit can explain the steps of a handicraft in detail and show a video of how the handicraft is performed according to the steps. For example, the providing unit can explain basic steps of a handicraft and show a video of how the handicraft is performed according to the steps. The providing unit can also explain advanced steps of a handicraft and show a video of how the handicraft is performed according to the steps. For example, the providing unit can explain advanced steps of a handicraft and show a video of how the handicraft is performed according to the steps. The providing unit can also explain tips and points for a handicraft and show a video of how the handicraft is performed according to the tips and points. For example, the providing unit can explain tips and points for a handicraft and show a video of how the handicraft is performed according to the tips and points. In this way, showing handicraft lessons in video makes it easier for the user to visually understand. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input craft steps into the generating AI and provide lessons based on the steps generated by the generating AI.

[0034] In a cooking lesson, the providing unit can explain the recipe and show the cooking steps in a video. For example, the providing unit can explain the recipe in detail and show a video of how to cook according to the recipe. For example, the providing unit can explain a basic recipe and show a video of how to cook according to the recipe. The providing unit can also explain an advanced recipe and show a video of how to cook according to the recipe. For example, the providing unit can explain an advanced recipe and show a video of how to cook according to the recipe. The providing unit can also explain cooking tips and points and show a video of how to cook according to the tips and points. For example, the providing unit can explain cooking tips and points and show a video of how to cook according to the tips and points. In this way, showing cooking lessons in a video makes it easier for users to understand visually. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit can input a cooking recipe into a generation AI and provide a lesson based on the recipe generated by the generation AI.

[0035] The collection unit can analyze the elderly person's past hobbies and special skills and select the optimal collection method. For example, if the elderly person has experience teaching handicrafts in the past, the collection unit can conduct a detailed interview about handicrafts. For example, the collection unit can analyze the elderly person's past activity records related to handicrafts and conduct an interview based on that information. Furthermore, if the elderly person has experience running cooking classes, the collection unit can also conduct a questionnaire about cooking. For example, the collection unit can analyze data about the elderly person's past cooking classes and create a questionnaire based on that information. Furthermore, if the elderly person has extensive experience playing music, the collection unit can also collect recorded data of the performances. For example, the collection unit can analyze data about the elderly person's past musical performances and collect recorded data based on that information. In this way, information can be collected in the optimal manner by analyzing the elderly person's past history. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without AI. For example, the collection unit can input the elderly person's past history data into a generation AI and select a collection method based on the information analyzed by the generation AI.

[0036] When collecting information, the collection unit can filter the information based on the elderly person's current living situation and areas of interest. For example, if the elderly person is currently interested in gardening, the collection unit prioritizes collecting information about gardening. For example, the collection unit analyzes the elderly person's current living situation and areas of interest and collects information about gardening. Furthermore, if the elderly person enjoys handicrafts in their current living situation, the collection unit can also collect information about handicrafts. For example, the collection unit analyzes the elderly person's current living situation and areas of interest and collects information about handicrafts. Furthermore, if the elderly person frequently cooks in their current living situation, the collection unit can also collect information about cooking. For example, the collection unit analyzes the elderly person's current living situation and areas of interest and collects information about cooking. This allows more relevant information to be collected by filtering information based on the elderly person's current situation and interests. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input data on the elderly person's current living situation and areas of interest into a generation AI and perform filtering based on the information analyzed by the generation AI.

[0037] When collecting information, the collection unit can prioritize collecting highly relevant information by taking into account the geographical location information of the elderly person. For example, if the elderly person lives in an urban area, the collection unit collects information about hobbies and special skills in the urban area. For example, the collection unit analyzes the geographical location information of the elderly person and collects information about hobbies and special skills in the urban area. Furthermore, if the elderly person lives in a rural area, the collection unit can also collect information about hobbies and special skills in the rural area. For example, the collection unit analyzes the geographical location information of the elderly person and collects information about hobbies and special skills in the rural area. Furthermore, if the elderly person lives in a specific area, the collection unit can also collect information about hobbies and special skills related to that area. For example, the collection unit analyzes the geographical location information of the elderly person and collects information about hobbies and special skills related to that area. In this way, more relevant information can be collected by taking into account the geographical location information of the elderly person. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the geographical location information of the elderly person to a generation AI and collect information based on information analyzed by the generation AI.

[0038] When collecting information, the collection unit can analyze the social media activities of the elderly and collect related information. For example, the collection unit collects information about hobbies and special skills that the elderly frequently post on social media. For example, the collection unit analyzes the social media activities of the elderly and collects information about the hobbies and special skills that the elderly frequently post on. The collection unit can also collect information related to accounts that the elderly follows on social media. For example, the collection unit analyzes accounts that the elderly follows and collects information related to the accounts. Furthermore, the collection unit can also collect information related to communities that the elderly participate in on social media. For example, the collection unit analyzes communities that the elderly participate in and collects information related to the communities. This allows for analyzing the social media activities of the elderly to collect more relevant information. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the social media activity data of the elderly to a generation AI and collect information based on information analyzed by the generation AI.

[0039] During learning, the learning unit can adjust the level of detail of learning based on the importance of collected data. For example, the learning unit learns data with high importance in detail and data with low importance in simple terms. For example, the learning unit evaluates the importance of collected data and adjusts the level of detail of learning based on the evaluation. The learning unit can also prioritize learning of data with high importance and postpone learning of data with low importance. For example, the learning unit evaluates the importance of collected data and determines the priority of learning based on the evaluation. Furthermore, the learning unit can allocate more resources to data with high importance for learning. For example, the learning unit evaluates the importance of collected data and adjusts resource allocation based on the evaluation. In this way, adjusting the level of detail of learning based on the importance of the data enables efficient learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input the importance of collected data to a generation AI and adjust the level of detail of learning based on information analyzed by the generation AI.

[0040] During learning, the learning unit can apply different learning algorithms depending on the category of the hobby or special skill. For example, the learning unit applies an image recognition algorithm to data related to handicrafts. For example, the learning unit analyzes data related to handicrafts and applies an image recognition algorithm to learn. The learning unit can also apply a recipe analysis algorithm to data related to cooking. For example, the learning unit analyzes data related to cooking and applies a recipe analysis algorithm to learn. The learning unit can also apply an audio analysis algorithm to data related to musical performance. For example, the learning unit analyzes data related to musical performance and applies an audio analysis algorithm to learn. In this way, learning can be more effective by applying a learning algorithm depending on the category. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data according to the category of the hobby or special skill into a generation AI and apply different learning algorithms based on the information analyzed by the generation AI.

[0041] During learning, the learning unit can weight the learning data based on the time the collected data was submitted. For example, the learning unit weights recently collected data more heavily during learning. For example, the learning unit evaluates the time the collected data was submitted and weights the data based on the evaluation. The learning unit can also weight older data less heavily during learning. For example, the learning unit evaluates the time the collected data was submitted and weights the data based on the evaluation. Furthermore, the learning unit can dynamically adjust the weight of the data based on the time of submission. For example, the learning unit evaluates the time the collected data was submitted and weights the data based on the evaluation. This allows for more effective learning by weighting the data based on the time of submission. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input the time the collected data was submitted to the generation AI and weight the data based on the information analyzed by the generation AI.

[0042] During learning, the learning unit can adjust the learning order based on the relevance of the collected data. The learning unit, for example, prioritizes learning of highly relevant data. For example, the learning unit evaluates the relevance of the collected data and adjusts the learning order based on the evaluation. The learning unit can also postpone learning of less relevant data. For example, the learning unit evaluates the relevance of the collected data and adjusts the learning order based on the evaluation. Furthermore, the learning unit can dynamically adjust the learning order based on the relevance of the data. For example, the learning unit evaluates the relevance of the collected data and adjusts the learning order based on the evaluation. In this way, adjusting the learning order based on the relevance of the data enables more effective learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the relevance of the collected data to a generation AI and adjust the learning order based on the information analyzed by the generation AI.

[0043] The providing unit can adjust the level of detail of the lesson based on the importance of the hobby or special skill when providing the lesson. For example, the providing unit provides a detailed lesson for a hobby or special skill that is highly important. For example, the providing unit evaluates the importance of the hobby or special skill and adjusts the level of detail of the lesson based on the evaluation. The providing unit can also provide a simplified lesson for a hobby or special skill that is less important. For example, the providing unit evaluates the importance of the hobby or special skill and adjusts the level of detail of the lesson based on the evaluation. Furthermore, the providing unit can dynamically adjust the level of detail of the lesson based on the importance. For example, the providing unit evaluates the importance of the hobby or special skill and adjusts the level of detail of the lesson based on the evaluation. In this way, by adjusting the level of detail of the lesson based on the importance of the hobby or special skill, more effective lessons can be provided. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input importance data of the hobby or special skill into a generating AI and adjust the level of detail of the lesson based on information analyzed by the generating AI.

[0044] When providing lessons, the provision unit can apply different provision algorithms depending on the hobby or special skill category. For example, the provision unit applies an image recognition algorithm to handicraft lessons. For example, the provision unit analyzes data related to handicrafts and applies an image recognition algorithm to provide lessons. The provision unit can also apply a recipe analysis algorithm to cooking lessons. For example, the provision unit analyzes data related to cooking and applies a recipe analysis algorithm to provide lessons. The provision unit can also apply an audio analysis algorithm to music performance lessons. For example, the provision unit analyzes data related to music performance and applies an audio analysis algorithm to provide lessons. In this way, more effective lessons can be provided by applying a provision algorithm depending on the hobby or special skill category. Some or all of the above-mentioned processing by the provision unit may be performed using, for example, AI, or may be performed without using AI. For example, the provision unit can input data according to the hobby or special skill category into a generation AI and apply a different provision algorithm based on the information analyzed by the generation AI.

[0045] When providing lessons, the providing unit can determine the priority of lessons based on the time of submission of hobbies and special skills. For example, the providing unit can prioritize lessons for recently submitted hobbies and special skills. For example, the providing unit can evaluate the time of submission of hobbies and special skills and determine the priority of lessons based on the evaluation. The providing unit can also provide lessons for older hobbies and special skills at a later date. For example, the providing unit can evaluate the time of submission of hobbies and special skills and determine the priority of lessons based on the evaluation. Furthermore, the providing unit can dynamically adjust the priority of lessons based on the time of submission. For example, the providing unit can evaluate the time of submission of hobbies and special skills and determine the priority of lessons based on the evaluation. In this way, by determining the priority of lessons based on the time of submission of hobbies and special skills, more effective lessons can be provided. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the providing unit can input data on the time of submission of hobbies and special skills into a generating AI and determine the priority of lessons based on the information analyzed by the generating AI.

[0046] The provision unit can adjust the order of lessons based on the relevance of hobbies and special skills when providing lessons. For example, the provision unit can prioritize providing lessons for highly relevant hobbies and special skills. For example, the provision unit can evaluate the relevance of hobbies and special skills and adjust the order of lessons based on the evaluation. The provision unit can also postpone providing lessons for less relevant hobbies and special skills. For example, the provision unit can evaluate the relevance of hobbies and special skills and adjust the order of lessons based on the evaluation. Furthermore, the provision unit can dynamically adjust the order of lessons based on the relevance of hobbies and special skills. For example, the provision unit can evaluate the relevance of hobbies and special skills and adjust the order of lessons based on the evaluation. In this way, adjusting the order of lessons based on the relevance of hobbies and special skills can provide more effective lessons. Some or all of the above-described processing in the provision unit can be performed using, for example, AI, or can be performed without using AI. For example, the provision unit can input relevance data of hobbies and special skills into a generation AI and adjust the order of lessons based on information analyzed by the generation AI.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] The online cram school system can further include a feedback unit. The feedback unit collects impressions and opinions from users after taking a lesson and uses them to improve the lesson content. For example, the feedback unit can evaluate the user's level of understanding and satisfaction with the lesson by having the user answer a questionnaire after the lesson. The feedback unit can also allow the user to freely enter any difficulties or areas for improvement they encountered during the lesson. Furthermore, the feedback unit can analyze the user's feedback and automatically adjust the lesson content and progress of the AI ​​avatar. This makes it possible to provide more effective lessons that reflect the user's opinions.

[0049] The collection unit can further monitor the health condition of the elderly person and adjust the timing of information collection based on the health condition. For example, the collection unit can monitor the elderly person's blood pressure and heart rate and conduct interviews when the elderly person's health condition is good. The collection unit can also temporarily suspend information collection if the elderly person is tired and resume it after the elderly person has rested. Furthermore, the collection unit can change the method of information collection depending on the elderly person's health condition. For example, a face-to-face interview is conducted when the elderly person's health condition is good, and a telephone or online interview is conducted when the elderly person's health condition is poor. This makes it possible to collect information taking into account the elderly person's health condition.

[0050] The learning unit can also select learning data taking into account the cultural background of the elderly person. For example, if the elderly person has traditional handicrafts from a particular region, the learning unit will prioritize learning data related to the culture and history of that region. In addition, if the elderly person has a particular religion or faith, the learning unit can also learn data related to that religion or faith. Furthermore, if the elderly person speaks a particular language, the learning unit can also learn data related to that language. This makes it possible to develop an AI avatar with a deeper understanding based on the cultural background of the elderly person.

[0051] The providing unit can further adjust the format of the lesson according to the user's learning style. For example, the providing unit can provide a lesson that makes extensive use of illustrations and videos to a user who prefers visual learning. The providing unit can also provide a lesson that mainly uses audio commentary to a user who prefers auditory learning. Furthermore, the providing unit can provide a lesson in a workshop format that involves hands-on learning to a user who prefers practical learning. In this way, it is possible to provide the most suitable lesson according to the user's learning style.

[0052] The providing unit can further adjust the difficulty of the lesson according to the user's progress. For example, if the user has mastered basic handicraft techniques, the providing unit can teach more advanced techniques in the next lesson. Also, if the user is having difficulty with a particular lesson, the providing unit can simplify the content of that lesson and provide it again in an easier-to-understand format. Furthermore, the providing unit can monitor the user's progress in real time and adjust the content and speed of the lesson as necessary. This makes it possible to provide effective lessons that match the user's learning pace.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The collection department collects information about the hobbies and special skills of the elderly. The collection department collects information through interviews, questionnaires, audio recordings, videos, etc. For example, information can be collected about hobbies and special skills such as handicrafts, cooking, gardening, and playing music. Step 2: The learning unit learns the information collected by the collection unit. The learning unit analyzes the collected data and acquires knowledge about the elderly person's hobbies and special skills. For example, it can learn handicraft techniques, cooking recipes, gardening tips, etc. Step 3: The provision unit acts as an online cram school instructor based on the knowledge learned by the learning unit. The provision unit allows users to access an AI avatar through a smartphone app and provides lessons on hobbies and special skills. For example, in a handicraft lesson, the provision unit can explain the steps and show videos of the actual handicraft process. In a cooking lesson, the provision unit can explain the recipe and show videos of the cooking steps. Furthermore, in a gardening lesson, the provision unit can explain tips and show videos of the actual gardening process.

[0055] (Example 2) An online tutoring system according to an embodiment of the present invention uses an AI avatar to collect hobbies and special skills that seniors can teach to younger generations. This online tutoring system first collects information about seniors' hobbies and special skills. The AI ​​avatar then learns the collected information. Once the AI ​​avatar has completed the learning process, it acts as a tutor for the online tutoring system. Users can access the AI ​​avatar through a smartphone app and receive lessons on hobbies and special skills. This service allows seniors to pass on their knowledge and experience to younger generations, promoting intergenerational exchange. It also allows younger generations to learn new hobbies and special skills, promoting self-improvement. For example, information about seniors' hobbies and special skills is collected. Examples include handicrafts, cooking, gardening, and playing music. This information is collected through interviews, questionnaires, audio recordings, videos, and so on. The AI ​​avatar then learns the collected information. The AI ​​avatar analyzes the collected data and acquires knowledge about seniors' hobbies and special skills. For example, it learns handicraft techniques, cooking recipes, and gardening tips. Once the AI ​​avatar has completed its training, it will act as a teacher at an online cram school. Users can access the AI ​​avatar through a smartphone app and receive lessons on hobbies and special skills. For example, in a handicraft lesson, the AI ​​avatar will explain the steps and show a video of the actual handicraft being performed. In a cooking lesson, the AI ​​avatar will explain the recipe and show a video of the cooking steps. This service allows the knowledge and experience of the elderly to be passed on to the younger generation, promoting intergenerational exchange. It also allows the younger generation to learn new hobbies and special skills, helping them to grow. In this way, the online cram school system can pass on the knowledge and experience of the elderly to the younger generation, promoting intergenerational exchange. It also allows the younger generation to learn new hobbies and special skills, helping them to grow.

[0056] An online tutoring system according to an embodiment includes a collection unit, a learning unit, and a providing unit. The collection unit collects information about the hobbies and special skills of elderly people. The collection unit collects information through, for example, interviews, questionnaires, audio recordings, videos, etc. For example, the collection unit can collect information about elderly people's hobbies and special skills, such as handicrafts, cooking, gardening, and playing music. The collection unit can collect detailed information about elderly people's hobbies and special skills through, for example, interviews. The collection unit can also collect information about elderly people's hobbies and special skills through questionnaires. Furthermore, the collection unit can collect information about elderly people's hobbies and special skills through audio recordings and videos. The learning unit studies the information collected by the collection unit. For example, the learning unit analyzes the collected data to acquire knowledge about elderly people's hobbies and special skills. For example, the learning unit can learn handicraft techniques, cooking recipes, gardening tips, etc. For example, the learning unit can analyze the collected data to acquire handicraft techniques. The learning unit can also analyze the collected data to acquire cooking recipes. Furthermore, the learning unit can analyze the collected data and teach gardening tips. The providing unit acts as an instructor for an online cram school based on the knowledge learned by the learning unit. For example, the providing unit allows a user to access an AI avatar through a smartphone app and provides lessons on hobbies and special skills. For example, the providing unit can explain the steps in a handicraft lesson and show a video of the actual handicraft being performed. Furthermore, the providing unit can explain recipes in a cooking lesson and show a video of the cooking steps. Furthermore, the providing unit can explain tips in a gardening lesson and show a video of the actual gardening. In this way, the online cram school system according to the embodiment collects, learns, and provides information about the hobbies and special skills of the elderly, promoting intergenerational exchange and allowing younger generations to learn new hobbies and special skills. Some or all of the above-described processing by the providing unit may be performed using, or without, AI. For example, the providing unit can input the information collected by the collecting unit into a generation AI and provide lessons based on the knowledge learned by the generation AI.

[0057] The collection unit can collect information through interviews or questionnaires, audio recordings, and videos. For example, the collection unit can collect detailed information about the elderly's hobbies and special skills through interviews. For example, the collection unit can ask the elderly questions about their hobbies and special skills and record the responses. The collection unit can also collect information about the elderly's hobbies and special skills through questionnaires. For example, the collection unit can administer a questionnaire about the elderly's hobbies and special skills to the elderly and collect the responses. The collection unit can also collect information about the elderly's hobbies and special skills through audio recordings and videos. For example, the collection unit can audio or video record the elderly demonstrating their hobbies or special skills and collect the data. This allows for more accurate and extensive information to be obtained by collecting information in a variety of ways. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit can input interview or questionnaire response data into a generation AI and collect information analyzed by the generation AI.

[0058] The learning unit can analyze the collected data and acquire knowledge about the elderly person's hobbies and special skills. The learning unit can, for example, analyze the collected data and acquire handicraft techniques. For example, the learning unit can analyze the collected handicraft-related data and acquire handicraft techniques. The learning unit can also analyze the collected data and acquire cooking recipes. For example, the learning unit can analyze the collected cooking-related data and acquire cooking recipes. The learning unit can also analyze the collected data and acquire gardening tips. For example, the learning unit can analyze the collected gardening-related data and acquire gardening tips. In this way, by analyzing the collected data, the AI ​​avatar can accurately acquire knowledge about the elderly person's hobbies and special skills. Some or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can input the collected data into a generation AI and learn the information analyzed by the generation AI.

[0059] The providing unit allows a user to access an AI avatar through a smartphone app and provides lessons related to hobbies or special skills. For example, in a handicraft lesson, the providing unit can explain the steps and show a video of the handicraft being performed. For example, the providing unit can explain the steps of the handicraft in detail and show a video of the handicraft being performed according to the steps. In a cooking lesson, the providing unit can also explain a recipe and show a video of the cooking steps. For example, the providing unit can explain a cooking recipe in detail and show a video of the cooking being performed according to the recipe. In a gardening lesson, the providing unit can also explain tips and show a video of the gardening being performed. For example, the providing unit can explain gardening tips in detail and show a video of the gardening being performed according to the tips. This allows a user to easily access the AI ​​avatar through the smartphone app and receive lessons. Some or all of the above-mentioned processing by the providing unit may be performed using AI, for example, or without AI. For example, the providing unit can input information collected by the collecting unit into the generating AI and provide lessons based on the knowledge learned by the generating AI.

[0060] The providing unit can explain the steps in a handicraft lesson and show a video of how the handicraft is performed. For example, the providing unit can explain the steps of a handicraft in detail and show a video of how the handicraft is performed according to the steps. For example, the providing unit can explain basic steps of a handicraft and show a video of how the handicraft is performed according to the steps. The providing unit can also explain advanced steps of a handicraft and show a video of how the handicraft is performed according to the steps. For example, the providing unit can explain advanced steps of a handicraft and show a video of how the handicraft is performed according to the steps. The providing unit can also explain tips and points for a handicraft and show a video of how the handicraft is performed according to the tips and points. For example, the providing unit can explain tips and points for a handicraft and show a video of how the handicraft is performed according to the tips and points. In this way, showing handicraft lessons in video makes it easier for the user to visually understand. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input craft steps into the generating AI and provide lessons based on the steps generated by the generating AI.

[0061] In a cooking lesson, the providing unit can explain the recipe and show the cooking steps in a video. For example, the providing unit can explain the recipe in detail and show a video of how to cook according to the recipe. For example, the providing unit can explain a basic recipe and show a video of how to cook according to the recipe. The providing unit can also explain an advanced recipe and show a video of how to cook according to the recipe. For example, the providing unit can explain an advanced recipe and show a video of how to cook according to the recipe. The providing unit can also explain cooking tips and points and show a video of how to cook according to the tips and points. For example, the providing unit can explain cooking tips and points and show a video of how to cook according to the tips and points. In this way, showing cooking lessons in a video makes it easier for users to understand visually. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit can input a cooking recipe into a generation AI and provide a lesson based on the recipe generated by the generation AI.

[0062] The collection unit can estimate the elderly person's emotions and adjust the timing of information collection based on the estimated elderly person's emotions. For example, the collection unit estimates the time periods when the elderly person is relaxed and conducts interviews during those times. For example, the collection unit can analyze the elderly person's facial expressions and voice to identify the time periods when the elderly person is relaxed. Furthermore, the collection unit can temporarily suspend information collection if the elderly person is feeling stressed and resume it after the elderly person has relaxed. For example, the collection unit can monitor the elderly person's heart rate and electrodermal activity to determine whether the elderly person is feeling stressed. Furthermore, if the elderly person is excited, the collection unit can actively collect information by utilizing the elderly person's emotions. For example, the collection unit can analyze the elderly person's state of excitement and adjust the timing of information collection according to that state. This allows for more effective information collection by adjusting the timing of information collection according to the elderly person's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input emotional data of the elderly person into the generation AI and adjust the timing of information collection based on the information analyzed by the generation AI.

[0063] The collection unit can analyze the elderly person's past hobbies and special skills and select the optimal collection method. For example, if the elderly person has experience teaching handicrafts in the past, the collection unit can conduct a detailed interview about handicrafts. For example, the collection unit can analyze the elderly person's past activity records related to handicrafts and conduct an interview based on that information. Furthermore, if the elderly person has experience running cooking classes, the collection unit can also conduct a questionnaire about cooking. For example, the collection unit can analyze data about the elderly person's past cooking classes and create a questionnaire based on that information. Furthermore, if the elderly person has extensive experience playing music, the collection unit can also collect recorded data of the performances. For example, the collection unit can analyze data about the elderly person's past musical performances and collect recorded data based on that information. In this way, information can be collected in the optimal manner by analyzing the elderly person's past history. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without AI. For example, the collection unit can input the elderly person's past history data into a generation AI and select a collection method based on the information analyzed by the generation AI.

[0064] When collecting information, the collection unit can filter the information based on the elderly person's current living situation and areas of interest. For example, if the elderly person is currently interested in gardening, the collection unit prioritizes collecting information about gardening. For example, the collection unit analyzes the elderly person's current living situation and areas of interest and collects information about gardening. Furthermore, if the elderly person enjoys handicrafts in their current living situation, the collection unit can also collect information about handicrafts. For example, the collection unit analyzes the elderly person's current living situation and areas of interest and collects information about handicrafts. Furthermore, if the elderly person frequently cooks in their current living situation, the collection unit can also collect information about cooking. For example, the collection unit analyzes the elderly person's current living situation and areas of interest and collects information about cooking. This allows more relevant information to be collected by filtering information based on the elderly person's current situation and interests. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input data on the elderly person's current living situation and areas of interest into a generation AI and perform filtering based on the information analyzed by the generation AI.

[0065] The collection unit can estimate the elderly person's emotions and prioritize information to be collected based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the collection unit prioritizes collecting detailed information. For example, the collection unit analyzes the elderly person's facial expressions and voice to identify their relaxed state and prioritize information based on that state. Furthermore, if the elderly person is feeling stressed, the collection unit can start with simple questions and gradually collect more detailed information. For example, the collection unit monitors the elderly person's heart rate and electrodermal activity to determine whether they are feeling stressed and prioritize information based on that state. Furthermore, if the elderly person is excited, the collection unit can actively collect information by utilizing their emotions. For example, the collection unit analyzes the elderly person's state of excitement and prioritizes information based on that state. This allows for more effective information collection by prioritizing information based on the elderly person's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input emotional data of the elderly person into the generation AI and determine the priority of the information based on the information analyzed by the generation AI.

[0066] When collecting information, the collection unit can prioritize collecting highly relevant information by taking into account the geographical location information of the elderly person. For example, if the elderly person lives in an urban area, the collection unit collects information about hobbies and special skills in the urban area. For example, the collection unit analyzes the geographical location information of the elderly person and collects information about hobbies and special skills in the urban area. Furthermore, if the elderly person lives in a rural area, the collection unit can also collect information about hobbies and special skills in the rural area. For example, the collection unit analyzes the geographical location information of the elderly person and collects information about hobbies and special skills in the rural area. Furthermore, if the elderly person lives in a specific area, the collection unit can also collect information about hobbies and special skills related to that area. For example, the collection unit analyzes the geographical location information of the elderly person and collects information about hobbies and special skills related to that area. In this way, more relevant information can be collected by taking into account the geographical location information of the elderly person. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the geographical location information of the elderly person to a generation AI and collect information based on information analyzed by the generation AI.

[0067] When collecting information, the collection unit can analyze the social media activities of the elderly and collect related information. For example, the collection unit collects information about hobbies and special skills that the elderly frequently post on social media. For example, the collection unit analyzes the social media activities of the elderly and collects information about the hobbies and special skills that the elderly frequently post on. The collection unit can also collect information related to accounts that the elderly follows on social media. For example, the collection unit analyzes accounts that the elderly follows and collects information related to the accounts. Furthermore, the collection unit can also collect information related to communities that the elderly participate in on social media. For example, the collection unit analyzes communities that the elderly participate in and collects information related to the communities. This allows for analyzing the social media activities of the elderly to collect more relevant information. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the social media activity data of the elderly to a generation AI and collect information based on information analyzed by the generation AI.

[0068] The learning unit can estimate the elderly person's emotions and select training data based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the learning unit prioritizes learning detailed data. For example, the learning unit analyzes the elderly person's facial expressions and voice to identify their relaxed state and select training data according to that state. Furthermore, if the elderly person is stressed, the learning unit can start learning from simple data. For example, the learning unit monitors the elderly person's heart rate and electrodermal activity to determine whether they are stressed and select training data according to that state. Furthermore, if the elderly person is excited, the learning unit can actively learn data by using that emotion. For example, the learning unit analyzes the elderly person's excited state and selects training data according to that state. This allows for more effective learning by selecting training data based on the elderly person's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit may input emotional data of the elderly into the generation AI and select learning data based on the information analyzed by the generation AI.

[0069] During learning, the learning unit can adjust the level of detail of learning based on the importance of collected data. For example, the learning unit learns data with high importance in detail and data with low importance in simple terms. For example, the learning unit evaluates the importance of collected data and adjusts the level of detail of learning based on the evaluation. The learning unit can also prioritize learning of data with high importance and postpone learning of data with low importance. For example, the learning unit evaluates the importance of collected data and determines the priority of learning based on the evaluation. Furthermore, the learning unit can allocate more resources to data with high importance for learning. For example, the learning unit evaluates the importance of collected data and adjusts resource allocation based on the evaluation. In this way, adjusting the level of detail of learning based on the importance of the data enables efficient learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input the importance of collected data to a generation AI and adjust the level of detail of learning based on information analyzed by the generation AI.

[0070] During learning, the learning unit can apply different learning algorithms depending on the category of the hobby or special skill. For example, the learning unit applies an image recognition algorithm to data related to handicrafts. For example, the learning unit analyzes data related to handicrafts and applies an image recognition algorithm to learn. The learning unit can also apply a recipe analysis algorithm to data related to cooking. For example, the learning unit analyzes data related to cooking and applies a recipe analysis algorithm to learn. The learning unit can also apply an audio analysis algorithm to data related to musical performance. For example, the learning unit analyzes data related to musical performance and applies an audio analysis algorithm to learn. In this way, learning can be more effective by applying a learning algorithm depending on the category. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data according to the category of the hobby or special skill into a generation AI and apply different learning algorithms based on the information analyzed by the generation AI.

[0071] The learning unit can estimate the elderly person's emotions and adjust the frequency of learning based on the estimated elderly person's emotions. For example, the learning unit increases the frequency of learning when the elderly person is relaxed. For example, the learning unit analyzes the elderly person's facial expressions and voice to identify a relaxed state and adjust the frequency of learning according to that state. The learning unit can also decrease the frequency of learning when the elderly person is stressed. For example, the learning unit monitors the elderly person's heart rate and electrodermal activity to determine whether the elderly person is stressed and adjusts the frequency of learning according to that state. Furthermore, the learning unit can adjust the frequency of learning based on the elderly person's emotions when the elderly person is excited. For example, the learning unit analyzes the elderly person's excited state and adjusts the frequency of learning according to that state. This allows for more effective learning by adjusting the frequency of learning based on the elderly person's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit may input emotional data of the elderly person into the generation AI and adjust the frequency of learning based on the information analyzed by the generation AI.

[0072] During learning, the learning unit can weight the learning data based on the time the collected data was submitted. For example, the learning unit weights recently collected data more heavily during learning. For example, the learning unit evaluates the time the collected data was submitted and weights the data based on the evaluation. The learning unit can also weight older data less heavily during learning. For example, the learning unit evaluates the time the collected data was submitted and weights the data based on the evaluation. Furthermore, the learning unit can dynamically adjust the weight of the data based on the time of submission. For example, the learning unit evaluates the time the collected data was submitted and weights the data based on the evaluation. This allows for more effective learning by weighting the data based on the time of submission. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input the time the collected data was submitted to the generation AI and weight the data based on the information analyzed by the generation AI.

[0073] During learning, the learning unit can adjust the learning order based on the relevance of the collected data. The learning unit, for example, prioritizes learning of highly relevant data. For example, the learning unit evaluates the relevance of the collected data and adjusts the learning order based on the evaluation. The learning unit can also postpone learning of less relevant data. For example, the learning unit evaluates the relevance of the collected data and adjusts the learning order based on the evaluation. Furthermore, the learning unit can dynamically adjust the learning order based on the relevance of the data. For example, the learning unit evaluates the relevance of the collected data and adjusts the learning order based on the evaluation. In this way, adjusting the learning order based on the relevance of the data enables more effective learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the relevance of the collected data to a generation AI and adjust the learning order based on the information analyzed by the generation AI.

[0074] The providing unit can estimate the user's emotions and adjust the presentation of the lesson based on the estimated user's emotions. For example, if the user is relaxed, the providing unit proceeds with the lesson at a leisurely pace. For example, the providing unit analyzes the user's facial expressions and voice to identify the user's relaxed state and adjusts the presentation of the lesson according to that state. Furthermore, if the user is in a hurry, the providing unit can provide a short lesson that focuses on the main points. For example, the providing unit monitors the user's heart rate and electrodermal activity to determine whether the user is in a hurry and adjusts the presentation of the lesson according to that state. Furthermore, if the user is excited, the providing unit can provide a lesson that adds visually stimulating effects by utilizing the user's excitement. For example, the providing unit analyzes the user's state of excitement and adjusts the presentation of the lesson according to that state. This allows for more effective lessons by adjusting the presentation of the lesson according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input user emotional data into the generating AI and adjust the way the lesson is presented based on the information analyzed by the generating AI.

[0075] The providing unit can adjust the level of detail of the lesson based on the importance of the hobby or special skill when providing the lesson. For example, the providing unit provides a detailed lesson for a hobby or special skill that is highly important. For example, the providing unit evaluates the importance of the hobby or special skill and adjusts the level of detail of the lesson based on the evaluation. The providing unit can also provide a simplified lesson for a hobby or special skill that is less important. For example, the providing unit evaluates the importance of the hobby or special skill and adjusts the level of detail of the lesson based on the evaluation. Furthermore, the providing unit can dynamically adjust the level of detail of the lesson based on the importance. For example, the providing unit evaluates the importance of the hobby or special skill and adjusts the level of detail of the lesson based on the evaluation. In this way, by adjusting the level of detail of the lesson based on the importance of the hobby or special skill, more effective lessons can be provided. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input importance data of the hobby or special skill into a generating AI and adjust the level of detail of the lesson based on information analyzed by the generating AI.

[0076] When providing lessons, the provision unit can apply different provision algorithms depending on the hobby or special skill category. For example, the provision unit applies an image recognition algorithm to handicraft lessons. For example, the provision unit analyzes data related to handicrafts and applies an image recognition algorithm to provide lessons. The provision unit can also apply a recipe analysis algorithm to cooking lessons. For example, the provision unit analyzes data related to cooking and applies a recipe analysis algorithm to provide lessons. The provision unit can also apply an audio analysis algorithm to music performance lessons. For example, the provision unit analyzes data related to music performance and applies an audio analysis algorithm to provide lessons. In this way, more effective lessons can be provided by applying a provision algorithm depending on the hobby or special skill category. Some or all of the above-mentioned processing by the provision unit may be performed using, for example, AI, or may be performed without using AI. For example, the provision unit can input data according to the hobby or special skill category into a generation AI and apply a different provision algorithm based on the information analyzed by the generation AI.

[0077] The providing unit can estimate the user's emotions and adjust the length of the lesson based on the estimated user emotions. For example, if the user is relaxed, the providing unit provides a longer lesson. For example, the providing unit analyzes the user's facial expressions and voice to identify a relaxed state and adjust the length of the lesson according to that state. The providing unit can also provide a shorter lesson if the user is in a hurry. For example, the providing unit monitors the user's heart rate and electrodermal activity to determine whether the user is in a hurry and adjust the length of the lesson according to that state. Furthermore, if the user is excited, the providing unit can adjust the length of the lesson using that emotion. For example, the providing unit analyzes the user's excited state and adjusts the length of the lesson according to that state. This allows for more effective lesson provision by adjusting the length of the lesson according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input the user's emotional data into the generating AI and adjust the length of the lesson based on the information analyzed by the generating AI.

[0078] When providing lessons, the providing unit can determine the priority of lessons based on the time of submission of hobbies and special skills. For example, the providing unit can prioritize lessons for recently submitted hobbies and special skills. For example, the providing unit can evaluate the time of submission of hobbies and special skills and determine the priority of lessons based on the evaluation. The providing unit can also provide lessons for older hobbies and special skills at a later date. For example, the providing unit can evaluate the time of submission of hobbies and special skills and determine the priority of lessons based on the evaluation. Furthermore, the providing unit can dynamically adjust the priority of lessons based on the time of submission. For example, the providing unit can evaluate the time of submission of hobbies and special skills and determine the priority of lessons based on the evaluation. In this way, by determining the priority of lessons based on the time of submission of hobbies and special skills, more effective lessons can be provided. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the providing unit can input data on the time of submission of hobbies and special skills into a generating AI and determine the priority of lessons based on the information analyzed by the generating AI.

[0079] The provision unit can adjust the order of lessons based on the relevance of hobbies and special skills when providing lessons. For example, the provision unit can prioritize providing lessons for highly relevant hobbies and special skills. For example, the provision unit can evaluate the relevance of hobbies and special skills and adjust the order of lessons based on the evaluation. The provision unit can also postpone providing lessons for less relevant hobbies and special skills. For example, the provision unit can evaluate the relevance of hobbies and special skills and adjust the order of lessons based on the evaluation. Furthermore, the provision unit can dynamically adjust the order of lessons based on the relevance of hobbies and special skills. For example, the provision unit can evaluate the relevance of hobbies and special skills and adjust the order of lessons based on the evaluation. In this way, adjusting the order of lessons based on the relevance of hobbies and special skills can provide more effective lessons. Some or all of the above-described processing in the provision unit can be performed using, for example, AI, or can be performed without using AI. For example, the provision unit can input relevance data of hobbies and special skills into a generation AI and adjust the order of lessons based on information analyzed by the generation AI. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, learning unit, and providing unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects information on the elderly person's hobbies and special skills using the camera 42 and microphone 38B of the smart device 14. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to acquire knowledge on the elderly person's hobbies and special skills. The providing unit is realized, for example, by the control unit 46A of the smart device 14, and provides lessons on hobbies and special skills to the user, who accesses an AI avatar through a smartphone app. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, learning unit, and providing unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects information on the elderly person's hobbies and special skills using the camera 42 and microphone 238 of the smart glasses 214. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to acquire knowledge on the elderly person's hobbies and special skills. The providing unit is realized, for example, by the control unit 46A of the smart glasses 214, and allows the user to access an AI avatar through a smartphone app and provides lessons on the hobbies and special skills. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, learning unit, and providing unit described above is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit collects information on the hobbies and special skills of the elderly person using the camera 42 and microphone 238 of the headset terminal 314. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to acquire knowledge on the hobbies and special skills of the elderly person. The providing unit is realized, for example, by the control unit 46A of the headset terminal 314, and provides lessons on hobbies and special skills to the user by allowing the user to access an AI avatar through a smartphone app. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, learning unit, and providing unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects information on the elderly person's hobbies and special skills using the camera 42 and microphone 238 of the robot 414. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data to acquire knowledge on the elderly person's hobbies and special skills. The providing unit is realized, for example, by the control unit 46A of the robot 414, and provides lessons on hobbies and special skills to the user by allowing the user to access an AI avatar through a smartphone app.

[0080] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0081] The online cram school system can further include a feedback unit. The feedback unit collects impressions and opinions from users after taking a lesson and uses them to improve the lesson content. For example, the feedback unit can evaluate the user's level of understanding and satisfaction with the lesson by having the user answer a questionnaire after the lesson. The feedback unit can also allow the user to freely enter any difficulties or areas for improvement they encountered during the lesson. Furthermore, the feedback unit can analyze the user's feedback and automatically adjust the lesson content and progress of the AI ​​avatar. This makes it possible to provide more effective lessons that reflect the user's opinions.

[0082] The collection unit can further monitor the health condition of the elderly person and adjust the timing of information collection based on the health condition. For example, the collection unit can monitor the elderly person's blood pressure and heart rate and conduct interviews when the elderly person's health condition is good. The collection unit can also temporarily suspend information collection if the elderly person is tired and resume it after the elderly person has rested. Furthermore, the collection unit can change the method of information collection depending on the elderly person's health condition. For example, a face-to-face interview is conducted when the elderly person's health condition is good, and a telephone or online interview is conducted when the elderly person's health condition is poor. This makes it possible to collect information taking into account the elderly person's health condition.

[0083] The learning unit can also select learning data taking into account the cultural background of the elderly person. For example, if the elderly person has traditional handicrafts from a particular region, the learning unit will prioritize learning data related to the culture and history of that region. In addition, if the elderly person has a particular religion or faith, the learning unit can also learn data related to that religion or faith. Furthermore, if the elderly person speaks a particular language, the learning unit can also learn data related to that language. This makes it possible to develop an AI avatar with a deeper understanding based on the cultural background of the elderly person.

[0084] The providing unit can further adjust the format of the lesson according to the user's learning style. For example, the providing unit can provide a lesson that makes extensive use of illustrations and videos to a user who prefers visual learning. The providing unit can also provide a lesson that mainly uses audio commentary to a user who prefers auditory learning. Furthermore, the providing unit can provide a lesson in a workshop format that involves hands-on learning to a user who prefers practical learning. In this way, it is possible to provide the most suitable lesson according to the user's learning style.

[0085] The providing unit can further adjust the difficulty of the lesson according to the user's progress. For example, if the user has mastered basic handicraft techniques, the providing unit can teach more advanced techniques in the next lesson. Also, if the user is having difficulty with a particular lesson, the providing unit can simplify the content of that lesson and provide it again in an easier-to-understand format. Furthermore, the providing unit can monitor the user's progress in real time and adjust the content and speed of the lesson as necessary. This makes it possible to provide effective lessons that match the user's learning pace.

[0086] The collection unit can estimate the elderly person's emotions and determine the priority of information to be collected based on the estimated elderly person's emotions. For example, the collection unit prioritizes collecting detailed information when the elderly person is relaxed. For example, the collection unit analyzes the elderly person's facial expressions and voice to identify a relaxed state and determine the priority of information based on that state. Furthermore, when the elderly person is feeling stressed, the collection unit can start by asking simple questions and gradually collect more detailed information. For example, the collection unit monitors the elderly person's heart rate and electrodermal activity to determine whether the elderly person is feeling stressed and determine the priority of information based on that state. Furthermore, when the elderly person is excited, the collection unit can actively collect information by utilizing the elderly person's emotions. For example, the collection unit analyzes the excited state of the elderly person and determines the priority of information based on that state. In this way, information can be collected more effectively by determining the priority of information based on the elderly person's emotions.

[0087] The learning unit can estimate the elderly person's emotions and select learning data based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the learning unit prioritizes learning detailed data. For example, the learning unit analyzes the elderly person's facial expressions and voice to identify a relaxed state and selects learning data according to that state. In addition, if the elderly person is feeling stressed, the learning unit can start learning from simple data. For example, the learning unit monitors the elderly person's heart rate and electrodermal activity to determine whether the elderly person is feeling stressed and selects learning data according to that state. Furthermore, if the elderly person is excited, the learning unit can actively learn data using that emotion. For example, the learning unit analyzes the elderly person's excited state and selects learning data according to that state. In this way, by selecting learning data based on the elderly person's emotions, learning can be performed more effectively.

[0088] The providing unit can estimate the user's emotions and adjust the presentation of the lesson based on the estimated user's emotions. For example, if the user is relaxed, the providing unit proceeds with the lesson at a leisurely pace. For example, the providing unit analyzes the user's facial expressions and voice to identify the user's relaxed state and adjusts the presentation of the lesson according to the state. Furthermore, if the user is in a hurry, the providing unit can provide a short lesson that focuses on the main points. For example, the providing unit monitors the user's heart rate and electrodermal activity to determine whether the user is in a hurry and adjusts the presentation of the lesson according to the state. Furthermore, if the user is excited, the providing unit can provide a lesson that adds visually stimulating effects by utilizing the user's emotions. For example, the providing unit analyzes the user's excited state and adjusts the presentation of the lesson according to the state. In this way, more effective lessons can be provided by adjusting the presentation of the lesson according to the user's emotions.

[0089] The providing unit can estimate the user's emotions and adjust the length of the lesson based on the estimated user's emotions. For example, the providing unit can provide a longer lesson if the user is relaxed. For example, the providing unit can analyze the user's facial expressions and voice to identify a relaxed state and adjust the length of the lesson according to that state. The providing unit can also provide a shorter lesson if the user is in a hurry. For example, the providing unit can monitor the user's heart rate and electrodermal activity to determine whether the user is in a hurry and adjust the length of the lesson according to that state. Furthermore, the providing unit can adjust the length of the lesson based on the user's emotions if the user is excited. For example, the providing unit can analyze the user's excited state and adjust the length of the lesson according to that state. In this way, more effective lessons can be provided by adjusting the length of the lesson according to the user's emotions.

[0090] The providing unit can estimate the user's emotions and customize the lesson content based on the estimated user's emotions. For example, if the user is relaxed, the providing unit can provide content that can be enjoyed in a relaxed state. For example, the providing unit can analyze the user's facial expressions and voice to identify the user's relaxed state and customize the lesson content according to that state. Furthermore, if the user is feeling stressed, the providing unit can provide content to reduce stress. For example, the providing unit can monitor the user's heart rate and electrodermal activity to determine whether the user is feeling stressed and customize the lesson content according to that state. Furthermore, if the user is excited, the providing unit can use that emotion to provide energetic content. For example, the providing unit can analyze the user's excited state and customize the lesson content according to that state. In this way, more effective lessons can be provided by customizing the lesson content according to the user's emotions.

[0091] The processing flow of the second embodiment will be briefly explained below.

[0092] Step 1: The collection department collects information about the hobbies and special skills of the elderly. The collection department collects information through interviews, questionnaires, audio recordings, videos, etc. For example, information can be collected about hobbies and special skills such as handicrafts, cooking, gardening, and playing music. Step 2: The learning unit learns the information collected by the collection unit. The learning unit analyzes the collected data and acquires knowledge about the elderly person's hobbies and special skills. For example, it can learn handicraft techniques, cooking recipes, gardening tips, etc. Step 3: The provision unit acts as an online cram school instructor based on the knowledge learned by the learning unit. The provision unit allows users to access an AI avatar through a smartphone app and provides lessons on hobbies and special skills. For example, in a handicraft lesson, the provision unit can explain the steps and show videos of the actual handicraft process. In a cooking lesson, the provision unit can explain the recipe and show videos of the cooking steps. Furthermore, in a gardening lesson, the provision unit can explain tips and show videos of the actual gardening process.

[0093] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0094] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0095] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0096] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0097] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0098] 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.

[0099] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0100] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0101] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0102] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0103] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0104] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0105] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0106] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0107] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0108] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0111] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0112] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0115] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0116] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0117] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0119] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0120] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0121] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0123] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0124] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0125] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0127] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0130] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0132] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0133] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0135] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0136] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0137] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0140] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0142] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0144] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0146] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0147] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0148] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0149] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0150] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0151] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0152] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0153] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0154] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0155] 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.

[0156] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0157] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0158] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0159] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0160] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0161] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0162] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0163] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0164] [Explanation of symbols]

[0165] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. The system comprises a collection unit that collects information on the hobbies and special skills of elderly people, a learning unit that learns the collected information, and a providing unit that acts as a lecturer at an online cram school based on the learned knowledge.

2. The system of claim 1 , wherein the collection unit collects information through interviews or questionnaires, audio recordings, and videos.

3. The learning unit Analyze the collected data and gain knowledge about the hobbies and special skills of the elderly.

2. The system of claim 1.

4. The providing unit Users access an AI avatar through a smartphone app and receive lessons on hobbies and special skills.

2. The system of claim 1.

5. The system according to claim 1 , wherein the providing unit explains the steps in the handicraft lesson and shows a video of how to perform the handicraft.

6. The system according to claim 1 , wherein the providing unit explains recipes in cooking lessons and shows cooking procedures in the form of videos.

7. The collecting unit Estimate the emotions of the elderly and adjust the timing of information collection based on the estimated emotions of the elderly.

2. The system of claim 1.

8. The system according to claim 1, wherein the collection unit analyzes the history of the elderly person's past hobbies and special skills and selects an appropriate collection method.

Images