system

Abstract

The system according to the embodiment aims to teach table manners one-on-one at low cost. [Solution] A system according to an embodiment includes an observation unit, a customization unit, and a recording unit. The observation unit observes a user's eating habits. The customization unit provides lessons in expressions that match the user's preferences based on data observed by the observation unit. The recording unit records the progress of the lessons provided by the customization unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, learning table manners was expensive and there were few one-on-one lessons available.

[0005] The system according to the embodiment aims to teach table manners one-on-one at low cost. [Means for solving the problem]

[0006] The system according to the embodiment includes an observation unit, a customization unit, and a recording unit. The observation unit observes the user's eating habits. The customization unit provides lessons in expressions that match the user's preferences based on the data observed by the observation unit. The recording unit records the progress of the lessons provided by the customization unit. [Effects of the Invention]

[0007] The system according to the embodiment allows people to learn table manners one-on-one at low cost. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A table manners learning system according to an embodiment of the present invention observes a user's eating habits, provides lessons using expressions tailored to the user's preferences, and records the user's progress. This system uses an agent equipped with a large-scale language model (LLM) that has learned table manners as a teacher, allowing users to receive one-on-one lessons at low cost. The agent observes the user's eating habits and provides lessons using expressions tailored to the user's preferences. For example, if a user is struggling with how to use a fork, the agent can provide specific advice and demonstrate the correct usage. The agent also records the user's progress and reflects it in the next lesson, supporting continuous learning. This facilitates the acquisition of table manners and improves consideration for the user during mealtimes. For example, the system may include an observation unit equipped with a camera or sensor to observe the user's eating habits. The observation unit records the user's behavior in real time. Next, a customization unit is provided to provide lessons using expressions tailored to the user's preferences. The customization unit adjusts the lesson content based on the user's past data and preferences. Furthermore, a recording unit is provided to record the user's progress and reflect it in the next lesson. This recording unit saves the user's learning history and uses it for the next lesson. This allows the user to continue learning table manners and improve consideration at mealtimes. The table manners learning system observes the user's eating habits, provides lessons that suit their preferences, and records their progress, allowing for continuous learning of table manners.

[0029] The table manners training system according to the embodiment includes an observation unit, a customization unit, and a recording unit. The observation unit observes a user's eating habits. The observation unit records the user's eating habits in real time using, for example, a camera or a sensor. The observation unit, for example, uses a camera to capture footage of the user's eating habits and analyzes the video data. The observation unit can also detect the user's movements using a sensor and record the data. For example, the observation unit can detect the user's hand movements using an infrared sensor and record the data. The customization unit provides lessons using expressions that match the user's preferences based on the data observed by the observation unit. The customization unit, for example, adjusts the content of the lessons based on the user's past data and preferences. For example, the customization unit can refer to the user's past lesson history and focus lessons on areas in which the user is weak. The customization unit can also adjust the way the lessons are presented based on the user's preferences. For example, if a user is having trouble using a fork, the customization unit can provide specific advice and demonstrate the correct way to use it. The recording unit records the progress of the lessons provided by the customization unit. The recording unit, for example, saves the user's learning history and uses it for the next lesson. The recording unit, for example, records the user's lesson content and achievement level and reflects that data in the next lesson. The recording unit can also record the user's progress in real time to support continuous learning. For example, the recording unit records the user's study time and level of learning and adjusts the content of the next lesson based on that data. As a result, the table manners acquisition system according to the embodiment observes the user's eating habits, provides lessons that suit their preferences, and records their progress, enabling continuous acquisition of table manners.

[0030] The observation unit can record the user's eating habits in real time using a camera or a sensor. For example, the observation unit can use a camera to capture the user's eating habits and analyze the video data. For example, the observation unit can use a webcam to capture the user's eating habits and analyze the video data in real time. The observation unit can also use a sensor to detect the user's movements and record the data. For example, the observation unit can use an infrared sensor to detect the user's hand movements and record the data. Furthermore, the observation unit can combine multiple cameras and sensors to record the user's eating habits in detail. For example, the observation unit can use multiple cameras to capture the user's eating habits from different angles and integrate and analyze the video data. In this way, the use of cameras and sensors can accurately observe and record the user's eating habits. Some or all of the above-mentioned processing in the observation unit can be performed using, for example, AI, or without AI. For example, the observation unit can input video data acquired by a camera into a generation AI and have the generation AI analyze the video data.

[0031] The customization unit can adjust the lesson content based on the user's past data or preferences. For example, the customization unit may refer to the user's past lesson history and focus lessons on areas in which the user is weak. For example, if the customization unit analyzes the user's past lesson history and the user is struggling with how to use a fork, the customization unit may focus lessons on how to use a fork. The customization unit can also adjust the presentation of the lesson based on the user's preferences. For example, if the user prefers visual presentation, the customization unit may use visual animations or illustrations to provide lessons. The customization unit can also adjust the lesson content based on user feedback. For example, the customization unit may analyze feedback provided by the user after a lesson and improve the content of the next lesson. This allows for more effective lessons by adjusting the lesson content based on the user's past data and preferences. Some or all of the above-described processing in the customization unit may be performed using, for example, AI, or may be performed without AI. For example, the customization unit may input the user's past data into a generation AI and have the generation AI adjust the lesson content.

[0032] The recording unit can save the user's learning history and use it for the next lesson. The recording unit, for example, records the user's lesson content and achievement level and reflects the data in the next lesson. For example, the recording unit can record the user's lesson content in detail and use that content in the next lesson. The recording unit can also record the user's progress in real time to support continuous learning. For example, the recording unit can record the user's learning time and level of mastery and adjust the next lesson content based on that data. Furthermore, the recording unit can record the user's feedback and reflect that data in the next lesson. For example, the recording unit can record feedback provided by the user after a lesson and improve the next lesson content based on that feedback. This enables continuous learning by saving the user's learning history and using it in the next lesson. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or without AI. For example, the recording unit can input the user's learning history into a generation AI and have the generation AI adjust the next lesson content.

[0033] If a user is having trouble using a fork, the customization unit can provide detailed advice and show them how to use it correctly. For example, if a user is having trouble using a fork, the customization unit can provide specific advice and show them how to use it correctly. For example, the customization unit can provide detailed instructions on how to hold a fork and the steps for using it. Furthermore, if a user is making a common mistake, the customization unit can point out the mistake and show them how to use it correctly. For example, if a user is holding a fork in the wrong hand, the customization unit can point out how to hold it and show them the correct way to hold it. Furthermore, the customization unit can record the user's progress and reflect this in the next lesson. For example, the customization unit can record the user's progress until they have mastered how to use a fork and adjust the content of the next lesson based on that data. In this way, if a user is having trouble using a fork, specific advice can be provided to help them master the correct way to use it. Some or all of the above-described processing in the customization unit may be performed using, for example, AI, or may be performed without AI. For example, the customization unit can input data regarding the user's use of the fork into a generation AI and cause the generation AI to provide specific advice.

[0034] The recording unit can record the user's progress and reflect it in the next lesson. For example, the recording unit can record the user's progress in real time and reflect the data in the next lesson. For example, the recording unit can record the user's study time and level of mastery and adjust the content of the next lesson based on that data. The recording unit can also record the user's feedback and reflect that data in the next lesson. For example, the recording unit can record feedback provided by the user after a lesson and improve the content of the next lesson based on that feedback. Furthermore, the recording unit can save the user's learning history and support continuous learning. For example, the recording unit can record the user's past lesson content and achievement level and adjust the content of the next lesson based on that data. This enables continuous learning by recording the user's progress and reflecting it in the next lesson. Some or all of the above-mentioned processing in the recording unit can be performed using, for example, AI, or without AI. For example, the recording unit can input the user's progress data into a generation AI and cause the generation AI to adjust the content of the next lesson.

[0035] The observation unit can analyze the user's past eating behavior and select an appropriate observation method. For example, if the user has previously preferred a particular eating style, the observation unit selects an observation method that matches that style. For example, if the observation unit analyzes the user's past eating behavior data and the user prefers Japanese food, the observation unit selects an observation method that matches that style. Furthermore, if the user has previously eaten at a particular time of day, the observation unit can select an observation method that matches that time of day. For example, the observation unit analyzes the user's past mealtime data and selects an observation method that matches the user's preference for evening meals if the user often eats at night. Furthermore, if the user has previously eaten in a particular dining environment, the observation unit can select an observation method that matches that environment. For example, the observation unit analyzes the user's past eating environment data and selects an observation method that matches the user's preference for restaurants if the user often eats at restaurants. This enables more effective observation by selecting an optimal observation method based on the user's past eating behavior. Some or all of the above-described processing by the observation unit may be performed using, for example, AI, or without AI. For example, the observation unit can input the user's past eating behavior data into the generation AI and have the generation AI select an observation method.

[0036] During observation, the observation unit can perform filtering based on the user's current eating environment and situation. For example, if the user is eating in a quiet environment, the observation unit filters and observes the audio data. For example, if the user's eating environment is quiet, the observation unit removes background noise and analyzes the audio data. Furthermore, if the user is eating in a bright environment, the observation unit can also filter and observe the video data. For example, if the user's eating environment is bright, the observation unit adjusts the brightness of the video data and analyzes it. Furthermore, if the user is eating in a crowded environment, the observation unit can also remove noise and observe the video data. For example, if the user's eating environment is crowded, the observation unit removes background noise and analyzes the audio data. This allows for more accurate data collection by filtering based on the user's current eating environment and situation. Some or all of the above-described processing in the observation unit may be performed using, or without, AI. For example, the observation unit can input the user's eating environment data into the generation AI and have the generation AI adjust the filtering.

[0037] During observation, the observation unit can prioritize observing highly relevant data by taking into account the user's geographical location information. For example, if the user is eating in a specific area, the observation unit prioritizes observing data related to the manners of that area. For example, the observation unit prioritizes collecting data related to the dining manners of that area based on the user's geographical location information. Furthermore, if the user is traveling, the observation unit can prioritize observing data related to the manners of the travel destination. For example, the observation unit prioritizes collecting data related to the dining manners of the travel destination based on the user's geographical location information. Furthermore, if the user is eating at home, the observation unit can prioritize observing data related to household manners. For example, the observation unit prioritizes collecting data related to household dining manners based on the user's geographical location information. In this way, highly relevant data can be prioritized by taking the user's geographical location information into account. Some or all of the above-described processing by the observation unit may be performed using AI, for example, or without AI. For example, the observation unit can input the user's geographical location information to the generation AI and cause the generation AI to perform prioritized observation of highly relevant data.

[0038] During observation, the observation unit can analyze the user's social media activity and observe related behavior. The observation unit, for example, observes dining etiquette based on photos of food shared by the user on social media. For example, the observation unit analyzes the user's social media posts and observes dining etiquette based on the shared photos of food. The observation unit can also observe dining etiquette based on information about restaurants mentioned by the user on social media. For example, the observation unit analyzes the user's social media posts and observes dining etiquette based on the mentioned restaurant information. The observation unit can also observe dining etiquette based on food-related accounts the user follows on social media. For example, the observation unit analyzes the accounts the user follows and observes dining etiquette based on the food-related accounts. In this way, related behavior can be observed by analyzing the user's social media activity. Some or all of the above-described processing by the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input the user's social media data into the generation AI and cause the generation AI to observe related behavior.

[0039] When customizing the lesson content, the customization unit can adjust the level of detail based on the user's level of importance. For example, the customization unit provides a detailed explanation of etiquette items that the user considers particularly important. For example, the customization unit analyzes the user's past lesson history and provides a detailed explanation of etiquette items that the user considers particularly important. The customization unit can also provide a concise explanation of etiquette items that the user considers less important. For example, the customization unit can provide a concise explanation of etiquette items that the user considers less important based on user feedback. Furthermore, the customization unit can also provide a focused explanation of etiquette items that the user has previously struggled with. For example, the customization unit analyzes the user's past lesson history and provides a focused explanation of etiquette items that the user has struggled with. This allows for more effective lessons by adjusting the level of detail of the lesson content based on the user's level of importance. Some or all of the above-described processing by the customization unit may be performed using, or without, AI. For example, the customization unit can input the user's level of importance data into a generation AI and cause the generation AI to adjust the level of detail of the lesson content.

[0040] When customizing the lesson content, the customization unit can apply different algorithms depending on the user's category. For example, if the user is a beginner, the customization unit applies an algorithm that provides lessons focusing on basic etiquette items. For example, the customization unit analyzes the user's category and applies an algorithm that provides lessons focusing on basic etiquette items suitable for beginners. Furthermore, if the user is an intermediate user, the customization unit can also apply an algorithm that provides lessons focusing on advanced etiquette items. For example, the customization unit analyzes the user's category and applies an algorithm that provides lessons focusing on advanced etiquette items suitable for intermediate users. Furthermore, if the user is an advanced user, the customization unit can also apply an algorithm that provides lessons focusing on specialized etiquette items. For example, the customization unit analyzes the user's category and applies an algorithm that provides lessons focusing on specialized etiquette items suitable for advanced users. This enables more effective lessons by applying different algorithms depending on the user's category. Some or all of the above-described processing in the customization unit may be performed using, or without, AI. For example, the customization unit can input user category data into a generation AI and cause the generation AI to apply a lesson algorithm.

[0041] When customizing lesson content, the customization unit can determine priorities based on the user's submission time. For example, if the user submits early, the customization unit can prioritize lessons. For example, the customization unit can analyze the user's submission time and prioritize customizing lesson content submitted early. The customization unit can also quickly customize lesson content submitted close to the deadline if the user submits close to the deadline. For example, the customization unit can analyze the user's submission time and quickly customize lesson content submitted close to the deadline. Furthermore, the customization unit can reflect the changes in the next lesson if the user misses the submission deadline. For example, the customization unit can analyze the user's submission time and reflect lesson content that has passed the submission deadline in the next lesson. This enables more effective lessons by determining priorities based on the user's submission time. Some or all of the above-described processing in the customization unit can be performed using, or without, AI. For example, the customization unit can input user submission time data into the generation AI and cause the generation AI to determine the priority of lesson content.

[0042] When customizing the lesson content, the customization unit can adjust the order based on the user's relevance. For example, the customization unit prioritizes lessons related to content the user has previously learned. For example, the customization unit analyzes the user's past lesson history and prioritizes lessons related to the content. The customization unit can also prioritize lessons related to content the user is currently learning. For example, the customization unit analyzes the user's current learning content and prioritizes lessons related to the content. The customization unit can also prioritize lessons related to content the user plans to learn in the future. For example, the customization unit analyzes the user's study plan and prioritizes lessons related to content the user plans to learn in the future. This allows for more effective lessons by adjusting the order based on the user's relevance. Some or all of the above-described processing in the customization unit may be performed using, or without, AI. For example, the customization unit may input user relevance data into a generation AI and cause the generation AI to adjust the order of the lesson content.

[0043] The recording unit can optimize the recording algorithm by referring to past learning data during recording. The recording unit optimizes the recording algorithm, for example, based on what the user has learned in the past. For example, the recording unit analyzes the user's past lesson history and selects an effective recording method. The recording unit can also apply an optimal recording algorithm based on the user's past learning data. For example, the recording unit analyzes the user's past learning history and applies an optimal recording algorithm. The recording unit can also optimize the recording algorithm based on user feedback. For example, the recording unit analyzes feedback provided by the user after a lesson and optimizes the recording algorithm. This allows the recording algorithm to be optimized by referring to the past learning data, enabling more effective recording. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's past learning data into a generation AI and cause the generation AI to optimize the recording algorithm.

[0044] The recording unit can customize the recording means based on the user's current learning situation during recording. For example, if the user is a beginner, the recording unit provides a basic recording means. For example, the recording unit analyzes the user's current learning situation and provides a basic recording means suitable for beginners. Furthermore, if the user is an intermediate learner, the recording unit can provide an advanced recording means. For example, the recording unit analyzes the user's current learning situation and provides an advanced recording means suitable for intermediate learners. Furthermore, if the user is an advanced learner, the recording unit can provide a specialized recording means. For example, the recording unit analyzes the user's current learning situation and provides a specialized recording means suitable for advanced learners. This enables more effective recording by customizing the recording means based on the user's current learning situation. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input the user's current learning situation data into a generation AI and cause the generation AI to customize the recording means.

[0045] The recording unit can weight the recorded data based on the user's submission time during recording. For example, if the user submits early, the recording unit may weight the recorded data more highly. For example, the recording unit may analyze the user's submission time and weight early submitted data more highly. The recording unit can also weight the recorded data less highly if the user submits near the deadline. For example, the recording unit may analyze the user's submission time and weight late submitted data less highly. Furthermore, the recording unit can reflect data submitted by the user past the deadline in the next lesson if the user misses the submission deadline. For example, the recording unit may analyze the user's submission time and reflect data that has passed the deadline in the next lesson. This allows for more effective data recording by weighting the recorded data based on the user's submission time. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit may input the user's submission time data into a generation AI and cause the generation AI to weight the recorded data.

[0046] The recording unit can analyze the user's social media activity and suggest a recording method when recording. The recording unit can, for example, suggest a recording method based on photos of meals shared by the user on social media. For example, the recording unit can analyze the user's social media posts and suggest a recording method based on the shared photos of meals. The recording unit can also suggest a recording method based on information about restaurants mentioned by the user on social media. For example, the recording unit can analyze the user's social media posts and suggest a recording method based on the mentioned restaurant information. The recording unit can also suggest a recording method based on food-related accounts the user follows on social media. For example, the recording unit can analyze the accounts the user follows and suggest a recording method based on the food-related accounts. In this way, by analyzing the user's social media activity, more appropriate recording methods can be suggested. Some or all of the above-described processing in the recording unit can be performed using, for example, AI, or can be performed without using AI. For example, the recording unit can input the user's social media data into a generation AI and cause the generation AI to suggest a recording method.

[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 observation unit can detect the user's posture while eating and issue an alert if the posture is poor. For example, the observation unit can use a camera to detect the curvature of the user's spine, and if it determines that the posture is poor, it can warn the user by audio or on-screen display. The observation unit can also issue an alert if the user maintains the same posture for a long period of time. For example, the observation unit can detect that the user has maintained the same posture for more than a certain period of time and prompt the user to change their posture appropriately. Furthermore, the observation unit can record the user's posture data and analyze it later. For example, the observation unit can save the user's posture data and later provide advice on how to improve posture. This allows the user to eat in the correct posture and develop healthy eating habits.

[0049] The customization unit can detect the user's eating speed and provide advice to eat at an appropriate speed. For example, if the user eats quickly, the customization unit can provide advice to encourage the user to eat slowly. Also, if the user eats slowly, the customization unit can provide advice to eat at an appropriate speed. Furthermore, the customization unit can record the user's eating speed data and analyze it later. For example, the customization unit can save the user's eating speed data and later provide advice to improve eating speed. This allows the user to eat at an appropriate speed and develop eating habits that are good for digestion and health.

[0050] The recording unit can record the content of conversations that a user has while eating and analyze it later. For example, the recording unit can record what topics the user talks about while eating and analyze the content later. The recording unit can also analyze the tone and emotions of the words used by the user while eating and provide appropriate conversation advice. Furthermore, the recording unit can save the user's conversation data and later provide advice to improve communication skills. For example, the recording unit can suggest better communication methods based on the user's conversation data. This allows the user to acquire better communication skills through conversations during meals.

[0051] The observation unit can detect the user's movements while eating and issue an alert if the movements are inappropriate. For example, the observation unit can use a camera to detect the user's hand movements, and if it detects inappropriate movements, it can warn the user by voice or on-screen display. The observation unit can also issue an alert if the user is not using tableware correctly. For example, the observation unit can detect when the user is not using a fork or knife correctly and show them how to use them correctly. Furthermore, the observation unit can record the user's movement data and analyze it later. For example, the observation unit can save the user's movement data and later provide advice on how to improve their movements. This allows the user to eat with correct movements and improve their table manners.

[0052] The customization unit can analyze the content of conversations the user has while eating and provide appropriate conversation advice. For example, the customization unit can analyze what topics the user talks about while eating and suggest appropriate topics. The customization unit can also analyze the tone and emotions of the words used by the user while eating and provide appropriate conversation advice. Furthermore, the customization unit can record the user's conversation data and later provide advice to improve communication skills. For example, the customization unit can suggest better communication methods based on the user's conversation data. This allows the user to acquire better communication skills through conversations during meals.

[0053] The recording unit can record posture data of the user while eating and analyze it later. For example, the recording unit can record the curvature of the user's spine and the position of their hands, and later provide advice to improve their posture. The recording unit can also record data when the user maintains the same posture for a long period of time, and provide advice to encourage the user to change their posture appropriately. Furthermore, the recording unit can save the user's posture data and later provide advice to develop healthy eating habits. For example, the recording unit can suggest ways to eat with better posture based on the user's posture data. This allows the user to eat with correct posture and develop healthy eating habits.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The observation unit observes how the user eats. For example, the observation unit uses a camera or a sensor to record how the user eats in real time. For example, the observation unit uses a camera to film how the user eats and analyzes the video data. The observation unit can also detect the user's movements using a sensor and record the data. For example, the observation unit uses an infrared sensor to detect the user's hand movements and record the data. Step 2: The customization unit provides lessons in expressions that match the user's preferences based on the data observed by the observation unit. The customization unit adjusts the content of the lessons based on the user's past data and preferences, for example. The customization unit may refer to the user's past lesson history and focus lessons on areas in which the user is weak. The customization unit may also adjust the way the lessons are presented based on the user's preferences. For example, if the user is having trouble using a fork, the customization unit may provide specific advice and show them the correct way to use it. Step 3: The recording unit records the progress of the lesson performed by the customization unit. For example, the recording unit saves the user's learning history and uses it for the next lesson. For example, the recording unit records the user's lesson content and achievement level and reflects that data in the next lesson. The recording unit can also record the user's progress in real time to support continuous learning. For example, the recording unit records the user's study time and level of acquisition and adjusts the content of the next lesson based on that data.

[0056] (Example 2) A table manners learning system according to an embodiment of the present invention observes a user's eating habits, provides lessons using expressions tailored to the user's preferences, and records the user's progress. This system uses an agent equipped with a large-scale language model (LLM) that has learned table manners as a teacher, allowing users to receive one-on-one lessons at low cost. The agent observes the user's eating habits and provides lessons using expressions tailored to the user's preferences. For example, if a user is struggling with how to use a fork, the agent can provide specific advice and demonstrate the correct usage. The agent also records the user's progress and reflects it in the next lesson, supporting continuous learning. This facilitates the acquisition of table manners and improves consideration for the user during mealtimes. For example, the system may include an observation unit equipped with a camera or sensor to observe the user's eating habits. The observation unit records the user's behavior in real time. Next, a customization unit is provided to provide lessons using expressions tailored to the user's preferences. The customization unit adjusts the lesson content based on the user's past data and preferences. Furthermore, a recording unit is provided to record the user's progress and reflect it in the next lesson. This recording unit saves the user's learning history and uses it for the next lesson. This allows the user to continue learning table manners and improve consideration at mealtimes. The table manners learning system observes the user's eating habits, provides lessons that suit their preferences, and records their progress, allowing for continuous learning of table manners.

[0057] The table manners training system according to the embodiment includes an observation unit, a customization unit, and a recording unit. The observation unit observes a user's eating habits. The observation unit records the user's eating habits in real time using, for example, a camera or a sensor. The observation unit, for example, uses a camera to capture footage of the user's eating habits and analyzes the video data. The observation unit can also detect the user's movements using a sensor and record the data. For example, the observation unit can detect the user's hand movements using an infrared sensor and record the data. The customization unit provides lessons using expressions that match the user's preferences based on the data observed by the observation unit. The customization unit, for example, adjusts the content of the lessons based on the user's past data and preferences. For example, the customization unit can refer to the user's past lesson history and focus lessons on areas in which the user is weak. The customization unit can also adjust the way the lessons are presented based on the user's preferences. For example, if a user is having trouble using a fork, the customization unit can provide specific advice and demonstrate the correct way to use it. The recording unit records the progress of the lessons provided by the customization unit. The recording unit, for example, saves the user's learning history and uses it for the next lesson. The recording unit, for example, records the user's lesson content and achievement level and reflects that data in the next lesson. The recording unit can also record the user's progress in real time to support continuous learning. For example, the recording unit records the user's study time and level of learning and adjusts the content of the next lesson based on that data. As a result, the table manners acquisition system according to the embodiment observes the user's eating habits, provides lessons that suit their preferences, and records their progress, enabling continuous acquisition of table manners.

[0058] The observation unit can record the user's eating habits in real time using a camera or a sensor. For example, the observation unit can use a camera to capture the user's eating habits and analyze the video data. For example, the observation unit can use a webcam to capture the user's eating habits and analyze the video data in real time. The observation unit can also use a sensor to detect the user's movements and record the data. For example, the observation unit can use an infrared sensor to detect the user's hand movements and record the data. Furthermore, the observation unit can combine multiple cameras and sensors to record the user's eating habits in detail. For example, the observation unit can use multiple cameras to capture the user's eating habits from different angles and integrate and analyze the video data. In this way, the use of cameras and sensors can accurately observe and record the user's eating habits. Some or all of the above-mentioned processing in the observation unit can be performed using, for example, AI, or without AI. For example, the observation unit can input video data acquired by a camera into a generation AI and have the generation AI analyze the video data.

[0059] The customization unit can adjust the lesson content based on the user's past data or preferences. For example, the customization unit may refer to the user's past lesson history and focus lessons on areas in which the user is weak. For example, if the customization unit analyzes the user's past lesson history and the user is struggling with how to use a fork, the customization unit may focus lessons on how to use a fork. The customization unit can also adjust the presentation of the lesson based on the user's preferences. For example, if the user prefers visual presentation, the customization unit may use visual animations or illustrations to provide lessons. The customization unit can also adjust the lesson content based on user feedback. For example, the customization unit may analyze feedback provided by the user after a lesson and improve the content of the next lesson. This allows for more effective lessons by adjusting the lesson content based on the user's past data and preferences. Some or all of the above-described processing in the customization unit may be performed using, for example, AI, or may be performed without AI. For example, the customization unit may input the user's past data into a generation AI and have the generation AI adjust the lesson content.

[0060] The recording unit can save the user's learning history and use it for the next lesson. The recording unit, for example, records the user's lesson content and achievement level and reflects the data in the next lesson. For example, the recording unit can record the user's lesson content in detail and use that content in the next lesson. The recording unit can also record the user's progress in real time to support continuous learning. For example, the recording unit can record the user's learning time and level of mastery and adjust the next lesson content based on that data. Furthermore, the recording unit can record the user's feedback and reflect that data in the next lesson. For example, the recording unit can record feedback provided by the user after a lesson and improve the next lesson content based on that feedback. This enables continuous learning by saving the user's learning history and using it in the next lesson. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or without AI. For example, the recording unit can input the user's learning history into a generation AI and have the generation AI adjust the next lesson content.

[0061] If a user is having trouble using a fork, the customization unit can provide detailed advice and show them how to use it correctly. For example, if a user is having trouble using a fork, the customization unit can provide specific advice and show them how to use it correctly. For example, the customization unit can provide detailed instructions on how to hold a fork and the steps for using it. Furthermore, if a user is making a common mistake, the customization unit can point out the mistake and show them how to use it correctly. For example, if a user is holding a fork in the wrong hand, the customization unit can point out how to hold it and show them the correct way to hold it. Furthermore, the customization unit can record the user's progress and reflect this in the next lesson. For example, the customization unit can record the user's progress until they have mastered how to use a fork and adjust the content of the next lesson based on that data. In this way, if a user is having trouble using a fork, specific advice can be provided to help them master the correct way to use it. Some or all of the above-described processing in the customization unit may be performed using, for example, AI, or may be performed without AI. For example, the customization unit can input data regarding the user's use of the fork into a generation AI and cause the generation AI to provide specific advice.

[0062] The recording unit can record the user's progress and reflect it in the next lesson. For example, the recording unit can record the user's progress in real time and reflect the data in the next lesson. For example, the recording unit can record the user's study time and level of mastery and adjust the content of the next lesson based on that data. The recording unit can also record the user's feedback and reflect that data in the next lesson. For example, the recording unit can record feedback provided by the user after a lesson and improve the content of the next lesson based on that feedback. Furthermore, the recording unit can save the user's learning history and support continuous learning. For example, the recording unit can record the user's past lesson content and achievement level and adjust the content of the next lesson based on that data. This enables continuous learning by recording the user's progress and reflecting it in the next lesson. Some or all of the above-mentioned processing in the recording unit can be performed using, for example, AI, or without AI. For example, the recording unit can input the user's progress data into a generation AI and cause the generation AI to adjust the content of the next lesson.

[0063] The observation unit can estimate the user's emotions and adjust the timing of observation based on the estimated user emotions. For example, if the user is nervous, the observation unit reduces the frequency of observation and performs observation when the user is relaxed. For example, the observation unit captures the user's facial expressions with a camera, detects the user's nervous state using an emotion estimation algorithm, and adjusts the frequency of observation. Furthermore, if the user is relaxed, the observation unit can increase the frequency of observation and collect more detailed data. For example, the observation unit can record the user's voice, detect the user's relaxed state using voice analysis technology, and adjust the frequency of observation. Furthermore, if the user is in a hurry, the observation unit can shorten the timing of observation and collect data more quickly. For example, the observation unit can analyze the user's behavioral patterns, detect the user's state of hurry, and adjust the timing of observation. By adjusting the timing of observation according to the user's emotions, more appropriate data can be collected. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit may input user emotion data to the generation AI and cause the generation AI to adjust the timing of observation.

[0064] The observation unit can analyze the user's past eating behavior and select an appropriate observation method. For example, if the user has previously preferred a particular eating style, the observation unit selects an observation method that matches that style. For example, if the observation unit analyzes the user's past eating behavior data and the user prefers Japanese food, the observation unit selects an observation method that matches that style. Furthermore, if the user has previously eaten at a particular time of day, the observation unit can select an observation method that matches that time of day. For example, the observation unit analyzes the user's past mealtime data and selects an observation method that matches the user's preference for evening meals if the user often eats at night. Furthermore, if the user has previously eaten in a particular dining environment, the observation unit can select an observation method that matches that environment. For example, the observation unit analyzes the user's past eating environment data and selects an observation method that matches the user's preference for restaurants if the user often eats at restaurants. This enables more effective observation by selecting an optimal observation method based on the user's past eating behavior. Some or all of the above-described processing by the observation unit may be performed using, for example, AI, or without AI. For example, the observation unit can input the user's past eating behavior data into the generation AI and have the generation AI select an observation method.

[0065] During observation, the observation unit can perform filtering based on the user's current eating environment and situation. For example, if the user is eating in a quiet environment, the observation unit filters and observes the audio data. For example, if the user's eating environment is quiet, the observation unit removes background noise and analyzes the audio data. Furthermore, if the user is eating in a bright environment, the observation unit can also filter and observe the video data. For example, if the user's eating environment is bright, the observation unit adjusts the brightness of the video data and analyzes it. Furthermore, if the user is eating in a crowded environment, the observation unit can also remove noise and observe the video data. For example, if the user's eating environment is crowded, the observation unit removes background noise and analyzes the audio data. This allows for more accurate data collection by filtering based on the user's current eating environment and situation. Some or all of the above-described processing in the observation unit may be performed using, or without, AI. For example, the observation unit can input the user's eating environment data into the generation AI and have the generation AI adjust the filtering.

[0066] The observation unit can estimate the user's emotions and prioritize the items to be observed based on the estimated user emotions. For example, if the user is nervous, the observation unit prioritizes observing basic etiquette items. For example, the observation unit captures the user's facial expressions with a camera, detects the user's nervous state using an emotion estimation algorithm, and prioritizes observing basic etiquette items. Furthermore, if the user is relaxed, the observation unit can prioritize observing detailed etiquette items. For example, the observation unit can record the user's voice, detect the user's relaxed state using voice analysis technology, and prioritize observing detailed etiquette items. Furthermore, if the user is in a hurry, the observation unit can prioritize observing important etiquette items. For example, the observation unit can analyze the user's behavioral patterns, detect the user's state of hurry, and prioritize observing important etiquette items. This enables more effective observation by prioritizing the items to be observed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the observation unit may be performed using AI, or may be performed without using AI. For example, the observation unit may input user emotion data into the generation AI and have the generation AI determine the priority of observation items.

[0067] During observation, the observation unit can prioritize observing highly relevant data by taking into account the user's geographical location information. For example, if the user is eating in a specific area, the observation unit prioritizes observing data related to the manners of that area. For example, the observation unit prioritizes collecting data related to the dining manners of that area based on the user's geographical location information. Furthermore, if the user is traveling, the observation unit can prioritize observing data related to the manners of the travel destination. For example, the observation unit prioritizes collecting data related to the dining manners of the travel destination based on the user's geographical location information. Furthermore, if the user is eating at home, the observation unit can prioritize observing data related to household manners. For example, the observation unit prioritizes collecting data related to household dining manners based on the user's geographical location information. In this way, highly relevant data can be prioritized by taking the user's geographical location information into account. Some or all of the above-described processing by the observation unit may be performed using AI, for example, or without AI. For example, the observation unit can input the user's geographical location information to the generation AI and cause the generation AI to perform prioritized observation of highly relevant data.

[0068] During observation, the observation unit can analyze the user's social media activity and observe related behavior. The observation unit, for example, observes dining etiquette based on photos of food shared by the user on social media. For example, the observation unit analyzes the user's social media posts and observes dining etiquette based on the shared photos of food. The observation unit can also observe dining etiquette based on information about restaurants mentioned by the user on social media. For example, the observation unit analyzes the user's social media posts and observes dining etiquette based on the mentioned restaurant information. The observation unit can also observe dining etiquette based on food-related accounts the user follows on social media. For example, the observation unit analyzes the accounts the user follows and observes dining etiquette based on the food-related accounts. In this way, related behavior can be observed by analyzing the user's social media activity. Some or all of the above-described processing by the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input the user's social media data into the generation AI and cause the generation AI to observe related behavior.

[0069] The customization unit can estimate the user's emotions and adjust the way the lesson is presented based on the estimated user emotions. For example, if the user is nervous, the customization unit can provide the lesson in a gentle tone. For example, the customization unit can capture the user's facial expression with a camera, detect the user's nervous state using an emotion estimation algorithm, and provide the lesson in a gentle tone. Furthermore, if the user is relaxed, the customization unit can provide a lesson with detailed explanations. For example, the customization unit can record the user's voice, detect the user's relaxed state using voice analysis technology, and provide a lesson with detailed explanations. Furthermore, if the user is in a hurry, the customization unit can provide a concise and to-the-point lesson. For example, the customization unit can analyze the user's behavioral patterns, detect the user's state of hurry, and provide a concise and to-the-point lesson. This allows for more effective lessons by adjusting the way the lesson is presented based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI 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 customization unit may be performed using AI or without AI. For example, the customization unit may input user emotion data into the generation AI and have the generation AI adjust the way the lesson is presented.

[0070] When customizing the lesson content, the customization unit can adjust the level of detail based on the user's level of importance. For example, the customization unit provides a detailed explanation of etiquette items that the user considers particularly important. For example, the customization unit analyzes the user's past lesson history and provides a detailed explanation of etiquette items that the user considers particularly important. The customization unit can also provide a concise explanation of etiquette items that the user considers less important. For example, the customization unit can provide a concise explanation of etiquette items that the user considers less important based on user feedback. Furthermore, the customization unit can also provide a focused explanation of etiquette items that the user has previously struggled with. For example, the customization unit analyzes the user's past lesson history and provides a focused explanation of etiquette items that the user has struggled with. This allows for more effective lessons by adjusting the level of detail of the lesson content based on the user's level of importance. Some or all of the above-described processing by the customization unit may be performed using, or without, AI. For example, the customization unit can input the user's level of importance data into a generation AI and cause the generation AI to adjust the level of detail of the lesson content.

[0071] When customizing the lesson content, the customization unit can apply different algorithms depending on the user's category. For example, if the user is a beginner, the customization unit applies an algorithm that provides lessons focusing on basic etiquette items. For example, the customization unit analyzes the user's category and applies an algorithm that provides lessons focusing on basic etiquette items suitable for beginners. Furthermore, if the user is an intermediate user, the customization unit can also apply an algorithm that provides lessons focusing on advanced etiquette items. For example, the customization unit analyzes the user's category and applies an algorithm that provides lessons focusing on advanced etiquette items suitable for intermediate users. Furthermore, if the user is an advanced user, the customization unit can also apply an algorithm that provides lessons focusing on specialized etiquette items. For example, the customization unit analyzes the user's category and applies an algorithm that provides lessons focusing on specialized etiquette items suitable for advanced users. This enables more effective lessons by applying different algorithms depending on the user's category. Some or all of the above-described processing in the customization unit may be performed using, or without, AI. For example, the customization unit can input user category data into a generation AI and cause the generation AI to apply a lesson algorithm.

[0072] The customization 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 nervous, the customization unit provides a short lesson. For example, the customization unit captures the user's facial expression with a camera, detects the user's nervous state using an emotion estimation algorithm, and provides a short lesson. The customization unit can also provide a longer lesson if the user is relaxed. For example, the customization unit records the user's voice, detects the user's relaxed state using voice analysis technology, and provides a longer lesson. Furthermore, if the user is in a hurry, the customization unit can provide a short lesson that focuses on the main points. For example, the customization unit analyzes the user's behavioral patterns, detects the user's state of hurry, and provides a short lesson that focuses on the main points. This allows for more effective lessons 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 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 customization unit may be performed using AI or without AI. For example, the customization unit may input user emotion data into the generation AI and have the generation AI adjust the length of the lesson.

[0073] When customizing lesson content, the customization unit can determine priorities based on the user's submission time. For example, if the user submits early, the customization unit can prioritize lessons. For example, the customization unit can analyze the user's submission time and prioritize customizing lesson content submitted early. The customization unit can also quickly customize lesson content submitted close to the deadline if the user submits close to the deadline. For example, the customization unit can analyze the user's submission time and quickly customize lesson content submitted close to the deadline. Furthermore, the customization unit can reflect the changes in the next lesson if the user misses the submission deadline. For example, the customization unit can analyze the user's submission time and reflect lesson content that has passed the submission deadline in the next lesson. This enables more effective lessons by determining priorities based on the user's submission time. Some or all of the above-described processing in the customization unit can be performed using, or without, AI. For example, the customization unit can input user submission time data into the generation AI and cause the generation AI to determine the priority of lesson content.

[0074] When customizing the lesson content, the customization unit can adjust the order based on the user's relevance. For example, the customization unit prioritizes lessons related to content the user has previously learned. For example, the customization unit analyzes the user's past lesson history and prioritizes lessons related to the content. The customization unit can also prioritize lessons related to content the user is currently learning. For example, the customization unit analyzes the user's current learning content and prioritizes lessons related to the content. The customization unit can also prioritize lessons related to content the user plans to learn in the future. For example, the customization unit analyzes the user's study plan and prioritizes lessons related to content the user plans to learn in the future. This allows for more effective lessons by adjusting the order based on the user's relevance. Some or all of the above-described processing in the customization unit may be performed using, or without, AI. For example, the customization unit may input user relevance data into a generation AI and cause the generation AI to adjust the order of the lesson content.

[0075] The recording unit can estimate the user's emotions and select recorded data based on the estimated user emotions. For example, if the user is nervous, the recording unit prioritizes recording basic etiquette items. For example, the recording unit captures the user's facial expressions with a camera, detects the user's nervous state using an emotion estimation algorithm, and prioritizes recording basic etiquette items. Furthermore, if the user is relaxed, the recording unit can prioritize recording detailed etiquette items. For example, the recording unit can record the user's voice, detect the user's relaxed state using voice analysis technology, and prioritize recording detailed etiquette items. Furthermore, if the user is in a hurry, the recording unit can prioritize recording important etiquette items. For example, the recording unit can analyze the user's behavioral patterns, detect the user's state of hurry, and prioritize recording important etiquette items. This allows for more appropriate data to be recorded by selecting recorded data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recording unit may be performed using AI, or may be performed without using AI. For example, the recording unit may input user emotion data into the generation AI and cause the generation AI to select the recorded data.

[0076] The recording unit can optimize the recording algorithm by referring to past learning data during recording. The recording unit optimizes the recording algorithm, for example, based on what the user has learned in the past. For example, the recording unit analyzes the user's past lesson history and selects an effective recording method. The recording unit can also apply an optimal recording algorithm based on the user's past learning data. For example, the recording unit analyzes the user's past learning history and applies an optimal recording algorithm. The recording unit can also optimize the recording algorithm based on user feedback. For example, the recording unit analyzes feedback provided by the user after a lesson and optimizes the recording algorithm. This allows the recording algorithm to be optimized by referring to the past learning data, enabling more effective recording. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's past learning data into a generation AI and cause the generation AI to optimize the recording algorithm.

[0077] The recording unit can customize the recording means based on the user's current learning situation during recording. For example, if the user is a beginner, the recording unit provides a basic recording means. For example, the recording unit analyzes the user's current learning situation and provides a basic recording means suitable for beginners. Furthermore, if the user is an intermediate learner, the recording unit can provide an advanced recording means. For example, the recording unit analyzes the user's current learning situation and provides an advanced recording means suitable for intermediate learners. Furthermore, if the user is an advanced learner, the recording unit can provide a specialized recording means. For example, the recording unit analyzes the user's current learning situation and provides a specialized recording means suitable for advanced learners. This enables more effective recording by customizing the recording means based on the user's current learning situation. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can input the user's current learning situation data into a generation AI and cause the generation AI to customize the recording means.

[0078] The recording unit can estimate the user's emotions and adjust the recording frequency based on the estimated user emotions. For example, if the user is nervous, the recording unit reduces the recording frequency and records when the user is relaxed. For example, the recording unit captures the user's facial expressions with a camera, detects the user's nervous state using an emotion estimation algorithm, and adjusts the recording frequency. Furthermore, if the user is relaxed, the recording unit can increase the recording frequency and collect more detailed data. For example, the recording unit records the user's voice, detects the user's relaxed state using voice analysis technology, and adjusts the recording frequency. Furthermore, if the user is in a hurry, the recording unit can shorten the recording timing and collect data more quickly. For example, the recording unit analyzes the user's behavioral patterns, detects the user's state of hurry, and adjusts the recording timing. By adjusting the recording frequency according to the user's emotions, data can be recorded at more appropriate times. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may input user emotion data to the generation AI and cause the generation AI to adjust the frequency of recording.

[0079] The recording unit can weight the recorded data based on the user's submission time during recording. For example, if the user submits early, the recording unit may weight the recorded data more highly. For example, the recording unit may analyze the user's submission time and weight early submitted data more highly. The recording unit can also weight the recorded data less highly if the user submits near the deadline. For example, the recording unit may analyze the user's submission time and weight late submitted data less highly. Furthermore, the recording unit can reflect data submitted by the user past the deadline in the next lesson if the user misses the submission deadline. For example, the recording unit may analyze the user's submission time and reflect data that has passed the deadline in the next lesson. This allows for more effective data recording by weighting the recorded data based on the user's submission time. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit may input the user's submission time data into a generation AI and cause the generation AI to weight the recorded data.

[0080] The recording unit can analyze the user's social media activity and suggest a recording method when recording. The recording unit can, for example, suggest a recording method based on photos of meals shared by the user on social media. For example, the recording unit can analyze the user's social media posts and suggest a recording method based on the shared photos of meals. The recording unit can also suggest a recording method based on information about restaurants mentioned by the user on social media. For example, the recording unit can analyze the user's social media posts and suggest a recording method based on the mentioned restaurant information. The recording unit can also suggest a recording method based on food-related accounts the user follows on social media. For example, the recording unit can analyze the accounts the user follows and suggest a recording method based on the food-related accounts. In this way, by analyzing the user's social media activity, more appropriate recording methods can be suggested. Some or all of the above-described processing in the recording unit can be performed using, for example, AI, or can be performed without using AI. For example, the recording unit can input the user's social media data into a generation AI and cause the generation AI to suggest a recording method. === Hard Collateral 1-1 === Each of the multiple elements, including the observation unit, customization unit, and recording 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 observation unit uses the camera 42 and sensors of the smart device 14 to record the user's eating habits in real time, and the control unit 46A analyzes the data. The customization unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the lesson content based on the user's past data and preferences. The recording unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and saves the user's learning history to use for the next lesson. === Hard Collateral 1-2 === Each of the multiple elements, including the observation unit, customization unit, and recording 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 observation unit uses the camera 42 and sensors of the smart glasses 214 to record the user's eating habits in real time, and the control unit 46A analyzes the data. The customization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and adjusts the lesson content based on the user's past data and preferences. The recording unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and saves the user's learning history to use for the next lesson. === Hard Collateral 1-3 === Each of the multiple elements, including the observation unit, customization unit, and recording 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 observation unit uses the camera 42 and sensors of the headset terminal 314 to record the user's eating habits in real time, and the control unit 46A analyzes the data. The customization unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the lesson content based on the user's past data and preferences. The recording unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and saves the user's learning history to use for the next lesson. === Hard Collateral 1-4 === Each of the multiple elements, including the observation unit, customization unit, and recording unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the observation unit uses the camera 42 and sensors of the robot 414 to record the user's eating habits in real time, and the control unit 46A analyzes the data. The customization unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the lesson content based on the user's past data and preferences. The recording unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and saves the user's learning history to use for the next lesson.

[0081] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0082] The observation unit can detect the user's posture while eating and issue an alert if the posture is poor. For example, the observation unit can use a camera to detect the curvature of the user's spine, and if it determines that the posture is poor, it can warn the user by audio or on-screen display. The observation unit can also issue an alert if the user maintains the same posture for a long period of time. For example, the observation unit can detect that the user has maintained the same posture for more than a certain period of time and prompt the user to change their posture appropriately. Furthermore, the observation unit can record the user's posture data and analyze it later. For example, the observation unit can save the user's posture data and later provide advice on how to improve posture. This allows the user to eat in the correct posture and develop healthy eating habits.

[0083] The customization unit can detect the user's eating speed and provide advice to eat at an appropriate speed. For example, if the user eats quickly, the customization unit can provide advice to encourage the user to eat slowly. Also, if the user eats slowly, the customization unit can provide advice to eat at an appropriate speed. Furthermore, the customization unit can record the user's eating speed data and analyze it later. For example, the customization unit can save the user's eating speed data and later provide advice to improve eating speed. This allows the user to eat at an appropriate speed and develop eating habits that are good for digestion and health.

[0084] The recording unit can record the content of conversations that a user has while eating and analyze it later. For example, the recording unit can record what topics the user talks about while eating and analyze the content later. The recording unit can also analyze the tone and emotions of the words used by the user while eating and provide appropriate conversation advice. Furthermore, the recording unit can save the user's conversation data and later provide advice to improve communication skills. For example, the recording unit can suggest better communication methods based on the user's conversation data. This allows the user to acquire better communication skills through conversations during meals.

[0085] The observation unit can detect the user's facial expression while eating and estimate the user's level of satisfaction with the meal. For example, the observation unit can capture the user's facial expression using a camera and encourage the user to continue eating if the user's level of satisfaction is high. The observation unit can also provide advice to improve the content or environment of the meal if the user's level of satisfaction is low. Furthermore, the observation unit can record the user's facial expression data and analyze it later. For example, the observation unit can save the user's facial expression data and later provide advice to improve the user's level of satisfaction with the meal. This allows the user to increase their satisfaction with the meal and have a more enjoyable dining experience.

[0086] The customization unit can estimate the user's emotions during a meal and provide lesson content according to the emotions. For example, if the user is feeling stressed, the customization unit can teach dining etiquette to help the user relax. Also, if the user is enjoying themselves, the customization unit can teach dining etiquette to help the user enjoy themselves even more. Furthermore, the customization unit can record the user's emotional data and analyze it later. For example, the customization unit can save the user's emotional data and later provide lesson content according to the emotions. This allows the user to learn appropriate dining etiquette according to their emotions and have a better dining experience.

[0087] The recording unit can estimate the user's emotions while eating and provide a recording method according to the emotions. For example, if the user is relaxed, the recording unit can provide detailed recording. If the user is nervous, the recording unit can provide brief recording. Furthermore, the recording unit can record the user's emotional data and analyze it later. For example, the recording unit can save the user's emotional data and later provide a recording method according to the emotions. This allows the user to use an appropriate recording method according to the emotions, enabling more effective learning.

[0088] The observation unit can detect the user's movements while eating and issue an alert if the movements are inappropriate. For example, the observation unit can use a camera to detect the user's hand movements, and if it detects inappropriate movements, it can warn the user by voice or on-screen display. The observation unit can also issue an alert if the user is not using tableware correctly. For example, the observation unit can detect when the user is not using a fork or knife correctly and show them how to use them correctly. Furthermore, the observation unit can record the user's movement data and analyze it later. For example, the observation unit can save the user's movement data and later provide advice on how to improve their movements. This allows the user to eat with correct movements and improve their table manners.

[0089] The customization unit can analyze the content of conversations the user has while eating and provide appropriate conversation advice. For example, the customization unit can analyze what topics the user talks about while eating and suggest appropriate topics. The customization unit can also analyze the tone and emotions of the words used by the user while eating and provide appropriate conversation advice. Furthermore, the customization unit can record the user's conversation data and later provide advice to improve communication skills. For example, the customization unit can suggest better communication methods based on the user's conversation data. This allows the user to acquire better communication skills through conversations during meals.

[0090] The recording unit can record posture data of the user while eating and analyze it later. For example, the recording unit can record the curvature of the user's spine and the position of their hands, and later provide advice to improve their posture. The recording unit can also record data when the user maintains the same posture for a long period of time, and provide advice to encourage the user to change their posture appropriately. Furthermore, the recording unit can save the user's posture data and later provide advice to develop healthy eating habits. For example, the recording unit can suggest ways to eat with better posture based on the user's posture data. This allows the user to eat with correct posture and develop healthy eating habits.

[0091] The customization unit can estimate the user's emotions during a meal and provide dietary advice according to the emotions. For example, if the user is feeling stressed, the customization unit can teach the user how to eat in a way that will help them relax. Also, if the user is enjoying themselves, the customization unit can teach the user how to eat in a way that will help them enjoy their meal even more. Furthermore, the customization unit can record the user's emotion data and analyze it later. For example, the customization unit can save the user's emotion data and later provide dietary advice according to the emotions. This allows the user to learn appropriate eating methods according to their emotions and have a better dining experience.

[0092] The processing flow of the second embodiment will be briefly explained below.

[0093] Step 1: The observation unit observes how the user eats. For example, the observation unit uses a camera or a sensor to record how the user eats in real time. For example, the observation unit uses a camera to film how the user eats and analyzes the video data. The observation unit can also detect the user's movements using a sensor and record the data. For example, the observation unit uses an infrared sensor to detect the user's hand movements and record the data. Step 2: The customization unit provides lessons in expressions that match the user's preferences based on the data observed by the observation unit. The customization unit adjusts the content of the lessons based on the user's past data and preferences, for example. The customization unit may refer to the user's past lesson history and focus lessons on areas in which the user is weak. The customization unit may also adjust the way the lessons are presented based on the user's preferences. For example, if the user is having trouble using a fork, the customization unit may provide specific advice and show them the correct way to use it. Step 3: The recording unit records the progress of the lesson performed by the customization unit. For example, the recording unit saves the user's learning history and uses it for the next lesson. For example, the recording unit records the user's lesson content and achievement level and reflects that data in the next lesson. The recording unit can also record the user's progress in real time to support continuous learning. For example, the recording unit records the user's study time and level of acquisition and adjusts the content of the next lesson based on that data.

[0094] 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.

[0095] 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, such as voice data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and 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.

[0096] 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.

[0097] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

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

[0114] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0115] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] The 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.

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

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[0121] Fig. 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.

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

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0124] In the 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.

[0125] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0126] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0128] 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.

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

[0130] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0131] 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.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0133] The 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.

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

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

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

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0152] 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."

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] [Explanation of symbols]

[0166] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an observation unit that observes how a user eats; a customization unit that provides lessons in a manner that matches the user's preferences based on the data observed by the observation unit; a recording unit that records the progress of the lesson performed by the customization unit; A system characterized by:

2. The observation unit is Recording the user's eating habits in real time using cameras or sensors The system of claim 1 .

3. The customization unit Tailor lesson content based on user historical data or preferences The system of claim 1 .

4. The recording unit Save the user's learning history and use it for the next lesson The system of claim 1 .

5. The customization unit If a user has trouble using a fork, provide detailed advice and show them how to use it correctly. The system of claim 1 .

6. The recording unit Track your progress and incorporate it into your next lesson The system of claim 1 .

7. The observation unit is Estimate the user's emotions and adjust the timing of observations based on the estimated user emotions. The system of claim 1 .

8. The observation unit is Analyze the user's past eating habits and select the appropriate observation method The system of claim 1 .

9. The observation unit is During observation, filtering is performed based on the user's current eating environment and situation. The system of claim 1 .

Images