System

Abstract

An object of the system according to the embodiment is to accurately grasp a posture during training and provide appropriate guidance.SOLUTION: A system according to an embodiment includes an estimation unit, a comparison unit, and a guidance unit. The estimation unit estimates a posture. The comparison unit compares the posture estimated by the estimation unit with the posture of the trainer. The instruction part gives instructions in natural language based on the comparison result obtained by the comparison part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem of making it difficult to accurately grasp posture during training and provide appropriate guidance.

[0005] The system according to the embodiment aims to accurately grasp posture during training and provide appropriate guidance. [Means for solving the problem]

[0006] The system according to the embodiment includes an estimation unit, a comparison unit, and an instruction unit. The estimation unit estimates a posture. The comparison unit compares the posture estimated by the estimation unit with the posture of a trainer. The instruction unit provides instruction in natural language based on the comparison result obtained by the comparison unit. [Effects of the Invention]

[0007] The system according to the embodiment can accurately grasp the posture during training and provide appropriate guidance. [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 training support system according to an embodiment of the present invention recognizes a user's posture during training using posture estimation technology based on image recognition for videos captured with a smartphone camera and calculates the difference between the video and the trainer's video. This training support system allows a user to capture a video of their posture during training with their smartphone camera, estimates their posture using image recognition technology, and compares it with the trainer's video. The training support system then calculates the difference between the video and the trainer's video and provides posture guidance in natural language in real time. Furthermore, the user's own posture can be overlaid on the trainer's video in real time, allowing the user to visually recognize the difference. Natural language prompts can also be provided to motivate the user. Furthermore, a video generation AI automatically generates videos of optimal training combinations tailored to each individual situation. Finally, the system analyzes nutritional value and manages dietary habits by allowing users to upload photos of their meals. For example, when a user is performing squats, the training support system analyzes the user's knee angle and back curvature and compares them with the trainer's correct posture. The system then calculates the difference between the video and the trainer's video and provides posture guidance in natural language in real time. For example, instructions such as "Bend your knees a little more" or "Keep your back straight" are given, allowing users to learn correct posture in real time. Furthermore, the training support system allows users to visually recognize differences by overlaying their own posture on the trainer's video in real time. For example, the user's posture is displayed superimposed on the trainer's, allowing them to see at a glance which parts are incorrect. Natural language interjections also motivate users. For example, encouraging words such as "Good luck!" or "Let's try a little harder!" are provided in real time. Furthermore, video generation AI automatically generates videos with optimal training combinations tailored to each individual situation. For example, optimal training menus are suggested based on the user's training history and current physical condition. Finally, users can upload photos of their meals, which allows for nutritional analysis and dietary management.For example, a system can analyze calorie and nutrient intake from a photo of a meal and suggest a balanced diet. This enables health management from both the training and diet perspectives. This allows the training support system to estimate the user's posture in real time and provide guidance by comparing it with the trainer's posture. For example, when a user is performing squats, the system analyzes the user's knee angle and back curvature and compares them with the trainer's correct posture. The training support system then calculates the difference between the user's posture and the trainer's video and provides real-time posture guidance in natural language. For example, instructions such as "Bend your knees a little more" or "Keep your back straight" are given. This allows the user to learn correct posture in real time. Furthermore, the training support system can visually recognize the difference by overlaying the user's posture on the trainer's video in real time. For example, the user's posture is superimposed on the trainer's posture, allowing the user to see at a glance which parts are incorrect. Furthermore, natural language prompts can motivate the user. For example, encouraging words such as "Good luck!" or "Let's try a little harder!" are provided in real time. Furthermore, video generation AI automatically generates videos of optimal training combinations tailored to each situation. For example, the system suggests optimal training menus based on the user's training history and current physical condition. Finally, users can upload photos of their meals, which are then analyzed for nutritional value and used to manage their diet. For example, the system analyzes calorie and nutrient intake from photos of meals and suggests balanced meals. This makes it possible to manage health from both training and dietary perspectives.

[0029] A training support system according to an embodiment includes an estimation unit, a comparison unit, and an instruction unit. The estimation unit estimates a user's posture. For example, the estimation unit receives a video captured by a smartphone camera as input and estimates the user's posture using image recognition technology. The estimation unit can also estimate the user's posture in real time. For example, when a user is performing squats, the estimation unit analyzes the knee angle and the degree of curvature of the back to estimate the posture. The estimation unit can also use a generation AI to estimate the user's posture. For example, the generation AI receives an instruction such as "Please estimate the user's posture" as a prompt for estimating the user's posture, and estimates the posture. The comparison unit compares the posture estimated by the estimation unit with the trainer's posture. For example, the comparison unit calculates the angle difference or positional deviation between the estimated posture and the trainer's posture. The comparison unit can also calculate the similarity between the estimated posture and the trainer's posture. For example, the comparison unit calculates the posture similarity using cosine similarity. The comparison unit can also visually display the difference between the estimated posture and the trainer's posture. For example, the comparison unit may superimpose the user's posture and the trainer's posture to visually indicate which parts are incorrect. The instruction unit provides instruction in natural language based on the comparison result obtained by the comparison unit. For example, the instruction unit may provide instructions such as, "Bend your knees a little more" or "Keep your back straight." The instruction unit may also provide interjections in natural language to motivate the user. For example, the instruction unit may provide encouraging words in real time, such as, "Good luck!" or "Let's try a little harder!" In this way, the training support system according to the embodiment can estimate the user's posture in real time, compare it with the trainer's posture, and provide instruction. Some or all of the above-described processing by the estimation unit, comparison unit, and instruction unit may be performed using, or without, AI. For example, the estimation unit inputs a video captured with a smartphone camera into the generation AI, which then estimates the posture. The comparison unit takes the estimated posture and the trainer's posture as input and calculates the similarity using an AI model that outputs the similarity.The instruction department provides instruction using an AI model that takes the comparison results as input and outputs instructions in natural language.

[0030] The training support system includes a generation unit that generates a training menu. The generation unit generates an optimal training menu based on the user's training history and current physical condition. For example, the generation unit receives the user's past training data as input and generates an optimal training menu using a generation AI. The generation unit can also receive the user's current physical condition data as input and adjust the training menu using the generation AI. For example, the generation unit adjusts the training menu based on the user's heart rate and fatigue level. The generation unit can also generate an individually customized training menu by combining the user's training history and physical condition data. For example, the generation unit adjusts the number of repetitions and sets of a specific exercise based on the user's past training data and current physical condition data. This allows the training support system to generate an optimal training menu based on the user's training history and current physical condition. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit inputs the user's training history data into the generation AI, which then generates an optimal training menu.

[0031] The training support system includes an analysis unit that analyzes food photos. The analysis unit analyzes food photos uploaded by a user and analyzes calorie and nutrient intake. For example, the analysis unit inputs food photos, identifies ingredients using image recognition technology, and calculates calorie and nutrient intake. The analysis unit can also improve analysis accuracy by taking into account the resolution and shooting angle of the food photos. For example, the analysis unit prioritizes analysis of high-resolution photos to accurately calculate calories. The analysis unit can also adjust the analysis results by taking into account the user's eating habits and preferences. For example, the analysis unit customizes the analysis results based on the user's preferred ingredients and ingredients to avoid. This allows the training support system to analyze food photos uploaded by a user and analyze calorie and nutrient intake. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit inputs food photo data to a generation AI, which identifies ingredients and calculates calories.

[0032] The training support system includes an analysis unit that analyzes nutritional values. The analysis unit suggests a balanced meal based on the analyzed data. For example, the analysis unit inputs calorie and nutrient intake data and suggests a balanced meal using AI. The analysis unit can also customize the meal suggestions based on the user's health condition and goals. For example, the analysis unit suggests meals with specific nutrients increased or decreased based on the user's weight and blood pressure. The analysis unit can also make individually customized meal suggestions taking into account the user's dietary history and preferences. For example, the analysis unit suggests a balanced meal menu based on the user's favorite ingredients. This allows the training support system to suggest a balanced meal based on the analyzed data. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit inputs calorie and nutrient intake data to a generation AI, which then suggests a balanced meal.

[0033] The estimation unit can select a posture estimation algorithm by referring to the user's past posture data. For example, the estimation unit selects the most suitable posture estimation algorithm based on posture data from training sessions the user has performed in the past. The estimation unit can also select an algorithm with high accuracy for a specific movement from the user's past posture data. The estimation unit can also analyze the user's past posture data and switch algorithms depending on the type of training. In this way, the optimal posture estimation algorithm can be selected by referring to the past posture data. Some or all of the above-described processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's past posture data into a generation AI, which then selects the optimal posture estimation algorithm.

[0034] The estimation unit can improve the accuracy of posture estimation by taking into account the user's body shape and muscle condition. The estimation unit, for example, customizes the posture estimation algorithm based on the user's body shape data. The estimation unit can also analyze the user's muscle condition in real time to improve the accuracy of posture estimation. The estimation unit can also perform posture estimation focusing on specific parts depending on the user's body shape and muscle condition. This improves the estimation accuracy by taking into account the user's body shape and muscle condition. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's body shape data into a generation AI, and the generation AI customizes the posture estimation algorithm.

[0035] The estimation unit can analyze the user's movement speed and rhythm during posture estimation and reflect them in the estimation result. For example, the estimation unit can analyze the user's movement speed in real time and adjust the accuracy of posture estimation. The estimation unit can also analyze the user's movement rhythm and reflect them in the estimation result. The estimation unit can also dynamically adjust the posture estimation algorithm according to the user's movement speed and rhythm. In this way, the user's movement speed and rhythm can be analyzed and reflected in the estimation result. Some or all of the above-mentioned processing in the estimation unit can be performed using, for example, AI, or can be performed without using AI. For example, the estimation unit inputs the user's movement data to a generation AI, which analyzes the movement speed and rhythm and reflects them in the estimation result.

[0036] The estimation unit can improve the estimation accuracy during posture estimation by taking into account the user's training environment. For example, when the user is training indoors, the estimation unit adjusts the posture estimation accuracy by taking into account lighting conditions. Furthermore, when the user is training outdoors, the estimation unit can also improve the posture estimation accuracy by taking into account the influence of ambient light. Furthermore, the estimation unit can select an optimal posture estimation algorithm depending on the user's training environment. This improves the estimation accuracy by taking the training environment into account. Some or all of the above-described processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's training environment data into a generation AI, which selects an optimal posture estimation algorithm.

[0037] The estimation unit can customize the estimation algorithm by referring to the user's past training history when estimating posture. The estimation unit customizes the optimal posture estimation algorithm based on, for example, the user's past training history. The estimation unit can also select an algorithm with high accuracy for a specific movement from the user's past training history. The estimation unit can also analyze the user's past training history and switch algorithms depending on the type of training. In this way, the estimation algorithm can be customized by referring to the past training history. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's past training history data into a generation AI, which then customizes the optimal posture estimation algorithm.

[0038] The estimation unit can adjust the estimation accuracy during posture estimation, taking into account the user's health condition. For example, the estimation unit analyzes the user's fatigue level in real time and adjusts the posture estimation accuracy. The estimation unit can also analyze the user's heart rate and reflect this in the estimation result. The estimation unit can also dynamically adjust the posture estimation algorithm according to the user's health condition. This improves estimation accuracy by taking the health condition into consideration. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the posture estimation algorithm.

[0039] The comparison unit can improve the accuracy of the comparison by referencing footage of the trainer's video from different angles during the comparison. For example, the comparison unit can compare the user's posture from multiple angles by referencing front and side footage of the trainer's video. The comparison unit can also improve the accuracy of the comparison by combining footage of the trainer's video from different angles. The comparison unit can also compare footage of the trainer's video from different angles while switching between them in real time. This improves the accuracy of the comparison by referring to footage from different angles. Some or all of the above-described processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the trainer's video data into a generation AI, which analyzes the footage from different angles to improve the accuracy of the comparison.

[0040] The comparison unit can adjust the comparison result by taking into account the consistency of the user's movements during comparison. For example, the comparison unit stabilizes the comparison result when the user's movements are consistent. The comparison unit can also dynamically adjust the comparison result when the user's movements are unstable. The comparison unit can also analyze the consistency of the user's movements in real time and reflect this in the comparison result. This stabilizes the comparison result by taking the consistency of the movements into account. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the user's movement data into a generation AI, which analyzes the consistency of the movements and adjusts the comparison result.

[0041] During comparison, the comparison unit can analyze the speed and rhythm of the user's movements and reflect them in the comparison results. The comparison unit can, for example, analyze the user's movement speed in real time and reflect them in the comparison results. The comparison unit can also analyze the user's movement rhythm and reflect them in the comparison results. The comparison unit can also dynamically adjust the comparison results according to the user's movement speed and rhythm. In this way, the movement speed and rhythm can be analyzed and reflected in the comparison results. Some or all of the above-mentioned processing in the comparison unit can be performed using, for example, AI, or can be performed without using AI. For example, the comparison unit inputs the user's movement data to a generation AI, which analyzes the movement speed and rhythm and reflects them in the comparison results.

[0042] The comparison unit can improve the comparison accuracy by taking into account the user's training environment during comparison. For example, when the user is training indoors, the comparison unit adjusts the comparison accuracy by taking into account lighting conditions. Furthermore, when the user is training outdoors, the comparison unit can improve the comparison accuracy by taking into account the influence of ambient light. Furthermore, the comparison unit can select an optimal comparison algorithm depending on the user's training environment. This improves the comparison accuracy by taking the training environment into account. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the user's training environment data into a generation AI, which selects the optimal comparison algorithm.

[0043] The comparison unit can customize the comparison algorithm by referring to the user's past training history when making the comparison. The comparison unit customizes the optimal comparison algorithm based on, for example, the user's past training history. The comparison unit can also select an algorithm with high accuracy for a specific movement from the user's past training history. The comparison unit can also analyze the user's past training history and switch algorithms depending on the type of training. This allows the comparison algorithm to be customized by referring to the past training history. Some or all of the above-described processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the user's past training history data into a generation AI, which then customizes the optimal comparison algorithm.

[0044] The comparison unit can adjust the comparison accuracy during comparison, taking into account the user's health condition. For example, the comparison unit analyzes the user's fatigue level in real time and adjusts the comparison accuracy. The comparison unit can also analyze the user's heart rate and reflect this in the comparison results. The comparison unit can also dynamically adjust the comparison algorithm according to the user's health condition. This improves the comparison accuracy by taking the health condition into consideration. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the comparison algorithm.

[0045] When providing instruction, the instruction unit can select the optimal instruction method by referring to the user's past training data. For example, the instruction unit selects the optimal instruction method based on the user's past training data. The instruction unit can also select an effective instruction method for a specific movement from the user's past training data. The instruction unit can also analyze the user's past training data and switch instruction methods depending on the type of training. In this way, the optimal instruction method can be selected by referring to the past training data. Some or all of the above-mentioned processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit inputs the user's past training data into a generation AI, which selects the optimal instruction method.

[0046] The training unit can customize the training content by taking into account the user's body shape and muscle condition when providing training. The training unit customizes the training content based on, for example, the user's body shape data. The training unit can also analyze the user's muscle condition in real time and adjust the training content. The training unit can also provide training that focuses on specific parts according to the user's body shape and muscle condition. This allows the training content to be customized by taking into account the body shape and muscle condition. Some or all of the above-mentioned processing in the training unit may be performed using, for example, AI, or may be performed without using AI. For example, the training unit inputs the user's body shape data into a generation AI, and the generation AI customizes the training content.

[0047] The instruction unit can analyze the user's movement speed and rhythm during instruction and reflect the results in the instruction content. For example, the instruction unit can analyze the user's movement speed in real time and adjust the instruction content. The instruction unit can also analyze the user's movement rhythm and reflect the results in the instruction content. The instruction unit can also dynamically adjust the instruction content according to the user's movement speed and rhythm. In this way, the analysis of the movement speed and rhythm can be reflected in the instruction content. Some or all of the above-mentioned processing in the instruction unit can be performed using, for example, AI, or can be performed without using AI. For example, the instruction unit inputs the user's movement data to a generation AI, which analyzes the movement speed and rhythm and reflects them in the instruction content.

[0048] The training unit can adjust the training content during training by taking into account the user's training environment. For example, if the user is training indoors, the training unit can adjust the training content by taking into account lighting conditions. Furthermore, if the user is training outdoors, the training unit can adjust the training content by taking into account the influence of ambient light. Furthermore, the training unit can select an optimal training method depending on the user's training environment. In this way, the training content can be adjusted by taking the training environment into account. Some or all of the above-mentioned processing in the training unit may be performed using, for example, AI, or may be performed without using AI. For example, the training unit inputs the user's training environment data into a generation AI, which then selects the optimal training method.

[0049] The training unit can customize the training algorithm by referring to the user's past training history when providing training. The training unit customizes the optimal training algorithm based on, for example, the user's past training history. The training unit can also select a training algorithm that is effective for a specific movement from the user's past training history. The training unit can also analyze the user's past training history and switch algorithms depending on the type of training. In this way, the training algorithm can be customized by referring to the past training history. Some or all of the above-mentioned processing in the training unit may be performed using, for example, AI, or may be performed without using AI. For example, the training unit inputs the user's past training history data into a generation AI, which then customizes the optimal training algorithm.

[0050] The instruction unit can adjust the instruction content taking into account the user's health condition when providing instruction. For example, the instruction unit analyzes the user's fatigue level in real time and adjusts the instruction content. The instruction unit can also analyze the user's heart rate and reflect this in the instruction content. The instruction unit can also dynamically adjust the instruction algorithm according to the user's health condition. This allows the instruction content to be adjusted by taking the health condition into consideration. Some or all of the above-mentioned processing in the instruction unit may be performed using AI, for example, or may be performed without using AI. For example, the instruction unit inputs the user's health condition data into a generation AI, and the generation AI adjusts the instruction algorithm.

[0051] When generating a training menu, the generation unit can select an optimal menu by referring to the user's past training data. The generation unit, for example, selects an optimal training menu based on the user's past training data. The generation unit can also select a menu that is effective for a specific movement from the user's past training data. The generation unit can also analyze the user's past training data and switch menus depending on the type of training. In this way, the optimal training menu can be selected by referring to the past training data. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's past training data into the generation AI, which selects an optimal training menu.

[0052] When generating a training menu, the generation unit can customize the menu taking into consideration the user's body shape and muscle condition. The generation unit customizes the training menu based on, for example, the user's body shape data. The generation unit can also analyze the user's muscle condition in real time and adjust the menu. The generation unit can also generate a training menu that focuses on a specific part of the body according to the user's body shape and muscle condition. This allows the training menu to be customized by taking into consideration the body shape and muscle condition. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's body shape data into the generation AI, and the generation AI customizes the training menu.

[0053] When generating a training menu, the generation unit can analyze the user's movement speed and rhythm and reflect the results in the menu. For example, the generation unit can analyze the user's movement speed in real time and adjust the training menu. The generation unit can also analyze the user's movement rhythm and reflect the results in the menu. The generation unit can also dynamically adjust the training menu according to the user's movement speed and rhythm. In this way, the movement speed and rhythm can be analyzed and reflected in the training menu. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's movement data into the generation AI, which analyzes the movement speed and rhythm and reflects the results in the menu.

[0054] When generating a training menu, the generation unit can adjust the menu taking into account the user's training environment. For example, when the user is training indoors, the generation unit adjusts the menu taking into account lighting conditions. Furthermore, when the user is training outdoors, the generation unit can adjust the menu taking into account the influence of ambient light. Furthermore, the generation unit can select an optimal training menu according to the user's training environment. In this way, the menu can be adjusted by taking the training environment into account. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's training environment data into the generation AI, which selects an optimal training menu.

[0055] When generating a training menu, the generation unit can customize the menu by referring to the user's past training history. The generation unit customizes an optimal training menu based on, for example, the user's past training history. The generation unit can also select a menu that is effective for a specific movement from the user's past training history. The generation unit can also analyze the user's past training history and switch menus depending on the type of training. In this way, the menu can be customized by referring to the past training history. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's past training history data into the generation AI, which then customizes an optimal training menu.

[0056] When generating a training menu, the generation unit can adjust the menu taking into account the user's health condition. For example, the generation unit analyzes the user's fatigue level in real time and adjusts the training menu. The generation unit can also analyze the user's heart rate and reflect this in the menu. The generation unit can also dynamically adjust the training menu according to the user's health condition. This allows the menu to be adjusted by taking the health condition into consideration. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the training menu.

[0057] When analyzing food photos, the analysis unit can select the optimal analysis method by referring to the user's past meal data. For example, the analysis unit selects the optimal analysis method based on the user's past meal data. The analysis unit can also select an analysis method that is effective for specific ingredients from the user's past meal data. The analysis unit can also analyze the user's past meal data and switch analysis methods depending on the type of meal. This makes it possible to select the optimal analysis method by referring to the past meal data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past meal data into the generation AI, which then selects the optimal analysis method.

[0058] When analyzing food photos, the analysis unit can improve analysis accuracy by taking into account the user's eating habits and preferences. The analysis unit improves analysis accuracy, for example, based on the user's eating habits. The analysis unit can also analyze the user's preferences in real time to improve analysis accuracy. The analysis unit can also perform analysis focusing on specific ingredients according to the user's eating habits and preferences. This improves analysis accuracy by taking into account the eating habits and preferences. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's eating habit data into the generation AI, and the generation AI improves analysis accuracy.

[0059] When analyzing meal photos, the analysis unit can adjust the analysis results taking into account the user's health condition. For example, the analysis unit analyzes the user's weight in real time and adjusts the analysis results. The analysis unit can also analyze the user's blood pressure and reflect this in the analysis results. The analysis unit can also dynamically adjust the analysis algorithm according to the user's health condition. This allows the analysis results to be adjusted by taking the health condition into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the analysis results.

[0060] When analyzing food photos, the analysis unit can improve analysis accuracy by taking into account the user's dining environment. For example, if the user is eating at home, the analysis unit applies an analysis method specialized for home cooking. Furthermore, if the user is eating at a restaurant, the analysis unit can also apply an analysis method based on the restaurant menu. Furthermore, the analysis unit can select an optimal analysis algorithm depending on the user's dining environment. This improves analysis accuracy by taking the dining environment into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's dining environment data into a generation AI, which then selects an optimal analysis algorithm.

[0061] When analyzing food photos, the analysis unit can customize the analysis algorithm by referring to the user's past meal history. The analysis unit, for example, customizes the optimal analysis algorithm based on the user's past meal history. The analysis unit can also select an analysis algorithm that is effective for specific ingredients from the user's past meal history. The analysis unit can also analyze the user's past meal history and switch the analysis algorithm depending on the type of meal. In this way, the analysis algorithm can be customized by referring to the past meal history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past meal history data into the generation AI, which then customizes the optimal analysis algorithm.

[0062] When analyzing food photos, the analysis unit can customize the analysis algorithm by referring to the user's past meal history. The analysis unit, for example, customizes the optimal analysis algorithm based on the user's past meal history. The analysis unit can also select an analysis algorithm that is effective for specific ingredients from the user's past meal history. The analysis unit can also analyze the user's past meal history and switch the analysis algorithm depending on the type of meal. In this way, the analysis algorithm can be customized by referring to the past meal history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past meal history data into the generation AI, which then customizes the optimal analysis algorithm.

[0063] When analyzing meal photos, the analysis unit can adjust the analysis accuracy taking into account the user's health condition. The analysis unit, for example, analyzes the user's weight in real time and adjusts the analysis accuracy. The analysis unit can also analyze the user's blood pressure and reflect this in the analysis results. The analysis unit can also dynamically adjust the analysis algorithm according to the user's health condition. This improves the analysis accuracy by taking the health condition into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the analysis accuracy.

[0064] When analyzing nutritional values, the analysis unit can select the optimal analysis method by referring to the user's past dietary data. For example, the analysis unit selects the optimal nutritional value analysis method based on the user's past dietary data. The analysis unit can also select an analysis method that is effective for specific nutrients from the user's past dietary data. The analysis unit can also analyze the user's past dietary data and switch the analysis method depending on the type of meal. This makes it possible to select the optimal analysis method by referring to the past dietary data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past dietary data into the generation AI, which then selects the optimal nutritional value analysis method.

[0065] The analysis unit can improve the accuracy of the analysis by taking into account the user's eating habits and preferences when analyzing nutritional values. The analysis unit improves the analysis accuracy, for example, based on the user's eating habits. The analysis unit can also improve the analysis accuracy by analyzing the user's preferences in real time. The analysis unit can also perform an analysis that focuses on specific nutrients according to the user's eating habits and preferences. This improves the analysis accuracy by taking into account the eating habits and preferences. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's eating habit data into the generation AI, and the generation AI improves the analysis accuracy.

[0066] The analysis unit can adjust the analysis results taking into account the user's health condition when analyzing nutritional values. For example, the analysis unit analyzes the user's weight in real time and adjusts the analysis results. The analysis unit can also analyze the user's blood pressure and reflect this in the analysis results. The analysis unit can also dynamically adjust the analysis algorithm according to the user's health condition. This allows the analysis results to be adjusted by taking the health condition into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the analysis results.

[0067] The analysis unit can improve the accuracy of the analysis by taking into account the user's eating environment when analyzing nutritional values. For example, if the user is eating at home, the analysis unit applies an analysis method specialized for home cooking. Furthermore, if the user is eating at a restaurant, the analysis unit can also apply an analysis method based on the restaurant menu. Furthermore, the analysis unit can select an optimal analysis algorithm depending on the user's eating environment. In this way, taking the eating environment into consideration improves the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's eating environment data into a generation AI, which then selects the optimal analysis algorithm.

[0068] The analysis unit can customize the analysis algorithm by referring to the user's past dietary history when analyzing nutritional values. The analysis unit customizes the optimal analysis algorithm based on the user's past dietary history, for example. The analysis unit can also select an analysis algorithm that is effective for specific nutrients from the user's past dietary history. The analysis unit can also analyze the user's past dietary history and switch the analysis algorithm depending on the type of meal. In this way, the analysis algorithm can be customized by referring to the past dietary history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past dietary history data into the generation AI, which then customizes the optimal analysis algorithm.

[0069] The analysis unit can adjust the analysis accuracy during nutritional value analysis, taking into account the user's health condition. For example, the analysis unit analyzes the user's weight in real time and adjusts the analysis accuracy. The analysis unit can also analyze the user's blood pressure and reflect this in the analysis results. The analysis unit can also dynamically adjust the analysis algorithm according to the user's health condition. This improves the analysis accuracy by taking the health condition into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the analysis accuracy.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The training support system can monitor the user's heart rate in real time during training and adjust the training intensity based on heart rate fluctuations. For example, if the user's heart rate becomes too high, the training support system can instruct the user to reduce the training intensity. If the heart rate is stable, the training support system can also instruct the user to maintain the training intensity. Furthermore, if the heart rate is low, the training support system can instruct the user to increase the training intensity. This makes it possible to provide the optimal training intensity according to the user's heart rate.

[0072] The training support system can analyze the user's breathing pattern during training and provide training guidance based on the breathing rhythm. For example, if the user stops breathing, the training support system can instruct the user to "keep breathing." If the user's breathing is shallow, the system can also instruct the user to "take deep breaths." Furthermore, if the breathing rhythm is disrupted, the system can provide guidance to regulate the rhythm. This makes it possible to provide appropriate training guidance based on the user's breathing pattern.

[0073] The training support system can analyze the user's muscle fatigue level during training in real time and suggest training break times based on the fatigue level. For example, if the user's muscles are fatigued, the training support system can instruct the user to "take a break." Alternatively, if the muscle fatigue level is low, the system can instruct the user to continue training. Furthermore, if a specific muscle is excessively fatigued, the system can suggest a different exercise to rest that muscle. This makes it possible to provide an optimal training plan based on the user's muscle fatigue level.

[0074] The training support system can store a user's posture data during training in the cloud and make it accessible from other devices. For example, if a user is training on a smartphone, the data can be saved in the cloud and viewed later on a tablet or PC. Even if the trainer is in a remote location, sharing the data on the cloud allows the user to receive feedback. Furthermore, by referencing past training data, the user can check their training progress. This allows for efficient management and utilization of the user's training data.

[0075] The training support system can analyze a user's posture data during training and suggest improvements to form for specific movements. For example, if a user is doing squats, it can suggest specific improvements to knee position or back angle. Also, if a user is doing push-ups, it can provide advice on hand position and elbow angle. Furthermore, when it comes to running form, it can suggest improvements to foot landing position and arm swing. This allows users to understand how to improve their form for specific movements and perform more effective training.

[0076] The processing flow of the first embodiment will be briefly explained below.

[0077] Step 1: The estimation unit estimates the user's posture. For example, the estimation unit takes a video taken with a smartphone camera as input and estimates the user's posture using image recognition technology. The estimation unit can also estimate the user's posture in real time. For example, when a user is doing squats, the estimation unit analyzes the angle of the knees and the degree of curvature of the back to estimate the posture. The estimation unit can also use a generation AI to estimate the user's posture. For example, the generation AI receives the instruction "Please estimate the user's posture" as a prompt to estimate the user's posture, and estimates the posture. Step 2: The comparison unit compares the posture estimated by the estimation unit with the posture of the trainer. The comparison unit, for example, calculates the angle difference or positional deviation between the estimated posture and the posture of the trainer. The comparison unit can also calculate the similarity between the estimated posture and the posture of the trainer. For example, the comparison unit calculates the posture similarity using cosine similarity. The comparison unit can also visually display the difference between the estimated posture and the posture of the trainer. For example, the comparison unit can superimpose the posture of the user and the posture of the trainer to visually indicate which parts are incorrect. Step 3: The instructor provides guidance in natural language based on the comparison results obtained by the comparison unit. For example, the instructor provides guidance such as "Bend your knees a little more" or "Keep your back straight." The instructor can also provide interjections in natural language to motivate the user. For example, the instructor provides encouraging words in real time such as "Good luck!" or "Try a little harder!"

[0078] (Example 2) A training support system according to an embodiment of the present invention recognizes a user's posture during training using posture estimation technology based on image recognition for videos captured with a smartphone camera and calculates the difference between the video and the trainer's video. This training support system allows a user to capture a video of their posture during training with their smartphone camera, estimates their posture using image recognition technology, and compares it with the trainer's video. The training support system then calculates the difference between the video and the trainer's video and provides posture guidance in natural language in real time. Furthermore, the user's own posture can be overlaid on the trainer's video in real time, allowing the user to visually recognize the difference. Natural language prompts can also be provided to motivate the user. Furthermore, a video generation AI automatically generates videos of optimal training combinations tailored to each individual situation. Finally, the system analyzes nutritional value and manages dietary habits by allowing users to upload photos of their meals. For example, when a user is performing squats, the training support system analyzes the user's knee angle and back curvature and compares them with the trainer's correct posture. The system then calculates the difference between the video and the trainer's video and provides posture guidance in natural language in real time. For example, instructions such as "Bend your knees a little more" or "Keep your back straight" are given, allowing users to learn correct posture in real time. Furthermore, the training support system allows users to visually recognize differences by overlaying their own posture on the trainer's video in real time. For example, the user's posture is displayed superimposed on the trainer's, allowing them to see at a glance which parts are incorrect. Natural language interjections also motivate users. For example, encouraging words such as "Good luck!" or "Let's try a little harder!" are provided in real time. Furthermore, video generation AI automatically generates videos with optimal training combinations tailored to each individual situation. For example, optimal training menus are suggested based on the user's training history and current physical condition. Finally, users can upload photos of their meals, which allows for nutritional analysis and dietary management.For example, a system can analyze calorie and nutrient intake from a photo of a meal and suggest a balanced diet. This enables health management from both the training and diet perspectives. This allows the training support system to estimate the user's posture in real time and provide guidance by comparing it with the trainer's posture. For example, when a user is performing squats, the system analyzes the user's knee angle and back curvature and compares them with the trainer's correct posture. The training support system then calculates the difference between the user's posture and the trainer's video and provides real-time posture guidance in natural language. For example, instructions such as "Bend your knees a little more" or "Keep your back straight" are given. This allows the user to learn correct posture in real time. Furthermore, the training support system can visually recognize the difference by overlaying the user's posture on the trainer's video in real time. For example, the user's posture is superimposed on the trainer's posture, allowing the user to see at a glance which parts are incorrect. Furthermore, natural language prompts can motivate the user. For example, encouraging words such as "Good luck!" or "Let's try a little harder!" are provided in real time. Furthermore, video generation AI automatically generates videos of optimal training combinations tailored to each situation. For example, the system suggests optimal training menus based on the user's training history and current physical condition. Finally, users can upload photos of their meals, which are then analyzed for nutritional value and used to manage their diet. For example, the system analyzes calorie and nutrient intake from photos of meals and suggests balanced meals. This makes it possible to manage health from both training and dietary perspectives.

[0079] A training support system according to an embodiment includes an estimation unit, a comparison unit, and an instruction unit. The estimation unit estimates a user's posture. For example, the estimation unit receives a video captured by a smartphone camera as input and estimates the user's posture using image recognition technology. The estimation unit can also estimate the user's posture in real time. For example, when a user is performing squats, the estimation unit analyzes the knee angle and the degree of curvature of the back to estimate the posture. The estimation unit can also use a generation AI to estimate the user's posture. For example, the generation AI receives an instruction such as "Please estimate the user's posture" as a prompt for estimating the user's posture, and estimates the posture. The comparison unit compares the posture estimated by the estimation unit with the trainer's posture. For example, the comparison unit calculates the angle difference or positional deviation between the estimated posture and the trainer's posture. The comparison unit can also calculate the similarity between the estimated posture and the trainer's posture. For example, the comparison unit calculates the posture similarity using cosine similarity. The comparison unit can also visually display the difference between the estimated posture and the trainer's posture. For example, the comparison unit may superimpose the user's posture and the trainer's posture to visually indicate which parts are incorrect. The instruction unit provides instruction in natural language based on the comparison result obtained by the comparison unit. For example, the instruction unit may provide instructions such as, "Bend your knees a little more" or "Keep your back straight." The instruction unit may also provide interjections in natural language to motivate the user. For example, the instruction unit may provide encouraging words in real time, such as, "Good luck!" or "Let's try a little harder!" In this way, the training support system according to the embodiment can estimate the user's posture in real time, compare it with the trainer's posture, and provide instruction. Some or all of the above-described processing by the estimation unit, comparison unit, and instruction unit may be performed using, or without, AI. For example, the estimation unit inputs a video captured with a smartphone camera into the generation AI, which then estimates the posture. The comparison unit takes the estimated posture and the trainer's posture as input and calculates the similarity using an AI model that outputs the similarity.The instruction department provides instruction using an AI model that takes the comparison results as input and outputs instructions in natural language.

[0080] The training support system includes a generation unit that generates a training menu. The generation unit generates an optimal training menu based on the user's training history and current physical condition. For example, the generation unit receives the user's past training data as input and generates an optimal training menu using a generation AI. The generation unit can also receive the user's current physical condition data as input and adjust the training menu using the generation AI. For example, the generation unit adjusts the training menu based on the user's heart rate and fatigue level. The generation unit can also generate an individually customized training menu by combining the user's training history and physical condition data. For example, the generation unit adjusts the number of repetitions and sets of a specific exercise based on the user's past training data and current physical condition data. This allows the training support system to generate an optimal training menu based on the user's training history and current physical condition. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit inputs the user's training history data into the generation AI, which then generates an optimal training menu.

[0081] The training support system includes an analysis unit that analyzes food photos. The analysis unit analyzes food photos uploaded by a user and analyzes calorie and nutrient intake. For example, the analysis unit inputs food photos, identifies ingredients using image recognition technology, and calculates calorie and nutrient intake. The analysis unit can also improve analysis accuracy by taking into account the resolution and shooting angle of the food photos. For example, the analysis unit prioritizes analysis of high-resolution photos to accurately calculate calories. The analysis unit can also adjust the analysis results by taking into account the user's eating habits and preferences. For example, the analysis unit customizes the analysis results based on the user's preferred ingredients and ingredients to avoid. This allows the training support system to analyze food photos uploaded by a user and analyze calorie and nutrient intake. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit inputs food photo data to a generation AI, which identifies ingredients and calculates calories.

[0082] The training support system includes an analysis unit that analyzes nutritional values. The analysis unit suggests a balanced meal based on the analyzed data. For example, the analysis unit inputs calorie and nutrient intake data and suggests a balanced meal using AI. The analysis unit can also customize the meal suggestions based on the user's health condition and goals. For example, the analysis unit suggests meals with specific nutrients increased or decreased based on the user's weight and blood pressure. The analysis unit can also make individually customized meal suggestions taking into account the user's dietary history and preferences. For example, the analysis unit suggests a balanced meal menu based on the user's favorite ingredients. This allows the training support system to suggest a balanced meal based on the analyzed data. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit inputs calorie and nutrient intake data to a generation AI, which then suggests a balanced meal.

[0083] The estimation unit can estimate the user's emotions and adjust the accuracy of posture estimation based on the estimated user emotions. For example, if the user is feeling stressed, the estimation unit performs more detailed image analysis to improve posture estimation accuracy. Furthermore, if the user is relaxed, the estimation unit can return the posture estimation accuracy to a normal setting and prioritize processing speed. Furthermore, if the user is in a hurry, the estimation unit can prioritize real-time performance even if it means slightly lowering the posture estimation accuracy. This enables more accurate posture estimation by adjusting the posture estimation accuracy according to the user's emotions. 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-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit inputs the user's facial expression data into the generation AI, which then estimates the emotion and adjusts the posture estimation accuracy based on the result.

[0084] The estimation unit can select a posture estimation algorithm by referring to the user's past posture data. For example, the estimation unit selects the most suitable posture estimation algorithm based on posture data from training sessions the user has performed in the past. The estimation unit can also select an algorithm with high accuracy for a specific movement from the user's past posture data. The estimation unit can also analyze the user's past posture data and switch algorithms depending on the type of training. In this way, the optimal posture estimation algorithm can be selected by referring to the past posture data. Some or all of the above-described processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's past posture data into a generation AI, which then selects the optimal posture estimation algorithm.

[0085] The estimation unit can improve the accuracy of posture estimation by taking into account the user's body shape and muscle condition. The estimation unit, for example, customizes the posture estimation algorithm based on the user's body shape data. The estimation unit can also analyze the user's muscle condition in real time to improve the accuracy of posture estimation. The estimation unit can also perform posture estimation focusing on specific parts depending on the user's body shape and muscle condition. This improves the estimation accuracy by taking into account the user's body shape and muscle condition. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's body shape data into a generation AI, and the generation AI customizes the posture estimation algorithm.

[0086] The estimation unit can analyze the user's movement speed and rhythm during posture estimation and reflect them in the estimation result. For example, the estimation unit can analyze the user's movement speed in real time and adjust the accuracy of posture estimation. The estimation unit can also analyze the user's movement rhythm and reflect them in the estimation result. The estimation unit can also dynamically adjust the posture estimation algorithm according to the user's movement speed and rhythm. In this way, the user's movement speed and rhythm can be analyzed and reflected in the estimation result. Some or all of the above-mentioned processing in the estimation unit can be performed using, for example, AI, or can be performed without using AI. For example, the estimation unit inputs the user's movement data to a generation AI, which analyzes the movement speed and rhythm and reflects them in the estimation result.

[0087] The estimation unit can estimate the user's emotions and adjust the display method of the estimation results based on the estimated user emotions. For example, if the user is nervous, the estimation unit provides a simple, highly visible display method. Furthermore, if the user is relaxed, the estimation unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the estimation unit can provide a display method that focuses on the main points. This enables more appropriate feedback by adjusting the display method of the estimation results according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation 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 estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit inputs the user's facial expression data into the generation AI, which then estimates the emotion and adjusts the display method of the estimation results based on the result.

[0088] The estimation unit can improve the estimation accuracy during posture estimation by taking into account the user's training environment. For example, when the user is training indoors, the estimation unit adjusts the posture estimation accuracy by taking into account lighting conditions. Furthermore, when the user is training outdoors, the estimation unit can also improve the posture estimation accuracy by taking into account the influence of ambient light. Furthermore, the estimation unit can select an optimal posture estimation algorithm depending on the user's training environment. This improves the estimation accuracy by taking the training environment into account. Some or all of the above-described processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's training environment data into a generation AI, which selects an optimal posture estimation algorithm.

[0089] The estimation unit can customize the estimation algorithm by referring to the user's past training history when estimating posture. The estimation unit customizes the optimal posture estimation algorithm based on, for example, the user's past training history. The estimation unit can also select an algorithm with high accuracy for a specific movement from the user's past training history. The estimation unit can also analyze the user's past training history and switch algorithms depending on the type of training. In this way, the estimation algorithm can be customized by referring to the past training history. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's past training history data into a generation AI, which then customizes the optimal posture estimation algorithm.

[0090] The estimation unit can adjust the estimation accuracy during posture estimation, taking into account the user's health condition. For example, the estimation unit analyzes the user's fatigue level in real time and adjusts the posture estimation accuracy. The estimation unit can also analyze the user's heart rate and reflect this in the estimation result. The estimation unit can also dynamically adjust the posture estimation algorithm according to the user's health condition. This improves estimation accuracy by taking the health condition into consideration. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the posture estimation algorithm.

[0091] The comparison unit can estimate the user's emotions and adjust the comparison criteria based on the estimated user emotions. For example, if the user is nervous, the comparison unit can relax the comparison criteria to make the user feel at ease. The comparison unit can also apply normal comparison criteria when the user is relaxed. If the user is in a hurry, the comparison unit can tighten the comparison criteria and provide quick feedback. This enables more appropriate comparison by adjusting the comparison criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 comparison unit can be performed using, for example, AI, or without AI. For example, the comparison unit inputs the user's facial expression data into the generation AI, which then estimates the emotion and adjusts the comparison criteria based on the result.

[0092] The comparison unit can improve the accuracy of the comparison by referencing footage of the trainer's video from different angles during the comparison. For example, the comparison unit can compare the user's posture from multiple angles by referencing front and side footage of the trainer's video. The comparison unit can also improve the accuracy of the comparison by combining footage of the trainer's video from different angles. The comparison unit can also compare footage of the trainer's video from different angles while switching between them in real time. This improves the accuracy of the comparison by referring to footage from different angles. Some or all of the above-described processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the trainer's video data into a generation AI, which analyzes the footage from different angles to improve the accuracy of the comparison.

[0093] The comparison unit can adjust the comparison result by taking into account the consistency of the user's movements during comparison. For example, the comparison unit stabilizes the comparison result when the user's movements are consistent. The comparison unit can also dynamically adjust the comparison result when the user's movements are unstable. The comparison unit can also analyze the consistency of the user's movements in real time and reflect this in the comparison result. This stabilizes the comparison result by taking the consistency of the movements into account. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the user's movement data into a generation AI, which analyzes the consistency of the movements and adjusts the comparison result.

[0094] During comparison, the comparison unit can analyze the speed and rhythm of the user's movements and reflect them in the comparison results. The comparison unit can, for example, analyze the user's movement speed in real time and reflect them in the comparison results. The comparison unit can also analyze the user's movement rhythm and reflect them in the comparison results. The comparison unit can also dynamically adjust the comparison results according to the user's movement speed and rhythm. In this way, the movement speed and rhythm can be analyzed and reflected in the comparison results. Some or all of the above-mentioned processing in the comparison unit can be performed using, for example, AI, or can be performed without using AI. For example, the comparison unit inputs the user's movement data to a generation AI, which analyzes the movement speed and rhythm and reflects them in the comparison results.

[0095] The comparison unit can estimate the user's emotion and adjust the display method of the comparison results based on the estimated user emotion. For example, if the user is nervous, the comparison unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the comparison unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the comparison unit can provide a display method that focuses on the main points. This enables more appropriate feedback by adjusting the display method of the comparison results according to the user's emotion. The emotion estimation is realized 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 comparison unit can be performed using, for example, AI, or without AI. For example, the comparison unit inputs the user's facial expression data into the generation AI, which then estimates the emotion and adjusts the display method of the comparison results based on the estimation result.

[0096] The comparison unit can improve the comparison accuracy by taking into account the user's training environment during comparison. For example, when the user is training indoors, the comparison unit adjusts the comparison accuracy by taking into account lighting conditions. Furthermore, when the user is training outdoors, the comparison unit can improve the comparison accuracy by taking into account the influence of ambient light. Furthermore, the comparison unit can select an optimal comparison algorithm depending on the user's training environment. This improves the comparison accuracy by taking the training environment into account. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the user's training environment data into a generation AI, which selects the optimal comparison algorithm.

[0097] The comparison unit can customize the comparison algorithm by referring to the user's past training history when making the comparison. The comparison unit customizes the optimal comparison algorithm based on, for example, the user's past training history. The comparison unit can also select an algorithm with high accuracy for a specific movement from the user's past training history. The comparison unit can also analyze the user's past training history and switch algorithms depending on the type of training. This allows the comparison algorithm to be customized by referring to the past training history. Some or all of the above-described processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the user's past training history data into a generation AI, which then customizes the optimal comparison algorithm.

[0098] The comparison unit can adjust the comparison accuracy during comparison, taking into account the user's health condition. For example, the comparison unit analyzes the user's fatigue level in real time and adjusts the comparison accuracy. The comparison unit can also analyze the user's heart rate and reflect this in the comparison results. The comparison unit can also dynamically adjust the comparison algorithm according to the user's health condition. This improves the comparison accuracy by taking the health condition into consideration. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the comparison algorithm.

[0099] The instruction unit can estimate the user's emotions and adjust the way in which the instruction is expressed based on the estimated user's emotions. For example, if the user is nervous, the instruction unit can provide gentle instruction. If the user is relaxed, the instruction unit can provide detailed instruction. If the user is in a hurry, the instruction unit can provide concise and quick instruction. This allows for more appropriate instruction by adjusting the way in which the instruction is expressed based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the instruction unit can be performed using, for example, AI, or without AI. For example, the instruction unit inputs the user's facial expression data into the generation AI, which then estimates the user's emotions and adjusts the way in which the instruction is expressed based on the results.

[0100] When providing instruction, the instruction unit can select the optimal instruction method by referring to the user's past training data. For example, the instruction unit selects the optimal instruction method based on the user's past training data. The instruction unit can also select an effective instruction method for a specific movement from the user's past training data. The instruction unit can also analyze the user's past training data and switch instruction methods depending on the type of training. In this way, the optimal instruction method can be selected by referring to the past training data. Some or all of the above-mentioned processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit inputs the user's past training data into a generation AI, which selects the optimal instruction method.

[0101] The training unit can customize the training content by taking into account the user's body shape and muscle condition when providing training. The training unit customizes the training content based on, for example, the user's body shape data. The training unit can also analyze the user's muscle condition in real time and adjust the training content. The training unit can also provide training that focuses on specific parts according to the user's body shape and muscle condition. This allows the training content to be customized by taking into account the body shape and muscle condition. Some or all of the above-mentioned processing in the training unit may be performed using, for example, AI, or may be performed without using AI. For example, the training unit inputs the user's body shape data into a generation AI, and the generation AI customizes the training content.

[0102] The instruction unit can analyze the user's movement speed and rhythm during instruction and reflect the results in the instruction content. For example, the instruction unit can analyze the user's movement speed in real time and adjust the instruction content. The instruction unit can also analyze the user's movement rhythm and reflect the results in the instruction content. The instruction unit can also dynamically adjust the instruction content according to the user's movement speed and rhythm. In this way, the analysis of the movement speed and rhythm can be reflected in the instruction content. Some or all of the above-mentioned processing in the instruction unit can be performed using, for example, AI, or can be performed without using AI. For example, the instruction unit inputs the user's movement data to a generation AI, which analyzes the movement speed and rhythm and reflects them in the instruction content.

[0103] The instruction unit can estimate the user's emotions and adjust the length of the instruction based on the estimated user emotions. For example, if the user is nervous, the instruction unit can provide short, to-the-point instruction. If the user is relaxed, the instruction unit can provide longer instruction with detailed explanations. If the user is in a hurry, the instruction unit can provide quick, concise instruction. This allows for more appropriate instruction by adjusting the length of the instruction according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the instruction unit can be performed using, for example, AI, or without AI. For example, the instruction unit inputs the user's facial expression data into the generation AI, which then estimates the user's emotions and adjusts the length of the instruction based on the estimation result.

[0104] The training unit can adjust the training content during training by taking into account the user's training environment. For example, if the user is training indoors, the training unit can adjust the training content by taking into account lighting conditions. Furthermore, if the user is training outdoors, the training unit can adjust the training content by taking into account the influence of ambient light. Furthermore, the training unit can select an optimal training method depending on the user's training environment. In this way, the training content can be adjusted by taking the training environment into account. Some or all of the above-mentioned processing in the training unit may be performed using, for example, AI, or may be performed without using AI. For example, the training unit inputs the user's training environment data into a generation AI, which then selects the optimal training method.

[0105] The training unit can customize the training algorithm by referring to the user's past training history when providing training. The training unit customizes the optimal training algorithm based on, for example, the user's past training history. The training unit can also select a training algorithm that is effective for a specific movement from the user's past training history. The training unit can also analyze the user's past training history and switch algorithms depending on the type of training. In this way, the training algorithm can be customized by referring to the past training history. Some or all of the above-mentioned processing in the training unit may be performed using, for example, AI, or may be performed without using AI. For example, the training unit inputs the user's past training history data into a generation AI, which then customizes the optimal training algorithm.

[0106] The instruction unit can adjust the instruction content taking into account the user's health condition when providing instruction. For example, the instruction unit analyzes the user's fatigue level in real time and adjusts the instruction content. The instruction unit can also analyze the user's heart rate and reflect this in the instruction content. The instruction unit can also dynamically adjust the instruction algorithm according to the user's health condition. This allows the instruction content to be adjusted by taking the health condition into consideration. Some or all of the above-mentioned processing in the instruction unit may be performed using AI, for example, or may be performed without using AI. For example, the instruction unit inputs the user's health condition data into a generation AI, and the generation AI adjusts the instruction algorithm.

[0107] The generation unit can estimate the user's emotions and adjust the training menu generation method based on the estimated user's emotions. For example, if the user is relaxed, the generation unit generates a training menu that progresses at a leisurely pace. Furthermore, if the user is in a hurry, the generation unit can also generate a short, effective training menu. Furthermore, if the user is excited, the generation unit can generate a training menu that adds visually stimulating effects. By adjusting the training menu generation method according to the user's emotions, a more appropriate menu is generated. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation 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 generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit inputs the user's facial expression data into the generation AI, which then estimates the user's emotions and adjusts the training menu generation method based on the results.

[0108] When generating a training menu, the generation unit can select an optimal menu by referring to the user's past training data. The generation unit, for example, selects an optimal training menu based on the user's past training data. The generation unit can also select a menu that is effective for a specific movement from the user's past training data. The generation unit can also analyze the user's past training data and switch menus depending on the type of training. In this way, the optimal training menu can be selected by referring to the past training data. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's past training data into the generation AI, which selects an optimal training menu.

[0109] When generating a training menu, the generation unit can customize the menu taking into consideration the user's body shape and muscle condition. The generation unit customizes the training menu based on, for example, the user's body shape data. The generation unit can also analyze the user's muscle condition in real time and adjust the menu. The generation unit can also generate a training menu that focuses on a specific part of the body according to the user's body shape and muscle condition. This allows the training menu to be customized by taking into consideration the body shape and muscle condition. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's body shape data into the generation AI, and the generation AI customizes the training menu.

[0110] When generating a training menu, the generation unit can analyze the user's movement speed and rhythm and reflect the results in the menu. For example, the generation unit can analyze the user's movement speed in real time and adjust the training menu. The generation unit can also analyze the user's movement rhythm and reflect the results in the menu. The generation unit can also dynamically adjust the training menu according to the user's movement speed and rhythm. In this way, the movement speed and rhythm can be analyzed and reflected in the training menu. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's movement data into the generation AI, which analyzes the movement speed and rhythm and reflects the results in the menu.

[0111] The generation unit can estimate the user's emotions and adjust the display method of the training menu based on the estimated user emotions. For example, if the user is nervous, the generation unit provides a simple, highly visible display method. Furthermore, if the user is relaxed, the generation unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the generation unit can provide a display method that focuses on the main points. This enables more appropriate feedback by adjusting the display method of the training menu according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation 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 generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit inputs the user's facial expression data into the generation AI, which then estimates the user's emotions and adjusts the display method of the training menu based on the results.

[0112] When generating a training menu, the generation unit can adjust the menu taking into account the user's training environment. For example, when the user is training indoors, the generation unit adjusts the menu taking into account lighting conditions. Furthermore, when the user is training outdoors, the generation unit can adjust the menu taking into account the influence of ambient light. Furthermore, the generation unit can select an optimal training menu according to the user's training environment. In this way, the menu can be adjusted by taking the training environment into account. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's training environment data into the generation AI, which selects an optimal training menu.

[0113] When generating a training menu, the generation unit can customize the menu by referring to the user's past training history. The generation unit customizes an optimal training menu based on, for example, the user's past training history. The generation unit can also select a menu that is effective for a specific movement from the user's past training history. The generation unit can also analyze the user's past training history and switch menus depending on the type of training. In this way, the menu can be customized by referring to the past training history. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's past training history data into the generation AI, which then customizes an optimal training menu.

[0114] When generating a training menu, the generation unit can adjust the menu taking into account the user's health condition. For example, the generation unit analyzes the user's fatigue level in real time and adjusts the training menu. The generation unit can also analyze the user's heart rate and reflect this in the menu. The generation unit can also dynamically adjust the training menu according to the user's health condition. This allows the menu to be adjusted by taking the health condition into consideration. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the training menu.

[0115] The analysis unit can estimate the user's emotions and adjust the analysis method for the food photos based on the estimated user emotions. For example, the analysis unit can perform a detailed analysis when the user is relaxed. The analysis unit can also perform a concise analysis when the user is in a hurry. The analysis unit can also perform an analysis that adds visually stimulating effects when the user is excited. This allows for more appropriate analysis by adjusting the analysis method for the food photos according to 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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using AI, or without AI. For example, the analysis unit inputs the user's facial expression data into the generation AI, which then estimates the emotion and adjusts the analysis method for the food photos based on the result.

[0116] When analyzing food photos, the analysis unit can select the optimal analysis method by referring to the user's past meal data. For example, the analysis unit selects the optimal analysis method based on the user's past meal data. The analysis unit can also select an analysis method that is effective for specific ingredients from the user's past meal data. The analysis unit can also analyze the user's past meal data and switch analysis methods depending on the type of meal. This makes it possible to select the optimal analysis method by referring to the past meal data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past meal data into the generation AI, which then selects the optimal analysis method.

[0117] When analyzing food photos, the analysis unit can improve analysis accuracy by taking into account the user's eating habits and preferences. The analysis unit improves analysis accuracy, for example, based on the user's eating habits. The analysis unit can also analyze the user's preferences in real time to improve analysis accuracy. The analysis unit can also perform analysis focusing on specific ingredients according to the user's eating habits and preferences. This improves analysis accuracy by taking into account the eating habits and preferences. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's eating habit data into the generation AI, and the generation AI improves analysis accuracy.

[0118] When analyzing meal photos, the analysis unit can adjust the analysis results taking into account the user's health condition. For example, the analysis unit analyzes the user's weight in real time and adjusts the analysis results. The analysis unit can also analyze the user's blood pressure and reflect this in the analysis results. The analysis unit can also dynamically adjust the analysis algorithm according to the user's health condition. This allows the analysis results to be adjusted by taking the health condition into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the analysis results.

[0119] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit provides a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. This enables more appropriate feedback by adjusting the display method of the analysis results according to 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 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 analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit inputs the user's facial expression data into the generation AI, which then estimates the user's emotions and adjusts the display method of the analysis results based on the estimation result.

[0120] When analyzing food photos, the analysis unit can improve analysis accuracy by taking into account the user's dining environment. For example, if the user is eating at home, the analysis unit applies an analysis method specialized for home cooking. Furthermore, if the user is eating at a restaurant, the analysis unit can also apply an analysis method based on the restaurant menu. Furthermore, the analysis unit can select an optimal analysis algorithm depending on the user's dining environment. This improves analysis accuracy by taking the dining environment into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's dining environment data into a generation AI, which then selects an optimal analysis algorithm.

[0121] When analyzing food photos, the analysis unit can customize the analysis algorithm by referring to the user's past meal history. The analysis unit, for example, customizes the optimal analysis algorithm based on the user's past meal history. The analysis unit can also select an analysis algorithm that is effective for specific ingredients from the user's past meal history. The analysis unit can also analyze the user's past meal history and switch the analysis algorithm depending on the type of meal. In this way, the analysis algorithm can be customized by referring to the past meal history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past meal history data into the generation AI, which then customizes the optimal analysis algorithm.

[0122] When analyzing food photos, the analysis unit can customize the analysis algorithm by referring to the user's past meal history. The analysis unit, for example, customizes the optimal analysis algorithm based on the user's past meal history. The analysis unit can also select an analysis algorithm that is effective for specific ingredients from the user's past meal history. The analysis unit can also analyze the user's past meal history and switch the analysis algorithm depending on the type of meal. In this way, the analysis algorithm can be customized by referring to the past meal history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past meal history data into the generation AI, which then customizes the optimal analysis algorithm.

[0123] When analyzing meal photos, the analysis unit can adjust the analysis accuracy taking into account the user's health condition. The analysis unit, for example, analyzes the user's weight in real time and adjusts the analysis accuracy. The analysis unit can also analyze the user's blood pressure and reflect this in the analysis results. The analysis unit can also dynamically adjust the analysis algorithm according to the user's health condition. This improves the analysis accuracy by taking the health condition into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the analysis accuracy.

[0124] The analysis unit can estimate the user's emotions and adjust the nutritional value analysis method based on the estimated user emotions. For example, if the user is relaxed, the analysis unit can perform a detailed nutritional value analysis. If the user is in a hurry, the analysis unit can also perform a brief nutritional value analysis. If the user is excited, the analysis unit can also perform a nutritional value analysis with visually stimulating effects. This allows for more appropriate analysis by adjusting the nutritional value analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit inputs the user's facial expression data into the generative AI, which then estimates the user's emotions and adjusts the nutritional value analysis method based on the results.

[0125] When analyzing nutritional values, the analysis unit can select the optimal analysis method by referring to the user's past dietary data. For example, the analysis unit selects the optimal nutritional value analysis method based on the user's past dietary data. The analysis unit can also select an analysis method that is effective for specific nutrients from the user's past dietary data. The analysis unit can also analyze the user's past dietary data and switch the analysis method depending on the type of meal. This makes it possible to select the optimal analysis method by referring to the past dietary data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past dietary data into the generation AI, which then selects the optimal nutritional value analysis method.

[0126] The analysis unit can improve the accuracy of the analysis by taking into account the user's eating habits and preferences when analyzing nutritional values. The analysis unit improves the analysis accuracy, for example, based on the user's eating habits. The analysis unit can also improve the analysis accuracy by analyzing the user's preferences in real time. The analysis unit can also perform an analysis that focuses on specific nutrients according to the user's eating habits and preferences. This improves the analysis accuracy by taking into account the eating habits and preferences. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's eating habit data into the generation AI, and the generation AI improves the analysis accuracy.

[0127] The analysis unit can adjust the analysis results taking into account the user's health condition when analyzing nutritional values. For example, the analysis unit analyzes the user's weight in real time and adjusts the analysis results. The analysis unit can also analyze the user's blood pressure and reflect this in the analysis results. The analysis unit can also dynamically adjust the analysis algorithm according to the user's health condition. This allows the analysis results to be adjusted by taking the health condition into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the analysis results.

[0128] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit provides a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. This enables more appropriate feedback by adjusting the display method of the analysis results according to 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 analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit inputs the user's facial expression data into the generation AI, which then estimates the user's emotions and adjusts the display method of the analysis results based on the estimation result.

[0129] The analysis unit can improve the accuracy of the analysis by taking into account the user's eating environment when analyzing nutritional values. For example, if the user is eating at home, the analysis unit applies an analysis method specialized for home cooking. Furthermore, if the user is eating at a restaurant, the analysis unit can also apply an analysis method based on the restaurant menu. Furthermore, the analysis unit can select an optimal analysis algorithm depending on the user's eating environment. In this way, taking the eating environment into consideration improves the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's eating environment data into a generation AI, which then selects the optimal analysis algorithm.

[0130] The analysis unit can customize the analysis algorithm by referring to the user's past dietary history when analyzing nutritional values. The analysis unit customizes the optimal analysis algorithm based on the user's past dietary history, for example. The analysis unit can also select an analysis algorithm that is effective for specific nutrients from the user's past dietary history. The analysis unit can also analyze the user's past dietary history and switch the analysis algorithm depending on the type of meal. In this way, the analysis algorithm can be customized by referring to the past dietary history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's past dietary history data into the generation AI, which then customizes the optimal analysis algorithm.

[0131] The analysis unit can adjust the analysis accuracy during nutritional value analysis, taking into account the user's health condition. For example, the analysis unit analyzes the user's weight in real time and adjusts the analysis accuracy. The analysis unit can also analyze the user's blood pressure and reflect this in the analysis results. The analysis unit can also dynamically adjust the analysis algorithm according to the user's health condition. This improves the analysis accuracy by taking the health condition into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit inputs the user's health condition data into the generation AI, and the generation AI adjusts the analysis accuracy. === Hard Collateral 1-1 === Each of the multiple elements, including the estimation unit, comparison unit, instruction unit, generation unit, analysis unit, and analysis unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the estimation unit captures a picture of the user's posture using the camera 42 of the smart device 14 and estimates the posture using the control unit 46A. The comparison unit compares the posture estimated by the specific processing unit 290 of the data processing device 12 with the posture of the trainer. The instruction unit provides instruction in natural language based on the comparison result using the specific processing unit 290 of the data processing device 12. The generation unit generates a training menu based on the user's training history and physical condition using the specific processing unit 290 of the data processing device 12. The analysis unit analyzes calorie and nutrient intake using photos of meals taken by the camera 42 of the smart device 14. The analysis unit suggests a balanced meal based on the data analyzed by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned estimation unit, comparison unit, instruction unit, generation unit, analysis unit, and analysis unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the estimation unit photographs the user's posture using the camera 42 of the smart glasses 214 and estimates the posture using the control unit 46A. The comparison unit compares the posture estimated by the specific processing unit 290 of the data processing device 12 with the posture of the trainer. The instruction unit provides instruction in natural language based on the comparison result using the specific processing unit 290 of the data processing device 12. The generation unit generates a training menu based on the user's training history and physical condition using the specific processing unit 290 of the data processing device 12. The analysis unit analyzes calorie and nutrient intake using photos of meals taken by the camera 42 of the smart glasses 214. The analysis unit suggests a balanced meal based on the data analyzed by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements, including the estimation unit, comparison unit, instruction unit, generation unit, analysis unit, and analysis unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the estimation unit photographs the user's posture using the camera 42 of the headset-type terminal 314 and estimates the posture using the control unit 46A. The comparison unit compares the posture estimated by the specific processing unit 290 of the data processing device 12 with the posture of the trainer. The instruction unit provides instruction in natural language based on the comparison result using the specific processing unit 290 of the data processing device 12. The generation unit generates a training menu based on the user's training history and physical condition using the specific processing unit 290 of the data processing device 12. The analysis unit analyzes calorie and nutrient intake using photos of meals taken by the camera 42 of the headset-type terminal 314. The analysis unit suggests a balanced meal based on the data analyzed by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the estimation unit, comparison unit, instruction unit, generation unit, analysis unit, and analysis unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the estimation unit photographs the user's posture using the camera 42 of the robot 414 and estimates the posture using the control unit 46A. The comparison unit compares the posture estimated by the specific processing unit 290 of the data processing device 12 with the posture of the trainer. The instruction unit provides instruction in natural language based on the comparison result using the specific processing unit 290 of the data processing device 12. The generation unit generates a training menu based on the user's training history and physical condition using the specific processing unit 290 of the data processing device 12. The analysis unit analyzes calorie and nutrient intake using photos of meals taken by the camera 42 of the robot 414. The analysis unit suggests a balanced meal based on the data analyzed by the specific processing unit 290 of the data processing device 12.

[0132] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0133] The training support system can monitor the user's heart rate in real time during training and adjust the training intensity based on heart rate fluctuations. For example, if the user's heart rate becomes too high, the training support system can instruct the user to reduce the training intensity. If the heart rate is stable, the training support system can also instruct the user to maintain the training intensity. Furthermore, if the heart rate is low, the training support system can instruct the user to increase the training intensity. This makes it possible to provide the optimal training intensity according to the user's heart rate.

[0134] The training support system can analyze the user's breathing pattern during training and provide training guidance based on the breathing rhythm. For example, if the user stops breathing, the training support system can instruct the user to "keep breathing." If the user's breathing is shallow, the system can also instruct the user to "take deep breaths." Furthermore, if the breathing rhythm is disrupted, the system can provide guidance to regulate the rhythm. This makes it possible to provide appropriate training guidance based on the user's breathing pattern.

[0135] The training support system can analyze the user's muscle fatigue level during training in real time and suggest training break times based on the fatigue level. For example, if the user's muscles are fatigued, the training support system can instruct the user to "take a break." Alternatively, if the muscle fatigue level is low, the system can instruct the user to continue training. Furthermore, if a specific muscle is excessively fatigued, the system can suggest a different exercise to rest that muscle. This makes it possible to provide an optimal training plan based on the user's muscle fatigue level.

[0136] The training support system can store a user's posture data during training in the cloud and make it accessible from other devices. For example, if a user is training on a smartphone, the data can be saved in the cloud and viewed later on a tablet or PC. Even if the trainer is in a remote location, sharing the data on the cloud allows the user to receive feedback. Furthermore, by referencing past training data, the user can check their training progress. This allows for efficient management and utilization of the user's training data.

[0137] The training support system can estimate the user's emotions and play music to increase motivation for training based on the estimated emotions. For example, if the user is tired, it can play upbeat music to invigorate them. If the user is relaxed, it can play calming music to increase concentration. Furthermore, if the user is feeling stressed, it can play music with a relaxing effect. In this way, it is possible to provide the optimal music according to the user's emotions and increase motivation for training.

[0138] The training support system can estimate the user's emotions and customize training feedback based on the estimated emotions. For example, if the user is feeling down, it can provide feedback that includes many encouraging words. If the user is feeling confident, it can provide feedback that points out specific areas for improvement. Furthermore, if the user is feeling impatient, it can provide concise and quick feedback. This makes it possible to provide appropriate feedback according to the user's emotions and maximize the effectiveness of training.

[0139] The training support system can estimate the user's emotions and adjust the training goals based on the estimated emotions. For example, if the user is feeling stressed, the goal can be relaxed a little to make it easier for the user to feel a sense of accomplishment. Also, if the user is relaxed, the goal can be set a little higher to stimulate a desire to take on a challenge. Furthermore, if the user is excited, it is possible to set a goal that can be achieved in a short period of time. This allows the system to set optimal goals according to the user's emotions and maintain motivation for training.

[0140] The training support system can estimate the user's emotions and adjust the progress of the training based on the estimated emotions. For example, if the user is tired, the progress of the training can be slowed down a little to allow the user to continue without straining themselves. Also, if the user is relaxed, the progress of the training can be kept normal. Furthermore, if the user is excited, the progress of the training can be sped up a little to maintain concentration. This makes it possible to provide an optimal training progress according to the user's emotions and improve the effectiveness of the training.

[0141] The training support system can estimate the user's emotions and adjust the timing of training breaks based on the estimated emotions. For example, if the user is tired, it can instruct the user to take an earlier break. If the user is relaxed, it can maintain the normal timing of breaks. Furthermore, if the user is excited, it can delay the break a little to maintain concentration during training. This makes it possible to provide the optimal timing of breaks according to the user's emotions and maximize the effectiveness of training.

[0142] The training support system can analyze a user's posture data during training and suggest improvements to form for specific movements. For example, if a user is doing squats, it can suggest specific improvements to knee position or back angle. Also, if a user is doing push-ups, it can provide advice on hand position and elbow angle. Furthermore, when it comes to running form, it can suggest improvements to foot landing position and arm swing. This allows users to understand how to improve their form for specific movements and perform more effective training.

[0143] The processing flow of the second embodiment will be briefly explained below.

[0144] Step 1: The estimation unit estimates the user's posture. For example, the estimation unit takes a video taken with a smartphone camera as input and estimates the user's posture using image recognition technology. The estimation unit can also estimate the user's posture in real time. For example, when a user is doing squats, the estimation unit analyzes the angle of the knees and the degree of curvature of the back to estimate the posture. The estimation unit can also use a generation AI to estimate the user's posture. For example, the generation AI receives the instruction "Please estimate the user's posture" as a prompt to estimate the user's posture, and estimates the posture. Step 2: The comparison unit compares the posture estimated by the estimation unit with the posture of the trainer. The comparison unit, for example, calculates the angle difference or positional deviation between the estimated posture and the posture of the trainer. The comparison unit can also calculate the similarity between the estimated posture and the posture of the trainer. For example, the comparison unit calculates the posture similarity using cosine similarity. The comparison unit can also visually display the difference between the estimated posture and the posture of the trainer. For example, the comparison unit can superimpose the posture of the user and the posture of the trainer to visually indicate which parts are incorrect. Step 3: The instructor provides guidance in natural language based on the comparison results obtained by the comparison unit. For example, the instructor provides guidance such as "Bend your knees a little more" or "Keep your back straight." The instructor can also provide interjections in natural language to motivate the user. For example, the instructor provides encouraging words in real time such as "Good luck!" or "Try a little harder!"

[0145] 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.

[0146] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] 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.

[0148] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0149] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0163] 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.

[0164] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0165] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0179] 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.

[0180] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0181] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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).

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0196] 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.

[0197] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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).

[0202] 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.

[0203] 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."

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] [Explanation of symbols]

[0217] 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 estimation unit that estimates a posture; a comparison unit that compares the posture estimated by the estimation unit with the posture of the trainer; a unit for providing instruction in natural language based on the comparison result obtained by the comparison unit; Equipped with A system characterized by:

2. A generating unit that generates a training menu is provided.

2. The system of claim 1.

3. Equipped with an analysis unit that analyzes photos of food 2. The system of claim 1.

4. Equipped with an analysis unit that analyzes nutritional values 2. The system of claim 1.

5. The estimation unit Estimate the user's emotion and adjust the accuracy of posture estimation based on the estimated user emotion.

2. The system of claim 1.

6. The estimation unit Select a posture estimation algorithm based on the user's past posture data.

2. The system of claim 1.

7. The estimation unit Improve posture estimation accuracy by taking into account the user's body shape and muscle condition 2. The system of claim 1.

8. The estimation unit When estimating posture, the speed and rhythm of the user's movements are analyzed and reflected in the estimation results.

2. The system of claim 1.

Images