system

Abstract

The system according to this embodiment aims to identify errors in the movements of athletes and provide real-time feedback. [Solution] The system according to the embodiment comprises a video capture unit, an analysis unit, a feedback unit, and a training plan generation unit. The video capture unit captures the movements of athletes on video. The analysis unit analyzes the video captured by the video capture unit and identifies errors in form. The feedback unit provides real-time feedback based on the errors in form identified by the analysis unit. The training plan generation unit generates an individualized training plan based on the feedback provided by the feedback unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to identify errors in the actions of sports players in real time and provide immediate feedback.

[0005] The system according to the embodiment aims to identify errors in the actions of sports players and provide feedback in real time.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a video capture unit, an analysis unit, a feedback unit, and a training plan generation unit. The video capture unit captures the movements of an athlete on video. The analysis unit analyzes the video captured by the video capture unit and identifies errors in form. The feedback unit provides real-time feedback based on the errors in form identified by the analysis unit. The training plan generation unit generates an individualized training plan based on the feedback provided by the feedback unit. [Effects of the Invention]

[0007] The system according to this embodiment can identify errors in the movements of athletes and provide real-time feedback. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An AI agent according to an embodiment of the present invention is a system that video-analyzes the movements of athletes, identifies errors in their form, and provides specific improvement suggestions. This system utilizes generative AI to capture subtle nuances of movement and provide effective training methods. For example, a video capture unit captures the movements of athletes on video, and an analysis unit analyzes the captured video to identify errors in form. A feedback unit provides real-time feedback to the athlete, prompting immediate improvement of their form. A training plan generation unit generates an individualized training plan based on the analysis results. This increases the rate of performance improvement, reduces the risk of injury, and maximizes training efficiency. The AI ​​agent is useful for competitive athletes, amateur sports enthusiasts aiming to improve their skills, sports coaches, and trainers. By utilizing multimodal AI, comprehensive analysis becomes possible, and customization based on individual movement data is realized. This supports sustainable improvement of athletic ability. As a result, the AI ​​agent can efficiently capture, analyze, provide feedback on, and generate training plans for athletes' movements.

[0029] The AI ​​agent according to this embodiment comprises a video capture unit, an analysis unit, a feedback unit, and a training plan generation unit. The video capture unit captures the movements of an athlete on video. For example, the video capture unit films the movements of an athlete with a high-resolution camera and saves it as video data. The video capture unit can also use multiple cameras to film from different angles simultaneously. For example, the video capture unit can simultaneously capture the movements of an athlete from the front, side, and rear, enabling detailed motion analysis. The video capture unit can also use a drone to film from the air. For example, the video capture unit can use a drone to capture the movements of an athlete from above, grasping the overall flow of movement. The analysis unit uses a generation AI to analyze the video captured by the video capture unit and identify errors in form. For example, the analysis unit receives the video data as input from the generation AI and analyzes the fine nuances of the movements. For example, the generation AI analyzes the athlete's posture and the timing of their movements to identify errors in form. The analysis unit can also use the generation AI to analyze movement patterns and identify the causes of errors. For example, the generating AI learns the player's movement patterns and identifies error tendencies. The feedback unit provides real-time feedback based on the form errors identified by the analysis unit. The feedback unit provides feedback to the player, for example, through audio or visual means. The feedback unit monitors the player's movements in real time and provides feedback the moment an error occurs. The feedback unit can also play back the player's movements on video and highlight the error areas. For example, the feedback unit can display the error areas in red during video playback, providing visual feedback to the player. The training plan generation unit generates an individualized training plan based on the feedback provided by the feedback unit. The training plan generation unit generates training menus tailored to the player's characteristics and goals, for example. The training plan generation unit generates training plans to strengthen specific movements based on the player's feedback data, for example.Furthermore, the training plan generation unit can adjust the training plan according to the athlete's progress. For example, the training plan generation unit analyzes the athlete's progress data and updates the training plan in real time. This enables the AI ​​agent according to the embodiment to efficiently capture, analyze, provide feedback on, and generate training plans for athletes.

[0030] The video capture unit captures the movements of athletes on video. For example, the video capture unit can film the movements of athletes with a high-resolution camera and save the data as video. High-resolution cameras can clearly capture the subtle movements and facial expressions of athletes, improving the accuracy of motion analysis. The video capture unit can also use multiple cameras to film from different angles simultaneously. For example, the video capture unit can simultaneously capture the movements of an athlete from the front, side, and rear, enabling detailed motion analysis. This allows for a multi-faceted view of the athlete's movements, enabling evaluation of consistency and balance. The video capture unit can also use drones to film from the air. For example, the video capture unit can use a drone to capture the movements of an athlete from above, understanding the overall flow of their movements. Because drones can cover a wide area, they can capture the movements of athletes holistically, making them particularly effective for motion analysis over a wide area, such as in field sports. Furthermore, the video capture unit has a function to transmit the captured video data to the analysis unit in real time, enabling rapid motion analysis. As a result, the video capture unit can capture the movements of athletes with high accuracy and from multiple angles, providing data for detailed motion analysis.

[0031] The analysis unit uses generative AI to analyze video captured by the video capture unit and identify errors in form. The generative AI receives video data as input and analyzes the subtle nuances of movement. Specifically, the generative AI analyzes the athlete's posture and movement timing to identify errors in form. For example, the generative AI analyzes the angle of the athlete's joints and the speed of movement, and detects errors by comparing them to the correct form. The generative AI can also analyze movement patterns and identify the causes of errors. For example, the generative AI learns the athlete's movement patterns and identifies error tendencies. This allows the analysis unit to understand what kinds of movements the athlete is prone to making mistakes in and to clearly identify areas for improvement. Furthermore, the analysis unit can more specifically identify areas for improvement in the athlete's movement by comparing it with past data and data from other athletes. For example, by comparing it with the movement data of top athletes in the same sport, it can clarify which parts of the athlete's movement need improvement. In this way, the analysis unit can use generative AI to analyze the movements of athletes in detail and identify errors in form and their causes.

[0032] The feedback unit provides real-time feedback based on form errors identified by the analysis unit. The feedback unit provides feedback to athletes, for example, through audio and visual means. Specifically, it monitors the athlete's movements in real time and provides feedback the moment an error occurs. For example, if an athlete makes a form error, the feedback unit will give voice instructions such as "correct your posture" or "adjust the angle of your arms." The feedback unit can also play back the athlete's movements on video and highlight the errors. For example, it can visually provide feedback to the athlete by highlighting errors in red during video playback. This allows the athlete to intuitively understand which part of their movement is incorrect. Furthermore, the feedback unit clarifies how the athlete should correct their movements by specifically showing areas for improvement. For example, it can show the correct form of an athlete's movement on video, helping the athlete improve by imitating it. This allows the feedback unit to provide athletes with real-time, specific feedback and support their movement improvement.

[0033] The training plan generation unit generates personalized training plans based on feedback provided by the feedback unit. For example, the training plan generation unit generates training menus tailored to the athlete's characteristics and goals. Specifically, it generates training plans to strengthen specific movements based on the athlete's feedback data. For instance, it creates training plans that include specific strength training and flexibility exercises for movements where the athlete is prone to form errors. The training plan generation unit can also adjust the training plan according to the athlete's progress. For example, it analyzes the athlete's progress data and updates the training plan in real time. When an athlete achieves a goal or new challenges arise, the training plan generation unit adjusts the training content accordingly to support the athlete's growth. Furthermore, the training plan generation unit can collect athlete feedback and evaluate the effectiveness of the training plan. This allows the training plan generation unit to provide the athlete with the optimal training plan and support efficient training.

[0034] The video capture unit can analyze the player's past movement history and select the optimal capture method. For example, the video capture unit can identify timings when a particular movement is frequently prone to errors based on past movement history and capture at those times. The video capture unit can also capture during the time when the player performs best, based on past movement history. For example, the video capture unit can analyze the player's past performance data to identify the optimal time. Furthermore, the video capture unit can analyze past movement history and select different camera angles for specific movement patterns. For example, the video capture unit can select the optimal camera angle for a specific movement and perform a detailed movement analysis. This allows the optimal capture method to be selected by analyzing past movement history. Some or all of the above processing in the video capture unit may be performed using AI, or without AI. For example, the video capture unit can input past movement data into a generating AI and have the generating AI select the optimal capture method.

[0035] The video capture unit can filter video based on the athlete's current training status and environment. For example, the video capture unit can capture only specific movements depending on the training status. The video capture unit can also automatically adjust the optimal capture settings based on environmental conditions (weather, lighting, etc.). For example, the video capture unit can adjust camera settings according to weather and lighting conditions to perform optimal capture. The video capture unit can also adjust the capture frequency according to the progress of the training. For example, the video capture unit can increase or decrease the capture frequency according to the progress of the training. This allows for optimal capture by filtering according to the training status and environment. Some or all of the above processing in the video capture unit may be performed using AI, for example, or without AI. For example, the video capture unit can input training status data into a generating AI and leave the filtering to the generating AI.

[0036] The video capture unit can prioritize capturing highly relevant actions by considering the player's geographical location information during video capture. For example, if a player is at a specific training facility, the video capture unit will prioritize capturing specific actions at that facility. Furthermore, if a player is training in a different environment, the video capture unit can prioritize capturing actions appropriate to that environment. For example, if a player is training outdoors, the video capture unit will prioritize capturing actions performed outdoors. Also, if a player is at a match venue, the video capture unit can prioritize capturing actions related to the match. For example, the video capture unit can capture pre-match warm-up actions and perform action analysis in preparation for the match. This allows for the priority capture of highly relevant actions by considering geographical location information. Some or all of the above processing in the video capture unit may be performed using AI, or without AI. For example, the video capture unit can input player location data into a generating AI and have the generating AI select highly relevant actions.

[0037] The video capture unit can analyze a player's social media activity during video capture and capture relevant actions. For example, if a player shares a specific action on social media, the video capture unit will prioritize capturing that action. The video capture unit can also identify actions that fans are interested in from the player's social media activity and capture those actions. For example, the video capture unit can identify actions that fans are interested in and capture those actions. The video capture unit can also analyze a player's social media activity and capture actions that align with trends. For example, the video capture unit can select and capture actions based on social media trends. This allows for the capture of relevant actions by analyzing social media activity. Some or all of the above processing in the video capture unit may be performed using AI, for example, or without AI. For example, the video capture unit can input social media data into a generating AI and have the generating AI select relevant actions.

[0038] The analysis unit can adjust the level of detail of the analysis based on the importance of the movement during motion analysis. For example, the analysis unit can perform a detailed analysis for important movements. It can also perform a concise analysis for basic movements. For example, it can perform a concise analysis for basic movements and a detailed analysis for important movements. Furthermore, the analysis unit can perform a specialized analysis for specific technical movements. For example, it can perform a specialized analysis for specific technical movements. This allows for optimal analysis results by adjusting the level of detail of the analysis according to the importance of the movement. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input motion data into a generating AI and have the generating AI adjust the level of detail of the analysis.

[0039] The analysis unit can apply different analysis algorithms depending on the category of motion during motion analysis. For example, the analysis unit can apply a running-specific analysis algorithm to running motions. Similarly, the analysis unit can apply a jumping-specific analysis algorithm to jumping motions. For example, the analysis unit can apply a jumping-specific analysis algorithm to jumping motions. Similarly, the analysis unit can apply a pitching-specific analysis algorithm to pitching motions. For example, the analysis unit can apply a pitching-specific analysis algorithm to pitching motions. By applying different analysis algorithms depending on the category of motion, the analysis unit can provide optimal analysis results. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input motion data into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0040] The analysis unit can determine the priority of analysis based on the timing of the movements during motion analysis. For example, the analysis unit may prioritize the analysis of the most recent movements. The analysis unit can also prioritize the analysis of important pre-match movements. For example, the analysis unit may prioritize the analysis of pre-match movements to improve movements in preparation for the match. The analysis unit can also prioritize the analysis of movements in the early stages of training. For example, the analysis unit may prioritize the analysis of movements in the early stages of training to improve basic movements. By determining the priority of analysis based on the timing of the movements, the analysis unit can provide optimal analysis results. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input motion data into a generating AI and have the generating AI determine the priority of analysis.

[0041] The analysis unit can adjust the order of analysis based on the relationships between movements during motion analysis. For example, the analysis unit can analyze consecutive movements as a whole. The analysis unit can also group related movements together for analysis. For example, the analysis unit can group related movements and analyze them all at once. Furthermore, the analysis unit can prioritize the analysis of movements related to a specific technology. For example, the analysis unit can prioritize the analysis of movements related to a specific technology and make technical improvements. By adjusting the order of analysis based on the relationships between movements, the analysis unit can provide optimal analysis results. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input motion data into a generating AI and have the generating AI adjust the order of analysis.

[0042] The feedback unit can adjust the level of detail of the feedback based on the importance of the action during the feedback process. For example, the feedback unit can provide detailed feedback for important actions. It can also provide concise feedback for basic actions. For example, it can provide concise feedback for basic actions and detailed feedback for important actions. Furthermore, it can provide expert feedback for specific technical actions. For example, it can provide expert feedback for specific technical actions. This allows for optimal feedback by adjusting the level of detail according to the importance of the action. Some or all of the above processing in the feedback unit may be performed using AI, or without AI. For example, the feedback unit can input action data into a generating AI and have the generating AI adjust the level of detail of the feedback.

[0043] The feedback unit can apply different feedback algorithms depending on the category of the action during feedback. For example, the feedback unit can apply a running-specific feedback algorithm to running actions. Similarly, the feedback unit can apply a jumping-specific feedback algorithm to jumping actions. Similarly, the feedback unit can apply a pitching-specific feedback algorithm to pitching actions. By applying different feedback algorithms depending on the category of the action, optimal feedback can be provided. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input action data into a generating AI and have the generating AI execute the application of the feedback algorithm.

[0044] The feedback unit can determine the priority of feedback based on the timing of the actions performed. For example, the feedback unit may prioritize feedback on the most recent actions. It can also prioritize feedback on important pre-match actions. For example, it may prioritize feedback on pre-match actions to improve those actions in preparation for the match. Furthermore, it can prioritize feedback on actions in the early stages of training. For example, it may prioritize feedback on actions in the early stages of training to improve basic movements. By determining the priority of feedback based on the timing of the actions performed, the feedback unit can provide optimal feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input action data into a generating AI and have the generating AI determine the priority of feedback.

[0045] The feedback unit can adjust the order of feedback based on the relevance of actions during the feedback process. For example, the feedback unit can provide feedback to a series of actions all at once. The feedback unit can also group related actions together and provide feedback to them all at once. For example, the feedback unit can group related actions together and provide feedback to them all at once. The feedback unit can also prioritize providing feedback to actions related to a specific technology. For example, the feedback unit can prioritize providing feedback to actions related to a specific technology to make technical improvements. By adjusting the order of feedback based on the relevance of actions, the feedback unit can provide optimal feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input action data into a generating AI and have the generating AI adjust the order of feedback.

[0046] The training plan generation unit can adjust the level of detail of the training plan based on the importance of the actions during the generation of the training plan. For example, the training plan generation unit can provide a detailed training plan for important actions. It can also provide a concise training plan for basic actions. For example, it can provide a concise training plan for basic actions and a detailed training plan for important actions. Furthermore, the training plan generation unit can provide a specialized training plan for specific technical actions. For example, it can provide a specialized training plan for specific technical actions. This allows for the provision of an optimal training plan by adjusting the level of detail of the plan according to the importance of the actions. Some or all of the above processing in the training plan generation unit may be performed using AI, for example, or without AI. For example, the training plan generation unit can input action data into a generation AI and have the generation AI perform the adjustment of the level of detail of the plan.

[0047] The training plan generation unit can apply different plan generation algorithms depending on the category of movement when generating a training plan. For example, the training plan generation unit can apply a running-specific plan generation algorithm to running movements. Similarly, the training plan generation unit can apply a jumping-specific plan generation algorithm to jumping movements. Similarly, the training plan generation unit can apply a pitching-specific plan generation algorithm to pitching movements. By applying different plan generation algorithms depending on the category of movement, the optimal training plan can be provided. Some or all of the above-described processes in the training plan generation unit may be performed using AI, for example, or without AI. For example, the training plan generation unit can input movement data into a generation AI and have the generation AI execute the application of the plan generation algorithm.

[0048] The training plan generation unit can determine the priority of training plans based on the timing of the actions performed. For example, the training plan generation unit can prioritize providing training plans for the most recent actions. It can also prioritize providing training plans for important pre-match actions. For example, it can prioritize providing training plans for pre-match actions to improve those actions in preparation for the match. Furthermore, the training plan generation unit can prioritize providing training plans for actions in the early stages of training. For example, it can prioritize providing training plans for actions in the early stages of training to improve basic movements. By determining the priority of plans based on the timing of the actions performed, the optimal training plan can be provided. Some or all of the above processing in the training plan generation unit may be performed using AI, for example, or without AI. For example, the training plan generation unit can input action data into a generation AI and have the generation AI determine the priority of the plans.

[0049] The training plan generation unit can adjust the order of plans based on the relationships between actions when generating a training plan. For example, the training plan generation unit can provide a training plan for consecutive actions all at once. The training plan generation unit can also group related actions and provide a training plan for them. For example, the training plan generation unit can group related actions and provide a training plan all at once. The training plan generation unit can also preferentially provide training plans for actions related to a specific technology. For example, the training plan generation unit can preferentially provide training plans for actions related to a specific technology and make technical improvements. By doing so, the optimal training plan can be provided by adjusting the order of plans based on the relationships between actions. Some or all of the above processing in the training plan generation unit may be performed using AI, for example, or without AI. For example, the training plan generation unit can input action data into a generation AI and have the generation AI perform the adjustment of the order of plans.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The video capture unit monitors the athlete's heart rate and breathing patterns while capturing their movements, and can adjust the capture timing based on this biometric data. For example, if an athlete's heart rate suddenly increases, the video capture unit will start capturing at that moment. Conversely, if the athlete's breathing is stable, capturing at that time will allow for a more natural recording of their movements. Furthermore, if the athlete's heart rate or breathing pattern shows abnormalities, the video capture unit can pause the capture and wait until the athlete's condition stabilizes. This makes it possible to select the optimal capture timing based on the athlete's biometric data.

[0052] The analysis department can evaluate the progress of an athlete's movements by referring to their past performance data and comparing it with current data. For example, it can assess whether the accuracy of a movement has improved compared to past data. Furthermore, based on past data, if an athlete repeatedly makes errors in a particular movement, the analysis department can identify the pattern of those errors and provide specific advice for improvement. In addition, it is possible to use past data to plot the athlete's growth curve and incorporate it into future training plans. This makes it possible to provide more accurate movement analysis and training plans by utilizing past performance data.

[0053] The training plan generation unit can adjust the difficulty level of the training plan based on the athlete's movement data. For example, if an athlete's movements are stable, it can provide a more advanced training menu. Conversely, if an athlete's movements are prone to errors, it can provide a more basic training menu. Furthermore, it can analyze the athlete's movement data and adjust the frequency of training for specific movements. For example, for an athlete who struggles with a particular movement, it can provide a training menu that focuses on that movement. This allows for the provision of an optimal training plan based on the athlete's movement data.

[0054] The video capture unit can monitor the athlete's muscle movements in real time while capturing their actions, and adjust the capture timing based on those movements. For example, it can start capturing the moment when the athlete's muscles are at their maximum contraction. It can also capture the moment when the athlete's muscles are relaxed to understand the overall flow of the movement. Furthermore, if the athlete's muscle movements show abnormalities, the video capture unit can pause the capture and wait until the athlete's condition stabilizes. This makes it possible to select the optimal capture timing based on the athlete's muscle movements.

[0055] The feedback system can adjust the format of feedback based on the athlete's movement data. For example, if an athlete's movements are stable, it can provide detailed text feedback. If an athlete's movements are prone to errors, it can provide visual feedback. Furthermore, it can analyze the athlete's movement data and adjust the format of feedback for specific movements. For example, a player who struggles with a particular movement can receive visual feedback for that movement. This allows for the provision of the optimal feedback format based on the athlete's movement data.

[0056] The video capture unit can monitor the athlete's body temperature in real time while capturing their movements and adjust the capture timing based on the temperature. For example, if the athlete's body temperature is rising, it will start capturing the moment. Conversely, if the athlete's body temperature is stable, capturing at that time will allow for a more natural recording of their movements. Furthermore, if the athlete's body temperature shows an abnormality, the video capture unit can pause the capture and wait until the athlete's condition stabilizes. This makes it possible to select the optimal capture timing based on the athlete's body temperature.

[0057] The following briefly describes the processing flow for example form 1.

[0058] Step 1: The video capture unit captures the movements of athletes on video. For example, the video capture unit uses a high-resolution camera to film the athlete's movements and saves them as video data. It can also use multiple cameras to film from different angles simultaneously, enabling detailed motion analysis from the front, side, and rear. Furthermore, it is possible to capture footage from the air using a drone to understand the overall flow of movement. Step 2: The analysis unit uses generative AI to analyze the video captured by the video capture unit and identify errors in form. The generative AI receives video data as input, analyzes the athlete's posture and timing of movements, and identifies errors in form. It can also analyze movement patterns and identify the cause of errors. The generative AI learns the athlete's movement patterns and identifies error tendencies. Step 3: The feedback unit provides real-time feedback based on the form errors identified by the analysis unit. The feedback unit provides feedback to the player, for example, through audio or visual means. It monitors the player's movements in real time and provides feedback the moment an error occurs. It also provides visual feedback to the player by highlighting the error in red during video playback. Step 4: The training plan generation unit generates an individualized training plan based on the feedback provided by the feedback unit. For example, the training plan generation unit generates a training menu tailored to the athlete's characteristics and goals. Based on the athlete's feedback data, it generates a training plan to strengthen specific movements. It also adjusts the training plan according to the athlete's progress and updates it in real time.

[0059] (Example of form 2) An AI agent according to an embodiment of the present invention is a system that video-analyzes the movements of athletes, identifies errors in their form, and provides specific improvement suggestions. This system utilizes generative AI to capture subtle nuances of movement and provide effective training methods. For example, a video capture unit captures the movements of athletes on video, and an analysis unit analyzes the captured video to identify errors in form. A feedback unit provides real-time feedback to the athlete, prompting immediate improvement of their form. A training plan generation unit generates an individualized training plan based on the analysis results. This increases the rate of performance improvement, reduces the risk of injury, and maximizes training efficiency. The AI ​​agent is useful for competitive athletes, amateur sports enthusiasts aiming to improve their skills, sports coaches, and trainers. By utilizing multimodal AI, comprehensive analysis becomes possible, and customization based on individual movement data is realized. This supports sustainable improvement of athletic ability. As a result, the AI ​​agent can efficiently capture, analyze, provide feedback on, and generate training plans for athletes' movements.

[0060] The AI ​​agent according to this embodiment comprises a video capture unit, an analysis unit, a feedback unit, and a training plan generation unit. The video capture unit captures the movements of an athlete on video. For example, the video capture unit films the movements of an athlete with a high-resolution camera and saves it as video data. The video capture unit can also use multiple cameras to film from different angles simultaneously. For example, the video capture unit can simultaneously capture the movements of an athlete from the front, side, and rear, enabling detailed motion analysis. The video capture unit can also use a drone to film from the air. For example, the video capture unit can use a drone to capture the movements of an athlete from above, grasping the overall flow of movement. The analysis unit uses a generation AI to analyze the video captured by the video capture unit and identify errors in form. For example, the analysis unit receives the video data as input from the generation AI and analyzes the fine nuances of the movements. For example, the generation AI analyzes the athlete's posture and the timing of their movements to identify errors in form. The analysis unit can also use the generation AI to analyze movement patterns and identify the causes of errors. For example, the generating AI learns the player's movement patterns and identifies error tendencies. The feedback unit provides real-time feedback based on the form errors identified by the analysis unit. The feedback unit provides feedback to the player, for example, through audio or visual means. The feedback unit monitors the player's movements in real time and provides feedback the moment an error occurs. The feedback unit can also play back the player's movements on video and highlight the error areas. For example, the feedback unit can display the error areas in red during video playback, providing visual feedback to the player. The training plan generation unit generates an individualized training plan based on the feedback provided by the feedback unit. The training plan generation unit generates training menus tailored to the player's characteristics and goals, for example. The training plan generation unit generates training plans to strengthen specific movements based on the player's feedback data, for example.Furthermore, the training plan generation unit can adjust the training plan according to the athlete's progress. For example, the training plan generation unit analyzes the athlete's progress data and updates the training plan in real time. This enables the AI ​​agent according to the embodiment to efficiently capture, analyze, provide feedback on, and generate training plans for athletes.

[0061] The video capture unit captures the movements of athletes on video. For example, the video capture unit can film the movements of athletes with a high-resolution camera and save the data as video. High-resolution cameras can clearly capture the subtle movements and facial expressions of athletes, improving the accuracy of motion analysis. The video capture unit can also use multiple cameras to film from different angles simultaneously. For example, the video capture unit can simultaneously capture the movements of an athlete from the front, side, and rear, enabling detailed motion analysis. This allows for a multi-faceted view of the athlete's movements, enabling evaluation of consistency and balance. The video capture unit can also use drones to film from the air. For example, the video capture unit can use a drone to capture the movements of an athlete from above, understanding the overall flow of their movements. Because drones can cover a wide area, they can capture the movements of athletes holistically, making them particularly effective for motion analysis over a wide area, such as in field sports. Furthermore, the video capture unit has a function to transmit the captured video data to the analysis unit in real time, enabling rapid motion analysis. As a result, the video capture unit can capture the movements of athletes with high accuracy and from multiple angles, providing data for detailed motion analysis.

[0062] The analysis unit uses generative AI to analyze video captured by the video capture unit and identify errors in form. The generative AI receives video data as input and analyzes the subtle nuances of movement. Specifically, the generative AI analyzes the athlete's posture and movement timing to identify errors in form. For example, the generative AI analyzes the angle of the athlete's joints and the speed of movement, and detects errors by comparing them to the correct form. The generative AI can also analyze movement patterns and identify the causes of errors. For example, the generative AI learns the athlete's movement patterns and identifies error tendencies. This allows the analysis unit to understand what kinds of movements the athlete is prone to making mistakes in and to clearly identify areas for improvement. Furthermore, the analysis unit can more specifically identify areas for improvement in the athlete's movement by comparing it with past data and data from other athletes. For example, by comparing it with the movement data of top athletes in the same sport, it can clarify which parts of the athlete's movement need improvement. In this way, the analysis unit can use generative AI to analyze the movements of athletes in detail and identify errors in form and their causes.

[0063] The feedback unit provides real-time feedback based on form errors identified by the analysis unit. The feedback unit provides feedback to athletes, for example, through audio and visual means. Specifically, it monitors the athlete's movements in real time and provides feedback the moment an error occurs. For example, if an athlete makes a form error, the feedback unit will give voice instructions such as "correct your posture" or "adjust the angle of your arms." The feedback unit can also play back the athlete's movements on video and highlight the errors. For example, it can visually provide feedback to the athlete by highlighting errors in red during video playback. This allows the athlete to intuitively understand which part of their movement is incorrect. Furthermore, the feedback unit clarifies how the athlete should correct their movements by specifically showing areas for improvement. For example, it can show the correct form of an athlete's movement on video, helping the athlete improve by imitating it. This allows the feedback unit to provide athletes with real-time, specific feedback and support their movement improvement.

[0064] The training plan generation unit generates personalized training plans based on feedback provided by the feedback unit. For example, the training plan generation unit generates training menus tailored to the athlete's characteristics and goals. Specifically, it generates training plans to strengthen specific movements based on the athlete's feedback data. For instance, it creates training plans that include specific strength training and flexibility exercises for movements where the athlete is prone to form errors. The training plan generation unit can also adjust the training plan according to the athlete's progress. For example, it analyzes the athlete's progress data and updates the training plan in real time. When an athlete achieves a goal or new challenges arise, the training plan generation unit adjusts the training content accordingly to support the athlete's growth. Furthermore, the training plan generation unit can collect athlete feedback and evaluate the effectiveness of the training plan. This allows the training plan generation unit to provide the athlete with the optimal training plan and support efficient training.

[0065] The video capture unit can estimate the emotions of athletes and adjust the timing of video capture based on the estimated emotions. For example, if an athlete is tense, the video capture unit can delay capture until the athlete relaxes. It can also start capturing immediately when an athlete is concentrating. For example, it can detect a moment of concentration and immediately begin capturing. Furthermore, if an athlete is tired, the video capture unit can resume capturing after a break. For example, it can resume capturing after the athlete has rested, capturing their actions at the optimal timing. This allows for optimal capture by adjusting the timing of video capture according to the athlete's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the video capture unit may be performed using AI, or without AI. For example, the video capture unit can input the player's facial expression data into a generating AI, which can then perform emotion estimation.

[0066] The video capture unit can analyze the player's past movement history and select the optimal capture method. For example, the video capture unit can identify timings when a particular movement is frequently prone to errors based on past movement history and capture at those times. The video capture unit can also capture during the time when the player performs best, based on past movement history. For example, the video capture unit can analyze the player's past performance data to identify the optimal time. Furthermore, the video capture unit can analyze past movement history and select different camera angles for specific movement patterns. For example, the video capture unit can select the optimal camera angle for a specific movement and perform a detailed movement analysis. This allows the optimal capture method to be selected by analyzing past movement history. Some or all of the above processing in the video capture unit may be performed using AI, or without AI. For example, the video capture unit can input past movement data into a generating AI and have the generating AI select the optimal capture method.

[0067] The video capture unit can filter video based on the athlete's current training status and environment. For example, the video capture unit can capture only specific movements depending on the training status. The video capture unit can also automatically adjust the optimal capture settings based on environmental conditions (weather, lighting, etc.). For example, the video capture unit can adjust camera settings according to weather and lighting conditions to perform optimal capture. The video capture unit can also adjust the capture frequency according to the progress of the training. For example, the video capture unit can increase or decrease the capture frequency according to the progress of the training. This allows for optimal capture by filtering according to the training status and environment. Some or all of the above processing in the video capture unit may be performed using AI, for example, or without AI. For example, the video capture unit can input training status data into a generating AI and leave the filtering to the generating AI.

[0068] The video capture unit can estimate the emotions of athletes and determine the priority of actions to capture based on the estimated emotions. For example, if an athlete is relaxed, the video capture unit will prioritize capturing complex actions. Conversely, if an athlete is tense, the video capture unit can also prioritize capturing basic actions. For example, the video capture unit will capture basic actions when the athlete is tense and complex actions when the athlete is relaxed. Furthermore, if an athlete is focused, the video capture unit can also prioritize capturing specific technical actions. For example, the video capture unit will capture technical actions when the athlete is focused and perform detailed analysis. This allows for optimal capture by determining the priority of actions to capture according to the athlete's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the video capture unit may be performed using AI, for example, or without AI. For example, the video capture unit can input the player's facial expression data into a generating AI, which can then perform emotion estimation.

[0069] The video capture unit can prioritize capturing highly relevant actions by considering the player's geographical location information during video capture. For example, if a player is at a specific training facility, the video capture unit will prioritize capturing specific actions at that facility. Furthermore, if a player is training in a different environment, the video capture unit can prioritize capturing actions appropriate to that environment. For example, if a player is training outdoors, the video capture unit will prioritize capturing actions performed outdoors. Also, if a player is at a match venue, the video capture unit can prioritize capturing actions related to the match. For example, the video capture unit can capture pre-match warm-up actions and perform action analysis in preparation for the match. This allows for the priority capture of highly relevant actions by considering geographical location information. Some or all of the above processing in the video capture unit may be performed using AI, or without AI. For example, the video capture unit can input player location data into a generating AI and have the generating AI select highly relevant actions.

[0070] The video capture unit can analyze a player's social media activity during video capture and capture relevant actions. For example, if a player shares a specific action on social media, the video capture unit will prioritize capturing that action. The video capture unit can also identify actions that fans are interested in from the player's social media activity and capture those actions. For example, the video capture unit can identify actions that fans are interested in and capture those actions. The video capture unit can also analyze a player's social media activity and capture actions that align with trends. For example, the video capture unit can select and capture actions based on social media trends. This allows for the capture of relevant actions by analyzing social media activity. Some or all of the above processing in the video capture unit may be performed using AI, for example, or without AI. For example, the video capture unit can input social media data into a generating AI and have the generating AI select relevant actions.

[0071] The analysis unit can estimate the emotions of athletes and adjust the representation of motion analysis based on the estimated emotions. For example, if the athlete is relaxed, the analysis unit can provide detailed analysis results. It can also provide concise and to-the-point analysis results if the athlete is tense. For example, it can provide concise analysis results when the athlete is tense and detailed analysis results when the athlete is relaxed. Furthermore, it can provide analysis results including technical details if the athlete is focused. For example, it can provide analysis results including technical details when the athlete is focused. This allows for optimal analysis results by adjusting the representation of motion analysis according to the athlete's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, or without AI. For example, the analysis department can input the players' facial expression data into a generating AI and have the AI ​​perform emotion estimation.

[0072] The analysis unit can adjust the level of detail of the analysis based on the importance of the movement during motion analysis. For example, the analysis unit can perform a detailed analysis for important movements. It can also perform a concise analysis for basic movements. For example, it can perform a concise analysis for basic movements and a detailed analysis for important movements. Furthermore, the analysis unit can perform a specialized analysis for specific technical movements. For example, it can perform a specialized analysis for specific technical movements. This allows for optimal analysis results by adjusting the level of detail of the analysis according to the importance of the movement. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input motion data into a generating AI and have the generating AI adjust the level of detail of the analysis.

[0073] The analysis unit can apply different analysis algorithms depending on the category of motion during motion analysis. For example, the analysis unit can apply a running-specific analysis algorithm to running motions. Similarly, the analysis unit can apply a jumping-specific analysis algorithm to jumping motions. For example, the analysis unit can apply a jumping-specific analysis algorithm to jumping motions. Similarly, the analysis unit can apply a pitching-specific analysis algorithm to pitching motions. For example, the analysis unit can apply a pitching-specific analysis algorithm to pitching motions. By applying different analysis algorithms depending on the category of motion, the analysis unit can provide optimal analysis results. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input motion data into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0074] The analysis unit can estimate the emotions of athletes and adjust the length of the analysis based on the estimated emotions. For example, if the athlete is relaxed, the analysis unit can perform a detailed analysis. Conversely, if the athlete is in a hurry, the analysis unit can perform a concise analysis. For example, the analysis unit can perform a concise analysis when the athlete is in a hurry and a detailed analysis when the athlete is relaxed. Furthermore, if the athlete is focused, the analysis unit can perform an analysis that includes technical details. For example, the analysis unit can perform an analysis that includes technical details when the athlete is focused. By adjusting the length of the analysis according to the emotions of the athlete, the optimal analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the athlete's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0075] The analysis unit can determine the priority of analysis based on the timing of the movements during motion analysis. For example, the analysis unit may prioritize the analysis of the most recent movements. The analysis unit can also prioritize the analysis of important pre-match movements. For example, the analysis unit may prioritize the analysis of pre-match movements to improve movements in preparation for the match. The analysis unit can also prioritize the analysis of movements in the early stages of training. For example, the analysis unit may prioritize the analysis of movements in the early stages of training to improve basic movements. By determining the priority of analysis based on the timing of the movements, the analysis unit can provide optimal analysis results. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input motion data into a generating AI and have the generating AI determine the priority of analysis.

[0076] The analysis unit can adjust the order of analysis based on the relationships between movements during motion analysis. For example, the analysis unit can analyze consecutive movements as a whole. The analysis unit can also group related movements together for analysis. For example, the analysis unit can group related movements and analyze them all at once. Furthermore, the analysis unit can prioritize the analysis of movements related to a specific technology. For example, the analysis unit can prioritize the analysis of movements related to a specific technology and make technical improvements. By adjusting the order of analysis based on the relationships between movements, the analysis unit can provide optimal analysis results. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input motion data into a generating AI and have the generating AI adjust the order of analysis.

[0077] The feedback unit can estimate the emotions of athletes and adjust the way feedback is expressed based on the estimated emotions. For example, if an athlete is relaxed, the feedback unit can provide detailed feedback. It can also provide concise and to-the-point feedback if the athlete is tense. For example, it can provide concise feedback when an athlete is tense and detailed feedback when they are relaxed. Furthermore, it can provide feedback that includes technical details when an athlete is focused. For example, it can provide feedback that includes technical details when an athlete is focused. This allows for the provision of optimal feedback by adjusting the way feedback is expressed according to the athlete's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI, or not. For example, the feedback unit can input the athlete's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0078] The feedback unit can adjust the level of detail of the feedback based on the importance of the action during the feedback process. For example, the feedback unit can provide detailed feedback for important actions. It can also provide concise feedback for basic actions. For example, it can provide concise feedback for basic actions and detailed feedback for important actions. Furthermore, it can provide expert feedback for specific technical actions. For example, it can provide expert feedback for specific technical actions. This allows for optimal feedback by adjusting the level of detail according to the importance of the action. Some or all of the above processing in the feedback unit may be performed using AI, or without AI. For example, the feedback unit can input action data into a generating AI and have the generating AI adjust the level of detail of the feedback.

[0079] The feedback unit can apply different feedback algorithms depending on the category of the action during feedback. For example, the feedback unit can apply a running-specific feedback algorithm to running actions. Similarly, the feedback unit can apply a jumping-specific feedback algorithm to jumping actions. Similarly, the feedback unit can apply a pitching-specific feedback algorithm to pitching actions. By applying different feedback algorithms depending on the category of the action, optimal feedback can be provided. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input action data into a generating AI and have the generating AI execute the application of the feedback algorithm.

[0080] The feedback unit can estimate the athlete's emotions and adjust the length of the feedback based on the estimated emotions. For example, if the athlete is relaxed, the feedback unit can provide detailed feedback. If the athlete is in a hurry, the feedback unit can also provide concise feedback. For example, the feedback unit can provide concise feedback when the athlete is in a hurry and detailed feedback when the athlete is relaxed. Furthermore, if the athlete is focused, the feedback unit can provide feedback that includes technical details. For example, the feedback unit can provide feedback that includes technical details when the athlete is focused. This allows for optimal feedback by adjusting the length of the feedback according to the athlete's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input the athlete's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0081] The feedback unit can determine the priority of feedback based on the timing of the actions performed. For example, the feedback unit may prioritize feedback on the most recent actions. It can also prioritize feedback on important pre-match actions. For example, it may prioritize feedback on pre-match actions to improve those actions in preparation for the match. Furthermore, it can prioritize feedback on actions in the early stages of training. For example, it may prioritize feedback on actions in the early stages of training to improve basic movements. By determining the priority of feedback based on the timing of the actions performed, the feedback unit can provide optimal feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input action data into a generating AI and have the generating AI determine the priority of feedback.

[0082] The feedback unit can adjust the order of feedback based on the relevance of actions during the feedback process. For example, the feedback unit can provide feedback to a series of actions all at once. The feedback unit can also group related actions together and provide feedback to them all at once. For example, the feedback unit can group related actions together and provide feedback to them all at once. The feedback unit can also prioritize providing feedback to actions related to a specific technology. For example, the feedback unit can prioritize providing feedback to actions related to a specific technology to make technical improvements. By adjusting the order of feedback based on the relevance of actions, the feedback unit can provide optimal feedback. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input action data into a generating AI and have the generating AI adjust the order of feedback.

[0083] The training plan generation unit can estimate the emotions of athletes and adjust the way the training plan is presented based on the estimated emotions. For example, if the athlete is relaxed, the training plan generation unit can provide a detailed training plan. It can also provide a concise and to-the-point training plan if the athlete is tense. For example, it can provide a concise training plan when the athlete is tense and a detailed training plan when the athlete is relaxed. Furthermore, if the athlete is focused, the training plan generation unit can provide a training plan that includes technical details. For example, it can provide a training plan that includes technical details when the athlete is focused. This allows for the provision of an optimal training plan by adjusting the presentation of the training plan according to the athlete's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the training plan generation unit may be performed using AI, or not. For example, the training plan generation unit can input the player's facial expression data into the generating AI and have the generating AI perform emotion estimation.

[0084] The training plan generation unit can adjust the level of detail of the training plan based on the importance of the actions during the generation of the training plan. For example, the training plan generation unit can provide a detailed training plan for important actions. It can also provide a concise training plan for basic actions. For example, it can provide a concise training plan for basic actions and a detailed training plan for important actions. Furthermore, the training plan generation unit can provide a specialized training plan for specific technical actions. For example, it can provide a specialized training plan for specific technical actions. This allows for the provision of an optimal training plan by adjusting the level of detail of the plan according to the importance of the actions. Some or all of the above processing in the training plan generation unit may be performed using AI, for example, or without AI. For example, the training plan generation unit can input action data into a generation AI and have the generation AI perform the adjustment of the level of detail of the plan.

[0085] The training plan generation unit can apply different plan generation algorithms depending on the category of movement when generating a training plan. For example, the training plan generation unit can apply a running-specific plan generation algorithm to running movements. Similarly, the training plan generation unit can apply a jumping-specific plan generation algorithm to jumping movements. Similarly, the training plan generation unit can apply a pitching-specific plan generation algorithm to pitching movements. By applying different plan generation algorithms depending on the category of movement, the optimal training plan can be provided. Some or all of the above-described processes in the training plan generation unit may be performed using AI, for example, or without AI. For example, the training plan generation unit can input movement data into a generation AI and have the generation AI execute the application of the plan generation algorithm.

[0086] The training plan generation unit can estimate the emotions of athletes and adjust the length of the training plan based on the estimated emotions. For example, if the athlete is relaxed, the training plan generation unit can provide a detailed training plan. It can also provide a concise training plan if the athlete is in a hurry. For example, it can provide a concise training plan when the athlete is in a hurry and a detailed training plan when the athlete is relaxed. Furthermore, if the athlete is focused, the training plan generation unit can provide a training plan that includes technical details. For example, it can provide a training plan that includes technical details when the athlete is focused. This allows for the provision of an optimal training plan by adjusting the length of the training plan according to the athlete's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the training plan generation unit may be performed using AI, or not. For example, the training plan generation unit can input the player's facial expression data into the generating AI and have the generating AI perform emotion estimation.

[0087] The training plan generation unit can determine the priority of training plans based on the timing of the actions performed. For example, the training plan generation unit can prioritize providing training plans for the most recent actions. It can also prioritize providing training plans for important pre-match actions. For example, it can prioritize providing training plans for pre-match actions to improve those actions in preparation for the match. Furthermore, the training plan generation unit can prioritize providing training plans for actions in the early stages of training. For example, it can prioritize providing training plans for actions in the early stages of training to improve basic movements. By determining the priority of plans based on the timing of the actions performed, the optimal training plan can be provided. Some or all of the above processing in the training plan generation unit may be performed using AI, for example, or without AI. For example, the training plan generation unit can input action data into a generation AI and have the generation AI determine the priority of the plans.

[0088] The training plan generation unit can adjust the order of plans based on the relationships between actions when generating a training plan. For example, the training plan generation unit can provide a training plan for consecutive actions all at once. The training plan generation unit can also group related actions and provide a training plan for them. For example, the training plan generation unit can group related actions and provide a training plan all at once. The training plan generation unit can also preferentially provide training plans for actions related to a specific technology. For example, the training plan generation unit can preferentially provide training plans for actions related to a specific technology and make technical improvements. By doing so, the optimal training plan can be provided by adjusting the order of plans based on the relationships between actions. Some or all of the above processing in the training plan generation unit may be performed using AI, for example, or without AI. For example, the training plan generation unit can input action data into a generation AI and have the generation AI perform the adjustment of the order of plans.

[0089] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0090] The video capture unit monitors the athlete's heart rate and breathing patterns while capturing their movements, and can adjust the capture timing based on this biometric data. For example, if an athlete's heart rate suddenly increases, the video capture unit will start capturing at that moment. Conversely, if the athlete's breathing is stable, capturing at that time will allow for a more natural recording of their movements. Furthermore, if the athlete's heart rate or breathing pattern shows abnormalities, the video capture unit can pause the capture and wait until the athlete's condition stabilizes. This makes it possible to select the optimal capture timing based on the athlete's biometric data.

[0091] The analysis department can evaluate the progress of an athlete's movements by referring to their past performance data and comparing it with current data. For example, it can assess whether the accuracy of a movement has improved compared to past data. Furthermore, based on past data, if an athlete repeatedly makes errors in a particular movement, the analysis department can identify the pattern of those errors and provide specific advice for improvement. In addition, it is possible to use past data to plot the athlete's growth curve and incorporate it into future training plans. This makes it possible to provide more accurate movement analysis and training plans by utilizing past performance data.

[0092] The feedback system can estimate the athlete's emotions and adjust the timing of feedback based on those estimates. For example, if an athlete is relaxed, providing immediate feedback makes it easier for them to understand areas for improvement on the spot. Conversely, if an athlete is tense, delaying the feedback slightly allows them to calmly accept it. Furthermore, if an athlete is focused, the feedback can be kept short and concise so as not to interrupt their concentration. This allows for the selection of the optimal feedback timing based on the athlete's emotions.

[0093] The training plan generation unit can adjust the difficulty level of the training plan based on the athlete's movement data. For example, if an athlete's movements are stable, it can provide a more advanced training menu. Conversely, if an athlete's movements are prone to errors, it can provide a more basic training menu. Furthermore, it can analyze the athlete's movement data and adjust the frequency of training for specific movements. For example, for an athlete who struggles with a particular movement, it can provide a training menu that focuses on that movement. This allows for the provision of an optimal training plan based on the athlete's movement data.

[0094] The video capture unit can monitor the athlete's muscle movements in real time while capturing their actions, and adjust the capture timing based on those movements. For example, it can start capturing the moment when the athlete's muscles are at their maximum contraction. It can also capture the moment when the athlete's muscles are relaxed to understand the overall flow of the movement. Furthermore, if the athlete's muscle movements show abnormalities, the video capture unit can pause the capture and wait until the athlete's condition stabilizes. This makes it possible to select the optimal capture timing based on the athlete's muscle movements.

[0095] The analysis unit can estimate the athlete's emotions and adjust the feedback content of the motion analysis based on those estimated emotions. For example, if the athlete is relaxed, it can provide detailed feedback. If the athlete is tense, it can provide concise and to-the-point feedback. Furthermore, if the athlete is focused, it can provide feedback that includes technical details. This allows for the provision of optimal feedback tailored to the athlete's emotions.

[0096] The feedback system can adjust the format of feedback based on the athlete's movement data. For example, if an athlete's movements are stable, it can provide detailed text feedback. If an athlete's movements are prone to errors, it can provide visual feedback. Furthermore, it can analyze the athlete's movement data and adjust the format of feedback for specific movements. For example, a player who struggles with a particular movement can receive visual feedback for that movement. This allows for the provision of the optimal feedback format based on the athlete's movement data.

[0097] The training plan generation unit can estimate the athlete's emotions and adjust the frequency of the training plan based on those emotions. For example, if the athlete is relaxed, the frequency of training can be increased to provide more training opportunities. Conversely, if the athlete is tense, the frequency of training can be decreased to reduce the athlete's burden. Furthermore, if the athlete is focused, the frequency of training can be adjusted to take advantage of that focus. This allows the system to provide the optimal training plan frequency tailored to the athlete's emotions.

[0098] The video capture unit can monitor the athlete's body temperature in real time while capturing their movements and adjust the capture timing based on the temperature. For example, if the athlete's body temperature is rising, it will start capturing the moment. Conversely, if the athlete's body temperature is stable, capturing at that time will allow for a more natural recording of their movements. Furthermore, if the athlete's body temperature shows an abnormality, the video capture unit can pause the capture and wait until the athlete's condition stabilizes. This makes it possible to select the optimal capture timing based on the athlete's body temperature.

[0099] The analysis unit can estimate the athlete's emotions and adjust the priority of motion analysis based on those estimates. For example, if the athlete is relaxed, it can prioritize the analysis of important movements. If the athlete is tense, it can prioritize the analysis of basic movements. Furthermore, if the athlete is focused, it can prioritize the analysis of technical movements. This allows the system to provide the optimal priority of motion analysis according to the athlete's emotions.

[0100] The following briefly describes the processing flow for example form 2.

[0101] Step 1: The video capture unit captures the movements of athletes on video. For example, the video capture unit uses a high-resolution camera to film the athlete's movements and saves them as video data. It can also use multiple cameras to film from different angles simultaneously, enabling detailed motion analysis from the front, side, and rear. Furthermore, it is possible to capture footage from the air using a drone to understand the overall flow of movement. Step 2: The analysis unit uses generative AI to analyze the video captured by the video capture unit and identify errors in form. The generative AI receives video data as input, analyzes the athlete's posture and timing of movements, and identifies errors in form. It can also analyze movement patterns and identify the cause of errors. The generative AI learns the athlete's movement patterns and identifies error tendencies. Step 3: The feedback unit provides real-time feedback based on the form errors identified by the analysis unit. The feedback unit provides feedback to the player, for example, through audio or visual means. It monitors the player's movements in real time and provides feedback the moment an error occurs. It also provides visual feedback to the player by highlighting the error in red during video playback. Step 4: The training plan generation unit generates an individualized training plan based on the feedback provided by the feedback unit. For example, the training plan generation unit generates a training menu tailored to the athlete's characteristics and goals. Based on the athlete's feedback data, it generates a training plan to strengthen specific movements. It also adjusts the training plan according to the athlete's progress and updates it in real time.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0103] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0104] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0105] Each of the multiple elements described above, including the video capture unit, analysis unit, feedback unit, and training plan generation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the video capture unit captures the movements of an athlete using the camera 42 of the smart device 14 and analyzes the video data using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and identifies errors in form using generated AI. The feedback unit is implemented in the control unit 46A of the smart device 14 and provides real-time feedback to the athlete. The training plan generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates an individualized training plan. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0106] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0107] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0112] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0113] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0114] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0115] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0116] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0117] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0121] Each of the multiple elements described above, including the video capture unit, analysis unit, feedback unit, and training plan generation unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the video capture unit captures the movements of an athlete using the camera 42 of the smart glasses 214 and analyzes the video data using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and identifies errors in form using generated AI. The feedback unit is implemented, for example, by the control unit 46A of the smart glasses 214 and provides real-time feedback to the athlete. The training plan generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates an individualized training plan. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0122] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0123] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0125] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0126] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0128] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0129] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0130] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0131] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0132] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0137] Each of the multiple elements described above, including the video capture unit, analysis unit, feedback unit, and training plan generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the video capture unit captures the movements of an athlete using the camera 42 of the headset terminal 314 and analyzes the video data using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and identifies errors in form using generated AI. The feedback unit is implemented in the control unit 46A of the headset terminal 314 and provides real-time feedback to the athlete. The training plan generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates an individualized training plan. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0138] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0139] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0140] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0142] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0144] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0145] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0146] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0148] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0149] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] Each of the multiple elements described above, including the video capture unit, analysis unit, feedback unit, and training plan generation unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the video capture unit captures the movements of an athlete using the camera 42 of the robot 414 and analyzes the video data using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and identifies errors in form using generated AI. The feedback unit is implemented, for example, by the control unit 46A of the robot 414 and provides real-time feedback to the athlete. The training plan generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates an individualized training plan. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0155] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0157] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0158] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0159] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0162] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0163] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0164] 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.

[0165] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0166] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0167] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0168] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0170] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0171] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0172] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0173] (Note 1) A video capture unit that captures the movements of athletes on video, An analysis unit analyzes the video captured by the aforementioned video capture unit and identifies errors in the form, A feedback unit provides real-time feedback based on form errors identified by the analysis unit, The system includes a training plan generation unit that generates an individualized training plan based on the feedback provided by the feedback unit. A system characterized by the following features. (Note 2) The aforementioned video capture unit is This system estimates the emotions of athletes and adjusts the timing of video captures based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned video capture unit is Analyze the player's past movement history and select the optimal capture method. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned video capture unit is During video capture, filtering is performed based on the player's current training status and environment. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned video capture unit is The system estimates the emotions of athletes and determines the priority of actions to capture based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned video capture unit is During video capture, the system prioritizes capturing highly relevant actions by considering the player's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned video capture unit is During video capture, the system analyzes the player's social media activity and captures relevant actions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit is We estimate the emotions of athletes and adjust the representation of their movements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit is During motion analysis, adjust the level of detail based on the importance of the motion. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit is During motion analysis, different analysis algorithms are applied depending on the category of motion. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit is The system estimates the emotions of athletes and adjusts the length of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit is During motion analysis, the priority of the analysis is determined based on when the motion was performed. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit is During motion analysis, the order of analysis is adjusted based on the relationships between the movements. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned feedback unit is This system estimates the emotions of athletes and adjusts the way feedback is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned feedback unit is When providing feedback, adjust the level of detail in the feedback based on the importance of the action. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned feedback unit is During feedback, different feedback algorithms are applied depending on the category of the action. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned feedback unit is The system estimates the emotions of athletes and adjusts the length of feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned feedback unit is When providing feedback, prioritize the feedback based on when the action was performed. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned feedback unit is During feedback, adjust the order of feedback based on the relevance of the actions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned training plan generation unit, This system estimates the emotions of athletes and adjusts the way training plans are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned training plan generation unit, When generating a training plan, adjust the level of detail in the plan based on the importance of the movements. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned training plan generation unit, When generating a training plan, different plan generation algorithms are applied depending on the category of the movement. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned training plan generation unit, The system estimates the emotions of athletes and adjusts the length of training plans based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned training plan generation unit, When generating a training plan, prioritize the plan based on when the actions should be performed. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned training plan generation unit, When generating a training plan, adjust the order of the plan based on the relevance of the actions. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A video capture unit that captures the movements of athletes on video, An analysis unit analyzes the video captured by the aforementioned video capture unit and identifies errors in the form, A feedback unit provides real-time feedback based on form errors identified by the analysis unit, The system includes a training plan generation unit that generates an individualized training plan based on the feedback provided by the feedback unit. A system characterized by the following features.

2. The aforementioned video capture unit is This system estimates the emotions of athletes and adjusts the timing of video captures based on those estimated emotions. The system according to feature 1.

3. The aforementioned video capture unit is Analyze the player's past movement history and select the optimal capture method. The system according to feature 1.

4. The aforementioned video capture unit is During video capture, filtering is performed based on the player's current training status and environment. The system according to feature 1.

5. The aforementioned video capture unit is The system estimates the emotions of athletes and determines the priority of actions to capture based on those estimated emotions. The system according to feature 1.

6. The aforementioned video capture unit is During video capture, the system prioritizes capturing highly relevant actions by considering the player's geographical location. The system according to feature 1.

7. The aforementioned video capture unit is During video capture, the system analyzes the player's social media activity and captures relevant actions. The system according to feature 1.

8. The aforementioned analysis unit is We estimate the emotions of athletes and adjust the representation of their movements based on those estimated emotions. The system according to feature 1.

Images