system

Abstract

The system according to this embodiment aims to efficiently provide feedback for acquiring the correct form in sports. [Solution] The system according to the embodiment comprises a reception unit, a generation unit, and a feedback unit. The reception unit receives uploads of videos of professional athletes and videos of the user's own sports. The generation unit synthesizes the videos uploaded by the reception unit. The feedback unit provides feedback on differences in form based on the video synthesized by the generation unit.

Description

Technical Field

[0004]

[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 character of the chatbot, 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

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult for a person to practice acquiring the correct form of sports alone, and there are time and cost constraints.

[0005] The system according to the embodiment aims to efficiently provide feedback for acquiring the correct form of sports.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a generation unit, and a feedback unit. The reception unit receives uploads of videos of professional athletes and videos of the user's own sports. The generation unit synthesizes the videos uploaded by the reception unit. The feedback unit provides feedback on differences in form based on the video synthesized by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently provide feedback to help players acquire the correct form in sports. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. <000009�> The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The form checker system according to an embodiment of the present invention is a system for supporting improvement in sports. In this form checker system, the user uploads a video of a professional athlete and a video of their own sports, and a generating AI combines the two videos and processes them to make them easier to compare. In addition, a text generating AI provides feedback on the differences in form. This mechanism makes it easier for the user to practice alone and solves problems of time constraints and costs. For example, the user uploads a video of a professional athlete and a video of their own sports. For example, in the case of a baseball pitching form, the user uploads a video from the stance to the throw. This information is input to the generating AI. Next, the generating AI combines the two videos. The generating AI cuts out the necessary length (e.g., from the stance to the throw) and the necessary range (e.g., centered on the person) and adjusts the scale. It also aligns the time axis to the timing of the same action and outputs the two videos side by side. This makes it easier for the user to compare the form of a professional with their own form. Furthermore, a text generating AI provides feedback on the differences in form. For example, it provides text-based feedback such as, "Compared to the pros, your elbow is lower," or "Compared to the pros, your hips rotate too early." This allows users to specifically understand areas for improvement in their form. This system makes it easier for users to practice alone and solves problems related to time constraints and costs. For example, when practicing while looking at books or photos, you need to compare yourself to the photos, but with this system, you can practice while watching videos. Also, when attending lessons, you can only get feedback when the coach is present, but with this system, you can get feedback anytime. Furthermore, using dedicated sensors is expensive, but this system can reduce costs. In this way, by utilizing generative AI and text-generating AI, we support improvement in sports and enable users to continue playing sports more enjoyably and consistently. As a result, they can lead healthier lives.This allows the form checker system to help users improve their sports performance by comparing their own videos with those of professional athletes and providing feedback on the differences in their form.

[0029] The form checker system according to this embodiment comprises a reception unit, a generation unit, and a feedback unit. The reception unit accepts uploads of videos of professional athletes and videos of the user's own sports. Videos of professional athletes include, but are not limited to, specific sports, shooting angles, and resolutions. Videos of the user's own sports include, but are not limited to, videos shot by the user, resolution, and frame rate. The generation unit synthesizes the videos uploaded by the reception unit. The generation unit synthesizes the two videos by, for example, cutting out the required length and range, aligning the scale, and aligning the time axis. The generation unit uses a generation AI to synthesize the videos. The generation AI specifies the start and end points of the videos and cuts out specific action parts. The generation AI also adjusts the number of pixels and maintains the aspect ratio to align the scale of the videos. Furthermore, the generation AI uses frame rate adjustments and synchronization methods to align the time axis of the videos. The generation unit outputs the two videos side by side to facilitate comparison. The generation unit adjusts, for example, the screen splitting method and display size. The feedback unit provides feedback on differences in form based on the video synthesized by the generation unit. The feedback unit provides text feedback such as, for example, "Your elbow position is lower than that of a professional" or "Your hip rotation timing is earlier than that of a professional." The feedback unit generates feedback using a text generation AI. The text generation AI analyzes the differences between the user's form and that of a professional, and provides specific areas for improvement in text. As a result, the form checker system according to this embodiment can support the user's improvement in sports by allowing them to compare their video with that of a professional athlete and receive feedback on the differences in form.

[0030] The reception desk accepts uploads of videos from professional athletes and videos of users' own sports. Videos from professional athletes may include, but are not limited to, specific sports, camera angles, and resolutions. Specifically, videos from professional athletes may include different camera angles and high-resolution footage, allowing users to review their form from multiple perspectives. Furthermore, videos from professional athletes may feature slow motion and zoom-in functions to show specific movements or techniques in detail. On the other hand, videos of users' own sports may include, but are not limited to, videos they have shot themselves, their resolution, and frame rate. Users can shoot and upload videos from any location using their smartphones or cameras. This allows users to easily record their own form and compare it to videos from professional athletes. The reception desk centrally manages these videos and provides an interface for easy user access. For example, users can upload and manage videos through a dedicated application or website. Furthermore, the reception desk has a function to automatically detect differences in video format and resolution and convert or adjust them as needed. This allows users to smoothly upload and use videos shot on different devices and in different environments.

[0031] The generation unit synthesizes the videos uploaded by the reception unit. For example, the generation unit cuts out the required length and range, aligns the scale, and aligns the timelines to synthesize the two videos. The generation unit uses a generation AI to synthesize the videos. For example, the generation AI specifies the start and end points of the videos and cuts out specific action sections. The generation AI also adjusts the number of pixels and maintains the aspect ratio to align the scale of the videos. Furthermore, the generation AI uses frame rate adjustments and synchronization methods to align the timelines of the videos. Specifically, the generation AI automatically detects the start points of the actions in the professional athlete's video and the user's video and adjusts them so that the actions start at the same time. This allows the user to accurately compare the actions of the professional with their own. The generation unit outputs the two videos side by side to facilitate comparison. For example, the generation unit adjusts the screen division method and display size. Specifically, the generation unit adjusts the screen division ratio and display position so that the user can easily view the videos. Furthermore, the generation unit adjusts the video playback speed and provides slow-motion playback and pause functions, allowing users to examine their form in detail. In addition, the generation unit automatically corrects any noise or distortion that may occur during the video synthesis process, providing clear images. As a result, the generation unit enables users to compare their own videos with those of professional athletes with high accuracy and clearly understand the differences in their form.

[0032] The feedback unit provides feedback on differences in form based on the video synthesized by the generation unit. The feedback unit provides text feedback such as, "Your elbow position is lower than the pro's," or "Your hip rotation timing is earlier than the pro's." The feedback unit generates feedback using text generation AI. The text generation AI analyzes the differences between the user's form and the pro's form and provides specific areas for improvement in text. Specifically, the text generation AI analyzes each frame of the video and quantifies the differences between the user's movements and the pro's movements. For example, it presents specific areas for improvement to the user based on specific data such as elbow angle and hip rotation speed. In addition, the text generation AI can provide customized feedback according to the user's level and goals. For example, it can provide basic form improvements to beginners and detailed technical advice to advanced users. Furthermore, the feedback unit can also provide visual explanations using diagrams and animations to make the feedback easier for the user to understand. This allows the user to visually confirm specific areas for improvement and effectively correct their form. The feedback section also includes a function that tracks user progress and visualizes user growth by comparing it with past feedback. This allows users to feel a sense of their own progress and maintain motivation to improve their sports skills.

[0033] The generation unit can combine two videos by cutting out the required length and range, aligning the scale, and aligning the timeline. For example, the generation unit can specify the start and end points of the videos and cut out a specific action portion. The generation unit uses generation AI to adjust the number of pixels and maintain the aspect ratio to align the scale of the videos. The generation unit uses generation AI to adjust the frame rate and synchronization method to align the timeline of the videos. This improves the accuracy of video compositing, allowing users to accurately compare professional forms with their own. Some or all of the above processes in the generation unit are performed using generation AI. For example, the generation unit inputs prompts to the generation AI specifying the start and end points of the videos, and the generation AI cuts out a specific action portion of the videos. The generation unit instructs the generation AI to adjust the number of pixels and maintain the aspect ratio, and the generation AI aligns the scale of the videos. The generation unit instructs the generation AI to adjust the frame rate and synchronization method, and the generation AI aligns the timeline of the videos.

[0034] The feedback unit can provide text-based feedback such as, "Your elbow is lower than a professional's," or "Your hips rotate earlier than a professional's." The feedback unit analyzes the differences between the user's form and a professional's form and provides specific areas for improvement in text. The feedback unit uses text generation AI to generate the feedback. The text generation AI analyzes the differences between the user's form and a professional's form and provides specific areas for improvement in text. This allows the user to understand specific areas for improvement in their form. Some or all of the above processing in the feedback unit is performed using text generation AI. For example, the feedback unit inputs a prompt to the text generation AI to analyze the differences between the user's form and a professional's form, and the text generation AI provides specific areas for improvement in text.

[0035] The generation unit can output two videos side-by-side for easier comparison. The generation unit adjusts, for example, the screen splitting method and display size. The generation unit uses a generation AI to output two videos side-by-side. The generation AI adjusts, for example, the display size of the videos and splits the screen to display the two videos side-by-side. This makes it easier for users to visually compare a professional form with their own form. Some or all of the above processing in the generation unit is performed using the generation AI. For example, the generation unit inputs a prompt to the generation AI to adjust the display size of the videos, and the generation AI splits the screen and displays the two videos side-by-side.

[0036] The feedback unit can display the differences in the forms using slow motion playback and explain what the differences are and when they occur. For example, the feedback unit can set the specific speed and method of slow motion playback to display the differences in the forms in detail. The feedback unit uses a generative AI to configure the slow motion playback. For example, the generative AI sets the playback speed multiplier and the start and end points of the slow motion playback. This allows the user to understand the differences in the forms in detail. Some or all of the above processing in the feedback unit is performed using the generative AI. For example, the feedback unit inputs a prompt to the generative AI to configure the slow motion playback, and the generative AI sets the playback speed multiplier and the start and end points of the slow motion playback.

[0037] The reception desk can analyze a user's past video upload history and select the optimal upload method. For example, the reception desk can analyze the time periods when a user frequently uploaded videos in the past and prompt the user to upload during those times. The reception desk can also prioritize suggesting upload methods the user has used in the past (Wi-Fi, mobile data, etc.). The reception desk can also suggest the optimal file format and resolution based on the user's past upload history. This allows the reception desk to suggest the optimal upload method based on the user's past history. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can input a prompt to the AI ​​to analyze the user's past video upload history, and the AI ​​can select the optimal upload method.

[0038] The reception desk can filter videos based on the user's current sports level and goals when they are uploaded. For example, if the user is a beginner, the reception desk will prioritize uploading videos of basic form. If the user is an intermediate, the reception desk may also prioritize uploading videos that include technical advice. If the user is an advanced, the reception desk may also prioritize uploading videos that require detailed form correction. This ensures that the user uploads the most suitable videos according to their sports level and goals. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input prompts to the AI ​​to filter the user's sports level and goals, and the AI ​​will select the most suitable videos.

[0039] The reception desk can prioritize uploading videos that are highly relevant to the user's geographical location when they upload a video. For example, if the user is in a specific region, the reception desk can prioritize uploading sports videos related to that region. If the user is traveling, the reception desk can also prioritize uploading sports videos related to their travel destination. If the user is at home, the reception desk can also prioritize uploading sports videos that can be done at home. This allows the reception desk to upload the most suitable videos based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input a prompt to the AI ​​to obtain the user's geographical location, and the AI ​​can select highly relevant videos.

[0040] The reception desk can analyze a user's social media activity when they upload a video and upload relevant videos. For example, if a user posts about a particular sport on social media, the reception desk can prioritize uploading videos related to that sport. If a user uses a particular hashtag on social media, the reception desk can also prioritize uploading videos related to that hashtag. If a user follows a particular athlete on social media, the reception desk can also prioritize uploading videos related to that athlete. This allows the reception desk to upload the most suitable videos based on the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input prompts to the AI ​​to analyze the user's social media activity, and the AI ​​can select relevant videos.

[0041] The generation unit can apply different synthesis algorithms depending on the type of sport during video synthesis. For example, in the case of baseball, the generation unit applies a synthesis algorithm specialized for pitching form. In the case of soccer, the generation unit can also apply a synthesis algorithm specialized for kicking form. In the case of tennis, the generation unit can also apply a synthesis algorithm specialized for swing form. This enables optimal video synthesis according to the type of sport. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI to apply a synthesis algorithm according to the type of sport, and the generation AI selects the optimal synthesis algorithm.

[0042] The generation unit can improve the accuracy of video synthesis by referring to the user's past form data. For example, the generation unit improves the accuracy of synthesis based on form data previously uploaded by the user. The generation unit can also extract improvements to specific actions from the user's past form data and reflect them in the synthesis. The generation unit can also analyze the user's past form data and select the optimal synthesis algorithm. This improves the accuracy of synthesis based on the user's past form data. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI to refer to the user's past form data, and the generation AI selects the optimal synthesis algorithm.

[0043] The generation unit can determine the priority of video synthesis based on the user's sports history. For example, the generation unit may prioritize synthesizing videos of sports the user has frequently played in the past. The generation unit can also prioritize synthesizing videos related to specific techniques based on the user's sports history. The generation unit can also analyze the user's sports history and select the most effective synthesis method. This enables optimal video synthesis based on the user's sports history. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI that refers to the user's sports history, and the generation AI selects the optimal synthesis method.

[0044] The generation unit can adjust the order of video synthesis based on the user's sports goals. For example, if the user wants to learn a specific technique, the generation unit will prioritize synthesizing videos related to that technique. If the user aims to improve their overall form, the generation unit can also synthesize videos starting with basic movements. If the user is preparing for a specific competition, the generation unit can also prioritize synthesizing movements related to that competition. This enables optimal video synthesis tailored to the user's sports goals. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs prompts to the generation AI that refer to the user's sports goals, and the generation AI selects the optimal synthesis order.

[0045] The feedback unit can adjust the level of detail in the feedback based on the importance of the form. For example, the feedback unit provides detailed feedback for important form differences. For minor form differences, it can provide concise feedback. The feedback unit can also prioritize feedback according to the importance of the form. This allows for the provision of optimal feedback according to the importance of the form. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit inputs a prompt to the AI ​​to evaluate the importance of the form, and the AI ​​adjusts the level of detail in the feedback.

[0046] The feedback unit can apply different feedback algorithms depending on the form category during feedback. For example, in the case of a pitching form, the feedback unit applies a feedback algorithm specialized for pitching. In the case of a batting form, the feedback unit can also apply a feedback algorithm specialized for batting. In the case of a swing form, the feedback unit can also apply a feedback algorithm specialized for swinging. This allows for the provision of optimal feedback according to the form category. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit inputs a prompt to the AI ​​to apply a feedback algorithm according to the form category, and the AI ​​selects the optimal feedback algorithm.

[0047] The feedback unit can prioritize feedback based on when the form was submitted. For example, it may prioritize feedback for the most recent form data. It may also prioritize feedback for form data submitted by the user within a specific deadline. The feedback unit can also adjust the order of feedback depending on when the form was submitted. This allows for the provision of optimal feedback based on the submission timing. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit may input a prompt to the AI ​​to evaluate when the form was submitted, and the AI ​​may determine the priority of the feedback.

[0048] The feedback unit can adjust the order of feedback based on the relevance of the forms during the feedback process. For example, the feedback unit can prioritize providing feedback on significant form differences. It can also postpone providing feedback on minor form differences. The feedback unit can also adjust the order of feedback according to the relevance of the forms. This allows for the provision of optimal feedback according to the relevance of the forms. 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 prompts to the AI ​​to evaluate the relevance of the forms, and the AI ​​can adjust the order of feedback.

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

[0050] The generation unit can determine the priority of video synthesis based on the user's sports history. For example, the generation unit may prioritize synthesizing videos of sports the user has frequently played in the past. The generation unit can also prioritize synthesizing videos related to specific techniques based on the user's sports history. The generation unit can also analyze the user's sports history and select the most effective synthesis method. This enables optimal video synthesis based on the user's sports history. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI that refers to the user's sports history, and the generation AI selects the optimal synthesis method.

[0051] The generation unit can improve the accuracy of video synthesis by referring to the user's past form data. For example, the generation unit improves the accuracy of synthesis based on form data previously uploaded by the user. The generation unit can also extract improvements to specific actions from the user's past form data and reflect them in the synthesis. The generation unit can also analyze the user's past form data and select the optimal synthesis algorithm. This improves the accuracy of synthesis based on the user's past form data. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI to refer to the user's past form data, and the generation AI selects the optimal synthesis algorithm.

[0052] The feedback unit can adjust the level of detail in the feedback based on the importance of the form. For example, the feedback unit provides detailed feedback for important form differences. For minor form differences, it can provide concise feedback. The feedback unit can also prioritize feedback according to the importance of the form. This allows for the provision of optimal feedback according to the importance of the form. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit inputs a prompt to the AI ​​to evaluate the importance of the form, and the AI ​​adjusts the level of detail in the feedback.

[0053] The generation unit can apply different synthesis algorithms depending on the type of sport during video synthesis. For example, in the case of baseball, the generation unit applies a synthesis algorithm specialized for pitching form. In the case of soccer, the generation unit can also apply a synthesis algorithm specialized for kicking form. In the case of tennis, the generation unit can also apply a synthesis algorithm specialized for swing form. This enables optimal video synthesis according to the type of sport. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI to apply a synthesis algorithm according to the type of sport, and the generation AI selects the optimal synthesis algorithm.

[0054] The reception desk can prioritize uploading videos that are highly relevant to the user's geographical location when they upload a video. For example, if the user is in a specific region, the reception desk can prioritize uploading sports videos related to that region. If the user is traveling, the reception desk can also prioritize uploading sports videos related to their travel destination. If the user is at home, the reception desk can also prioritize uploading sports videos that can be done at home. This allows the reception desk to upload the most suitable videos based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input a prompt to the AI ​​to obtain the user's geographical location, and the AI ​​can select highly relevant videos.

[0055] The feedback unit can apply different feedback algorithms depending on the form category during feedback. For example, in the case of a pitching form, the feedback unit applies a feedback algorithm specialized for pitching. In the case of a batting form, the feedback unit can also apply a feedback algorithm specialized for batting. In the case of a swing form, the feedback unit can also apply a feedback algorithm specialized for swinging. This allows for the provision of optimal feedback according to the form category. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit inputs a prompt to the AI ​​to apply a feedback algorithm according to the form category, and the AI ​​selects the optimal feedback algorithm.

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

[0057] Step 1: The reception desk accepts uploads of videos from professional athletes and videos of users' own sports. Videos from professional athletes include, but are not limited to, specific sports, shooting angles, and resolutions. Videos of users' own sports include, but are not limited to, videos shot by the user, resolution, and frame rate. Step 2: The generation unit combines the videos uploaded by the reception unit. The generation unit cuts out the required length and range, aligns the scale, and aligns the timelines to combine the two videos. Using the generation AI, the start and end points of the videos are specified, and specific action sections are cut out. The generation AI adjusts the number of pixels and maintains the aspect ratio to align the scale of the videos. Furthermore, the generation AI adjusts the frame rate and uses synchronization methods to align the timelines of the videos. The generation unit outputs the two videos side by side to make them easier to compare. The generation unit adjusts the screen splitting method and display size. Step 3: The feedback unit provides feedback on the differences in form based on the video synthesized by the generation unit. The feedback unit provides text feedback such as, "Your elbow is lower than the pro's," or "Your hips rotate earlier than the pro's." The feedback unit generates the feedback using text generation AI. The text generation AI analyzes the differences between the user's form and the pro's form and provides specific areas for improvement in text.

[0058] (Example of form 2) The form checker system according to an embodiment of the present invention is a system for supporting improvement in sports. In this form checker system, the user uploads a video of a professional athlete and a video of their own sports, and a generating AI combines the two videos and processes them to make them easier to compare. In addition, a text generating AI provides feedback on the differences in form. This mechanism makes it easier for the user to practice alone and solves problems of time constraints and costs. For example, the user uploads a video of a professional athlete and a video of their own sports. For example, in the case of a baseball pitching form, the user uploads a video from the stance to the throw. This information is input to the generating AI. Next, the generating AI combines the two videos. The generating AI cuts out the necessary length (e.g., from the stance to the throw) and the necessary range (e.g., centered on the person) and adjusts the scale. It also aligns the time axis to the timing of the same action and outputs the two videos side by side. This makes it easier for the user to compare the form of a professional with their own form. Furthermore, a text generating AI provides feedback on the differences in form. For example, it provides text-based feedback such as, "Compared to the pros, your elbow is lower," or "Compared to the pros, your hips rotate too early." This allows users to specifically understand areas for improvement in their form. This system makes it easier for users to practice alone and solves problems related to time constraints and costs. For example, when practicing while looking at books or photos, you need to compare yourself to the photos, but with this system, you can practice while watching videos. Also, when attending lessons, you can only get feedback when the coach is present, but with this system, you can get feedback anytime. Furthermore, using dedicated sensors is expensive, but this system can reduce costs. In this way, by utilizing generative AI and text-generating AI, we support improvement in sports and enable users to continue playing sports more enjoyably and consistently. As a result, they can lead healthier lives.This allows the form checker system to help users improve their sports performance by comparing their own videos with those of professional athletes and providing feedback on the differences in their form.

[0059] The form checker system according to this embodiment comprises a reception unit, a generation unit, and a feedback unit. The reception unit accepts uploads of videos of professional athletes and videos of the user's own sports. Videos of professional athletes include, but are not limited to, specific sports, shooting angles, and resolutions. Videos of the user's own sports include, but are not limited to, videos shot by the user, resolution, and frame rate. The generation unit synthesizes the videos uploaded by the reception unit. The generation unit synthesizes the two videos by, for example, cutting out the required length and range, aligning the scale, and aligning the time axis. The generation unit uses a generation AI to synthesize the videos. The generation AI specifies the start and end points of the videos and cuts out specific action parts. The generation AI also adjusts the number of pixels and maintains the aspect ratio to align the scale of the videos. Furthermore, the generation AI uses frame rate adjustments and synchronization methods to align the time axis of the videos. The generation unit outputs the two videos side by side to facilitate comparison. The generation unit adjusts, for example, the screen splitting method and display size. The feedback unit provides feedback on differences in form based on the video synthesized by the generation unit. The feedback unit provides text feedback such as, for example, "Your elbow position is lower than that of a professional" or "Your hip rotation timing is earlier than that of a professional." The feedback unit generates feedback using a text generation AI. The text generation AI analyzes the differences between the user's form and that of a professional, and provides specific areas for improvement in text. As a result, the form checker system according to this embodiment can support the user's improvement in sports by allowing them to compare their video with that of a professional athlete and receive feedback on the differences in form.

[0060] The reception desk accepts uploads of videos from professional athletes and videos of users' own sports. Videos from professional athletes may include, but are not limited to, specific sports, camera angles, and resolutions. Specifically, videos from professional athletes may include different camera angles and high-resolution footage, allowing users to review their form from multiple perspectives. Furthermore, videos from professional athletes may feature slow motion and zoom-in functions to show specific movements or techniques in detail. On the other hand, videos of users' own sports may include, but are not limited to, videos they have shot themselves, their resolution, and frame rate. Users can shoot and upload videos from any location using their smartphones or cameras. This allows users to easily record their own form and compare it to videos from professional athletes. The reception desk centrally manages these videos and provides an interface for easy user access. For example, users can upload and manage videos through a dedicated application or website. Furthermore, the reception desk has a function to automatically detect differences in video format and resolution and convert or adjust them as needed. This allows users to smoothly upload and use videos shot on different devices and in different environments.

[0061] The generation unit synthesizes the videos uploaded by the reception unit. For example, the generation unit cuts out the required length and range, aligns the scale, and aligns the timelines to synthesize the two videos. The generation unit uses a generation AI to synthesize the videos. For example, the generation AI specifies the start and end points of the videos and cuts out specific action sections. The generation AI also adjusts the number of pixels and maintains the aspect ratio to align the scale of the videos. Furthermore, the generation AI uses frame rate adjustments and synchronization methods to align the timelines of the videos. Specifically, the generation AI automatically detects the start points of the actions in the professional athlete's video and the user's video and adjusts them so that the actions start at the same time. This allows the user to accurately compare the actions of the professional with their own. The generation unit outputs the two videos side by side to facilitate comparison. For example, the generation unit adjusts the screen division method and display size. Specifically, the generation unit adjusts the screen division ratio and display position so that the user can easily view the videos. Furthermore, the generation unit adjusts the video playback speed and provides slow-motion playback and pause functions, allowing users to examine their form in detail. In addition, the generation unit automatically corrects any noise or distortion that may occur during the video synthesis process, providing clear images. As a result, the generation unit enables users to compare their own videos with those of professional athletes with high accuracy and clearly understand the differences in their form.

[0062] The feedback unit provides feedback on differences in form based on the video synthesized by the generation unit. The feedback unit provides text feedback such as, "Your elbow position is lower than the pro's," or "Your hip rotation timing is earlier than the pro's." The feedback unit generates feedback using text generation AI. The text generation AI analyzes the differences between the user's form and the pro's form and provides specific areas for improvement in text. Specifically, the text generation AI analyzes each frame of the video and quantifies the differences between the user's movements and the pro's movements. For example, it presents specific areas for improvement to the user based on specific data such as elbow angle and hip rotation speed. In addition, the text generation AI can provide customized feedback according to the user's level and goals. For example, it can provide basic form improvements to beginners and detailed technical advice to advanced users. Furthermore, the feedback unit can also provide visual explanations using diagrams and animations to make the feedback easier for the user to understand. This allows the user to visually confirm specific areas for improvement and effectively correct their form. The feedback section also includes a function that tracks user progress and visualizes user growth by comparing it with past feedback. This allows users to feel a sense of their own progress and maintain motivation to improve their sports skills.

[0063] The generation unit can combine two videos by cutting out the required length and range, aligning the scale, and aligning the timeline. For example, the generation unit can specify the start and end points of the videos and cut out a specific action portion. The generation unit uses generation AI to adjust the number of pixels and maintain the aspect ratio to align the scale of the videos. The generation unit uses generation AI to adjust the frame rate and synchronization method to align the timeline of the videos. This improves the accuracy of video compositing, allowing users to accurately compare professional forms with their own. Some or all of the above processes in the generation unit are performed using generation AI. For example, the generation unit inputs prompts to the generation AI specifying the start and end points of the videos, and the generation AI cuts out a specific action portion of the videos. The generation unit instructs the generation AI to adjust the number of pixels and maintain the aspect ratio, and the generation AI aligns the scale of the videos. The generation unit instructs the generation AI to adjust the frame rate and synchronization method, and the generation AI aligns the timeline of the videos.

[0064] The feedback unit can provide text-based feedback such as, "Your elbow is lower than a professional's," or "Your hips rotate earlier than a professional's." The feedback unit analyzes the differences between the user's form and a professional's form and provides specific areas for improvement in text. The feedback unit uses text generation AI to generate the feedback. The text generation AI analyzes the differences between the user's form and a professional's form and provides specific areas for improvement in text. This allows the user to understand specific areas for improvement in their form. Some or all of the above processing in the feedback unit is performed using text generation AI. For example, the feedback unit inputs a prompt to the text generation AI to analyze the differences between the user's form and a professional's form, and the text generation AI provides specific areas for improvement in text.

[0065] The generation unit can output two videos side-by-side for easier comparison. The generation unit adjusts, for example, the screen splitting method and display size. The generation unit uses a generation AI to output two videos side-by-side. The generation AI adjusts, for example, the display size of the videos and splits the screen to display the two videos side-by-side. This makes it easier for users to visually compare a professional form with their own form. Some or all of the above processing in the generation unit is performed using the generation AI. For example, the generation unit inputs a prompt to the generation AI to adjust the display size of the videos, and the generation AI splits the screen and displays the two videos side-by-side.

[0066] The feedback unit can display the differences in the forms using slow motion playback and explain what the differences are and when they occur. For example, the feedback unit can set the specific speed and method of slow motion playback to display the differences in the forms in detail. The feedback unit uses a generative AI to configure the slow motion playback. For example, the generative AI sets the playback speed multiplier and the start and end points of the slow motion playback. This allows the user to understand the differences in the forms in detail. Some or all of the above processing in the feedback unit is performed using the generative AI. For example, the feedback unit inputs a prompt to the generative AI to configure the slow motion playback, and the generative AI sets the playback speed multiplier and the start and end points of the slow motion playback.

[0067] The reception desk can estimate the user's emotions and adjust the video upload timing based on the estimated emotions. For example, if the user is feeling stressed, the reception desk may prompt them to upload a video during a time when they can relax. If the user is highly motivated, the reception desk may also prompt them to upload a video immediately. If the user is tired, the reception desk may suggest uploading a video after a break. This allows for video uploads at the optimal time according to the user'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 reception desk is performed using generative AI. For example, the reception desk inputs a prompt to the generative AI to estimate the user's emotions, and the generative AI estimates the user's emotions. Based on the generative AI, the reception desk adjusts the video upload timing.

[0068] The reception desk can analyze a user's past video upload history and select the optimal upload method. For example, the reception desk can analyze the time periods when a user frequently uploaded videos in the past and prompt the user to upload during those times. The reception desk can also prioritize suggesting upload methods the user has used in the past (Wi-Fi, mobile data, etc.). The reception desk can also suggest the optimal file format and resolution based on the user's past upload history. This allows the reception desk to suggest the optimal upload method based on the user's past history. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can input a prompt to the AI ​​to analyze the user's past video upload history, and the AI ​​can select the optimal upload method.

[0069] The reception desk can filter videos based on the user's current sports level and goals when they are uploaded. For example, if the user is a beginner, the reception desk will prioritize uploading videos of basic form. If the user is an intermediate, the reception desk may also prioritize uploading videos that include technical advice. If the user is an advanced, the reception desk may also prioritize uploading videos that require detailed form correction. This ensures that the user uploads the most suitable videos according to their sports level and goals. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input prompts to the AI ​​to filter the user's sports level and goals, and the AI ​​will select the most suitable videos.

[0070] The reception desk can estimate the user's emotions and determine the priority of videos to upload based on the estimated emotions. For example, if the user is excited, the reception desk will prioritize uploading the latest videos. If the user is relaxed, the reception desk may also re-upload older videos. If the user is stressed, the reception desk may also prioritize uploading videos with relaxing content. This allows for the priority uploading of videos that are optimal for the user'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 reception desk is performed using generative AI. For example, the reception desk inputs a prompt to the generative AI to estimate the user's emotions, and the generative AI estimates the user's emotions. Based on the generative AI, the reception desk determines the priority of videos.

[0071] The reception desk can prioritize uploading videos that are highly relevant to the user's geographical location when they upload a video. For example, if the user is in a specific region, the reception desk can prioritize uploading sports videos related to that region. If the user is traveling, the reception desk can also prioritize uploading sports videos related to their travel destination. If the user is at home, the reception desk can also prioritize uploading sports videos that can be done at home. This allows the reception desk to upload the most suitable videos based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input a prompt to the AI ​​to obtain the user's geographical location, and the AI ​​can select highly relevant videos.

[0072] The reception desk can analyze a user's social media activity when they upload a video and upload relevant videos. For example, if a user posts about a particular sport on social media, the reception desk can prioritize uploading videos related to that sport. If a user uses a particular hashtag on social media, the reception desk can also prioritize uploading videos related to that hashtag. If a user follows a particular athlete on social media, the reception desk can also prioritize uploading videos related to that athlete. This allows the reception desk to upload the most suitable videos based on the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input prompts to the AI ​​to analyze the user's social media activity, and the AI ​​can select relevant videos.

[0073] The generation unit can estimate the user's emotions and adjust the video synthesis method based on the estimated emotions. For example, if the user is relaxed, the generation AI can generate a video that progresses at a leisurely pace. If the user is in a hurry, the generation AI can also generate a video that emphasizes the shortest route. If the user is excited, the generation AI can also generate a video with visually stimulating effects. This allows for the provision of an optimal video synthesis method that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation 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 generation unit is performed using the generation AI. For example, the generation unit inputs a prompt to the generation AI to estimate the user's emotions, and the generation AI estimates the user's emotions. The generation unit adjusts the video synthesis method based on the generation AI.

[0074] The generation unit can apply different synthesis algorithms depending on the type of sport during video synthesis. For example, in the case of baseball, the generation unit applies a synthesis algorithm specialized for pitching form. In the case of soccer, the generation unit can also apply a synthesis algorithm specialized for kicking form. In the case of tennis, the generation unit can also apply a synthesis algorithm specialized for swing form. This enables optimal video synthesis according to the type of sport. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI to apply a synthesis algorithm according to the type of sport, and the generation AI selects the optimal synthesis algorithm.

[0075] The generation unit can improve the accuracy of video synthesis by referring to the user's past form data. For example, the generation unit improves the accuracy of synthesis based on form data previously uploaded by the user. The generation unit can also extract improvements to specific actions from the user's past form data and reflect them in the synthesis. The generation unit can also analyze the user's past form data and select the optimal synthesis algorithm. This improves the accuracy of synthesis based on the user's past form data. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI to refer to the user's past form data, and the generation AI selects the optimal synthesis algorithm.

[0076] The generation unit can estimate the user's emotions and adjust the length of the synthesized video based on the estimated emotions. For example, if the user is in a hurry, the generation AI can generate a short, concise video. If the user is relaxed, the generation AI can generate a longer video with detailed explanations. If the user is excited, the generation AI can generate a video with visually stimulating effects. This allows for the provision of an optimal video length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation 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 generation unit is performed using the generation AI. For example, the generation unit inputs a prompt to the generation AI to estimate the user's emotions, and the generation AI estimates the user's emotions. The generation unit adjusts the length of the video based on the generation AI.

[0077] The generation unit can determine the priority of video synthesis based on the user's sports history. For example, the generation unit may prioritize synthesizing videos of sports the user has frequently played in the past. The generation unit can also prioritize synthesizing videos related to specific techniques based on the user's sports history. The generation unit can also analyze the user's sports history and select the most effective synthesis method. This enables optimal video synthesis based on the user's sports history. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI that refers to the user's sports history, and the generation AI selects the optimal synthesis method.

[0078] The generation unit can adjust the order of video synthesis based on the user's sports goals. For example, if the user wants to learn a specific technique, the generation unit will prioritize synthesizing videos related to that technique. If the user aims to improve their overall form, the generation unit can also synthesize videos starting with basic movements. If the user is preparing for a specific competition, the generation unit can also prioritize synthesizing movements related to that competition. This enables optimal video synthesis tailored to the user's sports goals. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs prompts to the generation AI that refer to the user's sports goals, and the generation AI selects the optimal synthesis order.

[0079] The feedback unit can estimate the user's emotions and adjust the way it expresses the feedback based on the estimated emotions. For example, if the user is nervous, the feedback unit will provide feedback in gentle words. If the user is relaxed, the feedback unit can also provide detailed feedback. If the user is in a hurry, the feedback unit can provide concise and to-the-point feedback. This allows for the provision of optimal feedback tailored to the user'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-described processes in the feedback unit are performed using generative AI. For example, the feedback unit inputs a prompt to the generative AI to estimate the user's emotions, and the generative AI estimates the user's emotions. Based on the generative AI, the feedback unit adjusts the way it expresses the feedback.

[0080] The feedback unit can adjust the level of detail in the feedback based on the importance of the form. For example, the feedback unit provides detailed feedback for important form differences. For minor form differences, it can provide concise feedback. The feedback unit can also prioritize feedback according to the importance of the form. This allows for the provision of optimal feedback according to the importance of the form. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit inputs a prompt to the AI ​​to evaluate the importance of the form, and the AI ​​adjusts the level of detail in the feedback.

[0081] The feedback unit can apply different feedback algorithms depending on the form category during feedback. For example, in the case of a pitching form, the feedback unit applies a feedback algorithm specialized for pitching. In the case of a batting form, the feedback unit can also apply a feedback algorithm specialized for batting. In the case of a swing form, the feedback unit can also apply a feedback algorithm specialized for swinging. This allows for the provision of optimal feedback according to the form category. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit inputs a prompt to the AI ​​to apply a feedback algorithm according to the form category, and the AI ​​selects the optimal feedback algorithm.

[0082] The feedback unit can estimate the user's emotions and adjust the length of the feedback based on the estimated emotions. For example, if the user is in a hurry, the feedback unit can provide short, concise feedback. If the user is relaxed, the feedback unit can also provide longer feedback with detailed explanations. If the user is excited, the feedback unit can also provide feedback with visually stimulating effects. This allows for the provision of an optimal feedback length according to the user'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 is performed using generative AI. For example, the feedback unit inputs a prompt to the generative AI to estimate the user's emotions, and the generative AI estimates the user's emotions. The feedback unit then adjusts the length of the feedback based on the generative AI.

[0083] The feedback unit can prioritize feedback based on when the form was submitted. For example, it may prioritize feedback for the most recent form data. It may also prioritize feedback for form data submitted by the user within a specific deadline. The feedback unit can also adjust the order of feedback depending on when the form was submitted. This allows for the provision of optimal feedback based on the submission timing. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit may input a prompt to the AI ​​to evaluate when the form was submitted, and the AI ​​may determine the priority of the feedback.

[0084] The feedback unit can adjust the order of feedback based on the relevance of the forms during the feedback process. For example, the feedback unit can prioritize providing feedback on significant form differences. It can also postpone providing feedback on minor form differences. The feedback unit can also adjust the order of feedback according to the relevance of the forms. This allows for the provision of optimal feedback according to the relevance of the forms. 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 prompts to the AI ​​to evaluate the relevance of the forms, and the AI ​​can adjust the order of feedback.

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

[0086] The reception desk can estimate the user's emotions and suggest a method for uploading the video based on the estimated emotions. For example, if the user is stressed, it can suggest a method that allows for easy uploading. If the user is relaxed, it can suggest a method that allows for detailed settings. If the user is excited, it can suggest a method that allows for immediate uploading. This allows the system to provide the optimal upload method according to the user'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 reception desk is performed using generative AI. For example, the reception desk inputs a prompt to estimate the user's emotions into the generative AI, which then estimates the user's emotions. Based on the generative AI, the reception desk suggests a method for uploading the video.

[0087] The generation unit can determine the priority of video synthesis based on the user's sports history. For example, the generation unit may prioritize synthesizing videos of sports the user has frequently played in the past. The generation unit can also prioritize synthesizing videos related to specific techniques based on the user's sports history. The generation unit can also analyze the user's sports history and select the most effective synthesis method. This enables optimal video synthesis based on the user's sports history. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI that refers to the user's sports history, and the generation AI selects the optimal synthesis method.

[0088] The feedback unit can estimate the user's emotions and adjust the way it expresses the feedback based on the estimated emotions. For example, if the user is nervous, it can provide feedback in gentle words. If the user is relaxed, it can provide detailed feedback. If the user is in a hurry, it can provide concise and to-the-point feedback. This allows for the provision of optimal feedback tailored to the user'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-described processes in the feedback unit are performed using generative AI. For example, the feedback unit inputs a prompt to the generative AI to estimate the user's emotions, and the generative AI estimates the user's emotions. Based on the generative AI, the feedback unit adjusts the way it expresses the feedback.

[0089] The generation unit can improve the accuracy of video synthesis by referring to the user's past form data. For example, the generation unit improves the accuracy of synthesis based on form data previously uploaded by the user. The generation unit can also extract improvements to specific actions from the user's past form data and reflect them in the synthesis. The generation unit can also analyze the user's past form data and select the optimal synthesis algorithm. This improves the accuracy of synthesis based on the user's past form data. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI to refer to the user's past form data, and the generation AI selects the optimal synthesis algorithm.

[0090] The feedback unit can adjust the level of detail in the feedback based on the importance of the form. For example, the feedback unit provides detailed feedback for important form differences. For minor form differences, it can provide concise feedback. The feedback unit can also prioritize feedback according to the importance of the form. This allows for the provision of optimal feedback according to the importance of the form. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit inputs a prompt to the AI ​​to evaluate the importance of the form, and the AI ​​adjusts the level of detail in the feedback.

[0091] The reception desk can estimate the user's emotions and determine the priority of videos to upload based on the estimated emotions. For example, if the user is excited, the latest video will be uploaded first. If the user is relaxed, older videos may be re-uploaded. If the user is stressed, videos with relaxing content may be uploaded first. This allows for the uploading of the most suitable video according to the user'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 reception desk is performed using generative AI. For example, the reception desk inputs a prompt to the generative AI to estimate the user's emotions, and the generative AI estimates the user's emotions. The reception desk then determines the priority of videos based on the generative AI.

[0092] The generation unit can apply different synthesis algorithms depending on the type of sport during video synthesis. For example, in the case of baseball, the generation unit applies a synthesis algorithm specialized for pitching form. In the case of soccer, the generation unit can also apply a synthesis algorithm specialized for kicking form. In the case of tennis, the generation unit can also apply a synthesis algorithm specialized for swing form. This enables optimal video synthesis according to the type of sport. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a prompt to the generation AI to apply a synthesis algorithm according to the type of sport, and the generation AI selects the optimal synthesis algorithm.

[0093] The feedback unit can estimate the user's emotions and adjust the length of the feedback based on the estimated emotions. For example, if the user is in a hurry, it can provide short, concise feedback. If the user is relaxed, it can provide longer feedback with detailed explanations. If the user is excited, it can provide feedback with visually stimulating effects. This allows for the provision of the optimal feedback length according to the user'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 is performed using generative AI. For example, the feedback unit inputs a prompt to the generative AI to estimate the user's emotions, and the generative AI estimates the user's emotions. The feedback unit then adjusts the length of the feedback based on the generative AI.

[0094] The reception desk can prioritize uploading videos that are highly relevant to the user's geographical location when they upload a video. For example, if the user is in a specific region, the reception desk can prioritize uploading sports videos related to that region. If the user is traveling, the reception desk can also prioritize uploading sports videos related to their travel destination. If the user is at home, the reception desk can also prioritize uploading sports videos that can be done at home. This allows the reception desk to upload the most suitable videos based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input a prompt to the AI ​​to obtain the user's geographical location, and the AI ​​can select highly relevant videos.

[0095] The feedback unit can apply different feedback algorithms depending on the form category during feedback. For example, in the case of a pitching form, the feedback unit applies a feedback algorithm specialized for pitching. In the case of a batting form, the feedback unit can also apply a feedback algorithm specialized for batting. In the case of a swing form, the feedback unit can also apply a feedback algorithm specialized for swinging. This allows for the provision of optimal feedback according to the form category. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit inputs a prompt to the AI ​​to apply a feedback algorithm according to the form category, and the AI ​​selects the optimal feedback algorithm.

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

[0097] Step 1: The reception desk accepts uploads of videos from professional athletes and videos of users' own sports. Videos from professional athletes include, but are not limited to, specific sports, shooting angles, and resolutions. Videos of users' own sports include, but are not limited to, videos shot by the user, resolution, and frame rate. Step 2: The generation unit combines the videos uploaded by the reception unit. The generation unit cuts out the required length and range, aligns the scale, and aligns the timelines to combine the two videos. Using the generation AI, the start and end points of the videos are specified, and specific action sections are cut out. The generation AI adjusts the number of pixels and maintains the aspect ratio to align the scale of the videos. Furthermore, the generation AI adjusts the frame rate and uses synchronization methods to align the timelines of the videos. The generation unit outputs the two videos side by side to make them easier to compare. The generation unit adjusts the screen splitting method and display size. Step 3: The feedback unit provides feedback on the differences in form based on the video synthesized by the generation unit. The feedback unit provides text feedback such as, "Your elbow is lower than the pro's," or "Your hips rotate earlier than the pro's." The feedback unit generates the feedback using text generation AI. The text generation AI analyzes the differences between the user's form and the pro's form and provides specific areas for improvement in text.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

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

[0101] Each of the multiple elements described above, including the reception unit, generation unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and accepts the upload of a video of a professional athlete and a video of the user's own sports. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and synthesizes the two videos using a generation AI. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback on the differences in form using a text generation AI. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

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

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

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

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

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

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

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

[0110] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

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

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0116] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0117] Each of the multiple elements described above, including the reception unit, generation unit, and feedback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and accepts the upload of a video of a professional athlete and a video of the user's own sports. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and synthesizes the two videos using a generation AI. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback on the differences in form using a text generation AI. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

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

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

[0122] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

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

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

[0126] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

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

[0130] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0132] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0133] Each of the multiple elements described above, including the reception unit, generation unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and accepts the upload of videos of professional athletes and videos of the user's own sports. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and synthesizes the two videos using a generation AI. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback on the differences in form using a text generation AI. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

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

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

[0138] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

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

[0141] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

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

[0143] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

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

[0147] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0149] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the reception unit, generation unit, and feedback unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and accepts the upload of a video of a professional athlete and a video of the user's own sports. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and synthesizes the two videos using a generation AI. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides feedback on the differences in form using a text generation AI. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

[0160] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0161] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

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

[0163] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

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

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

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

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

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

[0169] (Note 1) A reception desk that accepts uploads of videos from professional athletes and videos of people's own sports activities. A generation unit that synthesizes the videos uploaded by the reception unit, The system includes a feedback unit that provides feedback on differences in form based on the video synthesized by the generation unit. A system characterized by the following features. (Note 2) The generating unit is Cut out the required length and range, align the scale, and synchronize the timelines to combine the two videos. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned feedback unit is Provide text-based feedback such as, "Compared to the pros, your elbows are positioned lower," or "Compared to the pros, your hips rotate earlier." The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Display the two videos side-by-side for easier comparison. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned feedback unit is The differences in form are shown in slow motion, and the differences are explained at what point in time. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is It estimates the user's emotions and adjusts the video upload timing based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is Analyze the user's past video upload history and select the optimal upload method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is When uploading videos, filtering is performed based on the user's current sports level and goals. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is It estimates user sentiment and prioritizes uploading videos based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When uploading videos, the system prioritizes uploading videos that are highly relevant to the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When uploading a video, the system analyzes the user's social media activity and uploads relevant videos. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is It estimates the user's emotions and adjusts the video compositing method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is When compositing videos, different compositing algorithms are applied depending on the type of sport. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When compositing videos, the system improves compositing accuracy by referencing the user's past form data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is It estimates the user's emotions and adjusts the length of the synthesized video based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is When compositing videos, the compositing priority is determined based on the user's sports history. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When compositing videos, the compositing order is adjusted based on the user's sports goals. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned feedback unit is It estimates the user's emotions and adjusts how feedback is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned feedback unit is When providing feedback, adjust the level of detail in the feedback based on the importance of the form. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned feedback unit is When providing feedback, different feedback algorithms are applied depending on the form category. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned feedback unit is It estimates the user's emotions and adjusts the length of the feedback based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned feedback unit is When providing feedback, we prioritize feedback based on when the form was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned feedback unit is When providing feedback, adjust the order of feedback based on the relevance of the form. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

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

Claims

1. A reception desk that accepts uploads of videos from professional athletes and videos of people's own sports activities. A generation unit that synthesizes the videos uploaded by the reception unit, The system includes a feedback unit that provides feedback on differences in form based on the video synthesized by the generation unit. A system characterized by the following features.

2. The generating unit is Cut out the required length and range, align the scale, and synchronize the timelines to combine the two videos. The system according to feature 1.

3. The aforementioned feedback unit is Provide feedback in text. The system according to feature 1.

4. The generating unit is Display the two videos side-by-side for easier comparison. The system according to feature 1.

5. The aforementioned feedback unit is The differences in form are shown in slow motion, and the differences are explained at what point in time. The system according to feature 1.

6. The aforementioned reception unit is It estimates the user's emotions and adjusts the video upload timing based on the estimated user emotions. The system according to feature 1.

7. The aforementioned reception unit is Analyze the user's past video upload history and select the optimal upload method. The system according to feature 1.

8. The aforementioned reception unit is When uploading videos, filtering is performed based on the user's current sports level and goals. The system according to feature 1.

9. The aforementioned reception unit is It estimates user sentiment and prioritizes uploading videos based on the estimated user sentiment. The system according to feature 1.

10. The aforementioned reception unit is When uploading videos, the system prioritizes uploading videos that are highly relevant to the user's geographical location. The system according to feature 1.

Images