system

Abstract

We provide the system. [Solution] A means of filming the movements of swimmers, A receiving means for receiving captured motion video, An evaluation method that analyzes received video data and evaluates the player's movements in real time, A generation means for generating coaching content for players based on evaluation results, A conversion means for converting the generated instructional content into data for display, A system including an output means for outputting the converted data to an underwater visual device.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Improving the form of a swimmer usually requires long-term training and accurate guidance. Especially for beginners and amateur swimmers, the absence of a coach and insufficient appropriate feedback are factors that hinder improvement. Therefore, there is a need for a system that allows swimmers to understand their own form in real time and make immediate improvements.

Means for Solving the Problems

[0005] This invention provides a system that automatically generates personalized coaching for each athlete by capturing their movements in real time and analyzing the video data using AI. The generated coaching content is displayed on an underwater visual device, allowing athletes to receive immediate visual feedback. This system supports athletes in effectively improving their form by employing analysis based on past performance data and a display method that offers excellent visibility underwater.

[0006] "Filming equipment" refers to devices or systems used to record the movements of swimmers in real time.

[0007] "Receiving means" refers to the technology for transferring and receiving video data acquired by the shooting means to a server or analysis device.

[0008] "Evaluation means" refers to a method or apparatus for analyzing a swimmer's form and movements based on analyzed video data and evaluating their performance.

[0009] "Generation means" refers to technology for automatically creating specific coaching content and improvement suggestions for players based on evaluation results.

[0010] A "conversion method" refers to a process or device that organizes the generated instructional content into a format that is easy for players to understand and adjusts it as data for display.

[0011] The "output means" refers to the technology that transmits the converted data to the user's underwater visual device, enabling the athlete to receive feedback.

[0012] An "underwater visual device" is a visual display system intended for use by users underwater, and is typically integrated into goggles or a mask. [Brief explanation of the drawing]

[0013] [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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception 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 reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] The 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.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is implemented as a system for efficiently improving the movements of swimmers. This system mainly comprises three elements: a terminal, a server, and a user.

[0035] The device has the function of capturing the movements of swimmers using cameras installed poolside. The high-resolution, high-speed cameras capture the swimmers' movements in detail and transmit the video to the server in real time.

[0036] The server receives video data transmitted from the terminal and analyzes it using AI technology. To analyze the player's form, it compares it with pre-trained data from top athletes and the player's own past data to identify movement habits and areas requiring improvement. It evaluates the player's performance and generates customized coaching content based on the results. This generated coaching content includes specific advice such as "stroke faster."

[0037] The generated instructional content is formatted by the server as AR content optimized for underwater use and sent to the device. The device displays this data on the user's swimming goggles. The user can visually check the instructional content in real time while swimming and adjust their form on the spot. For example, if the instruction is to "lower the stroke angle by 5 degrees," the user can immediately adjust accordingly.

[0038] This system provides support for athletes to improve their skills efficiently and effectively. While world-class coaches are not always present, this system allows athletes to improve themselves in real time and receive support for optimal training.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The device uses cameras installed poolside to capture high-definition footage of swimmers' movements. The captured video is encoded into a format that can be processed in real time.

[0042] Step 2:

[0043] The terminal transmits encoded video data to the server over the network. To maintain real-time performance, a high-speed and secure communication method is used.

[0044] Step 3:

[0045] The server receives video data transmitted from the terminal and performs decoding. To analyze this decoded data, an AI model is deployed to extract joint points from the athlete's movements.

[0046] Step 4:

[0047] The server analyzes the athlete's form and movement patterns based on extracted joint points. This includes an evaluation process that references data from top athletes and the athlete's past performance data to identify movement habits and areas for improvement.

[0048] Step 5:

[0049] Based on the analysis results from step 4, the server generates specific guidance in real time that indicates areas for improvement. This guidance is prepared in the form of specific operational instructions and suggestions for form modifications.

[0050] Step 6:

[0051] The server formats the generated instructional content as AR content and converts it into a display format that takes into account visibility underwater. The converted data is then ready to be sent to the device.

[0052] Step 7:

[0053] The device displays AR data received from the server onto the underwater goggles. Instructions are displayed on the goggles' screen for easy user visibility.

[0054] Step 8:

[0055] Users can view instructions displayed on their underwater goggles in real time and adjust their form and movements based on those instructions. For example, they might adjust the timing and angle of their strokes according to the displayed advice.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] For swimmers to efficiently and effectively improve their technique, they need to receive real-time feedback on their form. However, traditional methods require coaches to directly observe and provide feedback, which is subject to time and personnel constraints. Furthermore, providing detailed, real-time motion analysis and specific instructional content has only been possible under limited conditions.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes data analysis means, information generation means, and signal output means. This overcomes conventional limitations, making it possible to analyze video data captured by a terminal installed poolside by a swimmer in real time and immediately display specific feedback for improving form on an underwater visual device.

[0061] "Image acquisition means" refers to a device or system that has the function of capturing high-resolution images of a swimmer's movements.

[0062] "Information receiving means" refers to a device or system for receiving data transmitted from image acquisition means.

[0063] "Data analysis means" refers to a device or system that has the function of evaluating a player's form and movements based on received motion data and comparing it with past data of top players or individual players.

[0064] "Information generation means" refers to a device or system that generates specific coaching content for athletes based on the results of data analysis.

[0065] "Format conversion means" refers to a device or system that has the function of converting the generated instructional content into a data format that can be displayed on a visual device.

[0066] "Signal output means" refers to a device or system that has the function of transmitting the converted data to an underwater visual device and providing feedback to the athlete.

[0067] A "feedback provision method" is a device or system that provides visual instruction to enable swimmers to adjust their form in real time.

[0068] This invention is a real-time analysis and feedback system aimed at improving the technique of swimmers. The system consists of three elements: a terminal, a server, and a user.

[0069] The terminal is installed poolside and is equipped with a high-definition, high-speed camera. This camera has the ability to capture the athletes' movements in detail and transmit the video data to the server in real time. For network communication, it is equipped with a powerful encoder and a low-latency communication module.

[0070] The server analyzes the received video data using AI technology to evaluate the athlete's form. The AI ​​technology used is computer vision software with deep learning implemented, which analyzes the movements by comparing them with past data of top athletes and the athlete themselves. Through this analysis, the athlete's movement habits and areas for improvement are identified, and specific coaching content is generated. The generated coaching content is converted into a format that can be displayed on underwater visual devices.

[0071] The user wears a special visual device underwater. This device displays feedback sent from a server in real time, helping the athlete adjust their form on the spot. For example, if an athlete wants to improve their crawl stroke, the server generates advice such as "lower your stroke angle by 5 degrees" and displays it on the visual device. In this way, the athlete can make the necessary adjustments immediately and efficiently improve their technique.

[0072] By utilizing a generative AI model, the system provides customized feedback to each athlete. For example, a possible prompt could be, "Analyze my crawl stroke form and generate specific advice to improve it." This allows athletes to receive training optimized to their individual needs.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The device uses a high-resolution camera to film the swimmer's movements. The camera has a frame rate of 60fps or higher, capable of capturing even the finest details of movement. The input is the swimmer's actual movements, and the output is high-definition video data. This data is compressed and then transmitted to the server in real time.

[0076] Step 2:

[0077] The server receives video data transmitted from the terminal. Upon receipt, it verifies the integrity of the data and requests retransmission if necessary. The input is compressed video data, and the output is decoded video frames. These frames are then passed to the AI ​​analysis module.

[0078] Step 3:

[0079] The server uses an AI analysis module to analyze the received video data. This analysis utilizes computer vision technology to evaluate the athlete's form. Specifically, it analyzes the frames acquired as input in three dimensions and quantifies the athlete's movements. The output is data that includes the characteristics of the movements and the evaluation results.

[0080] Step 4:

[0081] Based on the analysis results, the server uses an information generation module to generate specific instructional content. For example, it might output something like, "The stroke angle is 10 degrees larger than ideal." Here, the input is characteristic data of the motion, and the output is advice.

[0082] Step 5:

[0083] The server converts the generated instructional content into a format compatible with visual devices using a format conversion module. It is optimized as AR content, including arrows and icons, to improve visibility underwater. This process uses advice data as input and produces AR format data as output.

[0084] Step 6:

[0085] The device transmits this converted data to an underwater visual device worn by the swimmer. The input is AR format data, and the output is visual information displayed on the underwater goggles. The user can then review this and adjust their form in real time.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] For many swimmers and health-conscious users, there is a challenge in receiving real-time performance evaluations and personalized feedback and exercise plans. This makes effective self-improvement and goal achievement difficult.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for analyzing received video data and evaluating the athlete's movements in real time, means for generating instruction content for the athlete based on the evaluation results, and means for adjusting the exercise plan based on the user's goals. This allows the user to receive real-time feedback on movement improvements and easily adjust the individually optimized exercise plan.

[0091] The term "swimmer" refers to someone who engages in exercise or competitive activities in a swimming pool.

[0092] "Means of recording" refers to devices or groups of devices used to record the actions of a subject as video footage.

[0093] "Receiving means" refers to the device or method for acquiring captured video data.

[0094] "Evaluation means" refers to processes and devices used to analyze acquired data and evaluate performance.

[0095] "Generation means" refers to the process or device for generating instructional content based on evaluation results.

[0096] "Conversion means" refers to the process or device used to convert the generated instructional content into data for display.

[0097] "Output means" refers to the process or device used to output the converted data to a visual device.

[0098] A "visual device" refers to a device that provides display data to the user visually.

[0099] A "user terminal" refers to a portable device used to receive feedback and information.

[0100] "Adjustment means" refers to a device or method for adjusting an exercise plan based on the user's goals.

[0101] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server has the function of receiving swimmer motion data acquired poolside by a camera in real time and analyzing that data. For the analysis, a generative AI model using TENSORFLOW® is used, and highly accurate motion evaluation is achieved by comparing it with past data. This evaluation result is generated as individual instruction content for the swimmer, and the generated instruction content is converted into display data by a conversion means.

[0102] The device has the function of outputting the converted data to an underwater visual device. Specifically, it processes the data as AR (augmented reality) content using Unity and displays the information on the underwater goggles used by swimmers. The user can then see the visual feedback on the spot.

[0103] Users can further provide feedback to the server based on their goals, and the server adjusts the exercise plan based on that information. This automatic adjustment recommends specific steps to help the user reach their set goals.

[0104] For example, if a swimmer aiming for a swimming competition uses this system, the server can provide real-time feedback by using a prompt message such as, "Based on the following input data, generate specific advice to improve the user's swimming technique. The data includes the user's current swimming form, which can be compared to the previous swimming technique analysis results."

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The server receives real-time video data of swimmers from cameras installed poolside. The input is high-definition video data, which is temporarily stored internally on the server as output. During this process, the video data is digitally compressed and placed on appropriate storage.

[0108] Step 2:

[0109] The server inputs the received video data into a generative AI model (using TensorFlow) for analysis. The input is video data frames, and the output is the motion analysis result. In this process, past data is referenced to evaluate the players' movements and identify specific points for motion improvement.

[0110] Step 3:

[0111] The server generates instruction content based on the analysis results. The input data is the motion analysis results, and the output is text data containing the instruction content. In this step, a pre-configured AI model uses the "generating AI model and prompt sentences" to create specific improvement instructions.

[0112] Step 4:

[0113] The server converts the generated instructional content into display data. Unity is used for this conversion, reorganizing the instructional content into an easy-to-view AR format. The input is the instructional content data, and the output is the display data.

[0114] Step 5:

[0115] The terminal outputs display data to the underwater visual device. It receives display data as input and outputs real-time feedback to the visual device. The display is adjusted so that the user can clearly see it even underwater.

[0116] Step 6:

[0117] The user adjusts their movements while reviewing the feedback. The input is visual feedback, and the output is expected to be actual improvements in form and movement. At this stage, the user works on practicing in pursuit of a more efficient swimming form.

[0118] Step 7:

[0119] Users can send additional information to the server via their device based on the feedback they receive from their exercises. The input is user feedback data, and the output is an updated exercise plan.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention is implemented as a swimming training system that incorporates an emotion engine. This system consists of three components: a terminal, a server, and a user.

[0122] The device has a camera installed poolside that captures swimmers' movements in high definition. Furthermore, it captures the user's facial expressions and transmits the video data to a server in real time. This allows for simultaneous monitoring of the swimmer's movements and emotional state.

[0123] The server receives video data from the terminal and uses AI technology to analyze the athlete's form. This analysis includes comparisons with data from top athletes and past performance data. Furthermore, the server uses an emotion engine to analyze the user's facial expression data and identify their emotional state at that moment. This emotional information is used to understand how the athlete is feeling during training and to reflect this in the feedback provided.

[0124] The generation method designs optimal coaching content for the player based on the analyzed form and emotional state. This coaching content takes into account the player's technical characteristics and current emotional state; for example, if the player is feeling frustrated, the coaching content can be adjusted to improve their motivation.

[0125] The conversion mechanism formats and presents the generated instructional content as AR content suitable for underwater visual devices. The modified instructional content and feedback are designed to minimize user burden and are provided in a format specifically tailored for underwater use.

[0126] The device displays this converted data on the swimming goggles. The user can then check the instructions in real time through the goggles and immediately adjust their form. For example, the server can instruct, "Try widening the angle of your arms even more," while the emotion engine simultaneously displays an encouraging message, "Keep it up!" In this way, the user is supported from both a technical and emotional perspective, promoting more efficient form improvement.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The device is a camera installed poolside that simultaneously captures the swimmers' movements and facial expressions in high definition. This video data is encoded and transmitted to a server in real time.

[0130] Step 2:

[0131] The server receives the video data transmitted from the terminal and performs decoding. The decoded video data is then prepared for analysis.

[0132] Step 3:

[0133] The server uses an AI model to analyze the athlete's form from video footage. Simultaneously, an emotion engine analyzes facial expression data to recognize the user's emotional state. This recognition result is then added to the real-time performance evaluation.

[0134] Step 4:

[0135] The server generates coaching content to provide to the player based on the analysis of their behavior and emotions. For example, if a player is feeling anxious, the server generates coaching content that includes encouraging messages.

[0136] Step 5:

[0137] The server formats the generated instructional content as AR content and converts it into a format suitable for underwater visual devices. This format is designed to be intuitive and low-intensity, with visibility in mind.

[0138] Step 6:

[0139] The device receives AR data transmitted from the server and displays the instructional content on the user's underwater goggles. The displayed content is optimized for improving underwater performance.

[0140] Step 7:

[0141] Users visually confirm the instructions displayed on their swimming goggles and adjust their movements accordingly. For example, if the analysis results and emotional feedback instruct them to "relax more," the user can improve their movements based on that instruction.

[0142] (Example 2)

[0143] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0144] For athletes to efficiently improve their skills in the water, real-time, appropriate feedback is crucial. However, conventional systems have difficulty providing feedback that considers not only technical movements but also the athlete's emotional state, and there is a lack of established methods for effectively presenting feedback in an underwater environment.

[0145] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0146] In this invention, the server includes a shooting means for capturing the actions of an athlete, an evaluation means for analyzing the received video data and evaluating the athlete's movements and emotional state in real time, and a conversion means for converting the generated instruction content into display data that can be viewed even underwater. This enables the provision of real-time feedback that simultaneously considers technical characteristics and emotional state, allowing for efficient form improvement.

[0147] A "participant" refers to an individual who engages in exercise, and is the subject of analysis for movements during sports such as swimming.

[0148] "Recording means" refers to devices or groups of devices used to record the movements of a person, and includes high-resolution devices such as cameras.

[0149] "Receiving means" refers to a device or system that has the function of incorporating video data collected by the shooting means into the system.

[0150] "Evaluation means" refers to technologies and devices used to analyze received data and measure and evaluate the movements and emotional state of an athlete.

[0151] "Generative means" refers to devices or algorithms that design and generate instructional content and feedback suitable for the athlete based on evaluated information.

[0152] "Conversion means" refers to technologies and systems for formatting the generated instructional content into a display format suitable for the underwater environment.

[0153] "Output means" refers to devices or methods used to provide the converted data to the person performing the action, and includes underwater visual devices, etc.

[0154] This invention is a system designed to support the improvement of athletes' skills, and is particularly intended for use in water. The system mainly consists of a terminal, a server, and a user.

[0155] The device uses a high-performance camera installed poolside to capture the movements of athletes in real time. This camera can acquire high-resolution image data, capturing the detailed movements of the athletes. In addition, it simultaneously captures information about the user's facial expressions and emotions and transmits it to the server. This process collects data that allows for an understanding of both the athletes' technical skills and emotions.

[0156] The server analyzes the received video data. This analysis utilizes AI technology and generative AI models. First, the server identifies the position of the skeleton and joints from the athlete's movements and performs a technical evaluation by comparing it with past data and the performance of top athletes. It also uses an emotion engine to analyze the athlete's psychological state from their facial expressions to understand how they are feeling. This enables technical instruction and emotionally responsive feedback.

[0157] Based on the analysis results, the server generates optimal instruction for the exerciser. This instruction includes not only technical guidance but also messages to boost motivation. For example, it generates feedback that simultaneously considers technical advice such as "Try widening the angle of your arms even more" and emotional encouragement such as "Keep it up!"

[0158] The generated instructional content is converted into a format that can be viewed by underwater visual devices. The terminal outputs this converted data to visual devices such as underwater goggles. This allows users to receive real-time feedback through the goggles and immediately adjust their form and mental state.

[0159] The fundamental principle of this system is to maximize training effectiveness by supporting the technical improvement of athletes while simultaneously providing mental support.

[0160] As an example of a prompt, the server receives the command, "Generate appropriate coaching content based on the player's form data and emotional state." This prompts the AI ​​model to automatically generate training feedback.

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The terminal uses a high-performance camera positioned poolside to capture the movements of athletes and the user's facial expressions. This capture process continuously collects high-resolution images every second. The camera accurately captures the athlete's body movements and facial expressions, recording them as digital data. The input is the athlete's movements and facial expressions, and the output is the captured video data. The captured data is immediately compressed and transferred to the server.

[0164] Step 2:

[0165] The server receives video data transmitted from the terminal and begins analysis using AI technology. First, it uses an image recognition algorithm to identify the position of the person's skeleton and joints. Next, based on this data, it performs a technical evaluation by comparing it with past databases and exemplary performances. This process quantifies the quality of the movement. The input is video data, and the output is technical evaluation data of the person performing the movement.

[0166] Step 3:

[0167] The server analyzes the received facial expression data using an emotion engine to determine the emotional state of the person performing the action. This analysis determines what emotions the person is experiencing based on features extracted from their facial expressions. For example, emotions such as smiling, concentration, and frustration can be identified. The input is facial expression data, and the output is the result of the emotion analysis.

[0168] Step 4:

[0169] The server generates instruction tailored to the athlete based on technical evaluation data and sentiment analysis results. Using a generative AI model, it automatically creates feedback that considers both technical and emotional aspects. For example, it can simultaneously generate technical instruction such as "Try widening the angle of your arms even more" and emotional encouragement such as "Keep it up!" The input is technical evaluation data and sentiment analysis results, and the output is instruction content.

[0170] Step 5:

[0171] The server converts the generated instructional content into underwater AR content and sends it to the device. This conversion process adjusts the information displayed on the visual device to a format easily recognizable underwater. The input is the instructional content, and the output is data for the visual device.

[0172] Step 6:

[0173] The device displays data converted into underwater goggles. Users receive real-time feedback through the goggles, allowing them to adjust their actions immediately. Specifically, they can correct their form or maintain their mental focus by looking at instructional messages displayed in front of them. The input is data for the visual device, and the output is feedback displayed on the goggles.

[0174] (Application Example 2)

[0175] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0176] In modern times, there are challenges in providing individualized instruction and maintaining motivation during home-based exercise and fitness activities. In particular, users find it difficult to properly observe their own form, and maintaining motivation during monotonous training is challenging. Therefore, there is a need to develop a system that provides users with appropriate technical guidance and psychological support in real time.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording the movements of an athlete, means for receiving the recorded movement video, means for analyzing the received video data and evaluating the athlete's movements and emotional state in real time, means for generating instruction content and motivational messages based on the evaluation results, means for converting the generated instruction content and messages into display data, and means for outputting the converted data to a visual device. This makes it possible to provide individualized instruction and psychological support to the athlete and improve the effectiveness of home training.

[0178] A "participant" refers to an individual who engages in exercise or fitness activities, and their movements and emotional state are the subjects of analysis.

[0179] "Recording means" refers to devices or technologies that capture or sense a person's movements and save them as digital data.

[0180] "Receiving means" refers to a function that transfers recorded operational data to a server and receives it in a format usable for analysis.

[0181] "Evaluation means" refers to a series of processes and systems for analyzing the movements of an athlete based on received video data and determining their form and emotional state.

[0182] "Generative means" refers to the function of creating appropriate instructional content and psychological motivational messages for athletes based on the results obtained from evaluation means.

[0183] "Conversion means" refers to processes and techniques that adjust the format in order to correctly display the generated instructional content and messages on a visual device.

[0184] "Output means" refers to a mechanism for transmitting data to a visual device in order to provide the converted instructional content and message to the exerciser.

[0185] The system implementing this invention analyzes the movements and emotional state of an exerciser in a home fitness environment in real time and provides personalized feedback. The system mainly consists of three components: a server, a terminal, and a user.

[0186] The server features an AI analysis engine based on Python, utilizing TensorFlow and PyTorch. The receiving device analyzes motion data transferred from the terminal in real time, evaluating the exerciser's form and emotional state. Based on the analysis results, the evaluation device generates exerciser-specific instruction content and motivational messages. The generated content is then converted using Unity by the conversion device into a data format displayable on visual devices.

[0187] The device uses cameras and sensors built into the home fitness robot to record the user's movements. The recorded data is transmitted to a server via a receiving device.

[0188] Users receive real-time feedback through visual devices. This allows users to immediately identify areas for improvement in their movements and enhance the effectiveness of their exercise. For example, when a user is doing yoga, the device might instruct them to "straighten your spine a little more," while an emotion engine on the server displays a real-time encouraging message such as "relax and continue to breathe deeply."

[0189] Examples of prompts to input into a generative AI model:

[0190] “You are designing a real-time feedback system for a home fitness robot. The system uses cameras to analyze user movements and emotions during exercise, and offers personalized guidance and motivational messages through AR goggles. Describe how you would implement such a system.”

[0191] In this way, by supporting exercisers from both technical and psychological perspectives, the home fitness experience can be made more effective and satisfying.

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The device records the movements of the person exercising using a camera. The input is video of the person's movements, and the recorded data is transmitted to the server in real time via a receiving device. The output is movement data in digital format.

[0195] Step 2:

[0196] The server inputs the received motion data into the AI ​​analysis engine. The input is motion data sent from the terminal, and the AI ​​technology is used to analyze the form and emotional state, and the results are obtained using an evaluation tool. The output is data on the athlete's form evaluation and emotional state.

[0197] Step 3:

[0198] The server uses the form evaluation and emotional state obtained from the evaluation means to generate instruction content and motivational messages for the exerciser using the generation means. The input is the evaluation result, and the output is the individualized instruction content and message. Specifically, the server uses a generation AI model to construct appropriate feedback content.

[0199] Step 4:

[0200] The server converts the generated instructional content and messages into a data format that can be displayed on AR goggles using a conversion device. The input is data from the generation device, and the output is display data suitable for visual devices. Data processing is performed using Unity.

[0201] Step 5:

[0202] Users receive instructional content and messages in real time through their visual devices. Input is display data transmitted from the server via the device, and output is visual feedback displayed on the exerciser's AR goggles. Specifically, users can adjust their form based on this feedback.

[0203] 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.

[0204] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0205] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] 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.

[0209] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0210] 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.

[0211] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0212] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0213] 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.

[0214] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0215] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0216] The 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.

[0217] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0218] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0219] This invention is implemented as a system for efficiently improving the movements of swimmers. This system mainly comprises three elements: a terminal, a server, and a user.

[0220] The device has the function of capturing the movements of swimmers using cameras installed poolside. The high-resolution, high-speed cameras capture the swimmers' movements in detail and transmit the video to the server in real time.

[0221] The server receives video data transmitted from the terminal and analyzes it using AI technology. To analyze the player's form, it compares it with pre-trained data from top athletes and the player's own past data to identify movement habits and areas requiring improvement. It evaluates the player's performance and generates customized coaching content based on the results. This generated coaching content includes specific advice such as "stroke faster."

[0222] The generated instructional content is formatted by the server as AR content optimized for underwater use and sent to the device. The device displays this data on the user's swimming goggles. The user can visually check the instructional content in real time while swimming and adjust their form on the spot. For example, if the instruction is to "lower the stroke angle by 5 degrees," the user can immediately adjust accordingly.

[0223] This system provides support for athletes to improve their skills efficiently and effectively. While world-class coaches are not always present, this system allows athletes to improve themselves in real time and receive support for optimal training.

[0224] The following describes the processing flow.

[0225] Step 1:

[0226] The device uses cameras installed poolside to capture high-definition footage of swimmers' movements. The captured video is encoded into a format that can be processed in real time.

[0227] Step 2:

[0228] The terminal transmits encoded video data to the server over the network. To maintain real-time performance, a high-speed and secure communication method is used.

[0229] Step 3:

[0230] The server receives video data transmitted from the terminal and performs decoding. To analyze this decoded data, an AI model is deployed to extract joint points from the athlete's movements.

[0231] Step 4:

[0232] The server analyzes the athlete's form and movement patterns based on extracted joint points. This includes an evaluation process that references data from top athletes and the athlete's past performance data to identify movement habits and areas for improvement.

[0233] Step 5:

[0234] Based on the analysis results from step 4, the server generates specific guidance in real time that indicates areas for improvement. This guidance is prepared in the form of specific operational instructions and suggestions for form modifications.

[0235] Step 6:

[0236] The server formats the generated instructional content as AR content and converts it into a display format that takes into account visibility underwater. The converted data is then ready to be sent to the device.

[0237] Step 7:

[0238] The device displays AR data received from the server onto the underwater goggles. Instructions are displayed on the goggles' screen for easy user visibility.

[0239] Step 8:

[0240] Users can view instructions displayed on their underwater goggles in real time and adjust their form and movements based on those instructions. For example, they might adjust the timing and angle of their strokes according to the displayed advice.

[0241] (Example 1)

[0242] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0243] For swimmers to efficiently and effectively improve their technique, they need to receive real-time feedback on their form. However, traditional methods require coaches to directly observe and provide feedback, which is subject to time and personnel constraints. Furthermore, providing detailed, real-time motion analysis and specific instructional content has only been possible under limited conditions.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes data analysis means, information generation means, and signal output means. This overcomes conventional limitations, making it possible to analyze video data captured by a terminal installed poolside by a swimmer in real time and immediately display specific feedback for improving form on an underwater visual device.

[0246] "Image acquisition means" refers to a device or system that has the function of capturing high-resolution images of a swimmer's movements.

[0247] "Information receiving means" refers to a device or system for receiving data transmitted from image acquisition means.

[0248] "Data analysis means" refers to a device or system that has the function of evaluating a player's form and movements based on received motion data and comparing it with past data of top players or individual players.

[0249] "Information generation means" refers to a device or system that generates specific coaching content for athletes based on the results of data analysis.

[0250] "Format conversion means" refers to a device or system that has the function of converting the generated instructional content into a data format that can be displayed on a visual device.

[0251] "Signal output means" refers to a device or system that has the function of transmitting the converted data to an underwater visual device and providing feedback to the athlete.

[0252] A "feedback provision method" is a device or system that provides visual instruction to enable swimmers to adjust their form in real time.

[0253] This invention is a real-time analysis and feedback system aimed at improving the technique of swimmers. The system consists of three elements: a terminal, a server, and a user.

[0254] The terminal is installed poolside and is equipped with a high-definition, high-speed camera. This camera has the ability to capture the athletes' movements in detail and transmit the video data to the server in real time. For network communication, it is equipped with a powerful encoder and a low-latency communication module.

[0255] The server analyzes the received video data using AI technology to evaluate the athlete's form. The AI ​​technology used is computer vision software with deep learning implemented, which analyzes the movements by comparing them with past data of top athletes and the athlete themselves. Through this analysis, the athlete's movement habits and areas for improvement are identified, and specific coaching content is generated. The generated coaching content is converted into a format that can be displayed on underwater visual devices.

[0256] The user wears a special visual device underwater. This device displays feedback sent from a server in real time, helping the athlete adjust their form on the spot. For example, if an athlete wants to improve their crawl stroke, the server generates advice such as "lower your stroke angle by 5 degrees" and displays it on the visual device. In this way, the athlete can make the necessary adjustments immediately and efficiently improve their technique.

[0257] By utilizing a generative AI model, the system provides customized feedback to each athlete. For example, a possible prompt could be, "Analyze my crawl stroke form and generate specific advice to improve it." This allows athletes to receive training optimized to their individual needs.

[0258] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0259] Step 1:

[0260] The device uses a high-resolution camera to film the swimmer's movements. The camera has a frame rate of 60fps or higher, capable of capturing even the finest details of movement. The input is the swimmer's actual movements, and the output is high-definition video data. This data is compressed and then transmitted to the server in real time.

[0261] Step 2:

[0262] The server receives video data transmitted from the terminal. Upon receipt, it verifies the integrity of the data and requests retransmission if necessary. The input is compressed video data, and the output is decoded video frames. These frames are then passed to the AI ​​analysis module.

[0263] Step 3:

[0264] The server uses an AI analysis module to analyze the received video data. This analysis utilizes computer vision technology to evaluate the athlete's form. Specifically, it analyzes the frames acquired as input in three dimensions and quantifies the athlete's movements. The output is data that includes the characteristics of the movements and the evaluation results.

[0265] Step 4:

[0266] Based on the analysis results, the server uses an information generation module to generate specific instructional content. For example, it might output something like, "The stroke angle is 10 degrees larger than ideal." Here, the input is characteristic data of the motion, and the output is advice.

[0267] Step 5:

[0268] The server converts the generated instructional content into a format compatible with visual devices using a format conversion module. It is optimized as AR content, including arrows and icons, to improve visibility underwater. This process uses advice data as input and produces AR format data as output.

[0269] Step 6:

[0270] The device transmits this converted data to an underwater visual device worn by the swimmer. The input is AR format data, and the output is visual information displayed on the underwater goggles. The user can then review this and adjust their form in real time.

[0271] (Application Example 1)

[0272] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] For many swimmers and health-conscious users, there is a challenge in receiving real-time performance evaluations and personalized feedback and exercise plans. This makes effective self-improvement and goal achievement difficult.

[0274] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0275] In this invention, the server includes means for analyzing received video data and evaluating the athlete's movements in real time, means for generating instruction content for the athlete based on the evaluation results, and means for adjusting the exercise plan based on the user's goals. This allows the user to receive real-time feedback on movement improvements and easily adjust the individually optimized exercise plan.

[0276] The term "swimmer" refers to someone who engages in exercise or competitive activities in a swimming pool.

[0277] "Means of recording" refers to devices or groups of devices used to record the actions of a subject as video footage.

[0278] "Receiving means" refers to the device or method for acquiring captured video data.

[0279] "Evaluation means" refers to processes and devices used to analyze acquired data and evaluate performance.

[0280] "Generation means" refers to the process or device for generating instructional content based on evaluation results.

[0281] "Conversion means" refers to the process or device used to convert the generated instructional content into data for display.

[0282] "Output means" refers to the process or device used to output the converted data to a visual device.

[0283] The "visual device" refers to a device for visually providing display data to the user.

[0284] The "user terminal" refers to a portable device for receiving feedback and information.

[0285] The "adjustment means" refers to a device or method for adjusting an exercise plan based on the user's goals.

[0286] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server has the function of receiving in real time the motion data of a swimmer obtained on the poolside by the photographing means and analyzing the data. For the analysis, a generative AI model using TensorFlow is used, and a highly accurate motion evaluation is realized by comparing with past data. This evaluation result is generated as individual guidance content for the athlete, and the generated guidance content is converted into display data by the conversion means.

[0287] The terminal has the function of outputting the converted data to an underwater visual device. Specifically, the data is processed as AR (augmented reality) content using Unity, and information is displayed on the underwater goggles used by the swimmer. Then, the user can confirm the visual feedback on the spot.

[0288] The user can further provide feedback to the server based on their own goals, and the server adjusts the exercise plan based on that information. This automatic adjustment recommends specific steps towards the goal set by the user.

[0289] For example, when a swimmer aiming for a swimming competition uses this system, the server can use a prompt sentence such as "Based on the following input data, please generate specific advice for improving the user's swimming style. The data includes the current swimming form that can be compared with the previous swimming style analysis results." to provide real-time feedback.

[0290] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0291] Step 1:

[0292] The server receives real-time video data of swimmers from cameras installed poolside. The input is high-definition video data, which is temporarily stored internally on the server as output. During this process, the video data is digitally compressed and placed on appropriate storage.

[0293] Step 2:

[0294] The server inputs the received video data into a generative AI model (using TensorFlow) for analysis. The input is video data frames, and the output is the motion analysis result. In this process, past data is referenced to evaluate the players' movements and identify specific points for motion improvement.

[0295] Step 3:

[0296] The server generates instruction content based on the analysis results. The input data is the motion analysis results, and the output is text data containing the instruction content. In this step, a pre-configured AI model uses the "generating AI model and prompt sentences" to create specific improvement instructions.

[0297] Step 4:

[0298] The server converts the generated instructional content into display data. Unity is used for this conversion, reorganizing the instructional content into an easy-to-view AR format. The input is the instructional content data, and the output is the display data.

[0299] Step 5:

[0300] The terminal outputs display data to the underwater vision device. The input received is the display data, and the output is real-time feedback to the vision device. The display is adjusted so that the user can clearly confirm it even underwater.

[0301] Step 6:

[0302] The user actually adjusts the movement while checking the feedback. The input is visual feedback, and as output, improvements in form or actual movement are expected. At this stage, the user pursues a more efficient swimming form and engages in practice.

[0303] Step 7:

[0304] Based on the executed feedback, the user can send additional information to the server via the terminal. The input is the feedback data from the user, and as output, an updated exercise plan is provided.

[0305] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0306] The present invention is implemented as a swimming training system combined with an emotion engine. This system is composed of a terminal, a server, and a user.

[0307] The terminal has a function of shooting the movements of a swimmer with high quality using a camera installed on the pool side. Furthermore, it shoots the user's expression and transmits the video data to the server in real time. Thereby, the movements and emotional states of the swimmer can be grasped simultaneously.

[0308] The server receives video data from the terminal and uses AI technology to analyze the athlete's form. This analysis includes comparisons with data from top athletes and past performance data. Furthermore, the server uses an emotion engine to analyze the user's facial expression data and identify their emotional state at that moment. This emotional information is used to understand how the athlete is feeling during training and to reflect this in the feedback provided.

[0309] The generation method designs optimal coaching content for the player based on the analyzed form and emotional state. This coaching content takes into account the player's technical characteristics and current emotional state; for example, if the player is feeling frustrated, the coaching content can be adjusted to improve their motivation.

[0310] The conversion mechanism formats and presents the generated instructional content as AR content suitable for underwater visual devices. The modified instructional content and feedback are designed to minimize user burden and are provided in a format specifically tailored for underwater use.

[0311] The device displays this converted data on the swimming goggles. The user can then check the instructions in real time through the goggles and immediately adjust their form. For example, the server can instruct, "Try widening the angle of your arms even more," while the emotion engine simultaneously displays an encouraging message, "Keep it up!" In this way, the user is supported from both a technical and emotional perspective, promoting more efficient form improvement.

[0312] The following describes the processing flow.

[0313] Step 1:

[0314] The device is a camera installed poolside that simultaneously captures the swimmers' movements and facial expressions in high definition. This video data is encoded and transmitted to a server in real time.

[0315] Step 2:

[0316] The server receives the video data transmitted from the terminal and performs decoding. The decoded video data is then prepared for analysis.

[0317] Step 3:

[0318] The server uses an AI model to analyze the athlete's form from video footage. Simultaneously, an emotion engine analyzes facial expression data to recognize the user's emotional state. This recognition result is then added to the real-time performance evaluation.

[0319] Step 4:

[0320] The server generates coaching content to provide to the player based on the analysis of their behavior and emotions. For example, if a player is feeling anxious, the server generates coaching content that includes encouraging messages.

[0321] Step 5:

[0322] The server formats the generated instructional content as AR content and converts it into a format suitable for underwater visual devices. This format is designed to be intuitive and low-intensity, with visibility in mind.

[0323] Step 6:

[0324] The device receives AR data transmitted from the server and displays the instructional content on the user's underwater goggles. The displayed content is optimized for improving underwater performance.

[0325] Step 7:

[0326] Users visually confirm the instructions displayed on their swimming goggles and adjust their movements accordingly. For example, if the analysis results and emotional feedback instruct them to "relax more," the user can improve their movements based on that instruction.

[0327] (Example 2)

[0328] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0329] For athletes to efficiently improve their skills in the water, real-time, appropriate feedback is crucial. However, conventional systems have difficulty providing feedback that considers not only technical movements but also the athlete's emotional state, and there is a lack of established methods for effectively presenting feedback in an underwater environment.

[0330] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0331] In this invention, the server includes a shooting means for capturing the actions of an athlete, an evaluation means for analyzing the received video data and evaluating the athlete's movements and emotional state in real time, and a conversion means for converting the generated instruction content into display data that can be viewed even underwater. This enables the provision of real-time feedback that simultaneously considers technical characteristics and emotional state, allowing for efficient form improvement.

[0332] A "participant" refers to an individual who engages in exercise, and is the subject of analysis for movements during sports such as swimming.

[0333] "Recording means" refers to devices or groups of devices used to record the movements of a person, and includes high-resolution devices such as cameras.

[0334] "Receiving means" refers to a device or system that has the function of incorporating video data collected by the shooting means into the system.

[0335] "Evaluation means" refers to technologies and devices used to analyze received data and measure and evaluate the movements and emotional state of an athlete.

[0336] "Generative means" refers to devices or algorithms that design and generate instructional content and feedback suitable for the athlete based on evaluated information.

[0337] "Conversion means" refers to technologies and systems for formatting the generated instructional content into a display format suitable for the underwater environment.

[0338] "Output means" refers to devices or methods used to provide the converted data to the person performing the action, and includes underwater visual devices, etc.

[0339] This invention is a system designed to support the improvement of athletes' skills, and is particularly intended for use in water. The system mainly consists of a terminal, a server, and a user.

[0340] The device uses a high-performance camera installed poolside to capture the movements of athletes in real time. This camera can acquire high-resolution image data, capturing the detailed movements of the athletes. In addition, it simultaneously captures information about the user's facial expressions and emotions and transmits it to the server. This process collects data that allows for an understanding of both the athletes' technical skills and emotions.

[0341] The server analyzes the received video data. This analysis utilizes AI technology and generative AI models. First, the server identifies the position of the skeleton and joints from the athlete's movements and performs a technical evaluation by comparing it with past data and the performance of top athletes. It also uses an emotion engine to analyze the athlete's psychological state from their facial expressions to understand how they are feeling. This enables technical instruction and emotionally responsive feedback.

[0342] Based on the analysis results, the server generates optimal instruction for the exerciser. This instruction includes not only technical guidance but also messages to boost motivation. For example, it generates feedback that simultaneously considers technical advice such as "Try widening the angle of your arms even more" and emotional encouragement such as "Keep it up!"

[0343] The generated instructional content is converted into a format that can be viewed by underwater visual devices. The terminal outputs this converted data to visual devices such as underwater goggles. This allows users to receive real-time feedback through the goggles and immediately adjust their form and mental state.

[0344] The fundamental principle of this system is to maximize training effectiveness by supporting the technical improvement of athletes while simultaneously providing mental support.

[0345] As an example of a prompt, the server receives the command, "Generate appropriate coaching content based on the player's form data and emotional state." This prompts the AI ​​model to automatically generate training feedback.

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] The terminal uses a high-performance camera positioned poolside to capture the movements of athletes and the user's facial expressions. This capture process continuously collects high-resolution images every second. The camera accurately captures the athlete's body movements and facial expressions, recording them as digital data. The input is the athlete's movements and facial expressions, and the output is the captured video data. The captured data is immediately compressed and transferred to the server.

[0349] Step 2:

[0350] The server receives video data transmitted from the terminal and begins analysis using AI technology. First, it uses an image recognition algorithm to identify the position of the person's skeleton and joints. Next, based on this data, it performs a technical evaluation by comparing it with past databases and exemplary performances. This process quantifies the quality of the movement. The input is video data, and the output is technical evaluation data of the person performing the movement.

[0351] Step 3:

[0352] The server analyzes the received facial expression data using an emotion engine to determine the emotional state of the person performing the action. This analysis determines what emotions the person is experiencing based on features extracted from their facial expressions. For example, emotions such as smiling, concentration, and frustration can be identified. The input is facial expression data, and the output is the result of the emotion analysis.

[0353] Step 4:

[0354] The server generates instruction tailored to the athlete based on technical evaluation data and sentiment analysis results. Using a generative AI model, it automatically creates feedback that considers both technical and emotional aspects. For example, it can simultaneously generate technical instruction such as "Try widening the angle of your arms even more" and emotional encouragement such as "Keep it up!" The input is technical evaluation data and sentiment analysis results, and the output is instruction content.

[0355] Step 5:

[0356] The server converts the generated instructional content into underwater AR content and sends it to the device. This conversion process adjusts the information displayed on the visual device to a format easily recognizable underwater. The input is the instructional content, and the output is data for the visual device.

[0357] Step 6:

[0358] The device displays data converted into underwater goggles. Users receive real-time feedback through the goggles, allowing them to adjust their actions immediately. Specifically, they can correct their form or maintain their mental focus by looking at instructional messages displayed in front of them. The input is data for the visual device, and the output is feedback displayed on the goggles.

[0359] (Application Example 2)

[0360] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0361] In modern times, there are challenges in providing individualized instruction and maintaining motivation during home-based exercise and fitness activities. In particular, users find it difficult to properly observe their own form, and maintaining motivation during monotonous training is challenging. Therefore, there is a need to develop a system that provides users with appropriate technical guidance and psychological support in real time.

[0362] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording the movements of an athlete, means for receiving the recorded movement video, means for analyzing the received video data and evaluating the athlete's movements and emotional state in real time, means for generating instruction content and motivational messages based on the evaluation results, means for converting the generated instruction content and messages into display data, and means for outputting the converted data to a visual device. This makes it possible to provide individualized instruction and psychological support to the athlete and improve the effectiveness of home training.

[0363] A "participant" refers to an individual who engages in exercise or fitness activities, and their movements and emotional state are the subjects of analysis.

[0364] "Recording means" refers to devices or technologies that capture or sense a person's movements and save them as digital data.

[0365] "Receiving means" refers to a function that transfers recorded operational data to a server and receives it in a format usable for analysis.

[0366] "Evaluation means" refers to a series of processes and systems for analyzing the movements of an athlete based on received video data and determining their form and emotional state.

[0367] "Generative means" refers to the function of creating appropriate instructional content and psychological motivational messages for athletes based on the results obtained from evaluation means.

[0368] "Conversion means" refers to processes and techniques that adjust the format in order to correctly display the generated instructional content and messages on a visual device.

[0369] "Output means" refers to a mechanism for transmitting data to a visual device in order to provide the converted instructional content and message to the exerciser.

[0370] The system implementing this invention analyzes the movements and emotional state of an exerciser in a home fitness environment in real time and provides personalized feedback. The system mainly consists of three components: a server, a terminal, and a user.

[0371] The server features an AI analysis engine based on Python, utilizing TensorFlow and PyTorch. The receiving device analyzes motion data transferred from the terminal in real time, evaluating the exerciser's form and emotional state. Based on the analysis results, the evaluation device generates exerciser-specific instruction content and motivational messages. The generated content is then converted using Unity by the conversion device into a data format displayable on visual devices.

[0372] The device uses cameras and sensors built into the home fitness robot to record the user's movements. The recorded data is transmitted to a server via a receiving device.

[0373] Users receive real-time feedback through visual devices. This allows users to immediately identify areas for improvement in their movements and enhance the effectiveness of their exercise. For example, when a user is doing yoga, the device might instruct them to "straighten your spine a little more," while an emotion engine on the server displays a real-time encouraging message such as "relax and continue to breathe deeply."

[0374] Examples of prompts to input into a generative AI model:

[0375] “You are designing a real-time feedback system for a home fitness robot. The system uses cameras to analyze user movements and emotions during exercise, and offers personalized guidance and motivational messages through AR goggles. Describe how you would implement such a system.”

[0376] In this way, by supporting exercisers from both technical and psychological perspectives, the home fitness experience can be made more effective and satisfying.

[0377] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0378] Step 1:

[0379] The device records the movements of the person exercising using a camera. The input is video of the person's movements, and the recorded data is transmitted to the server in real time via a receiving device. The output is movement data in digital format.

[0380] Step 2:

[0381] The server inputs the received motion data into the AI ​​analysis engine. The input is motion data sent from the terminal, and the AI ​​technology is used to analyze the form and emotional state, and the results are obtained using an evaluation tool. The output is data on the athlete's form evaluation and emotional state.

[0382] Step 3:

[0383] The server uses the form evaluation and emotional state obtained from the evaluation means to generate instruction content and motivational messages for the exerciser using the generation means. The input is the evaluation result, and the output is the individualized instruction content and message. Specifically, the server uses a generation AI model to construct appropriate feedback content.

[0384] Step 4:

[0385] The server converts the generated instructional content and messages into a data format that can be displayed on AR goggles using a conversion device. The input is data from the generation device, and the output is display data suitable for visual devices. Data processing is performed using Unity.

[0386] Step 5:

[0387] Users receive instructional content and messages in real time through their visual devices. Input is display data transmitted from the server via the device, and output is visual feedback displayed on the exerciser's AR goggles. Specifically, users can adjust their form based on this feedback.

[0388] 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.

[0389] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0390] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0391] [Third Embodiment]

[0392] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0393] 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.

[0394] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0395] 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.

[0396] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0397] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0398] 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.

[0399] 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.

[0400] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0401] The 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.

[0402] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0403] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0404] This invention is implemented as a system for efficiently improving the movements of swimmers. This system mainly comprises three elements: a terminal, a server, and a user.

[0405] The device has the function of capturing the movements of swimmers using cameras installed poolside. The high-resolution, high-speed cameras capture the swimmers' movements in detail and transmit the video to the server in real time.

[0406] The server receives video data transmitted from the terminal and analyzes it using AI technology. To analyze the player's form, it compares it with pre-trained data from top athletes and the player's own past data to identify movement habits and areas requiring improvement. It evaluates the player's performance and generates customized coaching content based on the results. This generated coaching content includes specific advice such as "stroke faster."

[0407] The generated instructional content is formatted by the server as AR content optimized for underwater use and sent to the device. The device displays this data on the user's swimming goggles. The user can visually check the instructional content in real time while swimming and adjust their form on the spot. For example, if the instruction is to "lower the stroke angle by 5 degrees," the user can immediately adjust accordingly.

[0408] This system provides support for athletes to improve their skills efficiently and effectively. While world-class coaches are not always present, this system allows athletes to improve themselves in real time and receive support for optimal training.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The device uses cameras installed poolside to capture high-definition footage of swimmers' movements. The captured video is encoded into a format that can be processed in real time.

[0412] Step 2:

[0413] The terminal transmits encoded video data to the server over the network. To maintain real-time performance, a high-speed and secure communication method is used.

[0414] Step 3:

[0415] The server receives video data transmitted from the terminal and performs decoding. To analyze this decoded data, an AI model is deployed to extract joint points from the athlete's movements.

[0416] Step 4:

[0417] The server analyzes the athlete's form and movement patterns based on extracted joint points. This includes an evaluation process that references data from top athletes and the athlete's past performance data to identify movement habits and areas for improvement.

[0418] Step 5:

[0419] Based on the analysis results from step 4, the server generates specific guidance in real time that indicates areas for improvement. This guidance is prepared in the form of specific operational instructions and suggestions for form modifications.

[0420] Step 6:

[0421] The server formats the generated instructional content as AR content and converts it into a display format that takes into account visibility underwater. The converted data is then ready to be sent to the device.

[0422] Step 7:

[0423] The device displays AR data received from the server onto the underwater goggles. Instructions are displayed on the goggles' screen for easy user visibility.

[0424] Step 8:

[0425] Users can view instructions displayed on their underwater goggles in real time and adjust their form and movements based on those instructions. For example, they might adjust the timing and angle of their strokes according to the displayed advice.

[0426] (Example 1)

[0427] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0428] For swimmers to efficiently and effectively improve their technique, they need to receive real-time feedback on their form. However, traditional methods require coaches to directly observe and provide feedback, which is subject to time and personnel constraints. Furthermore, providing detailed, real-time motion analysis and specific instructional content has only been possible under limited conditions.

[0429] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0430] In this invention, the server includes data analysis means, information generation means, and signal output means. This overcomes conventional limitations, making it possible to analyze video data captured by a terminal installed poolside by a swimmer in real time and immediately display specific feedback for improving form on an underwater visual device.

[0431] "Image acquisition means" refers to a device or system that has the function of capturing high-resolution images of a swimmer's movements.

[0432] "Information receiving means" refers to a device or system for receiving data transmitted from image acquisition means.

[0433] "Data analysis means" refers to a device or system that has the function of evaluating a player's form and movements based on received motion data and comparing it with past data of top players or individual players.

[0434] "Information generation means" refers to a device or system that generates specific coaching content for athletes based on the results of data analysis.

[0435] "Format conversion means" refers to a device or system that has the function of converting the generated instructional content into a data format that can be displayed on a visual device.

[0436] "Signal output means" refers to a device or system that has the function of transmitting the converted data to an underwater visual device and providing feedback to the athlete.

[0437] A "feedback provision method" is a device or system that provides visual instruction to enable swimmers to adjust their form in real time.

[0438] This invention is a real-time analysis and feedback system aimed at improving the technique of swimmers. The system consists of three elements: a terminal, a server, and a user.

[0439] The terminal is installed poolside and is equipped with a high-definition, high-speed camera. This camera has the ability to capture the athletes' movements in detail and transmit the video data to the server in real time. For network communication, it is equipped with a powerful encoder and a low-latency communication module.

[0440] The server analyzes the received video data using AI technology to evaluate the athlete's form. The AI ​​technology used is computer vision software with deep learning implemented, which analyzes the movements by comparing them with past data of top athletes and the athlete themselves. Through this analysis, the athlete's movement habits and areas for improvement are identified, and specific coaching content is generated. The generated coaching content is converted into a format that can be displayed on underwater visual devices.

[0441] The user wears a special visual device underwater. This device displays feedback sent from a server in real time, helping the athlete adjust their form on the spot. For example, if an athlete wants to improve their crawl stroke, the server generates advice such as "lower your stroke angle by 5 degrees" and displays it on the visual device. In this way, the athlete can make the necessary adjustments immediately and efficiently improve their technique.

[0442] By utilizing a generative AI model, the system provides customized feedback to each athlete. For example, a possible prompt could be, "Analyze my crawl stroke form and generate specific advice to improve it." This allows athletes to receive training optimized to their individual needs.

[0443] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0444] Step 1:

[0445] The device uses a high-resolution camera to film the swimmer's movements. The camera has a frame rate of 60fps or higher, capable of capturing even the finest details of movement. The input is the swimmer's actual movements, and the output is high-definition video data. This data is compressed and then transmitted to the server in real time.

[0446] Step 2:

[0447] The server receives video data transmitted from the terminal. Upon receipt, it verifies the integrity of the data and requests retransmission if necessary. The input is compressed video data, and the output is decoded video frames. These frames are then passed to the AI ​​analysis module.

[0448] Step 3:

[0449] The server uses an AI analysis module to analyze the received video data. This analysis utilizes computer vision technology to evaluate the athlete's form. Specifically, it analyzes the frames acquired as input in three dimensions and quantifies the athlete's movements. The output is data that includes the characteristics of the movements and the evaluation results.

[0450] Step 4:

[0451] Based on the analysis results, the server uses an information generation module to generate specific instructional content. For example, it might output something like, "The stroke angle is 10 degrees larger than ideal." Here, the input is characteristic data of the motion, and the output is advice.

[0452] Step 5:

[0453] The server converts the generated instructional content into a format compatible with visual devices using a format conversion module. It is optimized as AR content, including arrows and icons, to improve visibility underwater. This process uses advice data as input and produces AR format data as output.

[0454] Step 6:

[0455] The device transmits this converted data to an underwater visual device worn by the swimmer. The input is AR format data, and the output is visual information displayed on the underwater goggles. The user can then review this and adjust their form in real time.

[0456] (Application Example 1)

[0457] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0458] For many swimmers and health-conscious users, there is a challenge in receiving real-time performance evaluations and personalized feedback and exercise plans. This makes effective self-improvement and goal achievement difficult.

[0459] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0460] In this invention, the server includes means for analyzing received video data and evaluating the athlete's movements in real time, means for generating instruction content for the athlete based on the evaluation results, and means for adjusting the exercise plan based on the user's goals. This allows the user to receive real-time feedback on movement improvements and easily adjust the individually optimized exercise plan.

[0461] The term "swimmer" refers to someone who engages in exercise or competitive activities in a swimming pool.

[0462] "Means of recording" refers to devices or groups of devices used to record the actions of a subject as video footage.

[0463] "Receiving means" refers to the device or method for acquiring captured video data.

[0464] "Evaluation means" refers to processes and devices used to analyze acquired data and evaluate performance.

[0465] "Generation means" refers to the process or device for generating instructional content based on evaluation results.

[0466] "Conversion means" refers to the process or device used to convert the generated instructional content into data for display.

[0467] "Output means" refers to the process or device used to output the converted data to a visual device.

[0468] A "visual device" refers to a device that provides display data to the user visually.

[0469] A "user terminal" refers to a portable device used to receive feedback and information.

[0470] "Adjustment means" refers to a device or method for adjusting an exercise plan based on the user's goals.

[0471] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server has the function of receiving swimmer motion data acquired at the poolside by a camera in real time and analyzing that data. For the analysis, a generative AI model using TensorFlow is used, and highly accurate motion evaluation is achieved by comparing it with past data. This evaluation result is generated as individual instruction content for the swimmer, and the generated instruction content is converted into display data by a conversion means.

[0472] The device has the function of outputting the converted data to an underwater visual device. Specifically, it processes the data as AR (augmented reality) content using Unity and displays the information on the underwater goggles used by swimmers. The user can then see the visual feedback on the spot.

[0473] Users can further provide feedback to the server based on their goals, and the server adjusts the exercise plan based on that information. This automatic adjustment recommends specific steps to help the user reach their set goals.

[0474] For example, if a swimmer aiming for a swimming competition uses this system, the server can provide real-time feedback by using a prompt message such as, "Based on the following input data, generate specific advice to improve the user's swimming technique. The data includes the user's current swimming form, which can be compared to the previous swimming technique analysis results."

[0475] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0476] Step 1:

[0477] The server receives real-time video data of swimmers from cameras installed poolside. The input is high-definition video data, which is temporarily stored internally on the server as output. During this process, the video data is digitally compressed and placed on appropriate storage.

[0478] Step 2:

[0479] The server inputs the received video data into a generative AI model (using TensorFlow) for analysis. The input is video data frames, and the output is the motion analysis result. In this process, past data is referenced to evaluate the players' movements and identify specific points for motion improvement.

[0480] Step 3:

[0481] The server generates instruction content based on the analysis results. The input data is the motion analysis results, and the output is text data containing the instruction content. In this step, a pre-configured AI model uses the "generating AI model and prompt sentences" to create specific improvement instructions.

[0482] Step 4:

[0483] The server converts the generated instructional content into display data. Unity is used for this conversion, reorganizing the instructional content into an easy-to-view AR format. The input is the instructional content data, and the output is the display data.

[0484] Step 5:

[0485] The terminal outputs display data to the underwater visual device. It receives display data as input and outputs real-time feedback to the visual device. The display is adjusted so that the user can clearly see it even underwater.

[0486] Step 6:

[0487] The user adjusts their movements while reviewing the feedback. The input is visual feedback, and the output is expected to be actual improvements in form and movement. At this stage, the user works on practicing in pursuit of a more efficient swimming form.

[0488] Step 7:

[0489] Users can send additional information to the server via their device based on the feedback they receive from their exercises. The input is user feedback data, and the output is an updated exercise plan.

[0490] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0491] This invention is implemented as a swimming training system that incorporates an emotion engine. This system consists of three components: a terminal, a server, and a user.

[0492] The device has a camera installed poolside that captures swimmers' movements in high definition. Furthermore, it captures the user's facial expressions and transmits the video data to a server in real time. This allows for simultaneous monitoring of the swimmer's movements and emotional state.

[0493] The server receives video data from the terminal and uses AI technology to analyze the athlete's form. This analysis includes comparisons with data from top athletes and past performance data. Furthermore, the server uses an emotion engine to analyze the user's facial expression data and identify their emotional state at that moment. This emotional information is used to understand how the athlete is feeling during training and to reflect this in the feedback provided.

[0494] The generation method designs optimal coaching content for the player based on the analyzed form and emotional state. This coaching content takes into account the player's technical characteristics and current emotional state; for example, if the player is feeling frustrated, the coaching content can be adjusted to improve their motivation.

[0495] The conversion mechanism formats and presents the generated instructional content as AR content suitable for underwater visual devices. The modified instructional content and feedback are designed to minimize user burden and are provided in a format specifically tailored for underwater use.

[0496] The device displays this converted data on the swimming goggles. The user can then check the instructions in real time through the goggles and immediately adjust their form. For example, the server can instruct, "Try widening the angle of your arms even more," while the emotion engine simultaneously displays an encouraging message, "Keep it up!" In this way, the user is supported from both a technical and emotional perspective, promoting more efficient form improvement.

[0497] The following describes the processing flow.

[0498] Step 1:

[0499] The device is a camera installed poolside that simultaneously captures the swimmers' movements and facial expressions in high definition. This video data is encoded and transmitted to a server in real time.

[0500] Step 2:

[0501] The server receives the video data transmitted from the terminal and performs decoding. The decoded video data is then prepared for analysis.

[0502] Step 3:

[0503] The server uses an AI model to analyze the athlete's form from video footage. Simultaneously, an emotion engine analyzes facial expression data to recognize the user's emotional state. This recognition result is then added to the real-time performance evaluation.

[0504] Step 4:

[0505] The server generates coaching content to provide to the player based on the analysis of their behavior and emotions. For example, if a player is feeling anxious, the server generates coaching content that includes encouraging messages.

[0506] Step 5:

[0507] The server formats the generated instructional content as AR content and converts it into a format suitable for underwater visual devices. This format is designed to be intuitive and low-intensity, with visibility in mind.

[0508] Step 6:

[0509] The device receives AR data transmitted from the server and displays the instructional content on the user's underwater goggles. The displayed content is optimized for improving underwater performance.

[0510] Step 7:

[0511] Users visually confirm the instructions displayed on their swimming goggles and adjust their movements accordingly. For example, if the analysis results and emotional feedback instruct them to "relax more," the user can improve their movements based on that instruction.

[0512] (Example 2)

[0513] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0514] For athletes to efficiently improve their skills in the water, real-time, appropriate feedback is crucial. However, conventional systems have difficulty providing feedback that considers not only technical movements but also the athlete's emotional state, and there is a lack of established methods for effectively presenting feedback in an underwater environment.

[0515] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0516] In this invention, the server includes a shooting means for capturing the actions of an athlete, an evaluation means for analyzing the received video data and evaluating the athlete's movements and emotional state in real time, and a conversion means for converting the generated instruction content into display data that can be viewed even underwater. This enables the provision of real-time feedback that simultaneously considers technical characteristics and emotional state, allowing for efficient form improvement.

[0517] A "participant" refers to an individual who engages in exercise, and is the subject of analysis for movements during sports such as swimming.

[0518] "Recording means" refers to devices or groups of devices used to record the movements of a person, and includes high-resolution devices such as cameras.

[0519] "Receiving means" refers to a device or system that has the function of incorporating video data collected by the shooting means into the system.

[0520] "Evaluation means" refers to technologies and devices used to analyze received data and measure and evaluate the movements and emotional state of an athlete.

[0521] "Generative means" refers to devices or algorithms that design and generate instructional content and feedback suitable for the athlete based on evaluated information.

[0522] "Conversion means" refers to technologies and systems for formatting the generated instructional content into a display format suitable for the underwater environment.

[0523] "Output means" refers to devices or methods used to provide the converted data to the person performing the action, and includes underwater visual devices, etc.

[0524] This invention is a system designed to support the improvement of athletes' skills, and is particularly intended for use in water. The system mainly consists of a terminal, a server, and a user.

[0525] The device uses a high-performance camera installed poolside to capture the movements of athletes in real time. This camera can acquire high-resolution image data, capturing the detailed movements of the athletes. In addition, it simultaneously captures information about the user's facial expressions and emotions and transmits it to the server. This process collects data that allows for an understanding of both the athletes' technical skills and emotions.

[0526] The server analyzes the received video data. This analysis utilizes AI technology and generative AI models. First, the server identifies the position of the skeleton and joints from the athlete's movements and performs a technical evaluation by comparing it with past data and the performance of top athletes. It also uses an emotion engine to analyze the athlete's psychological state from their facial expressions to understand how they are feeling. This enables technical instruction and emotionally responsive feedback.

[0527] Based on the analysis results, the server generates optimal instruction for the exerciser. This instruction includes not only technical guidance but also messages to boost motivation. For example, it generates feedback that simultaneously considers technical advice such as "Try widening the angle of your arms even more" and emotional encouragement such as "Keep it up!"

[0528] The generated instructional content is converted into a format that can be viewed by underwater visual devices. The terminal outputs this converted data to visual devices such as underwater goggles. This allows users to receive real-time feedback through the goggles and immediately adjust their form and mental state.

[0529] The fundamental principle of this system is to maximize training effectiveness by supporting the technical improvement of athletes while simultaneously providing mental support.

[0530] As an example of a prompt, the server receives the command, "Generate appropriate coaching content based on the player's form data and emotional state." This prompts the AI ​​model to automatically generate training feedback.

[0531] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0532] Step 1:

[0533] The terminal uses a high-performance camera positioned poolside to capture the movements of athletes and the user's facial expressions. This capture process continuously collects high-resolution images every second. The camera accurately captures the athlete's body movements and facial expressions, recording them as digital data. The input is the athlete's movements and facial expressions, and the output is the captured video data. The captured data is immediately compressed and transferred to the server.

[0534] Step 2:

[0535] The server receives video data transmitted from the terminal and begins analysis using AI technology. First, it uses an image recognition algorithm to identify the position of the person's skeleton and joints. Next, based on this data, it performs a technical evaluation by comparing it with past databases and exemplary performances. This process quantifies the quality of the movement. The input is video data, and the output is technical evaluation data of the person performing the movement.

[0536] Step 3:

[0537] The server analyzes the received facial expression data using an emotion engine to determine the emotional state of the person performing the action. This analysis determines what emotions the person is experiencing based on features extracted from their facial expressions. For example, emotions such as smiling, concentration, and frustration can be identified. The input is facial expression data, and the output is the result of the emotion analysis.

[0538] Step 4:

[0539] The server generates instruction tailored to the athlete based on technical evaluation data and sentiment analysis results. Using a generative AI model, it automatically creates feedback that considers both technical and emotional aspects. For example, it can simultaneously generate technical instruction such as "Try widening the angle of your arms even more" and emotional encouragement such as "Keep it up!" The input is technical evaluation data and sentiment analysis results, and the output is instruction content.

[0540] Step 5:

[0541] The server converts the generated instructional content into underwater AR content and sends it to the device. This conversion process adjusts the information displayed on the visual device to a format easily recognizable underwater. The input is the instructional content, and the output is data for the visual device.

[0542] Step 6:

[0543] The device displays data converted into underwater goggles. Users receive real-time feedback through the goggles, allowing them to adjust their actions immediately. Specifically, they can correct their form or maintain their mental focus by looking at instructional messages displayed in front of them. The input is data for the visual device, and the output is feedback displayed on the goggles.

[0544] (Application Example 2)

[0545] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0546] In modern times, there are challenges in providing individualized instruction and maintaining motivation during home-based exercise and fitness activities. In particular, users find it difficult to properly observe their own form, and maintaining motivation during monotonous training is challenging. Therefore, there is a need to develop a system that provides users with appropriate technical guidance and psychological support in real time.

[0547] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording the movements of an athlete, means for receiving the recorded movement video, means for analyzing the received video data and evaluating the athlete's movements and emotional state in real time, means for generating instruction content and motivational messages based on the evaluation results, means for converting the generated instruction content and messages into display data, and means for outputting the converted data to a visual device. This makes it possible to provide individualized instruction and psychological support to the athlete and improve the effectiveness of home training.

[0548] A "participant" refers to an individual who engages in exercise or fitness activities, and their movements and emotional state are the subjects of analysis.

[0549] "Recording means" refers to devices or technologies that capture or sense a person's movements and save them as digital data.

[0550] "Receiving means" refers to a function that transfers recorded operational data to a server and receives it in a format usable for analysis.

[0551] "Evaluation means" refers to a series of processes and systems for analyzing the movements of an athlete based on received video data and determining their form and emotional state.

[0552] "Generative means" refers to the function of creating appropriate instructional content and psychological motivational messages for athletes based on the results obtained from evaluation means.

[0553] "Conversion means" refers to processes and techniques that adjust the format in order to correctly display the generated instructional content and messages on a visual device.

[0554] "Output means" refers to a mechanism for transmitting data to a visual device in order to provide the converted instructional content and message to the exerciser.

[0555] The system implementing this invention analyzes the movements and emotional state of an exerciser in a home fitness environment in real time and provides personalized feedback. The system mainly consists of three components: a server, a terminal, and a user.

[0556] The server features an AI analysis engine based on Python, utilizing TensorFlow and PyTorch. The receiving device analyzes motion data transferred from the terminal in real time, evaluating the exerciser's form and emotional state. Based on the analysis results, the evaluation device generates exerciser-specific instruction content and motivational messages. The generated content is then converted using Unity by the conversion device into a data format displayable on visual devices.

[0557] The device uses cameras and sensors built into the home fitness robot to record the user's movements. The recorded data is transmitted to a server via a receiving device.

[0558] Users receive real-time feedback through visual devices. This allows users to immediately identify areas for improvement in their movements and enhance the effectiveness of their exercise. For example, when a user is doing yoga, the device might instruct them to "straighten your spine a little more," while an emotion engine on the server displays a real-time encouraging message such as "relax and continue to breathe deeply."

[0559] Examples of prompts to input into a generative AI model:

[0560] “You are designing a real-time feedback system for a home fitness robot. The system uses cameras to analyze user movements and emotions during exercise, and offers personalized guidance and motivational messages through AR goggles. Describe how you would implement such a system.”

[0561] In this way, by supporting exercisers from both technical and psychological perspectives, the home fitness experience can be made more effective and satisfying.

[0562] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0563] Step 1:

[0564] The device records the movements of the person exercising using a camera. The input is video of the person's movements, and the recorded data is transmitted to the server in real time via a receiving device. The output is movement data in digital format.

[0565] Step 2:

[0566] The server inputs the received motion data into the AI ​​analysis engine. The input is motion data sent from the terminal, and the AI ​​technology is used to analyze the form and emotional state, and the results are obtained using an evaluation tool. The output is data on the athlete's form evaluation and emotional state.

[0567] Step 3:

[0568] The server uses the form evaluation and emotional state obtained from the evaluation means to generate instruction content and motivational messages for the exerciser using the generation means. The input is the evaluation result, and the output is the individualized instruction content and message. Specifically, the server uses a generation AI model to construct appropriate feedback content.

[0569] Step 4:

[0570] The server converts the generated instructional content and messages into a data format that can be displayed on AR goggles using a conversion device. The input is data from the generation device, and the output is display data suitable for visual devices. Data processing is performed using Unity.

[0571] Step 5:

[0572] Users receive instructional content and messages in real time through their visual devices. Input is display data transmitted from the server via the device, and output is visual feedback displayed on the exerciser's AR goggles. Specifically, users can adjust their form based on this feedback.

[0573] 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.

[0574] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0575] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0576] [Fourth Embodiment]

[0577] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0578] 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.

[0579] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0580] 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.

[0581] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0582] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0583] 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.

[0584] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0585] 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.

[0586] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0587] The 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.

[0588] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0589] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0590] This invention is implemented as a system for efficiently improving the movements of swimmers. This system mainly comprises three elements: a terminal, a server, and a user.

[0591] The device has the function of capturing the movements of swimmers using cameras installed poolside. The high-resolution, high-speed cameras capture the swimmers' movements in detail and transmit the video to the server in real time.

[0592] The server receives video data transmitted from the terminal and analyzes it using AI technology. To analyze the player's form, it compares it with pre-trained data from top athletes and the player's own past data to identify movement habits and areas requiring improvement. It evaluates the player's performance and generates customized coaching content based on the results. This generated coaching content includes specific advice such as "stroke faster."

[0593] The generated instructional content is formatted by the server as AR content optimized for underwater use and sent to the device. The device displays this data on the user's swimming goggles. The user can visually check the instructional content in real time while swimming and adjust their form on the spot. For example, if the instruction is to "lower the stroke angle by 5 degrees," the user can immediately adjust accordingly.

[0594] This system provides support for athletes to improve their skills efficiently and effectively. While world-class coaches are not always present, this system allows athletes to improve themselves in real time and receive support for optimal training.

[0595] The following describes the processing flow.

[0596] Step 1:

[0597] The device uses cameras installed poolside to capture high-definition footage of swimmers' movements. The captured video is encoded into a format that can be processed in real time.

[0598] Step 2:

[0599] The terminal transmits encoded video data to the server over the network. To maintain real-time performance, a high-speed and secure communication method is used.

[0600] Step 3:

[0601] The server receives video data transmitted from the terminal and performs decoding. To analyze this decoded data, an AI model is deployed to extract joint points from the athlete's movements.

[0602] Step 4:

[0603] The server analyzes the athlete's form and movement patterns based on extracted joint points. This includes an evaluation process that references data from top athletes and the athlete's past performance data to identify movement habits and areas for improvement.

[0604] Step 5:

[0605] Based on the analysis results from step 4, the server generates specific guidance in real time that indicates areas for improvement. This guidance is prepared in the form of specific operational instructions and suggestions for form modifications.

[0606] Step 6:

[0607] The server formats the generated instructional content as AR content and converts it into a display format that takes into account visibility underwater. The converted data is then ready to be sent to the device.

[0608] Step 7:

[0609] The device displays AR data received from the server onto the underwater goggles. Instructions are displayed on the goggles' screen for easy user visibility.

[0610] Step 8:

[0611] Users can view instructions displayed on their underwater goggles in real time and adjust their form and movements based on those instructions. For example, they might adjust the timing and angle of their strokes according to the displayed advice.

[0612] (Example 1)

[0613] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0614] For swimmers to efficiently and effectively improve their technique, they need to receive real-time feedback on their form. However, traditional methods require coaches to directly observe and provide feedback, which is subject to time and personnel constraints. Furthermore, providing detailed, real-time motion analysis and specific instructional content has only been possible under limited conditions.

[0615] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0616] In this invention, the server includes data analysis means, information generation means, and signal output means. This overcomes conventional limitations, making it possible to analyze video data captured by a terminal installed poolside by a swimmer in real time and immediately display specific feedback for improving form on an underwater visual device.

[0617] "Image acquisition means" refers to a device or system that has the function of capturing high-resolution images of a swimmer's movements.

[0618] "Information receiving means" refers to a device or system for receiving data transmitted from image acquisition means.

[0619] "Data analysis means" refers to a device or system that has the function of evaluating a player's form and movements based on received motion data and comparing it with past data of top players or individual players.

[0620] "Information generation means" refers to a device or system that generates specific coaching content for athletes based on the results of data analysis.

[0621] "Format conversion means" refers to a device or system that has the function of converting the generated instructional content into a data format that can be displayed on a visual device.

[0622] "Signal output means" refers to a device or system that has the function of transmitting the converted data to an underwater visual device and providing feedback to the athlete.

[0623] A "feedback provision method" is a device or system that provides visual instruction to enable swimmers to adjust their form in real time.

[0624] This invention is a real-time analysis and feedback system aimed at improving the technique of swimmers. The system consists of three elements: a terminal, a server, and a user.

[0625] The terminal is installed poolside and is equipped with a high-definition, high-speed camera. This camera has the ability to capture the athletes' movements in detail and transmit the video data to the server in real time. For network communication, it is equipped with a powerful encoder and a low-latency communication module.

[0626] The server analyzes the received video data using AI technology to evaluate the athlete's form. The AI ​​technology used is computer vision software with deep learning implemented, which analyzes the movements by comparing them with past data of top athletes and the athlete themselves. Through this analysis, the athlete's movement habits and areas for improvement are identified, and specific coaching content is generated. The generated coaching content is converted into a format that can be displayed on underwater visual devices.

[0627] The user wears a special visual device underwater. This device displays feedback sent from a server in real time, helping the athlete adjust their form on the spot. For example, if an athlete wants to improve their crawl stroke, the server generates advice such as "lower your stroke angle by 5 degrees" and displays it on the visual device. In this way, the athlete can make the necessary adjustments immediately and efficiently improve their technique.

[0628] By utilizing a generative AI model, the system provides customized feedback to each athlete. For example, a possible prompt could be, "Analyze my crawl stroke form and generate specific advice to improve it." This allows athletes to receive training optimized to their individual needs.

[0629] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0630] Step 1:

[0631] The device uses a high-resolution camera to film the swimmer's movements. The camera has a frame rate of 60fps or higher, capable of capturing even the finest details of movement. The input is the swimmer's actual movements, and the output is high-definition video data. This data is compressed and then transmitted to the server in real time.

[0632] Step 2:

[0633] The server receives video data transmitted from the terminal. Upon receipt, it verifies the integrity of the data and requests retransmission if necessary. The input is compressed video data, and the output is decoded video frames. These frames are then passed to the AI ​​analysis module.

[0634] Step 3:

[0635] The server uses an AI analysis module to analyze the received video data. This analysis utilizes computer vision technology to evaluate the athlete's form. Specifically, it analyzes the frames acquired as input in three dimensions and quantifies the athlete's movements. The output is data that includes the characteristics of the movements and the evaluation results.

[0636] Step 4:

[0637] Based on the analysis results, the server uses an information generation module to generate specific instructional content. For example, it might output something like, "The stroke angle is 10 degrees larger than ideal." Here, the input is characteristic data of the motion, and the output is advice.

[0638] Step 5:

[0639] The server converts the generated instructional content into a format compatible with visual devices using a format conversion module. It is optimized as AR content, including arrows and icons, to improve visibility underwater. This process uses advice data as input and produces AR format data as output.

[0640] Step 6:

[0641] The device transmits this converted data to an underwater visual device worn by the swimmer. The input is AR format data, and the output is visual information displayed on the underwater goggles. The user can then review this and adjust their form in real time.

[0642] (Application Example 1)

[0643] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0644] For many swimmers and health-conscious users, there is a challenge in receiving real-time performance evaluations and personalized feedback and exercise plans. This makes effective self-improvement and goal achievement difficult.

[0645] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0646] In this invention, the server includes means for analyzing received video data and evaluating the athlete's movements in real time, means for generating instruction content for the athlete based on the evaluation results, and means for adjusting the exercise plan based on the user's goals. This allows the user to receive real-time feedback on movement improvements and easily adjust the individually optimized exercise plan.

[0647] The term "swimmer" refers to someone who engages in exercise or competitive activities in a swimming pool.

[0648] "Means of recording" refers to devices or groups of devices used to record the actions of a subject as video footage.

[0649] "Receiving means" refers to the device or method for acquiring captured video data.

[0650] "Evaluation means" refers to processes and devices used to analyze acquired data and evaluate performance.

[0651] "Generation means" refers to the process or device for generating instructional content based on evaluation results.

[0652] "Conversion means" refers to the process or device used to convert the generated instructional content into data for display.

[0653] "Output means" refers to the process or device used to output the converted data to a visual device.

[0654] A "visual device" refers to a device that provides display data to the user visually.

[0655] A "user terminal" refers to a portable device used to receive feedback and information.

[0656] "Adjustment means" refers to a device or method for adjusting an exercise plan based on the user's goals.

[0657] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server has the function of receiving swimmer motion data acquired at the poolside by a camera in real time and analyzing that data. For the analysis, a generative AI model using TensorFlow is used, and highly accurate motion evaluation is achieved by comparing it with past data. This evaluation result is generated as individual instruction content for the swimmer, and the generated instruction content is converted into display data by a conversion means.

[0658] The device has the function of outputting the converted data to an underwater visual device. Specifically, it processes the data as AR (augmented reality) content using Unity and displays the information on the underwater goggles used by swimmers. The user can then see the visual feedback on the spot.

[0659] Users can further provide feedback to the server based on their goals, and the server adjusts the exercise plan based on that information. This automatic adjustment recommends specific steps to help the user reach their set goals.

[0660] For example, if a swimmer aiming for a swimming competition uses this system, the server can provide real-time feedback by using a prompt message such as, "Based on the following input data, generate specific advice to improve the user's swimming technique. The data includes the user's current swimming form, which can be compared to the previous swimming technique analysis results."

[0661] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0662] Step 1:

[0663] The server receives real-time video data of swimmers from cameras installed poolside. The input is high-definition video data, which is temporarily stored internally on the server as output. During this process, the video data is digitally compressed and placed on appropriate storage.

[0664] Step 2:

[0665] The server inputs the received video data into a generative AI model (using TensorFlow) for analysis. The input is video data frames, and the output is the motion analysis result. In this process, past data is referenced to evaluate the players' movements and identify specific points for motion improvement.

[0666] Step 3:

[0667] The server generates instruction content based on the analysis results. The input data is the motion analysis results, and the output is text data containing the instruction content. In this step, a pre-configured AI model uses the "generating AI model and prompt sentences" to create specific improvement instructions.

[0668] Step 4:

[0669] The server converts the generated instructional content into display data. Unity is used for this conversion, reorganizing the instructional content into an easy-to-view AR format. The input is the instructional content data, and the output is the display data.

[0670] Step 5:

[0671] The terminal outputs display data to the underwater visual device. It receives display data as input and outputs real-time feedback to the visual device. The display is adjusted so that the user can clearly see it even underwater.

[0672] Step 6:

[0673] The user adjusts their movements while reviewing the feedback. The input is visual feedback, and the output is expected to be actual improvements in form and movement. At this stage, the user works on practicing in pursuit of a more efficient swimming form.

[0674] Step 7:

[0675] Users can send additional information to the server via their device based on the feedback they receive from their exercises. The input is user feedback data, and the output is an updated exercise plan.

[0676] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0677] This invention is implemented as a swimming training system that incorporates an emotion engine. This system consists of three components: a terminal, a server, and a user.

[0678] The device has a camera installed poolside that captures swimmers' movements in high definition. Furthermore, it captures the user's facial expressions and transmits the video data to a server in real time. This allows for simultaneous monitoring of the swimmer's movements and emotional state.

[0679] The server receives video data from the terminal and uses AI technology to analyze the athlete's form. This analysis includes comparisons with data from top athletes and past performance data. Furthermore, the server uses an emotion engine to analyze the user's facial expression data and identify their emotional state at that moment. This emotional information is used to understand how the athlete is feeling during training and to reflect this in the feedback provided.

[0680] The generation method designs optimal coaching content for the player based on the analyzed form and emotional state. This coaching content takes into account the player's technical characteristics and current emotional state; for example, if the player is feeling frustrated, the coaching content can be adjusted to improve their motivation.

[0681] The conversion mechanism formats and presents the generated instructional content as AR content suitable for underwater visual devices. The modified instructional content and feedback are designed to minimize user burden and are provided in a format specifically tailored for underwater use.

[0682] The device displays this converted data on the swimming goggles. The user can then check the instructions in real time through the goggles and immediately adjust their form. For example, the server can instruct, "Try widening the angle of your arms even more," while the emotion engine simultaneously displays an encouraging message, "Keep it up!" In this way, the user is supported from both a technical and emotional perspective, promoting more efficient form improvement.

[0683] The following describes the processing flow.

[0684] Step 1:

[0685] The device is a camera installed poolside that simultaneously captures the swimmers' movements and facial expressions in high definition. This video data is encoded and transmitted to a server in real time.

[0686] Step 2:

[0687] The server receives the video data transmitted from the terminal and performs decoding. The decoded video data is then prepared for analysis.

[0688] Step 3:

[0689] The server uses an AI model to analyze the athlete's form from video footage. Simultaneously, an emotion engine analyzes facial expression data to recognize the user's emotional state. This recognition result is then added to the real-time performance evaluation.

[0690] Step 4:

[0691] The server generates coaching content to provide to the player based on the analysis of their behavior and emotions. For example, if a player is feeling anxious, the server generates coaching content that includes encouraging messages.

[0692] Step 5:

[0693] The server formats the generated instructional content as AR content and converts it into a format suitable for underwater visual devices. This format is designed to be intuitive and low-intensity, with visibility in mind.

[0694] Step 6:

[0695] The device receives AR data transmitted from the server and displays the instructional content on the user's underwater goggles. The displayed content is optimized for improving underwater performance.

[0696] Step 7:

[0697] Users visually confirm the instructions displayed on their swimming goggles and adjust their movements accordingly. For example, if the analysis results and emotional feedback instruct them to "relax more," the user can improve their movements based on that instruction.

[0698] (Example 2)

[0699] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0700] For athletes to efficiently improve their skills in the water, real-time, appropriate feedback is crucial. However, conventional systems have difficulty providing feedback that considers not only technical movements but also the athlete's emotional state, and there is a lack of established methods for effectively presenting feedback in an underwater environment.

[0701] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0702] In this invention, the server includes a shooting means for capturing the actions of an athlete, an evaluation means for analyzing the received video data and evaluating the athlete's movements and emotional state in real time, and a conversion means for converting the generated instruction content into display data that can be viewed even underwater. This enables the provision of real-time feedback that simultaneously considers technical characteristics and emotional state, allowing for efficient form improvement.

[0703] A "participant" refers to an individual who engages in exercise, and is the subject of analysis for movements during sports such as swimming.

[0704] "Recording means" refers to devices or groups of devices used to record the movements of a person, and includes high-resolution devices such as cameras.

[0705] "Receiving means" refers to a device or system that has the function of incorporating video data collected by the shooting means into the system.

[0706] "Evaluation means" refers to technologies and devices used to analyze received data and measure and evaluate the movements and emotional state of an athlete.

[0707] "Generative means" refers to devices or algorithms that design and generate instructional content and feedback suitable for the athlete based on evaluated information.

[0708] "Conversion means" refers to technologies and systems for formatting the generated instructional content into a display format suitable for the underwater environment.

[0709] "Output means" refers to devices or methods used to provide the converted data to the person performing the action, and includes underwater visual devices, etc.

[0710] This invention is a system designed to support the improvement of athletes' skills, and is particularly intended for use in water. The system mainly consists of a terminal, a server, and a user.

[0711] The device uses a high-performance camera installed poolside to capture the movements of athletes in real time. This camera can acquire high-resolution image data, capturing the detailed movements of the athletes. In addition, it simultaneously captures information about the user's facial expressions and emotions and transmits it to the server. This process collects data that allows for an understanding of both the athletes' technical skills and emotions.

[0712] The server analyzes the received video data. This analysis utilizes AI technology and generative AI models. First, the server identifies the position of the skeleton and joints from the athlete's movements and performs a technical evaluation by comparing it with past data and the performance of top athletes. It also uses an emotion engine to analyze the athlete's psychological state from their facial expressions to understand how they are feeling. This enables technical instruction and emotionally responsive feedback.

[0713] Based on the analysis results, the server generates optimal instruction for the exerciser. This instruction includes not only technical guidance but also messages to boost motivation. For example, it generates feedback that simultaneously considers technical advice such as "Try widening the angle of your arms even more" and emotional encouragement such as "Keep it up!"

[0714] The generated instructional content is converted into a format that can be viewed by underwater visual devices. The terminal outputs this converted data to visual devices such as underwater goggles. This allows users to receive real-time feedback through the goggles and immediately adjust their form and mental state.

[0715] The fundamental principle of this system is to maximize training effectiveness by supporting the technical improvement of athletes while simultaneously providing mental support.

[0716] As an example of a prompt, the server receives the command, "Generate appropriate coaching content based on the player's form data and emotional state." This prompts the AI ​​model to automatically generate training feedback.

[0717] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0718] Step 1:

[0719] The terminal uses a high-performance camera positioned poolside to capture the movements of athletes and the user's facial expressions. This capture process continuously collects high-resolution images every second. The camera accurately captures the athlete's body movements and facial expressions, recording them as digital data. The input is the athlete's movements and facial expressions, and the output is the captured video data. The captured data is immediately compressed and transferred to the server.

[0720] Step 2:

[0721] The server receives video data transmitted from the terminal and begins analysis using AI technology. First, it uses an image recognition algorithm to identify the position of the person's skeleton and joints. Next, based on this data, it performs a technical evaluation by comparing it with past databases and exemplary performances. This process quantifies the quality of the movement. The input is video data, and the output is technical evaluation data of the person performing the movement.

[0722] Step 3:

[0723] The server analyzes the received facial expression data using an emotion engine to determine the emotional state of the person performing the action. This analysis determines what emotions the person is experiencing based on features extracted from their facial expressions. For example, emotions such as smiling, concentration, and frustration can be identified. The input is facial expression data, and the output is the result of the emotion analysis.

[0724] Step 4:

[0725] The server generates instruction tailored to the athlete based on technical evaluation data and sentiment analysis results. Using a generative AI model, it automatically creates feedback that considers both technical and emotional aspects. For example, it can simultaneously generate technical instruction such as "Try widening the angle of your arms even more" and emotional encouragement such as "Keep it up!" The input is technical evaluation data and sentiment analysis results, and the output is instruction content.

[0726] Step 5:

[0727] The server converts the generated instructional content into underwater AR content and sends it to the device. This conversion process adjusts the information displayed on the visual device to a format easily recognizable underwater. The input is the instructional content, and the output is data for the visual device.

[0728] Step 6:

[0729] The device displays data converted into underwater goggles. Users receive real-time feedback through the goggles, allowing them to adjust their actions immediately. Specifically, they can correct their form or maintain their mental focus by looking at instructional messages displayed in front of them. The input is data for the visual device, and the output is feedback displayed on the goggles.

[0730] (Application Example 2)

[0731] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0732] In modern times, there are challenges in providing individualized instruction and maintaining motivation during home-based exercise and fitness activities. In particular, users find it difficult to properly observe their own form, and maintaining motivation during monotonous training is challenging. Therefore, there is a need to develop a system that provides users with appropriate technical guidance and psychological support in real time.

[0733] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording the movements of an athlete, means for receiving the recorded movement video, means for analyzing the received video data and evaluating the athlete's movements and emotional state in real time, means for generating instruction content and motivational messages based on the evaluation results, means for converting the generated instruction content and messages into display data, and means for outputting the converted data to a visual device. This makes it possible to provide individualized instruction and psychological support to the athlete and improve the effectiveness of home training.

[0734] A "participant" refers to an individual who engages in exercise or fitness activities, and their movements and emotional state are the subjects of analysis.

[0735] "Recording means" refers to devices or technologies that capture or sense a person's movements and save them as digital data.

[0736] "Receiving means" refers to a function that transfers recorded operational data to a server and receives it in a format usable for analysis.

[0737] "Evaluation means" refers to a series of processes and systems for analyzing the movements of an athlete based on received video data and determining their form and emotional state.

[0738] "Generative means" refers to the function of creating appropriate instructional content and psychological motivational messages for athletes based on the results obtained from evaluation means.

[0739] "Conversion means" refers to processes and techniques that adjust the format in order to correctly display the generated instructional content and messages on a visual device.

[0740] "Output means" refers to a mechanism for transmitting data to a visual device in order to provide the converted instructional content and message to the exerciser.

[0741] The system implementing this invention analyzes the movements and emotional state of an exerciser in a home fitness environment in real time and provides personalized feedback. The system mainly consists of three components: a server, a terminal, and a user.

[0742] The server features an AI analysis engine based on Python, utilizing TensorFlow and PyTorch. The receiving device analyzes motion data transferred from the terminal in real time, evaluating the exerciser's form and emotional state. Based on the analysis results, the evaluation device generates exerciser-specific instruction content and motivational messages. The generated content is then converted using Unity by the conversion device into a data format displayable on visual devices.

[0743] The device uses cameras and sensors built into the home fitness robot to record the user's movements. The recorded data is transmitted to a server via a receiving device.

[0744] Users receive real-time feedback through visual devices. This allows users to immediately identify areas for improvement in their movements and enhance the effectiveness of their exercise. For example, when a user is doing yoga, the device might instruct them to "straighten your spine a little more," while an emotion engine on the server displays a real-time encouraging message such as "relax and continue to breathe deeply."

[0745] Examples of prompts to input into a generative AI model:

[0746] “You are designing a real-time feedback system for a home fitness robot. The system uses cameras to analyze user movements and emotions during exercise, and offers personalized guidance and motivational messages through AR goggles. Describe how you would implement such a system.”

[0747] In this way, by supporting exercisers from both technical and psychological perspectives, the home fitness experience can be made more effective and satisfying.

[0748] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0749] Step 1:

[0750] The device records the movements of the person exercising using a camera. The input is video of the person's movements, and the recorded data is transmitted to the server in real time via a receiving device. The output is movement data in digital format.

[0751] Step 2:

[0752] The server inputs the received motion data into the AI ​​analysis engine. The input is motion data sent from the terminal, and the AI ​​technology is used to analyze the form and emotional state, and the results are obtained using an evaluation tool. The output is data on the athlete's form evaluation and emotional state.

[0753] Step 3:

[0754] The server uses the form evaluation and emotional state obtained from the evaluation means to generate instruction content and motivational messages for the exerciser using the generation means. The input is the evaluation result, and the output is the individualized instruction content and message. Specifically, the server uses a generation AI model to construct appropriate feedback content.

[0755] Step 4:

[0756] The server converts the generated instructional content and messages into a data format that can be displayed on AR goggles using a conversion device. The input is data from the generation device, and the output is display data suitable for visual devices. Data processing is performed using Unity.

[0757] Step 5:

[0758] Users receive instructional content and messages in real time through their visual devices. Input is display data transmitted from the server via the device, and output is visual feedback displayed on the exerciser's AR goggles. Specifically, users can adjust their form based on this feedback.

[0759] 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.

[0760] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0761] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0762] 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.

[0763] Figure 9 shows an 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.

[0764] 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.

[0765] 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.

[0766] 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, motorcycles, etc., 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, for example, based 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.

[0767] 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."

[0768] 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.

[0769] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0770] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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 the like 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.

[0779] 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.

[0780] The following is further disclosed regarding the embodiments described above.

[0781] (Claim 1)

[0782] A means of filming the movements of swimmers,

[0783] A receiving means for receiving captured motion video,

[0784] An evaluation method that analyzes received video data and evaluates the player's movements in real time,

[0785] A generation means for generating coaching content for players based on evaluation results,

[0786] A conversion means for converting the generated instructional content into data for display,

[0787] A system including an output means for outputting the converted data to an underwater visual device.

[0788] (Claim 2)

[0789] The system according to claim 1, wherein the evaluation means analyzes the player's movements using past performance data.

[0790] (Claim 3)

[0791] The system according to claim 1, wherein the display data is displayed in a way that takes into account visibility underwater.

[0792] "Example 1"

[0793] (Claim 1)

[0794] A means for acquiring images to film the movements of swimmers,

[0795] Information receiving means for receiving captured image data,

[0796] A data analysis method that analyzes received data and evaluates the player's movements in real time,

[0797] Information generation means for generating coaching content for players based on analysis results,

[0798] A format conversion means for converting the generated instructional content into data for display,

[0799] A signal output means for outputting the converted data to an underwater visual device,

[0800] A means of providing swimmers with real-time feedback to adjust their form in the water,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the data analysis means analyzes the movements of a player by comparing them with past data of top players or individual players.

[0804] (Claim 3)

[0805] The system according to claim 1, wherein the display data is a display method that combines visual guides and text to optimize visibility underwater.

[0806] "Application Example 1"

[0807] (Claim 1)

[0808] A means of filming the movements of swimmers,

[0809] A receiving means for receiving captured motion video,

[0810] An evaluation method that analyzes received video data and evaluates the player's movements in real time,

[0811] A generation means for generating coaching content for players based on evaluation results,

[0812] A conversion means for converting the generated instructional content into data for display,

[0813] Output means for outputting the converted data to a visual device and displaying feedback on the user terminal,

[0814] An adjustment mechanism to adjust the exercise plan based on the user's goals,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, wherein the evaluation means analyzes the player's movements using past performance data and generates real-time feedback.

[0818] (Claim 3)

[0819] The system according to claim 1, wherein the display data is displayed in a way that takes visibility underwater into consideration, and is displayed on a visual device using augmented reality technology.

[0820] "Example 2 of combining an emotion engine"

[0821] (Claim 1)

[0822] A means of filming the actions of athletes,

[0823] A receiving means for receiving captured behavioral information,

[0824] An evaluation means that analyzes received video data and evaluates the movements of the person performing the action in real time,

[0825] Based on the evaluation results, a generation means analyzes the emotional state of the exerciser and generates feedback content,

[0826] A conversion means for converting the generated feedback content into display data and formatting it into a format that can be viewed even underwater,

[0827] A system including an output means for outputting the converted data to an underwater visual device.

[0828] (Claim 2)

[0829] The system according to claim 1, wherein the evaluation means analyzes the movements of an athlete using past performance data and data of top athletes, and generates instructional content that takes into account technical characteristics and emotional state.

[0830] (Claim 3)

[0831] The system according to claim 1, wherein display data provides real-time feedback to the athlete via an improved visual device, thereby efficiently facilitating form adjustments.

[0832] "Application example 2 when combining with an emotional engine"

[0833] (Claim 1)

[0834] A recording means for recording the movements of an athlete,

[0835] A receiving means for receiving recorded motion video,

[0836] An evaluation means that analyzes received video data and evaluates the movements of the person performing the action in real time,

[0837] A generation means for generating instructional content and motivational messages for athletes based on evaluation results and emotional state,

[0838] A conversion means for converting the generated instructional content and messages into data for display,

[0839] A system including output means for outputting converted data to a visual device.

[0840] (Claim 2)

[0841] The system according to claim 1, wherein the evaluation means analyzes the movements of the exerciser using past performance data and emotion recognition data.

[0842] (Claim 3)

[0843] The system according to claim 1, wherein the display data is displayed in a manner that takes into account visibility in an exercise environment. [Explanation of Symbols]

[0844] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of filming the movements of swimmers, A receiving means for receiving captured motion video, An evaluation method that analyzes received video data and evaluates the player's movements in real time, A generation means for generating coaching content for players based on evaluation results, A conversion means for converting the generated instructional content into data for display, A system including an output means for outputting the converted data to an underwater visual device.

2. The system according to claim 1, wherein the evaluation means analyzes the player's movements using past performance data.

3. The system according to claim 1, wherein the display data is displayed in a way that takes into account visibility underwater.

Images