System

Abstract

A system is provided.SOLUTION: A system comprising: means for recording a swing motion of a user with a camera; means for transmitting the recorded video data to a server; means for analyzing the video data in the server and evaluating a swing form; means for generating a feedback for the user based on the evaluation result; and means for transmitting the feedback to the terminal and displaying it to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional golf swing training methods make it extremely difficult for players to accurately understand and improve their own form. They typically require instruction from a professional coach, which is a significant time and financial burden. Furthermore, when practicing alone, players are likely to repeat incorrect swing form, making it difficult to efficiently improve their skills. This invention aims to solve these problems by analyzing swing form in real time and providing feedback. [Means for solving the problem]

[0005] This invention is a system including a means for recording a user's swing motion with a camera, a means for transmitting the recorded video data to a server, a means for analyzing the video data and evaluating the swing form in the server, a means for generating feedback for the user based on the evaluation results, and a means for transmitting the feedback to the terminal and displaying it to the user. This allows the user to identify problems with their swing form in real time and immediately correct them. Furthermore, by adding a means for accumulating practice data for each user and continuously training the model, the accuracy of the feedback can be improved and individually optimized advice can be provided.

[0006] The "camera" is a video recording device for recording the user's swing motion.

[0007] "Swing motion" refers to the movement of the body and the action of the club in a golf swing.

[0008] "Video data" refers to video recording data of a swing motion captured by a camera.

[0009] A "server" is a computer system that receives video data, analyzes it, and generates feedback.

[0010] "Analysis" is the process of extracting feature points from the recorded video data and evaluating the swing form.

[0011] "Swing form" refers to the overall movements and posture in a golf swing.

[0012] "Evaluation" is the act of identifying problems and areas for improvement in a swing form based on analysis.

[0013] "Feedback" refers to advice or instructions provided to the user based on the evaluation results.

[0014] A "terminal" is a device that records camera footage, transmits it to a server, and displays feedback.

[0015] A "user" is an individual practitioner who uses the system to improve their golf swing.

[0016] "Model training" is the process of continuously improving the analysis algorithm using user-specific practice data.

[0017] "Real-time" refers to the immediacy of time, where feedback is provided immediately without delay.

[0018] "Advice" is specific instructions for improvement given to the user based on the evaluation results. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system aimed at improving golf swing skills, and helps improve swing form by analyzing the user's swing motion recorded on a camera in real time and providing feedback.

[0041] Overview of program processing

[0042] Data collection

[0043] The user sets up a camera at a driving range or at home and records their swing. The camera can be any camera device, such as a smartphone or a dedicated camera.

[0044] Video data transmission

[0045] The device sends the recorded video data to the server. The video data is sent in a compressed and encrypted format, ensuring security.

[0046] Receiving and analyzing video data

[0047] The server receives the video data sent from the device and begins analyzing the swing form using an AI model. During the analysis, the characteristic points of the human body (shoulders, elbows, hips, etc.) are extracted for each frame of the video, and the swing trajectory, body rotation, club angle, etc. are evaluated.

[0048] Feedback Generation

[0049] The server generates feedback for the user based on the analysis results. The feedback includes identifying the problem and providing specific advice for improvement. For example, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[0050] Send and view feedback

[0051] The server sends the generated feedback to the device, which then displays it to the user. The feedback is displayed as text or visual content, and the user can refer to it to correct their swing form.

[0052] Specific examples

[0053] 1. The user swings in their home practice room. The user sets up their smartphone on a tripod and records their swing.

[0054] 2. After recording, the device automatically sends the video data to the server. The data is properly compressed and encrypted before being sent.

[0055] 3. The server analyzes the received video data and extracts the swing form's characteristics, such as shoulder movement, hip rotation, and club trajectory.

[0056] 4. Based on the analysis results, the server generates feedback such as, "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing."

[0057] 5. The server sends the generated feedback to the device and displays it to the user in real time. The device displays the feedback in text and image format, allowing the user to correct their swing based on it.

[0058] 6. After reviewing the feedback, the user re-records a new swing with corrections and submits it to the system, which then receives new analysis and feedback. By repeating this process, the user can efficiently and effectively improve their swing form.

[0059] In this way, the present invention provides a specific system for supporting users in improving their golf skills, allowing users to properly understand their own swing form and efficiently improve their skills without the need for guidance from a professional coach.

[0060] The processing flow will be explained below.

[0061] Program processing steps

[0062] Step 1: Recording

[0063] User:

[0064] Set up the camera in an appropriate position and record your swing using a smartphone or dedicated camera.

[0065] Step 2: Sending video data

[0066] Device:

[0067] The recorded video data is sent to the server in a compressed and encrypted format to ensure security.

[0068] Step 3: Receiving video data

[0069] server:

[0070] Receives video data sent from the terminal. After receiving, checks the data for consistency and format.

[0071] Step 4: Preprocessing

[0072] server:

[0073] The received video data is processed before analysis, specifically by extracting frames, adjusting resolution, and removing noise if necessary.

[0074] Step 5: Feature point extraction

[0075] server:

[0076] An AI model is used to extract body features (shoulders, elbows, hips, etc.) from each frame, providing data for specific analysis of swing form movements.

[0077] Step 6: Form evaluation

[0078] server:

[0079] The user's swing form is evaluated based on the extracted feature points, including the swing trajectory, body balance, and club position.

[0080] Step 7: Identify the problem

[0081] server:

[0082] Based on the evaluation results, problems with the swing form are identified. For example, specific areas such as "insufficient rotation of the right shoulder" are identified.

[0083] Step 8: Advice Generation

[0084] server:

[0085] It generates specific advice for improvement based on identified problems, such as "Try to pull your left shoulder back during the backswing to increase the rotation of your right shoulder."

[0086] Step 9: Send your feedback

[0087] server:

[0088] Send the generated feedback to the device, which may include textual and / or visual guidance.

[0089] Step 10: Feedback display

[0090] Device:

[0091] The system receives feedback sent from the server and displays it to the user, including frame-by-frame images of problematic swings along with specific advice.

[0092] Step 11: User confirmation and correction

[0093] User:

[0094] Check the feedback displayed on your device and use it to modify your next swing. Use the feedback to try a new swing.

[0095] Step 12: Continuing the improvement process

[0096] User:

[0097] The corrected swing is then filmed again and the process is repeated from step 1. The user utilizes the feedback to continually improve their skills.

[0098] By repeating this series of steps, the user can improve their swing form accurately and efficiently.

[0099] Example 1

[0100] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0101] Current methods for improving golf swing skills (e.g., video analysis and direct instruction from a coach) are expensive and have the drawback of not providing real-time feedback. Therefore, there is a need for a system that allows users to easily analyze their swing form at home or at a driving range and receive real-time feedback. Furthermore, the difficulty of providing optimized feedback for each individual user is also an issue that needs to be resolved.

[0102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0103] In this invention, the server includes a means for using a camera to record the user's movements, a means for transmitting the data recorded by the camera to an information processing device, a means for analyzing the data and evaluating the movements in the information processing device, a means for generating feedback for the user based on the evaluation results, and a means for transmitting the feedback to the terminal and displaying it to the user. This allows users to easily analyze their own swing form and receive efficient feedback. Furthermore, feedback generated using an artificial intelligence model can provide advice optimized for each individual user in real time.

[0104] "Capture device" refers to a camera or video recording device for recording a user's actions.

[0105] "Information processing device" refers to a computer or server that receives and analyzes the recorded data.

[0106] "User" refers to an individual who uses the system to analyze their swing form and receive feedback.

[0107] "Data" refers to video information of the user's swing motion captured by a camera.

[0108] "Analysis" refers to a process in which an information processing device processes data to extract and evaluate features of a user's actions.

[0109] "Evaluation" refers to the act of judging whether a user's behavior is good or bad based on the analyzed data and identifying areas for improvement.

[0110] "Feedback" refers to advice or guidance provided to the user based on the evaluation results.

[0111] "Device" refers to the device (such as a smartphone or tablet) that a user uses to receive feedback.

[0112] "Artificial intelligence model" refers to the machine learning and deep learning algorithms used to analyze data and generate feedback.

[0113] "Evaluation results" refer to information about the user's behavior and diagnostic results derived during the analysis process.

[0114] "Means using a photographing device" refers to the act of a user recording their own swing motion with a video or camera.

[0115] "Transmitting means" refers to the process of transferring data from the image capture device to the information processing device.

[0116] "Means for displaying" refers to a method for conveying feedback to the user visually or audibly.

[0117] This invention is a system aimed at improving golf swing skills, and helps improve swing form by analyzing the user's swing motion recorded on a camera in real time and providing feedback.

[0118] System configuration

[0119] Data collection

[0120] The user sets up a camera at a driving range or at home and records their swing. The camera can be any type of camera, such as a smartphone or a dedicated camera. For example, the user sets up their smartphone on a tripod and records their swing. A frame rate of at least 30 fps is recommended for recording.

[0121] Video data transmission

[0122] The device (such as a smartphone or dedicated camera) transmits the recorded video data to the server. At this time, the video data is encoded in a compressed format such as H.264 and transmitted over an encrypted communication channel using SSL / TLS, thereby maintaining the privacy and integrity of the data.

[0123] Video data reception and preprocessing

[0124] The server receives the video data sent from the device. After receiving it, it decodes and preprocesses the data. Specifically, it uses libraries such as FFmpeg to split the video data into frames and prepares it in a format that can be analyzed by the AI ​​model. For example, it adjusts the resolution and color.

[0125] Swing form analysis

[0126] The server inputs the preprocessed frame data into an AI model to analyze the swing form. For example, it uses a human pose estimation model such as OpenPose to extract feature points such as shoulders, elbows, and hips for each frame. It then evaluates the swing trajectory, body rotation, and club angle to identify areas that need improvement.

[0127] Feedback Generation

[0128] The server generates feedback for the user based on the analysis results. The generative AI model receives prompts based on the analysis results to provide specific advice. For example, the generated advice might be, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[0129] Send and view feedback

[0130] The server sends the generated feedback to the device. The device then displays the received feedback to the user. At this time, a dedicated application is used to display the feedback in an easy-to-understand manner as text or visual content. For example, the feedback may include an arrow indicating "pull your left shoulder during the backswing" or an image containing supplementary explanations.

[0131] Specific examples

[0132] 1. The user sets up a smartphone on a tripod in their home practice room and records their swing. The camera angle is adjusted so that the full swing is clearly captured on screen.

[0133] 2. After recording, the device automatically compresses the video data in H.264 format and sends it to the server using SSL / TLS encrypted communication.

[0134] 3. The server uses FFmpeg to decode the received video data, split it into frames, adjust the resolution and color, and convert it into a format that is easy for the AI ​​model to analyze.

[0135] 4. The server inputs the frame data into the OpenPose model and extracts feature points such as shoulders, elbows, and hips. It then evaluates the swing trajectory, body rotation, and club angle based on the extracted data.

[0136] 5. The server uses a generative AI model to generate feedback such as, "Your right shoulder isn't rotating enough, so try pulling your left shoulder back more during the backswing."

[0137] 6. The server sends the generated feedback to the device and displays it to the user. The device displays the feedback in text and image format, and the user corrects their swing based on it. By repeating this process, the user can improve their swing form efficiently and effectively.

[0138] Example of input prompt for generative AI model

[0139] "Look at the motion of my golf swing. Evaluate whether my right shoulder is rotating properly, whether the club path is correct, and whether my feet are positioned properly, and provide advice on how to improve my swing form."

[0140] In this way, the present invention provides a specific method for helping users improve their golf skills.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Step 1:

[0143] The user sets up a recording device at a driving range or at home and records their swing. Specifically, the user sets up a smartphone on a tripod and records their swing as a video. The input is a swing video recorded with a smartphone or dedicated camera, and the output is a video file.

[0144] Step 2:

[0145] The device compresses the recorded video file and sends it to the server. At this time, it is encoded in a compression format such as H.264 and uses SSL / TLS encrypted communication. The input is the recorded video file, and the output is compressed and encrypted video data.

[0146] Step 3:

[0147] The server receives the video data sent from the device and performs decoding and preprocessing. Specifically, it uses FFmpeg to divide the video into frames and adjust the resolution and color. The input is compressed and encrypted video data, and the output is preprocessed frame data.

[0148] Step 4:

[0149] The server inputs the preprocessed frame data into the AI ​​model and analyzes the swing form. Specifically, it uses a human body pose estimation model such as OpenPose to extract feature points such as shoulders, elbows, and hips for each frame. The input is the preprocessed frame data, and the output is feature point data.

[0150] Step 5:

[0151] The server evaluates the swing form based on the extracted feature point data and generates feedback. Using the generative AI model, a prompt sentence is input that provides specific advice based on the analysis results. The input is the feature point data and the analysis results, and the output is feedback text. For example, the generated feedback might be, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[0152] Step 6:

[0153] The server sends the generated feedback to the terminal. The terminal displays the received feedback to the user. Using a dedicated application, the feedback is displayed in an easy-to-understand manner as text or visual content. The input is the feedback text, and the output is the feedback displayed to the user. For example, an arrow indicating "pull your left shoulder during the backswing" or an image containing additional explanations is displayed as feedback.

[0154] Step 7:

[0155] The user reviews the feedback and modifies their swing form based on it. They then re-record their modified swing motion and repeat the process from step 1. This allows the user to efficiently and effectively improve their swing form. The input is the modified swing motion, and the output is a new swing form with the modifications.

[0156] (Application example 1)

[0157] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0158] Conventional optimization of industrial machine operations often requires expensive sensors and specialized analytical equipment, or manual evaluation by skilled engineers, resulting in significant increases in cost and time. Furthermore, there is variation in feedback quality, and there is a lack of mechanisms for automatically learning and improving optimal operations. Furthermore, it is difficult to evaluate work operations and provide feedback in real time, hindering efficient automation.

[0159] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0160] In this invention, the server includes means for recording the work operations of the industrial machine using a camera, means for transmitting the recorded video data to the server, means for analyzing the video data and evaluating the work operations, means for generating feedback based on the evaluation results, means for transmitting the feedback to the terminal and displaying it to the user, and means for optimizing the work operations of the industrial machine, thereby making it possible to optimize the work operations of the industrial machine efficiently and with high accuracy.

[0161] A "camera" is a device that captures images of objects, and is an optical instrument that records still images and videos.

[0162] The term "user" refers to a person who uses the system of the present invention to record swing movements and work movements and receives evaluations and feedback.

[0163] "Recorded video data" refers to digital data of moving images and still images recorded by a camera.

[0164] The "server" is a central processing unit that analyzes the recorded video data and generates and transmits evaluations and feedback.

[0165] "Analysis" is the process of extracting movement characteristics from recorded video data and evaluating them.

[0166] "Feedback" refers to evaluation and advice information provided based on the analysis results, with the aim of improving work operations.

[0167] A "terminal" is a device that displays feedback to the user and manages received data.

[0168] "Industrial machinery" refers to machinery and equipment used in factories and production lines that performs specific tasks automatically or semi-automatically.

[0169] A "work action" is a specific movement or procedure performed by industrial machinery that is part of a production process.

[0170] "Work motion evaluation" is a process of evaluating the efficiency and accuracy of work based on the feature points and motion trajectories extracted through analysis.

[0171] "Optimization" is the process of efficiently and accurately adjusting and improving a target operation or process based on this feedback.

[0172] A system for implementing this invention includes a camera, a server, and a terminal, and is used to optimize the operation of industrial machinery. This system evaluates the work operation of the industrial machinery in real time and provides efficient and highly accurate feedback.

[0173] First, a camera is installed on an industrial machine operating in a factory, and its operation is recorded. The camera can be a general-purpose camera such as a Raspberry Pi camera module. The video data recorded by the camera is sent to a server via HTTP communication using a Python script. The data is compressed and encrypted during transmission to ensure security.

[0174] The server receives the recorded video data and performs analysis. This analysis uses machine learning libraries such as TENSORFLOW (registered trademark) and PyTorch to extract characteristic features of the industrial machinery's work movements (for example, joint angles and movement trajectories). Based on the analysis results, problems are identified and feedback is generated. The feedback includes specific improvements and advice.

[0175] The generated feedback is sent from the server to the terminal, which acts as a user device and displays the feedback in text and visual form, and is automatically reflected in the robot's control system, for example, using the MQTT protocol.

[0176] The following hardware and software are used to process this program:

[0177] Camera: Raspberry Pi camera module

[0178] Sending data: Python, Requests library

[0179] Data analysis: TensorFlow, PyTorch, Docker

[0180] Feedback transmission: MQTT protocol

[0181] As a concrete example, consider the case of improving the operation of an assembly robot on a production line. For example, if an issue occurs when attaching a part due to an improper wrist joint angle, the system analyzes the recorded data and generates feedback such as "the wrist angle is 5 degrees too short." The robot's operation program is then updated based on this feedback, resolving the problem.

[0182] As an example of a prompt, you could input the following instructions to a generative AI model:

[0183] "After analyzing the robot's motion, we found that the wrist angle is 5 degrees short. Please explain how to change the settings of the wrist joint module to increase the wrist angle by 5 degrees."

[0184] This allows the generative AI model to provide specific advice on changing settings, resulting in more accurate performance improvements.

[0185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0186] Step 1:

[0187] The user records the operation of industrial machinery with a camera. The camera can be a fixed camera installed in the factory or a camera attached to a robot. The input is the video of the industrial machinery in operation, and the output is the recorded video data. The specific operation involves placing the camera in an appropriate position and pressing a button to start recording the video.

[0188] Step 2:

[0189] The device compresses and encrypts the recorded video data before sending it to the server. The input is the recorded video data, and the output is the compressed and encrypted video data. Specifically, the device uses a Python script to convert the video data into an appropriate format and uploads it to the server using HTTP communication.

[0190] Step 3:

[0191] The server decrypts the received compressed and encrypted video data and performs data analysis. The input is the compressed and encrypted video data, and the output is the analysis results. Specifically, after the decoding process, TensorFlow and PyTorch are used to extract feature points (joint angles, movement trajectories, etc.) from the video and evaluate the movement.

[0192] Step 4:

[0193] The server generates feedback based on the analysis results. The input is the analysis results, and the output is feedback information. Specifically, it automatically generates improvement measures and advice based on problems identified from the analysis results. For example, in response to an evaluation result that "the wrist angle is 5 degrees short," it provides specific advice on how to increase the wrist angle by 5 degrees.

[0194] Step 5:

[0195] The server sends the generated feedback to the terminal and displays it to the user. The input is the feedback information, and the output is the feedback displayed on the user's terminal. Specifically, the server converts the feedback information into text or visual format and sends it to the terminal.

[0196] Step 6:

[0197] The terminal displays the received feedback information to the user and reflects it in the robot's control system. The input is the feedback information sent from the server, and the output is a control program that reflects the feedback. Specifically, the terminal displays the feedback content on the screen, sends instructions to the robot control system using the MQTT protocol, and updates the program.

[0198] Step 7:

[0199] The user re-records the operation of the industrial machine based on the updated control program and confirms the optimized operation. The input is the updated control program, and the output is the re-recorded video data and the operation evaluation results. Specifically, the operation video is recorded again with a camera, and the process is repeated from the first step 1.

[0200] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0201] This invention is a system aimed at improving golf swing skills. It not only analyzes the user's swing motion captured on a camera in real time and provides feedback, but also combines it with an emotion engine that recognizes the user's emotions to provide feedback that takes into account the user's motivation and mental state.

[0202] Overview of program processing

[0203] Data collection

[0204] Users set up a camera at a driving range or at home to record their swing. The camera can be any device, such as a smartphone or a dedicated camera. The emotion engine analyzes the user's emotions in real time from the camera footage and audio data.

[0205] Video data transmission

[0206] The device sends the recorded video data and emotion data to a server. The data is sent in a compressed and encrypted format, ensuring security.

[0207] Receiving and analyzing video data

[0208] The server receives the video and emotion data sent from the device and begins analyzing the swing form using an AI model. During the analysis, human body features (shoulders, elbows, hips, etc.) are extracted for each frame of video, and the swing trajectory, body rotation, club angle, etc. are evaluated. In addition, the emotion engine analyzes the user's emotional state.

[0209] Feedback Generation

[0210] The server generates feedback for the user based on the analysis results. The feedback includes identifying problems and providing specific advice for improvement. Furthermore, by taking emotional data into consideration, feedback appropriate to the user's mental state can be provided. For example, if the user is feeling tense, advice to relax may be added.

[0211] Send and view feedback

[0212] The server sends the generated feedback to the device, which then displays it to the user. The feedback is displayed as text and visual content, allowing the user to refer to it and correct their swing form. Additional advice based on emotion data is also displayed.

[0213] Specific examples

[0214] 1. The user takes a swing in their home practice room. The user sets up their smartphone on a tripod and records their swing. The camera and microphone are used to record the swing, and the user's facial expressions and voice are also captured.

[0215] 2. After recording, the device automatically sends the video and emotion data to the server. The data is appropriately compressed and encrypted before being sent.

[0216] 3. The server analyzes the received video data and emotional data to extract the swing form features and the user's emotional state, such as shoulder movement, hip rotation, and club trajectory.

[0217] 4. Based on the analysis results, the server generates feedback such as, "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing." In addition, if it determines that the user is tense, it also adds advice such as, "Take a deep breath and relax."

[0218] 5. The server sends the generated feedback to the device and displays it to the user in real time. The device displays the feedback in text and image format, allowing the user to correct their swing based on that feedback. Emotion-based advice is also displayed simultaneously.

[0219] 6. After reviewing the feedback, the user re-records a new swing with corrections and submits it to the system, which then receives new analysis and feedback. By repeating this process, the user can efficiently and effectively improve their swing form.

[0220] In this way, the present invention not only provides a specific system for supporting the improvement of a user's golf skills, but also, by combining it with an emotion engine, enables feedback that takes into account the user's mental state, allowing the user to properly understand their own swing form and continue practicing with peace of mind, even without guidance from a professional coach.

[0221] The processing flow will be explained below.

[0222] Program processing steps

[0223] Step 1: Video recording and emotional data acquisition

[0224] User:

[0225] The camera and microphone are placed in appropriate positions to record your swing, facial expressions, and voice. The camera and microphone can be a smartphone or a dedicated device.

[0226] Step 2: Sending video data and emotion data

[0227] Device:

[0228] The recorded video data and emotion data are sent to the server in a compressed and encrypted format, and a notification is sent when the data is complete.

[0229] Step 3: Receiving video and emotion data

[0230] server:

[0231] Receives video data and emotion data sent from the device. After receiving, checks the data for consistency and format.

[0232] Step 4: Preprocessing

[0233] server:

[0234] The received video data is processed before analysis. Specifically, frames are extracted, resolution is adjusted, and noise is removed as necessary. Emotion data is also converted into an analyzable format.

[0235] Step 5: Feature point extraction

[0236] server:

[0237] It uses an AI model to extract human body features from each frame of video, pinpointing the positions of shoulders, elbows, hips, etc., and analyzing their movements.

[0238] Step 6: Sentiment Analysis

[0239] server:

[0240] An emotion engine is used to analyze the user's emotional state from recorded facial expressions and voice, identifying states such as tension, excitement, and relaxation.

[0241] Step 7: Form evaluation and emotional alignment

[0242] server:

[0243] Based on the extracted features, the system evaluates the user's swing form, including swing trajectory, body balance, and club position, while also taking into account their emotional state.

[0244] Step 8: Identify the problem

[0245] server:

[0246] Based on form evaluation and emotion analysis results, it identifies which part of the swing is problematic. For example, it identifies "insufficient rotation of the right shoulder" and takes into account if the user is tense.

[0247] Step 9: Advice Generation

[0248] server:

[0249] Based on the identified issues and the user's emotional state, the system generates specific feedback for improvement, such as "Try to pull your left shoulder back during the backswing to increase the rotation of your right shoulder. Take a deep breath to relax."

[0250] Step 10: Send feedback

[0251] server:

[0252] Sends generated feedback to the device, including textual and visual guides.

[0253] Step 11: Feedback display

[0254] Device:

[0255] The feedback sent from the server is received and displayed to the user, who can see frame-by-frame images of problematic swings and emotion-based advice along with specific advice.

[0256] Step 12: User confirmation and correction

[0257] User:

[0258] Check the feedback displayed on your device and modify your next swing based on it. Try a new swing based on the feedback and emotional advice.

[0259] Step 13: Continuing the improvement process

[0260] User:

[0261] The corrected swing is then recorded again and the process is repeated from step 1. The user utilizes feedback and emotional advice to continually improve their skills.

[0262] By repeating this series of steps, users can improve their swing form accurately and efficiently, and continue practicing with peace of mind.

[0263] Example 2

[0264] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0265] Conventional golf swing training systems focus only on the user's swing form and are unable to provide feedback that takes into account the user's mental state or motivation, resulting in limited improvement. Furthermore, the feedback provided is uniform, and individualized responses to each user are insufficient. This makes it difficult to effectively improve a user's swing form and also lacks motivation to continue practicing over the long term.

[0266] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving video data and emotion data, means for analyzing the received data and evaluating the swing form, means for analyzing the user's emotion state using an emotion engine, means for generating feedback for the user based on the analysis results, and means for transmitting the feedback to the terminal and displaying it to the user. This makes it possible to provide feedback that takes into account not only the user's swing form but also their mental state and motivation, enabling effective skill improvement and motivation for continuous practice.

[0267] A "camera" is an optical device for recording a user's swing motion.

[0268] A "terminal" is an electronic device that transmits recorded video data and emotional data to a server and displays feedback to the user.

[0269] The "server" is a centralized management system for receiving video data and emotion data, analyzing them, and generating feedback.

[0270] "Video data" is video information of the user's swing motion captured by a camera.

[0271] "Emotion data" is information that indicates the emotional state of the user based on sensor data from a camera, microphone, etc.

[0272] An "emotion engine" is software or an algorithm for analyzing a user's emotional state from video and audio data.

[0273] "Swing form" refers to the configuration of each part of the body, such as the position and angle, during a user's golf swing motion.

[0274] "Feedback" is information that includes advice on improving the user's swing form and depending on the user's emotional state based on the analysis results.

[0275] A "generative AI model" is an artificial intelligence model trained to generate feedback based on a user's swing form and emotional state.

[0276] MODE FOR CARRYING OUT THE INVENTION

[0277] This invention is a system aimed at improving a user's golf swing skills, analyzing the user's swing motion captured by a camera in real time and providing feedback. Furthermore, by combining it with an emotion engine, it is possible to provide feedback that takes into account the user's motivation and mental state. This system is described in detail below.

[0278] Hardware and software used

[0279] The user records their swing using a smartphone or a dedicated camera. This allows for the acquisition of video data. Audio data can also be collected using a microphone. This recording device can be any commercially available camera or microphone.

[0280] The device is an electronic device that transmits the recorded video data and emotion data to the server. This device can be a typical smartphone, tablet, or PC. An application for collecting data is installed on the device, and it has the function of compressing and encrypting the recorded data before transmitting it to the server.

[0281] The server is a centralized management system that analyzes the received video and emotion data and generates feedback, and can use high-performance computers and cloud services. A generative AI model and emotion engine are used for the analysis. The generative AI model analyzes and evaluates the swing form, and the emotion engine analyzes the user's emotional state from the video and audio data.

[0282] Data processing and calculation

[0283] When the server receives the video and emotion data sent from the device, it first preprocesses the data. This preprocessing involves dividing the video data into frames and extracting human body features (shoulders, elbows, hips, etc.) from each frame. Next, it uses a generative AI model to analyze the swing form and evaluate the swing trajectory, body rotation, club angle, etc.

[0284] At the same time, an emotion engine is used to analyze the user's emotional data. For example, emotional states such as tension, joy, or irritation can be detected from the user's facial expressions and tone of voice. This allows the user's mental state to be understood.

[0285] The server generates feedback based on the analysis results. This feedback identifies problems with the swing form and includes specific advice for improvement. Furthermore, by taking emotional data into consideration, feedback appropriate to the user's mental state is provided. For example, if the right shoulder rotation is insufficient, the server generates advice such as "Try pulling your left shoulder back a bit more during the backswing." Furthermore, if the user is feeling tense, the server adds advice such as "Take a deep breath and relax."

[0286] The generated feedback is sent to the device and displayed to the user as text and visual content, allowing the user to refer to it and correct their swing form.

[0287] Specific examples

[0288] 1. The user sets up their smartphone on a tripod in their home practice room and records their swing. The camera and microphone are used to record the user's facial expressions and voice.

[0289] 2. After recording, the device automatically transmits the video and emotion data to the server, where the data is compressed and encrypted.

[0290] 3. The server uses the received data to extract and analyze the swing form's characteristics, such as shoulder movement, hip rotation, and club trajectory.

[0291] 4. The emotion engine analyzes the user's emotional state from video and audio data and detects when the user is nervous.

[0292] 5. Based on the analysis results, the server generates feedback such as "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing," along with advice such as "Take a deep breath and relax."

[0293] 6. This feedback is sent to the device and displayed to the user in real time, allowing the user to refer to it to correct their swing form and continue practicing.

[0294] Prompt Sentence Examples

[0295] "Please describe a system that analyzes video footage of a user's golf swing and emotional data to provide feedback."

[0296] This system analyzes the user's movements and emotions in real time and provides appropriate feedback to improve the user's golf skills. By using an emotion engine, it is possible to provide instruction that takes into account the user's mental state.

[0297] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0298] Step 1: Data collection

[0299] A user sets up a camera at a driving range or at home and records their swing. For example, a user mounts a smartphone on a tripod, launches a camera app, and records their swing. The input data is video data and audio data. The output data is the recorded video and audio files. The user's facial expressions and voice are also collected during recording.

[0300] Step 2: Send data

[0301] After recording is complete, the device automatically transmits the video and emotion data to the server. At this time, the device first compresses and encrypts the data. For example, the video data is compressed in H.264 format and encrypted using AES. The input data are the recorded video and audio files. The output data is the compressed and encrypted data, which is then transmitted to the server via the Internet.

[0302] Step 3: Data reception and preprocessing

[0303] The server receives data sent from the terminal. After receiving the data, it first decompresses and decrypts it. For example, it decrypts AES-encrypted data and decompresses H.264-compressed data. The input data is the compressed and encrypted data. The output data is the original video and audio files.

[0304] Step 4: Swing form analysis

[0305] The server analyzes the video file frame by frame and extracts the body's feature points (shoulders, elbows, hips, etc.). For example, it uses the OpenPose library to identify the coordinates of each body part. The input data is the video file. The output data is the feature point coordinate data for each frame. Based on this data, the swing trajectory, body rotation, club angle, etc. are evaluated. Furthermore, analysis is performed using a generative AI model, enabling highly accurate evaluation.

[0306] Step 5: Sentiment Analysis

[0307] The server analyzes the user's emotional state from audio and video files. For example, audio analysis uses TensorFlow or OpenSMILE to analyze the tone and speed of the voice, and video analysis uses a facial expression recognition algorithm (e.g., FaceAPI) to identify the user's emotions. The input data are audio and video files. The output data is the analyzed emotional state information (e.g., joy, anger, tension, etc.).

[0308] Step 6: Feedback generation

[0309] The server generates feedback for the user based on the results of the swing form analysis and emotion analysis. For example, it generates technical advice such as "Your right shoulder rotation is insufficient, so try pulling your left shoulder back a bit more during your backswing," or emotion-based advice such as "Take a deep breath and relax." The input data are feature point coordinate data of the swing form and emotional state information. The output data is a feedback message.

[0310] Step 7: Send and view feedback

[0311] The server sends the generated feedback to the terminal. For example, data is sent using secure HTTP communication (HTTPS). The input data is the feedback message. The output data is the feedback message sent to the terminal. The terminal displays the received feedback to the user. The display format is provided as text and image content. For example, the application displays the text "Your right shoulder rotation is insufficient" along with an illustration showing the corresponding movement. The user can then correct their swing form based on this.

[0312] (Application example 2)

[0313] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0314] Robots performing various tasks in factories lack appropriate feedback to improve the efficiency and accuracy of their operations. Furthermore, there is a lack of means to analyze the robot's behavior and the causes of errors in real time and determine the need for maintenance or updates. This leads to problems such as reduced work efficiency and delays in maintenance, which can easily lead to problems.

[0315] The specific processing 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 user's swing motion with a camera, means for transmitting the recorded video data to the server, means for analyzing the video data and evaluating the swing form, means for analyzing the robot's motion in real time and generating feedback to improve the accuracy and efficiency of the motion, means for monitoring the robot's status and providing appropriate maintenance advice, and means for transmitting the feedback to the terminal and displaying it to the user. This makes it possible to analyze the robot's motion in real time and provide feedback to improve efficiency and accuracy, as well as to monitor the robot's status and perform appropriate maintenance.

[0316] A "camera" is a video device used to record the actions of the user or robot.

[0317] "Recorded video data" refers to video data collected by a camera.

[0318] A "server" is a computer system that receives and analyzes recorded video data.

[0319] "Swing form evaluation" refers to analyzing the user's swing motion based on the recorded video data and determining whether it is good or bad.

[0320] "Feedback" refers to advice or instructions provided to the user or robot based on the analysis results.

[0321] "Real-time" means that processing is done almost simultaneously and the results are reflected immediately.

[0322] "Robot movement analysis" refers to the detailed analysis of a robot's movements using recorded video data.

[0323] "Motion accuracy" is an index that indicates how accurate a robot's movements are relative to set goals or standards.

[0324] "Operation efficiency" is a measure of how efficiently a robot works to achieve its objectives.

[0325] "Maintenance advice" involves analyzing the robot's operation and condition and proposing necessary maintenance and repairs.

[0326] "Terminals" are devices that users and engineers use to receive feedback, such as computers and smartphones.

[0327] "Transmitting video data" means transferring the recorded video data to a server via a network.

[0328] "Feedback to improve the accuracy and efficiency of movements" refers to feedback that includes instructions and advice to make the robot's movements more accurate and efficient.

[0329] "Robot status" refers to the operational status of the robot, such as how it is currently operating and whether any errors have occurred.

[0330] "Users" are people or engineers who use the system and receive feedback.

[0331] A system for realizing this invention includes a camera, a server, a terminal, and dedicated software. The system program records user actions with the camera, transmits the recorded video data to the server, analyzes the data, transmits generated feedback to the terminal, and displays the feedback.

[0332] The server receives video footage of the user's movements captured by the camera and analyzes the video data in real time using OpenCV. Feature extraction uses an algorithm that recognizes the user's shoulders, elbows, waist, etc. from the video. The software used is OpenCV for video processing and TensorFlow for loading the machine learning model.

[0333] In particular, the server analyzes recorded video and real-time feeds using an emotion engine powered by TensorFlow. This emotion engine recognizes the user's emotions in real time from camera footage and audio data, enabling feedback that takes into account the user's mental state.

[0334] As an example, consider the analysis of the movements of a robot working in a factory. A camera records the robot's movements and sends the recorded video data to a server. The server receives the video data, analyzes it using OpenCV, and evaluates the robot's movement accuracy and efficiency. It then uses an emotion engine to analyze the robot's condition and the cause of any movement errors, and generates necessary maintenance advice. As a result, specific advice such as "correct the angle of the arm" or "perform regular maintenance" is sent as feedback and displayed on the terminal.

[0335] An example of a prompt is as follows:

[0336] "Analyze the robot's working movements, generate optimal movement patterns, and provide feedback. Also, monitor the robot's condition and provide appropriate maintenance advice. The video of the robot's movements contains key feature point data such as shoulders, elbows, and waists. Generate movement feedback based on the feature point data, and perform emotion analysis using an emotion recognition engine."

[0337] Based on this prompt, the generative AI model generates specific feedback, enabling the system to provide real-time behavioral feedback and emotion-based advice to the user.

[0338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0339] Step 1:

[0340] The user installs a camera and records the robot's movements. For example, a Logitech HD Pro Webcam C920 is used as the camera. The input is the recorded video and audio data. The output is real-time video and audio data acquired from the camera.

[0341] Step 2:

[0342] The device sends the recorded video and audio data to the server. When sending the data, it is appropriately compressed and encrypted. The input is the video and audio data acquired from the camera. The output is the compressed and encrypted video and audio data.

[0343] Step 3:

[0344] The server analyzes the received video data in real time using OpenCV. This analysis extracts feature points from each part of the robot (e.g., shoulders, elbows, waist, etc.) for each video frame. The input is compressed and encrypted video data sent from the terminal. The output is the analysis results, including feature point data.

[0345] Step 4:

[0346] The server uses an emotion engine based on TensorFlow to recognize the robot's state from video and audio data. This analysis determines whether the robot is operating normally or if an error has occurred. The input is feature point data and audio data. The output is the analysis result regarding the robot's state.

[0347] Step 5:

[0348] The server evaluates the accuracy and efficiency of the robot's movements based on the analysis results and generates feedback. Specifically, it generates feedback indicating where movement corrections and maintenance are needed. The input is the analysis results from the video data analysis and emotion engine. The output is the generated feedback.

[0349] Step 6:

[0350] The server sends the generated feedback to the terminal. The terminal displays the received feedback to the user in text and / or visual form. The input is the generated feedback. The output is the transmission and display of the feedback data to the terminal.

[0351] Step 7:

[0352] The user reviews the feedback and adjusts the robot's behavior as necessary. The user also creates a maintenance plan for the next maintenance based on the feedback. The input is the feedback content. The output is the revised robot's behavior and maintenance plan.

[0353] Step 8:

[0354] The device re-records the modified robot's movements and transmits the new video data to the server, starting a new analysis and feedback cycle. The input is the video of the modified robot's movements. The output is the transmission of the re-recorded video data.

[0355] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0356] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0357] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0358] [Second embodiment]

[0359] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0360] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0361] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0362] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0363] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0364] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0365] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0366] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0367] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0368] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0369] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0370] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0371] This invention is a system aimed at improving golf swing skills, and helps improve swing form by analyzing the user's swing motion recorded on a camera in real time and providing feedback.

[0372] Overview of program processing

[0373] Data collection

[0374] The user sets up a camera at a driving range or at home and records their swing. The camera can be any camera device, such as a smartphone or a dedicated camera.

[0375] Video data transmission

[0376] The device sends the recorded video data to the server. The video data is sent in a compressed and encrypted format, ensuring security.

[0377] Receiving and analyzing video data

[0378] The server receives the video data sent from the device and begins analyzing the swing form using an AI model. During the analysis, the characteristic points of the human body (shoulders, elbows, hips, etc.) are extracted for each frame of the video, and the swing trajectory, body rotation, club angle, etc. are evaluated.

[0379] Feedback Generation

[0380] The server generates feedback for the user based on the analysis results. The feedback includes identifying the problem and providing specific advice for improvement. For example, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[0381] Send and view feedback

[0382] The server sends the generated feedback to the device, which then displays it to the user. The feedback is displayed as text or visual content, and the user can refer to it to correct their swing form.

[0383] Specific examples

[0384] 1. The user swings in their home practice room. The user sets up their smartphone on a tripod and records their swing.

[0385] 2. After recording, the device automatically sends the video data to the server. The data is properly compressed and encrypted before being sent.

[0386] 3. The server analyzes the received video data and extracts the swing form's characteristics, such as shoulder movement, hip rotation, and club trajectory.

[0387] 4. Based on the analysis results, the server generates feedback such as, "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing."

[0388] 5. The server sends the generated feedback to the device and displays it to the user in real time. The device displays the feedback in text and image format, allowing the user to correct their swing based on it.

[0389] 6. After reviewing the feedback, the user re-records a new swing with corrections and submits it to the system, which then receives new analysis and feedback. By repeating this process, the user can efficiently and effectively improve their swing form.

[0390] In this way, the present invention provides a specific system for supporting users in improving their golf skills, allowing users to properly understand their own swing form and efficiently improve their skills without the need for guidance from a professional coach.

[0391] The processing flow will be explained below.

[0392] Program processing steps

[0393] Step 1: Recording

[0394] User:

[0395] Set up the camera in an appropriate position and record your swing using a smartphone or dedicated camera.

[0396] Step 2: Sending video data

[0397] Device:

[0398] The recorded video data is sent to the server in a compressed and encrypted format to ensure security.

[0399] Step 3: Receiving video data

[0400] server:

[0401] Receives video data sent from the terminal. After receiving, checks the data for consistency and format.

[0402] Step 4: Preprocessing

[0403] server:

[0404] The received video data is processed before analysis, specifically by extracting frames, adjusting resolution, and removing noise if necessary.

[0405] Step 5: Feature point extraction

[0406] server:

[0407] An AI model is used to extract body features (shoulders, elbows, hips, etc.) from each frame, providing data for specific analysis of swing form movements.

[0408] Step 6: Form evaluation

[0409] server:

[0410] The user's swing form is evaluated based on the extracted feature points, including the swing trajectory, body balance, and club position.

[0411] Step 7: Identify the problem

[0412] server:

[0413] Based on the evaluation results, problems with the swing form are identified. For example, specific areas such as "insufficient rotation of the right shoulder" are identified.

[0414] Step 8: Advice Generation

[0415] server:

[0416] It generates specific advice for improvement based on identified problems, such as "Try to pull your left shoulder back during the backswing to increase the rotation of your right shoulder."

[0417] Step 9: Send your feedback

[0418] server:

[0419] Send the generated feedback to the device, which may include textual and / or visual guidance.

[0420] Step 10: Feedback display

[0421] Device:

[0422] The system receives feedback sent from the server and displays it to the user, including frame-by-frame images of problematic swings along with specific advice.

[0423] Step 11: User confirmation and correction

[0424] User:

[0425] Check the feedback displayed on your device and use it to modify your next swing. Use the feedback to try a new swing.

[0426] Step 12: Continuing the improvement process

[0427] User:

[0428] The corrected swing is then filmed again and the process is repeated from step 1. The user utilizes the feedback to continually improve their skills.

[0429] By repeating this series of steps, the user can improve their swing form accurately and efficiently.

[0430] Example 1

[0431] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0432] Current methods for improving golf swing skills (e.g., video analysis and direct instruction from a coach) are expensive and have the drawback of not providing real-time feedback. Therefore, there is a need for a system that allows users to easily analyze their swing form at home or at a driving range and receive real-time feedback. Furthermore, the difficulty of providing optimized feedback for each individual user is also an issue that needs to be resolved.

[0433] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0434] In this invention, the server includes a means for using a camera to record the user's movements, a means for transmitting the data recorded by the camera to an information processing device, a means for analyzing the data and evaluating the movements in the information processing device, a means for generating feedback for the user based on the evaluation results, and a means for transmitting the feedback to the terminal and displaying it to the user. This allows users to easily analyze their own swing form and receive efficient feedback. Furthermore, feedback generated using an artificial intelligence model can provide advice optimized for each individual user in real time.

[0435] "Capture device" refers to a camera or video recording device for recording a user's actions.

[0436] "Information processing device" refers to a computer or server that receives and analyzes the recorded data.

[0437] "User" refers to an individual who uses the system to analyze their swing form and receive feedback.

[0438] "Data" refers to video information of the user's swing motion captured by a camera.

[0439] "Analysis" refers to a process in which an information processing device processes data to extract and evaluate features of a user's actions.

[0440] "Evaluation" refers to the act of judging whether a user's behavior is good or bad based on the analyzed data and identifying areas for improvement.

[0441] "Feedback" refers to advice or guidance provided to the user based on the evaluation results.

[0442] "Device" refers to the device (such as a smartphone or tablet) that a user uses to receive feedback.

[0443] "Artificial intelligence model" refers to the machine learning and deep learning algorithms used to analyze data and generate feedback.

[0444] "Evaluation results" refer to information about the user's behavior and diagnostic results derived during the analysis process.

[0445] "Means using a photographing device" refers to the act of a user recording their own swing motion with a video or camera.

[0446] "Transmitting means" refers to the process of transferring data from the image capture device to the information processing device.

[0447] "Means for displaying" refers to a method for conveying feedback to the user visually or audibly.

[0448] This invention is a system aimed at improving golf swing skills, and helps improve swing form by analyzing the user's swing motion recorded on a camera in real time and providing feedback.

[0449] System configuration

[0450] Data collection

[0451] The user sets up a camera at a driving range or at home and records their swing. The camera can be any type of camera, such as a smartphone or a dedicated camera. For example, the user sets up their smartphone on a tripod and records their swing. A frame rate of at least 30 fps is recommended for recording.

[0452] Video data transmission

[0453] The device (such as a smartphone or dedicated camera) transmits the recorded video data to the server. At this time, the video data is encoded in a compressed format such as H.264 and transmitted over an encrypted communication channel using SSL / TLS, thereby maintaining the privacy and integrity of the data.

[0454] Video data reception and preprocessing

[0455] The server receives the video data sent from the device. After receiving it, it decodes and preprocesses the data. Specifically, it uses libraries such as FFmpeg to split the video data into frames and prepares it in a format that can be analyzed by the AI ​​model. For example, it adjusts the resolution and color.

[0456] Swing form analysis

[0457] The server inputs the preprocessed frame data into an AI model to analyze the swing form. For example, it uses a human pose estimation model such as OpenPose to extract feature points such as shoulders, elbows, and hips for each frame. It then evaluates the swing trajectory, body rotation, and club angle to identify areas that need improvement.

[0458] Feedback Generation

[0459] The server generates feedback for the user based on the analysis results. The generative AI model receives prompts based on the analysis results to provide specific advice. For example, the generated advice might be, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[0460] Send and view feedback

[0461] The server sends the generated feedback to the device. The device then displays the received feedback to the user. At this time, a dedicated application is used to display the feedback in an easy-to-understand manner as text or visual content. For example, the feedback may include an arrow indicating "pull your left shoulder during the backswing" or an image containing supplementary explanations.

[0462] Specific examples

[0463] 1. The user sets up a smartphone on a tripod in their home practice room and records their swing. The camera angle is adjusted so that the full swing is clearly captured on screen.

[0464] 2. After recording, the device automatically compresses the video data in H.264 format and sends it to the server using SSL / TLS encrypted communication.

[0465] 3. The server uses FFmpeg to decode the received video data, split it into frames, adjust the resolution and color, and convert it into a format that is easy for the AI ​​model to analyze.

[0466] 4. The server inputs the frame data into the OpenPose model and extracts feature points such as shoulders, elbows, and hips. It then evaluates the swing trajectory, body rotation, and club angle based on the extracted data.

[0467] 5. The server uses a generative AI model to generate feedback such as, "Your right shoulder isn't rotating enough, so try pulling your left shoulder back more during the backswing."

[0468] 6. The server sends the generated feedback to the device and displays it to the user. The device displays the feedback in text and image format, and the user corrects their swing based on it. By repeating this process, the user can improve their swing form efficiently and effectively.

[0469] Example of input prompt for generative AI model

[0470] "Look at the motion of my golf swing. Evaluate whether my right shoulder is rotating properly, whether the club path is correct, and whether my feet are positioned properly, and provide advice on how to improve my swing form."

[0471] In this way, the present invention provides a specific method for helping users improve their golf skills.

[0472] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0473] Step 1:

[0474] The user sets up a recording device at a driving range or at home and records their swing. Specifically, the user sets up a smartphone on a tripod and records their swing as a video. The input is a swing video recorded with a smartphone or dedicated camera, and the output is a video file.

[0475] Step 2:

[0476] The device compresses the recorded video file and sends it to the server. At this time, it is encoded in a compression format such as H.264 and uses SSL / TLS encrypted communication. The input is the recorded video file, and the output is compressed and encrypted video data.

[0477] Step 3:

[0478] The server receives the video data sent from the device and performs decoding and preprocessing. Specifically, it uses FFmpeg to divide the video into frames and adjust the resolution and color. The input is compressed and encrypted video data, and the output is preprocessed frame data.

[0479] Step 4:

[0480] The server inputs the preprocessed frame data into the AI ​​model and analyzes the swing form. Specifically, it uses a human body pose estimation model such as OpenPose to extract feature points such as shoulders, elbows, and hips for each frame. The input is the preprocessed frame data, and the output is feature point data.

[0481] Step 5:

[0482] The server evaluates the swing form based on the extracted feature point data and generates feedback. Using the generative AI model, a prompt sentence is input that provides specific advice based on the analysis results. The input is the feature point data and the analysis results, and the output is feedback text. For example, the generated feedback might be, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[0483] Step 6:

[0484] The server sends the generated feedback to the terminal. The terminal displays the received feedback to the user. Using a dedicated application, the feedback is displayed in an easy-to-understand manner as text or visual content. The input is the feedback text, and the output is the feedback displayed to the user. For example, an arrow indicating "pull your left shoulder during the backswing" or an image containing additional explanations is displayed as feedback.

[0485] Step 7:

[0486] The user reviews the feedback and modifies their swing form based on it. They then re-record their modified swing motion and repeat the process from step 1. This allows the user to efficiently and effectively improve their swing form. The input is the modified swing motion, and the output is a new swing form with the modifications.

[0487] (Application example 1)

[0488] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0489] Conventional optimization of industrial machine operations often requires expensive sensors and specialized analytical equipment, or manual evaluation by skilled engineers, resulting in significant increases in cost and time. Furthermore, there is variation in feedback quality, and there is a lack of mechanisms for automatically learning and improving optimal operations. Furthermore, it is difficult to evaluate work operations and provide feedback in real time, hindering efficient automation.

[0490] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0491] In this invention, the server includes means for recording the work operations of the industrial machine using a camera, means for transmitting the recorded video data to the server, means for analyzing the video data and evaluating the work operations, means for generating feedback based on the evaluation results, means for transmitting the feedback to the terminal and displaying it to the user, and means for optimizing the work operations of the industrial machine, thereby making it possible to optimize the work operations of the industrial machine efficiently and with high accuracy.

[0492] A "camera" is a device that captures images of objects, and is an optical instrument that records still images and videos.

[0493] The term "user" refers to a person who uses the system of the present invention to record swing movements and work movements and receives evaluations and feedback.

[0494] "Recorded video data" refers to digital data of moving images and still images recorded by a camera.

[0495] The "server" is a central processing unit that analyzes the recorded video data and generates and transmits evaluations and feedback.

[0496] "Analysis" is the process of extracting movement characteristics from recorded video data and evaluating them.

[0497] "Feedback" refers to evaluation and advice information provided based on the analysis results, with the aim of improving work operations.

[0498] A "terminal" is a device that displays feedback to the user and manages received data.

[0499] "Industrial machinery" refers to machinery and equipment used in factories and production lines that performs specific tasks automatically or semi-automatically.

[0500] A "work action" is a specific movement or procedure performed by industrial machinery that is part of a production process.

[0501] "Work motion evaluation" is a process of evaluating the efficiency and accuracy of work based on the feature points and motion trajectories extracted through analysis.

[0502] "Optimization" is the process of efficiently and accurately adjusting and improving a target operation or process based on this feedback.

[0503] A system for implementing this invention includes a camera, a server, and a terminal, and is used to optimize the operation of industrial machinery. This system evaluates the work operation of the industrial machinery in real time and provides efficient and highly accurate feedback.

[0504] First, a camera is installed on an industrial machine operating in a factory, and its operation is recorded. The camera can be a general-purpose camera such as a Raspberry Pi camera module. The video data recorded by the camera is sent to a server via HTTP communication using a Python script. The data is compressed and encrypted during transmission to ensure security.

[0505] The server receives and analyzes the recorded video data. This analysis uses machine learning libraries such as TensorFlow and PyTorch to extract characteristic features of the industrial machinery's work movements (for example, joint angles and movement trajectories). Based on the analysis results, problems are identified and feedback is generated. The feedback includes specific improvements and advice.

[0506] The generated feedback is sent from the server to the terminal, which acts as a user device and displays the feedback in text and visual form, and is automatically reflected in the robot's control system, for example, using the MQTT protocol.

[0507] The following hardware and software are used to process this program:

[0508] Camera: Raspberry Pi camera module

[0509] Sending data: Python, Requests library

[0510] Data analysis: TensorFlow, PyTorch, Docker

[0511] Feedback transmission: MQTT protocol

[0512] As a concrete example, consider the case of improving the operation of an assembly robot on a production line. For example, if an issue occurs when attaching a part due to an improper wrist joint angle, the system analyzes the recorded data and generates feedback such as "the wrist angle is 5 degrees too short." The robot's operation program is then updated based on this feedback, resolving the problem.

[0513] As an example of a prompt, you could input the following instructions to a generative AI model:

[0514] "After analyzing the robot's motion, we found that the wrist angle is 5 degrees short. Please explain how to change the settings of the wrist joint module to increase the wrist angle by 5 degrees."

[0515] This allows the generative AI model to provide specific advice on changing settings, resulting in more accurate performance improvements.

[0516] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0517] Step 1:

[0518] The user records the operation of industrial machinery with a camera. The camera can be a fixed camera installed in the factory or a camera attached to a robot. The input is the video of the industrial machinery in operation, and the output is the recorded video data. The specific operation involves placing the camera in an appropriate position and pressing a button to start recording the video.

[0519] Step 2:

[0520] The device compresses and encrypts the recorded video data before sending it to the server. The input is the recorded video data, and the output is the compressed and encrypted video data. Specifically, the device uses a Python script to convert the video data into an appropriate format and uploads it to the server using HTTP communication.

[0521] Step 3:

[0522] The server decrypts the received compressed and encrypted video data and performs data analysis. The input is the compressed and encrypted video data, and the output is the analysis results. Specifically, after the decoding process, TensorFlow and PyTorch are used to extract feature points (joint angles, movement trajectories, etc.) from the video and evaluate the movement.

[0523] Step 4:

[0524] The server generates feedback based on the analysis results. The input is the analysis results, and the output is feedback information. Specifically, it automatically generates improvement measures and advice based on problems identified from the analysis results. For example, in response to an evaluation result that "the wrist angle is 5 degrees short," it provides specific advice on how to increase the wrist angle by 5 degrees.

[0525] Step 5:

[0526] The server sends the generated feedback to the terminal and displays it to the user. The input is the feedback information, and the output is the feedback displayed on the user's terminal. Specifically, the server converts the feedback information into text or visual format and sends it to the terminal.

[0527] Step 6:

[0528] The terminal displays the received feedback information to the user and reflects it in the robot's control system. The input is the feedback information sent from the server, and the output is a control program that reflects the feedback. Specifically, the terminal displays the feedback content on the screen, sends instructions to the robot control system using the MQTT protocol, and updates the program.

[0529] Step 7:

[0530] The user re-records the operation of the industrial machine based on the updated control program and confirms the optimized operation. The input is the updated control program, and the output is the re-recorded video data and the operation evaluation results. Specifically, the operation video is recorded again with a camera, and the process is repeated from the first step 1.

[0531] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0532] This invention is a system aimed at improving golf swing skills. It not only analyzes the user's swing motion captured on a camera in real time and provides feedback, but also combines it with an emotion engine that recognizes the user's emotions to provide feedback that takes into account the user's motivation and mental state.

[0533] Overview of program processing

[0534] Data collection

[0535] Users set up a camera at a driving range or at home to record their swing. The camera can be any device, such as a smartphone or a dedicated camera. The emotion engine analyzes the user's emotions in real time from the camera footage and audio data.

[0536] Video data transmission

[0537] The device sends the recorded video data and emotion data to a server. The data is sent in a compressed and encrypted format, ensuring security.

[0538] Receiving and analyzing video data

[0539] The server receives the video and emotion data sent from the device and begins analyzing the swing form using an AI model. During the analysis, human body features (shoulders, elbows, hips, etc.) are extracted for each frame of video, and the swing trajectory, body rotation, club angle, etc. are evaluated. In addition, the emotion engine analyzes the user's emotional state.

[0540] Feedback Generation

[0541] The server generates feedback for the user based on the analysis results. The feedback includes identifying problems and providing specific advice for improvement. Furthermore, by taking emotional data into consideration, feedback appropriate to the user's mental state can be provided. For example, if the user is feeling tense, advice to relax may be added.

[0542] Send and view feedback

[0543] The server sends the generated feedback to the device, which then displays it to the user. The feedback is displayed as text and visual content, allowing the user to refer to it and correct their swing form. Additional advice based on emotion data is also displayed.

[0544] Specific examples

[0545] 1. The user takes a swing in their home practice room. The user sets up their smartphone on a tripod and records their swing. The camera and microphone are used to record the swing, and the user's facial expressions and voice are also captured.

[0546] 2. After recording, the device automatically sends the video and emotion data to the server. The data is appropriately compressed and encrypted before being sent.

[0547] 3. The server analyzes the received video data and emotional data to extract the swing form features and the user's emotional state, such as shoulder movement, hip rotation, and club trajectory.

[0548] 4. Based on the analysis results, the server generates feedback such as, "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing." In addition, if it determines that the user is tense, it also adds advice such as, "Take a deep breath and relax."

[0549] 5. The server sends the generated feedback to the device and displays it to the user in real time. The device displays the feedback in text and image format, allowing the user to correct their swing based on that feedback. Emotion-based advice is also displayed simultaneously.

[0550] 6. After reviewing the feedback, the user re-records a new swing with corrections and submits it to the system, which then receives new analysis and feedback. By repeating this process, the user can efficiently and effectively improve their swing form.

[0551] In this way, the present invention not only provides a specific system for supporting the improvement of a user's golf skills, but also, by combining it with an emotion engine, enables feedback that takes into account the user's mental state, allowing the user to properly understand their own swing form and continue practicing with peace of mind, even without guidance from a professional coach.

[0552] The processing flow will be explained below.

[0553] Program processing steps

[0554] Step 1: Video recording and emotional data acquisition

[0555] User:

[0556] The camera and microphone are placed in appropriate positions to record your swing, facial expressions, and voice. The camera and microphone can be a smartphone or a dedicated device.

[0557] Step 2: Sending video data and emotion data

[0558] Device:

[0559] The recorded video data and emotion data are sent to the server in a compressed and encrypted format, and a notification is sent when the data is complete.

[0560] Step 3: Receiving video and emotion data

[0561] server:

[0562] Receives video data and emotion data sent from the device. After receiving, checks the data for consistency and format.

[0563] Step 4: Preprocessing

[0564] server:

[0565] The received video data is processed before analysis. Specifically, frames are extracted, resolution is adjusted, and noise is removed as necessary. Emotion data is also converted into an analyzable format.

[0566] Step 5: Feature point extraction

[0567] server:

[0568] It uses an AI model to extract human body features from each frame of video, pinpointing the positions of shoulders, elbows, hips, etc., and analyzing their movements.

[0569] Step 6: Sentiment Analysis

[0570] server:

[0571] An emotion engine is used to analyze the user's emotional state from recorded facial expressions and voice, identifying states such as tension, excitement, and relaxation.

[0572] Step 7: Form evaluation and emotional alignment

[0573] server:

[0574] Based on the extracted features, the system evaluates the user's swing form, including swing trajectory, body balance, and club position, while also taking into account their emotional state.

[0575] Step 8: Identify the problem

[0576] server:

[0577] Based on form evaluation and emotion analysis results, it identifies which part of the swing is problematic. For example, it identifies "insufficient rotation of the right shoulder" and takes into account if the user is tense.

[0578] Step 9: Advice Generation

[0579] server:

[0580] Based on the identified issues and the user's emotional state, the system generates specific feedback for improvement, such as "Try to pull your left shoulder back during the backswing to increase the rotation of your right shoulder. Take a deep breath to relax."

[0581] Step 10: Send feedback

[0582] server:

[0583] Sends generated feedback to the device, including textual and visual guides.

[0584] Step 11: Feedback display

[0585] Device:

[0586] The feedback sent from the server is received and displayed to the user, who can see frame-by-frame images of problematic swings and emotion-based advice along with specific advice.

[0587] Step 12: User confirmation and correction

[0588] User:

[0589] Check the feedback displayed on your device and modify your next swing based on it. Try a new swing based on the feedback and emotional advice.

[0590] Step 13: Continuing the improvement process

[0591] User:

[0592] The corrected swing is then recorded again and the process is repeated from step 1. The user utilizes feedback and emotional advice to continually improve their skills.

[0593] By repeating this series of steps, users can improve their swing form accurately and efficiently, and continue practicing with peace of mind.

[0594] Example 2

[0595] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0596] Conventional golf swing training systems focus only on the user's swing form and are unable to provide feedback that takes into account the user's mental state or motivation, resulting in limited improvement. Furthermore, the feedback provided is uniform, and individualized responses to each user are insufficient. This makes it difficult to effectively improve a user's swing form and also lacks motivation to continue practicing over the long term.

[0597] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving video data and emotion data, means for analyzing the received data and evaluating the swing form, means for analyzing the user's emotion state using an emotion engine, means for generating feedback for the user based on the analysis results, and means for transmitting the feedback to the terminal and displaying it to the user. This makes it possible to provide feedback that takes into account not only the user's swing form but also their mental state and motivation, enabling effective skill improvement and motivation for continuous practice.

[0598] A "camera" is an optical device for recording a user's swing motion.

[0599] A "terminal" is an electronic device that transmits recorded video data and emotional data to a server and displays feedback to the user.

[0600] The "server" is a centralized management system for receiving video data and emotion data, analyzing them, and generating feedback.

[0601] "Video data" is video information of the user's swing motion captured by a camera.

[0602] "Emotion data" is information that indicates the emotional state of the user based on sensor data from a camera, microphone, etc.

[0603] An "emotion engine" is software or an algorithm for analyzing a user's emotional state from video and audio data.

[0604] "Swing form" refers to the configuration of each part of the body, such as the position and angle, during a user's golf swing motion.

[0605] "Feedback" is information that includes advice on improving the user's swing form and depending on the user's emotional state based on the analysis results.

[0606] A "generative AI model" is an artificial intelligence model trained to generate feedback based on a user's swing form and emotional state.

[0607] MODE FOR CARRYING OUT THE INVENTION

[0608] This invention is a system aimed at improving a user's golf swing skills, analyzing the user's swing motion captured by a camera in real time and providing feedback. Furthermore, by combining it with an emotion engine, it is possible to provide feedback that takes into account the user's motivation and mental state. This system is described in detail below.

[0609] Hardware and software used

[0610] The user records their swing using a smartphone or a dedicated camera. This allows for the acquisition of video data. Audio data can also be collected using a microphone. This recording device can be any commercially available camera or microphone.

[0611] The device is an electronic device that transmits the recorded video data and emotion data to the server. This device can be a typical smartphone, tablet, or PC. An application for collecting data is installed on the device, and it has the function of compressing and encrypting the recorded data before transmitting it to the server.

[0612] The server is a centralized management system that analyzes the received video and emotion data and generates feedback, and can use high-performance computers and cloud services. A generative AI model and emotion engine are used for the analysis. The generative AI model analyzes and evaluates the swing form, and the emotion engine analyzes the user's emotional state from the video and audio data.

[0613] Data processing and calculation

[0614] When the server receives the video and emotion data sent from the device, it first preprocesses the data. This preprocessing involves dividing the video data into frames and extracting human body features (shoulders, elbows, hips, etc.) from each frame. Next, it uses a generative AI model to analyze the swing form and evaluate the swing trajectory, body rotation, club angle, etc.

[0615] At the same time, an emotion engine is used to analyze the user's emotional data. For example, emotional states such as tension, joy, or irritation can be detected from the user's facial expressions and tone of voice. This allows the user's mental state to be understood.

[0616] The server generates feedback based on the analysis results. This feedback identifies problems with the swing form and includes specific advice for improvement. Furthermore, by taking emotional data into consideration, feedback appropriate to the user's mental state is provided. For example, if the right shoulder rotation is insufficient, the server generates advice such as "Try pulling your left shoulder back a bit more during the backswing." Furthermore, if the user is feeling tense, the server adds advice such as "Take a deep breath and relax."

[0617] The generated feedback is sent to the device and displayed to the user as text and visual content, allowing the user to refer to it and correct their swing form.

[0618] Specific examples

[0619] 1. The user sets up their smartphone on a tripod in their home practice room and records their swing. The camera and microphone are used to record the user's facial expressions and voice.

[0620] 2. After recording, the device automatically transmits the video and emotion data to the server, where the data is compressed and encrypted.

[0621] 3. The server uses the received data to extract and analyze the swing form's characteristics, such as shoulder movement, hip rotation, and club trajectory.

[0622] 4. The emotion engine analyzes the user's emotional state from video and audio data and detects when the user is nervous.

[0623] 5. Based on the analysis results, the server generates feedback such as "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing," along with advice such as "Take a deep breath and relax."

[0624] 6. This feedback is sent to the device and displayed to the user in real time, allowing the user to refer to it to correct their swing form and continue practicing.

[0625] Prompt Sentence Examples

[0626] "Please describe a system that analyzes video footage of a user's golf swing and emotional data to provide feedback."

[0627] This system analyzes the user's movements and emotions in real time and provides appropriate feedback to improve the user's golf skills. By using an emotion engine, it is possible to provide instruction that takes into account the user's mental state.

[0628] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0629] Step 1: Data collection

[0630] A user sets up a camera at a driving range or at home and records their swing. For example, a user mounts a smartphone on a tripod, launches a camera app, and records their swing. The input data is video data and audio data. The output data is the recorded video and audio files. The user's facial expressions and voice are also collected during recording.

[0631] Step 2: Send data

[0632] After recording is complete, the device automatically transmits the video and emotion data to the server. At this time, the device first compresses and encrypts the data. For example, the video data is compressed in H.264 format and encrypted using AES. The input data are the recorded video and audio files. The output data is the compressed and encrypted data, which is then transmitted to the server via the Internet.

[0633] Step 3: Data reception and preprocessing

[0634] The server receives data sent from the terminal. After receiving the data, it first decompresses and decrypts it. For example, it decrypts AES-encrypted data and decompresses H.264-compressed data. The input data is the compressed and encrypted data. The output data is the original video and audio files.

[0635] Step 4: Swing form analysis

[0636] The server analyzes the video file frame by frame and extracts the body's feature points (shoulders, elbows, hips, etc.). For example, it uses the OpenPose library to identify the coordinates of each body part. The input data is the video file. The output data is the feature point coordinate data for each frame. Based on this data, the swing trajectory, body rotation, club angle, etc. are evaluated. Furthermore, analysis is performed using a generative AI model, enabling highly accurate evaluation.

[0637] Step 5: Sentiment Analysis

[0638] The server analyzes the user's emotional state from audio and video files. For example, audio analysis uses TensorFlow or OpenSMILE to analyze the tone and speed of the voice, and video analysis uses a facial expression recognition algorithm (e.g., FaceAPI) to identify the user's emotions. The input data are audio and video files. The output data is the analyzed emotional state information (e.g., joy, anger, tension, etc.).

[0639] Step 6: Feedback generation

[0640] The server generates feedback for the user based on the results of the swing form analysis and emotion analysis. For example, it generates technical advice such as "Your right shoulder rotation is insufficient, so try pulling your left shoulder back a bit more during your backswing," or emotion-based advice such as "Take a deep breath and relax." The input data are feature point coordinate data of the swing form and emotional state information. The output data is a feedback message.

[0641] Step 7: Send and view feedback

[0642] The server sends the generated feedback to the terminal. For example, data is sent using secure HTTP communication (HTTPS). The input data is the feedback message. The output data is the feedback message sent to the terminal. The terminal displays the received feedback to the user. The display format is provided as text and image content. For example, the application displays the text "Your right shoulder rotation is insufficient" along with an illustration showing the corresponding movement. The user can then correct their swing form based on this.

[0643] (Application example 2)

[0644] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0645] Robots performing various tasks in factories lack appropriate feedback to improve the efficiency and accuracy of their operations. Furthermore, there is a lack of means to analyze the robot's behavior and the causes of errors in real time and determine the need for maintenance or updates. This leads to problems such as reduced work efficiency and delays in maintenance, which can easily lead to problems.

[0646] The specific processing 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 user's swing motion with a camera, means for transmitting the recorded video data to the server, means for analyzing the video data and evaluating the swing form, means for analyzing the robot's motion in real time and generating feedback to improve the accuracy and efficiency of the motion, means for monitoring the robot's status and providing appropriate maintenance advice, and means for transmitting the feedback to the terminal and displaying it to the user. This makes it possible to analyze the robot's motion in real time and provide feedback to improve efficiency and accuracy, as well as to monitor the robot's status and perform appropriate maintenance.

[0647] A "camera" is a video device used to record the actions of the user or robot.

[0648] "Recorded video data" refers to video data collected by a camera.

[0649] A "server" is a computer system that receives and analyzes recorded video data.

[0650] "Swing form evaluation" refers to analyzing the user's swing motion based on the recorded video data and determining whether it is good or bad.

[0651] "Feedback" refers to advice or instructions provided to the user or robot based on the analysis results.

[0652] "Real-time" means that processing is done almost simultaneously and the results are reflected immediately.

[0653] "Robot movement analysis" refers to the detailed analysis of a robot's movements using recorded video data.

[0654] "Motion accuracy" is an index that indicates how accurate a robot's movements are relative to set goals or standards.

[0655] "Operation efficiency" is a measure of how efficiently a robot works to achieve its objectives.

[0656] "Maintenance advice" involves analyzing the robot's operation and condition and proposing necessary maintenance and repairs.

[0657] "Terminals" are devices that users and engineers use to receive feedback, such as computers and smartphones.

[0658] "Transmitting video data" means transferring the recorded video data to a server via a network.

[0659] "Feedback to improve the accuracy and efficiency of movements" refers to feedback that includes instructions and advice to make the robot's movements more accurate and efficient.

[0660] "Robot status" refers to the operational status of the robot, such as how it is currently operating and whether any errors have occurred.

[0661] "Users" are people or engineers who use the system and receive feedback.

[0662] A system for realizing this invention includes a camera, a server, a terminal, and dedicated software. The system program records user actions with the camera, transmits the recorded video data to the server, analyzes the data, transmits generated feedback to the terminal, and displays the feedback.

[0663] The server receives video footage of the user's movements captured by the camera and analyzes the video data in real time using OpenCV. Feature extraction uses an algorithm that recognizes the user's shoulders, elbows, waist, etc. from the video. The software used is OpenCV for video processing and TensorFlow for loading the machine learning model.

[0664] In particular, the server analyzes recorded video and real-time feeds using an emotion engine powered by TensorFlow. This emotion engine recognizes the user's emotions in real time from camera footage and audio data, enabling feedback that takes into account the user's mental state.

[0665] As an example, consider the analysis of the movements of a robot working in a factory. A camera records the robot's movements and sends the recorded video data to a server. The server receives the video data, analyzes it using OpenCV, and evaluates the robot's movement accuracy and efficiency. It then uses an emotion engine to analyze the robot's condition and the cause of any movement errors, and generates necessary maintenance advice. As a result, specific advice such as "correct the angle of the arm" or "perform regular maintenance" is sent as feedback and displayed on the terminal.

[0666] An example of a prompt is as follows:

[0667] "Analyze the robot's working movements, generate optimal movement patterns, and provide feedback. Also, monitor the robot's condition and provide appropriate maintenance advice. The video of the robot's movements contains key feature point data such as shoulders, elbows, and waists. Generate movement feedback based on the feature point data, and perform emotion analysis using an emotion recognition engine."

[0668] Based on this prompt, the generative AI model generates specific feedback, enabling the system to provide real-time behavioral feedback and emotion-based advice to the user.

[0669] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0670] Step 1:

[0671] The user installs a camera and records the robot's movements. For example, a Logitech HD Pro Webcam C920 is used as the camera. The input is the recorded video and audio data. The output is real-time video and audio data acquired from the camera.

[0672] Step 2:

[0673] The device sends the recorded video and audio data to the server. When sending the data, it is appropriately compressed and encrypted. The input is the video and audio data acquired from the camera. The output is the compressed and encrypted video and audio data.

[0674] Step 3:

[0675] The server analyzes the received video data in real time using OpenCV. This analysis extracts feature points from each part of the robot (e.g., shoulders, elbows, waist, etc.) for each video frame. The input is compressed and encrypted video data sent from the terminal. The output is the analysis results, including feature point data.

[0676] Step 4:

[0677] The server uses an emotion engine based on TensorFlow to recognize the robot's state from video and audio data. This analysis determines whether the robot is operating normally or if an error has occurred. The input is feature point data and audio data. The output is the analysis result regarding the robot's state.

[0678] Step 5:

[0679] The server evaluates the accuracy and efficiency of the robot's movements based on the analysis results and generates feedback. Specifically, it generates feedback indicating where movement corrections and maintenance are needed. The input is the analysis results from the video data analysis and emotion engine. The output is the generated feedback.

[0680] Step 6:

[0681] The server sends the generated feedback to the terminal. The terminal displays the received feedback to the user in text and / or visual form. The input is the generated feedback. The output is the transmission and display of the feedback data to the terminal.

[0682] Step 7:

[0683] The user reviews the feedback and adjusts the robot's behavior as necessary. The user also creates a maintenance plan for the next maintenance based on the feedback. The input is the feedback content. The output is the revised robot's behavior and maintenance plan.

[0684] Step 8:

[0685] The device re-records the modified robot's movements and transmits the new video data to the server, starting a new analysis and feedback cycle. The input is the video of the modified robot's movements. The output is the transmission of the re-recorded video data.

[0686] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0687] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0688] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0689] [Third embodiment]

[0690] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0691] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0692] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0693] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0694] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0695] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0696] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0697] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0698] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0699] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0700] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0701] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0702] This invention is a system aimed at improving golf swing skills, and helps improve swing form by analyzing the user's swing motion recorded on a camera in real time and providing feedback.

[0703] Overview of program processing

[0704] Data collection

[0705] The user sets up a camera at a driving range or at home and records their swing. The camera can be any camera device, such as a smartphone or a dedicated camera.

[0706] Video data transmission

[0707] The device sends the recorded video data to the server. The video data is sent in a compressed and encrypted format, ensuring security.

[0708] Receiving and analyzing video data

[0709] The server receives the video data sent from the device and begins analyzing the swing form using an AI model. During the analysis, the characteristic points of the human body (shoulders, elbows, hips, etc.) are extracted for each frame of the video, and the swing trajectory, body rotation, club angle, etc. are evaluated.

[0710] Feedback Generation

[0711] The server generates feedback for the user based on the analysis results. The feedback includes identifying the problem and providing specific advice for improvement. For example, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[0712] Send and view feedback

[0713] The server sends the generated feedback to the device, which then displays it to the user. The feedback is displayed as text or visual content, and the user can refer to it to correct their swing form.

[0714] Specific examples

[0715] 1. The user swings in their home practice room. The user sets up their smartphone on a tripod and records their swing.

[0716] 2. After recording, the device automatically sends the video data to the server. The data is properly compressed and encrypted before being sent.

[0717] 3. The server analyzes the received video data and extracts the swing form's characteristics, such as shoulder movement, hip rotation, and club trajectory.

[0718] 4. Based on the analysis results, the server generates feedback such as, "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing."

[0719] 5. The server sends the generated feedback to the device and displays it to the user in real time. The device displays the feedback in text and image format, allowing the user to correct their swing based on it.

[0720] 6. After reviewing the feedback, the user re-records a new swing with corrections and submits it to the system, which then receives new analysis and feedback. By repeating this process, the user can efficiently and effectively improve their swing form.

[0721] In this way, the present invention provides a specific system for supporting users in improving their golf skills, allowing users to properly understand their own swing form and efficiently improve their skills without the need for guidance from a professional coach.

[0722] The processing flow will be explained below.

[0723] Program processing steps

[0724] Step 1: Recording

[0725] User:

[0726] Set up the camera in an appropriate position and record your swing using a smartphone or dedicated camera.

[0727] Step 2: Sending video data

[0728] Device:

[0729] The recorded video data is sent to the server in a compressed and encrypted format to ensure security.

[0730] Step 3: Receiving video data

[0731] server:

[0732] Receives video data sent from the terminal. After receiving, checks the data for consistency and format.

[0733] Step 4: Preprocessing

[0734] server:

[0735] The received video data is processed before analysis, specifically by extracting frames, adjusting resolution, and removing noise if necessary.

[0736] Step 5: Feature point extraction

[0737] server:

[0738] An AI model is used to extract body features (shoulders, elbows, hips, etc.) from each frame, providing data for specific analysis of swing form movements.

[0739] Step 6: Form evaluation

[0740] server:

[0741] The user's swing form is evaluated based on the extracted feature points, including the swing trajectory, body balance, and club position.

[0742] Step 7: Identify the problem

[0743] server:

[0744] Based on the evaluation results, problems with the swing form are identified. For example, specific areas such as "insufficient rotation of the right shoulder" are identified.

[0745] Step 8: Advice Generation

[0746] server:

[0747] It generates specific advice for improvement based on identified problems, such as "Try to pull your left shoulder back during the backswing to increase the rotation of your right shoulder."

[0748] Step 9: Send your feedback

[0749] server:

[0750] Send the generated feedback to the device, which may include textual and / or visual guidance.

[0751] Step 10: Feedback display

[0752] Device:

[0753] The system receives feedback sent from the server and displays it to the user, including frame-by-frame images of problematic swings along with specific advice.

[0754] Step 11: User confirmation and correction

[0755] User:

[0756] Check the feedback displayed on your device and use it to modify your next swing. Use the feedback to try a new swing.

[0757] Step 12: Continuing the improvement process

[0758] User:

[0759] The corrected swing is then filmed again and the process is repeated from step 1. The user utilizes the feedback to continually improve their skills.

[0760] By repeating this series of steps, the user can improve their swing form accurately and efficiently.

[0761] Example 1

[0762] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0763] Current methods for improving golf swing skills (e.g., video analysis and direct instruction from a coach) are expensive and have the drawback of not providing real-time feedback. Therefore, there is a need for a system that allows users to easily analyze their swing form at home or at a driving range and receive real-time feedback. Furthermore, the difficulty of providing optimized feedback for each individual user is also an issue that needs to be resolved.

[0764] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0765] In this invention, the server includes a means for using a camera to record the user's movements, a means for transmitting the data recorded by the camera to an information processing device, a means for analyzing the data and evaluating the movements in the information processing device, a means for generating feedback for the user based on the evaluation results, and a means for transmitting the feedback to the terminal and displaying it to the user. This allows users to easily analyze their own swing form and receive efficient feedback. Furthermore, feedback generated using an artificial intelligence model can provide advice optimized for each individual user in real time.

[0766] "Capture device" refers to a camera or video recording device for recording a user's actions.

[0767] "Information processing device" refers to a computer or server that receives and analyzes the recorded data.

[0768] "User" refers to an individual who uses the system to analyze their swing form and receive feedback.

[0769] "Data" refers to video information of the user's swing motion captured by a camera.

[0770] "Analysis" refers to a process in which an information processing device processes data to extract and evaluate features of a user's actions.

[0771] "Evaluation" refers to the act of judging whether a user's behavior is good or bad based on the analyzed data and identifying areas for improvement.

[0772] "Feedback" refers to advice or guidance provided to the user based on the evaluation results.

[0773] "Device" refers to the device (such as a smartphone or tablet) that a user uses to receive feedback.

[0774] "Artificial intelligence model" refers to the machine learning and deep learning algorithms used to analyze data and generate feedback.

[0775] "Evaluation results" refer to information about the user's behavior and diagnostic results derived during the analysis process.

[0776] "Means using a photographing device" refers to the act of a user recording their own swing motion with a video or camera.

[0777] "Transmitting means" refers to the process of transferring data from the image capture device to the information processing device.

[0778] "Means for displaying" refers to a method for conveying feedback to the user visually or audibly.

[0779] This invention is a system aimed at improving golf swing skills, and helps improve swing form by analyzing the user's swing motion recorded on a camera in real time and providing feedback.

[0780] System configuration

[0781] Data collection

[0782] The user sets up a camera at a driving range or at home and records their swing. The camera can be any type of camera, such as a smartphone or a dedicated camera. For example, the user sets up their smartphone on a tripod and records their swing. A frame rate of at least 30 fps is recommended for recording.

[0783] Video data transmission

[0784] The device (such as a smartphone or dedicated camera) transmits the recorded video data to the server. At this time, the video data is encoded in a compressed format such as H.264 and transmitted over an encrypted communication channel using SSL / TLS, thereby maintaining the privacy and integrity of the data.

[0785] Video data reception and preprocessing

[0786] The server receives the video data sent from the device. After receiving it, it decodes and preprocesses the data. Specifically, it uses libraries such as FFmpeg to split the video data into frames and prepares it in a format that can be analyzed by the AI ​​model. For example, it adjusts the resolution and color.

[0787] Swing form analysis

[0788] The server inputs the preprocessed frame data into an AI model to analyze the swing form. For example, it uses a human pose estimation model such as OpenPose to extract feature points such as shoulders, elbows, and hips for each frame. It then evaluates the swing trajectory, body rotation, and club angle to identify areas that need improvement.

[0789] Feedback Generation

[0790] The server generates feedback for the user based on the analysis results. The generative AI model receives prompts based on the analysis results to provide specific advice. For example, the generated advice might be, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[0791] Send and view feedback

[0792] The server sends the generated feedback to the device. The device then displays the received feedback to the user. At this time, a dedicated application is used to display the feedback in an easy-to-understand manner as text or visual content. For example, the feedback may include an arrow indicating "pull your left shoulder during the backswing" or an image containing supplementary explanations.

[0793] Specific examples

[0794] 1. The user sets up a smartphone on a tripod in their home practice room and records their swing. The camera angle is adjusted so that the full swing is clearly captured on screen.

[0795] 2. After recording, the device automatically compresses the video data in H.264 format and sends it to the server using SSL / TLS encrypted communication.

[0796] 3. The server uses FFmpeg to decode the received video data, split it into frames, adjust the resolution and color, and convert it into a format that is easy for the AI ​​model to analyze.

[0797] 4. The server inputs the frame data into the OpenPose model and extracts feature points such as shoulders, elbows, and hips. It then evaluates the swing trajectory, body rotation, and club angle based on the extracted data.

[0798] 5. The server uses a generative AI model to generate feedback such as, "Your right shoulder isn't rotating enough, so try pulling your left shoulder back more during the backswing."

[0799] 6. The server sends the generated feedback to the device and displays it to the user. The device displays the feedback in text and image format, and the user corrects their swing based on it. By repeating this process, the user can improve their swing form efficiently and effectively.

[0800] Example of input prompt for generative AI model

[0801] "Look at the motion of my golf swing. Evaluate whether my right shoulder is rotating properly, whether the club path is correct, and whether my feet are positioned properly, and provide advice on how to improve my swing form."

[0802] In this way, the present invention provides a specific method for helping users improve their golf skills.

[0803] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0804] Step 1:

[0805] The user sets up a recording device at a driving range or at home and records their swing. Specifically, the user sets up a smartphone on a tripod and records their swing as a video. The input is a swing video recorded with a smartphone or dedicated camera, and the output is a video file.

[0806] Step 2:

[0807] The device compresses the recorded video file and sends it to the server. At this time, it is encoded in a compression format such as H.264 and uses SSL / TLS encrypted communication. The input is the recorded video file, and the output is compressed and encrypted video data.

[0808] Step 3:

[0809] The server receives the video data sent from the device and performs decoding and preprocessing. Specifically, it uses FFmpeg to divide the video into frames and adjust the resolution and color. The input is compressed and encrypted video data, and the output is preprocessed frame data.

[0810] Step 4:

[0811] The server inputs the preprocessed frame data into the AI ​​model and analyzes the swing form. Specifically, it uses a human body pose estimation model such as OpenPose to extract feature points such as shoulders, elbows, and hips for each frame. The input is the preprocessed frame data, and the output is feature point data.

[0812] Step 5:

[0813] The server evaluates the swing form based on the extracted feature point data and generates feedback. Using the generative AI model, a prompt sentence is input that provides specific advice based on the analysis results. The input is the feature point data and the analysis results, and the output is feedback text. For example, the generated feedback might be, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[0814] Step 6:

[0815] The server sends the generated feedback to the terminal. The terminal displays the received feedback to the user. Using a dedicated application, the feedback is displayed in an easy-to-understand manner as text or visual content. The input is the feedback text, and the output is the feedback displayed to the user. For example, an arrow indicating "pull your left shoulder during the backswing" or an image containing additional explanations is displayed as feedback.

[0816] Step 7:

[0817] The user reviews the feedback and modifies their swing form based on it. They then re-record their modified swing motion and repeat the process from step 1. This allows the user to efficiently and effectively improve their swing form. The input is the modified swing motion, and the output is a new swing form with the modifications.

[0818] (Application example 1)

[0819] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0820] Conventional optimization of industrial machine operations often requires expensive sensors and specialized analytical equipment, or manual evaluation by skilled engineers, resulting in significant increases in cost and time. Furthermore, there is variation in feedback quality, and there is a lack of mechanisms for automatically learning and improving optimal operations. Furthermore, it is difficult to evaluate work operations and provide feedback in real time, hindering efficient automation.

[0821] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0822] In this invention, the server includes means for recording the work operations of the industrial machine using a camera, means for transmitting the recorded video data to the server, means for analyzing the video data and evaluating the work operations, means for generating feedback based on the evaluation results, means for transmitting the feedback to the terminal and displaying it to the user, and means for optimizing the work operations of the industrial machine, thereby making it possible to optimize the work operations of the industrial machine efficiently and with high accuracy.

[0823] A "camera" is a device that captures images of objects, and is an optical instrument that records still images and videos.

[0824] The term "user" refers to a person who uses the system of the present invention to record swing movements and work movements and receives evaluations and feedback.

[0825] "Recorded video data" refers to digital data of moving images and still images recorded by a camera.

[0826] The "server" is a central processing unit that analyzes the recorded video data and generates and transmits evaluations and feedback.

[0827] "Analysis" is the process of extracting movement characteristics from recorded video data and evaluating them.

[0828] "Feedback" refers to evaluation and advice information provided based on the analysis results, with the aim of improving work operations.

[0829] A "terminal" is a device that displays feedback to the user and manages received data.

[0830] "Industrial machinery" refers to machinery and equipment used in factories and production lines that performs specific tasks automatically or semi-automatically.

[0831] A "work action" is a specific movement or procedure performed by industrial machinery that is part of a production process.

[0832] "Work motion evaluation" is a process of evaluating the efficiency and accuracy of work based on the feature points and motion trajectories extracted through analysis.

[0833] "Optimization" is the process of efficiently and accurately adjusting and improving a target operation or process based on this feedback.

[0834] A system for implementing this invention includes a camera, a server, and a terminal, and is used to optimize the operation of industrial machinery. This system evaluates the work operation of the industrial machinery in real time and provides efficient and highly accurate feedback.

[0835] First, a camera is installed on an industrial machine operating in a factory, and its operation is recorded. The camera can be a general-purpose camera such as a Raspberry Pi camera module. The video data recorded by the camera is sent to a server via HTTP communication using a Python script. The data is compressed and encrypted during transmission to ensure security.

[0836] The server receives and analyzes the recorded video data. This analysis uses machine learning libraries such as TensorFlow and PyTorch to extract characteristic features of the industrial machinery's work movements (for example, joint angles and movement trajectories). Based on the analysis results, problems are identified and feedback is generated. The feedback includes specific improvements and advice.

[0837] The generated feedback is sent from the server to the terminal, which acts as a user device and displays the feedback in text and visual form, and is automatically reflected in the robot's control system, for example, using the MQTT protocol.

[0838] The following hardware and software are used to process this program:

[0839] Camera: Raspberry Pi camera module

[0840] Sending data: Python, Requests library

[0841] Data analysis: TensorFlow, PyTorch, Docker

[0842] Feedback transmission: MQTT protocol

[0843] As a concrete example, consider the case of improving the operation of an assembly robot on a production line. For example, if an issue occurs when attaching a part due to an improper wrist joint angle, the system analyzes the recorded data and generates feedback such as "the wrist angle is 5 degrees too short." The robot's operation program is then updated based on this feedback, resolving the problem.

[0844] As an example of a prompt, you could input the following instructions to a generative AI model:

[0845] "After analyzing the robot's motion, we found that the wrist angle is 5 degrees short. Please explain how to change the settings of the wrist joint module to increase the wrist angle by 5 degrees."

[0846] This allows the generative AI model to provide specific advice on changing settings, resulting in more accurate performance improvements.

[0847] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0848] Step 1:

[0849] The user records the operation of industrial machinery with a camera. The camera can be a fixed camera installed in the factory or a camera attached to a robot. The input is the video of the industrial machinery in operation, and the output is the recorded video data. The specific operation involves placing the camera in an appropriate position and pressing a button to start recording the video.

[0850] Step 2:

[0851] The device compresses and encrypts the recorded video data before sending it to the server. The input is the recorded video data, and the output is the compressed and encrypted video data. Specifically, the device uses a Python script to convert the video data into an appropriate format and uploads it to the server using HTTP communication.

[0852] Step 3:

[0853] The server decrypts the received compressed and encrypted video data and performs data analysis. The input is the compressed and encrypted video data, and the output is the analysis results. Specifically, after the decoding process, TensorFlow and PyTorch are used to extract feature points (joint angles, movement trajectories, etc.) from the video and evaluate the movement.

[0854] Step 4:

[0855] The server generates feedback based on the analysis results. The input is the analysis results, and the output is feedback information. Specifically, it automatically generates improvement measures and advice based on problems identified from the analysis results. For example, in response to an evaluation result that "the wrist angle is 5 degrees short," it provides specific advice on how to increase the wrist angle by 5 degrees.

[0856] Step 5:

[0857] The server sends the generated feedback to the terminal and displays it to the user. The input is the feedback information, and the output is the feedback displayed on the user's terminal. Specifically, the server converts the feedback information into text or visual format and sends it to the terminal.

[0858] Step 6:

[0859] The terminal displays the received feedback information to the user and reflects it in the robot's control system. The input is the feedback information sent from the server, and the output is a control program that reflects the feedback. Specifically, the terminal displays the feedback content on the screen, sends instructions to the robot control system using the MQTT protocol, and updates the program.

[0860] Step 7:

[0861] The user re-records the operation of the industrial machine based on the updated control program and confirms the optimized operation. The input is the updated control program, and the output is the re-recorded video data and the operation evaluation results. Specifically, the operation video is recorded again with a camera, and the process is repeated from the first step 1.

[0862] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0863] This invention is a system aimed at improving golf swing skills. It not only analyzes the user's swing motion captured on a camera in real time and provides feedback, but also combines it with an emotion engine that recognizes the user's emotions to provide feedback that takes into account the user's motivation and mental state.

[0864] Overview of program processing

[0865] Data collection

[0866] Users set up a camera at a driving range or at home to record their swing. The camera can be any device, such as a smartphone or a dedicated camera. The emotion engine analyzes the user's emotions in real time from the camera footage and audio data.

[0867] Video data transmission

[0868] The device sends the recorded video data and emotion data to a server. The data is sent in a compressed and encrypted format, ensuring security.

[0869] Receiving and analyzing video data

[0870] The server receives the video and emotion data sent from the device and begins analyzing the swing form using an AI model. During the analysis, human body features (shoulders, elbows, hips, etc.) are extracted for each frame of video, and the swing trajectory, body rotation, club angle, etc. are evaluated. In addition, the emotion engine analyzes the user's emotional state.

[0871] Feedback Generation

[0872] The server generates feedback for the user based on the analysis results. The feedback includes identifying problems and providing specific advice for improvement. Furthermore, by taking emotional data into consideration, feedback appropriate to the user's mental state can be provided. For example, if the user is feeling tense, advice to relax may be added.

[0873] Send and view feedback

[0874] The server sends the generated feedback to the device, which then displays it to the user. The feedback is displayed as text and visual content, allowing the user to refer to it and correct their swing form. Additional advice based on emotion data is also displayed.

[0875] Specific examples

[0876] 1. The user takes a swing in their home practice room. The user sets up their smartphone on a tripod and records their swing. The camera and microphone are used to record the swing, and the user's facial expressions and voice are also captured.

[0877] 2. After recording, the device automatically sends the video and emotion data to the server. The data is appropriately compressed and encrypted before being sent.

[0878] 3. The server analyzes the received video data and emotional data to extract the swing form features and the user's emotional state, such as shoulder movement, hip rotation, and club trajectory.

[0879] 4. Based on the analysis results, the server generates feedback such as, "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing." In addition, if it determines that the user is tense, it also adds advice such as, "Take a deep breath and relax."

[0880] 5. The server sends the generated feedback to the device and displays it to the user in real time. The device displays the feedback in text and image format, allowing the user to correct their swing based on that feedback. Emotion-based advice is also displayed simultaneously.

[0881] 6. After reviewing the feedback, the user re-records a new swing with corrections and submits it to the system, which then receives new analysis and feedback. By repeating this process, the user can efficiently and effectively improve their swing form.

[0882] In this way, the present invention not only provides a specific system for supporting the improvement of a user's golf skills, but also, by combining it with an emotion engine, enables feedback that takes into account the user's mental state, allowing the user to properly understand their own swing form and continue practicing with peace of mind, even without guidance from a professional coach.

[0883] The processing flow will be explained below.

[0884] Program processing steps

[0885] Step 1: Video recording and emotional data acquisition

[0886] User:

[0887] The camera and microphone are placed in appropriate positions to record your swing, facial expressions, and voice. The camera and microphone can be a smartphone or a dedicated device.

[0888] Step 2: Sending video data and emotion data

[0889] Device:

[0890] The recorded video data and emotion data are sent to the server in a compressed and encrypted format, and a notification is sent when the data is complete.

[0891] Step 3: Receiving video and emotion data

[0892] server:

[0893] Receives video data and emotion data sent from the device. After receiving, checks the data for consistency and format.

[0894] Step 4: Preprocessing

[0895] server:

[0896] The received video data is processed before analysis. Specifically, frames are extracted, resolution is adjusted, and noise is removed as necessary. Emotion data is also converted into an analyzable format.

[0897] Step 5: Feature point extraction

[0898] server:

[0899] It uses an AI model to extract human body features from each frame of video, pinpointing the positions of shoulders, elbows, hips, etc., and analyzing their movements.

[0900] Step 6: Sentiment Analysis

[0901] server:

[0902] An emotion engine is used to analyze the user's emotional state from recorded facial expressions and voice, identifying states such as tension, excitement, and relaxation.

[0903] Step 7: Form evaluation and emotional alignment

[0904] server:

[0905] Based on the extracted features, the system evaluates the user's swing form, including swing trajectory, body balance, and club position, while also taking into account their emotional state.

[0906] Step 8: Identify the problem

[0907] server:

[0908] Based on form evaluation and emotion analysis results, it identifies which part of the swing is problematic. For example, it identifies "insufficient rotation of the right shoulder" and takes into account if the user is tense.

[0909] Step 9: Advice Generation

[0910] server:

[0911] Based on the identified issues and the user's emotional state, the system generates specific feedback for improvement, such as "Try to pull your left shoulder back during the backswing to increase the rotation of your right shoulder. Take a deep breath to relax."

[0912] Step 10: Send feedback

[0913] server:

[0914] Sends generated feedback to the device, including textual and visual guides.

[0915] Step 11: Feedback display

[0916] Device:

[0917] The feedback sent from the server is received and displayed to the user, who can see frame-by-frame images of problematic swings and emotion-based advice along with specific advice.

[0918] Step 12: User confirmation and correction

[0919] User:

[0920] Check the feedback displayed on your device and modify your next swing based on it. Try a new swing based on the feedback and emotional advice.

[0921] Step 13: Continuing the improvement process

[0922] User:

[0923] The corrected swing is then recorded again and the process is repeated from step 1. The user utilizes feedback and emotional advice to continually improve their skills.

[0924] By repeating this series of steps, users can improve their swing form accurately and efficiently, and continue practicing with peace of mind.

[0925] Example 2

[0926] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0927] Conventional golf swing training systems focus only on the user's swing form and are unable to provide feedback that takes into account the user's mental state or motivation, resulting in limited improvement. Furthermore, the feedback provided is uniform, and individualized responses to each user are insufficient. This makes it difficult to effectively improve a user's swing form and also lacks motivation to continue practicing over the long term.

[0928] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving video data and emotion data, means for analyzing the received data and evaluating the swing form, means for analyzing the user's emotion state using an emotion engine, means for generating feedback for the user based on the analysis results, and means for transmitting the feedback to the terminal and displaying it to the user. This makes it possible to provide feedback that takes into account not only the user's swing form but also their mental state and motivation, enabling effective skill improvement and motivation for continuous practice.

[0929] A "camera" is an optical device for recording a user's swing motion.

[0930] A "terminal" is an electronic device that transmits recorded video data and emotional data to a server and displays feedback to the user.

[0931] The "server" is a centralized management system for receiving video data and emotion data, analyzing them, and generating feedback.

[0932] "Video data" is video information of the user's swing motion captured by a camera.

[0933] "Emotion data" is information that indicates the emotional state of the user based on sensor data from a camera, microphone, etc.

[0934] An "emotion engine" is software or an algorithm for analyzing a user's emotional state from video and audio data.

[0935] "Swing form" refers to the configuration of each part of the body, such as the position and angle, during a user's golf swing motion.

[0936] "Feedback" is information that includes advice on improving the user's swing form and depending on the user's emotional state based on the analysis results.

[0937] A "generative AI model" is an artificial intelligence model trained to generate feedback based on a user's swing form and emotional state.

[0938] MODE FOR CARRYING OUT THE INVENTION

[0939] This invention is a system aimed at improving a user's golf swing skills, analyzing the user's swing motion captured by a camera in real time and providing feedback. Furthermore, by combining it with an emotion engine, it is possible to provide feedback that takes into account the user's motivation and mental state. This system is described in detail below.

[0940] Hardware and software used

[0941] The user records their swing using a smartphone or a dedicated camera. This allows for the acquisition of video data. Audio data can also be collected using a microphone. This recording device can be any commercially available camera or microphone.

[0942] The device is an electronic device that transmits the recorded video data and emotion data to the server. This device can be a typical smartphone, tablet, or PC. An application for collecting data is installed on the device, and it has the function of compressing and encrypting the recorded data before transmitting it to the server.

[0943] The server is a centralized management system that analyzes the received video and emotion data and generates feedback, and can use high-performance computers and cloud services. A generative AI model and emotion engine are used for the analysis. The generative AI model analyzes and evaluates the swing form, and the emotion engine analyzes the user's emotional state from the video and audio data.

[0944] Data processing and calculation

[0945] When the server receives the video and emotion data sent from the device, it first preprocesses the data. This preprocessing involves dividing the video data into frames and extracting human body features (shoulders, elbows, hips, etc.) from each frame. Next, it uses a generative AI model to analyze the swing form and evaluate the swing trajectory, body rotation, club angle, etc.

[0946] At the same time, an emotion engine is used to analyze the user's emotional data. For example, emotional states such as tension, joy, or irritation can be detected from the user's facial expressions and tone of voice. This allows the user's mental state to be understood.

[0947] The server generates feedback based on the analysis results. This feedback identifies problems with the swing form and includes specific advice for improvement. Furthermore, by taking emotional data into consideration, feedback appropriate to the user's mental state is provided. For example, if the right shoulder rotation is insufficient, the server generates advice such as "Try pulling your left shoulder back a bit more during the backswing." Furthermore, if the user is feeling tense, the server adds advice such as "Take a deep breath and relax."

[0948] The generated feedback is sent to the device and displayed to the user as text and visual content, allowing the user to refer to it and correct their swing form.

[0949] Specific examples

[0950] 1. The user sets up their smartphone on a tripod in their home practice room and records their swing. The camera and microphone are used to record the user's facial expressions and voice.

[0951] 2. After recording, the device automatically transmits the video and emotion data to the server, where the data is compressed and encrypted.

[0952] 3. The server uses the received data to extract and analyze the swing form's characteristics, such as shoulder movement, hip rotation, and club trajectory.

[0953] 4. The emotion engine analyzes the user's emotional state from video and audio data and detects when the user is nervous.

[0954] 5. Based on the analysis results, the server generates feedback such as "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing," along with advice such as "Take a deep breath and relax."

[0955] 6. This feedback is sent to the device and displayed to the user in real time, allowing the user to refer to it to correct their swing form and continue practicing.

[0956] Prompt Sentence Examples

[0957] "Please describe a system that analyzes video footage of a user's golf swing and emotional data to provide feedback."

[0958] This system analyzes the user's movements and emotions in real time and provides appropriate feedback to improve the user's golf skills. By using an emotion engine, it is possible to provide instruction that takes into account the user's mental state.

[0959] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0960] Step 1: Data collection

[0961] A user sets up a camera at a driving range or at home and records their swing. For example, a user mounts a smartphone on a tripod, launches a camera app, and records their swing. The input data is video data and audio data. The output data is the recorded video and audio files. The user's facial expressions and voice are also collected during recording.

[0962] Step 2: Send data

[0963] After recording is complete, the device automatically transmits the video and emotion data to the server. At this time, the device first compresses and encrypts the data. For example, the video data is compressed in H.264 format and encrypted using AES. The input data are the recorded video and audio files. The output data is the compressed and encrypted data, which is then transmitted to the server via the Internet.

[0964] Step 3: Data reception and preprocessing

[0965] The server receives data sent from the terminal. After receiving the data, it first decompresses and decrypts it. For example, it decrypts AES-encrypted data and decompresses H.264-compressed data. The input data is the compressed and encrypted data. The output data is the original video and audio files.

[0966] Step 4: Swing form analysis

[0967] The server analyzes the video file frame by frame and extracts the body's feature points (shoulders, elbows, hips, etc.). For example, it uses the OpenPose library to identify the coordinates of each body part. The input data is the video file. The output data is the feature point coordinate data for each frame. Based on this data, the swing trajectory, body rotation, club angle, etc. are evaluated. Furthermore, analysis is performed using a generative AI model, enabling highly accurate evaluation.

[0968] Step 5: Sentiment Analysis

[0969] The server analyzes the user's emotional state from audio and video files. For example, audio analysis uses TensorFlow or OpenSMILE to analyze the tone and speed of the voice, and video analysis uses a facial expression recognition algorithm (e.g., FaceAPI) to identify the user's emotions. The input data are audio and video files. The output data is the analyzed emotional state information (e.g., joy, anger, tension, etc.).

[0970] Step 6: Feedback generation

[0971] The server generates feedback for the user based on the results of the swing form analysis and emotion analysis. For example, it generates technical advice such as "Your right shoulder rotation is insufficient, so try pulling your left shoulder back a bit more during your backswing," or emotion-based advice such as "Take a deep breath and relax." The input data are feature point coordinate data of the swing form and emotional state information. The output data is a feedback message.

[0972] Step 7: Send and view feedback

[0973] The server sends the generated feedback to the terminal. For example, data is sent using secure HTTP communication (HTTPS). The input data is the feedback message. The output data is the feedback message sent to the terminal. The terminal displays the received feedback to the user. The display format is provided as text and image content. For example, the application displays the text "Your right shoulder rotation is insufficient" along with an illustration showing the corresponding movement. The user can then correct their swing form based on this.

[0974] (Application example 2)

[0975] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0976] Robots performing various tasks in factories lack appropriate feedback to improve the efficiency and accuracy of their operations. Furthermore, there is a lack of means to analyze the robot's behavior and the causes of errors in real time and determine the need for maintenance or updates. This leads to problems such as reduced work efficiency and delays in maintenance, which can easily lead to problems.

[0977] The specific processing 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 user's swing motion with a camera, means for transmitting the recorded video data to the server, means for analyzing the video data and evaluating the swing form, means for analyzing the robot's motion in real time and generating feedback to improve the accuracy and efficiency of the motion, means for monitoring the robot's status and providing appropriate maintenance advice, and means for transmitting the feedback to the terminal and displaying it to the user. This makes it possible to analyze the robot's motion in real time and provide feedback to improve efficiency and accuracy, as well as to monitor the robot's status and perform appropriate maintenance.

[0978] A "camera" is a video device used to record the actions of the user or robot.

[0979] "Recorded video data" refers to video data collected by a camera.

[0980] A "server" is a computer system that receives and analyzes recorded video data.

[0981] "Swing form evaluation" refers to analyzing the user's swing motion based on the recorded video data and determining whether it is good or bad.

[0982] "Feedback" refers to advice or instructions provided to the user or robot based on the analysis results.

[0983] "Real-time" means that processing is done almost simultaneously and the results are reflected immediately.

[0984] "Robot movement analysis" refers to the detailed analysis of a robot's movements using recorded video data.

[0985] "Motion accuracy" is an index that indicates how accurate a robot's movements are relative to set goals or standards.

[0986] "Operation efficiency" is a measure of how efficiently a robot works to achieve its objectives.

[0987] "Maintenance advice" involves analyzing the robot's operation and condition and proposing necessary maintenance and repairs.

[0988] "Terminals" are devices that users and engineers use to receive feedback, such as computers and smartphones.

[0989] "Transmitting video data" means transferring the recorded video data to a server via a network.

[0990] "Feedback to improve the accuracy and efficiency of movements" refers to feedback that includes instructions and advice to make the robot's movements more accurate and efficient.

[0991] "Robot status" refers to the operational status of the robot, such as how it is currently operating and whether any errors have occurred.

[0992] "Users" are people or engineers who use the system and receive feedback.

[0993] A system for realizing this invention includes a camera, a server, a terminal, and dedicated software. The system program records user actions with the camera, transmits the recorded video data to the server, analyzes the data, transmits generated feedback to the terminal, and displays the feedback.

[0994] The server receives video footage of the user's movements captured by the camera and analyzes the video data in real time using OpenCV. Feature extraction uses an algorithm that recognizes the user's shoulders, elbows, waist, etc. from the video. The software used is OpenCV for video processing and TensorFlow for loading the machine learning model.

[0995] In particular, the server analyzes recorded video and real-time feeds using an emotion engine powered by TensorFlow. This emotion engine recognizes the user's emotions in real time from camera footage and audio data, enabling feedback that takes into account the user's mental state.

[0996] As an example, consider the analysis of the movements of a robot working in a factory. A camera records the robot's movements and sends the recorded video data to a server. The server receives the video data, analyzes it using OpenCV, and evaluates the robot's movement accuracy and efficiency. It then uses an emotion engine to analyze the robot's condition and the cause of any movement errors, and generates necessary maintenance advice. As a result, specific advice such as "correct the angle of the arm" or "perform regular maintenance" is sent as feedback and displayed on the terminal.

[0997] An example of a prompt is as follows:

[0998] "Analyze the robot's working movements, generate optimal movement patterns, and provide feedback. Also, monitor the robot's condition and provide appropriate maintenance advice. The video of the robot's movements contains key feature point data such as shoulders, elbows, and waists. Generate movement feedback based on the feature point data, and perform emotion analysis using an emotion recognition engine."

[0999] Based on this prompt, the generative AI model generates specific feedback, enabling the system to provide real-time behavioral feedback and emotion-based advice to the user.

[1000] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1001] Step 1:

[1002] The user installs a camera and records the robot's movements. For example, a Logitech HD Pro Webcam C920 is used as the camera. The input is the recorded video and audio data. The output is real-time video and audio data acquired from the camera.

[1003] Step 2:

[1004] The device sends the recorded video and audio data to the server. When sending the data, it is appropriately compressed and encrypted. The input is the video and audio data acquired from the camera. The output is the compressed and encrypted video and audio data.

[1005] Step 3:

[1006] The server analyzes the received video data in real time using OpenCV. This analysis extracts feature points from each part of the robot (e.g., shoulders, elbows, waist, etc.) for each video frame. The input is compressed and encrypted video data sent from the terminal. The output is the analysis results, including feature point data.

[1007] Step 4:

[1008] The server uses an emotion engine based on TensorFlow to recognize the robot's state from video and audio data. This analysis determines whether the robot is operating normally or if an error has occurred. The input is feature point data and audio data. The output is the analysis result regarding the robot's state.

[1009] Step 5:

[1010] The server evaluates the accuracy and efficiency of the robot's movements based on the analysis results and generates feedback. Specifically, it generates feedback indicating where movement corrections and maintenance are needed. The input is the analysis results from the video data analysis and emotion engine. The output is the generated feedback.

[1011] Step 6:

[1012] The server sends the generated feedback to the terminal. The terminal displays the received feedback to the user in text and / or visual form. The input is the generated feedback. The output is the transmission and display of the feedback data to the terminal.

[1013] Step 7:

[1014] The user reviews the feedback and adjusts the robot's behavior as necessary. The user also creates a maintenance plan for the next maintenance based on the feedback. The input is the feedback content. The output is the revised robot's behavior and maintenance plan.

[1015] Step 8:

[1016] The device re-records the modified robot's movements and transmits the new video data to the server, starting a new analysis and feedback cycle. The input is the video of the modified robot's movements. The output is the transmission of the re-recorded video data.

[1017] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1018] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1019] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1020] [Fourth embodiment]

[1021] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1022] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1024] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1025] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1026] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1028] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1029] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1030] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1032] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1034] This invention is a system aimed at improving golf swing skills, and helps improve swing form by analyzing the user's swing motion recorded on a camera in real time and providing feedback.

[1035] Overview of program processing

[1036] Data collection

[1037] The user sets up a camera at a driving range or at home and records their swing. The camera can be any camera device, such as a smartphone or a dedicated camera.

[1038] Video data transmission

[1039] The device sends the recorded video data to the server. The video data is sent in a compressed and encrypted format, ensuring security.

[1040] Receiving and analyzing video data

[1041] The server receives the video data sent from the device and begins analyzing the swing form using an AI model. During the analysis, the characteristic points of the human body (shoulders, elbows, hips, etc.) are extracted for each frame of the video, and the swing trajectory, body rotation, club angle, etc. are evaluated.

[1042] Feedback Generation

[1043] The server generates feedback for the user based on the analysis results. The feedback includes identifying the problem and providing specific advice for improvement. For example, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[1044] Send and view feedback

[1045] The server sends the generated feedback to the device, which then displays it to the user. The feedback is displayed as text or visual content, and the user can refer to it to correct their swing form.

[1046] Specific examples

[1047] 1. The user swings in their home practice room. The user sets up their smartphone on a tripod and records their swing.

[1048] 2. After recording, the device automatically sends the video data to the server. The data is properly compressed and encrypted before being sent.

[1049] 3. The server analyzes the received video data and extracts the swing form's characteristics, such as shoulder movement, hip rotation, and club trajectory.

[1050] 4. Based on the analysis results, the server generates feedback such as, "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing."

[1051] 5. The server sends the generated feedback to the device and displays it to the user in real time. The device displays the feedback in text and image format, allowing the user to correct their swing based on it.

[1052] 6. After reviewing the feedback, the user re-records a new swing with corrections and submits it to the system, which then receives new analysis and feedback. By repeating this process, the user can efficiently and effectively improve their swing form.

[1053] In this way, the present invention provides a specific system for supporting users in improving their golf skills, allowing users to properly understand their own swing form and efficiently improve their skills without the need for guidance from a professional coach.

[1054] The processing flow will be explained below.

[1055] Program processing steps

[1056] Step 1: Recording

[1057] User:

[1058] Set up the camera in an appropriate position and record your swing using a smartphone or dedicated camera.

[1059] Step 2: Sending video data

[1060] Device:

[1061] The recorded video data is sent to the server in a compressed and encrypted format to ensure security.

[1062] Step 3: Receiving video data

[1063] server:

[1064] Receives video data sent from the terminal. After receiving, checks the data for consistency and format.

[1065] Step 4: Preprocessing

[1066] server:

[1067] The received video data is processed before analysis, specifically by extracting frames, adjusting resolution, and removing noise if necessary.

[1068] Step 5: Feature point extraction

[1069] server:

[1070] An AI model is used to extract body features (shoulders, elbows, hips, etc.) from each frame, providing data for specific analysis of swing form movements.

[1071] Step 6: Form evaluation

[1072] server:

[1073] The user's swing form is evaluated based on the extracted feature points, including the swing trajectory, body balance, and club position.

[1074] Step 7: Identify the problem

[1075] server:

[1076] Based on the evaluation results, problems with the swing form are identified. For example, specific areas such as "insufficient rotation of the right shoulder" are identified.

[1077] Step 8: Advice Generation

[1078] server:

[1079] It generates specific advice for improvement based on identified problems, such as "Try to pull your left shoulder back during the backswing to increase the rotation of your right shoulder."

[1080] Step 9: Send your feedback

[1081] server:

[1082] Send the generated feedback to the device, which may include textual and / or visual guidance.

[1083] Step 10: Feedback display

[1084] Device:

[1085] The system receives feedback sent from the server and displays it to the user, including frame-by-frame images of problematic swings along with specific advice.

[1086] Step 11: User confirmation and correction

[1087] User:

[1088] Check the feedback displayed on your device and use it to modify your next swing. Use the feedback to try a new swing.

[1089] Step 12: Continuing the improvement process

[1090] User:

[1091] The corrected swing is then filmed again and the process is repeated from step 1. The user utilizes the feedback to continually improve their skills.

[1092] By repeating this series of steps, the user can improve their swing form accurately and efficiently.

[1093] Example 1

[1094] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1095] Current methods for improving golf swing skills (e.g., video analysis and direct instruction from a coach) are expensive and have the drawback of not providing real-time feedback. Therefore, there is a need for a system that allows users to easily analyze their swing form at home or at a driving range and receive real-time feedback. Furthermore, the difficulty of providing optimized feedback for each individual user is also an issue that needs to be resolved.

[1096] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1097] In this invention, the server includes a means for using a camera to record the user's movements, a means for transmitting the data recorded by the camera to an information processing device, a means for analyzing the data and evaluating the movements in the information processing device, a means for generating feedback for the user based on the evaluation results, and a means for transmitting the feedback to the terminal and displaying it to the user. This allows users to easily analyze their own swing form and receive efficient feedback. Furthermore, feedback generated using an artificial intelligence model can provide advice optimized for each individual user in real time.

[1098] "Capture device" refers to a camera or video recording device for recording a user's actions.

[1099] "Information processing device" refers to a computer or server that receives and analyzes the recorded data.

[1100] "User" refers to an individual who uses the system to analyze their swing form and receive feedback.

[1101] "Data" refers to video information of the user's swing motion captured by a camera.

[1102] "Analysis" refers to a process in which an information processing device processes data to extract and evaluate features of a user's actions.

[1103] "Evaluation" refers to the act of judging whether a user's behavior is good or bad based on the analyzed data and identifying areas for improvement.

[1104] "Feedback" refers to advice or guidance provided to the user based on the evaluation results.

[1105] "Device" refers to the device (such as a smartphone or tablet) that a user uses to receive feedback.

[1106] "Artificial intelligence model" refers to the machine learning and deep learning algorithms used to analyze data and generate feedback.

[1107] "Evaluation results" refer to information about the user's behavior and diagnostic results derived during the analysis process.

[1108] "Means using a photographing device" refers to the act of a user recording their own swing motion with a video or camera.

[1109] "Transmitting means" refers to the process of transferring data from the image capture device to the information processing device.

[1110] "Means for displaying" refers to a method for conveying feedback to the user visually or audibly.

[1111] This invention is a system aimed at improving golf swing skills, and helps improve swing form by analyzing the user's swing motion recorded on a camera in real time and providing feedback.

[1112] System configuration

[1113] Data collection

[1114] The user sets up a camera at a driving range or at home and records their swing. The camera can be any type of camera, such as a smartphone or a dedicated camera. For example, the user sets up their smartphone on a tripod and records their swing. A frame rate of at least 30 fps is recommended for recording.

[1115] Video data transmission

[1116] The device (such as a smartphone or dedicated camera) transmits the recorded video data to the server. At this time, the video data is encoded in a compressed format such as H.264 and transmitted over an encrypted communication channel using SSL / TLS, thereby maintaining the privacy and integrity of the data.

[1117] Video data reception and preprocessing

[1118] The server receives the video data sent from the device. After receiving it, it decodes and preprocesses the data. Specifically, it uses libraries such as FFmpeg to split the video data into frames and prepares it in a format that can be analyzed by the AI ​​model. For example, it adjusts the resolution and color.

[1119] Swing form analysis

[1120] The server inputs the preprocessed frame data into an AI model to analyze the swing form. For example, it uses a human pose estimation model such as OpenPose to extract feature points such as shoulders, elbows, and hips for each frame. It then evaluates the swing trajectory, body rotation, and club angle to identify areas that need improvement.

[1121] Feedback Generation

[1122] The server generates feedback for the user based on the analysis results. The generative AI model receives prompts based on the analysis results to provide specific advice. For example, the generated advice might be, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[1123] Send and view feedback

[1124] The server sends the generated feedback to the device. The device then displays the received feedback to the user. At this time, a dedicated application is used to display the feedback in an easy-to-understand manner as text or visual content. For example, the feedback may include an arrow indicating "pull your left shoulder during the backswing" or an image containing supplementary explanations.

[1125] Specific examples

[1126] 1. The user sets up a smartphone on a tripod in their home practice room and records their swing. The camera angle is adjusted so that the full swing is clearly captured on screen.

[1127] 2. After recording, the device automatically compresses the video data in H.264 format and sends it to the server using SSL / TLS encrypted communication.

[1128] 3. The server uses FFmpeg to decode the received video data, split it into frames, adjust the resolution and color, and convert it into a format that is easy for the AI ​​model to analyze.

[1129] 4. The server inputs the frame data into the OpenPose model and extracts feature points such as shoulders, elbows, and hips. It then evaluates the swing trajectory, body rotation, and club angle based on the extracted data.

[1130] 5. The server uses a generative AI model to generate feedback such as, "Your right shoulder isn't rotating enough, so try pulling your left shoulder back more during the backswing."

[1131] 6. The server sends the generated feedback to the device and displays it to the user. The device displays the feedback in text and image format, and the user corrects their swing based on it. By repeating this process, the user can improve their swing form efficiently and effectively.

[1132] Example of input prompt for generative AI model

[1133] "Look at the motion of my golf swing. Evaluate whether my right shoulder is rotating properly, whether the club path is correct, and whether my feet are positioned properly, and provide advice on how to improve my swing form."

[1134] In this way, the present invention provides a specific method for helping users improve their golf skills.

[1135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1136] Step 1:

[1137] The user sets up a recording device at a driving range or at home and records their swing. Specifically, the user sets up a smartphone on a tripod and records their swing as a video. The input is a swing video recorded with a smartphone or dedicated camera, and the output is a video file.

[1138] Step 2:

[1139] The device compresses the recorded video file and sends it to the server. At this time, it is encoded in a compression format such as H.264 and uses SSL / TLS encrypted communication. The input is the recorded video file, and the output is compressed and encrypted video data.

[1140] Step 3:

[1141] The server receives the video data sent from the device and performs decoding and preprocessing. Specifically, it uses FFmpeg to divide the video into frames and adjust the resolution and color. The input is compressed and encrypted video data, and the output is preprocessed frame data.

[1142] Step 4:

[1143] The server inputs the preprocessed frame data into the AI ​​model and analyzes the swing form. Specifically, it uses a human body pose estimation model such as OpenPose to extract feature points such as shoulders, elbows, and hips for each frame. The input is the preprocessed frame data, and the output is feature point data.

[1144] Step 5:

[1145] The server evaluates the swing form based on the extracted feature point data and generates feedback. Using the generative AI model, a prompt sentence is input that provides specific advice based on the analysis results. The input is the feature point data and the analysis results, and the output is feedback text. For example, the generated feedback might be, "Your right shoulder is not rotating enough, so pull your left shoulder back more during the backswing."

[1146] Step 6:

[1147] The server sends the generated feedback to the terminal. The terminal displays the received feedback to the user. Using a dedicated application, the feedback is displayed in an easy-to-understand manner as text or visual content. The input is the feedback text, and the output is the feedback displayed to the user. For example, an arrow indicating "pull your left shoulder during the backswing" or an image containing additional explanations is displayed as feedback.

[1148] Step 7:

[1149] The user reviews the feedback and modifies their swing form based on it. They then re-record their modified swing motion and repeat the process from step 1. This allows the user to efficiently and effectively improve their swing form. The input is the modified swing motion, and the output is a new swing form with the modifications.

[1150] (Application example 1)

[1151] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1152] Conventional optimization of industrial machine operations often requires expensive sensors and specialized analytical equipment, or manual evaluation by skilled engineers, resulting in significant increases in cost and time. Furthermore, there is variation in feedback quality, and there is a lack of mechanisms for automatically learning and improving optimal operations. Furthermore, it is difficult to evaluate work operations and provide feedback in real time, hindering efficient automation.

[1153] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1154] In this invention, the server includes means for recording the work operations of the industrial machine using a camera, means for transmitting the recorded video data to the server, means for analyzing the video data and evaluating the work operations, means for generating feedback based on the evaluation results, means for transmitting the feedback to the terminal and displaying it to the user, and means for optimizing the work operations of the industrial machine, thereby making it possible to optimize the work operations of the industrial machine efficiently and with high accuracy.

[1155] A "camera" is a device that captures images of objects, and is an optical instrument that records still images and videos.

[1156] The term "user" refers to a person who uses the system of the present invention to record swing movements and work movements and receives evaluations and feedback.

[1157] "Recorded video data" refers to digital data of moving images and still images recorded by a camera.

[1158] The "server" is a central processing unit that analyzes the recorded video data and generates and transmits evaluations and feedback.

[1159] "Analysis" is the process of extracting movement characteristics from recorded video data and evaluating them.

[1160] "Feedback" refers to evaluation and advice information provided based on the analysis results, with the aim of improving work operations.

[1161] A "terminal" is a device that displays feedback to the user and manages received data.

[1162] "Industrial machinery" refers to machinery and equipment used in factories and production lines that performs specific tasks automatically or semi-automatically.

[1163] A "work action" is a specific movement or procedure performed by industrial machinery that is part of a production process.

[1164] "Work motion evaluation" is a process of evaluating the efficiency and accuracy of work based on the feature points and motion trajectories extracted through analysis.

[1165] "Optimization" is the process of efficiently and accurately adjusting and improving a target operation or process based on this feedback.

[1166] A system for implementing this invention includes a camera, a server, and a terminal, and is used to optimize the operation of industrial machinery. This system evaluates the work operation of the industrial machinery in real time and provides efficient and highly accurate feedback.

[1167] First, a camera is installed on an industrial machine operating in a factory, and its operation is recorded. The camera can be a general-purpose camera such as a Raspberry Pi camera module. The video data recorded by the camera is sent to a server via HTTP communication using a Python script. The data is compressed and encrypted during transmission to ensure security.

[1168] The server receives and analyzes the recorded video data. This analysis uses machine learning libraries such as TensorFlow and PyTorch to extract characteristic features of the industrial machinery's work movements (for example, joint angles and movement trajectories). Based on the analysis results, problems are identified and feedback is generated. The feedback includes specific improvements and advice.

[1169] The generated feedback is sent from the server to the terminal, which acts as a user device and displays the feedback in text and visual form, and is automatically reflected in the robot's control system, for example, using the MQTT protocol.

[1170] The following hardware and software are used to process this program:

[1171] Camera: Raspberry Pi camera module

[1172] Sending data: Python, Requests library

[1173] Data analysis: TensorFlow, PyTorch, Docker

[1174] Feedback transmission: MQTT protocol

[1175] As a concrete example, consider the case of improving the operation of an assembly robot on a production line. For example, if an issue occurs when attaching a part due to an improper wrist joint angle, the system analyzes the recorded data and generates feedback such as "the wrist angle is 5 degrees too short." The robot's operation program is then updated based on this feedback, resolving the problem.

[1176] As an example of a prompt, you could input the following instructions to a generative AI model:

[1177] "After analyzing the robot's motion, we found that the wrist angle is 5 degrees short. Please explain how to change the settings of the wrist joint module to increase the wrist angle by 5 degrees."

[1178] This allows the generative AI model to provide specific advice on changing settings, resulting in more accurate performance improvements.

[1179] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1180] Step 1:

[1181] The user records the operation of industrial machinery with a camera. The camera can be a fixed camera installed in the factory or a camera attached to a robot. The input is the video of the industrial machinery in operation, and the output is the recorded video data. The specific operation involves placing the camera in an appropriate position and pressing a button to start recording the video.

[1182] Step 2:

[1183] The device compresses and encrypts the recorded video data before sending it to the server. The input is the recorded video data, and the output is the compressed and encrypted video data. Specifically, the device uses a Python script to convert the video data into an appropriate format and uploads it to the server using HTTP communication.

[1184] Step 3:

[1185] The server decrypts the received compressed and encrypted video data and performs data analysis. The input is the compressed and encrypted video data, and the output is the analysis results. Specifically, after the decoding process, TensorFlow and PyTorch are used to extract feature points (joint angles, movement trajectories, etc.) from the video and evaluate the movement.

[1186] Step 4:

[1187] The server generates feedback based on the analysis results. The input is the analysis results, and the output is feedback information. Specifically, it automatically generates improvement measures and advice based on problems identified from the analysis results. For example, in response to an evaluation result that "the wrist angle is 5 degrees short," it provides specific advice on how to increase the wrist angle by 5 degrees.

[1188] Step 5:

[1189] The server sends the generated feedback to the terminal and displays it to the user. The input is the feedback information, and the output is the feedback displayed on the user's terminal. Specifically, the server converts the feedback information into text or visual format and sends it to the terminal.

[1190] Step 6:

[1191] The terminal displays the received feedback information to the user and reflects it in the robot's control system. The input is the feedback information sent from the server, and the output is a control program that reflects the feedback. Specifically, the terminal displays the feedback content on the screen, sends instructions to the robot control system using the MQTT protocol, and updates the program.

[1192] Step 7:

[1193] The user re-records the operation of the industrial machine based on the updated control program and confirms the optimized operation. The input is the updated control program, and the output is the re-recorded video data and the operation evaluation results. Specifically, the operation video is recorded again with a camera, and the process is repeated from the first step 1.

[1194] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1195] This invention is a system aimed at improving golf swing skills. It not only analyzes the user's swing motion captured on a camera in real time and provides feedback, but also combines it with an emotion engine that recognizes the user's emotions to provide feedback that takes into account the user's motivation and mental state.

[1196] Overview of program processing

[1197] Data collection

[1198] Users set up a camera at a driving range or at home to record their swing. The camera can be any device, such as a smartphone or a dedicated camera. The emotion engine analyzes the user's emotions in real time from the camera footage and audio data.

[1199] Video data transmission

[1200] The device sends the recorded video data and emotion data to a server. The data is sent in a compressed and encrypted format, ensuring security.

[1201] Receiving and analyzing video data

[1202] The server receives the video and emotion data sent from the device and begins analyzing the swing form using an AI model. During the analysis, human body features (shoulders, elbows, hips, etc.) are extracted for each frame of video, and the swing trajectory, body rotation, club angle, etc. are evaluated. In addition, the emotion engine analyzes the user's emotional state.

[1203] Feedback Generation

[1204] The server generates feedback for the user based on the analysis results. The feedback includes identifying problems and providing specific advice for improvement. Furthermore, by taking emotional data into consideration, feedback appropriate to the user's mental state can be provided. For example, if the user is feeling tense, advice to relax may be added.

[1205] Send and view feedback

[1206] The server sends the generated feedback to the device, which then displays it to the user. The feedback is displayed as text and visual content, allowing the user to refer to it and correct their swing form. Additional advice based on emotion data is also displayed.

[1207] Specific examples

[1208] 1. The user takes a swing in their home practice room. The user sets up their smartphone on a tripod and records their swing. The camera and microphone are used to record the swing, and the user's facial expressions and voice are also captured.

[1209] 2. After recording, the device automatically sends the video and emotion data to the server. The data is appropriately compressed and encrypted before being sent.

[1210] 3. The server analyzes the received video data and emotional data to extract the swing form features and the user's emotional state, such as shoulder movement, hip rotation, and club trajectory.

[1211] 4. Based on the analysis results, the server generates feedback such as, "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing." In addition, if it determines that the user is tense, it also adds advice such as, "Take a deep breath and relax."

[1212] 5. The server sends the generated feedback to the device and displays it to the user in real time. The device displays the feedback in text and image format, allowing the user to correct their swing based on that feedback. Emotion-based advice is also displayed simultaneously.

[1213] 6. After reviewing the feedback, the user re-records a new swing with corrections and submits it to the system, which then receives new analysis and feedback. By repeating this process, the user can efficiently and effectively improve their swing form.

[1214] In this way, the present invention not only provides a specific system for supporting the improvement of a user's golf skills, but also, by combining it with an emotion engine, enables feedback that takes into account the user's mental state, allowing the user to properly understand their own swing form and continue practicing with peace of mind, even without guidance from a professional coach.

[1215] The processing flow will be explained below.

[1216] Program processing steps

[1217] Step 1: Video recording and emotional data acquisition

[1218] User:

[1219] The camera and microphone are placed in appropriate positions to record your swing, facial expressions, and voice. The camera and microphone can be a smartphone or a dedicated device.

[1220] Step 2: Sending video data and emotion data

[1221] Device:

[1222] The recorded video data and emotion data are sent to the server in a compressed and encrypted format, and a notification is sent when the data is complete.

[1223] Step 3: Receiving video and emotion data

[1224] server:

[1225] Receives video data and emotion data sent from the device. After receiving, checks the data for consistency and format.

[1226] Step 4: Preprocessing

[1227] server:

[1228] The received video data is processed before analysis. Specifically, frames are extracted, resolution is adjusted, and noise is removed as necessary. Emotion data is also converted into an analyzable format.

[1229] Step 5: Feature point extraction

[1230] server:

[1231] It uses an AI model to extract human body features from each frame of video, pinpointing the positions of shoulders, elbows, hips, etc., and analyzing their movements.

[1232] Step 6: Sentiment Analysis

[1233] server:

[1234] An emotion engine is used to analyze the user's emotional state from recorded facial expressions and voice, identifying states such as tension, excitement, and relaxation.

[1235] Step 7: Form evaluation and emotional alignment

[1236] server:

[1237] Based on the extracted features, the system evaluates the user's swing form, including swing trajectory, body balance, and club position, while also taking into account their emotional state.

[1238] Step 8: Identify the problem

[1239] server:

[1240] Based on form evaluation and emotion analysis results, it identifies which part of the swing is problematic. For example, it identifies "insufficient rotation of the right shoulder" and takes into account if the user is tense.

[1241] Step 9: Advice Generation

[1242] server:

[1243] Based on the identified issues and the user's emotional state, the system generates specific feedback for improvement, such as "Try to pull your left shoulder back during the backswing to increase the rotation of your right shoulder. Take a deep breath to relax."

[1244] Step 10: Send feedback

[1245] server:

[1246] Sends generated feedback to the device, including textual and visual guides.

[1247] Step 11: Feedback display

[1248] Device:

[1249] The feedback sent from the server is received and displayed to the user, who can see frame-by-frame images of problematic swings and emotion-based advice along with specific advice.

[1250] Step 12: User confirmation and correction

[1251] User:

[1252] Check the feedback displayed on your device and modify your next swing based on it. Try a new swing based on the feedback and emotional advice.

[1253] Step 13: Continuing the improvement process

[1254] User:

[1255] The corrected swing is then recorded again and the process is repeated from step 1. The user utilizes feedback and emotional advice to continually improve their skills.

[1256] By repeating this series of steps, users can improve their swing form accurately and efficiently, and continue practicing with peace of mind.

[1257] Example 2

[1258] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1259] Conventional golf swing training systems focus only on the user's swing form and are unable to provide feedback that takes into account the user's mental state or motivation, resulting in limited improvement. Furthermore, the feedback provided is uniform, and individualized responses to each user are insufficient. This makes it difficult to effectively improve a user's swing form and also lacks motivation to continue practicing over the long term.

[1260] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving video data and emotion data, means for analyzing the received data and evaluating the swing form, means for analyzing the user's emotion state using an emotion engine, means for generating feedback for the user based on the analysis results, and means for transmitting the feedback to the terminal and displaying it to the user. This makes it possible to provide feedback that takes into account not only the user's swing form but also their mental state and motivation, enabling effective skill improvement and motivation for continuous practice.

[1261] A "camera" is an optical device for recording a user's swing motion.

[1262] A "terminal" is an electronic device that transmits recorded video data and emotional data to a server and displays feedback to the user.

[1263] The "server" is a centralized management system for receiving video data and emotion data, analyzing them, and generating feedback.

[1264] "Video data" is video information of the user's swing motion captured by a camera.

[1265] "Emotion data" is information that indicates the emotional state of the user based on sensor data from a camera, microphone, etc.

[1266] An "emotion engine" is software or an algorithm for analyzing a user's emotional state from video and audio data.

[1267] "Swing form" refers to the configuration of each part of the body, such as the position and angle, during a user's golf swing motion.

[1268] "Feedback" is information that includes advice on improving the user's swing form and depending on the user's emotional state based on the analysis results.

[1269] A "generative AI model" is an artificial intelligence model trained to generate feedback based on a user's swing form and emotional state.

[1270] MODE FOR CARRYING OUT THE INVENTION

[1271] This invention is a system aimed at improving a user's golf swing skills, analyzing the user's swing motion captured by a camera in real time and providing feedback. Furthermore, by combining it with an emotion engine, it is possible to provide feedback that takes into account the user's motivation and mental state. This system is described in detail below.

[1272] Hardware and software used

[1273] The user records their swing using a smartphone or a dedicated camera. This allows for the acquisition of video data. Audio data can also be collected using a microphone. This recording device can be any commercially available camera or microphone.

[1274] The device is an electronic device that transmits the recorded video data and emotion data to the server. This device can be a typical smartphone, tablet, or PC. An application for collecting data is installed on the device, and it has the function of compressing and encrypting the recorded data before transmitting it to the server.

[1275] The server is a centralized management system that analyzes the received video and emotion data and generates feedback, and can use high-performance computers and cloud services. A generative AI model and emotion engine are used for the analysis. The generative AI model analyzes and evaluates the swing form, and the emotion engine analyzes the user's emotional state from the video and audio data.

[1276] Data processing and calculation

[1277] When the server receives the video and emotion data sent from the device, it first preprocesses the data. This preprocessing involves dividing the video data into frames and extracting human body features (shoulders, elbows, hips, etc.) from each frame. Next, it uses a generative AI model to analyze the swing form and evaluate the swing trajectory, body rotation, club angle, etc.

[1278] At the same time, an emotion engine is used to analyze the user's emotional data. For example, emotional states such as tension, joy, or irritation can be detected from the user's facial expressions and tone of voice. This allows the user's mental state to be understood.

[1279] The server generates feedback based on the analysis results. This feedback identifies problems with the swing form and includes specific advice for improvement. Furthermore, by taking emotional data into consideration, feedback appropriate to the user's mental state is provided. For example, if the right shoulder rotation is insufficient, the server generates advice such as "Try pulling your left shoulder back a bit more during the backswing." Furthermore, if the user is feeling tense, the server adds advice such as "Take a deep breath and relax."

[1280] The generated feedback is sent to the device and displayed to the user as text and visual content, allowing the user to refer to it and correct their swing form.

[1281] Specific examples

[1282] 1. The user sets up their smartphone on a tripod in their home practice room and records their swing. The camera and microphone are used to record the user's facial expressions and voice.

[1283] 2. After recording, the device automatically transmits the video and emotion data to the server, where the data is compressed and encrypted.

[1284] 3. The server uses the received data to extract and analyze the swing form's characteristics, such as shoulder movement, hip rotation, and club trajectory.

[1285] 4. The emotion engine analyzes the user's emotional state from video and audio data and detects when the user is nervous.

[1286] 5. Based on the analysis results, the server generates feedback such as "Your right shoulder is not rotating enough, so try pulling your left shoulder back a bit more during the backswing," along with advice such as "Take a deep breath and relax."

[1287] 6. This feedback is sent to the device and displayed to the user in real time, allowing the user to refer to it to correct their swing form and continue practicing.

[1288] Prompt Sentence Examples

[1289] "Please describe a system that analyzes video footage of a user's golf swing and emotional data to provide feedback."

[1290] This system analyzes the user's movements and emotions in real time and provides appropriate feedback to improve the user's golf skills. By using an emotion engine, it is possible to provide instruction that takes into account the user's mental state.

[1291] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1292] Step 1: Data collection

[1293] A user sets up a camera at a driving range or at home and records their swing. For example, a user mounts a smartphone on a tripod, launches a camera app, and records their swing. The input data is video data and audio data. The output data is the recorded video and audio files. The user's facial expressions and voice are also collected during recording.

[1294] Step 2: Send data

[1295] After recording is complete, the device automatically transmits the video and emotion data to the server. At this time, the device first compresses and encrypts the data. For example, the video data is compressed in H.264 format and encrypted using AES. The input data are the recorded video and audio files. The output data is the compressed and encrypted data, which is then transmitted to the server via the Internet.

[1296] Step 3: Data reception and preprocessing

[1297] The server receives data sent from the terminal. After receiving the data, it first decompresses and decrypts it. For example, it decrypts AES-encrypted data and decompresses H.264-compressed data. The input data is the compressed and encrypted data. The output data is the original video and audio files.

[1298] Step 4: Swing form analysis

[1299] The server analyzes the video file frame by frame and extracts the body's feature points (shoulders, elbows, hips, etc.). For example, it uses the OpenPose library to identify the coordinates of each body part. The input data is the video file. The output data is the feature point coordinate data for each frame. Based on this data, the swing trajectory, body rotation, club angle, etc. are evaluated. Furthermore, analysis is performed using a generative AI model, enabling highly accurate evaluation.

[1300] Step 5: Sentiment Analysis

[1301] The server analyzes the user's emotional state from audio and video files. For example, audio analysis uses TensorFlow or OpenSMILE to analyze the tone and speed of the voice, and video analysis uses a facial expression recognition algorithm (e.g., FaceAPI) to identify the user's emotions. The input data are audio and video files. The output data is the analyzed emotional state information (e.g., joy, anger, tension, etc.).

[1302] Step 6: Feedback generation

[1303] The server generates feedback for the user based on the results of the swing form analysis and emotion analysis. For example, it generates technical advice such as "Your right shoulder rotation is insufficient, so try pulling your left shoulder back a bit more during your backswing," or emotion-based advice such as "Take a deep breath and relax." The input data are feature point coordinate data of the swing form and emotional state information. The output data is a feedback message.

[1304] Step 7: Send and view feedback

[1305] The server sends the generated feedback to the terminal. For example, data is sent using secure HTTP communication (HTTPS). The input data is the feedback message. The output data is the feedback message sent to the terminal. The terminal displays the received feedback to the user. The display format is provided as text and image content. For example, the application displays the text "Your right shoulder rotation is insufficient" along with an illustration showing the corresponding movement. The user can then correct their swing form based on this.

[1306] (Application example 2)

[1307] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1308] Robots performing various tasks in factories lack appropriate feedback to improve the efficiency and accuracy of their operations. Furthermore, there is a lack of means to analyze the robot's behavior and the causes of errors in real time and determine the need for maintenance or updates. This leads to problems such as reduced work efficiency and delays in maintenance, which can easily lead to problems.

[1309] The specific processing 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 user's swing motion with a camera, means for transmitting the recorded video data to the server, means for analyzing the video data and evaluating the swing form, means for analyzing the robot's motion in real time and generating feedback to improve the accuracy and efficiency of the motion, means for monitoring the robot's status and providing appropriate maintenance advice, and means for transmitting the feedback to the terminal and displaying it to the user. This makes it possible to analyze the robot's motion in real time and provide feedback to improve efficiency and accuracy, as well as to monitor the robot's status and perform appropriate maintenance.

[1310] A "camera" is a video device used to record the actions of the user or robot.

[1311] "Recorded video data" refers to video data collected by a camera.

[1312] A "server" is a computer system that receives and analyzes recorded video data.

[1313] "Swing form evaluation" refers to analyzing the user's swing motion based on the recorded video data and determining whether it is good or bad.

[1314] "Feedback" refers to advice or instructions provided to the user or robot based on the analysis results.

[1315] "Real-time" means that processing is done almost simultaneously and the results are reflected immediately.

[1316] "Robot movement analysis" refers to the detailed analysis of a robot's movements using recorded video data.

[1317] "Motion accuracy" is an index that indicates how accurate a robot's movements are relative to set goals or standards.

[1318] "Operation efficiency" is a measure of how efficiently a robot works to achieve its objectives.

[1319] "Maintenance advice" involves analyzing the robot's operation and condition and proposing necessary maintenance and repairs.

[1320] "Terminals" are devices that users and engineers use to receive feedback, such as computers and smartphones.

[1321] "Transmitting video data" means transferring the recorded video data to a server via a network.

[1322] "Feedback to improve the accuracy and efficiency of movements" refers to feedback that includes instructions and advice to make the robot's movements more accurate and efficient.

[1323] "Robot status" refers to the operational status of the robot, such as how it is currently operating and whether any errors have occurred.

[1324] "Users" are people or engineers who use the system and receive feedback.

[1325] A system for realizing this invention includes a camera, a server, a terminal, and dedicated software. The system program records user actions with the camera, transmits the recorded video data to the server, analyzes the data, transmits generated feedback to the terminal, and displays the feedback.

[1326] The server receives video footage of the user's movements captured by the camera and analyzes the video data in real time using OpenCV. Feature extraction uses an algorithm that recognizes the user's shoulders, elbows, waist, etc. from the video. The software used is OpenCV for video processing and TensorFlow for loading the machine learning model.

[1327] In particular, the server analyzes recorded video and real-time feeds using an emotion engine powered by TensorFlow. This emotion engine recognizes the user's emotions in real time from camera footage and audio data, enabling feedback that takes into account the user's mental state.

[1328] As an example, consider the analysis of the movements of a robot working in a factory. A camera records the robot's movements and sends the recorded video data to a server. The server receives the video data, analyzes it using OpenCV, and evaluates the robot's movement accuracy and efficiency. It then uses an emotion engine to analyze the robot's condition and the cause of any movement errors, and generates necessary maintenance advice. As a result, specific advice such as "correct the angle of the arm" or "perform regular maintenance" is sent as feedback and displayed on the terminal.

[1329] An example of a prompt is as follows:

[1330] "Analyze the robot's working movements, generate optimal movement patterns, and provide feedback. Also, monitor the robot's condition and provide appropriate maintenance advice. The video of the robot's movements contains key feature point data such as shoulders, elbows, and waists. Generate movement feedback based on the feature point data, and perform emotion analysis using an emotion recognition engine."

[1331] Based on this prompt, the generative AI model generates specific feedback, enabling the system to provide real-time behavioral feedback and emotion-based advice to the user.

[1332] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1333] Step 1:

[1334] The user installs a camera and records the robot's movements. For example, a Logitech HD Pro Webcam C920 is used as the camera. The input is the recorded video and audio data. The output is real-time video and audio data acquired from the camera.

[1335] Step 2:

[1336] The device sends the recorded video and audio data to the server. When sending the data, it is appropriately compressed and encrypted. The input is the video and audio data acquired from the camera. The output is the compressed and encrypted video and audio data.

[1337] Step 3:

[1338] The server analyzes the received video data in real time using OpenCV. This analysis extracts feature points from each part of the robot (e.g., shoulders, elbows, waist, etc.) for each video frame. The input is compressed and encrypted video data sent from the terminal. The output is the analysis results, including feature point data.

[1339] Step 4:

[1340] The server uses an emotion engine based on TensorFlow to recognize the robot's state from video and audio data. This analysis determines whether the robot is operating normally or if an error has occurred. The input is feature point data and audio data. The output is the analysis result regarding the robot's state.

[1341] Step 5:

[1342] The server evaluates the accuracy and efficiency of the robot's movements based on the analysis results and generates feedback. Specifically, it generates feedback indicating where movement corrections and maintenance are needed. The input is the analysis results from the video data analysis and emotion engine. The output is the generated feedback.

[1343] Step 6:

[1344] The server sends the generated feedback to the terminal. The terminal displays the received feedback to the user in text and / or visual form. The input is the generated feedback. The output is the transmission and display of the feedback data to the terminal.

[1345] Step 7:

[1346] The user reviews the feedback and adjusts the robot's behavior as necessary. The user also creates a maintenance plan for the next maintenance based on the feedback. The input is the feedback content. The output is the revised robot's behavior and maintenance plan.

[1347] Step 8:

[1348] The device re-records the modified robot's movements and transmits the new video data to the server, starting a new analysis and feedback cycle. The input is the video of the modified robot's movements. The output is the transmission of the re-recorded video data.

[1349] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1350] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1351] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1352] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1353] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1354] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1355] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1356] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1357] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1358] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1359] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1360] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1361] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1362] 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.

[1363] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1364] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1365] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1366] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1367] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1368] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1369] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1370] The following is further disclosed regarding the above embodiment.

[1371] (Claim 1)

[1372] A means for recording a user's swing motion by a camera;

[1373] means for transmitting the recorded video data to a server;

[1374] a means for analyzing the video data and evaluating the swing form in the server;

[1375] means for generating feedback to the user based on the evaluation results;

[1376] means for transmitting said feedback to said terminal and displaying said feedback to a user;

[1377] A system including:

[1378] (Claim 2)

[1379] 10. The system of claim 1, further comprising means for accumulating practice data for each user and for continuously training the model.

[1380] (Claim 3)

[1381] 10. The system of claim 1, further comprising means for including audio advice in said feedback.

[1382] "Example 1"

[1383] (Claim 1)

[1384] means for using a camera to record the user's actions;

[1385] a means for transmitting data captured by the imaging device to an information processing device;

[1386] means for analyzing the data and evaluating the operation in the information processing device;

[1387] means for generating feedback to the user based on the evaluation results;

[1388] means for transmitting said feedback to said terminal and displaying said feedback to a user;

[1389] A system including:

[1390] (Claim 2)

[1391] 10. The system of claim 1, further comprising means for accumulating practice data for each user and for continuously training the model.

[1392] (Claim 3)

[1393] means for generating feedback based on the evaluation results using an artificial intelligence model;

[1394] 10. The system of claim 1, further comprising means for including audio advice in said feedback.

[1395] "Application Example 1"

[1396] (Claim 1)

[1397] A means for recording a user's swing motion by a camera;

[1398] means for transmitting the recorded video data to a server;

[1399] a means for analyzing the video data and evaluating the swing form in the server;

[1400] means for generating feedback to the user based on the evaluation results;

[1401] means for transmitting said feedback to said terminal and displaying said feedback to a user;

[1402] a means for recording the work operation of the industrial machine by the camera;

[1403] means for generating feedback based on the evaluation result of the work operation of the industrial machine and optimizing the work operation;

[1404] A system including:

[1405] (Claim 2)

[1406] 10. The system of claim 1, further comprising means for accumulating practice data for each user and for continuously training the model.

[1407] (Claim 3)

[1408] 10. The system of claim 1, further comprising means for including audio advice in said feedback.

[1409] "Example 2: Combining Emotion Engines"

[1410] (Claim 1)

[1411] A means for recording a user's swing motion by a camera;

[1412] means for transmitting the recorded video data and emotion data to a server;

[1413] a means for analyzing the video data and evaluating the swing form in the server;

[1414] means for analyzing a user's emotional state using an emotion engine;

[1415] means for generating feedback to the user based on the evaluation result and the emotion analysis result;

[1416] means for transmitting said feedback to said terminal and displaying said feedback to a user;

[1417] A system including:

[1418] (Claim 2)

[1419] 10. The system of claim 1, further comprising means for accumulating practice data and emotion data for each user and for continuously training the generative AI model.

[1420] (Claim 3)

[1421] 10. The system of claim 1, further comprising means for including audio advice in said feedback.

[1422] "Application example 2 when combining emotion engines"

[1423] (Claim 1)

[1424] A means for recording a user's swing motion by a camera;

[1425] means for transmitting the recorded video data to a server;

[1426] a means for analyzing the video data and evaluating the swing form in the server;

[1427] means for generating feedback to the user based on the evaluation results;

[1428] a means for analyzing the robot's motion in real time and generating feedback to improve the accuracy and efficiency of its motion;

[1429] means for monitoring the status of the robot and providing appropriate maintenance advice;

[1430] means for transmitting said feedback to said terminal and displaying said feedback to a user;

[1431] A system including:

[1432] (Claim 2)

[1433] 10. The system of claim 1, further comprising means for accumulating practice data for each user and for continuously training the model.

[1434] (Claim 3)

[1435] 10. The system of claim 1, further comprising means for including audio advice in said feedback. [Explanation of symbols]

[1436] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for recording a user's swing motion by a camera; means for transmitting the recorded video data to a server; a means for analyzing the video data and evaluating the swing form in the server; means for generating feedback to the user based on the evaluation results; means for transmitting said feedback to said terminal and displaying said feedback to a user; A system including:

2. 10. The system of claim 1, further comprising means for accumulating practice data for each user and for continuously training the model.

3. The system of claim 1 further comprising means for including audio advice in said feedback.

Images