system

Abstract

We provide the system. [Solution] An evaluation means for automatically evaluating the actions of a target operation by analyzing motion data acquired from a high-precision video acquisition means, A notification means that generates areas for improvement based on the analysis results and notifies the user via a visual display means, A means of providing a plan to support efficient and safe work by providing guidance plans based on the identified areas for improvement, A data transmission means for sending video data to a cloud server and performing analysis using a generated AI model, A feedback mechanism that generates analysis results using prompt messages and displays practical guidelines to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional motion analysis and improvement guidance methods have the problem that feedback is delayed and it is difficult to respond in real time. Also, with general analysis tools, it has been difficult to evaluate individual technical elements in detail and present a training plan optimized for each individual. As a result, it has not been possible to quickly support the technical growth of athletes, and there has been a limit to the improvement of competitiveness.

Means for Solving the Problems

[0005] This invention provides an evaluation device that analyzes video data acquired from a high-precision video acquisition device and automatically evaluates the motion of a target object, thereby enabling real-time technical evaluation. Furthermore, by providing a notification device that immediately notifies the user of areas for improvement based on the analysis results, rapid technical improvement can be achieved. In addition, by providing a training plan provision device that provides a training plan based on the notified areas for improvement, a system is realized that enables training optimized for each athlete and supports continuous performance improvement.

[0006] A "video acquisition device" is a device that captures high-precision video data and supplies it to an analysis device.

[0007] An "analysis device" is a device or a series of processes used to automatically evaluate the motion of a target object using acquired video data.

[0008] An "evaluation device" is a device that determines the technical level and areas for improvement of a target object based on the analysis results.

[0009] A "notification device" is a device that informs the user of the analysis results and areas for improvement generated by the evaluation device.

[0010] A "training plan provider" is a device that provides users with an optimal training plan based on improvements received from a notification device.

[0011] A "motion pattern" is a set of movements performed by an object, and serves as a criterion for technical evaluation. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] The present invention relates to a system for motion analysis and training feedback, and its embodiments are described in detail below. This system receives video data in real time from a high-precision video acquisition device, and a server analyzes this data to identify and evaluate motion patterns.

[0034] Server operation

[0035] When the server receives video data, it first applies a generative AI model to analyze the movement of the target object. This allows the server to extract the technical elements of the movement and analyze them by comparing them to standard movement patterns. For example, the server monitors an athlete's swing speed and weight transfer and performs a technical evaluation.

[0036] Feedback generation

[0037] Based on the analysis results, the server automatically generates areas for improvement. For example, if the server determines that "swing timing is delayed," it is the server's responsibility to provide specific reasons and methods for correction. Based on this information, the server proposes an optimal training plan to the user.

[0038] Terminal operation

[0039] The terminal receives feedback sent from the server and presents it through the user interface. To make the displayed content visually easier to understand, the terminal can show areas for improvement in the form of graphs, videos, and other visual aids.

[0040] User actions

[0041] Users can review the feedback displayed on their devices and apply it to modifying their form and training. For example, by receiving suggestions for specific behavioral corrections, they can consciously practice those suggestions during their next training session.

[0042] Thus, the present invention is a system that supports efficient training and skill improvement by performing video analysis and technical evaluation in real time and immediately providing users with areas for improvement.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives video data in real time from high-precision video acquisition equipment. The video captures the players' movements in detail, and metadata such as timestamps and player identification information is added.

[0046] Step 2:

[0047] The server uses a generative AI model to analyze the received video data. The AI ​​model extracts technical movement elements of the players from the video (e.g., hand and foot positions, swing angle) and quantifies them.

[0048] Step 3:

[0049] The server compares the extracted operational data with standard operational patterns and historical data. This comparison evaluates the accuracy and consistency of the operation and identifies areas for improvement.

[0050] Step 4:

[0051] The server automatically generates improvement suggestions based on the analysis results. Specifically, it creates detailed feedback that includes information such as which parts of the operation differ from the ideal and how they should be corrected.

[0052] Step 5:

[0053] The server sends the generated feedback and recommended training plan to the terminal. Communication with the terminal is conducted in a secure and fast manner.

[0054] Step 6:

[0055] The terminal immediately displays feedback received from the server. To present information in a visually easy-to-understand manner, the terminal uses videos, graphs, and other visual aids to highlight areas for improvement.

[0056] Step 7:

[0057] Users can review feedback on their devices and reflect on their own skills. They can then implement suggested improvement methods and training menus to enhance their skills.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] Providing highly accurate real-time analysis and appropriate feedback in the technical assessment of exercise is a challenging task. Conventional methods have struggled to effectively analyze an exerciser's movements and quickly identify specific areas for improvement. In particular, there is a need to perform accurate assessments tailored to individual characteristics using vast amounts of exercise data, and to develop efficient training plans.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes an evaluation means for analyzing image information acquired from a high-precision image acquisition means, a notification means for generating and notifying correction points based on the analysis results, a planning means for providing a motion plan based on the notified correction points, a preprocessing means for preprocessing video data and performing noise reduction and frame correction, a generation model usage means for analyzing the movement of a target object frame by frame and extracting motion patterns as numerical information, and a comparison means for calculating deviations of technical parameters by comparing with a standard motion pattern database. This enables precise motion analysis and feedback in real time.

[0063] "High-precision image acquisition means" refers to devices and methods for acquiring high-resolution, detailed video in real time.

[0064] "Evaluation means" refers to a process or device for analyzing acquired image information and automatically analyzing and evaluating the behavior of a target object.

[0065] "Notification means" refers to methods or devices for communicating corrections generated based on analysis results to the user.

[0066] "Plan delivery means" refers to the function of formulating and providing the optimal exercise plan for the user based on the notified revisions.

[0067] "Preprocessing means" refers to the process of preparing the video data to be analyzed, such as by removing noise or correcting frames.

[0068] "Generative model usage" refers to the process of applying an AI model to analyze the movement of a target object and extract its movement pattern as numerical information.

[0069] "Comparison method" refers to the process of comparing extracted technical parameters with a standard operating pattern database and calculating the deviation.

[0070] This invention provides a system that offers automated motion analysis and effective feedback. This system operates through the interaction of a server, terminals, and users.

[0071] The server receives image information collected in real time by high-precision image acquisition methods. To preprocess the video data, the server performs noise reduction and frame correction to prepare data suitable for analysis. This process can utilize common image processing libraries. The preprocessed data is analyzed using generative modeling methods. The server utilizes AI frameworks such as TENSORFLOW® and PyTorch to extract the motion patterns of target objects as numerical information on a frame-by-frame basis.

[0072] The extracted technical elements are compared to a standard operating pattern database within the server. The server uses Python's statistical libraries to calculate the deviations from the analyzed technical parameters, thereby performing a technical evaluation. Based on the evaluation results, the server suggests modifications and notifies the user. In this notification process, the proposed modifications are determined by referring to past cases and expert knowledge stored in the database.

[0073] The device receives feedback sent from the server and presents it to the user. The device uses HTML5 and JavaScript (registered trademark) to display the feedback clearly through visual elements such as graphs and animations. This allows the user to intuitively understand the suggested improvements.

[0074] Based on the feedback displayed on the device, users can create training plans to improve their skills. For example, if the feedback includes instructions such as "start your swing 0.2 seconds earlier," the user is expected to consciously implement those instructions in their next practice session.

[0075] In this way, the system aims to effectively improve athletic technique through the cooperation of the server, terminal, and user. An example of a prompt message would be, "Analyze the speed and timing of the golf swing and suggest areas for improvement."

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server receives image information in real time from a high-precision image acquisition system. The input is raw video data, and the output is pre-processed, analyzable data. This video information requires noise reduction and frame correction, and the server performs these preprocessing steps using an image processing library. Preprocessing includes contrast adjustment and filtering of unwanted noise.

[0079] Step 2:

[0080] The server inputs pre-processed data into a generating AI model to extract the motion patterns of the target object. The input is denoised video data, and the output is numerical data representing the motion patterns. In this process, the server utilizes TensorFlow to analyze the characteristics of the motion. Specifically, this includes analyzing the speed and angle of the motion frame by frame.

[0081] Step 3:

[0082] The server compares the extracted movement patterns with standard movement patterns. The input is numerical data of the movement, and the output is an evaluation result including deviations. The server refers to a standard pattern database and calculates deviations using Python's statistical libraries. The evaluation includes technical elements such as swing timing and the degree of agreement in weight transfer.

[0083] Step 4:

[0084] The server generates corrections based on the evaluation results and creates feedback tailored to the user. The input is the evaluation result, and the output is feedback that presents specific improvement measures. The server proposes improvements based on past data and expert knowledge. This step often includes specific instructions such as "move the swing timing forward by 0.2 seconds."

[0085] Step 5:

[0086] The terminal receives feedback from the server and presents it visually in the user interface. The input is feedback information sent from the server, and the output is a visual presentation using graphs and animations. The terminal uses HTML5 and JavaScript to display the feedback graphically in an intuitive and easy-to-understand manner.

[0087] Step 6:

[0088] Users review the feedback displayed on their device and incorporate it into their movements. The input is the visual feedback displayed on the device, and the output is putting the suggested improvements into practice. Users will keep the displayed corrections in mind during their next training session and work on specific improvements to their movements.

[0089] (Application Example 1)

[0090] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0091] This invention aims to improve work efficiency and safety in factories, but the evaluation of individual actions in current work procedures and the proposal for improvement are sometimes not adequately carried out. Therefore, there is a need for a means to understand the actions of the workers themselves and to realize efficient work improvements. Furthermore, there is a need for visual and explicit feedback to immediately put the obtained suggestions into practice.

[0092] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0093] In this invention, the server includes an evaluation means for analyzing motion data acquired from a high-precision video acquisition means, a notification means for generating improvement points based on the analysis results and notifying the user via a visual display means, and a plan provision means for providing a guidance plan based on the notified improvement points to support efficient and safe work. As a result, workers can have their movements accurately analyzed and immediately receive specific improvement measures through visual feedback.

[0094] A "high-precision video acquisition method" is a device that accurately records the movements of a subject in real time, enabling detailed motion analysis.

[0095] "Motion data" refers to numerical and video data that represents information about the movements of the worker in question, and this data is used to evaluate the movements.

[0096] "Evaluation means" refers to a system or function that analyzes acquired motion data and automatically performs an evaluation of the efficiency and safety of the target work.

[0097] "Notification means" refers to devices or functions that visually or audibly communicate to the user any improvements or precautions derived from the analysis results.

[0098] "Visual display means" refers to a device or function that displays analysis results using graphs, animations, etc., in order to provide information in a way that is easy for the user to understand.

[0099] A "planning provision method" refers to a system or function that provides users with specific work improvement guidance and procedures based on evaluation results.

[0100] A "training plan" is a plan that includes improvement methods and procedures, prepared to carry out work efficiently and safely.

[0101] A "generative AI model" is a program or model that uses machine learning and artificial intelligence technologies to analyze data and generate useful information or suggestions.

[0102] A "prompt statement" is an instruction or command statement provided as input necessary for a generative AI model to perform accurate analysis and make suggestions.

[0103] A "feedback mechanism" is a system or function that provides users with analyzed results and improvement suggestions to encourage them to modify or improve their actions.

[0104] This invention is a system for improving the efficiency and safety of factory operations. The system primarily consists of three main components: a high-precision video acquisition device, a server, and a terminal.

[0105] The server first receives motion data acquired by a high-precision video acquisition system. This data contains information about the movements of workers in the factory. Next, the server analyzes this motion data using a generative AI model. This analysis evaluates work efficiency and safety and identifies areas for improvement. The specific analysis process uses software such as Python and TensorFlow. This makes it possible to compare complex motion patterns with standard movements and identify differences and areas for improvement.

[0106] The analysis results are generated using prompt messages. These prompt messages are entered in the form of "Based on the worker's motion video, please provide efficient motion patterns. We will generate feedback that emphasizes smooth weight transfer and hand movements." The server generates specific improvement suggestions based on these prompt messages and sends them to the terminal.

[0107] The terminal receives feedback sent from the server and notifies the user through visual means. This allows the user to immediately grasp areas for improvement, and the information is presented in formats such as graphs and animations, making it easy to understand intuitively. The terminal also provides a specific guidance plan based on the areas for improvement, supporting the user in improving their work.

[0108] As a concrete example, let's consider manual assembly work on a manufacturing line. This system analyzes the worker's movements, identifies inefficient material handling and unnecessary actions, and provides improvement suggestions based on efficient movement patterns. As a result, workers can immediately optimize their work procedures, leading to safer and more efficient work.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server receives motion data acquired in real time using high-precision video acquisition methods. The input is video data transmitted from the camera, and the output is data in a format that allows for efficient analysis. This data is processed using Python and the OpenCV library.

[0112] Step 2:

[0113] The server analyzes the received motion data using a generating AI model. The input is the motion data obtained in step 1, and the output is the evaluation results of the motion and suggested improvement data. Here, TensorFlow is used to have the AI ​​model analyze the motion data and extract areas for improvement in work efficiency and safety.

[0114] Step 3:

[0115] The server generates a prompt message based on the analysis results and creates feedback based on it. The input is the analysis data obtained in step 2, and the output is feedback information that includes specific improvement suggestions to be provided to the user. Specifically, it generates the prompt message: "Based on the video of the worker's movements, please provide an efficient movement pattern. We will generate feedback that emphasizes smooth weight transfer and hand movements."

[0116] Step 4:

[0117] The server sends the generated feedback to the terminal. The input is feedback information, and the output is specific improvement suggestions that the user receives. Here, the HTTP protocol is used to send the data to the terminal.

[0118] Step 5:

[0119] The terminal visually displays the feedback information received from the server. The input is the feedback received in step 4, and the output is improvement suggestions displayed in a way that the user can understand. Specifically, feedback is displayed in graph and animation format using tools such as MPANDROID®Chart.

[0120] Step 6:

[0121] The user reviews the feedback displayed on the device and takes specific corrective actions. The input is visually displayed information, and the output is the improvement of their own work procedures. At this stage, the user proceeds with the work while being mindful of the proposed training plan.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention is a system that combines motion analysis and emotion recognition, achieving both improved user motion performance and emotional care. This system includes a video acquisition device, an analysis device, a notification device, a plan provision device, an emotion engine, and an adjustment device, and its embodiments are described in detail below.

[0124] Server operation

[0125] The server receives video data in real time from a high-precision video acquisition device and analyzes the player's movements. Next, the server extracts the technical elements of the movements using a generated AI model, compares them to standard movements, and performs an evaluation. After that, the server automatically generates areas for improvement based on the evaluation results.

[0126] Manipulating the Emotion Engine

[0127] The server analyzes facial expression data from the user's device using an emotion engine to recognize the user's emotions. The recognized emotions become important information for optimizing training content according to the user's psychological state. For example, if the emotion engine determines that the user is anxious, it will instruct the server to generate motivational feedback.

[0128] Feedback and training plan

[0129] The server creates an optimized training plan based on the analysis results and the output of the emotion engine. Feedback is customized to the user's emotional state through an adjustment mechanism and communicated to the user. For example, the server suggests challenging training when the user is feeling motivated, and a recovery-focused plan when fatigue is observed.

[0130] Terminal operation

[0131] The device receives feedback and training plans sent from the server and presents them to the user. The device provides a visually and audibly intuitive interface, with emphasis on emotional care.

[0132] User actions

[0133] Based on the information provided, users can utilize it for their own training methods and emotional care, aiming for efficient skill improvement. Specifically, by understanding the content of the training plan, practicing according to it, and reflecting on the feedback, they can maintain sustainable growth and mental health.

[0134] This invention realizes a system that supports both the user's technical abilities and psychological state by integrating motion analysis and emotion recognition, thereby providing a more personalized experience.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The server receives real-time video footage of players from high-precision video acquisition equipment. The server then organizes the data by adding timestamps and player identification information to the video data.

[0138] Step 2:

[0139] The server processes the received video data through an analysis device and uses a generated AI model to technically analyze the player's movements. It extracts elements of the movement (e.g., swing angle, movement speed) and evaluates them by comparing them to existing standards.

[0140] Step 3:

[0141] The server uses an emotion engine to analyze the user's facial expression data sent from the terminal in real time. Based on the data from the face and voice, the emotion engine evaluates the user's emotional state (joy, anxiety, concentration, etc.).

[0142] Step 4:

[0143] The server comprehensively analyzes both exercise and emotional data to generate optimal training feedback for the user. When the user is feeling down, it provides feedback that includes encouraging messages to maintain motivation.

[0144] Step 5:

[0145] The server sends the generated feedback and training plan to the terminal. The terminal then presents this feedback and plan to the user as a daily training menu.

[0146] Step 6:

[0147] The terminal visually organizes information sent from the server and displays it on the user interface. It utilizes colors and sounds to highlight content relevant to the user's emotional state and presents it in a way that is easy for the user to understand.

[0148] Step 7:

[0149] Users review the displayed feedback and incorporate it into their training. For example, they might improve their skills by focusing on specific techniques in their next practice session based on the suggested improvements. Users also use the feedback to help understand their own emotional state.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] This invention aims to provide an efficient method for simultaneously improving athletic performance and providing psychological care. Conventional techniques have focused solely on the technical evaluation of exercise, with insufficient consideration given to the user's emotional state and optimization of training plans. Therefore, a new system is needed to support users in both their athletic and psychological aspects.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes an evaluation means that analyzes motion data acquired from high-precision imaging equipment and evaluates the subject's movement state; a notification means that automatically generates points for technical improvement using a generation AI based on the analysis results and communicates these improvements to the user; and a plan provision means that recognizes the user's emotional state and creates an exercise plan optimized for that state. This makes it possible to provide a personalized training plan that takes into account the user's emotional state, along with improving the technical aspects of the exercise.

[0155] "High-precision imaging equipment" refers to devices such as cameras and sensors that capture the subject's movements at high resolution and frame rate, providing detailed data.

[0156] "Motion data" refers to information about the subject's movement generated from video information acquired by the camera.

[0157] "Evaluation means" refers to a device or program for analyzing acquired motion data, extracting the technical elements of the movement, and evaluating the subject's movement state.

[0158] "Generative AI" refers to systems or programs that use artificial intelligence technology to automatically generate new data and information.

[0159] A "notification means" is a device or program used to communicate evaluation results and areas for improvement to users.

[0160] "Emotion recognition means" refers to a program or device that analyzes a user's facial expression data and identifies their emotional state.

[0161] A "feedback mechanism" is a device or program that provides appropriate feedback to the user based on the analysis results and emotional state.

[0162] "Presentation means" refers to a device or interface for presenting information transmitted from a server to a user visually or audibly.

[0163] A "comparison device" is a device or program used to evaluate acquired motion data by comparing it with past data.

[0164] "Selection means" refers to a device or program for generating different exercise plans according to the user's selection.

[0165] This invention is a system that integrates motor evaluation and emotion recognition, simultaneously achieving improvement in the user's motor skills and psychological care. The system includes imaging equipment, analysis equipment, notification equipment, planning equipment, emotion recognition equipment, and adjustment equipment. Specific embodiments are described below.

[0166] Server operation

[0167] The server first receives motion data in real time from high-precision imaging equipment. This motion data is acquired, for example, by a typical high-resolution camera. The server then applies a Python motion analysis algorithm to extract the technical elements of the motion. Subsequently, it uses generative AI to compare it with reference motions stored in a database to derive a technical evaluation and areas for improvement. The server then notifies the user of the evaluation results and areas for improvement.

[0168] Manipulating the Emotion Engine

[0169] The server receives facial expression data from the user's device and analyzes it using an emotion engine. The emotion engine identifies the user's emotional state, for example, by using a common emotion recognition API. The emotional state is determined as a state such as "anxiety" or "concentration." Based on the analysis results, the server generates a training plan that is best suited to the user's state.

[0170] Feedback and training plan

[0171] The server creates an optimized training plan based on the analysis results and emotional state. This process utilizes an AI model that takes into account the user's past data. The feedback content is also customized according to the user's emotional state. The server provides the user with customized feedback to maximize the effectiveness of the training.

[0172] Terminal operation

[0173] The terminal receives information transmitted from the server and presents it to the user in an easy-to-understand manner. The terminal is designed with a visually and audibly designed interface to allow the user to easily understand the feedback. Through the information provided on the terminal, the user can adjust their exercise methods and manage their mental state.

[0174] User utilization

[0175] Based on the feedback and training plan provided, users improve their athletic abilities and maintain their mental well-being. For example, they improve their form and take care of their mental health according to the feedback. By continuously reviewing their training content, long-term growth can be expected.

[0176] Specific examples and prompt statements

[0177] For example, the server might analyze a tennis player's swing motion, and if the emotion recognition engine determines that the player is concentrating, it might generate a training plan aimed at further improving their technique. An example of a prompt to the generated AI model would be, "Analyze the user's swing motion, compare it to standard motion, and provide an evaluation and suggestions for improvement."

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] The server receives motion data in real time from high-precision imaging equipment. The input is video data captured by the camera. This video data represents the player's movements and is converted into an analyzable video dataset as output. Specifically, the server receives the video data and prepares it for analysis while maintaining its image quality.

[0181] Step 2:

[0182] The server applies a motion analysis algorithm to extract the technical elements of the athlete. The input is the video dataset obtained in step 1, and the output is analysis data containing the technical elements. The server uses an algorithm implemented in Python to perform motion analysis, quantifying, for example, the movement and speed of the athlete's limbs.

[0183] Step 3:

[0184] The server uses a generative AI model to compare technical elements with reference motions. Inputs include analysis data and reference motion data, and the output generates a technical evaluation of the motion and areas for improvement. Specifically, the server inputs prompt statements into the generative AI model, which then derives the technical evaluation and necessary improvements.

[0185] Step 4:

[0186] The server receives facial expression data from the user's device and analyzes the emotional state using an emotion recognition engine. The input is facial expression data acquired from the user's device, and the output is a specific label that determines the user's emotional state. The server inputs the facial expression data into the emotion engine, processes the results, and determines the emotional state.

[0187] Step 5:

[0188] The server creates an optimized training plan based on the analysis results and emotional state. Inputs include technical evaluation, areas for improvement, and emotional state, while the output is a user-specific training plan. The server integrates this data to generate the most effective training content.

[0189] Step 6:

[0190] The server generates feedback and sends it to the terminal. The input is a well-organized technical evaluation and training plan, and the output is feedback data presented to the user visually and aurally. Specifically, the server compiles the feedback and sends it to the terminal via a reconciliation device.

[0191] Step 7:

[0192] The terminal displays the received feedback and training plan. The input is feedback data sent from the server, and the output is information displayed to the user. The terminal uses a graphical user interface to visually display the feedback content and, with voice assistance as needed, conveys the information clearly.

[0193] Step 8:

[0194] The user utilizes the provided feedback and training plan to carry out the training. The input is the feedback and plan presented on the device, and the output is the user's improved skills and improved psychological state. In terms of specific actions, the user trains according to the presented areas for improvement and continues practicing towards the goal.

[0195] (Application Example 2)

[0196] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0197] To simultaneously improve athletic performance and provide psychological support, it is necessary to provide personalized feedback and training plans to each individual user in real time. However, conventional systems can only perform exercise analysis and emotion recognition independently, making it difficult to effectively integrate the results of each into the presentation of feedback and plans.

[0198] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0199] In this invention, the server includes an evaluation means for analyzing image data acquired from a high-precision image acquisition means and automatically evaluating the movement of a target object; a notification means for generating areas for improvement based on the analysis results and notifying the user of these areas for improvement; and an emotion analysis means for analyzing the user's emotional state using an emotion recognition means and adjusting the feedback based on the emotion data. This makes it possible to simultaneously provide personalized movement improvement suggestions and psychological support for each user.

[0200] A "high-precision image acquisition method" is an image acquisition device with excellent resolution and accuracy for capturing the movement of a target object in detail.

[0201] The "evaluation means" refers to a function that analyzes acquired video data, extracts characteristics related to the motion of the target object, and evaluates its motion performance by comparing it with standard motion.

[0202] A "notification device" is a device that uses visual or auditory media to communicate information about analyzed areas for improvement to the user.

[0203] "Emotion recognition means" refers to a function that analyzes facial expressions and voice data to determine the user's emotional state and estimate their psychological state.

[0204] "Emotion analysis means" refers to a system function that adjusts the content of feedback and training plans based on recognized user emotion data.

[0205] The "plan delivery method" refers to the function of formulating and providing training schedules optimized for individual users based on information obtained from evaluation methods and emotion analysis methods.

[0206] This invention utilizes a system that integrates motion analysis and emotion recognition. The server receives video data from a high-precision image acquisition means and uses an image analysis library (e.g., OpenCV) for motion analysis. The acquired video data is analyzed to compare the movement of the target object with a standard movement and evaluate the movement. Based on the analysis results, the system provides suggestions for improvement to the user via a notification means. For example, it may provide specific advice such as, "Try swinging your arms a little more" when describing running form.

[0207] Furthermore, the server uses emotion recognition capabilities and utilizes speech analysis libraries (e.g., Librosa) and machine learning libraries (e.g., TensorFlow and PyTorch) to analyze the user's emotional state. This emotional data is used to provide feedback and adjust training plans, offering appropriate psychological support to the user. For example, if the server determines that the user's motivation is low, it can play upbeat music as an "encouraging message."

[0208] The device receives notifications and plans from the server and presents them to the user through an intuitively understandable interface (e.g., touchscreen or audio output). Based on the information provided, the user can adjust their training plan to ensure continuous skill improvement and emotional support.

[0209] As a concrete example, when a user goes jogging, the system can suggest a jogging plan tailored to their motivation and physical condition that day via their device. An example of a prompt used in this case is: "If the user looks anxious, please suggest what kind of motivational feedback would be appropriate." In this way, by providing feedback and training plans using a generative AI model, it is possible to provide optimal support to each individual user.

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The server captures the user's movements using image acquisition equipment and receives video data in real time. The input is high-precision video data, which is divided into frames and subjected to initial processing using an image analysis library. The output is frame data, which forms the basis for the analysis process. Based on this frame data, the system is ready to extract the user's movement patterns.

[0213] Step 2:

[0214] The server applies an image analysis algorithm to extract motion patterns from video data and compares them with a standard motion database. The input is pre-processed frame data, and the output is an evaluation result regarding the motion performance of the target object. This data processing reveals specific areas for improvement in the user's movements.

[0215] Step 3:

[0216] The server generates improvement suggestions using an AI model based on the user's evaluation results. This process outputs a feedback script, including prompts, based on the input performance evaluation data. The generated feedback is then refined to make it easier for the user to understand.

[0217] Step 4:

[0218] The server uses emotion recognition to receive user voice data from the terminal and perform emotion analysis. The input is voice data, and emotions are identified using a machine learning library. The output is data about the user's emotional state. This data is used to adjust the feedback.

[0219] Step 5:

[0220] The device presents the user with a training plan based on improvement suggestions and sentiment data received from the server. Inputs are notification data and training plan data from the server. Output is an interface display that intuitively shows the user feedback and training plan. The device uses visual and auditory elements to present information to the user and support smooth training.

[0221] Step 6:

[0222] Users perform exercises based on feedback and training plans provided through their devices. The inputs are the feedback and plan information, and the user's actions are the output. By utilizing this feedback, users can improve their skills and maintain their mental well-being.

[0223] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0224] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0225] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0229] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0230] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0231] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0232] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0233] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0234] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0235] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0236] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0237] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0238] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0239] The present invention relates to a system for motion analysis and training feedback, and its embodiments are described in detail below. This system receives video data in real time from a high-precision video acquisition device, and a server analyzes this data to identify and evaluate motion patterns.

[0240] Server operation

[0241] When the server receives video data, it first applies a generative AI model to analyze the movement of the target object. This allows the server to extract the technical elements of the movement and analyze them by comparing them to standard movement patterns. For example, the server monitors an athlete's swing speed and weight transfer and performs a technical evaluation.

[0242] Feedback generation

[0243] Based on the analysis results, the server automatically generates areas for improvement. For example, if the server determines that "swing timing is delayed," it is the server's responsibility to provide specific reasons and methods for correction. Based on this information, the server proposes an optimal training plan to the user.

[0244] Terminal operation

[0245] The terminal receives feedback sent from the server and presents it through the user interface. To make the displayed content visually easy to understand, the terminal can show areas for improvement in the form of graphs, videos, and other visual aids.

[0246] User actions

[0247] Users can review the feedback displayed on their devices and apply it to correcting their form and training. For example, by receiving suggestions for specific behavioral corrections, they can consciously practice those suggestions during their next training session.

[0248] Thus, the present invention is a system that supports efficient training and skill improvement by performing video analysis and technical evaluation in real time and immediately providing users with areas for improvement.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The server receives video data in real time from high-precision video acquisition equipment. The video captures the players' movements in detail, and metadata such as timestamps and player identification information is added.

[0252] Step 2:

[0253] The server uses a generative AI model to analyze the received video data. The AI ​​model extracts technical movement elements of the players from the video (e.g., hand and foot positions, swing angle) and quantifies them.

[0254] Step 3:

[0255] The server compares the extracted operational data with standard operational patterns and historical data. This comparison evaluates the accuracy and consistency of the operation and identifies areas for improvement.

[0256] Step 4:

[0257] The server automatically generates improvement suggestions based on the analysis results. Specifically, it creates detailed feedback that includes information such as which parts of the operation differ from the ideal and how they should be corrected.

[0258] Step 5:

[0259] The server sends the generated feedback and recommended training plan to the terminal. Communication with the terminal is conducted in a secure and fast manner.

[0260] Step 6:

[0261] The terminal immediately displays feedback received from the server. To present information in a visually easy-to-understand manner, the terminal uses videos, graphs, and other visual aids to highlight areas for improvement.

[0262] Step 7:

[0263] Users can review feedback on their devices and reflect on their own skills. They can then implement suggested improvement methods and training menus to enhance their skills.

[0264] (Example 1)

[0265] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0266] Providing highly accurate real-time analysis and appropriate feedback in the technical assessment of exercise is a challenging task. Conventional methods have struggled to effectively analyze an exerciser's movements and quickly identify specific areas for improvement. In particular, there is a need to perform accurate assessments tailored to individual characteristics using vast amounts of exercise data, and to develop efficient training plans.

[0267] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0268] In this invention, the server includes an evaluation means for analyzing image information acquired from a high-precision image acquisition means, a notification means for generating and notifying correction points based on the analysis results, a planning means for providing a motion plan based on the notified correction points, a preprocessing means for preprocessing video data and performing noise reduction and frame correction, a generation model usage means for analyzing the movement of a target object frame by frame and extracting motion patterns as numerical information, and a comparison means for calculating deviations of technical parameters by comparing with a standard motion pattern database. This enables precise motion analysis and feedback in real time.

[0269] "High-precision image acquisition means" refers to devices and methods for acquiring high-resolution, detailed video in real time.

[0270] "Evaluation means" refers to a process or device for analyzing acquired image information and automatically analyzing and evaluating the behavior of a target object.

[0271] "Notification means" refers to methods or devices for communicating corrections generated based on analysis results to the user.

[0272] "Plan delivery means" refers to the function of formulating and providing the optimal exercise plan for the user based on the notified revisions.

[0273] "Preprocessing means" refers to the process of preparing the video data to be analyzed, such as by removing noise or correcting frames.

[0274] "Generative model usage" refers to the process of applying an AI model to analyze the movement of a target object and extract its movement pattern as numerical information.

[0275] "Comparison method" refers to the process of comparing extracted technical parameters with a standard operating pattern database and calculating the deviation.

[0276] This invention provides a system that offers automated motion analysis and effective feedback. This system operates through the interaction of a server, terminals, and users.

[0277] The server receives image information collected in real time by high-precision image acquisition methods. To preprocess the video data, the server performs noise reduction and frame correction to prepare data suitable for analysis. This process can use common image processing libraries. The preprocessed data is analyzed using generative modeling methods. The server utilizes AI frameworks such as TensorFlow and PyTorch to extract the motion patterns of target objects as numerical information on a frame-by-frame basis.

[0278] The extracted technical elements are compared to a standard operating pattern database within the server. The server uses Python's statistical libraries to calculate the deviations from the analyzed technical parameters, thereby performing a technical evaluation. Based on the evaluation results, the server suggests modifications and notifies the user. In this notification process, the proposed modifications are determined by referring to past cases and expert knowledge stored in the database.

[0279] The device receives feedback sent from the server and presents it to the user. Using HTML5 and JavaScript, the device clearly displays the feedback through visual elements such as graphs and animations. This allows the user to intuitively understand the suggested improvements.

[0280] Based on the feedback displayed on the device, users can create training plans to improve their skills. For example, if the feedback includes instructions such as "start your swing 0.2 seconds earlier," the user is expected to consciously implement those instructions in their next practice session.

[0281] In this way, the system aims to effectively improve athletic technique through the cooperation of the server, terminal, and user. An example of a prompt message would be, "Analyze the speed and timing of the golf swing and suggest areas for improvement."

[0282] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0283] Step 1:

[0284] The server receives image information in real time from a high-precision image acquisition system. The input is raw video data, and the output is pre-processed, analyzable data. This video information requires noise reduction and frame correction, and the server performs these preprocessing steps using an image processing library. Preprocessing includes contrast adjustment and filtering of unwanted noise.

[0285] Step 2:

[0286] The server inputs the pre - processed data into the generative AI model to extract the motion pattern of the target object. The input is the video data after noise processing, and the output is the numerical data representing the motion pattern. In this process, the server utilizes TensorFlow to analyze the characteristics of the motion. Specific motions include the analysis of speed and angle for each frame of the motion.

[0287] Step 3:

[0288] The server compares the extracted motion pattern with the standard motion pattern. The input is the numerical data of the motion, and the output is the evaluation result including the deviation. The server refers to the standard pattern database and uses the statistical library of Python to calculate the deviation. The evaluation includes technical elements such as the timing of the swing and the degree of weight transfer consistency.

[0289] Step 4:

[0290] Based on the evaluation result, the server generates points for improvement and creates feedback suitable for the user. The input is the evaluation result, and the output is the feedback presenting specific improvement measures. The server proposes improvement points based on past data and expert knowledge. In this step, instructions such as "advance the swing timing by 0.2 seconds" are often included as specific examples.

[0291] Step 5: <所

[0292] The terminal receives the feedback from the server and visually presents it on the user interface. The input is the feedback information sent from the server, and the output is the visual presentation using graphs or animations. The terminal utilizes HTML5 and JavaScript to graphically display the feedback so that it can be intuitively understood.

[0293] Step 6:

[0294] Users review the feedback displayed on their device and incorporate it into their movements. The input is the visual feedback displayed on the device, and the output is putting the suggested improvements into practice. Users will keep the displayed corrections in mind during their next training session and work on specific improvements to their movements.

[0295] (Application Example 1)

[0296] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0297] This invention aims to improve work efficiency and safety in factories, but the evaluation of individual actions in current work procedures and the proposal for improvement are sometimes not adequately carried out. Therefore, there is a need for a means to understand the actions of the workers themselves and to realize efficient work improvements. Furthermore, there is a need for visual and explicit feedback to immediately put the obtained suggestions into practice.

[0298] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0299] In this invention, the server includes an evaluation means for analyzing motion data acquired from a high-precision video acquisition means, a notification means for generating improvement points based on the analysis results and notifying the user via a visual display means, and a plan provision means for providing a guidance plan based on the notified improvement points to support efficient and safe work. As a result, workers can have their movements accurately analyzed and immediately receive specific improvement measures through visual feedback.

[0300] A "high-precision video acquisition method" is a device that accurately records the movements of a subject in real time, enabling detailed motion analysis.

[0301] "Operation data" refers to numerical or video data representing information about the movements of the target operator, based on which the evaluation of operations is carried out.

[0302] "Evaluation means" refers to a system or function that analyzes the acquired operation data and automatically evaluates the efficiency and safety of the target operation.

[0303] "Notification means" refers to a device or function for visually or audibly conveying improvement points and precautions obtained from the analysis results to the user.

[0304] "Visual display means" refers to a device or function that displays the analysis results using graphs, animations, etc. in a form that is easy for the user to understand in order to provide information.

[0305] "Plan providing means" refers to a system or function for showing specific operation improvement guidance and procedures to the user based on the evaluation results.

[0306] "Guidance plan" refers to a plan containing improvement methods and procedures prepared to carry out operations efficiently and safely.

[0307] "Generated AI model" refers to a program or model that analyzes data using machine learning and artificial intelligence technologies to generate useful information and proposals.

[0308] "Prompt text" refers to an instruction text or command text provided as an input necessary for the generated AI model to perform accurate analysis and proposals.

[0309] "Feedback means" refers to a system or function for providing the analyzed results and improvement proposals to the user to prompt the correction and improvement of operations.

[0310] This invention is a system for realizing the improvement of the efficiency and safety of factory work. This system is mainly composed of three main components: a high-precision video acquisition device, a server, and a terminal.

[0311] The server first receives motion data acquired by a high-precision video acquisition system. This data contains information about the movements of workers in the factory. Next, the server analyzes this motion data using a generative AI model. This analysis evaluates work efficiency and safety and identifies areas for improvement. The specific analysis process uses software such as Python and TensorFlow. This makes it possible to compare complex motion patterns with standard movements and identify differences and areas for improvement.

[0312] The analysis results are generated using prompt messages. These prompt messages are entered in the form of "Based on the worker's motion video, please provide efficient motion patterns. We will generate feedback that emphasizes smooth weight transfer and hand movements." The server generates specific improvement suggestions based on these prompt messages and sends them to the terminal.

[0313] The terminal receives feedback sent from the server and notifies the user through visual means. This allows the user to immediately grasp areas for improvement, and the information is presented in formats such as graphs and animations, making it easy to understand intuitively. The terminal also provides a specific guidance plan based on the areas for improvement, supporting the user in improving their work.

[0314] As a concrete example, let's consider manual assembly work on a manufacturing line. This system analyzes the worker's movements, identifies inefficient material handling and unnecessary actions, and provides improvement suggestions based on efficient movement patterns. As a result, workers can immediately optimize their work procedures, leading to safer and more efficient work.

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The server receives motion data acquired in real time using high-precision video acquisition methods. The input is video data transmitted from the camera, and the output is data in a format that allows for efficient analysis. This data is processed using Python and the OpenCV library.

[0318] Step 2:

[0319] The server analyzes the received motion data using a generating AI model. The input is the motion data obtained in step 1, and the output is the evaluation results of the motion and suggested improvement data. Here, TensorFlow is used to have the AI ​​model analyze the motion data and extract areas for improvement in work efficiency and safety.

[0320] Step 3:

[0321] The server generates a prompt message based on the analysis results and creates feedback based on it. The input is the analysis data obtained in step 2, and the output is feedback information that includes specific improvement suggestions to be provided to the user. Specifically, it generates the prompt message: "Based on the video of the worker's movements, please provide an efficient movement pattern. We will generate feedback that emphasizes smooth weight transfer and hand movements."

[0322] Step 4:

[0323] The server sends the generated feedback to the terminal. The input is feedback information, and the output is specific improvement suggestions that the user receives. Here, the HTTP protocol is used to send the data to the terminal.

[0324] Step 5:

[0325] The device visually displays the feedback information received from the server. The input is the feedback received in step 4, and the output is improvement suggestions displayed in a way that the user can understand. Specifically, feedback is displayed in graph or animation format using tools such as MPAndroidChart.

[0326] Step 6:

[0327] The user reviews the feedback displayed on the device and takes specific corrective actions. The input is visually displayed information, and the output is the improvement of their own work procedures. At this stage, the user proceeds with the work while being mindful of the proposed training plan.

[0328] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0329] This invention is a system that combines motion analysis and emotion recognition, achieving both improved user motion performance and emotional care. This system includes a video acquisition device, an analysis device, a notification device, a plan provision device, an emotion engine, and an adjustment device, and its embodiments are described in detail below.

[0330] Server operation

[0331] The server receives video data in real time from a high-precision video acquisition device and analyzes the player's movements. Next, the server extracts the technical elements of the movements using a generated AI model, compares them to standard movements, and performs an evaluation. After that, the server automatically generates areas for improvement based on the evaluation results.

[0332] Manipulating the Emotion Engine

[0333] The server analyzes facial expression data from the user's device using an emotion engine to recognize the user's emotions. The recognized emotions become important information for optimizing training content according to the user's psychological state. For example, if the emotion engine determines that the user is anxious, it will instruct the server to generate motivational feedback.

[0334] Feedback and training plan

[0335] The server creates an optimized training plan based on the analysis results and the output of the emotion engine. Feedback is customized to the user's emotional state through an adjustment mechanism and communicated to the user. For example, the server suggests challenging training when the user is feeling motivated, and a recovery-focused plan when fatigue is observed.

[0336] Terminal operation

[0337] The device receives feedback and training plans sent from the server and presents them to the user. The device provides a visually and audibly intuitive interface, with emphasis on emotional care.

[0338] User actions

[0339] Based on the information provided, users can utilize it for their own training methods and emotional care, aiming for efficient skill improvement. Specifically, by understanding the content of the training plan, practicing according to it, and reflecting on the feedback, they can maintain sustainable growth and mental health.

[0340] This invention realizes a system that supports both the user's technical abilities and psychological state by integrating motion analysis and emotion recognition, thereby providing a more personalized experience.

[0341] The following describes the processing flow.

[0342] Step 1:

[0343] The server receives real-time video footage of players from high-precision video acquisition equipment. The server then organizes the data by adding timestamps and player identification information to the video data.

[0344] Step 2:

[0345] The server processes the received video data through an analysis device and uses a generated AI model to technically analyze the player's movements. It extracts elements of the movement (e.g., swing angle, movement speed) and evaluates them by comparing them to existing standards.

[0346] Step 3:

[0347] The server uses an emotion engine to analyze the user's facial expression data sent from the terminal in real time. Based on the data from the face and voice, the emotion engine evaluates the user's emotional state (joy, anxiety, concentration, etc.).

[0348] Step 4:

[0349] The server comprehensively analyzes both exercise and emotional data to generate optimal training feedback for the user. When the user is feeling down, it provides feedback that includes encouraging messages to maintain motivation.

[0350] Step 5:

[0351] The server sends the generated feedback and training plan to the terminal. The terminal then presents this feedback and plan to the user as a daily training menu.

[0352] Step 6:

[0353] The terminal visually organizes information sent from the server and displays it on the user interface. It utilizes colors and sounds to highlight content relevant to the user's emotional state and presents it in a way that is easy for the user to understand.

[0354] Step 7:

[0355] Users review the displayed feedback and incorporate it into their training. For example, they might improve their skills by focusing on specific techniques in their next practice session based on the suggested improvements. Users also use the feedback to help understand their own emotional state.

[0356] (Example 2)

[0357] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0358] This invention aims to provide an efficient method for simultaneously improving athletic performance and providing psychological care. Conventional techniques have focused solely on the technical evaluation of exercise, with insufficient consideration given to the user's emotional state and optimization of training plans. Therefore, a new system is needed to support users in both their athletic and psychological aspects.

[0359] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0360] In this invention, the server includes an evaluation means that analyzes motion data acquired from high-precision imaging equipment and evaluates the subject's movement state; a notification means that automatically generates points for technical improvement using a generation AI based on the analysis results and communicates these improvements to the user; and a plan provision means that recognizes the user's emotional state and creates an exercise plan optimized for that state. This makes it possible to provide a personalized training plan that takes into account the user's emotional state, along with improving the technical aspects of the exercise.

[0361] "High-precision imaging equipment" refers to devices such as cameras and sensors that capture the subject's movements at high resolution and frame rate, providing detailed data.

[0362] "Motion data" refers to information about the subject's movement generated from video information acquired by the camera.

[0363] "Evaluation means" refers to a device or program for analyzing acquired motion data, extracting the technical elements of the movement, and evaluating the subject's movement state.

[0364] "Generative AI" refers to systems or programs that use artificial intelligence technology to automatically generate new data and information.

[0365] A "notification means" is a device or program used to communicate evaluation results and areas for improvement to users.

[0366] "Emotion recognition means" refers to a program or device that analyzes a user's facial expression data and identifies their emotional state.

[0367] A "feedback mechanism" is a device or program that provides appropriate feedback to the user based on the analysis results and emotional state.

[0368] "Presentation means" refers to a device or interface for presenting information transmitted from a server to a user visually or audibly.

[0369] A "comparison device" is a device or program used to evaluate acquired motion data by comparing it with past data.

[0370] "Selection means" refers to a device or program for generating different exercise plans according to the user's selection.

[0371] This invention is a system that integrates motor evaluation and emotion recognition, simultaneously achieving improvement in the user's motor skills and psychological care. The system includes imaging equipment, analysis equipment, notification equipment, planning equipment, emotion recognition equipment, and adjustment equipment. Specific embodiments are described below.

[0372] Server operation

[0373] The server first receives motion data in real time from high-precision imaging equipment. This motion data is acquired, for example, by a typical high-resolution camera. The server then applies a Python motion analysis algorithm to extract the technical elements of the motion. Subsequently, it uses generative AI to compare it with reference motions stored in a database to derive a technical evaluation and areas for improvement. The server then notifies the user of the evaluation results and areas for improvement.

[0374] Manipulating the Emotion Engine

[0375] The server receives facial expression data from the user's device and analyzes it using an emotion engine. The emotion engine identifies the user's emotional state, for example, by using a common emotion recognition API. The emotional state is determined as a state such as "anxiety" or "concentration." Based on the analysis results, the server generates a training plan that is best suited to the user's state.

[0376] Feedback and training plan

[0377] The server creates an optimized training plan based on the analysis results and emotional state. This process utilizes an AI model that takes into account the user's past data. The feedback content is also customized according to the user's emotional state. The server provides the user with customized feedback to maximize the effectiveness of the training.

[0378] Terminal operation

[0379] The terminal receives information transmitted from the server and presents it to the user in an easy-to-understand manner. The terminal is designed with a visually and audibly designed interface to allow the user to easily understand the feedback. Through the information provided on the terminal, the user can adjust their exercise methods and manage their mental state.

[0380] User utilization

[0381] Based on the feedback and training plan provided, users improve their athletic performance while maintaining their mental well-being. For example, they can improve their form and take care of their mental health according to the feedback. By continuously reviewing their training content, long-term growth can be expected.

[0382] Specific examples and prompt statements

[0383] For example, the server might analyze a tennis player's swing motion, and if the emotion recognition engine determines that the player is concentrating, it might generate a training plan aimed at further improving their technique. An example of a prompt to the generated AI model would be, "Analyze the user's swing motion, compare it to standard motion, and provide an evaluation and suggestions for improvement."

[0384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0385] Step 1:

[0386] The server receives motion data in real time from high-precision imaging equipment. The input is video data captured by the camera. This video data represents the player's movements and is converted into an analyzable video dataset as output. Specifically, the server receives the video data and prepares it for analysis while maintaining its image quality.

[0387] Step 2:

[0388] The server applies a motion analysis algorithm to extract the technical elements of the athlete. The input is the video dataset obtained in step 1, and the output is analysis data containing the technical elements. The server uses an algorithm implemented in Python to perform motion analysis, quantifying, for example, the movement and speed of the athlete's limbs.

[0389] Step 3:

[0390] The server uses a generative AI model to compare technical elements with reference motions. Inputs include analysis data and reference motion data, and the output generates a technical evaluation of the motion and areas for improvement. Specifically, the server inputs prompt statements into the generative AI model, which then derives the technical evaluation and necessary improvements.

[0391] Step 4:

[0392] The server receives facial expression data from the user's device and analyzes the emotional state using an emotion recognition engine. The input is facial expression data acquired from the user's device, and the output is a specific label that determines the user's emotional state. The server inputs the facial expression data into the emotion engine, processes the results, and determines the emotional state.

[0393] Step 5:

[0394] The server creates an optimized training plan based on the analysis results and emotional state. Inputs include technical evaluation, areas for improvement, and emotional state, while the output is a user-specific training plan. The server integrates this data to generate the most effective training content.

[0395] Step 6:

[0396] The server generates feedback and sends it to the terminal. The input is a well-organized technical evaluation and training plan, and the output is feedback data presented to the user visually and aurally. Specifically, the server compiles the feedback and sends it to the terminal via a reconciliation device.

[0397] Step 7:

[0398] The terminal displays the received feedback and training plan. The input is feedback data sent from the server, and the output is information displayed to the user. The terminal uses a graphical user interface to visually display the feedback content and, with voice assistance as needed, conveys the information clearly.

[0399] Step 8:

[0400] The user utilizes the provided feedback and training plan to carry out the training. The input is the feedback and plan presented on the device, and the output is the user's improved skills and improved psychological state. In terms of specific actions, the user trains according to the presented areas for improvement and continues practicing towards the goal.

[0401] (Application Example 2)

[0402] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0403] To simultaneously improve athletic performance and provide psychological support, it is necessary to provide personalized feedback and training plans to each individual user in real time. However, conventional systems can only perform exercise analysis and emotion recognition independently, making it difficult to effectively integrate the results of each into the presentation of feedback and plans.

[0404] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0405] In this invention, the server includes an evaluation means for analyzing image data acquired from a high-precision image acquisition means and automatically evaluating the movement of a target object; a notification means for generating areas for improvement based on the analysis results and notifying the user of these areas for improvement; and an emotion analysis means for analyzing the user's emotional state using an emotion recognition means and adjusting the feedback based on the emotion data. This makes it possible to simultaneously provide personalized movement improvement suggestions and psychological support for each user.

[0406] A "high-precision image acquisition method" is an image acquisition device with excellent resolution and accuracy for capturing the movement of a target object in detail.

[0407] "Evaluation means" refers to a function that analyzes acquired video data, extracts characteristics related to the motion of the target object, and evaluates its motion performance by comparing it with standard motion.

[0408] A "notification device" is a device that uses visual or auditory media to communicate information about analyzed areas for improvement to the user.

[0409] "Emotion recognition means" refers to a function that analyzes facial expressions and voice data to determine the user's emotional state and estimate their psychological state.

[0410] "Emotion analysis means" refers to a system function that adjusts the content of feedback and training plans based on recognized user emotion data.

[0411] The "plan delivery method" refers to the function of formulating and providing training schedules optimized for individual users based on information obtained from evaluation methods and emotion analysis methods.

[0412] This invention utilizes a system that integrates motion analysis and emotion recognition. The server receives video data from a high-precision image acquisition means and uses an image analysis library (e.g., OpenCV) for motion analysis. The acquired video data is analyzed to compare the movement of the target object with a standard movement and evaluate the movement. Based on the analysis results, the system provides suggestions for improvement to the user via a notification means. For example, it may provide specific advice such as, "Try swinging your arms a little more" when describing running form.

[0413] Furthermore, the server uses emotion recognition capabilities and utilizes speech analysis libraries (e.g., Librosa) and machine learning libraries (e.g., TensorFlow and PyTorch) to analyze the user's emotional state. This emotional data is used to provide feedback and adjust training plans, offering appropriate psychological support to the user. For example, if the server determines that the user's motivation is low, it can play upbeat music as an "encouraging message."

[0414] The device receives notifications and plans from the server and presents them to the user through an intuitively understandable interface (e.g., touchscreen or audio output). Based on the information provided, the user can adjust their training plan to ensure continuous skill improvement and emotional support.

[0415] As a concrete example, when a user goes jogging, the system can suggest a jogging plan tailored to their motivation and physical condition that day via their device. An example of a prompt used in this case is: "If the user looks anxious, please suggest what kind of motivational feedback would be appropriate." In this way, by providing feedback and training plans using a generative AI model, it is possible to provide optimal support to each individual user.

[0416] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0417] Step 1:

[0418] The server captures the user's movements using image acquisition equipment and receives video data in real time. The input is high-precision video data, which is divided into frames and subjected to initial processing using an image analysis library. The output is frame data, which forms the basis for the analysis process. Based on this frame data, the system is ready to extract the user's movement patterns.

[0419] Step 2:

[0420] The server applies an image analysis algorithm to extract motion patterns from video data and compares them with a standard motion database. The input is pre-processed frame data, and the output is an evaluation result regarding the motion performance of the target object. This data processing reveals specific areas for improvement in the user's movements.

[0421] Step 3:

[0422] The server generates improvement suggestions using an AI model based on the user's evaluation results. This process outputs a feedback script, including prompts, based on the input performance evaluation data. The generated feedback is then refined to make it easier for the user to understand.

[0423] Step 4:

[0424] The server uses emotion recognition to receive user voice data from the terminal and perform emotion analysis. The input is voice data, and emotions are identified using a machine learning library. The output is data about the user's emotional state. This data is used to adjust the feedback.

[0425] Step 5:

[0426] The device presents the user with a training plan based on improvement suggestions and sentiment data received from the server. Inputs are notification data and training plan data from the server. Output is an interface display that intuitively shows the user feedback and training plan. The device uses visual and auditory elements to present information to the user and support smooth training.

[0427] Step 6:

[0428] Users perform exercises based on feedback and training plans provided through their devices. The inputs are the feedback and plan information, and the user's actions are the output. By utilizing this feedback, users can improve their skills and maintain their mental well-being.

[0429] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0430] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0431] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0432] [Third Embodiment]

[0433] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0434] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0435] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0436] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0437] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0438] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0439] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0440] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0441] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0442] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0443] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0444] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0445] The present invention relates to a system for motion analysis and training feedback, and its embodiments are described in detail below. This system receives video data in real time from a high-precision video acquisition device, and a server analyzes this data to identify and evaluate motion patterns.

[0446] Server operation

[0447] When the server receives video data, it first applies a generative AI model to analyze the movement of the target object. This allows the server to extract the technical elements of the movement and analyze them by comparing them to standard movement patterns. For example, the server monitors an athlete's swing speed and weight transfer and performs a technical evaluation.

[0448] Feedback generation

[0449] Based on the analysis results, the server automatically generates areas for improvement. For example, if the server determines that "swing timing is delayed," it is the server's responsibility to provide specific reasons and methods for correction. Based on this information, the server proposes an optimal training plan to the user.

[0450] Terminal operation

[0451] The terminal receives feedback sent from the server and presents it through the user interface. To make the displayed content visually easy to understand, the terminal can show areas for improvement in the form of graphs, videos, and other visual aids.

[0452] User actions

[0453] Users can review the feedback displayed on their devices and apply it to correcting their form and training. For example, by receiving suggestions for specific behavioral corrections, they can consciously practice those suggestions during their next training session.

[0454] Thus, the present invention is a system that supports efficient training and skill improvement by performing video analysis and technical evaluation in real time and immediately providing users with areas for improvement.

[0455] The following describes the processing flow.

[0456] Step 1:

[0457] The server receives video data in real time from high-precision video acquisition equipment. The video captures the players' movements in detail, and metadata such as timestamps and player identification information is added.

[0458] Step 2:

[0459] The server uses a generative AI model to analyze the received video data. The AI ​​model extracts technical movement elements of the players from the video (e.g., hand and foot positions, swing angle) and quantifies them.

[0460] Step 3:

[0461] The server compares the extracted operational data with standard operational patterns and historical data. This comparison evaluates the accuracy and consistency of the operation and identifies areas for improvement.

[0462] Step 4:

[0463] The server automatically generates improvement suggestions based on the analysis results. Specifically, it creates detailed feedback that includes information such as which parts of the operation differ from the ideal and how they should be corrected.

[0464] Step 5:

[0465] The server sends the generated feedback and recommended training plan to the terminal. Communication with the terminal is conducted in a secure and fast manner.

[0466] Step 6:

[0467] The terminal immediately displays feedback received from the server. To present information in a visually easy-to-understand manner, the terminal uses videos, graphs, and other visual aids to highlight areas for improvement.

[0468] Step 7:

[0469] Users can review feedback on their devices and reflect on their own skills. They can then implement suggested improvement methods and training menus to enhance their skills.

[0470] (Example 1)

[0471] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0472] Providing highly accurate real-time analysis and appropriate feedback in the technical assessment of exercise is a challenging task. Conventional methods have struggled to effectively analyze an exerciser's movements and quickly identify specific areas for improvement. In particular, there is a need to perform accurate assessments tailored to individual characteristics using vast amounts of exercise data, and to develop efficient training plans.

[0473] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0474] In this invention, the server includes an evaluation means for analyzing image information acquired from a high-precision image acquisition means, a notification means for generating and notifying correction points based on the analysis results, a planning means for providing a motion plan based on the notified correction points, a preprocessing means for preprocessing video data and performing noise reduction and frame correction, a generation model usage means for analyzing the movement of a target object frame by frame and extracting motion patterns as numerical information, and a comparison means for calculating deviations of technical parameters by comparing with a standard motion pattern database. This enables precise motion analysis and feedback in real time.

[0475] "High-precision image acquisition means" refers to devices and methods for acquiring high-resolution, detailed video in real time.

[0476] "Evaluation means" refers to a process or device for analyzing acquired image information and automatically analyzing and evaluating the behavior of a target object.

[0477] "Notification means" refers to methods or devices for communicating corrections generated based on analysis results to the user.

[0478] "Plan delivery means" refers to the function of formulating and providing the optimal exercise plan for the user based on the notified revisions.

[0479] "Preprocessing means" refers to the process of preparing the video data to be analyzed, such as by removing noise or correcting frames.

[0480] "Generative model usage" refers to the process of applying an AI model to analyze the movement of a target object and extract its movement pattern as numerical information.

[0481] "Comparison method" refers to the process of comparing extracted technical parameters with a standard operating pattern database and calculating the deviation.

[0482] This invention provides a system that offers automated motion analysis and effective feedback. This system operates through the interaction of a server, terminals, and users.

[0483] The server receives image information collected in real time by high-precision image acquisition methods. To preprocess the video data, the server performs noise reduction and frame correction to prepare data suitable for analysis. This process can use common image processing libraries. The preprocessed data is analyzed using generative modeling methods. The server utilizes AI frameworks such as TensorFlow and PyTorch to extract the motion patterns of target objects as numerical information on a frame-by-frame basis.

[0484] The extracted technical elements are compared to a standard operating pattern database within the server. The server uses Python's statistical libraries to calculate the deviations from the analyzed technical parameters, thereby performing a technical evaluation. Based on the evaluation results, the server suggests modifications and notifies the user. In this notification process, the proposed modifications are determined by referring to past cases and expert knowledge stored in the database.

[0485] The device receives feedback sent from the server and presents it to the user. Using HTML5 and JavaScript, the device clearly displays the feedback through visual elements such as graphs and animations. This allows the user to intuitively understand the suggested improvements.

[0486] Based on the feedback displayed on the device, users can create training plans to improve their skills. For example, if the feedback includes instructions such as "start your swing 0.2 seconds earlier," the user is expected to consciously implement those instructions in their next practice session.

[0487] In this way, the system aims to effectively improve athletic technique through the cooperation of the server, terminal, and user. An example of a prompt message would be, "Analyze the speed and timing of the golf swing and suggest areas for improvement."

[0488] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0489] Step 1:

[0490] The server receives image information in real time from a high-precision image acquisition system. The input is raw video data, and the output is pre-processed, analyzable data. This video information requires noise reduction and frame correction, and the server performs these preprocessing steps using an image processing library. Preprocessing includes contrast adjustment and filtering of unwanted noise.

[0491] Step 2:

[0492] The server inputs pre-processed data into a generating AI model to extract the motion patterns of the target object. The input is denoised video data, and the output is numerical data representing the motion patterns. In this process, the server utilizes TensorFlow to analyze the characteristics of the motion. Specifically, this includes analyzing the speed and angle of the motion frame by frame.

[0493] Step 3:

[0494] The server compares the extracted movement patterns with standard movement patterns. The input is numerical data of the movement, and the output is an evaluation result including deviations. The server refers to a standard pattern database and calculates deviations using Python's statistical libraries. The evaluation includes technical elements such as swing timing and the degree of agreement in weight transfer.

[0495] Step 4:

[0496] The server generates corrections based on the evaluation results and creates feedback tailored to the user. The input is the evaluation result, and the output is feedback that presents specific improvement measures. The server proposes improvements based on past data and expert knowledge. This step often includes specific instructions such as "move the swing timing forward by 0.2 seconds."

[0497] Step 5:

[0498] The terminal receives feedback from the server and presents it visually in the user interface. The input is feedback information sent from the server, and the output is a visual presentation using graphs and animations. The terminal uses HTML5 and JavaScript to display the feedback graphically in an intuitive and easy-to-understand manner.

[0499] Step 6:

[0500] Users review the feedback displayed on their device and incorporate it into their movements. The input is the visual feedback displayed on the device, and the output is putting the suggested improvements into practice. Users will keep the displayed corrections in mind during their next training session and work on specific improvements to their movements.

[0501] (Application Example 1)

[0502] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0503] This invention aims to improve work efficiency and safety in factories, but the evaluation of individual actions in current work procedures and the proposal for improvement are sometimes not adequately carried out. Therefore, there is a need for a means to understand the actions of the workers themselves and to realize efficient work improvements. Furthermore, there is a need for visual and explicit feedback to immediately put the obtained suggestions into practice.

[0504] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0505] In this invention, the server includes an evaluation means for analyzing motion data acquired from a high-precision video acquisition means, a notification means for generating improvement points based on the analysis results and notifying the user via a visual display means, and a plan provision means for providing a guidance plan based on the notified improvement points to support efficient and safe work. As a result, workers can have their movements accurately analyzed and immediately receive specific improvement measures through visual feedback.

[0506] A "high-precision video acquisition method" is a device that accurately records the movements of a subject in real time, enabling detailed motion analysis.

[0507] "Motion data" refers to numerical and video data that represents information about the movements of the worker in question, and this data is used to evaluate the movements.

[0508] "Evaluation means" refers to a system or function that analyzes acquired motion data and automatically performs an evaluation of the efficiency and safety of the target work.

[0509] "Notification means" refers to devices or functions that visually or audibly communicate to the user any improvements or precautions derived from the analysis results.

[0510] "Visual display means" refers to a device or function that displays analysis results using graphs, animations, etc., in order to provide information in a way that is easy for the user to understand.

[0511] A "planning provision method" refers to a system or function that provides users with specific work improvement guidance and procedures based on evaluation results.

[0512] A "training plan" is a plan that includes improvement methods and procedures, prepared to carry out work efficiently and safely.

[0513] A "generative AI model" is a program or model that uses machine learning and artificial intelligence technologies to analyze data and generate useful information or suggestions.

[0514] A "prompt statement" is an instruction or command statement provided as input necessary for a generative AI model to perform accurate analysis and make suggestions.

[0515] A "feedback mechanism" is a system or function that provides users with analyzed results and improvement suggestions to encourage them to modify or improve their actions.

[0516] This invention is a system for improving the efficiency and safety of factory operations. The system primarily consists of three main components: a high-precision video acquisition device, a server, and a terminal.

[0517] The server first receives motion data acquired by a high-precision video acquisition system. This data contains information about the movements of workers in the factory. Next, the server analyzes this motion data using a generative AI model. This analysis evaluates work efficiency and safety and identifies areas for improvement. The specific analysis process uses software such as Python and TensorFlow. This makes it possible to compare complex motion patterns with standard movements and identify differences and areas for improvement.

[0518] The analysis results are generated using prompt messages. These prompt messages are entered in the form of "Based on the worker's motion video, please provide efficient motion patterns. We will generate feedback that emphasizes smooth weight transfer and hand movements." The server generates specific improvement suggestions based on these prompt messages and sends them to the terminal.

[0519] The terminal receives feedback sent from the server and notifies the user through visual means. This allows the user to immediately grasp areas for improvement, and the information is presented in formats such as graphs and animations, making it easy to understand intuitively. The terminal also provides a specific guidance plan based on the areas for improvement, supporting the user in improving their work.

[0520] As a concrete example, let's consider manual assembly work on a manufacturing line. This system analyzes the worker's movements, identifies inefficient material handling and unnecessary actions, and provides improvement suggestions based on efficient movement patterns. As a result, workers can immediately optimize their work procedures, leading to safer and more efficient work.

[0521] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0522] Step 1:

[0523] The server receives motion data acquired in real time using high-precision video acquisition methods. The input is video data transmitted from the camera, and the output is data in a format that allows for efficient analysis. This data is processed using Python and the OpenCV library.

[0524] Step 2:

[0525] The server analyzes the received motion data using a generating AI model. The input is the motion data obtained in step 1, and the output is the evaluation results of the motion and suggested improvement data. Here, TensorFlow is used to have the AI ​​model analyze the motion data and extract areas for improvement in work efficiency and safety.

[0526] Step 3:

[0527] The server generates a prompt message based on the analysis results and creates feedback based on it. The input is the analysis data obtained in step 2, and the output is feedback information that includes specific improvement suggestions to be provided to the user. Specifically, it generates the prompt message: "Based on the video of the worker's movements, please provide an efficient movement pattern. We will generate feedback that emphasizes smooth weight transfer and hand movements."

[0528] Step 4:

[0529] The server sends the generated feedback to the terminal. The input is feedback information, and the output is specific improvement suggestions that the user receives. Here, the HTTP protocol is used to send the data to the terminal.

[0530] Step 5:

[0531] The device visually displays the feedback information received from the server. The input is the feedback received in step 4, and the output is improvement suggestions displayed in a way that the user can understand. Specifically, feedback is displayed in graph or animation format using tools such as MPAndroidChart.

[0532] Step 6:

[0533] The user reviews the feedback displayed on the device and takes specific corrective actions. The input is visually displayed information, and the output is the improvement of their own work procedures. At this stage, the user proceeds with the work while being mindful of the proposed training plan.

[0534] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0535] This invention is a system that combines motion analysis and emotion recognition, achieving both improved user motion performance and emotional care. This system includes a video acquisition device, an analysis device, a notification device, a plan provision device, an emotion engine, and an adjustment device, and its embodiments are described in detail below.

[0536] Server operation

[0537] The server receives video data in real time from a high-precision video acquisition device and analyzes the player's movements. Next, the server extracts the technical elements of the movements using a generated AI model, compares them to standard movements, and performs an evaluation. After that, the server automatically generates areas for improvement based on the evaluation results.

[0538] Manipulating the Emotion Engine

[0539] The server analyzes facial expression data from the user's device using an emotion engine to recognize the user's emotions. The recognized emotions become important information for optimizing training content according to the user's psychological state. For example, if the emotion engine determines that the user is anxious, it will instruct the server to generate motivational feedback.

[0540] Feedback and training plan

[0541] The server creates an optimized training plan based on the analysis results and the output of the emotion engine. Feedback is customized to the user's emotional state through an adjustment mechanism and communicated to the user. For example, the server suggests challenging training when the user is feeling motivated, and a recovery-focused plan when fatigue is observed.

[0542] Terminal operation

[0543] The device receives feedback and training plans sent from the server and presents them to the user. The device provides a visually and audibly intuitive interface, with emphasis on emotional care.

[0544] User actions

[0545] Based on the information provided, users can utilize it for their own training methods and emotional care, aiming for efficient skill improvement. Specifically, by understanding the content of the training plan, practicing according to it, and reflecting on the feedback, they can maintain sustainable growth and mental health.

[0546] This invention realizes a system that supports both the user's technical abilities and psychological state by integrating motion analysis and emotion recognition, thereby providing a more personalized experience.

[0547] The following describes the processing flow.

[0548] Step 1:

[0549] The server receives real-time video footage of players from high-precision video acquisition equipment. The server then organizes the data by adding timestamps and player identification information to the video data.

[0550] Step 2:

[0551] The server processes the received video data through an analysis device and uses a generated AI model to technically analyze the player's movements. It extracts elements of the movement (e.g., swing angle, movement speed) and evaluates them by comparing them to existing standards.

[0552] Step 3:

[0553] The server uses an emotion engine to analyze the user's facial expression data sent from the terminal in real time. Based on the data from the face and voice, the emotion engine evaluates the user's emotional state (joy, anxiety, concentration, etc.).

[0554] Step 4:

[0555] The server comprehensively analyzes both exercise and emotional data to generate optimal training feedback for the user. When the user is feeling down, it provides feedback that includes encouraging messages to maintain motivation.

[0556] Step 5:

[0557] The server sends the generated feedback and training plan to the terminal. The terminal then presents this feedback and plan to the user as a daily training menu.

[0558] Step 6:

[0559] The terminal visually organizes information sent from the server and displays it on the user interface. It utilizes colors and sounds to highlight content relevant to the user's emotional state and presents it in a way that is easy for the user to understand.

[0560] Step 7:

[0561] Users review the displayed feedback and incorporate it into their training. For example, they might improve their skills by focusing on specific techniques in their next practice session based on the suggested improvements. Users also use the feedback to help understand their own emotional state.

[0562] (Example 2)

[0563] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0564] This invention aims to provide an efficient method for simultaneously improving athletic performance and providing psychological care. Conventional techniques have focused solely on the technical evaluation of exercise, with insufficient consideration given to the user's emotional state and optimization of training plans. Therefore, a new system is needed to support users in both their athletic and psychological aspects.

[0565] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0566] In this invention, the server includes an evaluation means that analyzes motion data acquired from high-precision imaging equipment and evaluates the subject's movement state; a notification means that automatically generates points for technical improvement using a generation AI based on the analysis results and communicates these improvements to the user; and a plan provision means that recognizes the user's emotional state and creates an exercise plan optimized for that state. This makes it possible to provide a personalized training plan that takes into account the user's emotional state, along with improving the technical aspects of the exercise.

[0567] "High-precision imaging equipment" refers to devices such as cameras and sensors that capture the subject's movements at high resolution and frame rate, providing detailed data.

[0568] "Motion data" refers to information about the subject's movement generated from video information acquired by the camera.

[0569] "Evaluation means" refers to a device or program for analyzing acquired motion data, extracting the technical elements of the movement, and evaluating the subject's movement state.

[0570] "Generative AI" refers to systems or programs that use artificial intelligence technology to automatically generate new data and information.

[0571] A "notification means" is a device or program used to communicate evaluation results and areas for improvement to users.

[0572] "Emotion recognition means" refers to a program or device that analyzes a user's facial expression data and identifies their emotional state.

[0573] A "feedback mechanism" is a device or program that provides appropriate feedback to the user based on the analysis results and emotional state.

[0574] "Presentation means" refers to a device or interface for presenting information transmitted from a server to a user visually or audibly.

[0575] A "comparison device" is a device or program used to evaluate acquired motion data by comparing it with past data.

[0576] "Selection means" refers to a device or program for generating different exercise plans according to the user's selection.

[0577] This invention is a system that integrates motor evaluation and emotion recognition, simultaneously achieving improvement in the user's motor skills and psychological care. The system includes imaging equipment, analysis equipment, notification equipment, planning equipment, emotion recognition equipment, and adjustment equipment. Specific embodiments are described below.

[0578] Server operation

[0579] The server first receives motion data in real time from high-precision imaging equipment. This motion data is acquired, for example, by a typical high-resolution camera. The server then applies a Python motion analysis algorithm to extract the technical elements of the motion. Subsequently, it uses generative AI to compare it with reference motions stored in a database to derive a technical evaluation and areas for improvement. The server then notifies the user of the evaluation results and areas for improvement.

[0580] Manipulating the Emotion Engine

[0581] The server receives facial expression data from the user's device and analyzes it using an emotion engine. The emotion engine identifies the user's emotional state, for example, by using a common emotion recognition API. The emotional state is determined as a state such as "anxiety" or "concentration." Based on the analysis results, the server generates a training plan that is best suited to the user's state.

[0582] Feedback and training plan

[0583] The server creates an optimized training plan based on the analysis results and emotional state. This process utilizes an AI model that takes into account the user's past data. The feedback content is also customized according to the user's emotional state. The server provides the user with customized feedback to maximize the effectiveness of the training.

[0584] Terminal operation

[0585] The terminal receives information transmitted from the server and presents it to the user in an easy-to-understand manner. The terminal is designed with a visually and audibly designed interface to allow the user to easily understand the feedback. Through the information provided on the terminal, the user can adjust their exercise methods and manage their mental state.

[0586] User utilization

[0587] Based on the feedback and training plan provided, users improve their athletic performance while maintaining their mental well-being. For example, they can improve their form and take care of their mental health according to the feedback. By continuously reviewing their training content, long-term growth can be expected.

[0588] Specific examples and prompt statements

[0589] For example, the server might analyze a tennis player's swing motion, and if the emotion recognition engine determines that the player is concentrating, it might generate a training plan aimed at further improving their technique. An example of a prompt to the generated AI model would be, "Analyze the user's swing motion, compare it to standard motion, and provide an evaluation and suggestions for improvement."

[0590] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0591] Step 1:

[0592] The server receives motion data in real time from high-precision imaging equipment. The input is video data captured by the camera. This video data represents the player's movements and is converted into an analyzable video dataset as output. Specifically, the server receives the video data and prepares it for analysis while maintaining its image quality.

[0593] Step 2:

[0594] The server applies a motion analysis algorithm to extract the technical elements of the athlete. The input is the video dataset obtained in step 1, and the output is analysis data containing the technical elements. The server uses an algorithm implemented in Python to perform motion analysis, quantifying, for example, the movement and speed of the athlete's limbs.

[0595] Step 3:

[0596] The server uses a generative AI model to compare technical elements with reference motions. Inputs include analysis data and reference motion data, and the output generates a technical evaluation of the motion and areas for improvement. Specifically, the server inputs prompt statements into the generative AI model, which then derives the technical evaluation and necessary improvements.

[0597] Step 4:

[0598] The server receives facial expression data from the user's device and analyzes the emotional state using an emotion recognition engine. The input is facial expression data acquired from the user's device, and the output is a specific label that determines the user's emotional state. The server inputs the facial expression data into the emotion engine, processes the results, and determines the emotional state.

[0599] Step 5:

[0600] The server creates an optimized training plan based on the analysis results and emotional state. Inputs include technical evaluation, areas for improvement, and emotional state, while the output is a user-specific training plan. The server integrates this data to generate the most effective training content.

[0601] Step 6:

[0602] The server generates feedback and sends it to the terminal. The input is a well-organized technical evaluation and training plan, and the output is feedback data presented to the user visually and aurally. Specifically, the server compiles the feedback and sends it to the terminal via a reconciliation device.

[0603] Step 7:

[0604] The terminal displays the received feedback and training plan. The input is feedback data sent from the server, and the output is information displayed to the user. The terminal uses a graphical user interface to visually display the feedback content and, with voice assistance as needed, conveys the information clearly.

[0605] Step 8:

[0606] The user utilizes the provided feedback and training plan to carry out the training. The input is the feedback and plan presented on the device, and the output is the user's improved skills and improved psychological state. In terms of specific actions, the user trains according to the presented areas for improvement and continues practicing towards the goal.

[0607] (Application Example 2)

[0608] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0609] To simultaneously improve athletic performance and provide psychological support, it is necessary to provide personalized feedback and training plans to each individual user in real time. However, conventional systems can only perform exercise analysis and emotion recognition independently, making it difficult to effectively integrate the results of each into the presentation of feedback and plans.

[0610] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0611] In this invention, the server includes an evaluation means for analyzing image data acquired from a high-precision image acquisition means and automatically evaluating the movement of a target object; a notification means for generating areas for improvement based on the analysis results and notifying the user of these areas for improvement; and an emotion analysis means for analyzing the user's emotional state using an emotion recognition means and adjusting the feedback based on the emotion data. This makes it possible to simultaneously provide personalized movement improvement suggestions and psychological support for each user.

[0612] A "high-precision image acquisition method" is an image acquisition device with excellent resolution and accuracy for capturing the movement of a target object in detail.

[0613] "Evaluation means" refers to a function that analyzes acquired video data, extracts characteristics related to the motion of the target object, and evaluates its motion performance by comparing it with standard motion.

[0614] A "notification device" is a device that uses visual or auditory media to communicate information about analyzed areas for improvement to the user.

[0615] "Emotion recognition means" refers to a function that analyzes facial expressions and voice data to determine the user's emotional state and estimate their psychological state.

[0616] "Emotion analysis means" refers to a system function that adjusts the content of feedback and training plans based on recognized user emotion data.

[0617] The "plan delivery method" refers to the function of formulating and providing training schedules optimized for individual users based on information obtained from evaluation methods and emotion analysis methods.

[0618] This invention utilizes a system that integrates motion analysis and emotion recognition. The server receives video data from a high-precision image acquisition means and uses an image analysis library (e.g., OpenCV) for motion analysis. The acquired video data is analyzed to compare the movement of the target object with a standard movement and evaluate the movement. Based on the analysis results, the system provides suggestions for improvement to the user via a notification means. For example, it may provide specific advice such as, "Try swinging your arms a little more" when describing running form.

[0619] Furthermore, the server uses emotion recognition capabilities and utilizes speech analysis libraries (e.g., Librosa) and machine learning libraries (e.g., TensorFlow and PyTorch) to analyze the user's emotional state. This emotional data is used to provide feedback and adjust training plans, offering appropriate psychological support to the user. For example, if the server determines that the user's motivation is low, it can play upbeat music as an "encouraging message."

[0620] The device receives notifications and plans from the server and presents them to the user through an intuitively understandable interface (e.g., touchscreen or audio output). Based on the information provided, the user can adjust their training plan to ensure continuous skill improvement and emotional support.

[0621] As a concrete example, when a user goes jogging, the system can suggest a jogging plan tailored to their motivation and physical condition that day via their device. An example of a prompt used in this case is: "If the user looks anxious, please suggest what kind of motivational feedback would be appropriate." In this way, by providing feedback and training plans using a generative AI model, it is possible to provide optimal support to each individual user.

[0622] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0623] Step 1:

[0624] The server captures the user's movements using image acquisition equipment and receives video data in real time. The input is high-precision video data, which is divided into frames and subjected to initial processing using an image analysis library. The output is frame data, which forms the basis for the analysis process. Based on this frame data, the system is ready to extract the user's movement patterns.

[0625] Step 2:

[0626] The server applies an image analysis algorithm to extract motion patterns from video data and compares them with a standard motion database. The input is pre-processed frame data, and the output is an evaluation result regarding the motion performance of the target object. This data processing reveals specific areas for improvement in the user's movements.

[0627] Step 3:

[0628] The server generates improvement suggestions using an AI model based on the user's evaluation results. This process outputs a feedback script, including prompts, based on the input performance evaluation data. The generated feedback is then refined to make it easier for the user to understand.

[0629] Step 4:

[0630] The server uses emotion recognition to receive user voice data from the terminal and perform emotion analysis. The input is voice data, and emotions are identified using a machine learning library. The output is data about the user's emotional state. This data is used to adjust the feedback.

[0631] Step 5:

[0632] The device presents the user with a training plan based on improvement suggestions and sentiment data received from the server. Inputs are notification data and training plan data from the server. Output is an interface display that intuitively shows the user feedback and training plan. The device uses visual and auditory elements to present information to the user and support smooth training.

[0633] Step 6:

[0634] Users perform exercises based on feedback and training plans provided through their devices. The inputs are the feedback and plan information, and the user's actions are the output. By utilizing this feedback, users can improve their skills and maintain their mental well-being.

[0635] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0636] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0637] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0638] [Fourth Embodiment]

[0639] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0640] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0641] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0642] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0643] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0644] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0645] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0646] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0647] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0648] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0649] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0650] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0651] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0652] The present invention relates to a system for motion analysis and training feedback, and its embodiments are described in detail below. This system receives video data in real time from a high-precision video acquisition device, and a server analyzes this data to identify and evaluate motion patterns.

[0653] Server operation

[0654] When the server receives video data, it first applies a generative AI model to analyze the movement of the target object. This allows the server to extract the technical elements of the movement and analyze them by comparing them to standard movement patterns. For example, the server monitors an athlete's swing speed and weight transfer and performs a technical evaluation.

[0655] Feedback generation

[0656] Based on the analysis results, the server automatically generates areas for improvement. For example, if the server determines that "swing timing is delayed," it is the server's responsibility to provide specific reasons and methods for correction. Based on this information, the server proposes an optimal training plan to the user.

[0657] Terminal operation

[0658] The terminal receives feedback sent from the server and presents it through the user interface. To make the displayed content visually easy to understand, the terminal can show areas for improvement in the form of graphs, videos, and other visual aids.

[0659] User actions

[0660] Users can review the feedback displayed on their devices and apply it to correcting their form and training. For example, by receiving suggestions for specific behavioral corrections, they can consciously practice those suggestions during their next training session.

[0661] Thus, the present invention is a system that supports efficient training and skill improvement by performing video analysis and technical evaluation in real time and immediately providing users with areas for improvement.

[0662] The following describes the processing flow.

[0663] Step 1:

[0664] The server receives video data in real time from high-precision video acquisition equipment. The video captures the players' movements in detail, and metadata such as timestamps and player identification information is added.

[0665] Step 2:

[0666] The server uses a generative AI model to analyze the received video data. The AI ​​model extracts technical movement elements of the players from the video (e.g., hand and foot positions, swing angle) and quantifies them.

[0667] Step 3:

[0668] The server compares the extracted operational data with standard operational patterns and historical data. This comparison evaluates the accuracy and consistency of the operation and identifies areas for improvement.

[0669] Step 4:

[0670] The server automatically generates improvement suggestions based on the analysis results. Specifically, it creates detailed feedback that includes information such as which parts of the operation differ from the ideal and how they should be corrected.

[0671] Step 5:

[0672] The server sends the generated feedback and recommended training plan to the terminal. Communication with the terminal is conducted in a secure and fast manner.

[0673] Step 6:

[0674] The terminal immediately displays feedback received from the server. To present information in a visually easy-to-understand manner, the terminal uses videos, graphs, and other visual aids to highlight areas for improvement.

[0675] Step 7:

[0676] Users can review feedback on their devices and reflect on their own skills. They can then implement suggested improvement methods and training menus to enhance their skills.

[0677] (Example 1)

[0678] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0679] Providing highly accurate real-time analysis and appropriate feedback in the technical assessment of exercise is a challenging task. Conventional methods have struggled to effectively analyze an exerciser's movements and quickly identify specific areas for improvement. In particular, there is a need to perform accurate assessments tailored to individual characteristics using vast amounts of exercise data, and to develop efficient training plans.

[0680] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0681] In this invention, the server includes an evaluation means for analyzing image information acquired from a high-precision image acquisition means, a notification means for generating and notifying correction points based on the analysis results, a planning means for providing a motion plan based on the notified correction points, a preprocessing means for preprocessing video data and performing noise reduction and frame correction, a generation model usage means for analyzing the movement of a target object frame by frame and extracting motion patterns as numerical information, and a comparison means for calculating deviations of technical parameters by comparing with a standard motion pattern database. This enables precise motion analysis and feedback in real time.

[0682] "High-precision image acquisition means" refers to devices and methods for acquiring high-resolution, detailed video in real time.

[0683] "Evaluation means" refers to a process or device for analyzing acquired image information and automatically analyzing and evaluating the behavior of a target object.

[0684] "Notification means" refers to methods or devices for communicating corrections generated based on analysis results to the user.

[0685] "Plan delivery means" refers to the function of formulating and providing the optimal exercise plan for the user based on the notified revisions.

[0686] "Preprocessing means" refers to the process of preparing the video data to be analyzed, such as by removing noise or correcting frames.

[0687] "Generative model usage" refers to the process of applying an AI model to analyze the movement of a target object and extract its movement pattern as numerical information.

[0688] "Comparison method" refers to the process of comparing extracted technical parameters with a standard operating pattern database and calculating the deviation.

[0689] This invention provides a system that offers automated motion analysis and effective feedback. This system operates through the interaction of a server, terminals, and users.

[0690] The server receives image information collected in real time by high-precision image acquisition methods. To preprocess the video data, the server performs noise reduction and frame correction to prepare data suitable for analysis. This process can use common image processing libraries. The preprocessed data is analyzed using generative modeling methods. The server utilizes AI frameworks such as TensorFlow and PyTorch to extract the motion patterns of target objects as numerical information on a frame-by-frame basis.

[0691] The extracted technical elements are compared to a standard operating pattern database within the server. The server uses Python's statistical libraries to calculate the deviations from the analyzed technical parameters, thereby performing a technical evaluation. Based on the evaluation results, the server suggests modifications and notifies the user. In this notification process, the proposed modifications are determined by referring to past cases and expert knowledge stored in the database.

[0692] The device receives feedback sent from the server and presents it to the user. Using HTML5 and JavaScript, the device clearly displays the feedback through visual elements such as graphs and animations. This allows the user to intuitively understand the suggested improvements.

[0693] Based on the feedback displayed on the device, users can create training plans to improve their skills. For example, if the feedback includes instructions such as "start your swing 0.2 seconds earlier," the user is expected to consciously implement those instructions in their next practice session.

[0694] In this way, the system aims to effectively improve athletic technique through the cooperation of the server, terminal, and user. An example of a prompt message would be, "Analyze the speed and timing of the golf swing and suggest areas for improvement."

[0695] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0696] Step 1:

[0697] The server receives image information in real time from a high-precision image acquisition system. The input is raw video data, and the output is pre-processed, analyzable data. This video information requires noise reduction and frame correction, and the server performs these preprocessing steps using an image processing library. Preprocessing includes contrast adjustment and filtering of unwanted noise.

[0698] Step 2:

[0699] The server inputs pre-processed data into a generating AI model to extract the motion patterns of the target object. The input is denoised video data, and the output is numerical data representing the motion patterns. In this process, the server utilizes TensorFlow to analyze the characteristics of the motion. Specifically, this includes analyzing the speed and angle of the motion frame by frame.

[0700] Step 3:

[0701] The server compares the extracted movement patterns with standard movement patterns. The input is numerical data of the movement, and the output is an evaluation result including deviations. The server refers to a standard pattern database and calculates deviations using Python's statistical libraries. The evaluation includes technical elements such as swing timing and the degree of agreement in weight transfer.

[0702] Step 4:

[0703] The server generates corrections based on the evaluation results and creates feedback tailored to the user. The input is the evaluation result, and the output is feedback that presents specific improvement measures. The server proposes improvements based on past data and expert knowledge. This step often includes specific instructions such as "move the swing timing forward by 0.2 seconds."

[0704] Step 5:

[0705] The terminal receives feedback from the server and presents it visually in the user interface. The input is feedback information sent from the server, and the output is a visual presentation using graphs and animations. The terminal uses HTML5 and JavaScript to display the feedback graphically in an intuitive and easy-to-understand manner.

[0706] Step 6:

[0707] Users review the feedback displayed on their device and incorporate it into their movements. The input is the visual feedback displayed on the device, and the output is putting the suggested improvements into practice. Users will keep the displayed corrections in mind during their next training session and work on specific improvements to their movements.

[0708] (Application Example 1)

[0709] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0710] This invention aims to improve work efficiency and safety in factories, but the evaluation of individual actions in current work procedures and the proposal for improvement are sometimes not adequately carried out. Therefore, there is a need for a means to understand the actions of the workers themselves and to realize efficient work improvements. Furthermore, there is a need for visual and explicit feedback to immediately put the obtained suggestions into practice.

[0711] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0712] In this invention, the server includes an evaluation means for analyzing motion data acquired from a high-precision video acquisition means, a notification means for generating improvement points based on the analysis results and notifying the user via a visual display means, and a plan provision means for providing a guidance plan based on the notified improvement points to support efficient and safe work. As a result, workers can have their movements accurately analyzed and immediately receive specific improvement measures through visual feedback.

[0713] A "high-precision video acquisition method" is a device that accurately records the movements of a subject in real time, enabling detailed motion analysis.

[0714] "Motion data" refers to numerical and video data that represents information about the movements of the worker in question, and this data is used to evaluate the movements.

[0715] "Evaluation means" refers to a system or function that analyzes acquired motion data and automatically performs an evaluation of the efficiency and safety of the target work.

[0716] "Notification means" refers to devices or functions that visually or audibly communicate to the user any improvements or precautions derived from the analysis results.

[0717] "Visual display means" refers to a device or function that displays analysis results using graphs, animations, etc., in order to provide information in a way that is easy for the user to understand.

[0718] A "planning provision method" refers to a system or function that provides users with specific work improvement guidance and procedures based on evaluation results.

[0719] A "training plan" is a plan that includes improvement methods and procedures, prepared to carry out work efficiently and safely.

[0720] A "generative AI model" is a program or model that uses machine learning and artificial intelligence technologies to analyze data and generate useful information or suggestions.

[0721] A "prompt statement" is an instruction or command statement provided as input necessary for a generative AI model to perform accurate analysis and make suggestions.

[0722] A "feedback mechanism" is a system or function that provides users with analyzed results and improvement suggestions to encourage them to modify or improve their actions.

[0723] This invention is a system for improving the efficiency and safety of factory operations. The system primarily consists of three main components: a high-precision video acquisition device, a server, and a terminal.

[0724] The server first receives motion data acquired by a high-precision video acquisition system. This data contains information about the movements of workers in the factory. Next, the server analyzes this motion data using a generative AI model. This analysis evaluates work efficiency and safety and identifies areas for improvement. The specific analysis process uses software such as Python and TensorFlow. This makes it possible to compare complex motion patterns with standard movements and identify differences and areas for improvement.

[0725] The analysis results are generated using prompt messages. These prompt messages are entered in the form of "Based on the worker's motion video, please provide efficient motion patterns. We will generate feedback that emphasizes smooth weight transfer and hand movements." The server generates specific improvement suggestions based on these prompt messages and sends them to the terminal.

[0726] The terminal receives feedback sent from the server and notifies the user through visual means. This allows the user to immediately grasp areas for improvement, and the information is presented in formats such as graphs and animations, making it easy to understand intuitively. The terminal also provides a specific guidance plan based on the areas for improvement, supporting the user in improving their work.

[0727] As a concrete example, let's consider manual assembly work on a manufacturing line. This system analyzes the worker's movements, identifies inefficient material handling and unnecessary actions, and provides improvement suggestions based on efficient movement patterns. As a result, workers can immediately optimize their work procedures, leading to safer and more efficient work.

[0728] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0729] Step 1:

[0730] The server receives motion data acquired in real time using high-precision video acquisition methods. The input is video data transmitted from the camera, and the output is data in a format that allows for efficient analysis. This data is processed using Python and the OpenCV library.

[0731] Step 2:

[0732] The server analyzes the received motion data using a generating AI model. The input is the motion data obtained in step 1, and the output is the evaluation results of the motion and suggested improvement data. Here, TensorFlow is used to have the AI ​​model analyze the motion data and extract areas for improvement in work efficiency and safety.

[0733] Step 3:

[0734] The server generates a prompt message based on the analysis results and creates feedback based on it. The input is the analysis data obtained in step 2, and the output is feedback information that includes specific improvement suggestions to be provided to the user. Specifically, it generates the prompt message: "Based on the video of the worker's movements, please provide an efficient movement pattern. We will generate feedback that emphasizes smooth weight transfer and hand movements."

[0735] Step 4:

[0736] The server sends the generated feedback to the terminal. The input is feedback information, and the output is specific improvement suggestions that the user receives. Here, the HTTP protocol is used to send the data to the terminal.

[0737] Step 5:

[0738] The device visually displays the feedback information received from the server. The input is the feedback received in step 4, and the output is improvement suggestions displayed in a way that the user can understand. Specifically, feedback is displayed in graph or animation format using tools such as MPAndroidChart.

[0739] Step 6:

[0740] The user reviews the feedback displayed on the device and takes specific corrective actions. The input is visually displayed information, and the output is the improvement of their own work procedures. At this stage, the user proceeds with the work while being mindful of the proposed training plan.

[0741] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0742] This invention is a system that combines motion analysis and emotion recognition, achieving both improved user motion performance and emotional care. This system includes a video acquisition device, an analysis device, a notification device, a plan provision device, an emotion engine, and an adjustment device, and its embodiments are described in detail below.

[0743] Server operation

[0744] The server receives video data in real time from a high-precision video acquisition device and analyzes the player's movements. Next, the server extracts the technical elements of the movements using a generated AI model, compares them to standard movements, and performs an evaluation. After that, the server automatically generates areas for improvement based on the evaluation results.

[0745] Manipulating the Emotion Engine

[0746] The server analyzes facial expression data from the user's device using an emotion engine to recognize the user's emotions. The recognized emotions become important information for optimizing training content according to the user's psychological state. For example, if the emotion engine determines that the user is anxious, it will instruct the server to generate motivational feedback.

[0747] Feedback and training plan

[0748] The server creates an optimized training plan based on the analysis results and the output of the emotion engine. Feedback is customized to the user's emotional state through an adjustment mechanism and communicated to the user. For example, the server suggests challenging training when the user is feeling motivated, and a recovery-focused plan when fatigue is observed.

[0749] Terminal operation

[0750] The device receives feedback and training plans sent from the server and presents them to the user. The device provides a visually and audibly intuitive interface, with emphasis on emotional care.

[0751] User actions

[0752] Based on the information provided, users can utilize it for their own training methods and emotional care, aiming for efficient skill improvement. Specifically, by understanding the content of the training plan, practicing according to it, and reflecting on the feedback, they can maintain sustainable growth and mental health.

[0753] This invention realizes a system that supports both the user's technical abilities and psychological state by integrating motion analysis and emotion recognition, thereby providing a more personalized experience.

[0754] The following describes the processing flow.

[0755] Step 1:

[0756] The server receives real-time video footage of players from high-precision video acquisition equipment. The server then organizes the data by adding timestamps and player identification information to the video data.

[0757] Step 2:

[0758] The server processes the received video data through an analysis device and uses a generated AI model to technically analyze the player's movements. It extracts elements of the movement (e.g., swing angle, movement speed) and evaluates them by comparing them to existing standards.

[0759] Step 3:

[0760] The server uses an emotion engine to analyze the user's facial expression data sent from the terminal in real time. Based on the data from the face and voice, the emotion engine evaluates the user's emotional state (joy, anxiety, concentration, etc.).

[0761] Step 4:

[0762] The server comprehensively analyzes both exercise and emotional data to generate optimal training feedback for the user. When the user is feeling down, it provides feedback that includes encouraging messages to maintain motivation.

[0763] Step 5:

[0764] The server sends the generated feedback and training plan to the terminal. The terminal then presents this feedback and plan to the user as a daily training menu.

[0765] Step 6:

[0766] The terminal visually organizes information sent from the server and displays it on the user interface. It utilizes colors and sounds to highlight content relevant to the user's emotional state and presents it in a way that is easy for the user to understand.

[0767] Step 7:

[0768] Users review the displayed feedback and incorporate it into their training. For example, they might improve their skills by focusing on specific techniques in their next practice session based on the suggested improvements. Users also use the feedback to help understand their own emotional state.

[0769] (Example 2)

[0770] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0771] This invention aims to provide an efficient method for simultaneously improving athletic performance and providing psychological care. Conventional techniques have focused solely on the technical evaluation of exercise, with insufficient consideration given to the user's emotional state and optimization of training plans. Therefore, a new system is needed to support users in both their athletic and psychological aspects.

[0772] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0773] In this invention, the server includes an evaluation means that analyzes motion data acquired from high-precision imaging equipment and evaluates the subject's movement state; a notification means that automatically generates points for technical improvement using a generation AI based on the analysis results and communicates these improvements to the user; and a plan provision means that recognizes the user's emotional state and creates an exercise plan optimized for that state. This makes it possible to provide a personalized training plan that takes into account the user's emotional state, along with improving the technical aspects of the exercise.

[0774] "High-precision imaging equipment" refers to devices such as cameras and sensors that capture the subject's movements at high resolution and frame rate, providing detailed data.

[0775] "Motion data" refers to information about the subject's movement generated from video information acquired by the camera.

[0776] "Evaluation means" refers to a device or program for analyzing acquired motion data, extracting the technical elements of the movement, and evaluating the subject's movement state.

[0777] "Generative AI" refers to systems or programs that use artificial intelligence technology to automatically generate new data and information.

[0778] A "notification means" is a device or program used to communicate evaluation results and areas for improvement to users.

[0779] "Emotion recognition means" refers to a program or device that analyzes a user's facial expression data and identifies their emotional state.

[0780] A "feedback mechanism" is a device or program that provides appropriate feedback to the user based on the analysis results and emotional state.

[0781] "Presentation means" refers to a device or interface for presenting information transmitted from a server to a user visually or audibly.

[0782] A "comparison device" is a device or program used to evaluate acquired motion data by comparing it with past data.

[0783] "Selection means" refers to a device or program for generating different exercise plans according to the user's selection.

[0784] This invention is a system that integrates motor evaluation and emotion recognition, simultaneously achieving improvement in the user's motor skills and psychological care. The system includes imaging equipment, analysis equipment, notification equipment, planning equipment, emotion recognition equipment, and adjustment equipment. Specific embodiments are described below.

[0785] Server operation

[0786] The server first receives motion data in real time from high-precision imaging equipment. This motion data is acquired, for example, by a typical high-resolution camera. The server then applies a Python motion analysis algorithm to extract the technical elements of the motion. Subsequently, it uses generative AI to compare it with reference motions stored in a database to derive a technical evaluation and areas for improvement. The server then notifies the user of the evaluation results and areas for improvement.

[0787] Manipulating the Emotion Engine

[0788] The server receives facial expression data from the user's device and analyzes it using an emotion engine. The emotion engine identifies the user's emotional state, for example, by using a common emotion recognition API. The emotional state is determined as a state such as "anxiety" or "concentration." Based on the analysis results, the server generates a training plan that is best suited to the user's state.

[0789] Feedback and training plan

[0790] The server creates an optimized training plan based on the analysis results and emotional state. This process utilizes an AI model that takes into account the user's past data. The feedback content is also customized according to the user's emotional state. The server provides the user with customized feedback to maximize the effectiveness of the training.

[0791] Terminal operation

[0792] The terminal receives information transmitted from the server and presents it to the user in an easy-to-understand manner. The terminal is designed with a visually and audibly designed interface to allow the user to easily understand the feedback. Through the information provided on the terminal, the user can adjust their exercise methods and manage their mental state.

[0793] User utilization

[0794] Based on the feedback and training plan provided, users improve their athletic performance while maintaining their mental well-being. For example, they can improve their form and take care of their mental health according to the feedback. By continuously reviewing their training content, long-term growth can be expected.

[0795] Specific examples and prompt statements

[0796] For example, the server might analyze a tennis player's swing motion, and if the emotion recognition engine determines that the player is concentrating, it might generate a training plan aimed at further improving their technique. An example of a prompt to the generated AI model would be, "Analyze the user's swing motion, compare it to standard motion, and provide an evaluation and suggestions for improvement."

[0797] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0798] Step 1:

[0799] The server receives motion data in real time from high-precision imaging equipment. The input is video data captured by the camera. This video data represents the player's movements and is converted into an analyzable video dataset as output. Specifically, the server receives the video data and prepares it for analysis while maintaining its image quality.

[0800] Step 2:

[0801] The server applies a motion analysis algorithm to extract the technical elements of the athlete. The input is the video dataset obtained in step 1, and the output is analysis data containing the technical elements. The server uses an algorithm implemented in Python to perform motion analysis, quantifying, for example, the movement and speed of the athlete's limbs.

[0802] Step 3:

[0803] The server uses a generative AI model to compare technical elements with reference motions. Inputs include analysis data and reference motion data, and the output generates a technical evaluation of the motion and areas for improvement. Specifically, the server inputs prompt statements into the generative AI model, which then derives the technical evaluation and necessary improvements.

[0804] Step 4:

[0805] The server receives facial expression data from the user's device and analyzes the emotional state using an emotion recognition engine. The input is facial expression data acquired from the user's device, and the output is a specific label that determines the user's emotional state. The server inputs the facial expression data into the emotion engine, processes the results, and determines the emotional state.

[0806] Step 5:

[0807] The server creates an optimized training plan based on the analysis results and emotional state. Inputs include technical evaluation, areas for improvement, and emotional state, while the output is a user-specific training plan. The server integrates this data to generate the most effective training content.

[0808] Step 6:

[0809] The server generates feedback and sends it to the terminal. The input is a well-organized technical evaluation and training plan, and the output is feedback data presented to the user visually and aurally. Specifically, the server compiles the feedback and sends it to the terminal via a reconciliation device.

[0810] Step 7:

[0811] The terminal displays the received feedback and training plan. The input is feedback data sent from the server, and the output is information displayed to the user. The terminal uses a graphical user interface to visually display the feedback content and, with voice assistance as needed, conveys the information clearly.

[0812] Step 8:

[0813] The user utilizes the provided feedback and training plan to carry out the training. The input is the feedback and plan presented on the device, and the output is the user's improved skills and improved psychological state. In terms of specific actions, the user trains according to the presented areas for improvement and continues practicing towards the goal.

[0814] (Application Example 2)

[0815] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0816] To simultaneously improve athletic performance and provide psychological support, it is necessary to provide personalized feedback and training plans to each individual user in real time. However, conventional systems can only perform exercise analysis and emotion recognition independently, making it difficult to effectively integrate the results of each into the presentation of feedback and plans.

[0817] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0818] In this invention, the server includes an evaluation means for analyzing image data acquired from a high-precision image acquisition means and automatically evaluating the movement of a target object; a notification means for generating areas for improvement based on the analysis results and notifying the user of these areas for improvement; and an emotion analysis means for analyzing the user's emotional state using an emotion recognition means and adjusting the feedback based on the emotion data. This makes it possible to simultaneously provide personalized movement improvement suggestions and psychological support for each user.

[0819] A "high-precision image acquisition method" is an image acquisition device with excellent resolution and accuracy for capturing the movement of a target object in detail.

[0820] "Evaluation means" refers to a function that analyzes acquired video data, extracts characteristics related to the motion of the target object, and evaluates its motion performance by comparing it with standard motion.

[0821] A "notification device" is a device that uses visual or auditory media to communicate information about analyzed areas for improvement to the user.

[0822] "Emotion recognition means" refers to a function that analyzes facial expressions and voice data to determine the user's emotional state and estimate their psychological state.

[0823] "Emotion analysis means" refers to a system function that adjusts the content of feedback and training plans based on recognized user emotion data.

[0824] The "plan delivery method" refers to the function of formulating and providing training schedules optimized for individual users based on information obtained from evaluation methods and emotion analysis methods.

[0825] This invention utilizes a system that integrates motion analysis and emotion recognition. The server receives video data from a high-precision image acquisition means and uses an image analysis library (e.g., OpenCV) for motion analysis. The acquired video data is analyzed to compare the movement of the target object with a standard movement and evaluate the movement. Based on the analysis results, the system provides suggestions for improvement to the user via a notification means. For example, it may provide specific advice such as, "Try swinging your arms a little more" when describing running form.

[0826] Furthermore, the server uses emotion recognition capabilities and utilizes speech analysis libraries (e.g., Librosa) and machine learning libraries (e.g., TensorFlow and PyTorch) to analyze the user's emotional state. This emotional data is used to provide feedback and adjust training plans, offering appropriate psychological support to the user. For example, if the server determines that the user's motivation is low, it can play upbeat music as an "encouraging message."

[0827] The device receives notifications and plans from the server and presents them to the user through an intuitively understandable interface (e.g., touchscreen or audio output). Based on the information provided, the user can adjust their training plan to ensure continuous skill improvement and emotional support.

[0828] As a concrete example, when a user goes jogging, the system can suggest a jogging plan tailored to their motivation and physical condition that day via their device. An example of a prompt used in this case is: "If the user looks anxious, please suggest what kind of motivational feedback would be appropriate." In this way, by providing feedback and training plans using a generative AI model, it is possible to provide optimal support to each individual user.

[0829] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0830] Step 1:

[0831] The server captures the user's movements using image acquisition equipment and receives video data in real time. The input is high-precision video data, which is divided into frames and subjected to initial processing using an image analysis library. The output is frame data, which forms the basis for the analysis process. Based on this frame data, the system is ready to extract the user's movement patterns.

[0832] Step 2:

[0833] The server applies an image analysis algorithm to extract motion patterns from video data and compares them with a standard motion database. The input is pre-processed frame data, and the output is an evaluation result regarding the motion performance of the target object. This data processing reveals specific areas for improvement in the user's movements.

[0834] Step 3:

[0835] The server generates improvement suggestions using an AI model based on the user's evaluation results. This process outputs a feedback script, including prompts, based on the input performance evaluation data. The generated feedback is then refined to make it easier for the user to understand.

[0836] Step 4:

[0837] The server uses emotion recognition to receive user voice data from the terminal and perform emotion analysis. The input is voice data, and emotions are identified using a machine learning library. The output is data about the user's emotional state. This data is used to adjust the feedback.

[0838] Step 5:

[0839] The device presents the user with a training plan based on improvement suggestions and sentiment data received from the server. Inputs are notification data and training plan data from the server. Output is an interface display that intuitively shows the user feedback and training plan. The device uses visual and auditory elements to present information to the user and support smooth training.

[0840] Step 6:

[0841] Users perform exercises based on feedback and training plans provided through their devices. The inputs are the feedback and plan information, and the user's actions are the output. By utilizing this feedback, users can improve their skills and maintain their mental well-being.

[0842] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0843] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0844] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0845] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0846] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0847] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0848] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0849] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0850] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0851] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0852] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0853] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0854] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0855] 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.

[0856] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0857] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0858] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0859] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0860] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0861] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0862] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0863] The following is further disclosed regarding the embodiments described above.

[0864] (Claim 1)

[0865] An evaluation device for automatically evaluating the motion of a target object by analyzing video data acquired from a high-precision video acquisition device,

[0866] A notification device that generates areas for improvement based on the analysis results and notifies the user of these areas for improvement,

[0867] A planning device for providing a training plan based on the notified areas for improvement,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, further comprising a comparison device for comparing motion patterns extracted from video data with past data.

[0871] (Claim 3)

[0872] The system according to claim 1, further comprising a selection device for generating different training plans according to user selection.

[0873] "Example 1"

[0874] (Claim 1)

[0875] An evaluation means for analyzing image information acquired from a high-precision image acquisition means and automatically evaluating the movement of a target object,

[0876] A notification means for generating corrections based on the analysis results and notifying the user of those corrections,

[0877] A means for providing an exercise plan based on the notified modifications,

[0878] A preprocessing means that preprocesses video data to perform noise reduction and frame correction,

[0879] A generative model is used to analyze the movement of a target object frame by frame and extract the motion pattern as numerical information.

[0880] A comparison means for calculating deviations in technical parameters by comparing them with a standard operating pattern database,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, further comprising a comparison means for comparing an action pattern extracted from image information with past information.

[0884] (Claim 3)

[0885] The system according to claim 1, further comprising a selection means for generating different exercise plans according to the user's selection.

[0886] "Application Example 1"

[0887] (Claim 1)

[0888] An evaluation means for automatically evaluating the actions of a target operation by analyzing motion data acquired from a high-precision video acquisition means,

[0889] A notification means that generates areas for improvement based on the analysis results and notifies the user via a visual display means,

[0890] A means of providing a plan to support efficient and safe work by providing guidance plans based on the identified areas for improvement,

[0891] A data transmission means for sending video data to a cloud server and performing analysis using a generated AI model,

[0892] A feedback mechanism that generates analysis results using prompt messages and displays practical guidelines to the user,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, further comprising a comparison means for comparing motion patterns obtained by a data acquisition means with past data.

[0896] (Claim 3)

[0897] The system according to claim 1, further comprising a selection means for generating different instructional plans according to the user's selection.

[0898] "Example 2 of combining an emotion engine"

[0899] (Claim 1)

[0900] An evaluation means that analyzes motion data acquired from high-precision imaging equipment to evaluate the motion state of the subject,

[0901] A notification system that automatically generates technical improvement points using a generation AI based on the analysis results and communicates those improvement points to the user,

[0902] A plan provision method that recognizes the emotional state of the user and creates an exercise plan optimized for that state,

[0903] An emotion recognition means that analyzes the user's facial expression data using an emotion engine to identify emotions,

[0904] A feedback means that generates personalized feedback based on analysis results and emotional state,

[0905] A presentation method for showing the received feedback and exercise plan to the user,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, further comprising a comparison means for comparing acquired exercise data with past data.

[0909] (Claim 3)

[0910] The system according to claim 1, further comprising a selection means for generating different exercise plans according to the user's selection.

[0911] "Application example 2 when combining with an emotional engine"

[0912] (Claim 1)

[0913] An evaluation means for analyzing image data acquired from a high-precision image acquisition means and automatically evaluating the motion of a target object,

[0914] A notification system for generating improvement points based on analysis results and notifying users of those improvement points,

[0915] An emotion analysis means for analyzing the user's emotional state using emotion recognition means and adjusting feedback based on emotional data,

[0916] A means for providing a training plan based on notified areas for improvement and sentiment data,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, further comprising a comparison means for comparing motion patterns extracted from image data with past data.

[0920] (Claim 3)

[0921] The system according to claim 1, further comprising a selection means for generating different training plans according to the user's selection. [Explanation of symbols]

[0922] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An evaluation means for automatically evaluating the actions of a target operation by analyzing motion data acquired from a high-precision video acquisition means, A notification means that generates areas for improvement based on the analysis results and notifies the user via a visual display means, A means of providing a plan to support efficient and safe work by providing guidance plans based on the identified areas for improvement, A data transmission means for sending video data to a cloud server and performing analysis using a generated AI model, A feedback mechanism that generates analysis results using prompt messages and displays practical guidelines to the user, A system that includes this.

2. The system according to claim 1, further comprising a comparison means for comparing motion patterns obtained by a data acquisition means with past data.

3. The system according to claim 1, further comprising a selection means for generating different instructional plans according to the user's selection.

Images