System

Abstract

To provide a system.SOLUTION: A system includes: measurement means for measuring a user's physique; recording means for recording specific movements performed by the user; an emotion engine for recognizing emotion of the user; means for transmitting physique data measured by the measurement means and movement data recorded by the recording means to a server; comparison means for inputting a prompt sentence for comparing the user's movements with movements of a specific professional athlete based on the physique data and the movement data and proposing correction points of the user's movements, into a generated AI model to compare the user's physique with a physique of the professional athlete, and comparing the recorded user's movements with the movements of a specific professional athlete whose physique is similar to that of the user based on the comparison result; means for proposing the correction points of the movements to the user based on a result of the comparison and taking into account information from the emotion engine; and means for displaying the proposed correction points on the user's terminal.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Users who want to learn to move like professional athletes face the challenge of finding it difficult to accurately grasp the correct movement corrections required due to differences in their own physique and that of professional athletes. [Means for solving the problem]

[0005] As a means for solving this problem, the system of the present invention includes a measuring means for measuring a user's physique, a recording means for recording specific movements performed by the user, an emotion engine for recognizing the emotions of the user, a means for transmitting physique data measured by the measuring means and movement data recorded by the recording means to a server, a comparison means for comparing the user's movement with the movement of a specific professional athlete based on the physique data and the movement data, and inputting a prompt sentence that suggests modifications to the user's movement into a generative AI model, thereby comparing the user's physique with that of the professional athlete, and based on the comparison result, comparing the recorded user's movement with the movement of the specific professional athlete whose physique is similar to that of the user, a means for suggesting modifications to the movement to the user based on the result of the comparison and taking into account information from the emotion engine, and a means for displaying the proposed modifications on the user's terminal. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (e.g., voice 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 voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out 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 the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, a user first measures his or her physique using a 3D body scan. This measurement is performed, for example, using a device that provides a 3D body scan. Next, the user performs a specific movement, such as batting or pitching in baseball. This movement is recorded using a camera, sensor, or the like. The recorded movement is analyzed by AI. Using deep learning, the AI ​​compares the user's movement with that of a professional athlete with a similar physique. Then, based on the comparison results, suggestions are made to the user on how to modify the movement. These suggestions are presented to the user, for example, through an application on a device such as a smartphone or tablet.

[0029] "Example 2"

[0030] In one embodiment of the present invention, a user first measures his or her physique using a 3D body scan. This measurement is performed, for example, using a device that provides a 3D body scan. Next, the user performs a specific movement, such as batting or pitching in baseball. This movement is recorded using a camera, sensor, or the like. The recorded movement is analyzed by AI. Using deep learning, the AI ​​compares the user's movement with that of a professional athlete with a similar physique. Then, based on the comparison results, suggestions are made to the user on how to modify the movement. These suggestions are presented to the user, for example, through an application on a device such as a smartphone or tablet.

[0031] The process flow of each embodiment will be described below.

[0032] "Example 1"

[0033] Step 1: The user measures their physique using a 3D body scan. This measurement is taken, for example, using a device that provides a 3D body scan.

[0034] Step 2: Next, the user performs a specific action, such as batting or pitching a baseball. This action is recorded using cameras and sensors.

[0035] Step 3: The recorded movements are analyzed by AI, which uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[0036] Step 4: Based on the comparison results, the system then suggests modifications to the user's behavior. These suggestions are presented to the user, for example, via an application on a device such as a smartphone or tablet.

[0037] "Example 2"

[0038] Step 1: The user measures their physique using a 3D body scan. This measurement is taken, for example, using a device that provides a 3D body scan.

[0039] Step 2: Next, the user performs a specific action, such as batting or pitching a baseball. This action is recorded using cameras and sensors.

[0040] Step 3: The recorded movements are analyzed by AI, which uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[0041] Step 4: Based on the comparison results, the system then suggests modifications to the user's behavior. These suggestions are presented to the user, for example, via an application on a device such as a smartphone or tablet.

[0042] Example 1

[0043] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0044] Conventional motion analysis systems have had difficulty in accurately measuring and recording a user's physique and movements and providing appropriate feedback. In addition, there was a lack of means to perform highly accurate analysis when comparing a user's movements with those of professional athletes. This made it difficult for users to effectively improve their own movements.

[0045] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0046] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for transmitting the recorded movement data and physique data to the server, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for displaying the suggested corrections on the user's terminal. This allows the user to accurately measure and record their own physique and movements, and obtain specific corrections by comparing them with the movements of professional athletes.

[0047] "User" refers to an individual who uses the system to measure and record their physique and movements and receive feedback.

[0048] "Body Measurements" refers to a User's physical characteristics and measurements, including data measured by means of a 3D body scan or similar means.

[0049] "Movement" refers to specific physical movements or performances performed by users, which are recorded using cameras and sensors.

[0050] "Server" refers to a computer system that receives data sent by a User, analyzes it using AI means, and provides the results to the User.

[0051] "3D body scanning" refers to technology and equipment that measures a user's physique in three dimensions and is used to obtain detailed data about the user's body.

[0052] "AI Means" refers to means for analysing a user's movements using artificial intelligence technology and comparing them with the movements of a professional athlete.

[0053] "Deep learning" is a field of artificial intelligence that refers to a technology that uses multi-layer neural networks to learn the characteristics of data and perform advanced analysis and predictions.

[0054] "Fix" refers to specific changes or suggestions suggested to improve a user's experience.

[0055] "Terminal" refers to the device that a user uses to access the system, including smartphones and tablets.

[0056] "Comparison Results" refers to the results of a comparison made by AI means between the User's movements and the movements of a professional athlete, and includes data that serves as the basis for feedback to the User.

[0057] This invention is a system that measures and records a user's physique and movements, analyzes them using AI, and suggests specific movement corrections to the user. A specific embodiment of this system will be described below.

[0058] First, the user measures their physique using a device that provides a 3D body scan, such as Kinect or Structure Sensor, which acquires the user's physique data and stores it on the user's device (smartphone or tablet).

[0059] Next, the user performs a specific movement, such as a batting or pitching form in baseball. This movement is recorded using a smartphone camera or a GoPro. The recorded video data is saved on the user's device.

[0060] The user's device transmits the recorded movement data and physique data to the server. An Internet connection is required for transmission. When the user presses the "Data transmission" button in the application, the device uploads the data to the server.

[0061] The server inputs the received movement data and physique data into the AI ​​model. This AI model uses TENSORFLOW (registered trademark) and PyTorch, and uses deep learning to compare the user's movements with those of professional athletes with a similar physique. The server inputs the data into the AI ​​model and starts the comparison process. When the process is complete, the comparison results are generated.

[0062] The server generates corrections for the user's movements based on the results of the comparison with the AI ​​model. These corrections are summarized as specific advice or improvement methods. For example, specific advice such as "You need to rotate your hips faster to increase the swing speed of your batting form" is generated.

[0063] The server sends the generated corrections to the user's device. The user's device displays the received corrections in the application. The user opens the application and checks the proposed corrections. For example, specific advice such as "how to practice to rotate your hips faster" is displayed.

[0064] As a concrete example, consider the case where a user wants to improve their baseball batting form. The user first measures their physique using a 3D body scanning device (e.g. Kinect). Next, they record their batting form using a smartphone camera. This recorded data is input into a deep learning model using TensorFlow and compared with the movements of professional batters. Based on the comparison results, corrections to the user's batting form are presented through a dedicated app.

[0065] An example of a prompt is, "Taking the user's physique data and a video of their batting form as input, compare it with the movements of a professional batter and suggest corrections."

[0066] In this way, users can compare their own movements with those of professionals and get specific corrections.

[0067] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0068] Step 1:

[0069] Users measure their physique using a 3D body scanning device.

[0070] Input: User's body position

[0071] Specific action: The user stands in front of the Kinect and rotates their body according to the instructions.

[0072] Data Processing: The scanning device collects the user's physique data and generates a 3D model.

[0073] Output: The generated physique data is saved on the user's device.

[0074] Step 2:

[0075] The user performs a specific movement (e.g., batting form in baseball) and records that movement.

[0076] Input: User actions

[0077] Specific actions: The user sets the smartphone on a tripod and takes a picture of their batting form.

[0078] Data processing: The camera records the user's actions as video data.

[0079] Output: The recorded video data is stored on the user's device.

[0080] Step 3:

[0081] The user's device transmits the recorded movement data and physical data to a server.

[0082] Input: Movement and body data

[0083] Specific action: The user presses the "Submit Data" button within the application.

[0084] Data processing: The device compresses the data and uploads it to a server via the Internet.

[0085] Output: Data is sent to the server.

[0086] Step 4:

[0087] The server inputs the received movement data and physique data into the AI ​​model.

[0088] Input: Movement and body data

[0089] Specific actions: The server inputs the data into the AI ​​model and begins the comparison process.

[0090] Data calculation: The AI ​​model uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[0091] Output: The comparison results are generated.

[0092] Step 5:

[0093] The server generates corrections to the user's behavior based on the comparison results of the AI ​​model.

[0094] Input: Comparison result

[0095] Specific actions: The server generates specific advice such as "You need to rotate your hips faster to increase the swing speed of your batting form."

[0096] Data processing: Analyze the comparison results and generate corrections in text format.

[0097] Output: The corrections are generated.

[0098] Step 6:

[0099] The server sends the generated modifications to the user's terminal.

[0100] Input: Correction

[0101] Specific operation: The server sends the modifications to the user's device.

[0102] Data processing: Convert the corrections into the appropriate format and send them.

[0103] Output: The corrections are sent to the user's terminal.

[0104] Step 7:

[0105] The user's device will display the received corrections within the application.

[0106] Input: Correction

[0107] What happens: The user opens the application and sees the suggested fixes.

[0108] Data processing: Display the corrections in a user-friendly format.

[0109] Output: User can see the corrections.

[0110] (Application example 1)

[0111] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0112] In conventional factory work, there is a lack of specific feedback to improve the efficiency and safety of workers' movements. As a result, workers continue to make inappropriate movements, which leads to problems of reduced work efficiency and increased physical strain. In addition, there is no system to optimize workers' movements, which makes it difficult to provide appropriate guidance to individual workers.

[0113] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for measuring the physique of the user, a means for recording specific movements performed by the user, an AI means for analyzing the recorded movements and comparing them with movements of workers with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for displaying suggestions for optimizing the movements of factory workers. This makes it possible to provide specific feedback for improving the efficiency and safety of the movements of the workers.

[0114] "User" means an individual who utilizes the System to have their physique and / or movement measured and analyzed.

[0115] "Physique" refers to the physical characteristics and measurements of a user.

[0116] "Movement" refers to a specific physical movement or task performed by a user.

[0117] A "recording means" is a device or method for saving a user's actions as video or data.

[0118] "AI means" means technology that uses artificial intelligence to analyze recorded movements and compare them with other movements.

[0119] "Deep learning" is a type of artificial intelligence, a technology that uses multi-layered neural networks to analyze and learn from data.

[0120] A "means for suggesting modifications" is a method or device for suggesting improvements to a user's operation based on the analysis results.

[0121] A "factory worker" is a worker who performs specific tasks in a factory.

[0122] The "means for displaying suggestions for optimization" refers to a device or method for visually presenting suggestions for improving the efficiency and safety of operations to a user.

[0123] "3D body scanning" is a technology that measures a user's body in three dimensions.

[0124] A system for implementing the present invention includes means for measuring a user's physique, means for recording specific movements performed by the user, AI means for analyzing the recorded movements and comparing them with the movements of workers with a similar physique, means for suggesting to the user corrections to their movements based on the comparison results, and means for displaying suggestions for optimizing the movements of factory workers.

[0125] Hardware and Software Used

[0126] 3D body scanning device: A device for measuring the user's body size in three dimensions.

[0127] Camera: A device used to record user actions. An example is the Logitech C920.

[0128] Smart glasses: A device that visually indicates to the user the correction of their actions. An example is Google® Glass®.

[0129] Tablet: A device used to display operational corrections and optimization suggestions. An example is the iPad.

[0130] Server: A computer system for processing data and running AI models.

[0131] Software: Uses program libraries such as Python (registered trademark), OpenCV (registered trademark), and Keras.

[0132] Data processing and calculation

[0133] 1. Acquisition of physique data: The server acquires the user's physique data using a 3D body scanning device. This data represents the user's physical characteristics and dimensions in three dimensions.

[0134] 2. Recording of actions: The server records the user's actions using a camera. The recorded actions are saved as image data.

[0135] 3. Motion analysis: The server inputs the recorded image data and physique data into the AI ​​model to analyze the motion. The AI ​​model uses deep learning to compare the user's motion with that of workers with a similar physique.

[0136] 4. Suggested modifications: The server will suggest modifications to the user based on the analysis results, and these suggestions will be displayed on the smart glasses or tablet.

[0137] Examples

[0138] When a factory worker lifts a heavy object, the movement is recorded using a 3D body scan and a camera, and then analyzed by AI. As a result of the analysis, corrections such as the angle of the waist and the position of the hands when lifting are suggested, allowing the worker to perform the work efficiently and safely.

[0139] Examples of prompt statements

[0140] "Record factory workers lifting heavy objects and feed that into the AI ​​along with their 3D body scan data to compare with efficient movements and suggest corrections."

[0141] The above is an embodiment of the present invention.

[0142] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0143] Step 1:

[0144] The server acquires the user's physique data using a 3D body scanning device. The input includes the user's physical characteristics and dimensions. The data is processed by converting these characteristics and dimensions into a data format that represents them three-dimensionally. The output is the user's physique data.

[0145] Step 2:

[0146] The server records the user's actions using a camera. The input includes the specific actions performed by the user. The data processing includes storing the actions as video data. The output includes image data of the recorded actions.

[0147] Step 3:

[0148] The server inputs the recorded image data and physique data into the AI ​​model and analyzes the movements. The input data includes image data and physique data. For data calculation, the AI ​​model uses deep learning to compare the user's movements with those of workers with a similar physique. The output is the analysis result of the movements.

[0149] Step 4:

[0150] The server proposes to the user corrections to the behavior based on the analysis results. The input includes the analysis results of the behavior. The data processing generates specific correction suggestions. The output is the proposed corrections.

[0151] Step 5:

[0152] The server displays the suggested corrections on the smart glasses or tablet. An input includes the suggested corrections. A specific operation includes generating and sending data for visually displaying the suggested corrections to the smart glasses or tablet. An output includes the suggested corrections that are visually visible to the user.

[0153] The above is the processing flow of this program.

[0154] Example 2

[0155] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0156] Conventional motion analysis systems have difficulty in accurately measuring and recording a user's physique and motion, and suggesting appropriate corrections. In addition, there is a lack of means to suggest specific corrections to users, which has led to problems with effective improvement of motion.

[0157] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0158] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements performed by the user, an artificial intelligence means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for presenting the corrections to the user. This makes it possible to accurately measure and record the user's physique and movements, suggest appropriate corrections, and present specific corrections to the user.

[0159] "User" refers to an individual who uses the System to measure and record their physique and movements and receive suggestions for movement modifications.

[0160] "Means for measuring body size" refers to devices or technologies that measure the dimensions and shape of a user's body in three dimensions.

[0161] "Means for recording specific actions" refers to devices or technologies that use cameras or sensors to record actions performed by users.

[0162] "Artificial intelligence means" refers to AI technology used to analyze recorded movement data and compare the movements of users with those of professional athletes.

[0163] "Means for suggesting corrections" refers to a technology that extracts and suggests improvements to the user's actions based on the analysis results by the artificial intelligence means.

[0164] "Means for suggesting corrections" means a device or application that visually or audibly communicates the suggested corrections to the user.

[0165] "3D body scanning" refers to a technology that measures a user's body in three dimensions.

[0166] "Deep learning" refers to a machine learning technique using multiple layers of neural networks used in artificial intelligence tools.

[0167] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0168] The present invention relates to a system that measures a user's physique, records and analyzes specific movements, and suggests corrections to those movements. A specific embodiment of this system will be described below.

[0169] User body measurements

[0170] The user measures his or her physique using a 3D body scanning device. Examples of such devices include a "3D scanner" or a "motion capture system." The user follows the device's instructions to scan his or her physique while rotating 360 degrees. The device processes the scan data in real time and generates the user's physique data. The generated data is sent to a server via wireless communication.

[0171] Recording actions

[0172] Next, the user performs a specific movement, such as batting or pitching a baseball. The user records the movement using a camera or sensor. The hardware used may be a "high-resolution camera" or a "motion capture system." The device generates the recorded video data or motion capture data and sends it to a server.

[0173] Analysis of behavior

[0174] The server inputs the received physique data and movement data into an AI model. This AI model uses deep learning to compare the user's movements with those of professional athletes. The software used is a "deep learning framework." The server extracts corrections for the user's movements from the output of the AI ​​model.

[0175] Suggested behavior modifications

[0176] The server sends the extracted correction points to the device. The device displays the received correction points in a dedicated application. The user can check the correction points through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[0177] Examples

[0178] Example 1: Correcting baseball batting form

[0179] The user measures their physique using a 3D body scanning device and sends the data to the server. After that, a high-resolution camera is used to capture their batting form, and the video data is uploaded to the server. The server analyzes the data using a deep learning framework and extracts corrections that are presented to the user through a dedicated application. The user works to improve their batting form while looking at the application.

[0180] Example 2: Correcting pitching form

[0181] The user uses a 3D scanner to measure their physique and sends the data to the server. The motion capture system then records their pitching form and uploads the data to the server. The server then analyzes the data using a deep learning framework and extracts corrections that are presented to the user through a dedicated application. The user works on improving their pitching form while looking at the application.

[0182] Examples of prompt statements

[0183] Prompt 1: Baseball batting form

[0184] "Please generate an AI model that takes a user's 3D body scan data and video data of their batting form as input, compares it with data from professional baseball players, and suggests corrections."

[0185] Prompt 2: Pitching form

[0186] "Please generate an AI model that takes the user's 3D body scan data and motion capture data of their pitching form as input, compares it with data from professional baseball players, and suggests corrections."

[0187] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0188] Program processing flow

[0189] Step 1: Measuring the user's body size

[0190] The user activates the 3D body scanning device. Following the device's instructions, the user rotates 360 degrees to scan their physique. The device processes the scan data in real time and generates physique data for the user. The generated data is then transmitted to the server via wireless communication.

[0191] Input: User's body scan data

[0192] Data processing: Real-time processing of scan data

[0193] Output: User's physical data

[0194] Step 2: Recording the action

[0195] Using a high-resolution camera and a motion capture system, the user performs a specific movement, such as batting or pitching a baseball. The device records the movement and generates video data or motion capture data. The generated data is sent to the server.

[0196] Input: User actions

[0197] Data processing: Motion recording and data generation

[0198] Output: Video data or motion capture data

[0199] Step 3: Analyze the behavior

[0200] The server inputs the received physique data and movement data into an artificial intelligence model. The artificial intelligence model uses deep learning to compare the user's movements with those of professional athletes. The server extracts corrections for the user's movements from the output of the artificial intelligence model.

[0201] Input: Body size data, movement data

[0202] Data processing: Motion comparison using deep learning

[0203] Output: Behavior fixes

[0204] Step 4: Propose behavior modifications

[0205] The server sends the extracted correction points to the device. The device displays the received correction points in a dedicated application. The user can check the correction points through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[0206] Input: Behavior fixes

[0207] Data processing: Preparation for displaying corrections

[0208] Output: A suggestion for the user to make corrections

[0209] Adding specific actions

[0210] Step 1: Measuring the user's body size

[0211] The user activates the 3D body scanning device and follows the device's instructions to scan their physique. The scan data is processed in real time to generate the user's physique data. The generated data is then transmitted to the server via wireless communication.

[0212] Step 2: Recording the action

[0213] The user sets up a high-resolution camera and records the batting form of a baseball player. The camera records high-resolution video and saves it on the device. The device compresses the saved video data and uploads it to the server.

[0214] Step 3: Analyze the behavior

[0215] The server inputs the received physique data and video data into a deep learning framework. The AI ​​model compares the user's batting form with that of professional baseball players. Features such as joint angles and movement speed are used for the comparison. The server extracts corrections for the user's movements from the output of the AI ​​model.

[0216] Step 4: Propose behavior modifications

[0217] The server sends the extracted corrections in JSON format to the device. The device displays the received corrections in a dedicated application. The user can check the corrections through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[0218] (Application example 2)

[0219] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0220] Conventional optimization of factory robots' movements relied on manual adjustments and experience, making it difficult to achieve efficient and highly accurate optimization. In addition, because individual optimization based on the user's physique or movements was not performed, general-purpose optimization methods were sometimes ineffective. This created a risk of a decline in factory productivity and quality.

[0221] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0222] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user points for correcting the movements based on the comparison results, a means for recording and analyzing the movements of a robot used in the factory, and a means for suggesting points for correcting the movements of the robot. This enables individual optimization based on the user's physique and movements, and makes it possible to efficiently and accurately optimize the movements of factory robots.

[0223] "User" means any individual or legal entity that uses the System to measure and analyze their physique and movements.

[0224] "Physique" refers to the shape and dimensions of a User's body, as measured by means such as a 3D body scan.

[0225] A "specific action" is a specific movement or task performed by a user that is recorded using a camera or sensor.

[0226] "Recording means" refers to devices or methods that use cameras, sensors, etc. to save user actions as data.

[0227] "AI means" refers to technology that uses artificial intelligence to analyze recorded movement data and compare the user's movements with those of professional athletes.

[0228] "Deep learning" is a type of artificial intelligence, a technology that uses multi-layered neural networks to analyze and learn from data.

[0229] A "professional athlete" is an athlete who is professionally active in a particular sport, and is the subject against which the user's movements are compared.

[0230] "Behavior Modifications" are specific improvements suggested to optimize a user's performance.

[0231] A "factory robot" is an automated mechanical device used on a factory production line or in a workshop.

[0232] "Optimization" means adjusting something to the most efficient and effective state for a particular purpose.

[0233] To implement this invention, the following hardware and software are used. The hardware requires a 3D scanner, a camera, a sensor, a server, and a user terminal (a smartphone or a tablet). The software requires Python, OpenCV, Keras, etc.

[0234] First, the user measures his or her own physique using a 3D scanner. The 3D scanner captures the shape and dimensions of the user's body with high precision and stores them as digital data. This data is then sent to a server.

[0235] Next, the user performs a specific action, for example to mimic the action of a robot used in a factory, and the action is recorded using cameras and sensors, and the recorded action data is also sent to the server.

[0236] The server inputs the received 3D scan data and movement data into the AI ​​system. The AI ​​system analyzes the data using deep learning and compares the user's movements with those of professional athletes with a similar physique. Based on the comparison results, the AI ​​system suggests corrections to the user's movements.

[0237] In addition, to optimize the operation of the robots used in the factory, the robots' operation data is also recorded and analyzed by AI means. Based on the analysis results, corrections are proposed to optimize the robot's operation. These suggestions are displayed on the user's terminal.

[0238] As a concrete example, consider optimizing the operation of a welding robot used in a factory. A 3D scanner captures the shape data of the robot, and cameras and sensors record its operation data. This data is input into an AI tool, and the tool suggests corrections to the welding angle and speed based on the analysis results.

[0239] An example of a prompt sentence to be input into the generative AI model is, "Please input the welding robot's motion data along with the 3D scan data and suggest optimal motion corrections."

[0240] As described above, the present invention enables individual optimization based on the physique and movements of a user, and can optimize the movements of factory robots efficiently and with high accuracy.

[0241] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0242] Step 1:

[0243] Users measure their body size using a 3D scanner.

[0244] Input: User's body

[0245] Data processing: A 3D scanner captures the shape and dimensions of the user's body with high precision and stores them as digital data.

[0246] Output: 3D scan data

[0247] Step 2:

[0248] The user performs a specific action and the action is recorded using cameras and sensors.

[0249] Input: User actions

[0250] Data processing: Cameras and sensors record user actions as video and sensor data.

[0251] Output: Operation data

[0252] Step 3:

[0253] The server receives the 3D scan data and the motion data.

[0254] Input: 3D scan data, motion data

[0255] Data processing: The server receives these data and prepares them for input into the AI ​​means.

[0256] Output: Prepared data

[0257] Step 4:

[0258] The server analyzes the 3D scan data and the motion data using AI means.

[0259] Input: Prepared data

[0260] Data processing: Using a deep learning model, we compare the user's movements with those of professional athletes with a similar physique.

[0261] Output: Analysis results

[0262] Step 5:

[0263] The server then suggests modifications to the user's behavior based on the analysis results.

[0264] Input: Analysis results

[0265] Data Transformation: Use the analysis to generate specific modifications to optimize user behavior.

[0266] Output: suggested fixes

[0267] Step 6:

[0268] Suggested fixes will be displayed on the user's device.

[0269] Input: Suggested fix

[0270] Data processing: Converting the proposal content into a format for display on the user's device.

[0271] Output: The corrections displayed on the user's terminal.

[0272] Step 7:

[0273] The operations of robots used in factories are recorded and transmitted to a server.

[0274] Input: Robot movement

[0275] Data processing: Cameras and sensors record the robot's movements as video and sensor data, and send them to a server.

[0276] Output: Robot motion data

[0277] Step 8:

[0278] The server analyzes the robot's operational data using AI means and suggests modifications for optimization.

[0279] Input: Robot motion data

[0280] Data processing: Using deep learning models, the robot's behavior is analyzed and corrections are generated for optimization.

[0281] Output: Suggested modifications to the robot's behavior

[0282] Step 9:

[0283] Suggestions for correcting the robot's behavior are displayed on the user's device.

[0284] Input: Suggested modifications to the robot's behavior

[0285] Data processing: Converting the proposal content into a format for display on the user's device.

[0286] Output: Robot behavior corrections displayed on the user's device

[0287] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0288] "Example 1"

[0289] In one embodiment of the present invention, a system is provided that includes a means for measuring a user's physique, a means for recording a specific movement performed by the user, an AI means for analyzing the recorded movement and comparing it with the movement of a professional athlete with a similar physique, a means for suggesting to the user a correction to the movement based on the comparison result, and an emotion engine for recognizing the user's emotions. The emotion engine recognizes emotions from the user's facial expressions and tone of voice, and provides the information to the AI ​​means. The AI ​​means proposes corrections to the movement by taking into account not only the comparison between the user's movement and the movement of the professional athlete, but also the user's emotions. For example, if the user feels frustrated, the AI ​​means proposes corrections in a form that is easy for the user to accept, taking into account the information. In this way, it is possible to propose improvement of the movement by taking into account the user's emotions.

[0290] "Example 2"

[0291] In one embodiment of the present invention, a system is provided that includes a means for measuring a user's physique, a means for recording a specific movement performed by the user, an AI means for analyzing the recorded movement and comparing it with the movement of a professional athlete with a similar physique, a means for suggesting to the user a correction to the movement based on the comparison result, and an emotion engine for recognizing the user's emotions. The emotion engine recognizes emotions from the user's facial expressions and tone of voice, and provides the information to the AI ​​means. The AI ​​means proposes corrections to the movement by taking into account not only the comparison between the user's movement and the movement of the professional athlete, but also the user's emotions. For example, if the user feels frustrated, the AI ​​means proposes corrections in a form that is easy for the user to accept, taking into account the information. In this way, it is possible to propose improvement of the movement by taking into account the user's emotions.

[0292] The process flow of each embodiment will be described below.

[0293] "Example 1"

[0294] Step 1: Measure the user's physique with a 3D body scan.

[0295] Step 2: A user's specific action (e.g., batting or pitching a baseball) is recorded using a video camera or motion sensors.

[0296] Step 3: The recorded movements are analyzed using AI tools and compared to those of professional athletes with a similar physique.

[0297] Step 4: Understand the user's emotions using an emotion engine that recognizes emotions from the user's facial expressions and tone of voice.

[0298] Step 5: The AI ​​tool takes into account the comparison of the user's movements with those of professional athletes and the user's emotions and suggests corrections to the movements.

[0299] Step 6: The proposed behavioral modifications are presented to the user via an application on a device such as a smartphone or tablet.

[0300] "Example 2"

[0301] Step 1: Measure the user's physique with a 3D body scan.

[0302] Step 2: A user's specific action (e.g., batting or pitching a baseball) is recorded using a video camera or motion sensors.

[0303] Step 3: The recorded movements are analyzed using AI tools and compared to those of professional athletes with a similar physique.

[0304] Step 4: Understand the user's emotions using an emotion engine that recognizes emotions from the user's facial expressions and tone of voice.

[0305] Step 5: The AI ​​tool takes into account the comparison of the user's movements with those of professional athletes and the user's emotions and suggests corrections to the movements.

[0306] Step 6: The proposed behavioral modifications are presented to the user via an application on a device such as a smartphone or tablet.

[0307] Example 1

[0308] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0309] Conventional motion improvement systems make suggestions based on the user's physique and motion data, but since the suggestions do not take into account the user's feelings, users may find it difficult to accept the suggestions. In addition, since the points to correct in motion are not specific, it is difficult for users to understand how to improve.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0311] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, an artificial intelligence means for analyzing the recorded movements and comparing them with movements of professional athletes with a similar physique, a means for suggesting to the user points for correcting the movements based on the comparison results, a means for recognizing the user's emotions, and a means for suggesting points for correcting the movements taking into account the emotion data. This makes it possible to suggest movement improvements taking into account the user's physique and emotions.

[0312] A "means for measuring a user's physique" is a device or method for measuring a user's physical characteristics and acquiring them as digital data.

[0313] "Means for recording specific actions performed by a user" refers to a device or method that uses video or a sensor to record specific actions performed by a user as digital data.

[0314] "Artificial intelligence means" means software or systems that analyse the recorded data and use specific algorithms to compare the user's movements with other data (e.g. the movements of a professional sportsperson).

[0315] The "means for suggesting points for modification of motion" refers to a device or method that suggests points for improvement or methods for modification of motion to a user based on the analysis results.

[0316] A "means for recognizing a user's emotions" refers to a device or method that analyzes the user's emotions from their facial expressions, tone of voice, etc., and acquires them as digital data.

[0317] The "means for proposing corrections to movements taking emotion data into consideration" refers to a device or method that proposes corrections to movements in a more acceptable form based on the user's emotion data.

[0318] "3D body scanning" is a technology that scans the user's body in three dimensions and obtains detailed physique data.

[0319] "Deep learning" is an artificial intelligence technique that uses multi-layered neural networks to analyze data and learn patterns and features.

[0320] This invention is a system that analyzes the user's physique and movements, compares them with the movements of professional athletes, and suggests corrections to the user's movements. Furthermore, by recognizing the user's emotions and making suggestions taking into account the user's emotion data, it is possible to present corrections to the user's movements in a form that is easy for the user to accept.

[0321] Hardware and Software Used

[0322] 1. User's body measurements

[0323] A user measures their physique using equipment that provides a three-dimensional body scan, which may include, for example, a 3D scanner or a dedicated body scanning application, to obtain detailed physique data, such as the user's height, weight, and body fat percentage.

[0324] 2. Recording the action

[0325] Users use a smartphone camera or a dedicated motion capture device to record a specific movement (e.g., batting or pitching a baseball), and the recorded data includes detailed movement information such as swing speed and angle.

[0326] 3. Transmission of operation data

[0327] The device transmits the recorded movement and physique data to a server in real time over the Internet, where the data is encrypted and uses a secure communication protocol.

[0328] 4. Analysis of movements

[0329] The server inputs the received data into an AI model, which uses deep learning algorithms to compare the user's movements with those of professional athletes. The software used is a deep learning framework such as TensorFlow or PyTorch. For example, it calculates how much the user's swing speed differs from the average speed of a professional player.

[0330] 5. Emotion Recognition

[0331] The device uses an emotion engine that analyzes the user's facial expressions and tone of voice in real time. This emotion engine determines whether the user is frustrated or satisfied and sends this information to the server. The software used is an emotion recognition API (e.g., Microsoft® Azure®'s Emotion API).

[0332] 6. Suggestions for behavior modifications

[0333] The server then suggests to the user how to improve their swing based on the comparison of their movements and their emotion data. For example, if the user feels frustrated, the server might suggest, "Just changing the way you grip the bat a little might make your swing smoother." The server notifies the user of the suggestion through an application on their device, such as a smartphone or tablet.

[0334] Examples

[0335] Example 1: Improving baseball batting form

[0336] The user uses a 3D scanner to measure their physique and records their batting form with their smartphone camera. The device sends the recorded data to a server, which inputs the data into an AI model and compares it with the form of professional baseball players. If the emotion engine detects the user's frustration, the server will make suggestions such as, "Maybe your swing will be smoother if you just change the way you grip the bat a little." The suggestion is notified to the user through a smartphone application.

[0337] Example prompts for generative AI models

[0338] "Please input the user's 3D body scan data and a video of their batting form, compare it with the form of a professional baseball player, and suggest improvements while taking into account the user's emotions."

[0339] In this way, it becomes possible to suggest motion improvements that take into account the user's physique and emotions.

[0340] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0341] Step 1:

[0342] Users measure their physique using a device that provides a 3D body scan. As input, a 3D scanner is used to scan the user's body. As output, detailed physique data is generated, including the user's height, weight, and body fat percentage. This data is then stored on the device.

[0343] Step 2:

[0344] Users record a specific movement (e.g. batting or pitching in baseball) using a smartphone camera or a dedicated motion capture device. As input, the user's movements are captured by the camera or sensors. As output, detailed movement data such as swing speed and angle is generated. This data is stored on the device.

[0345] Step 3:

[0346] The terminal transmits the recorded movement data and physique data to the server. As input, the movement data and physique data stored on the terminal are used. As output, these data are transmitted to the server via the Internet. The data is encrypted and uses a secure communication protocol.

[0347] Step 4:

[0348] The server inputs the received data into the AI ​​model. As input, the motion and physique data sent to the server are used. As output, the AI ​​model generates the results of comparing the user's motion with those of professional athletes. This AI model uses deep learning algorithms and utilizes deep learning frameworks such as TensorFlow and PyTorch.

[0349] Step 5:

[0350] The device uses an emotion engine that analyzes the user's facial expressions and tone of voice in real time. As input, the user's facial and voice data is captured through a camera and microphone. As output, emotion data is generated, such as whether the user is frustrated or satisfied. This data is then sent to a server.

[0351] Step 6:

[0352] The server proposes corrections to the user's movements based on the comparison results of the movements and the emotion data. The comparison results of the AI ​​model and the emotion data are used as inputs. As output, corrections to the user's movements are generated. For example, if the user feels frustrated, the server will suggest, "Maybe your swing will become smoother if you just change the way you grip the bat a little." The suggestion is notified to the user through an application on a device such as a smartphone or tablet.

[0353] (Application example 1)

[0354] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0355] Conventional motion analysis systems could analyze a user's physique and movements, but had the problem of not being able to suggest corrections to movements that took the user's emotions into account. Also, when optimizing the movements of robots working in factories, there was a lack of real-time monitoring of movement efficiency and error rates and suggestions for improvement. This resulted in issues such as reduced movement efficiency for users and robots, preventing optimal performance.

[0356] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0357] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user movement corrections based on the comparison results, an emotion engine for recognizing the user's emotions, a means for suggesting movement corrections taking into account information from the emotion engine, a means for optimizing the robot's movements, a means for monitoring the robot's movement efficiency and error rate, and a means for making improvement suggestions in real time. This makes it possible to suggest movement corrections taking into account the user's emotions, and further to monitor the movement efficiency and error rate of a robot working in a factory in real time, thereby enabling optimal movement performance to be achieved.

[0358] "Means for measuring the user's body size" refers to devices or technologies for accurately measuring the dimensions and shape of the user's body.

[0359] "Means for recording specific actions performed by a user" refers to devices or technologies that use cameras, sensors, etc. to record specific actions performed by a user.

[0360] "AI means for analyzing recorded movements and comparing them with the movements of professional athletes with a similar physique" refers to artificial intelligence technology for analyzing the recorded movement data of a user and comparing it with the movement data of a professional athlete with a similar physique.

[0361] "Means of suggesting to the user points to modify their movements based on the results of the comparison" refers to devices or technologies that suggest points to improve or modify movements to the user based on the results of the movement comparison performed by AI.

[0362] The "emotion engine that recognizes user emotions" is a technology that identifies emotions from the user's facial expressions, tone of voice, etc.

[0363] The "means for proposing modifications to actions while taking into consideration information from an emotion engine" refers to a device or technology that suggests modifications to actions based on the user's emotion information recognized by an emotion engine.

[0364] "Means for optimizing robot operation" refers to devices and technologies that optimize the operation of robots performing work in a factory to make them efficient and effective.

[0365] The "means for monitoring the robot's operational efficiency and error rate" refers to a device or technology that monitors the robot's operational efficiency and error occurrence rate in real time.

[0366] "Means of making improvement suggestions in real time" refers to devices or technologies that analyze robot operation data in real time and immediately suggest improvements.

[0367] A system for implementing this invention includes means for measuring a user's physique, means for recording specific movements performed by the user, AI means for analyzing the recorded movements and comparing them with the movements of a professional athlete with a similar physique, means for suggesting to the user modifications to their movements based on the comparison results, an emotion engine for recognizing the user's emotions, means for suggesting modifications to the movements taking into account information from the emotion engine, means for optimizing the robot's movements, means for monitoring the robot's movement efficiency and error rate, and means for making improvement suggestions in real time.

[0368] Hardware and Software Configuration

[0369] Hardware:

[0370] 3D body scanning device

[0371] Camera (e.g. Logitech C920)

[0372] Computer (e.g. Intel Core i7, 16GB RAM)

[0373] software:

[0374] OpenCV: Motion recording and image processing

[0375] Keras: Loading and predicting deep learning models

[0376] EmotionRecognizer: Emotion recognition library

[0377] Processing flow

[0378] The server first acquires the user's physique data using a 3D body scanning device. Then, it uses a camera to record the specific movements the user makes. The recorded movement data is preprocessed using OpenCV and analyzed with a deep learning model using Keras. The analysis results are compared with the movement data of professional athletes with a similar physique.

[0379] In addition, we use EmotionRecognizer to recognize the user's emotions and propose behavior modifications taking into account the information from the emotion engine. The proposed modifications are presented to the user.

[0380] For robots working in factories, measures are used to optimize the robot's operation. The robot's operation efficiency and error rate are monitored in real time, and improvement suggestions are made. This makes it possible to optimize the robot's operation performance.

[0381] Examples

[0382] For example, if a robot assembling parts in a factory is moving slowly, the AI ​​will analyze its movements and suggest correcting the angle and speed of its movements. Furthermore, if the robot is making frequent errors, it will determine through emotion recognition that it is feeling frustrated and suggest that it should move more slowly.

[0383] Examples of prompt statements

[0384] "To optimize the movements of a robot assembling parts in a factory, design a system that uses 3D body scanning and cameras to record the movements, analyzes them with AI, and suggests optimal movement patterns. In addition, add a function that monitors the robot's movement efficiency and error rate, and suggests improvements in real time."

[0385] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0386] Step 1:

[0387] The server acquires the user's physique data using a 3D body scanning device. As input, it scans the user's body dimensions and shape, and generates 3D physique data as output. This data is used to accurately determine the user's physique.

[0388] Step 2:

[0389] The server uses a camera to record certain actions performed by the user, capturing the actions performed by the user in real time as input, and generating video data of the actions as output, which is used for subsequent action analysis.

[0390] Step 3:

[0391] The server pre-processes the recorded motion data using OpenCV. It receives motion video data as input and produces pre-processed image data as output. This pre-processing includes image resizing and noise removal.

[0392] Step 4:

[0393] The server analyzes the preprocessed image data with a deep learning model using Keras. It receives the preprocessed image data as input and extracts motion features as output. These features are used to analyze the user's motion in detail.

[0394] Step 5:

[0395] The server compares the extracted features with the motion data of professional athletes with a similar build. It receives the user's motion features and the motion data of professional athletes as input, and generates a comparison result as output. This comparison result is used to identify corrections to the user's motion.

[0396] Step 6:

[0397] The server recognizes the user's emotions using EmotionRecognizer. As input, it captures the user's facial expressions and tone of voice during the action, and generates emotion data as output. This emotion data is used to understand the user's emotional state.

[0398] Step 7:

[0399] The server proposes behavior modifications taking into account information from the emotion engine. It receives as input the comparison results and emotion data, and generates as output behavior modifications for the user. The modifications are proposed taking into account the user's emotional state.

[0400] Step 8:

[0401] The server executes a means for optimizing the motion of a robot performing work in a factory, receiving motion data of the robot as input and generating an optimized motion pattern as output. This optimization is performed to improve the efficiency of the robot's motion.

[0402] Step 9:

[0403] The server monitors the robot's operation efficiency and error rate in real time. As input, it receives the robot's operation data in real time, and generates the monitoring results of the operation efficiency and error rate as output. The monitoring results are used to understand the operation status of the robot.

[0404] Step 10:

[0405] The server provides real-time improvement suggestions, taking the monitoring results as input and generating improvement suggestions as output, which are made to optimize the robot's motion performance.

[0406] Example 2

[0407] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0408] Conventional motion improvement systems have difficulty accurately measuring the user's physique and motion and providing appropriate feedback. In addition, motion improvement suggestions were not made taking the user's emotions into account, so there was a lack of feedback in a form that made it easy for the user to accept the suggestions. This limited the effectiveness of the user's motion improvement.

[0409] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0410] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for transmitting the recorded movements, an artificial intelligence means for analyzing the recorded movements and comparing them with movements of professional athletes with a similar physique, a means for suggesting to the user how to modify the movements based on the comparison results, a means for recognizing the user's emotions, and a means for suggesting how to modify the movements while taking the recognized emotions into consideration. This makes it possible to accurately measure the user's physique and movements and provide appropriate feedback. Furthermore, since suggestions for movement improvement are made taking the user's emotions into consideration, feedback is provided in a form that makes it easy for the user to accept the suggestions, improving the effectiveness of movement improvement.

[0411] "Means for measuring the user's body size" refers to devices or technologies that measure the dimensions and shape of the user's body in three dimensions.

[0412] "Means for recording specific actions performed by a user" refers to devices or technologies that use video or sensors to record specific actions performed by a user.

[0413] The "means for transmitting the recorded motion" refers to a communication means for transmitting the recorded motion data to a server or other device.

[0414] "Artificial intelligence means" refers to artificial intelligence technology used to analyze recorded movement data and compare the movements of a user with the movements of a professional athlete.

[0415] "Means for suggesting modifications to movements" refers to a device or technology that suggests improvements to movements to a user based on the results of analysis by the artificial intelligence means.

[0416] "Means of recognizing the user's emotions" refers to devices or technologies for recognizing emotions from the user's facial expressions, tone of voice, etc.

[0417] "Means for suggesting modifications to behavior taking into account recognized emotions" refers to devices or technologies that suggest modifications to behavior in a manner that is easy for the user to accept, based on the user's emotional information.

[0418] The present invention is a system that measures a user's physique, records specific movements, analyzes the movements, and suggests corrections. The system can recognize the user's emotions and suggest corrections to movements taking them into account.

[0419] First, the user measures their physique using a 3D body scanning device. Specifically, devices such as the Structure Sensor and Kinect are used. This allows the user's physique data to be acquired and stored on the device.

[0420] Next, the user performs a specific motion (e.g., batting or pitching a baseball). This motion is recorded using a camera or sensors (e.g., a GoPro camera or a Vicon motion capture system). The recorded motion data is stored on the device.

[0421] The device transmits the recorded motion and physique data to a server. The data is transmitted using a secure protocol (e.g., HTTPS).

[0422] The server inputs the received data into an AI model, built using deep learning frameworks (e.g. TensorFlow or PyTorch), that compares the user's movements with those of professional athletes of a similar build. The server generates the comparison results and identifies corrections to the movements.

[0423] The server sends the identified corrections to the terminal, which then presents the corrections to the user through an application on the device, such as a smartphone or tablet. For example, specific advice such as "It would be better if you increased the angle of your bat swing a little more" is displayed.

[0424] In addition, the device inputs the user's facial expressions and tone of voice into the emotion engine, which uses Affectiva and Microsoft Azure Emotion API to recognize the user's emotions in real time. The recognition results are stored on the device.

[0425] The device sends the recognized emotion information to the server. The server reevaluates the AI ​​model taking the emotion information into account and suggests modifications that are easy for the user to accept. For example, if the user feels frustrated, the server generates a suggestion such as "First, relax, then be aware of the release point" and sends it to the device. The device displays this suggestion to the user.

[0426] Examples

[0427] Example 1: Improving baseball batting form

[0428] The user uses the Structure Sensor to measure their physique and a GoPro camera to record their batting form. The device sends this data to the server. The server uses TensorFlow to compare the batting form with that of professional baseball players and suggests through a smartphone app that the user "increase the bat swing angle a little more." If the user is feeling frustrated, the emotion engine recognizes this and the server suggests, "First, relax, and then try to be conscious of your swing angle."

[0429] Example 2: Improving pitching form

[0430] The user uses a Kinect to measure their physique and a Vicon motion capture system to record their pitching form. The device sends this data to the server. The server uses PyTorch to compare the form with that of professional pitchers and suggests through a tablet app that the user "should move the release point a little further forward." If the user is feeling frustrated, the emotion engine recognizes this and the server suggests, "First, relax, and then try to be conscious of the release point."

[0431] Examples of prompt statements

[0432] "The user uses a 3D body scanning device to measure their physique and records their batting form with a camera. The AI ​​uses TensorFlow to compare their form with that of professional baseball players and suggests corrections via a smartphone app. If the user is frustrated, the emotion engine recognizes this and the AI ​​suggests corrections in a way that is easy for the user to accept."

[0433] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0434] Step 1:

[0435] Users measure their own physique using a 3D body scanning device. Specifically, users acquire physique data using the "Structure Sensor" or "Kinect." The input is the dimensions and shape of the user's body, and the output is physique data as a 3D model. This data is stored on the device.

[0436] Step 2:

[0437] The user performs a specific movement (e.g. batting or pitching a baseball). The user records the movement using a GoPro camera or a Vicon motion capture system. The input is the user's movement, and the output is high-resolution video data. This data is stored on the device.

[0438] Step 3:

[0439] The terminal transmits the recorded motion data and physique data to the server. The input is the motion data and physique data, and the output is the data transmission to the server. The data is transmitted using a secure protocol (e.g., HTTPS).

[0440] Step 4:

[0441] The server inputs the received data into the AI ​​model. The AI ​​model is built using TensorFlow and PyTorch, and compares the user's movements with those of professional athletes with a similar physique. The input is movement data and physique data, and the output is the comparison results, including corrections to the movements.

[0442] Step 5:

[0443] The server sends the identified corrections to the terminal. The input is the comparison result, and the output is the transmission of the corrections to the terminal. The terminal presents the corrections to the user through an application on a device such as a smartphone or tablet. For example, specific advice such as "It would be better if you increased the bat swing angle a little more" is displayed.

[0444] Step 6:

[0445] The device inputs the user's facial expressions and tone of voice into the emotion engine. The emotion engine uses "Affectiva" and "Microsoft Azure Emotion API" to recognize the user's emotions in real time. The input is the user's facial expressions and tone of voice, and the output is the recognized emotion information. This information is stored on the device.

[0446] Step 7:

[0447] The device sends the recognized emotional information to the server. The input is emotional information, and the output is the transmission of emotional information to the server. The server reevaluates the AI ​​model taking into account the emotional information and suggests corrections in a way that is easy for the user to accept. For example, if the user feels frustrated, the server generates a suggestion such as "First, relax, and then be aware of the release point," and sends it to the device. The device displays this suggestion to the user.

[0448] (Application example 2)

[0449] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0450] Conventional motion analysis systems record the physique and movements of users and compare them with the movements of professional athletes to suggest corrections, but they were not designed to optimize the movements of robots working in factories. They also lacked the ability to detect abnormalities in the robot and suggest corrections to its movements based on those abnormalities. This made it difficult to efficiently manage the movements of robots in factories.

[0451] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0452] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user how to modify the movements based on the comparison results, a means for recording the robot's movements and proposing optimal movement patterns, and a means for detecting abnormalities in the robot and proposing how to modify the movements based on that information. This not only improves the user's movements, but also enables efficient management and optimization of the movements of robots in factories.

[0453] "User" refers to an individual who uses the System to measure and analyze their physique and movement.

[0454] "Physique" refers to the physical characteristics and measurements of a User.

[0455] "Specific movement" refers to a specific action or movement performed by a user (e.g., batting or pitching form in baseball).

[0456] "Means of recording" refers to devices or methods that use cameras, sensors, etc. to save the actions of a user or robot as digital data.

[0457] "AI means" refers to a system that uses artificial intelligence to analyze data and output results according to a specific purpose.

[0458] "Deep learning" refers to a machine learning technique that uses multi-layered neural networks to learn from data and extract complex patterns and features.

[0459] A "professional athlete" refers to an athlete who has high skills in a particular sport and engages in the sport professionally.

[0460] "Behavior Modifications" refers to specific changes or adjustments proposed to improve a user's or robot's behavior.

[0461] A "robot" refers to an automated mechanical device that performs tasks in a factory.

[0462] "Abnormality" refers to conditions such as vibrations or temperature increases that deviate from the robot's normal operation.

[0463] "Means for sensing" refers to methods or devices that use sensors or monitoring devices to detect abnormalities.

[0464] An "optimal motion pattern" refers to a series of procedures or methods of robot motion proposed to perform a task efficiently and effectively.

[0465] The embodiment of the present invention will be described. First, a 3D body scanning device is used to measure the physique of a user. Specifically, a 3D scanner such as Intel RealSense is used to obtain physique data of the user. This data is used to accurately record the physical characteristics and dimensions of the user.

[0466] Next, cameras and sensors are used to record specific actions taken by the user. For example, Intel RealSense cameras are used to record user actions with high accuracy. This recorded data is then analyzed by AI tools, which will be described later.

[0467] The recorded movement data is analyzed by AI tools using deep learning such as TensorFlow and Keras. The AI ​​tools compare the user's movements with those of professional athletes with a similar physique and suggest corrections to the movements. These suggestions are presented to the user through an application on a smartphone or tablet.

[0468] Furthermore, the system includes a means for recording the motion of the robot and proposing an optimal motion pattern in order to optimize the motion of the robot working in the factory. The motion of the robot is recorded using a 3D scanner or a camera and analyzed by the AI ​​means. The AI ​​means proposes an optimal motion pattern and makes the robot's motion more efficient.

[0469] In addition, vibration and temperature sensors are used to detect abnormalities in the robot. OpenCV and PyTorch are used to detect abnormalities and propose corrections to the robot's behavior based on that information. This optimizes the robot's behavior and enables it to work more efficiently.

[0470] For example, if a robot assembles parts in a factory and its movements slow down or abnormal vibrations occur, the system records the movement and the AI ​​proposes the optimal movement pattern. If the emotion engine detects an abnormality, it is reflected in the proposal to correct the movement.

[0471] Here is an example of a prompt to be input to the generative AI model:

[0472] "To optimize the movements of robots assembling parts in a factory, AI should suggest optimal movement patterns using data recorded by 3D scans and cameras. Also, detect abnormal vibrations or temperature increases in the robot and suggest movement corrections based on that."

[0473] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0474] Step 1:

[0475] A user uses a 3D body scanning device to obtain physique data.

[0476] Input: User's body

[0477] Output: 3D body scan data

[0478] How it works: The user stands in front of the 3D scanner, which scans the entire body and generates digital data.

[0479] Step 2:

[0480] The user's specific actions are recorded using cameras and sensors.

[0481] Input: User actions

[0482] Output: Operation record data

[0483] Specific movements: The user performs a specific movement (e.g. batting or pitching form) in front of the camera, and the camera records that movement with high accuracy.

[0484] Step 3:

[0485] The server analyzes the recorded motion data using AI means.

[0486] Input: Motion record data, 3D body scan data

[0487] Output: Motion analysis results

[0488] Specific operation: The server uses TensorFlow and Keras to input motion record data and 3D body scan data into an AI model to analyze the user's movements.

[0489] Step 4:

[0490] Based on the results of the behavior analysis, the server suggests to the user how to modify their behavior.

[0491] Input: Motion analysis results

[0492] Output: Proposal for corrective action

[0493] Specific actions: Based on the analysis results, the server generates specific corrections to improve the user's behavior and presents them to the user via a smartphone or tablet application.

[0494] Step 5:

[0495] The robot's movements are recorded using 3D scanners and cameras.

[0496] Input: Robot movement

[0497] Output: Robot operation record data

[0498] Specific actions: As the robot performs a task, 3D scanners and cameras record its movements.

[0499] Step 6:

[0500] The server analyzes the robot's operation record data using AI means.

[0501] Input: Robot motion record data

[0502] Output: Robot motion analysis results

[0503] Specific operation: The server uses TensorFlow and Keras to input the robot's movement record data into an AI model and analyze the robot's movement.

[0504] Step 7:

[0505] The server detects an abnormality in the robot.

[0506] Input: Robot vibration data, temperature data

[0507] Output: Anomaly detection result

[0508] Specific operation: The server analyzes data from vibration and temperature sensors using OpenCV and PyTorch to detect anomalies.

[0509] Step 8:

[0510] The server suggests optimal movement patterns based on the results of the robot's movement analysis and anomaly detection.

[0511] Input: Robot operation analysis results, anomaly detection results

[0512] Output: Optimal motion pattern suggestions

[0513] Specific behavior: The server integrates the analysis results and anomaly detection results, generates specific behavior patterns to optimize the robot's behavior, and applies them to the robot.

[0514] 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 a voice indicating a user input for the result of the specific processing.

[0515] The control unit 46A transmits voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0516] The data generation model 58 is a so-called generative AI (Artificial Intelligence) model. An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0517] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0518] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0519] [Second embodiment]

[0520] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0521] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0522] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0523] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0524] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0525] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0526] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0527] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0528] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0529] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0530] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0531] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0532] "Example 1"

[0533] In one embodiment of the present invention, a user first measures his or her physique using a 3D body scan. This measurement is performed, for example, using a device that provides a 3D body scan. Next, the user performs a specific movement, such as batting or pitching in baseball. This movement is recorded using a camera, sensor, or the like. The recorded movement is analyzed by AI. Using deep learning, the AI ​​compares the user's movement with that of a professional athlete with a similar physique. Then, based on the comparison results, suggestions are made to the user on how to modify the movement. These suggestions are presented to the user, for example, through an application on a device such as a smartphone or tablet.

[0534] "Example 2"

[0535] In one embodiment of the present invention, a user first measures his or her physique using a 3D body scan. This measurement is performed, for example, using a device that provides a 3D body scan. Next, the user performs a specific movement, such as batting or pitching in baseball. This movement is recorded using a camera, sensor, or the like. The recorded movement is analyzed by AI. Using deep learning, the AI ​​compares the user's movement with that of a professional athlete with a similar physique. Then, based on the comparison results, suggestions are made to the user on how to modify the movement. These suggestions are presented to the user, for example, through an application on a device such as a smartphone or tablet.

[0536] The process flow of each embodiment will be described below.

[0537] "Example 1"

[0538] Step 1: The user measures their physique using a 3D body scan. This measurement is taken, for example, using a device that provides a 3D body scan.

[0539] Step 2: Next, the user performs a specific action, such as batting or pitching a baseball. This action is recorded using cameras and sensors.

[0540] Step 3: The recorded movements are analyzed by AI, which uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[0541] Step 4: Based on the comparison results, the system then suggests modifications to the user's behavior. These suggestions are presented to the user, for example, via an application on a device such as a smartphone or tablet.

[0542] "Example 2"

[0543] Step 1: The user measures their physique using a 3D body scan. This measurement is taken, for example, using a device that provides a 3D body scan.

[0544] Step 2: Next, the user performs a specific action, such as batting or pitching a baseball. This action is recorded using cameras and sensors.

[0545] Step 3: The recorded movements are analyzed by AI, which uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[0546] Step 4: Based on the comparison results, the system then suggests modifications to the user's behavior. These suggestions are presented to the user, for example, via an application on a device such as a smartphone or tablet.

[0547] Example 1

[0548] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0549] Conventional motion analysis systems have had difficulty in accurately measuring and recording a user's physique and movements and providing appropriate feedback. In addition, there was a lack of means to perform highly accurate analysis when comparing a user's movements with those of professional athletes. This made it difficult for users to effectively improve their own movements.

[0550] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0551] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for transmitting the recorded movement data and physique data to the server, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for displaying the suggested corrections on the user's terminal. This allows the user to accurately measure and record their own physique and movements, and obtain specific corrections by comparing them with the movements of professional athletes.

[0552] "User" refers to an individual who uses the system to measure and record their physique and movements and receive feedback.

[0553] "Body Measurements" refers to a User's physical characteristics and measurements, including data measured by means of a 3D body scan or similar means.

[0554] "Movement" refers to specific physical movements or performances performed by users, which are recorded using cameras and sensors.

[0555] "Server" refers to a computer system that receives data sent by a User, analyzes it using AI means, and provides the results to the User.

[0556] "3D body scanning" refers to technology and equipment that measures a user's physique in three dimensions and is used to obtain detailed data about the user's body.

[0557] "AI Means" refers to means for using artificial intelligence technology to analyze a user's movements and compare them with the movements of a professional athlete.

[0558] "Deep learning" is a field of artificial intelligence that refers to a technology that uses multi-layer neural networks to learn the characteristics of data and perform advanced analysis and predictions.

[0559] "Fix" refers to specific changes or suggestions suggested to improve a user's experience.

[0560] "Terminal" refers to the device that a user uses to access the system, including smartphones and tablets.

[0561] "Comparison Results" refers to the results of a comparison made by AI means between the User's movements and the movements of a professional athlete, and includes data that serves as the basis for feedback to the User.

[0562] This invention is a system that measures and records a user's physique and movements, analyzes them using AI, and suggests specific movement corrections to the user. A specific embodiment of this system will be described below.

[0563] First, the user measures his or her physique using a device that provides a 3D body scan, such as Kinect or Structure Sensor, which acquires the user's physique data and stores it on the user's device (smartphone or tablet).

[0564] Next, the user performs a specific movement, such as a batting or pitching form in baseball. This movement is recorded using a smartphone camera or a GoPro. The recorded video data is saved on the user's device.

[0565] The user's device transmits the recorded movement data and physique data to the server. An Internet connection is required for transmission. When the user presses the "Data transmission" button in the application, the device uploads the data to the server.

[0566] The server inputs the received motion data and physique data into the AI ​​model. The AI ​​model uses TensorFlow and PyTorch, and uses deep learning to compare the user's motion with that of a professional athlete with a similar physique. The server inputs the data into the AI ​​model and starts the comparison process. Once the process is complete, the comparison results are generated.

[0567] The server generates corrections for the user's movements based on the results of the comparison with the AI ​​model. These corrections are summarized as specific advice or improvement methods. For example, specific advice such as "You need to rotate your hips faster to increase the swing speed of your batting form" is generated.

[0568] The server sends the generated corrections to the user's device. The user's device displays the received corrections in the application. The user opens the application and checks the proposed corrections. For example, specific advice such as "how to practice to rotate your hips faster" is displayed.

[0569] As a concrete example, consider the case where a user wants to improve their baseball batting form. The user first measures their physique using a 3D body scanning device (e.g. Kinect). Next, they record their batting form using a smartphone camera. This recorded data is input into a deep learning model using TensorFlow and compared with the movements of professional batters. Based on the comparison results, corrections to the user's batting form are presented through a dedicated app.

[0570] An example of a prompt is, "Taking the user's physique data and a video of their batting form as input, compare it with the movements of a professional batter and suggest corrections."

[0571] In this way, users can compare their own movements with those of professionals and get specific corrections.

[0572] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0573] Step 1:

[0574] Users measure their physique using a 3D body scanning device.

[0575] Input: User's body position

[0576] Specific action: The user stands in front of the Kinect and rotates their body according to the instructions.

[0577] Data Processing: The scanning device collects the user's physique data and generates a 3D model.

[0578] Output: The generated physique data is saved on the user's device.

[0579] Step 2:

[0580] The user performs a specific movement (e.g., batting form in baseball) and records that movement.

[0581] Input: User actions

[0582] Specific actions: The user sets the smartphone on a tripod and takes a picture of their batting form.

[0583] Data processing: The camera records the user's movements as video data.

[0584] Output: The recorded video data is stored on the user's device.

[0585] Step 3:

[0586] The user's device transmits the recorded movement data and physical data to a server.

[0587] Input: Movement and body data

[0588] Specific action: The user presses the "Submit Data" button within the application.

[0589] Data processing: The device compresses the data and uploads it to a server via the Internet.

[0590] Output: Data is sent to the server.

[0591] Step 4:

[0592] The server inputs the received movement data and physique data into the AI ​​model.

[0593] Input: Movement and body data

[0594] Specific actions: The server inputs the data into the AI ​​model and begins the comparison process.

[0595] Data calculation: The AI ​​model uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[0596] Output: The comparison results are generated.

[0597] Step 5:

[0598] The server generates corrections to the user's behavior based on the comparison results of the AI ​​model.

[0599] Input: Comparison result

[0600] Specific actions: The server generates specific advice such as "You need to rotate your hips faster to increase the swing speed of your batting form."

[0601] Data processing: Analyze the comparison results and generate corrections in text format.

[0602] Output: The corrections are generated.

[0603] Step 6:

[0604] The server sends the generated modifications to the user's terminal.

[0605] Input: Correction

[0606] Specific operation: The server sends the modifications to the user's device.

[0607] Data processing: Convert the corrections into the appropriate format and send them.

[0608] Output: The corrections are sent to the user's terminal.

[0609] Step 7:

[0610] The user's device will display the received corrections within the application.

[0611] Input: Correction

[0612] What happens: The user opens the application and sees the suggested fixes.

[0613] Data processing: Display the corrections in a user-friendly format.

[0614] Output: User can see the corrections.

[0615] (Application example 1)

[0616] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0617] In conventional factory work, there is a lack of specific feedback to improve the efficiency and safety of workers' movements. As a result, workers continue to make inappropriate movements, which leads to problems of reduced work efficiency and increased physical strain. In addition, there is no system to optimize workers' movements, which makes it difficult to provide appropriate guidance to individual workers.

[0618] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for measuring the physique of the user, a means for recording specific movements performed by the user, an AI means for analyzing the recorded movements and comparing them with movements of workers with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for displaying suggestions for optimizing the movements of factory workers. This makes it possible to provide specific feedback for improving the efficiency and safety of the movements of the workers.

[0619] "User" means an individual who utilizes the System to have their physique and / or movement measured and analyzed.

[0620] "Physique" refers to the physical characteristics and measurements of a user.

[0621] "Movement" refers to a specific physical movement or task performed by a user.

[0622] A "recording means" is a device or method for saving a user's actions as video or data.

[0623] "AI means" means technology that uses artificial intelligence to analyze recorded movements and compare them with other movements.

[0624] "Deep learning" is a type of artificial intelligence, a technology that uses multi-layered neural networks to analyze and learn from data.

[0625] A "means for suggesting modifications" is a method or device for suggesting improvements to a user's operation based on the analysis results.

[0626] A "factory worker" is a worker who performs specific tasks in a factory.

[0627] The "means for displaying suggestions for optimization" refers to a device or method for visually presenting suggestions for improving the efficiency and safety of operations to a user.

[0628] "3D body scanning" is a technology that measures a user's body in three dimensions.

[0629] A system for implementing the present invention includes means for measuring a user's physique, means for recording specific movements performed by the user, AI means for analyzing the recorded movements and comparing them with the movements of workers with a similar physique, means for suggesting to the user corrections to their movements based on the comparison results, and means for displaying suggestions for optimizing the movements of factory workers.

[0630] Hardware and Software Used

[0631] 3D body scanning device: A device for measuring the user's body size in three dimensions.

[0632] Camera: A device used to record user actions. An example is the Logitech C920.

[0633] Smart glasses: A device that visually indicates to the user the correction of their actions. An example is Google Glass.

[0634] Tablet: A device used to display performance corrections and optimization suggestions. An example is the iPad.

[0635] Server: A computer system for processing data and running AI models.

[0636] Software: Using Python, OpenCV, Keras and other program libraries.

[0637] Data processing and calculation

[0638] 1. Acquisition of physique data: The server acquires the user's physique data using a 3D body scanning device. This data represents the user's physical characteristics and dimensions in three dimensions.

[0639] 2. Recording of actions: The server records the user's actions using a camera. The recorded actions are saved as image data.

[0640] 3. Motion analysis: The server inputs the recorded image data and physique data into the AI ​​model to analyze the motion. The AI ​​model uses deep learning to compare the user's motion with that of workers with a similar physique.

[0641] 4. Suggested modifications: The server will suggest modifications to the user based on the analysis results, and these suggestions will be displayed on the smart glasses or tablet.

[0642] Examples

[0643] When a factory worker lifts a heavy object, the movement is recorded using a 3D body scan and a camera, and then analyzed by AI. As a result of the analysis, corrections such as the angle of the waist and the position of the hands when lifting are suggested, allowing the worker to perform the work efficiently and safely.

[0644] Examples of prompt statements

[0645] "Record factory workers lifting heavy objects and feed that into the AI ​​along with their 3D body scan data to compare with efficient movements and suggest corrections."

[0646] The above is an embodiment of the present invention.

[0647] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0648] Step 1:

[0649] The server acquires the user's physique data using a 3D body scanning device. The input includes the user's physical characteristics and dimensions. The data is processed by converting these characteristics and dimensions into a data format that represents them three-dimensionally. The output is the user's physique data.

[0650] Step 2:

[0651] The server records the user's actions using a camera. The input includes the specific actions performed by the user. The data processing includes storing the actions as video data. The output includes image data of the recorded actions.

[0652] Step 3:

[0653] The server inputs the recorded image data and physique data into the AI ​​model and analyzes the movements. The input data includes image data and physique data. For data calculation, the AI ​​model uses deep learning to compare the user's movements with those of workers with a similar physique. The output is the analysis result of the movements.

[0654] Step 4:

[0655] The server proposes to the user corrections to the behavior based on the analysis results. The input includes the analysis results of the behavior. The data processing generates specific correction suggestions. The output is the proposed corrections.

[0656] Step 5:

[0657] The server displays the suggested corrections on the smart glasses or tablet. An input includes the suggested corrections. A specific operation includes generating and sending data for visually displaying the suggested corrections to the smart glasses or tablet. An output includes the suggested corrections that are visually visible to the user.

[0658] The above is the processing flow of this program.

[0659] Example 2

[0660] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0661] Conventional motion analysis systems have difficulty in accurately measuring and recording a user's physique and motion, and suggesting appropriate corrections. In addition, there is a lack of means to suggest specific corrections to users, which has led to problems with effective improvement of motion.

[0662] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0663] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements performed by the user, an artificial intelligence means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for presenting the corrections to the user. This makes it possible to accurately measure and record the user's physique and movements, suggest appropriate corrections, and present specific corrections to the user.

[0664] "User" refers to an individual who uses the System to measure and record their physique and movements and receive suggestions for movement modifications.

[0665] "Means for measuring body size" refers to devices or technologies that measure the dimensions and shape of a user's body in three dimensions.

[0666] "Means for recording specific actions" refers to devices or technologies that use cameras or sensors to record actions performed by users.

[0667] "Artificial intelligence means" refers to AI technology used to analyze recorded movement data and compare the movements of users with those of professional athletes.

[0668] "Means for suggesting corrections" refers to a technology that extracts and suggests improvements to the user's actions based on the analysis results by the artificial intelligence means.

[0669] "Means for suggesting corrections" means a device or application that visually or audibly communicates the suggested corrections to the user.

[0670] "3D body scanning" refers to a technology that measures a user's body in three dimensions.

[0671] "Deep learning" refers to a machine learning technique using multiple layers of neural networks used in artificial intelligence tools.

[0672] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0673] The present invention relates to a system that measures a user's physique, records and analyzes specific movements, and suggests corrections to those movements. A specific embodiment of this system will be described below.

[0674] User body measurements

[0675] The user measures his or her physique using a 3D body scanning device. Examples of such devices include a "3D scanner" or a "motion capture system." The user follows the device's instructions to scan his or her physique while rotating 360 degrees. The device processes the scan data in real time and generates the user's physique data. The generated data is sent to a server via wireless communication.

[0676] Recording actions

[0677] Next, the user performs a specific movement, such as batting or pitching a baseball. The user records the movement using a camera or sensor. The hardware used may be a "high-resolution camera" or a "motion capture system." The device generates the recorded video data or motion capture data and sends it to a server.

[0678] Analysis of behavior

[0679] The server inputs the received physique data and movement data into an AI model. This AI model uses deep learning to compare the user's movements with those of professional athletes. The software used is a "deep learning framework." The server extracts corrections for the user's movements from the output of the AI ​​model.

[0680] Suggested behavior modifications

[0681] The server sends the extracted correction points to the device. The device displays the received correction points in a dedicated application. The user can check the correction points through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[0682] Examples

[0683] Example 1: Correcting baseball batting form

[0684] The user measures their physique using a 3D body scanning device and sends the data to the server. After that, a high-resolution camera is used to capture their batting form, and the video data is uploaded to the server. The server analyzes the data using a deep learning framework and extracts corrections that are presented to the user through a dedicated application. The user works to improve their batting form while looking at the application.

[0685] Example 2: Correcting pitching form

[0686] The user uses a 3D scanner to measure their physique and sends the data to the server. The motion capture system then records their pitching form and uploads the data to the server. The server then analyzes the data using a deep learning framework and extracts corrections that are presented to the user through a dedicated application. The user works on improving their pitching form while looking at the application.

[0687] Examples of prompt statements

[0688] Prompt 1: Baseball batting form

[0689] "Please generate an AI model that takes a user's 3D body scan data and video data of their batting form as input, compares it with data from professional baseball players, and suggests corrections."

[0690] Prompt 2: Pitching form

[0691] "Please generate an AI model that takes the user's 3D body scan data and motion capture data of their pitching form as input, compares it with data from professional baseball players, and suggests corrections."

[0692] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0693] Program processing flow

[0694] Step 1: Measuring the user's body size

[0695] The user activates the 3D body scanning device. Following the device's instructions, the user rotates 360 degrees to scan their physique. The device processes the scan data in real time and generates physique data for the user. The generated data is then transmitted to the server via wireless communication.

[0696] Input: User's body scan data

[0697] Data processing: Real-time processing of scan data

[0698] Output: User's physical data

[0699] Step 2: Recording the action

[0700] Using a high-resolution camera and a motion capture system, the user performs a specific movement, such as batting or pitching a baseball. The device records the movement and generates video data or motion capture data. The generated data is sent to the server.

[0701] Input: User actions

[0702] Data processing: Motion recording and data generation

[0703] Output: Video data or motion capture data

[0704] Step 3: Analyze the behavior

[0705] The server inputs the received physique data and movement data into an artificial intelligence model. The artificial intelligence model uses deep learning to compare the user's movements with those of professional athletes. The server extracts corrections for the user's movements from the output of the artificial intelligence model.

[0706] Input: Body size data, movement data

[0707] Data processing: Motion comparison using deep learning

[0708] Output: Behavior fixes

[0709] Step 4: Propose behavior modifications

[0710] The server sends the extracted correction points to the device. The device displays the received correction points in a dedicated application. The user can check the correction points through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[0711] Input: Behavior fixes

[0712] Data processing: Preparation for displaying corrections

[0713] Output: A suggestion for the user to make corrections

[0714] Adding specific actions

[0715] Step 1: Measuring the user's body size

[0716] The user activates the 3D body scanning device and follows the device's instructions to scan their physique. The scan data is processed in real time to generate the user's physique data. The generated data is then transmitted to the server via wireless communication.

[0717] Step 2: Recording the action

[0718] The user sets up a high-resolution camera and records the batting form of a baseball player. The camera records high-resolution video and saves it on the device. The device compresses the saved video data and uploads it to the server.

[0719] Step 3: Analyze the behavior

[0720] The server inputs the received physique data and video data into a deep learning framework. The AI ​​model compares the user's batting form with that of professional baseball players. Features such as joint angles and movement speed are used for the comparison. The server extracts corrections for the user's movements from the output of the AI ​​model.

[0721] Step 4: Propose behavior modifications

[0722] The server sends the extracted corrections in JSON format to the device. The device displays the received corrections in a dedicated application. The user can check the corrections through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[0723] (Application example 2)

[0724] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[0725] Conventional optimization of factory robots' movements relied on manual adjustments and experience, making it difficult to achieve efficient and highly accurate optimization. In addition, because individual optimization based on the user's physique or movements was not performed, general-purpose optimization methods were sometimes ineffective. This created a risk of a decline in factory productivity and quality.

[0726] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0727] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user points for correcting the movements based on the comparison results, a means for recording and analyzing the movements of a robot used in the factory, and a means for suggesting points for correcting the movements of the robot. This enables individual optimization based on the user's physique and movements, and makes it possible to efficiently and accurately optimize the movements of factory robots.

[0728] "User" means any individual or legal entity that uses the System to measure and analyze their physique and movements.

[0729] "Physique" refers to the shape and dimensions of a User's body, as measured by means such as a 3D body scan.

[0730] A "specific action" is a specific movement or task performed by a user that is recorded using a camera or sensor.

[0731] "Recording means" refers to devices or methods that use cameras, sensors, etc. to save user actions as data.

[0732] "AI means" refers to technology that uses artificial intelligence to analyze recorded movement data and compare the user's movements with those of professional athletes.

[0733] "Deep learning" is a type of artificial intelligence, a technology that uses multi-layered neural networks to analyze and learn from data.

[0734] A "professional athlete" is an athlete who is professionally active in a particular sport, and is the subject against which the user's movements are compared.

[0735] "Behavior Modifications" are specific improvements suggested to optimize a user's performance.

[0736] A "factory robot" is an automated mechanical device used on a factory production line or in a workshop.

[0737] "Optimization" means adjusting something to the most efficient and effective state for a particular purpose.

[0738] To implement this invention, the following hardware and software are used. The hardware requires a 3D scanner, a camera, a sensor, a server, and a user terminal (a smartphone or a tablet). The software requires Python, OpenCV, Keras, etc.

[0739] First, the user measures his or her own physique using a 3D scanner. The 3D scanner captures the shape and dimensions of the user's body with high precision and stores them as digital data. This data is then sent to a server.

[0740] Next, the user performs a specific action, for example to mimic the action of a robot used in a factory, and the action is recorded using cameras and sensors, and the recorded action data is also sent to the server.

[0741] The server inputs the received 3D scan data and movement data into the AI ​​system. The AI ​​system analyzes the data using deep learning and compares the user's movements with those of professional athletes with a similar physique. Based on the comparison results, the AI ​​system suggests corrections to the user's movements.

[0742] In addition, to optimize the operation of the robots used in the factory, the robots' operation data is also recorded and analyzed by AI means. Based on the analysis results, corrections are proposed to optimize the robot's operation. These suggestions are displayed on the user's terminal.

[0743] As a concrete example, consider optimizing the operation of a welding robot used in a factory. A 3D scanner captures the shape data of the robot, and cameras and sensors record its operation data. This data is input into an AI tool, and the tool suggests corrections to the welding angle and speed based on the analysis results.

[0744] An example of a prompt sentence to be input into the generative AI model is, "Please input the welding robot's motion data along with the 3D scan data and suggest optimal motion corrections."

[0745] As described above, the present invention enables individual optimization based on the physique and movements of a user, and can optimize the movements of factory robots efficiently and with high accuracy.

[0746] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0747] Step 1:

[0748] Users measure their body size using a 3D scanner.

[0749] Input: User's body

[0750] Data processing: A 3D scanner captures the shape and dimensions of the user's body with high precision and stores them as digital data.

[0751] Output: 3D scan data

[0752] Step 2:

[0753] The user performs a specific action and the action is recorded using cameras and sensors.

[0754] Input: User actions

[0755] Data processing: Cameras and sensors record user actions as video and sensor data.

[0756] Output: Operation data

[0757] Step 3:

[0758] The server receives the 3D scan data and the motion data.

[0759] Input: 3D scan data, motion data

[0760] Data processing: The server receives these data and prepares them for input into the AI ​​means.

[0761] Output: Prepared data

[0762] Step 4:

[0763] The server analyzes the 3D scan data and the motion data using AI means.

[0764] Input: Prepared data

[0765] Data processing: Using a deep learning model, we compare the user's movements with those of professional athletes with a similar physique.

[0766] Output: Analysis results

[0767] Step 5:

[0768] The server then suggests modifications to the user's behavior based on the analysis results.

[0769] Input: Analysis results

[0770] Data Transformation: Use the analysis to generate specific modifications to optimize user behavior.

[0771] Output: suggested fixes

[0772] Step 6:

[0773] Suggested fixes will be displayed on the user's device.

[0774] Input: Suggested fix

[0775] Data processing: Converting the proposal content into a format for display on the user's device.

[0776] Output: The corrections displayed on the user's terminal.

[0777] Step 7:

[0778] The operations of robots used in factories are recorded and transmitted to a server.

[0779] Input: Robot movement

[0780] Data processing: Cameras and sensors record the robot's movements as video and sensor data, and send them to a server.

[0781] Output: Robot motion data

[0782] Step 8:

[0783] The server analyzes the robot's operational data using AI means and suggests modifications for optimization.

[0784] Input: Robot motion data

[0785] Data processing: Using deep learning models, the robot's behavior is analyzed and corrections are generated for optimization.

[0786] Output: Suggested modifications to the robot's behavior

[0787] Step 9:

[0788] Suggestions for correcting the robot's behavior are displayed on the user's device.

[0789] Input: Suggested modifications to the robot's behavior

[0790] Data processing: Converting the proposal content into a format for display on the user's device.

[0791] Output: Robot behavior corrections displayed on the user's device

[0792] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0793] "Example 1"

[0794] In one embodiment of the present invention, a system is provided that includes a means for measuring a user's physique, a means for recording a specific movement performed by the user, an AI means for analyzing the recorded movement and comparing it with the movement of a professional athlete with a similar physique, a means for suggesting to the user a correction to the movement based on the comparison result, and an emotion engine for recognizing the user's emotions. The emotion engine recognizes emotions from the user's facial expressions and tone of voice, and provides the information to the AI ​​means. The AI ​​means proposes corrections to the movement by taking into account not only the comparison between the user's movement and the movement of the professional athlete, but also the user's emotions. For example, if the user feels frustrated, the AI ​​means proposes corrections in a form that is easy for the user to accept, taking into account the information. In this way, it is possible to propose improvement of the movement by taking into account the user's emotions.

[0795] "Example 2"

[0796] In one embodiment of the present invention, a system is provided that includes a means for measuring a user's physique, a means for recording a specific movement performed by the user, an AI means for analyzing the recorded movement and comparing it with the movement of a professional athlete with a similar physique, a means for suggesting to the user a correction to the movement based on the comparison result, and an emotion engine for recognizing the user's emotions. The emotion engine recognizes emotions from the user's facial expressions and tone of voice, and provides the information to the AI ​​means. The AI ​​means proposes corrections to the movement by taking into account not only the comparison between the user's movement and the movement of the professional athlete, but also the user's emotions. For example, if the user feels frustrated, the AI ​​means proposes corrections in a form that is easy for the user to accept, taking into account the information. In this way, it is possible to propose improvement of the movement by taking into account the user's emotions.

[0797] The process flow of each embodiment will be described below.

[0798] "Example 1"

[0799] Step 1: Measure the user's physique with a 3D body scan.

[0800] Step 2: A user's specific action (e.g., batting or pitching a baseball) is recorded using a video camera or motion sensors.

[0801] Step 3: The recorded movements are analyzed using AI tools and compared to those of professional athletes with a similar physique.

[0802] Step 4: Understand the user's emotions using an emotion engine that recognizes emotions from the user's facial expressions and tone of voice.

[0803] Step 5: The AI ​​tool takes into account the comparison of the user's movements with those of professional athletes and the user's emotions and suggests corrections to the movements.

[0804] Step 6: The proposed behavioral modifications are presented to the user via an application on a device such as a smartphone or tablet.

[0805] "Example 2"

[0806] Step 1: Measure the user's physique with a 3D body scan.

[0807] Step 2: A user's specific action (e.g., batting or pitching a baseball) is recorded using a video camera or motion sensors.

[0808] Step 3: The recorded movements are analyzed using AI tools and compared to those of professional athletes with a similar physique.

[0809] Step 4: Understand the user's emotions using an emotion engine that recognizes emotions from the user's facial expressions and tone of voice.

[0810] Step 5: The AI ​​tool takes into account the comparison of the user's movements with those of professional athletes and the user's emotions and suggests corrections to the movements.

[0811] Step 6: The proposed behavioral modifications are presented to the user via an application on a device such as a smartphone or tablet.

[0812] Example 1

[0813] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0814] Conventional motion improvement systems make suggestions based on the user's physique and motion data, but since the suggestions do not take into account the user's feelings, users may find it difficult to accept the suggestions. In addition, since the points to correct in motion are not specific, it is difficult for users to understand how to improve.

[0815] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0816] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, an artificial intelligence means for analyzing the recorded movements and comparing them with movements of professional athletes with a similar physique, a means for suggesting to the user points for correcting the movements based on the comparison results, a means for recognizing the user's emotions, and a means for suggesting points for correcting the movements taking into account the emotion data. This makes it possible to suggest movement improvements taking into account the user's physique and emotions.

[0817] A "means for measuring a user's physique" is a device or method for measuring a user's physical characteristics and acquiring them as digital data.

[0818] "Means for recording specific actions performed by a user" refers to a device or method that uses video or a sensor to record specific actions performed by a user as digital data.

[0819] "Artificial intelligence means" means software or systems that analyse the recorded data and use specific algorithms to compare the user's movements with other data (e.g. the movements of a professional sportsperson).

[0820] The "means for suggesting points for modification of motion" refers to a device or method that suggests points for improvement or methods for modification of motion to a user based on the analysis results.

[0821] A "means for recognizing a user's emotions" refers to a device or method that analyzes the user's emotions from their facial expressions, tone of voice, etc., and acquires them as digital data.

[0822] The "means for proposing corrections to movements taking emotion data into consideration" refers to a device or method that proposes corrections to movements in a more acceptable form based on the user's emotion data.

[0823] "3D body scanning" is a technology that scans the user's body in three dimensions and obtains detailed physique data.

[0824] "Deep learning" is an artificial intelligence technique that uses multi-layered neural networks to analyze data and learn patterns and features.

[0825] This invention is a system that analyzes the user's physique and movements, compares them with the movements of professional athletes, and suggests corrections to the user's movements. Furthermore, by recognizing the user's emotions and making suggestions taking into account the user's emotion data, it is possible to present corrections to the user's movements in a form that is easy for the user to accept.

[0826] Hardware and Software Used

[0827] 1. User's body measurements

[0828] A user measures their physique using equipment that provides a three-dimensional body scan, which may include, for example, a 3D scanner or a dedicated body scanning application, to obtain detailed physique data, such as the user's height, weight, and body fat percentage.

[0829] 2. Recording the action

[0830] Users use a smartphone camera or a dedicated motion capture device to record a specific movement (e.g., batting or pitching a baseball), and the recorded data includes detailed movement information such as swing speed and angle.

[0831] 3. Transmission of operation data

[0832] The device transmits the recorded movement and physique data to a server in real time over the Internet, where the data is encrypted and uses a secure communication protocol.

[0833] 4. Analysis of movements

[0834] The server inputs the received data into an AI model, which uses deep learning algorithms to compare the user's movements with those of professional athletes. The software used is a deep learning framework such as TensorFlow or PyTorch. For example, it calculates how much the user's swing speed differs from the average speed of a professional player.

[0835] 5. Emotion Recognition

[0836] The device uses an emotion engine that analyzes the user's facial expressions and tone of voice in real time. This emotion engine determines whether the user is frustrated or satisfied and sends that information to a server. The software used is an emotion recognition API (e.g. Microsoft Azure's Emotion API).

[0837] 6. Suggestions for behavior modifications

[0838] The server then suggests to the user how to improve their swing based on the comparison of their movements and their emotion data. For example, if the user feels frustrated, the server might suggest, "Just changing the way you grip the bat a little might make your swing smoother." The server notifies the user of the suggestion through an application on their device, such as a smartphone or tablet.

[0839] Examples

[0840] Example 1: Improving baseball batting form

[0841] The user uses a 3D scanner to measure their physique and records their batting form with their smartphone camera. The device sends the recorded data to a server, which inputs the data into an AI model and compares it with the form of professional baseball players. If the emotion engine detects the user's frustration, the server will make suggestions such as, "Maybe your swing will be smoother if you just change the way you grip the bat a little." The suggestion is notified to the user through a smartphone application.

[0842] Example prompts for generative AI models

[0843] "Please input the user's 3D body scan data and a video of their batting form, compare it with the form of a professional baseball player, and suggest improvements while taking into account the user's emotions."

[0844] In this way, it becomes possible to suggest motion improvements that take into account the user's physique and emotions.

[0845] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0846] Step 1:

[0847] Users measure their physique using a device that provides a 3D body scan. As input, a 3D scanner is used to scan the user's body. As output, detailed physique data is generated, including the user's height, weight, and body fat percentage. This data is then stored on the device.

[0848] Step 2:

[0849] Users record a specific movement (e.g. batting or pitching in baseball) using a smartphone camera or a dedicated motion capture device. As input, the user's movements are captured by the camera or sensors. As output, detailed movement data such as swing speed and angle is generated. This data is stored on the device.

[0850] Step 3:

[0851] The terminal transmits the recorded movement data and physique data to the server. As input, the movement data and physique data stored on the terminal are used. As output, these data are transmitted to the server via the Internet. The data is encrypted and uses a secure communication protocol.

[0852] Step 4:

[0853] The server inputs the received data into the AI ​​model. As input, the motion and physique data sent to the server are used. As output, the AI ​​model generates the results of comparing the user's motion with those of professional athletes. This AI model uses deep learning algorithms and utilizes deep learning frameworks such as TensorFlow and PyTorch.

[0854] Step 5:

[0855] The device uses an emotion engine that analyzes the user's facial expressions and tone of voice in real time. As input, the user's facial and voice data is captured through a camera and microphone. As output, emotion data is generated, such as whether the user is frustrated or satisfied. This data is then sent to a server.

[0856] Step 6:

[0857] The server proposes corrections to the user's movements based on the comparison results of the movements and the emotion data. The comparison results of the AI ​​model and the emotion data are used as inputs. As output, corrections to the user's movements are generated. For example, if the user feels frustrated, the server will suggest, "Maybe your swing will become smoother if you just change the way you grip the bat a little." The suggestion is notified to the user through an application on a device such as a smartphone or tablet.

[0858] (Application example 1)

[0859] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0860] Conventional motion analysis systems could analyze a user's physique and movements, but had the problem of not being able to suggest corrections to movements that took the user's emotions into account. Also, when optimizing the movements of robots working in factories, there was a lack of real-time monitoring of movement efficiency and error rates and suggestions for improvement. This resulted in issues such as reduced movement efficiency for users and robots, preventing optimal performance.

[0861] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0862] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user movement corrections based on the comparison results, an emotion engine for recognizing the user's emotions, a means for suggesting movement corrections taking into account information from the emotion engine, a means for optimizing the robot's movements, a means for monitoring the robot's movement efficiency and error rate, and a means for making improvement suggestions in real time. This makes it possible to suggest movement corrections taking into account the user's emotions, and further to monitor the movement efficiency and error rate of a robot working in a factory in real time, thereby enabling optimal movement performance to be achieved.

[0863] "Means for measuring the user's body size" refers to devices or technologies for accurately measuring the dimensions and shape of the user's body.

[0864] "Means for recording specific actions performed by a user" refers to devices or technologies that use cameras, sensors, etc. to record specific actions performed by a user.

[0865] "AI means for analyzing recorded movements and comparing them with the movements of professional athletes with a similar physique" refers to artificial intelligence technology for analyzing the recorded movement data of a user and comparing it with the movement data of a professional athlete with a similar physique.

[0866] "Means of suggesting to the user points to modify their movements based on the results of the comparison" refers to devices or technologies that suggest points to improve or modify movements to the user based on the results of the movement comparison performed by AI.

[0867] The "emotion engine that recognizes user emotions" is a technology that identifies emotions from the user's facial expressions, tone of voice, etc.

[0868] The "means for proposing modifications to actions while taking into consideration information from an emotion engine" refers to a device or technology that suggests modifications to actions based on the user's emotion information recognized by an emotion engine.

[0869] "Means for optimizing robot operation" refers to devices and technologies that optimize the operation of robots performing work in a factory to make them efficient and effective.

[0870] The "means for monitoring the robot's operational efficiency and error rate" refers to a device or technology that monitors the robot's operational efficiency and error occurrence rate in real time.

[0871] "Means of making improvement suggestions in real time" refers to devices or technologies that analyze robot operation data in real time and immediately suggest improvements.

[0872] A system for implementing this invention includes means for measuring a user's physique, means for recording specific movements performed by the user, AI means for analyzing the recorded movements and comparing them with the movements of a professional athlete with a similar physique, means for suggesting to the user modifications to their movements based on the comparison results, an emotion engine for recognizing the user's emotions, means for suggesting modifications to the movements taking into account information from the emotion engine, means for optimizing the robot's movements, means for monitoring the robot's movement efficiency and error rate, and means for making improvement suggestions in real time.

[0873] Hardware and Software Configuration

[0874] Hardware:

[0875] 3D body scanning device

[0876] Camera (e.g. Logitech C920)

[0877] Computer (e.g. Intel Core i7, 16GB RAM)

[0878] software:

[0879] OpenCV: Motion recording and image processing

[0880] Keras: Loading and predicting deep learning models

[0881] EmotionRecognizer: Emotion recognition library

[0882] Processing flow

[0883] The server first acquires the user's physique data using a 3D body scanning device. Then, it uses a camera to record the specific movements the user makes. The recorded movement data is preprocessed using OpenCV and analyzed with a deep learning model using Keras. The analysis results are compared with the movement data of professional athletes with a similar physique.

[0884] In addition, we use EmotionRecognizer to recognize the user's emotions and propose behavior modifications taking into account the information from the emotion engine. The proposed modifications are presented to the user.

[0885] For robots working in factories, measures are used to optimize the robot's operation. The robot's operation efficiency and error rate are monitored in real time, and improvement suggestions are made. This makes it possible to optimize the robot's operation performance.

[0886] Examples

[0887] For example, if a robot assembling parts in a factory is moving slowly, the AI ​​will analyze its movements and suggest correcting the angle and speed of its movements. Furthermore, if the robot is making frequent errors, it will determine through emotion recognition that it is feeling frustrated and suggest that it should move more slowly.

[0888] Examples of prompt statements

[0889] "To optimize the movements of a robot assembling parts in a factory, design a system that uses 3D body scanning and cameras to record the movements, analyzes them with AI, and suggests optimal movement patterns. In addition, add a function that monitors the robot's movement efficiency and error rate, and suggests improvements in real time."

[0890] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0891] Step 1:

[0892] The server acquires the user's physique data using a 3D body scanning device. As input, it scans the user's body dimensions and shape, and generates 3D physique data as output. This data is used to accurately determine the user's physique.

[0893] Step 2:

[0894] The server uses a camera to record certain actions performed by the user, capturing the actions performed by the user in real time as input, and generating video data of the actions as output, which is used for subsequent action analysis.

[0895] Step 3:

[0896] The server pre-processes the recorded motion data using OpenCV. It receives motion video data as input and produces pre-processed image data as output. This pre-processing includes image resizing and noise removal.

[0897] Step 4:

[0898] The server analyzes the preprocessed image data with a deep learning model using Keras. It receives the preprocessed image data as input and extracts motion features as output. These features are used to analyze the user's motion in detail.

[0899] Step 5:

[0900] The server compares the extracted features with the motion data of professional athletes with a similar build. It receives the user's motion features and the motion data of professional athletes as input, and generates a comparison result as output. This comparison result is used to identify corrections to the user's motion.

[0901] Step 6:

[0902] The server recognizes the user's emotions using EmotionRecognizer. As input, it captures the user's facial expressions and tone of voice during the action, and generates emotion data as output. This emotion data is used to understand the user's emotional state.

[0903] Step 7:

[0904] The server proposes behavior modifications taking into account information from the emotion engine. It receives as input the comparison results and emotion data, and generates as output behavior modifications for the user. The modifications are proposed taking into account the user's emotional state.

[0905] Step 8:

[0906] The server executes a means for optimizing the motion of a robot performing work in a factory, receiving motion data of the robot as input and generating an optimized motion pattern as output. This optimization is performed to improve the efficiency of the robot's motion.

[0907] Step 9:

[0908] The server monitors the robot's operation efficiency and error rate in real time. As input, it receives the robot's operation data in real time, and generates the monitoring results of the operation efficiency and error rate as output. The monitoring results are used to understand the operation status of the robot.

[0909] Step 10:

[0910] The server provides real-time improvement suggestions, taking the monitoring results as input and generating improvement suggestions as output, which are made to optimize the robot's motion performance.

[0911] Example 2

[0912] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0913] Conventional motion improvement systems have difficulty accurately measuring the user's physique and motion and providing appropriate feedback. In addition, motion improvement suggestions were not made taking the user's emotions into account, so there was a lack of feedback in a form that made it easy for the user to accept the suggestions. This limited the effectiveness of the user's motion improvement.

[0914] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0915] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for transmitting the recorded movements, an artificial intelligence means for analyzing the recorded movements and comparing them with movements of professional athletes with a similar physique, a means for suggesting to the user how to modify the movements based on the comparison results, a means for recognizing the user's emotions, and a means for suggesting how to modify the movements while taking the recognized emotions into consideration. This makes it possible to accurately measure the user's physique and movements and provide appropriate feedback. Furthermore, since suggestions for movement improvement are made taking the user's emotions into consideration, feedback is provided in a form that makes it easy for the user to accept the suggestions, improving the effectiveness of movement improvement.

[0916] "Means for measuring the user's body size" refers to devices or technologies that measure the dimensions and shape of the user's body in three dimensions.

[0917] "Means for recording specific actions performed by a user" refers to devices or technologies that use video or sensors to record specific actions performed by a user.

[0918] The "means for transmitting the recorded motion" refers to a communication means for transmitting the recorded motion data to a server or other device.

[0919] "Artificial intelligence means" refers to artificial intelligence technology used to analyze recorded movement data and compare the movements of a user with the movements of a professional athlete.

[0920] "Means for suggesting modifications to movements" refers to a device or technology that suggests improvements to movements to a user based on the results of analysis by the artificial intelligence means.

[0921] "Means of recognizing the user's emotions" refers to devices or technologies for recognizing emotions from the user's facial expressions, tone of voice, etc.

[0922] "Means for suggesting modifications to behavior taking into account recognized emotions" refers to devices or technologies that suggest modifications to behavior in a manner that is easy for the user to accept, based on the user's emotional information.

[0923] The present invention is a system that measures a user's physique, records specific movements, analyzes the movements, and suggests corrections. The system can recognize the user's emotions and suggest corrections to movements taking them into account.

[0924] First, the user measures their physique using a 3D body scanning device. Specifically, devices such as the Structure Sensor and Kinect are used. This allows the user's physique data to be acquired and stored on the device.

[0925] Next, the user performs a specific motion (e.g., batting or pitching a baseball). This motion is recorded using a camera or sensors (e.g., a GoPro camera or a Vicon motion capture system). The recorded motion data is stored on the device.

[0926] The device transmits the recorded motion and physique data to a server. The data is transmitted using a secure protocol (e.g., HTTPS).

[0927] The server inputs the received data into an AI model, built using deep learning frameworks (e.g. TensorFlow or PyTorch), that compares the user's movements with those of professional athletes of a similar build. The server generates the comparison results and identifies corrections to the movements.

[0928] The server sends the identified corrections to the terminal, which then presents the corrections to the user through an application on the device, such as a smartphone or tablet. For example, specific advice such as "It would be better if you increased the angle of your bat swing a little more" is displayed.

[0929] In addition, the device inputs the user's facial expressions and tone of voice into the emotion engine, which uses Affectiva and Microsoft Azure Emotion API to recognize the user's emotions in real time. The recognition results are stored on the device.

[0930] The device sends the recognized emotion information to the server. The server reevaluates the AI ​​model taking the emotion information into account and suggests modifications that are easy for the user to accept. For example, if the user feels frustrated, the server generates a suggestion such as "First, relax, then be aware of the release point" and sends it to the device. The device displays this suggestion to the user.

[0931] Examples

[0932] Example 1: Improving baseball batting form

[0933] The user uses the Structure Sensor to measure their physique and a GoPro camera to record their batting form. The device sends this data to the server. The server uses TensorFlow to compare the batting form with that of professional baseball players and suggests through a smartphone app that the user "increase the bat swing angle a little more." If the user is feeling frustrated, the emotion engine recognizes this and the server suggests, "First, relax, and then try to be conscious of your swing angle."

[0934] Example 2: Improving pitching form

[0935] The user uses a Kinect to measure their physique and a Vicon motion capture system to record their pitching form. The device sends this data to the server. The server uses PyTorch to compare the form with that of professional pitchers and suggests through a tablet app that the user "should move the release point a little further forward." If the user is feeling frustrated, the emotion engine recognizes this and the server suggests, "First, relax, and then try to be conscious of the release point."

[0936] Examples of prompt statements

[0937] "The user uses a 3D body scanning device to measure their physique and records their batting form with a camera. The AI ​​uses TensorFlow to compare their form with that of professional baseball players and suggests corrections via a smartphone app. If the user is frustrated, the emotion engine recognizes this and the AI ​​suggests corrections in a way that is easy for the user to accept."

[0938] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0939] Step 1:

[0940] Users measure their own physique using a 3D body scanning device. Specifically, users acquire physique data using the "Structure Sensor" or "Kinect." The input is the dimensions and shape of the user's body, and the output is physique data as a 3D model. This data is stored on the device.

[0941] Step 2:

[0942] The user performs a specific movement (e.g. batting or pitching a baseball). The user records the movement using a GoPro camera or a Vicon motion capture system. The input is the user's movement, and the output is high-resolution video data. This data is stored on the device.

[0943] Step 3:

[0944] The terminal transmits the recorded motion data and physique data to the server. The input is the motion data and physique data, and the output is the data transmission to the server. The data is transmitted using a secure protocol (e.g., HTTPS).

[0945] Step 4:

[0946] The server inputs the received data into the AI ​​model. The AI ​​model is built using TensorFlow and PyTorch, and compares the user's movements with those of professional athletes with a similar physique. The input is movement data and physique data, and the output is the comparison results, including corrections to the movements.

[0947] Step 5:

[0948] The server sends the identified corrections to the terminal. The input is the comparison result, and the output is the transmission of the corrections to the terminal. The terminal presents the corrections to the user through an application on a device such as a smartphone or tablet. For example, specific advice such as "It would be better if you increased the bat swing angle a little more" is displayed.

[0949] Step 6:

[0950] The device inputs the user's facial expressions and tone of voice into the emotion engine. The emotion engine uses "Affectiva" and "Microsoft Azure Emotion API" to recognize the user's emotions in real time. The input is the user's facial expressions and tone of voice, and the output is the recognized emotion information. This information is stored on the device.

[0951] Step 7:

[0952] The device sends the recognized emotional information to the server. The input is emotional information, and the output is the transmission of emotional information to the server. The server reevaluates the AI ​​model taking into account the emotional information and suggests corrections in a way that is easy for the user to accept. For example, if the user feels frustrated, the server generates a suggestion such as "First, relax, and then be aware of the release point," and sends it to the device. The device displays this suggestion to the user.

[0953] (Application example 2)

[0954] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[0955] Conventional motion analysis systems record the physique and movements of users and compare them with the movements of professional athletes to suggest corrections, but they were not designed to optimize the movements of robots working in factories. They also lacked the ability to detect abnormalities in the robot and suggest corrections to its movements based on those abnormalities. This made it difficult to efficiently manage the movements of robots in factories.

[0956] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0957] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user how to modify the movements based on the comparison results, a means for recording the robot's movements and proposing optimal movement patterns, and a means for detecting abnormalities in the robot and proposing how to modify the movements based on that information. This not only improves the user's movements, but also enables efficient management and optimization of the movements of robots in factories.

[0958] "User" refers to an individual who uses the System to measure and analyze their physique and movement.

[0959] "Physique" refers to the physical characteristics and measurements of a User.

[0960] "Specific movement" refers to a specific action or movement performed by a user (e.g., batting or pitching form in baseball).

[0961] "Means of recording" refers to devices or methods that use cameras, sensors, etc. to save the actions of a user or robot as digital data.

[0962] "AI means" refers to a system that uses artificial intelligence to analyze data and output results according to a specific purpose.

[0963] "Deep learning" refers to a machine learning technique that uses multi-layered neural networks to learn from data and extract complex patterns and features.

[0964] A "professional athlete" refers to an athlete who has high skills in a particular sport and engages in the sport professionally.

[0965] "Behavior Modifications" refers to specific changes or adjustments proposed to improve a user's or robot's behavior.

[0966] A "robot" refers to an automated mechanical device that performs tasks in a factory.

[0967] "Abnormality" refers to conditions such as vibrations or temperature increases that deviate from the robot's normal operation.

[0968] "Means for sensing" refers to methods or devices that use sensors or monitoring devices to detect abnormalities.

[0969] An "optimal motion pattern" refers to a series of procedures or methods of robot motion proposed to perform a task efficiently and effectively.

[0970] The embodiment of the present invention will be described. First, a 3D body scanning device is used to measure the physique of a user. Specifically, a 3D scanner such as Intel RealSense is used to obtain physique data of the user. This data is used to accurately record the physical characteristics and dimensions of the user.

[0971] Next, cameras and sensors are used to record specific actions taken by the user. For example, Intel RealSense cameras are used to record user actions with high accuracy. This recorded data is then analyzed by AI tools, which will be described later.

[0972] The recorded movement data is analyzed by AI tools using deep learning such as TensorFlow and Keras. The AI ​​tools compare the user's movements with those of professional athletes with a similar physique and suggest corrections to the movements. These suggestions are presented to the user through an application on a smartphone or tablet.

[0973] Furthermore, the system includes a means for recording the motion of the robot and proposing an optimal motion pattern in order to optimize the motion of the robot working in the factory. The motion of the robot is recorded using a 3D scanner or a camera and analyzed by the AI ​​means. The AI ​​means proposes an optimal motion pattern and makes the robot's motion more efficient.

[0974] In addition, vibration and temperature sensors are used to detect abnormalities in the robot. OpenCV and PyTorch are used to detect abnormalities and propose corrections to the robot's behavior based on that information. This optimizes the robot's behavior and enables it to work more efficiently.

[0975] For example, if a robot assembles parts in a factory and its movements slow down or abnormal vibrations occur, the system records the movement and the AI ​​proposes the optimal movement pattern. If the emotion engine detects an abnormality, it is reflected in the proposal to correct the movement.

[0976] Here is an example of a prompt to be input to the generative AI model:

[0977] "To optimize the movements of robots assembling parts in a factory, AI should suggest optimal movement patterns using data recorded by 3D scans and cameras. Also, detect abnormal vibrations or temperature increases in the robot and suggest movement corrections based on that."

[0978] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0979] Step 1:

[0980] A user uses a 3D body scanning device to obtain physique data.

[0981] Input: User's body

[0982] Output: 3D body scan data

[0983] How it works: The user stands in front of the 3D scanner, which scans the entire body and generates digital data.

[0984] Step 2:

[0985] The user's specific actions are recorded using cameras and sensors.

[0986] Input: User actions

[0987] Output: Operation record data

[0988] Specific movements: The user performs a specific movement (e.g. batting or pitching form) in front of the camera, and the camera records that movement with high accuracy.

[0989] Step 3:

[0990] The server analyzes the recorded motion data using AI means.

[0991] Input: Motion record data, 3D body scan data

[0992] Output: Motion analysis results

[0993] Specific operation: The server uses TensorFlow and Keras to input motion record data and 3D body scan data into an AI model to analyze the user's movements.

[0994] Step 4:

[0995] Based on the results of the behavior analysis, the server suggests to the user how to modify their behavior.

[0996] Input: Motion analysis results

[0997] Output: Proposal for corrective action

[0998] Specific actions: Based on the analysis results, the server generates specific corrections to improve the user's behavior and presents them to the user via a smartphone or tablet application.

[0999] Step 5:

[1000] The robot's movements are recorded using 3D scanners and cameras.

[1001] Input: Robot movement

[1002] Output: Robot operation record data

[1003] Specific actions: As the robot performs a task, 3D scanners and cameras record its movements.

[1004] Step 6:

[1005] The server analyzes the robot's operation record data using AI means.

[1006] Input: Robot motion record data

[1007] Output: Robot motion analysis results

[1008] Specific operation: The server uses TensorFlow and Keras to input the robot's movement record data into an AI model and analyze the robot's movement.

[1009] Step 7:

[1010] The server detects an abnormality in the robot.

[1011] Input: Robot vibration data, temperature data

[1012] Output: Anomaly detection result

[1013] Specific operation: The server analyzes data from vibration and temperature sensors using OpenCV and PyTorch to detect anomalies.

[1014] Step 8:

[1015] The server suggests optimal movement patterns based on the results of the robot's movement analysis and anomaly detection.

[1016] Input: Robot operation analysis results, anomaly detection results

[1017] Output: Optimal motion pattern suggestions

[1018] Specific behavior: The server integrates the analysis results and anomaly detection results, generates specific behavior patterns to optimize the robot's behavior, and applies them to the robot.

[1019] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1020] The data generation model 58 is a so-called generative AI (Artificial Intelligence) model. An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1021] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1022] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1023] [Third embodiment]

[1024] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1025] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[1027] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1028] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[1029] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1031] Fig. 6 shows an example of main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1032] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1034] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1035] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1036] "Example 1"

[1037] In one embodiment of the present invention, a user first measures his or her physique using a 3D body scan. This measurement is performed, for example, using a device that provides a 3D body scan. Next, the user performs a specific movement, such as batting or pitching in baseball. This movement is recorded using a camera, sensor, or the like. The recorded movement is analyzed by AI. Using deep learning, the AI ​​compares the user's movement with that of a professional athlete with a similar physique. Then, based on the comparison results, suggestions are made to the user on how to modify the movement. These suggestions are presented to the user, for example, through an application on a device such as a smartphone or tablet.

[1038] "Example 2"

[1039] In one embodiment of the present invention, a user first measures his or her physique using a 3D body scan. This measurement is performed, for example, using a device that provides a 3D body scan. Next, the user performs a specific movement, such as batting or pitching in baseball. This movement is recorded using a camera, sensor, or the like. The recorded movement is analyzed by AI. Using deep learning, the AI ​​compares the user's movement with that of a professional athlete with a similar physique. Then, based on the comparison results, suggestions are made to the user on how to modify the movement. These suggestions are presented to the user, for example, through an application on a device such as a smartphone or tablet.

[1040] The process flow of each embodiment will be described below.

[1041] "Example 1"

[1042] Step 1: The user measures their physique using a 3D body scan. This measurement is taken, for example, using a device that provides a 3D body scan.

[1043] Step 2: Next, the user performs a specific action, such as batting or pitching a baseball. This action is recorded using cameras and sensors.

[1044] Step 3: The recorded movements are analyzed by AI, which uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[1045] Step 4: Based on the comparison results, the system then suggests modifications to the user's behavior. These suggestions are presented to the user, for example, via an application on a device such as a smartphone or tablet.

[1046] "Example 2"

[1047] Step 1: The user measures their physique using a 3D body scan. This measurement is taken, for example, using a device that provides a 3D body scan.

[1048] Step 2: Next, the user performs a specific action, such as batting or pitching a baseball. This action is recorded using cameras and sensors.

[1049] Step 3: The recorded movements are analyzed by AI, which uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[1050] Step 4: Based on the comparison results, the system then suggests modifications to the user's behavior. These suggestions are presented to the user, for example, via an application on a device such as a smartphone or tablet.

[1051] Example 1

[1052] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1053] Conventional motion analysis systems have had difficulty in accurately measuring and recording a user's physique and movements and providing appropriate feedback. In addition, there was a lack of means to perform highly accurate analysis when comparing a user's movements with those of professional athletes. This made it difficult for users to effectively improve their own movements.

[1054] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1055] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for transmitting the recorded movement data and physique data to the server, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for displaying the suggested corrections on the user's terminal. This allows the user to accurately measure and record their own physique and movements, and obtain specific corrections by comparing them with the movements of professional athletes.

[1056] "User" refers to an individual who uses the system to measure and record their physique and movements and receive feedback.

[1057] "Body Measurements" refers to a User's physical characteristics and measurements, including data measured by means of a 3D body scan or similar means.

[1058] "Movement" refers to a specific physical movement or performance performed by the user, which is recorded using cameras and sensors.

[1059] "Server" refers to a computer system that receives data sent by a User, analyzes it using AI means, and provides the results to the User.

[1060] "3D body scanning" refers to technology and equipment that measures a user's physique in three dimensions and is used to obtain detailed data about the user's body.

[1061] "AI Means" refers to means for analysing a user's movements using artificial intelligence technology and comparing them with the movements of a professional athlete.

[1062] "Deep learning" is a field of artificial intelligence that refers to a technology that uses multi-layer neural networks to learn the characteristics of data and perform advanced analysis and predictions.

[1063] "Fix" refers to specific changes or suggestions suggested to improve a user's experience.

[1064] "Terminal" refers to the device that a user uses to access the system, including smartphones and tablets.

[1065] "Comparison Results" refers to the results of a comparison made by AI means between the User's movements and the movements of a professional athlete, and includes data that serves as the basis for feedback to the User.

[1066] This invention is a system that measures and records a user's physique and movements, analyzes them using AI, and suggests specific movement corrections to the user. A specific embodiment of this system will be described below.

[1067] First, the user measures their physique using a device that provides a 3D body scan, such as Kinect or Structure Sensor, which acquires the user's physique data and stores it on the user's device (smartphone or tablet).

[1068] Next, the user performs a specific movement, such as a batting or pitching form in baseball. This movement is recorded using a smartphone camera or a GoPro. The recorded video data is saved on the user's device.

[1069] The user's device transmits the recorded movement data and physique data to the server. An Internet connection is required for transmission. When the user presses the "Data transmission" button in the application, the device uploads the data to the server.

[1070] The server inputs the received motion data and physique data into the AI ​​model. The AI ​​model uses TensorFlow and PyTorch, and uses deep learning to compare the user's motion with that of a professional athlete with a similar physique. The server inputs the data into the AI ​​model and starts the comparison process. Once the process is complete, the comparison results are generated.

[1071] The server generates corrections for the user's movements based on the results of the comparison with the AI ​​model. These corrections are summarized as specific advice or improvement methods. For example, specific advice such as "You need to rotate your hips faster to increase the swing speed of your batting form" is generated.

[1072] The server sends the generated corrections to the user's device. The user's device displays the received corrections in the application. The user opens the application and checks the proposed corrections. For example, specific advice such as "how to practice to rotate your hips faster" is displayed.

[1073] As a concrete example, consider the case where a user wants to improve their baseball batting form. The user first measures their physique using a 3D body scanning device (e.g. Kinect). Next, they record their batting form using a smartphone camera. This recorded data is input into a deep learning model using TensorFlow and compared with the movements of professional batters. Based on the comparison results, corrections to the user's batting form are presented through a dedicated app.

[1074] An example of a prompt is, "Taking the user's physique data and a video of their batting form as input, compare it with the movements of a professional batter and suggest corrections."

[1075] In this way, users can compare their own movements with those of professionals and get specific corrections.

[1076] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1077] Step 1:

[1078] Users measure their physique using a 3D body scanning device.

[1079] Input: User's body position

[1080] Specific action: The user stands in front of the Kinect and rotates their body according to the instructions.

[1081] Data Processing: The scanning device collects the user's physique data and generates a 3D model.

[1082] Output: The generated physique data is saved on the user's device.

[1083] Step 2:

[1084] The user performs a specific movement (e.g., batting form in baseball) and records that movement.

[1085] Input: User actions

[1086] Specific actions: The user sets the smartphone on a tripod and takes a picture of their batting form.

[1087] Data processing: The camera records the user's actions as video data.

[1088] Output: The recorded video data is stored on the user's device.

[1089] Step 3:

[1090] The user's device transmits the recorded movement data and physical data to a server.

[1091] Input: Movement and body data

[1092] Specific action: The user presses the "Submit Data" button within the application.

[1093] Data processing: The device compresses the data and uploads it to a server via the Internet.

[1094] Output: Data is sent to the server.

[1095] Step 4:

[1096] The server inputs the received movement data and physique data into the AI ​​model.

[1097] Input: Movement and body data

[1098] Specific actions: The server inputs the data into the AI ​​model and begins the comparison process.

[1099] Data calculation: The AI ​​model uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[1100] Output: The comparison results are generated.

[1101] Step 5:

[1102] The server generates corrections to the user's behavior based on the comparison results of the AI ​​model.

[1103] Input: Comparison result

[1104] Specific actions: The server generates specific advice such as "You need to rotate your hips faster to increase the swing speed of your batting form."

[1105] Data processing: Analyze the comparison results and generate corrections in text format.

[1106] Output: The corrections are generated.

[1107] Step 6:

[1108] The server sends the generated modifications to the user's terminal.

[1109] Input: Correction

[1110] Specific operation: The server sends the modifications to the user's device.

[1111] Data processing: Convert the corrections into the appropriate format and send them.

[1112] Output: The corrections are sent to the user's terminal.

[1113] Step 7:

[1114] The user's device will display the received corrections within the application.

[1115] Input: Correction

[1116] What happens: The user opens the application and sees the suggested fixes.

[1117] Data processing: Display the corrections in a user-friendly format.

[1118] Output: User can see the corrections.

[1119] (Application example 1)

[1120] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1121] In conventional factory work, there is a lack of specific feedback to improve the efficiency and safety of workers' movements. As a result, workers continue to make inappropriate movements, which leads to problems of reduced work efficiency and increased physical strain. In addition, there is no system to optimize workers' movements, which makes it difficult to provide appropriate guidance to individual workers.

[1122] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for measuring the physique of the user, a means for recording specific movements performed by the user, an AI means for analyzing the recorded movements and comparing them with movements of workers with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for displaying suggestions for optimizing the movements of factory workers. This makes it possible to provide specific feedback for improving the efficiency and safety of the movements of the workers.

[1123] "User" means an individual who utilizes the System to have their physique and / or movement measured and analyzed.

[1124] "Physique" refers to the physical characteristics and measurements of a user.

[1125] "Movement" refers to a specific physical movement or task performed by a user.

[1126] A "recording means" is a device or method for saving a user's actions as video or data.

[1127] "AI means" means technology that uses artificial intelligence to analyze recorded movements and compare them with other movements.

[1128] "Deep learning" is a type of artificial intelligence, a technology that uses multi-layered neural networks to analyze and learn from data.

[1129] A "means for suggesting modifications" is a method or device for suggesting improvements to a user's operation based on the analysis results.

[1130] A "factory worker" is a worker who performs specific tasks in a factory.

[1131] The "means for displaying suggestions for optimization" refers to a device or method for visually presenting suggestions for improving the efficiency and safety of operations to a user.

[1132] "3D body scanning" is a technology that measures a user's body in three dimensions.

[1133] A system for implementing the present invention includes means for measuring a user's physique, means for recording specific movements performed by the user, AI means for analyzing the recorded movements and comparing them with the movements of workers with a similar physique, means for suggesting to the user corrections to their movements based on the comparison results, and means for displaying suggestions for optimizing the movements of factory workers.

[1134] Hardware and Software Used

[1135] 3D body scanning device: A device for measuring the user's body size in three dimensions.

[1136] Camera: A device used to record user actions. An example is the Logitech C920.

[1137] Smart glasses: A device that visually indicates to the user the correction of their actions. An example is Google Glass.

[1138] Tablet: A device used to display performance corrections and optimization suggestions. An example is the iPad.

[1139] Server: A computer system for processing data and running AI models.

[1140] Software: Using Python, OpenCV, Keras and other program libraries.

[1141] Data processing and calculation

[1142] 1. Acquisition of physique data: The server acquires the user's physique data using a 3D body scanning device. This data represents the user's physical characteristics and dimensions in three dimensions.

[1143] 2. Recording of actions: The server records the user's actions using a camera. The recorded actions are saved as image data.

[1144] 3. Motion analysis: The server inputs the recorded image data and physique data into the AI ​​model to analyze the motion. The AI ​​model uses deep learning to compare the user's motion with that of workers with a similar physique.

[1145] 4. Suggested modifications: The server will suggest modifications to the user based on the analysis results, and these suggestions will be displayed on the smart glasses or tablet.

[1146] Examples

[1147] When a factory worker lifts a heavy object, the movement is recorded using a 3D body scan and a camera, and then analyzed by AI. As a result of the analysis, corrections such as the angle of the waist and the position of the hands when lifting are suggested, allowing the worker to perform the work efficiently and safely.

[1148] Examples of prompt statements

[1149] "Record factory workers lifting heavy objects and feed that into the AI ​​along with their 3D body scan data to compare with efficient movements and suggest corrections."

[1150] The above is an embodiment of the present invention.

[1151] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1152] Step 1:

[1153] The server acquires the user's physique data using a 3D body scanning device. The input includes the user's physical characteristics and dimensions. The data is processed by converting these characteristics and dimensions into a data format that represents them three-dimensionally. The output is the user's physique data.

[1154] Step 2:

[1155] The server records the user's actions using a camera. The input includes the specific actions performed by the user. The data processing includes storing the actions as video data. The output includes image data of the recorded actions.

[1156] Step 3:

[1157] The server inputs the recorded image data and physique data into the AI ​​model and analyzes the movements. The input data includes image data and physique data. For data calculation, the AI ​​model uses deep learning to compare the user's movements with those of workers with a similar physique. The output is the analysis result of the movements.

[1158] Step 4:

[1159] The server proposes to the user corrections to the behavior based on the analysis results. The input includes the analysis results of the behavior. The data processing generates specific correction suggestions. The output is the proposed corrections.

[1160] Step 5:

[1161] The server displays the suggested corrections on the smart glasses or tablet. An input includes the suggested corrections. A specific operation includes generating and sending data for visually displaying the suggested corrections to the smart glasses or tablet. An output includes the suggested corrections that are visually visible to the user.

[1162] The above is the processing flow of this program.

[1163] Example 2

[1164] Next, a second embodiment of the second form will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1165] Conventional motion analysis systems have difficulty in accurately measuring and recording a user's physique and motion, and suggesting appropriate corrections. In addition, there is a lack of means to suggest specific corrections to users, which has led to problems with effective improvement of motion.

[1166] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1167] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements performed by the user, an artificial intelligence means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for presenting the corrections to the user. This makes it possible to accurately measure and record the user's physique and movements, suggest appropriate corrections, and present specific corrections to the user.

[1168] "User" refers to an individual who uses the System to measure and record their physique and movements and receive suggestions for movement modifications.

[1169] "Means for measuring body size" refers to devices or technologies that measure the dimensions and shape of a user's body in three dimensions.

[1170] "Means for recording specific actions" refers to devices or technologies that use cameras or sensors to record actions performed by users.

[1171] "Artificial intelligence means" refers to AI technology used to analyze recorded movement data and compare the movements of users with those of professional athletes.

[1172] "Means for suggesting corrections" refers to a technology that extracts and suggests improvements to the user's actions based on the analysis results by the artificial intelligence means.

[1173] "Means for suggesting corrections" means a device or application that visually or audibly communicates the suggested corrections to the user.

[1174] "3D body scanning" refers to a technology that measures a user's body in three dimensions.

[1175] "Deep learning" refers to a machine learning technique using multiple layers of neural networks used in artificial intelligence tools.

[1176] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1177] The present invention relates to a system that measures a user's physique, records and analyzes specific movements, and suggests corrections to those movements. A specific embodiment of this system will be described below.

[1178] User body measurements

[1179] The user measures his or her physique using a 3D body scanning device. Examples of such devices include a "3D scanner" or a "motion capture system." The user follows the device's instructions to scan his or her physique while rotating 360 degrees. The device processes the scan data in real time and generates the user's physique data. The generated data is sent to a server via wireless communication.

[1180] Recording actions

[1181] Next, the user performs a specific movement, such as batting or pitching a baseball. The user records the movement using a camera or sensor. The hardware used may be a "high-resolution camera" or a "motion capture system." The device generates the recorded video data or motion capture data and sends it to a server.

[1182] Analysis of behavior

[1183] The server inputs the received physique data and movement data into an AI model. This AI model uses deep learning to compare the user's movements with those of professional athletes. The software used is a "deep learning framework." The server extracts corrections for the user's movements from the output of the AI ​​model.

[1184] Suggested behavior modifications

[1185] The server sends the extracted correction points to the device. The device displays the received correction points in a dedicated application. The user can check the correction points through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[1186] Examples

[1187] Example 1: Correcting baseball batting form

[1188] The user measures their physique using a 3D body scanning device and sends the data to the server. After that, a high-resolution camera is used to capture their batting form, and the video data is uploaded to the server. The server analyzes the data using a deep learning framework and extracts corrections that are presented to the user through a dedicated application. The user works to improve their batting form while looking at the application.

[1189] Example 2: Correcting pitching form

[1190] The user uses a 3D scanner to measure their physique and sends the data to the server. The motion capture system then records their pitching form and uploads the data to the server. The server then analyzes the data using a deep learning framework and extracts corrections that are presented to the user through a dedicated application. The user works on improving their pitching form while looking at the application.

[1191] Examples of prompt statements

[1192] Prompt 1: Baseball batting form

[1193] "Please generate an AI model that takes a user's 3D body scan data and video data of their batting form as input, compares it with data from professional baseball players, and suggests corrections."

[1194] Prompt 2: Pitching form

[1195] "Please generate an AI model that takes the user's 3D body scan data and motion capture data of their pitching form as input, compares it with data from professional baseball players, and suggests corrections."

[1196] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1197] Program processing flow

[1198] Step 1: Measuring the user's body size

[1199] The user activates the 3D body scanning device. Following the device's instructions, the user rotates 360 degrees to scan their physique. The device processes the scan data in real time and generates physique data for the user. The generated data is then transmitted to the server via wireless communication.

[1200] Input: User's body scan data

[1201] Data processing: Real-time processing of scan data

[1202] Output: User's physical data

[1203] Step 2: Recording the action

[1204] Using a high-resolution camera and a motion capture system, the user performs a specific movement, such as batting or pitching a baseball. The device records the movement and generates video data or motion capture data. The generated data is sent to the server.

[1205] Input: User actions

[1206] Data processing: Motion recording and data generation

[1207] Output: Video data or motion capture data

[1208] Step 3: Analyze the behavior

[1209] The server inputs the received physique data and movement data into an artificial intelligence model. The artificial intelligence model uses deep learning to compare the user's movements with those of professional athletes. The server extracts corrections for the user's movements from the output of the artificial intelligence model.

[1210] Input: Body size data, movement data

[1211] Data processing: Motion comparison using deep learning

[1212] Output: Behavior fixes

[1213] Step 4: Propose behavior modifications

[1214] The server sends the extracted correction points to the device. The device displays the received correction points in a dedicated application. The user can check the correction points through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[1215] Input: Behavior fixes

[1216] Data processing: Preparation for displaying corrections

[1217] Output: A suggestion for the user to make corrections

[1218] Adding specific actions

[1219] Step 1: Measuring the user's body size

[1220] The user activates the 3D body scanning device and follows the device's instructions to scan their physique. The scan data is processed in real time to generate the user's physique data. The generated data is then transmitted to the server via wireless communication.

[1221] Step 2: Recording the action

[1222] The user sets up a high-resolution camera and records the batting form of a baseball player. The camera records high-resolution video and saves it on the device. The device compresses the saved video data and uploads it to the server.

[1223] Step 3: Analyze the behavior

[1224] The server inputs the received physique data and video data into a deep learning framework. The AI ​​model compares the user's batting form with that of professional baseball players. Features such as joint angles and movement speed are used for the comparison. The server extracts corrections for the user's movements from the output of the AI ​​model.

[1225] Step 4: Propose behavior modifications

[1226] The server sends the extracted corrections in JSON format to the device. The device displays the received corrections in a dedicated application. The user can check the corrections through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[1227] (Application example 2)

[1228] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1229] Conventional optimization of factory robots' movements relied on manual adjustments and experience, making it difficult to achieve efficient and highly accurate optimization. In addition, because individual optimization based on the user's physique or movements was not performed, general-purpose optimization methods were sometimes ineffective. This created a risk of a decline in factory productivity and quality.

[1230] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1231] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user points for correcting the movements based on the comparison results, a means for recording and analyzing the movements of a robot used in the factory, and a means for suggesting points for correcting the movements of the robot. This enables individual optimization based on the user's physique and movements, and makes it possible to efficiently and accurately optimize the movements of factory robots.

[1232] "User" means any individual or legal entity that uses the System to measure and analyze their physique and movements.

[1233] "Physique" refers to the shape and dimensions of a User's body, as measured by means such as a 3D body scan.

[1234] A "specific action" is a specific movement or task performed by a user that is recorded using a camera or sensor.

[1235] "Recording means" refers to devices or methods that use cameras, sensors, etc. to save user actions as data.

[1236] "AI means" refers to technology that uses artificial intelligence to analyze recorded movement data and compare the user's movements with those of professional athletes.

[1237] "Deep learning" is a type of artificial intelligence, a technology that uses multi-layered neural networks to analyze and learn from data.

[1238] A "professional athlete" is an athlete who is professionally active in a particular sport, and is the subject against which the user's movements are compared.

[1239] "Behavior Modifications" are specific improvements suggested to optimize a user's performance.

[1240] A "factory robot" is an automated mechanical device used on a factory production line or in a workshop.

[1241] "Optimization" means adjusting something to the most efficient and effective state for a particular purpose.

[1242] To implement this invention, the following hardware and software are used. The hardware requires a 3D scanner, a camera, a sensor, a server, and a user terminal (a smartphone or a tablet). The software requires Python, OpenCV, Keras, etc.

[1243] First, the user measures his or her own physique using a 3D scanner. The 3D scanner captures the shape and dimensions of the user's body with high precision and stores them as digital data. This data is then sent to a server.

[1244] Next, the user performs a specific action, for example to mimic the action of a robot used in a factory, and the action is recorded using cameras and sensors, and the recorded action data is also sent to the server.

[1245] The server inputs the received 3D scan data and movement data into the AI ​​system. The AI ​​system analyzes the data using deep learning and compares the user's movements with those of professional athletes with a similar physique. Based on the comparison results, the AI ​​system suggests corrections to the user's movements.

[1246] In addition, to optimize the operation of the robots used in the factory, the robots' operation data is also recorded and analyzed by AI means. Based on the analysis results, corrections are proposed to optimize the robot's operation. These suggestions are displayed on the user's terminal.

[1247] As a concrete example, consider optimizing the operation of a welding robot used in a factory. A 3D scanner captures the shape data of the robot, and cameras and sensors record its operation data. This data is input into an AI tool, and suggestions are made on how to correct the welding angle and speed based on the analysis results.

[1248] An example of a prompt sentence to be input into the generative AI model is, "Please input the welding robot's motion data along with the 3D scan data and suggest optimal motion corrections."

[1249] As described above, the present invention enables individual optimization based on the physique and movements of a user, and can optimize the movements of factory robots efficiently and with high accuracy.

[1250] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1251] Step 1:

[1252] Users measure their body size using a 3D scanner.

[1253] Input: User's body

[1254] Data processing: A 3D scanner captures the shape and dimensions of the user's body with high precision and stores them as digital data.

[1255] Output: 3D scan data

[1256] Step 2:

[1257] The user performs a specific action and the action is recorded using cameras and sensors.

[1258] Input: User actions

[1259] Data processing: Cameras and sensors record user actions as video and sensor data.

[1260] Output: Operation data

[1261] Step 3:

[1262] The server receives the 3D scan data and the motion data.

[1263] Input: 3D scan data, motion data

[1264] Data processing: The server receives these data and prepares them for input into the AI ​​means.

[1265] Output: Prepared data

[1266] Step 4:

[1267] The server analyzes the 3D scan data and the motion data using AI means.

[1268] Input: Prepared data

[1269] Data processing: Using a deep learning model, we compare the user's movements with those of professional athletes with a similar physique.

[1270] Output: Analysis results

[1271] Step 5:

[1272] The server then suggests modifications to the user's behavior based on the analysis results.

[1273] Input: Analysis results

[1274] Data Transformation: Use the analysis to generate specific modifications to optimize user behavior.

[1275] Output: suggested fixes

[1276] Step 6:

[1277] Suggested fixes will be displayed on the user's device.

[1278] Input: Suggested fix

[1279] Data processing: Converting the proposal content into a format for display on the user's device.

[1280] Output: The corrections displayed on the user's terminal.

[1281] Step 7:

[1282] The operations of robots used in factories are recorded and transmitted to a server.

[1283] Input: Robot movement

[1284] Data processing: Cameras and sensors record the robot's movements as video and sensor data, and send them to a server.

[1285] Output: Robot motion data

[1286] Step 8:

[1287] The server analyzes the robot's operational data using AI means and suggests modifications for optimization.

[1288] Input: Robot motion data

[1289] Data processing: Using deep learning models, the robot's behavior is analyzed and corrections are generated for optimization.

[1290] Output: Suggested modifications to the robot's behavior

[1291] Step 9:

[1292] Suggestions for correcting the robot's behavior are displayed on the user's device.

[1293] Input: Suggested modifications to the robot's behavior

[1294] Data processing: Converting the proposal content into a format for display on the user's device.

[1295] Output: Robot behavior corrections displayed on the user's device

[1296] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1297] "Example 1"

[1298] In one embodiment of the present invention, a system is provided that includes a means for measuring a user's physique, a means for recording a specific movement performed by the user, an AI means for analyzing the recorded movement and comparing it with the movement of a professional athlete with a similar physique, a means for suggesting to the user movement corrections based on the comparison result, and an emotion engine for recognizing the user's emotions. The emotion engine recognizes emotions from the user's facial expressions and tone of voice, and provides the information to the AI ​​means. The AI ​​means suggests movement corrections taking into account not only the comparison between the user's movement and the movement of the professional athlete, but also the user's emotions.

[1299] For example, if a user is feeling frustrated, the AI ​​solution can take that information into account and suggest modifications in a way that is acceptable to the user. In this way, it is possible to suggest behavior improvements that take the user's emotions into account.

[1300] "Example 2"

[1301] In one embodiment of the present invention, a system is provided that includes a means for measuring a user's physique, a means for recording a specific movement performed by the user, an AI means for analyzing the recorded movement and comparing it with the movement of a professional athlete with a similar physique, a means for suggesting to the user a correction to the movement based on the comparison result, and an emotion engine for recognizing the user's emotions. The emotion engine recognizes emotions from the user's facial expressions and tone of voice, and provides the information to the AI ​​means. The AI ​​means proposes corrections to the movement by taking into account not only the comparison between the user's movement and the movement of the professional athlete, but also the user's emotions. For example, if the user feels frustrated, the AI ​​means proposes corrections in a form that is easy for the user to accept, taking into account the information. In this way, it is possible to propose improvement of the movement by taking into account the user's emotions.

[1302] The process flow of each embodiment will be described below.

[1303] "Example 1"

[1304] Step 1: Measure the user's physique with a 3D body scan.

[1305] Step 2: A user's specific action (e.g., batting or pitching a baseball) is recorded using a video camera or motion sensors.

[1306] Step 3: The recorded movements are analyzed using AI tools and compared to those of professional athletes with a similar physique.

[1307] Step 4: Understand the user's emotions using an emotion engine that recognizes emotions from the user's facial expressions and tone of voice.

[1308] Step 5: The AI ​​tool takes into account the comparison of the user's movements with those of professional athletes and the user's emotions and suggests corrections to the movements.

[1309] Step 6: The proposed behavioral modifications are presented to the user via an application on a device such as a smartphone or tablet.

[1310] "Example 2"

[1311] Step 1: Measure the user's physique with a 3D body scan.

[1312] Step 2: A user's specific action (e.g., batting or pitching a baseball) is recorded using a video camera or motion sensors.

[1313] Step 3: The recorded movements are analyzed using AI tools and compared to those of professional athletes with a similar physique.

[1314] Step 4: Understand the user's emotions using an emotion engine that recognizes emotions from the user's facial expressions and tone of voice.

[1315] Step 5: The AI ​​tool takes into account the comparison of the user's movements with those of professional athletes and the user's emotions and suggests corrections to the movements.

[1316] Step 6: The proposed behavioral modifications are presented to the user via an application on a device such as a smartphone or tablet.

[1317] Example 1

[1318] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1319] Conventional motion improvement systems make suggestions based on the user's physique and motion data, but since the suggestions do not take into account the user's feelings, users may find it difficult to accept the suggestions. In addition, since the points to correct in motion are not specific, it is difficult for users to understand how to improve.

[1320] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1321] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, an artificial intelligence means for analyzing the recorded movements and comparing them with movements of professional athletes with a similar physique, a means for suggesting to the user points for correcting the movements based on the comparison results, a means for recognizing the user's emotions, and a means for suggesting points for correcting the movements taking into account the emotion data. This makes it possible to suggest movement improvements taking into account the user's physique and emotions.

[1322] A "means for measuring a user's physique" is a device or method for measuring a user's physical characteristics and acquiring them as digital data.

[1323] "Means for recording specific actions performed by a user" refers to a device or method that uses video or a sensor to record specific actions performed by a user as digital data.

[1324] "Artificial intelligence means" means software or systems that analyse the recorded data and use specific algorithms to compare the user's movements with other data (e.g. the movements of a professional sportsperson).

[1325] The "means for suggesting points for modification of motion" refers to a device or method that suggests points for improvement or methods for modification of motion to a user based on the analysis results.

[1326] A "means for recognizing a user's emotions" refers to a device or method that analyzes the user's emotions from their facial expressions, tone of voice, etc., and acquires them as digital data.

[1327] The "means for proposing corrections to movements taking emotion data into consideration" refers to a device or method that proposes corrections to movements in a more acceptable form based on the user's emotion data.

[1328] "3D body scanning" is a technology that scans the user's body in three dimensions and obtains detailed physique data.

[1329] "Deep learning" is an artificial intelligence technique that uses multi-layered neural networks to analyze data and learn patterns and features.

[1330] This invention is a system that analyzes the user's physique and movements, compares them with the movements of professional athletes, and suggests corrections to the user's movements. Furthermore, by recognizing the user's emotions and making suggestions taking into account the user's emotion data, it is possible to present corrections to the user's movements in a form that is easy for the user to accept.

[1331] Hardware and Software Used

[1332] 1. User's body measurements

[1333] A user measures their physique using equipment that provides a three-dimensional body scan, which may include, for example, a 3D scanner or a dedicated body scanning application, to obtain detailed physique data, such as the user's height, weight, and body fat percentage.

[1334] 2. Recording the action

[1335] Users use a smartphone camera or a dedicated motion capture device to record a specific movement (e.g., batting or pitching a baseball), and the recorded data includes detailed movement information such as swing speed and angle.

[1336] 3. Transmission of operation data

[1337] The device transmits the recorded movement and physique data to a server in real time over the Internet, where the data is encrypted and uses a secure communication protocol.

[1338] 4. Analysis of movements

[1339] The server inputs the received data into an AI model, which uses deep learning algorithms to compare the user's movements with those of professional athletes. The software used is a deep learning framework such as TensorFlow or PyTorch. For example, it calculates how much the user's swing speed differs from the average speed of a professional player.

[1340] 5. Emotion Recognition

[1341] The device uses an emotion engine that analyzes the user's facial expressions and tone of voice in real time. This emotion engine determines whether the user is frustrated or satisfied and sends that information to a server. The software used is an emotion recognition API (e.g. Microsoft Azure's Emotion API).

[1342] 6. Suggestions for behavior modifications

[1343] The server then suggests to the user how to improve their swing based on the comparison of their movements and their emotion data. For example, if the user feels frustrated, the server might suggest, "Just changing the way you grip the bat a little might make your swing smoother." The server notifies the user of the suggestion through an application on their device, such as a smartphone or tablet.

[1344] Examples

[1345] Example 1: Improving baseball batting form

[1346] The user uses a 3D scanner to measure their physique and records their batting form with their smartphone camera. The device sends the recorded data to a server, which inputs the data into an AI model and compares it with the form of professional baseball players. If the emotion engine detects the user's frustration, the server will make suggestions such as, "Maybe your swing will be smoother if you just change the way you grip the bat a little." The suggestion is notified to the user through a smartphone application.

[1347] Example prompts for generative AI models

[1348] "Please input the user's 3D body scan data and a video of their batting form, compare it with the form of a professional baseball player, and suggest improvements while taking into account the user's emotions."

[1349] In this way, it becomes possible to suggest motion improvements that take into account the user's physique and emotions.

[1350] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1351] Step 1:

[1352] Users measure their physique using a device that provides a 3D body scan. As input, a 3D scanner is used to scan the user's body. As output, detailed physique data is generated, including the user's height, weight, and body fat percentage. This data is then stored on the device.

[1353] Step 2:

[1354] Users record a specific movement (e.g. batting or pitching in baseball) using a smartphone camera or a dedicated motion capture device. As input, the user's movements are captured by the camera or sensors. As output, detailed movement data such as swing speed and angle is generated. This data is stored on the device.

[1355] Step 3:

[1356] The terminal transmits the recorded movement data and physique data to the server. As input, the movement data and physique data stored on the terminal are used. As output, these data are transmitted to the server via the Internet. The data is encrypted and uses a secure communication protocol.

[1357] Step 4:

[1358] The server inputs the received data into the AI ​​model. As input, the motion and physique data sent to the server are used. As output, the AI ​​model generates the results of comparing the user's motion with those of professional athletes. This AI model uses deep learning algorithms and utilizes deep learning frameworks such as TensorFlow and PyTorch.

[1359] Step 5:

[1360] The device uses an emotion engine that analyzes the user's facial expressions and tone of voice in real time. As input, the user's facial and voice data is captured through a camera and microphone. As output, emotion data is generated, such as whether the user is frustrated or satisfied. This data is then sent to a server.

[1361] Step 6:

[1362] The server proposes corrections to the user's movements based on the comparison results of the movements and the emotion data. The comparison results of the AI ​​model and the emotion data are used as inputs. As output, corrections to the user's movements are generated. For example, if the user feels frustrated, the server will suggest, "Maybe your swing will become smoother if you just change the way you grip the bat a little." The suggestion is notified to the user through an application on a device such as a smartphone or tablet.

[1363] (Application example 1)

[1364] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1365] Conventional motion analysis systems could analyze a user's physique and movements, but had the problem of not being able to suggest corrections to movements that took the user's emotions into account. Also, when optimizing the movements of robots working in factories, there was a lack of real-time monitoring of movement efficiency and error rates and suggestions for improvement. This resulted in issues such as reduced movement efficiency for users and robots, preventing optimal performance.

[1366] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1367] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user movement corrections based on the comparison results, an emotion engine for recognizing the user's emotions, a means for suggesting movement corrections taking into account information from the emotion engine, a means for optimizing the robot's movements, a means for monitoring the robot's movement efficiency and error rate, and a means for making improvement suggestions in real time. This makes it possible to suggest movement corrections taking into account the user's emotions, and further to monitor the movement efficiency and error rate of a robot working in a factory in real time, thereby enabling optimal movement performance to be achieved.

[1368] "Means for measuring the user's body size" refers to devices or technologies for accurately measuring the dimensions and shape of the user's body.

[1369] "Means for recording specific actions performed by a user" refers to devices or technologies that use cameras, sensors, etc. to record specific actions performed by a user.

[1370] "AI means for analyzing recorded movements and comparing them with the movements of professional athletes with a similar physique" refers to artificial intelligence technology for analyzing the recorded movement data of a user and comparing it with the movement data of a professional athlete with a similar physique.

[1371] "Means of suggesting to the user points to modify their movements based on the results of the comparison" refers to devices or technologies that suggest points to improve or modify movements to the user based on the results of the movement comparison performed by AI.

[1372] The "emotion engine that recognizes user emotions" is a technology that identifies emotions from the user's facial expressions, tone of voice, etc.

[1373] The "means for proposing modifications to actions while taking into consideration information from an emotion engine" refers to a device or technology that suggests modifications to actions based on the user's emotion information recognized by an emotion engine.

[1374] "Means for optimizing robot operation" refers to devices and technologies that optimize the operation of robots performing work in a factory to make them efficient and effective.

[1375] The "means for monitoring the robot's operational efficiency and error rate" refers to a device or technology that monitors the robot's operational efficiency and error occurrence rate in real time.

[1376] "Means of making improvement suggestions in real time" refers to devices or technologies that analyze robot operation data in real time and immediately suggest improvements.

[1377] A system for implementing this invention includes means for measuring a user's physique, means for recording specific movements performed by the user, AI means for analyzing the recorded movements and comparing them with the movements of a professional athlete with a similar physique, means for suggesting to the user modifications to their movements based on the comparison results, an emotion engine for recognizing the user's emotions, means for suggesting modifications to the movements taking into account information from the emotion engine, means for optimizing the robot's movements, means for monitoring the robot's movement efficiency and error rate, and means for making improvement suggestions in real time.

[1378] Hardware and Software Configuration

[1379] Hardware:

[1380] 3D body scanning device

[1381] Camera (e.g. Logitech C920)

[1382] Computer (e.g. Intel Core i7, 16GB RAM)

[1383] software:

[1384] OpenCV: Motion recording and image processing

[1385] Keras: Loading and predicting deep learning models

[1386] EmotionRecognizer: Emotion recognition library

[1387] Processing flow

[1388] The server first acquires the user's physique data using a 3D body scanning device. Then, it uses a camera to record the specific movements the user makes. The recorded movement data is preprocessed using OpenCV and analyzed with a deep learning model using Keras. The analysis results are compared with the movement data of professional athletes with a similar physique.

[1389] In addition, we use EmotionRecognizer to recognize the user's emotions and propose behavior modifications taking into account the information from the emotion engine. The proposed modifications are presented to the user.

[1390] For robots working in factories, measures are used to optimize the robot's operation. The robot's operation efficiency and error rate are monitored in real time, and improvement suggestions are made. This makes it possible to optimize the robot's operation performance.

[1391] Examples

[1392] For example, if a robot assembling parts in a factory is moving slowly, the AI ​​will analyze its movements and suggest correcting the angle and speed of its movements. Furthermore, if the robot is making frequent errors, it will determine through emotion recognition that it is feeling frustrated and suggest that it should move more slowly.

[1393] Examples of prompt statements

[1394] "To optimize the movements of a robot assembling parts in a factory, design a system that uses 3D body scanning and cameras to record the movements, analyzes them with AI, and suggests optimal movement patterns. In addition, add a function that monitors the robot's movement efficiency and error rate, and suggests improvements in real time."

[1395] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1396] Step 1:

[1397] The server acquires the user's physique data using a 3D body scanning device. As input, it scans the user's body dimensions and shape, and generates 3D physique data as output. This data is used to accurately determine the user's physique.

[1398] Step 2:

[1399] The server uses a camera to record certain actions performed by the user, capturing the actions performed by the user in real time as input, and generating video data of the actions as output, which is used for subsequent action analysis.

[1400] Step 3:

[1401] The server pre-processes the recorded motion data using OpenCV. It receives motion video data as input and produces pre-processed image data as output. This pre-processing includes image resizing and noise removal.

[1402] Step 4:

[1403] The server analyzes the preprocessed image data with a deep learning model using Keras. It receives the preprocessed image data as input and extracts motion features as output. These features are used to analyze the user's motion in detail.

[1404] Step 5:

[1405] The server compares the extracted features with the motion data of professional athletes with a similar build. It receives the user's motion features and the motion data of professional athletes as input, and generates a comparison result as output. This comparison result is used to identify corrections to the user's motion.

[1406] Step 6:

[1407] The server recognizes the user's emotions using EmotionRecognizer. As input, it captures the user's facial expressions and tone of voice during the action, and generates emotion data as output. This emotion data is used to understand the user's emotional state.

[1408] Step 7:

[1409] The server proposes behavior modifications taking into account information from the emotion engine. It receives as input the comparison results and emotion data, and generates as output behavior modifications for the user. The modifications are proposed taking into account the user's emotional state.

[1410] Step 8:

[1411] The server executes a means for optimizing the motion of a robot performing work in a factory, receiving motion data of the robot as input and generating an optimized motion pattern as output. This optimization is performed to improve the efficiency of the robot's motion.

[1412] Step 9:

[1413] The server monitors the robot's operation efficiency and error rate in real time. As input, it receives the robot's operation data in real time, and generates the monitoring results of the operation efficiency and error rate as output. The monitoring results are used to understand the operation status of the robot.

[1414] Step 10:

[1415] The server provides real-time improvement suggestions, taking the monitoring results as input and generating improvement suggestions as output, which are made to optimize the robot's motion performance.

[1416] Example 2

[1417] Next, a second embodiment of the second form will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1418] Conventional motion improvement systems have difficulty accurately measuring the user's physique and motion and providing appropriate feedback. In addition, motion improvement suggestions were not made taking the user's emotions into account, so there was a lack of feedback in a form that made it easy for the user to accept the suggestions. This limited the effectiveness of the user's motion improvement.

[1419] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1420] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for transmitting the recorded movements, an artificial intelligence means for analyzing the recorded movements and comparing them with movements of professional athletes with a similar physique, a means for suggesting to the user how to modify the movements based on the comparison results, a means for recognizing the user's emotions, and a means for suggesting how to modify the movements while taking the recognized emotions into consideration. This makes it possible to accurately measure the user's physique and movements and provide appropriate feedback. Furthermore, since suggestions for movement improvement are made taking the user's emotions into consideration, feedback is provided in a form that makes it easy for the user to accept the suggestions, improving the effectiveness of movement improvement.

[1421] "Means for measuring the user's body size" refers to devices or technologies that measure the dimensions and shape of the user's body in three dimensions.

[1422] "Means for recording specific actions performed by a user" refers to devices or technologies that use video or sensors to record specific actions performed by a user.

[1423] The "means for transmitting the recorded motion" refers to a communication means for transmitting the recorded motion data to a server or other device.

[1424] "Artificial intelligence means" refers to artificial intelligence technology used to analyze recorded movement data and compare the movements of a user with the movements of a professional athlete.

[1425] "Means for suggesting modifications to movements" refers to a device or technology that suggests improvements to movements to a user based on the results of analysis by the artificial intelligence means.

[1426] "Means of recognizing the user's emotions" refers to devices or technologies for recognizing emotions from the user's facial expressions, tone of voice, etc.

[1427] "Means for suggesting modifications to behavior taking into account recognized emotions" refers to devices or technologies that suggest modifications to behavior in a manner that is easy for the user to accept, based on the user's emotional information.

[1428] The present invention is a system that measures a user's physique, records specific movements, analyzes the movements, and suggests corrections. The system can recognize the user's emotions and suggest corrections to movements taking them into account.

[1429] First, the user measures their physique using a 3D body scanning device. Specifically, devices such as the Structure Sensor and Kinect are used. This allows the user's physique data to be acquired and stored on the device.

[1430] Next, the user performs a specific motion (e.g., batting or pitching a baseball). This motion is recorded using a camera or sensors (e.g., a GoPro camera or a Vicon motion capture system). The recorded motion data is stored on the device.

[1431] The device transmits the recorded motion and physique data to a server. The data is transmitted using a secure protocol (e.g., HTTPS).

[1432] The server inputs the received data into an AI model, built using deep learning frameworks (e.g. TensorFlow or PyTorch), that compares the user's movements with those of professional athletes of a similar build. The server generates the comparison results and identifies corrections to the movements.

[1433] The server sends the identified corrections to the terminal, which then presents the corrections to the user through an application on the device, such as a smartphone or tablet. For example, specific advice such as "It would be better if you increased the angle of your bat swing a little more" is displayed.

[1434] In addition, the device inputs the user's facial expressions and tone of voice into the emotion engine, which uses Affectiva and Microsoft Azure Emotion API to recognize the user's emotions in real time. The recognition results are stored on the device.

[1435] The device sends the recognized emotion information to the server. The server reevaluates the AI ​​model taking the emotion information into account and suggests modifications that are easy for the user to accept. For example, if the user feels frustrated, the server generates a suggestion such as "First, relax, then be aware of the release point" and sends it to the device. The device displays this suggestion to the user.

[1436] Examples

[1437] Example 1: Improving baseball batting form

[1438] The user uses the Structure Sensor to measure their physique and a GoPro camera to record their batting form. The device sends this data to the server. The server uses TensorFlow to compare the batting form with that of professional baseball players and suggests through a smartphone app that the user "increase the bat swing angle a little more." If the user is feeling frustrated, the emotion engine recognizes this and the server suggests, "First, relax, and then try to be conscious of your swing angle."

[1439] Example 2: Improving pitching form

[1440] The user uses a Kinect to measure their physique and a Vicon motion capture system to record their pitching form. The device sends this data to the server. The server uses PyTorch to compare the form with that of professional pitchers and suggests through a tablet app that the user "should move the release point a little further forward." If the user is feeling frustrated, the emotion engine recognizes this and the server suggests, "First, relax, and then try to be conscious of the release point."

[1441] Examples of prompt statements

[1442] "The user uses a 3D body scanning device to measure their physique and records their batting form with a camera. The AI ​​uses TensorFlow to compare their form with that of professional baseball players and suggests corrections via a smartphone app. If the user is frustrated, the emotion engine recognizes this and the AI ​​suggests corrections in a way that is easy for the user to accept."

[1443] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1444] Step 1:

[1445] Users measure their own physique using a 3D body scanning device. Specifically, users acquire physique data using the "Structure Sensor" or "Kinect." The input is the dimensions and shape of the user's body, and the output is physique data as a 3D model. This data is stored on the device.

[1446] Step 2:

[1447] The user performs a specific movement (e.g. batting or pitching a baseball). The user records the movement using a GoPro camera or a Vicon motion capture system. The input is the user's movement, and the output is high-resolution video data. This data is stored on the device.

[1448] Step 3:

[1449] The terminal transmits the recorded motion data and physique data to the server. The input is the motion data and physique data, and the output is the data transmission to the server. The data is transmitted using a secure protocol (e.g., HTTPS).

[1450] Step 4:

[1451] The server inputs the received data into the AI ​​model. The AI ​​model is built using TensorFlow and PyTorch, and compares the user's movements with those of professional athletes with a similar physique. The input is movement data and physique data, and the output is the comparison results, including corrections to the movements.

[1452] Step 5:

[1453] The server sends the identified corrections to the terminal. The input is the comparison result, and the output is the transmission of the corrections to the terminal. The terminal presents the corrections to the user through an application on a device such as a smartphone or tablet. For example, specific advice such as "It would be better if you increased the bat swing angle a little more" is displayed.

[1454] Step 6:

[1455] The device inputs the user's facial expressions and tone of voice into the emotion engine. The emotion engine uses "Affectiva" and "Microsoft Azure Emotion API" to recognize the user's emotions in real time. The input is the user's facial expressions and tone of voice, and the output is the recognized emotion information. This information is stored on the device.

[1456] Step 7:

[1457] The device sends the recognized emotional information to the server. The input is emotional information, and the output is the transmission of emotional information to the server. The server reevaluates the AI ​​model taking into account the emotional information and suggests corrections in a way that is easy for the user to accept. For example, if the user feels frustrated, the server generates a suggestion such as "First, relax, and then be aware of the release point," and sends it to the device. The device displays this suggestion to the user.

[1458] (Application example 2)

[1459] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1460] Conventional motion analysis systems record the physique and movements of users and compare them with the movements of professional athletes to suggest corrections, but they were not designed to optimize the movements of robots working in factories. They also lacked the ability to detect abnormalities in the robot and suggest corrections to its movements based on those abnormalities. This made it difficult to efficiently manage the movements of robots in factories.

[1461] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1462] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user how to modify the movements based on the comparison results, a means for recording the robot's movements and proposing optimal movement patterns, and a means for detecting abnormalities in the robot and proposing how to modify the movements based on that information. This not only improves the user's movements, but also enables efficient management and optimization of the movements of robots in factories.

[1463] "User" refers to an individual who uses the System to measure and analyze their physique and movement.

[1464] "Physique" refers to the physical characteristics and measurements of a User.

[1465] "Specific movement" refers to a specific action or movement performed by a user (e.g., batting or pitching form in baseball).

[1466] "Means of recording" refers to devices or methods that use cameras, sensors, etc. to save the actions of a user or robot as digital data.

[1467] "AI means" refers to a system that uses artificial intelligence to analyze data and output results according to a specific purpose.

[1468] "Deep learning" refers to a machine learning technique that uses multi-layered neural networks to learn from data and extract complex patterns and features.

[1469] A "professional athlete" refers to an athlete who has high skills in a particular sport and engages in the sport professionally.

[1470] "Behavior Modifications" refers to specific changes or adjustments proposed to improve a user's or robot's behavior.

[1471] A "robot" refers to an automated mechanical device that performs tasks in a factory.

[1472] "Abnormality" refers to conditions such as vibrations or temperature increases that deviate from the robot's normal operation.

[1473] "Means for sensing" refers to methods or devices that use sensors or monitoring devices to detect abnormalities.

[1474] An "optimal motion pattern" refers to a series of procedures or methods of robot motion proposed to perform a task efficiently and effectively.

[1475] The embodiment of the present invention will be described. First, a 3D body scanning device is used to measure the physique of a user. Specifically, a 3D scanner such as Intel RealSense is used to obtain physique data of the user. This data is used to accurately record the physical characteristics and dimensions of the user.

[1476] Next, cameras and sensors are used to record specific actions taken by the user. For example, Intel RealSense cameras are used to record user actions with high accuracy. This recorded data is then analyzed by AI tools, which will be described later.

[1477] The recorded movement data is analyzed by AI tools using deep learning such as TensorFlow and Keras. The AI ​​tools compare the user's movements with those of professional athletes with a similar physique and suggest corrections to the movements. These suggestions are presented to the user through an application on a smartphone or tablet.

[1478] Furthermore, the system includes a means for recording the motion of the robot and proposing an optimal motion pattern in order to optimize the motion of the robot working in the factory. The motion of the robot is recorded using a 3D scanner or a camera and analyzed by the AI ​​means. The AI ​​means proposes an optimal motion pattern and makes the robot's motion more efficient.

[1479] In addition, vibration and temperature sensors are used to detect abnormalities in the robot. OpenCV and PyTorch are used to detect abnormalities and propose corrections to the robot's behavior based on that information. This optimizes the robot's behavior and enables it to work more efficiently.

[1480] For example, if a robot assembles parts in a factory and its movements slow down or abnormal vibrations occur, the system records the movement and the AI ​​proposes the optimal movement pattern. If the emotion engine detects an abnormality, it is reflected in the proposal to correct the movement.

[1481] Here is an example of a prompt to be input to the generative AI model:

[1482] "To optimize the movements of robots assembling parts in a factory, AI should suggest optimal movement patterns using data recorded by 3D scans and cameras. Also, detect abnormal vibrations or temperature increases in the robot and suggest movement corrections based on that."

[1483] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1484] Step 1:

[1485] A user uses a 3D body scanning device to obtain physique data.

[1486] Input: User's body

[1487] Output: 3D body scan data

[1488] How it works: The user stands in front of the 3D scanner, which scans the entire body and generates digital data.

[1489] Step 2:

[1490] The user's specific actions are recorded using cameras and sensors.

[1491] Input: User actions

[1492] Output: Operation record data

[1493] Specific movements: The user performs a specific movement (e.g. batting or pitching form) in front of the camera, and the camera records that movement with high accuracy.

[1494] Step 3:

[1495] The server analyzes the recorded motion data using AI means.

[1496] Input: Motion record data, 3D body scan data

[1497] Output: Motion analysis results

[1498] Specific operation: The server uses TensorFlow and Keras to input motion record data and 3D body scan data into an AI model to analyze the user's movements.

[1499] Step 4:

[1500] Based on the results of the behavior analysis, the server suggests to the user how to modify their behavior.

[1501] Input: Motion analysis results

[1502] Output: Proposal for corrective action

[1503] Specific actions: Based on the analysis results, the server generates specific corrections to improve the user's behavior and presents them to the user via a smartphone or tablet application.

[1504] Step 5:

[1505] The robot's movements are recorded using 3D scanners and cameras.

[1506] Input: Robot movement

[1507] Output: Robot operation record data

[1508] Specific actions: As the robot performs a task, 3D scanners and cameras record its movements.

[1509] Step 6:

[1510] The server analyzes the robot's operation record data using AI means.

[1511] Input: Robot motion record data

[1512] Output: Robot motion analysis results

[1513] Specific operation: The server uses TensorFlow and Keras to input the robot's movement record data into an AI model and analyze the robot's movement.

[1514] Step 7:

[1515] The server detects an abnormality in the robot.

[1516] Input: Robot vibration data, temperature data

[1517] Output: Anomaly detection result

[1518] Specific operation: The server analyzes data from vibration and temperature sensors using OpenCV and PyTorch to detect anomalies.

[1519] Step 8:

[1520] The server suggests optimal movement patterns based on the results of the robot's movement analysis and anomaly detection.

[1521] Input: Robot operation analysis results, anomaly detection results

[1522] Output: Optimal motion pattern suggestions

[1523] Specific behavior: The server integrates the analysis results and anomaly detection results, generates specific behavior patterns to optimize the robot's behavior, and applies them to the robot.

[1524] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1525] The data generation model 58 is a so-called generative AI (Artificial Intelligence) model. An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1526] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1527] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1528] [Fourth embodiment]

[1529] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1530] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1531] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34.

[1532] In addition, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a Wide Area Network (WAN) and / or a Local Area Network (LAN).

[1533] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1534] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[1535] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1536] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1537] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1538] Fig. 8 shows an example of main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1539] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1540] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1541] In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1542] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1543] "Example 1"

[1544] In one embodiment of the present invention, a user first measures his or her physique using a 3D body scan. This measurement is performed, for example, using a device that provides a 3D body scan. Next, the user performs a specific movement, such as batting or pitching in baseball. This movement is recorded using a camera, sensor, or the like. The recorded movement is analyzed by AI. Using deep learning, the AI ​​compares the user's movement with that of a professional athlete with a similar physique. Then, based on the comparison results, suggestions are made to the user on how to modify the movement. These suggestions are presented to the user, for example, through an application on a device such as a smartphone or tablet.

[1545] "Example 2"

[1546] In one embodiment of the present invention, a user first measures his or her physique using a 3D body scan. This measurement is performed, for example, using a device that provides a 3D body scan. Next, the user performs a specific movement, such as batting or pitching in baseball. This movement is recorded using a camera, sensor, or the like. The recorded movement is analyzed by AI. Using deep learning, the AI ​​compares the user's movement with that of a professional athlete with a similar physique. Then, based on the comparison results, suggestions are made to the user on how to modify the movement. These suggestions are presented to the user, for example, through an application on a device such as a smartphone or tablet.

[1547] The process flow of each embodiment will be described below.

[1548] "Example 1"

[1549] Step 1: The user measures their physique using a 3D body scan. This measurement is taken, for example, using a device that provides a 3D body scan.

[1550] Step 2: Next, the user performs a specific action, such as batting or pitching a baseball. This action is recorded using cameras and sensors.

[1551] Step 3: The recorded movements are analyzed by AI, which uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[1552] Step 4: Based on the comparison results, the system then suggests modifications to the user's behavior. These suggestions are presented to the user, for example, via an application on a device such as a smartphone or tablet.

[1553] "Example 2"

[1554] Step 1: The user measures their physique using a 3D body scan. This measurement is taken, for example, using a device that provides a 3D body scan.

[1555] Step 2: Next, the user performs a specific action, such as batting or pitching a baseball. This action is recorded using cameras and sensors.

[1556] Step 3: The recorded movements are analyzed by AI, which uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[1557] Step 4: Based on the comparison results, the system then suggests modifications to the user's behavior. These suggestions are presented to the user, for example, via an application on a device such as a smartphone or tablet.

[1558] Example 1

[1559] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1560] Conventional motion analysis systems have had difficulty in accurately measuring and recording a user's physique and movements and providing appropriate feedback. In addition, there was a lack of means to perform highly accurate analysis when comparing a user's movements with those of professional athletes. This made it difficult for users to effectively improve their own movements.

[1561] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1562] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements made by the user, a means for transmitting the recorded movement data and physique data to the server, an AI means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for displaying the suggested corrections on the user's terminal. This allows the user to accurately measure and record their own physique and movements, and obtain specific corrections by comparing them with the movements of professional athletes.

[1563] "User" refers to an individual who uses the system to measure and record their physique and movements and receive feedback.

[1564] "Body Measurements" refers to a User's physical characteristics and measurements, including data measured by means of a 3D body scan or similar means.

[1565] "Movement" refers to a specific physical movement or performance performed by the user, which is recorded using cameras and sensors.

[1566] "Server" refers to a computer system that receives data sent by a User, analyzes it using AI means, and provides the results to the User.

[1567] "3D body scanning" refers to technology and equipment that measures a user's physique in three dimensions and is used to obtain detailed data about the user's body.

[1568] "AI Means" refers to means for analysing a user's movements using artificial intelligence technology and comparing them with the movements of a professional athlete.

[1569] "Deep learning" is a field of artificial intelligence that refers to a technology that uses multi-layer neural networks to learn the characteristics of data and perform advanced analysis and predictions.

[1570] "Fix" refers to specific changes or suggestions suggested to improve a user's experience.

[1571] "Terminal" refers to the device that a user uses to access the system, including smartphones and tablets.

[1572] "Comparison Results" refers to the results of a comparison made by AI means between the User's movements and the movements of a professional athlete, and includes data that serves as the basis for feedback to the User.

[1573] This invention is a system that measures and records a user's physique and movements, analyzes them using AI, and suggests specific movement corrections to the user. A specific embodiment of this system will be described below.

[1574] First, the user measures his or her physique using a device that provides a 3D body scan, such as Kinect or Structure Sensor, which acquires the user's physique data and stores it on the user's device (smartphone or tablet).

[1575] Next, the user performs a specific movement, such as a batting or pitching form in baseball. This movement is recorded using a smartphone camera or a GoPro. The recorded video data is saved on the user's device.

[1576] The user's device transmits the recorded movement data and physique data to the server. An Internet connection is required for transmission. When the user presses the "Data transmission" button in the application, the device uploads the data to the server.

[1577] The server inputs the received motion data and physique data into the AI ​​model. The AI ​​model uses TensorFlow and PyTorch, and uses deep learning to compare the user's motion with that of a professional athlete with a similar physique. The server inputs the data into the AI ​​model and starts the comparison process. Once the process is complete, the comparison results are generated.

[1578] The server generates corrections for the user's movements based on the results of the comparison with the AI ​​model. These corrections are summarized as specific advice or improvement methods. For example, specific advice such as "You need to rotate your hips faster to increase the swing speed of your batting form" is generated.

[1579] The server sends the generated corrections to the user's device. The user's device displays the received corrections in the application. The user opens the application and checks the proposed corrections. For example, specific advice such as "how to practice to rotate your hips faster" is displayed.

[1580] As a concrete example, consider the case where a user wants to improve their baseball batting form. The user first measures their physique using a 3D body scanning device (e.g. Kinect). Next, they record their batting form using a smartphone camera. This recorded data is input into a deep learning model using TensorFlow and compared with the movements of professional batters. Based on the comparison results, corrections to the user's batting form are presented through a dedicated app.

[1581] An example of a prompt is, "Taking the user's physique data and a video of their batting form as input, compare it with the movements of a professional batter and suggest corrections."

[1582] In this way, users can compare their own movements with those of professionals and get specific corrections.

[1583] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1584] Step 1:

[1585] Users measure their physique using a 3D body scanning device.

[1586] Input: User's body position

[1587] Specific action: The user stands in front of the Kinect and rotates their body according to the instructions.

[1588] Data Processing: The scanning device collects the user's physique data and generates a 3D model.

[1589] Output: The generated physique data is saved on the user's device.

[1590] Step 2:

[1591] The user performs a specific movement (e.g., batting form in baseball) and records that movement.

[1592] Input: User actions

[1593] Specific actions: The user sets the smartphone on a tripod and takes a picture of their batting form.

[1594] Data processing: The camera records the user's actions as video data.

[1595] Output: The recorded video data is stored on the user's device.

[1596] Step 3:

[1597] The user's device transmits the recorded movement data and physical data to a server.

[1598] Input: Movement and body data

[1599] Specific action: The user presses the "Submit Data" button within the application.

[1600] Data processing: The device compresses the data and uploads it to a server via the Internet.

[1601] Output: Data is sent to the server.

[1602] Step 4:

[1603] The server inputs the received movement data and physique data into the AI ​​model.

[1604] Input: Movement and body data

[1605] Specific actions: The server inputs the data into the AI ​​model and begins the comparison process.

[1606] Data calculation: The AI ​​model uses deep learning to compare the user's movements with those of professional athletes with a similar physique.

[1607] Output: The comparison results are generated.

[1608] Step 5:

[1609] The server generates corrections to the user's behavior based on the comparison results of the AI ​​model.

[1610] Input: Comparison result

[1611] Specific actions: The server generates specific advice such as "You need to rotate your hips faster to increase the swing speed of your batting form."

[1612] Data processing: Analyze the comparison results and generate corrections in text format.

[1613] Output: The corrections are generated.

[1614] Step 6:

[1615] The server sends the generated modifications to the user's terminal.

[1616] Input: Correction

[1617] Specific operation: The server sends the modifications to the user's device.

[1618] Data processing: Convert the corrections into the appropriate format and send them.

[1619] Output: The corrections are sent to the user's terminal.

[1620] Step 7:

[1621] The user's device will display the received corrections within the application.

[1622] Input: Correction

[1623] What happens: The user opens the application and sees the suggested fixes.

[1624] Data processing: Display the corrections in a user-friendly format.

[1625] Output: User can see the corrections.

[1626] (Application example 1)

[1627] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1628] In conventional factory work, there is a lack of specific feedback to improve the efficiency and safety of workers' movements. As a result, workers continue to make inappropriate movements, which leads to problems of reduced work efficiency and increased physical strain. In addition, there is no system to optimize workers' movements, which makes it difficult to provide appropriate guidance to individual workers.

[1629] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for measuring the physique of the user, a means for recording specific movements performed by the user, an AI means for analyzing the recorded movements and comparing them with movements of workers with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for displaying suggestions for optimizing the movements of factory workers. This makes it possible to provide specific feedback for improving the efficiency and safety of the movements of the workers.

[1630] "User" means an individual who utilizes the System to have their physique and / or movement measured and analyzed.

[1631] "Physique" refers to the physical characteristics and measurements of a user.

[1632] "Movement" refers to a specific physical movement or task performed by a user.

[1633] A "recording means" is a device or method for saving a user's actions as video or data.

[1634] "AI means" means technology that uses artificial intelligence to analyze recorded movements and compare them with other movements.

[1635] "Deep learning" is a type of artificial intelligence, a technology that uses multi-layered neural networks to analyze and learn from data.

[1636] A "means for suggesting modifications" is a method or device for suggesting improvements to a user's operation based on the analysis results.

[1637] A "factory worker" is a worker who performs specific tasks in a factory.

[1638] The "means for displaying suggestions for optimization" refers to a device or method for visually presenting suggestions for improving the efficiency and safety of operations to a user.

[1639] "3D body scanning" is a technology that measures a user's body in three dimensions.

[1640] A system for implementing the present invention includes means for measuring a user's physique, means for recording specific movements performed by the user, AI means for analyzing the recorded movements and comparing them with the movements of workers with a similar physique, means for suggesting to the user corrections to their movements based on the comparison results, and means for displaying suggestions for optimizing the movements of factory workers.

[1641] Hardware and Software Used

[1642] 3D body scanning device: A device for measuring the user's body size in three dimensions.

[1643] Camera: A device used to record user actions. An example is the Logitech C920.

[1644] Smart glasses: A device that visually indicates to the user the correction of their actions. An example is Google Glass.

[1645] Tablet: A device used to display performance corrections and optimization suggestions. An example is the iPad.

[1646] Server: A computer system for processing data and running AI models.

[1647] Software: Using Python, OpenCV, Keras and other program libraries.

[1648] Data processing and calculation

[1649] 1. Acquisition of physique data: The server acquires the user's physique data using a 3D body scanning device. This data represents the user's physical characteristics and dimensions in three dimensions.

[1650] 2. Recording of actions: The server records the user's actions using a camera. The recorded actions are saved as image data.

[1651] 3. Motion analysis: The server inputs the recorded image data and physique data into the AI ​​model to analyze the motion. The AI ​​model uses deep learning to compare the user's motion with that of workers with a similar physique.

[1652] 4. Suggested modifications: The server will suggest modifications to the user based on the analysis results, and these suggestions will be displayed on the smart glasses or tablet.

[1653] Examples

[1654] When a factory worker lifts a heavy object, the movement is recorded using a 3D body scan and a camera, and then analyzed by AI. As a result of the analysis, corrections such as the angle of the waist and the position of the hands when lifting are suggested, allowing the worker to perform the work efficiently and safely.

[1655] Examples of prompt statements

[1656] "Record factory workers lifting heavy objects and feed that into the AI ​​along with their 3D body scan data to compare with efficient movements and suggest corrections."

[1657] The above is an embodiment of the present invention.

[1658] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1659] Step 1:

[1660] The server acquires the user's physique data using a 3D body scanning device. The input includes the user's physical characteristics and dimensions. The data is processed by converting these characteristics and dimensions into a data format that represents them three-dimensionally. The output is the user's physique data.

[1661] Step 2:

[1662] The server records the user's actions using a camera. The input includes the specific actions performed by the user. The data processing includes storing the actions as video data. The output includes image data of the recorded actions.

[1663] Step 3:

[1664] The server inputs the recorded image data and physique data into the AI ​​model and analyzes the movements. The input data includes image data and physique data. For data calculation, the AI ​​model uses deep learning to compare the user's movements with those of workers with a similar physique. The output is the analysis result of the movements.

[1665] Step 4:

[1666] The server proposes to the user corrections to the behavior based on the analysis results. The input includes the analysis results of the behavior. The data processing generates specific correction suggestions. The output is the proposed corrections.

[1667] Step 5:

[1668] The server displays the suggested corrections on the smart glasses or tablet. An input includes the suggested corrections. A specific operation includes generating and sending data for visually displaying the suggested corrections to the smart glasses or tablet. An output includes the suggested corrections that are visually visible to the user.

[1669] The above is the processing flow of this program.

[1670] Example 2

[1671] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1672] Conventional motion analysis systems have difficulty in accurately measuring and recording a user's physique and motion, and suggesting appropriate corrections. In addition, there is a lack of means to suggest specific corrections to users, which has led to problems with effective improvement of motion.

[1673] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1674] In this invention, the server includes a means for measuring the user's physique, a means for recording specific movements performed by the user, an artificial intelligence means for analyzing the recorded movements and comparing them with those of professional athletes with a similar physique, a means for suggesting to the user corrections to the movements based on the comparison results, and a means for presenting the corrections to the user. This makes it possible to accurately measure and record the user's physique and movements, suggest appropriate corrections, and present specific corrections to the user.

[1675] "User" refers to an individual who uses the System to measure and record their physique and movements and receive suggestions for movement modifications.

[1676] "Means for measuring body size" refers to devices or technologies that measure the dimensions and shape of a user's body in three dimensions.

[1677] "Means for recording specific actions" refers to devices or technologies that use cameras or sensors to record actions performed by users.

[1678] "Artificial intelligence means" refers to AI technology used to analyze recorded movement data and compare the movements of users with those of professional athletes.

[1679] "Means for suggesting corrections" refers to a technology that extracts and suggests improvements to the user's actions based on the analysis results by the artificial intelligence means.

[1680] "Means for suggesting corrections" means a device or application that visually or audibly communicates the suggested corrections to the user.

[1681] "3D body scanning" refers to a technology that measures a user's body in three dimensions.

[1682] "Deep learning" refers to a machine learning technique using multiple layers of neural networks used in artificial intelligence tools.

[1683] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1684] The present invention relates to a system that measures a user's physique, records and analyzes specific movements, and suggests corrections to those movements. A specific embodiment of this system will be described below.

[1685] User body measurements

[1686] The user measures his or her physique using a 3D body scanning device. Examples of such devices include a "3D scanner" or a "motion capture system." The user follows the device's instructions to scan his or her physique while rotating 360 degrees. The device processes the scan data in real time and generates the user's physique data. The generated data is sent to a server via wireless communication.

[1687] Recording actions

[1688] Next, the user performs a specific movement, such as batting or pitching a baseball. The user records the movement using a camera or sensor. The hardware used may be a "high-resolution camera" or a "motion capture system." The device generates the recorded video data or motion capture data and sends it to a server.

[1689] Analysis of behavior

[1690] The server inputs the received physique data and movement data into an AI model. This AI model uses deep learning to compare the user's movements with those of professional athletes. The software used is a "deep learning framework." The server extracts corrections for the user's movements from the output of the AI ​​model.

[1691] Suggested behavior modifications

[1692] The server sends the extracted correction points to the device. The device displays the received correction points in a dedicated application. The user can check the correction points through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[1693] Examples

[1694] Example 1: Correcting baseball batting form

[1695] The user measures their physique using a 3D body scanning device and sends the data to the server. After that, a high-resolution camera is used to capture their batting form, and the video data is uploaded to the server. The server analyzes the data using a deep learning framework and extracts corrections that are presented to the user through a dedicated application. The user works to improve their batting form while looking at the application.

[1696] Example 2: Correcting pitching form

[1697] The user uses a 3D scanner to measure their physique and sends the data to the server. The motion capture system then records their pitching form and uploads the data to the server. The server then analyzes the data using a deep learning framework and extracts corrections that are presented to the user through a dedicated application. The user works on improving their pitching form while looking at the application.

[1698] Examples of prompt statements

[1699] Prompt 1: Baseball batting form

[1700] "Please generate an AI model that takes a user's 3D body scan data and video data of their batting form as input, compares it with data from professional baseball players, and suggests corrections."

[1701] Prompt 2: Pitching form

[1702] "Please generate an AI model that takes the user's 3D body scan data and motion capture data of their pitching form as input, compares it with data from professional baseball players, and suggests corrections."

[1703] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1704] Program processing flow

[1705] Step 1: Measuring the user's body size

[1706] The user activates the 3D body scanning device. Following the device's instructions, the user rotates 360 degrees to scan their physique. The device processes the scan data in real time and generates physique data for the user. The generated data is then transmitted to the server via wireless communication.

[1707] Input: User's body scan data

[1708] Data processing: Real-time processing of scan data

[1709] Output: User's physical data

[1710] Step 2: Recording the action

[1711] Using a high-resolution camera and a motion capture system, the user performs a specific movement, such as batting or pitching a baseball. The device records the movement and generates video data or motion capture data. The generated data is sent to the server.

[1712] Input: User actions

[1713] Data processing: Motion recording and data generation

[1714] Output: Video data or motion capture data

[1715] Step 3: Analyze the behavior

[1716] The server inputs the received physique data and movement data into an artificial intelligence model. The artificial intelligence model uses deep learning to compare the user's movements with those of professional athletes. The server extracts corrections for the user's movements from the output of the artificial intelligence model.

[1717] Input: Body size data, movement data

[1718] Data processing: Motion comparison using deep learning

[1719] Output: Behavior fixes

[1720] Step 4: Propose behavior modifications

[1721] The server sends the extracted correction points to the device. The device displays the received correction points in a dedicated application. The user can check the correction points through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[1722] Input: Behavior fixes

[1723] Data processing: Preparation for displaying corrections

[1724] Output: A suggestion for the user to make corrections

[1725] Adding specific actions

[1726] Step 1: Measuring the user's body size

[1727] The user activates the 3D body scanning device and follows the device's instructions to scan their physique. The scan data is processed in real time to generate the user's physique data. The generated data is then transmitted to the server via wireless communication.

[1728] Step 2: Recording the action

[1729] The user sets up a high-resolution camera and records the batting form of a baseball player. The camera records high-resolution video and saves it on the device. The device compresses the saved video data and uploads it to the server.

[1730] Step 3: Analyze the behavior

[1731] The server inputs the received physique data and video data into a deep learning framework. The AI ​​model compares the user's batting form with that of professional baseball players. Features such as joint angles and movement speed are used for the comparison. The server extracts corrections for the user's movements from the output of the AI ​​model.

[1732] Step 4: Propose behavior modifications

[1733] The server sends the extracted corrections in JSON format to the device. The device displays the received corrections in a dedicated application. The user can check the corrections through the application and learn specific ways to improve. For example, specific instructions such as "increase the angle at the start of the bat swing by 10 degrees" are displayed.

[1734] (Application example 2)

[1735] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1736] Conventional optimization of factory robots' movements relied on manual adjustments and experience, making it difficult to achieve efficient and highly accurate optimization. In addition, because individual optimization based on the user's physique or movements was not performed, general-purpose o...

Claims

1. A measuring means for measuring the user's physique; A recording means for recording a specific action performed by the user; an emotion engine that recognizes the emotion of the user; a means for transmitting the physique data measured by the measuring means and the motion data recorded by the recording means to a server; a comparison means for comparing the user's motion with the motion of a specific professional athlete based on the physique data and the motion data, and inputting a prompt sentence that suggests corrections to the user's motion into a generation AI model, thereby comparing the user's physique with that of the professional athlete, and comparing the recorded user's motion with the motion of the specific professional athlete, whose physique is close to that of the user, based on the comparison result; means for suggesting modifications to the user based on the results of the comparison and taking into account information from the emotion engine; means for displaying the proposed modifications on the user's terminal; A system including:

2. The user is a factory worker, The system of claim 1 , wherein the user actions are actions of the factory worker.

3. The system of claim 1 , wherein the comparison means uses deep learning to compare the user's movements with the professional athlete's movements.

Images