System

Abstract

A system is provided.SOLUTION: A system comprising: collecting means for collecting motion data of a player; transferring means for transferring the data collected by the collecting means to a terminal of a user; transmitting means for transmitting the data transferred by the transferring means to a cloud server; generating means for analyzing the data transmitted by the transmitting means and generating optimal feedback for the player in the cloud server; and providing means for transmitting the feedback generated by the generating means to the terminal of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In current sports coaching, especially in student sports, many members tend to receive the same training menu and instruction. However, because each player's physique, skill level, goals, and assigned role are different, a uniform coaching method is not effective enough. As a result, players may experience stunted growth and a decrease in motivation. Furthermore, because it takes a great deal of effort and time for coaches to provide appropriate instruction to each individual player, it is difficult to provide equal instruction to all players. Therefore, a system that provides individually optimized coaching methods is needed. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including a collection means for collecting player motion data, a transfer means for transferring the data collected by the collection means to a user's device, a transmission means for transmitting the data transferred by the transfer means to a cloud server, a generation means in the cloud server for analyzing the data transmitted by the transmission means and generating optimal feedback for the player, and a provision means for transmitting the feedback generated by the generation means to the user's device. This allows for individual players to be provided with individually optimized training methods and advice by comparing their data with that of professional players. Real-time feedback and coaching support are also possible, promoting player growth and helping players experience the joy of sports.

[0006] "Player" refers to the person who actually competes in a sporting activity.

[0007] "Motion data" refers to specific numerical values ​​and records related to the movements of a player, including parameters such as swing speed, angle, ball speed, and number of spins.

[0008] "Collection Implements" means any device or system used to collect Player Movement Data, including sensors and recording devices.

[0009] "Transfer means" refers to a means for transferring the operational data acquired by the collection means to another terminal, including wireless communication technologies such as Bluetooth and WiFi.

[0010] "User devices" refers to electronic devices such as mobile phones, tablets, and computers used by players and coaches.

[0011] "Transmission means" refers to the means for transmitting data from the user's device to the cloud server, including data transfer via an internet connection.

[0012] A "cloud server" refers to a server system for storing, analyzing, and processing data via the Internet.

[0013] "Analysis" refers to the process of understanding collected operational data and transforming it into meaningful information.

[0014] "Generation means" refers to a means for automatically generating optimal feedback and advice for a player based on the analyzed data.

[0015] The "providing means" refers to a means for transmitting the feedback and advice generated by the generating means to the user's terminal. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] 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.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] 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.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] 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.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention proposes a system that collects and analyzes player motion data and provides optimal feedback to each player. This system is realized through the following steps.

[0038] System Configuration

[0039] The main elements of the system are IoT devices (including sensors) dedicated to the player, the user's terminal (smartphone or tablet), and a cloud server.

[0040] Data collection method

[0041] Terminal (IoT device)

[0042] As players practice batting and pitching, sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate. This collection method provides detailed player data.

[0043] User

[0044] Players simply practice as they normally would, with no special operations required. The sensors automatically collect data and transfer it to the user's device during practice.

[0045] Data Transfer Method

[0046] Device (smartphone or tablet)

[0047] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, and a dedicated application is installed on the user's device to receive and manage the data.

[0048] Data transmission method

[0049] Terminal

[0050] Once the user's training session is over, the collected data is sent to the cloud server automatically, without the user needing to be aware of it.

[0051] Data analysis and feedback generation

[0052] server

[0053] The cloud server receives the transmitted data and first checks the data for consistency. If any outliers or missing data are found, corrections are made. Next, the generated AI is used to analyze the player's movement data.

[0054] Specifically, the system compares a player's data with a database of professional players to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional players, the system will identify the specific movements and muscle strength deficiencies that are causing this.

[0055] generation means

[0056] Based on the results of the analysis, the AI ​​generates an individually optimized training menu and feedback, proposing specific improvement methods and daily training plans to the player.

[0057] How to provide feedback

[0058] Device (user's smartphone or tablet)

[0059] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to view it and reflect it in their next practice.

[0060] Coaching Support

[0061] User

[0062] During practice, users can ask the AI ​​generator questions in real time, such as "Is this swing correct?" or "What kind of practice should I do next?", and the AI ​​generator will respond with immediate advice.

[0063] Terminal

[0064] The user's question is sent from the device to the server and analyzed by the generating AI.

[0065] server

[0066] The generative AI generates appropriate answers to questions and sends them to the user's device, allowing the user to receive real-time coaching and maximize the effectiveness of their practice.

[0067] Specific examples

[0068] Example 1: Batting practice

[0069] As a player takes batting practice, IoT sensors collect swing speed and angle. The data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. The user can then review this feedback and consciously adjust their swing angle during their next practice session.

[0070] Example 2: Pitching practice

[0071] As a player practices pitching, IoT sensors collect ball speed and spin rate. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The user then practices while paying attention to the spin rate.

[0072] This system allows players to receive specific and effective feedback in real time to improve their performance, and also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The user begins batting or pitching practice. As the player practices as usual, the IoT sensors collect motion data, such as the player's bat swing speed and angle, as well as the ball's speed and spin rate.

[0076] Step 2:

[0077] The device (IoT device) collects player movement data in real time, and the collected data is transferred to the user's device via Bluetooth or WiFi via sensors attached to the bat and ball.

[0078] Step 3:

[0079] The terminal (user's smartphone or tablet) temporarily stores the movement data received from the IoT device, and a dedicated application displays the data, allowing the user to check their performance during practice.

[0080] Step 4:

[0081] The device (user's smartphone or tablet) sends the accumulated data to a cloud server. This is usually done automatically after the practice session is completed. The data is uploaded to the server via the Internet.

[0082] Step 5:

[0083] The server receives the operational data sent from the device, first checks the consistency of the data, and corrects any abnormal or missing values.

[0084] Step 6:

[0085] The server uses the generated AI to compare the analyzed motion data with a database of experienced professional players, specifically comparing the player's performance, such as swing speed, angle, ball speed, and spin rate, with those of professional players to identify differences and areas for improvement.

[0086] Step 7:

[0087] The server generates personalized, optimized feedback based on the analysis results. The AI ​​generator then suggests specific ways to improve and practice to the player. For example, "Your swing speed is good, but your swing angle is 10 degrees outward. Here's a practice menu to correct that."

[0088] Step 8:

[0089] The server sends the generated feedback to the user's device, where it is provided in a form that can be easily viewed by the user through a dedicated application.

[0090] Step 9:

[0091] The user opens the app and checks the feedback from the AI, understands specific ways to improve, and what to focus on in the next practice session, and practices accordingly.

[0092] Step 10:

[0093] Users can ask the generated AI questions in real time while practicing, such as "Is this swing correct?" or "What kind of practice should I do next?" through the app.

[0094] Step 11:

[0095] The device receives the user's question and sends it to the cloud server, where the application processes the question and forwards it to the server in real time.

[0096] Step 12:

[0097] The server receives questions from users, and the AI ​​generates appropriate answers for those questions, providing specific and applicable advice by referencing the player's data and a database of professional players.

[0098] Step 13:

[0099] The server sends the generated answer to the user's device, providing real-time feedback to the user.

[0100] Step 14:

[0101] The user can check the answers through the application and reflect them in their next action. Real-time coaching support can improve the player's performance.

[0102] Through the above steps, the present invention realizes a system that provides effective individualized optimal instruction to each player and supports the player's growth.

[0103] Example 1

[0104] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0105] Current training systems for players often collect and analyze motion data manually, making it difficult to obtain fast and effective feedback. Furthermore, these systems are unable to provide optimized feedback for individual players, making it difficult to accurately identify areas for improvement. Furthermore, a lack of real-time coaching support means that players are unable to receive immediate advice during practice.

[0106] 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.

[0107] In this invention, the server includes a correction means for checking the consistency of the transmitted data and correcting it, an analysis means for analyzing the corrected data, and a generation means for generating optimal feedback for the player using a generative AI model based on the analyzed data. This automates the entire process from collecting and analyzing player movement data, generating feedback, and providing real-time coaching, making it possible to provide quick, individually optimized feedback to the player.

[0108] "Collection means" refers to devices and sensors used to collect player movement data.

[0109] "Transfer means" refers to the technology or mechanism used to send collected data to the user's device.

[0110] "Transmission means" refers to the technology or mechanism for sending data from the user's device to the cloud server.

[0111] "Correction means" refers to the technology or mechanism used to check the consistency of data sent to the cloud server and correct abnormal values ​​or missing data.

[0112] "Analysis tools" refers to the technology or mechanisms used to analyze the corrected data and compare the motion data with a database of professional athletes or other standards.

[0113] "Generation means" refers to the technology or mechanism that uses a generative AI model to generate optimal feedback for the player based on the analyzed data.

[0114] "Provision means" refers to the technology or mechanism for transmitting the generated feedback to the user's device and providing it to the user.

[0115] "Motion Data" refers to performance data such as swing speed, angle, ball speed, and spin rate collected during a player's training.

[0116] A "generative AI model" is an artificial intelligence model used in the process of data analysis and feedback generation.

[0117] A "prompt" is a question or request input to a generative AI model, and is the text that serves as the basis for the AI ​​to analyze and generate an answer.

[0118] This invention is a system that collects and analyzes player motion data and provides personalized, optimized feedback. This system consists of a player-dedicated IoT device, a user terminal (smartphone or tablet), and a cloud server.

[0119] Data collection method

[0120] Terminal (IoT device)

[0121] When a user practices batting or pitching as a player, IoT sensors collect real-time motion data such as swing speed, angle, ball speed, and spin rate. The sensors are attached to the bat or ball and collect detailed player data during practice.

[0122] User

[0123] Players simply practice as they normally would without any special operations, and the sensors automatically collect and transmit movement data to the user's device during practice.

[0124] Data Transfer Method

[0125] Device (smartphone or tablet)

[0126] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, where a dedicated application is installed to receive and manage the data.

[0127] Data transmission method

[0128] Terminal

[0129] After the practice session, the user's device automatically sends the collected data to the cloud server. This process is transparent to the user. A dedicated application automatically sends the data to the cloud and stores it on the cloud server.

[0130] Data analysis and feedback generation

[0131] server

[0132] The cloud server checks the integrity of the transmitted data and corrects any abnormal values ​​or missing data. The corrected data is then analyzed using analytical tools, and the player's motion data is compared with a database of other players. For example, if a player's swing speed is slower than that of other players, the underlying motions and muscle strength deficiencies are specifically identified.

[0133] Generation AI

[0134] Based on the analysis results, the generative AI model generates personalized training menus and feedback, suggesting specific ways to improve and daily training plans for each player.

[0135] How to provide feedback

[0136] Device (user's smartphone or tablet)

[0137] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to refer to this feedback for their next practice.

[0138] Coaching Support

[0139] User

[0140] If a player has questions during practice, they can ask the generative AI model questions in real time, such as "Is this swing correct?" or "What practice should I do next?"

[0141] Terminal

[0142] The user's question is sent from the device to a cloud server and analyzed by a generative AI model.

[0143] server

[0144] The generative AI model generates appropriate answers to questions and sends them to the user's device, allowing them to receive real-time coaching and maximize the effectiveness of their practice.

[0145] Specific examples

[0146] Example 1: Batting practice

[0147] When a user takes batting practice, IoT sensors collect swing speed and angle. The collected data is transferred to the user's device and sent to a cloud server. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. The user can then use this feedback to consciously adjust their swing angle during their next practice session.

[0148] Example 2: Pitching practice

[0149] When a user practices pitching, the IoT sensor collects the ball's speed and spin rate. The collected data is transferred to the user's device and sent to a cloud server. The cloud server analyzes the data and generates feedback such as "the ball's speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The user can use this feedback to practice while focusing on the spin rate.

[0150] Prompt Sentence Examples

[0151] "A player has good swing speed, but the swing angle is not right. How do I fix it?"

[0152] "My player's ball velocity is adequate, but he lacks spin. Can you tell me some specific practice methods to increase the spin?"

[0153] This system allows users to receive specific and effective feedback in real time to improve their performance, and also allows coaches to provide accurate guidance to each player, which is expected to improve overall performance.

[0154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0155] Step 1: Data collection

[0156] The device uses IoT sensors to collect real-time motion data such as swing speed, angle, ball speed, and spin rate when a player practices batting or pitching. Each data point detected by the sensor (e.g., swing speed) is sent to the user's device via Bluetooth or WiFi. The input is the motion data detected by the sensor, and the output is the data sent to the user's device. Specifically, the sensor records the swing speed every time the player swings the bat and sends it wirelessly to the device.

[0157] Step 2: Data Transfer

[0158] The user's device manages the received motion data using a dedicated application. This application stores the data in local storage immediately after receiving it via Bluetooth or WiFi. The input is motion data from the sensor, and the output is data stored in the device's local storage. Specifically, every time the player swings, data is displayed on the device and immediately accumulated within the application.

[0159] Step 3: Send data

[0160] When the user's device finishes practicing, it automatically sends the collected data to a cloud server. This is often done via Wi-Fi. The input is the movement data stored in the local storage, and the output is the data sent to the cloud server. Specifically, when the practice is finished, the application displays "Data transmission completed."

[0161] Step 4: Data integrity check

[0162] The server checks the integrity of the data it receives and performs corrections if outliers or missing data are found. The input is the raw data sent to the cloud server, and the output is the corrected data that has been checked for integrity. Specifically, if a data point sent to the database is outside the abnormal range, the data is automatically corrected.

[0163] Step 5: Data analysis

[0164] The server analyzes the corrected data and compares the player's motion data with a database of other players. A generative AI model is used for the analysis. The input is the corrected data, and the output is the analysis results. Specifically, the swing speed and angle are compared with other players' data to detect any differences.

[0165] Step 6: Feedback generation

[0166] The server uses a generative AI model based on the analysis results to generate optimal feedback for the player. The input is the analysis results, and the output is the generated feedback. Specific actions are suggested for improvement, such as "your swing speed is good, but your angle is too high."

[0167] Step 7: Provide feedback

[0168] The server sends the generated feedback to the user's device, which then displays it through a dedicated application. The input is the generated feedback, and the output is the feedback displayed on the user's device. Specifically, a notification in the application notifies the user that feedback has been received, allowing them to view the details.

[0169] Step 8: Real-time questions and coaching support

[0170] Users can pose questions to the generative AI model in real time through a dedicated application. For example, they can ask, "Is this swing correct?" This question is sent to the server via the device, and the generative AI model analyzes it. Appropriate advice is generated from the analysis results and sent to the device. The input is the question from the user, and the output is the answer generated by the generative AI model. Specifically, when a question is entered, the server analyzes it and the results are displayed on the device in real time, allowing the user to receive immediate feedback.

[0171] (Application example 1)

[0172] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0173] While automation using robots is progressing in modern factories, issues remain with regard to the efficiency and quality control of robot operations. In particular, there is a demand for systems that can collect and analyze each robot's operation data in real time and provide optimal feedback each time. However, existing systems have problems such as low data collection accuracy and time-consuming analysis. The present invention aims to solve these problems and improve the efficiency and quality of robot operations in factories.

[0174] 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.

[0175] In this invention, the server includes a collection means for collecting robot operation data, a transfer means for transferring the data collected by the collection means to a user's terminal, a transmission means for transmitting the data transferred by the transfer means to a cloud server, a generation means in the cloud server for analyzing the data transmitted by the transmission means and generating optimal feedback for the robot, and a providing means for transmitting the feedback generated by the generation means to the user's terminal, thereby making it possible to collect and analyze robot operation data in real time and provide accurate feedback.

[0176] A "robot" is a mechanical device used to perform automated work in factories and the like, and is a general term for mechanical devices that can execute motion control.

[0177] "Motion data" refers to data relating to the robot's motion, and specifically includes data on motion speed, motion angle, and force.

[0178] "Collection means" refers to a means for collecting motion data using sensors and devices attached to the robot.

[0179] "Transfer means" refers to the means for transferring collected operational data to the user's device, and generally uses communication technologies such as Bluetooth or WiFi.

[0180] The "transmission means" is a means for transmitting the data transferred to the user's terminal by the transfer means to the cloud server.

[0181] A "cloud server" is a remote server device accessible via the Internet, and is a computer resource that can store and analyze large amounts of data.

[0182] The "generation means" is a means for analyzing the data transmitted by the transmission means in the cloud server and generating optimal feedback for the robot.

[0183] The "providing means" is a means for transmitting the feedback generated by the generating means to the user's terminal.

[0184] This invention relates to a system that collects and analyzes the operation data of factory robots and provides individual optimal feedback. This system consists of the following main elements:

[0185] System Configuration

[0186] The system consists of sensors attached to the robot, the user's device (e.g., a smartphone or tablet), and a cloud server.

[0187] Data collection method

[0188] Collection Method

[0189] Sensors attached to the robot collect real-time operational data such as movement speed, movement angle, and force. For example, pressure sensors, acceleration sensors, gyro sensors, etc. can be attached to robots working on factory production lines to obtain various types of data.

[0190] User

[0191] Without any special operations by factory managers or engineers, the robots simply continue to operate as usual, and the sensors automatically collect data and transfer it to the user's device.

[0192] Data Transfer Method

[0193] Transfer Method

[0194] Collected data is transmitted to the user's device in real time via Bluetooth or WiFi, simplifying on-site operation and improving data collection efficiency.

[0195] User

[0196] A dedicated application is installed on the user's device, and this application receives and manages the data. For example, by installing the dedicated application on a smartphone, you can check the operation data of a robot in a factory.

[0197] Data transmission method

[0198] Transmission method

[0199] The user's device sends the collected data to a cloud server. This happens automatically, so the user does not need to be aware of it. For example, a smartphone app automatically uploads data to the cloud.

[0200] Data analysis and feedback generation

[0201] Cloud Server

[0202] The cloud server receives the transmitted data and first checks its integrity. If any outliers or missing data are identified, corrections are made. Next, the data is analyzed using a generative AI model to evaluate the robot's operational efficiency and quality.

[0203] generation means

[0204] Based on the analysis results, the generative AI model identifies the optimal individual movement method and areas for improvement, and generates feedback. For example, if the robot's movement speed is appropriate but the movement angle is inappropriate, it will generate feedback that "the movement angle needs to be corrected."

[0205] How to provide feedback

[0206] Providing means

[0207] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to adjust the robot's behavior based on this feedback.

[0208] Coaching Support

[0209] User

[0210] Users can ask the generative AI model questions in real time, such as "Is this action efficient?" or "What should I do next?", and the generative AI model will respond with immediate advice.

[0211] Prompt Sentence Examples

[0212] For example, you can enter the following prompt:

[0213] "Analyze the robot's motion data and generate feedback to optimize efficiency and reduce errors."

[0214] "Tell me what adjustments I should make next."

[0215] The above system enables robots in the factory to operate efficiently, improving overall productivity and quality.

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] Collecting robot movement data

[0219] Input: Sensors attached to the robot acquire movement data (movement speed, movement angle, force).

[0220] Output: Raw motion speed, motion angle and force dataset.

[0221] Specific behavior: Sensors monitor the robot's behavior in real time and measure and record the necessary physical parameters, for example, pressure sensors measure the robot's movement force, and gyro sensors measure the movement angle.

[0222] Step 2:

[0223] Data Transfer

[0224] Input: Collected behavioral data.

[0225] Output: Data transfer to the user's device.

[0226] How it works: Data collected from sensors is transmitted to the user's device via Bluetooth or WiFi, where a dedicated application is installed. This application receives and temporarily stores the data.

[0227] Step 3:

[0228] Sending data to a cloud server

[0229] Input: Operational data transferred to the user's device.

[0230] Output: Data sent to the cloud server.

[0231] How it works: A dedicated application on the user's device automatically sends the collected data to a cloud server via the Internet, allowing the cloud server to receive the data for analysis.

[0232] Step 4:

[0233] Data Integrity Check

[0234] Input: The motion data sent to the cloud server.

[0235] Output: Data that has been checked for consistency or corrected.

[0236] Specific operation: The cloud server first checks the integrity of the received data. If outliers or missing data are found, the outliers are filtered out and missing values ​​are imputed.

[0237] Step 5:

[0238] Data analysis and feedback generation

[0239] Input: Data whose integrity has been checked.

[0240] Output: Analysis of the robot's operation efficiency and quality, along with optimal feedback.

[0241] Specific operation: A generative AI model installed on a cloud server analyzes the data whose consistency has been confirmed. For example, it evaluates whether the movement speed is appropriate or whether there are any problems with the movement angle, and based on that, it generates areas for improvement and optimal operation methods.

[0242] Step 6:

[0243] Providing Feedback

[0244] Input: Feedback from the generative AI model.

[0245] Output: Feedback sent to the user's device.

[0246] Specific behavior: The cloud server sends the generated feedback to the user's device, where it is displayed by a dedicated application. The user can then adjust the robot's behavior based on this feedback.

[0247] Step 7:

[0248] Real-time coaching support

[0249] Input: The user's question (prompt sentence).

[0250] Output: The answer from the generative AI model.

[0251] Specific Actions: When a user sends a question to the generative AI model in real time, the cloud server analyzes the question, generates an appropriate answer, and delivers it to the user's device. For example, in response to a question such as "Is this action efficient?", it is possible to provide specific feedback such as "The speed of the action is appropriate, but the angle of the action should be improved by 10 degrees."

[0252] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0253] This invention proposes a system that collects and analyzes player movement data, and recognizes and utilizes the user's emotional data to provide personalized and optimal feedback. This system is realized through the following steps.

[0254] System Configuration

[0255] The main elements of the system are a player-dedicated IoT device (including sensors), the user's device (smartphone or tablet), a cloud server, and an emotion engine that recognizes the user's emotions.

[0256] Data collection method

[0257] Terminal (IoT device)

[0258] As players practice batting and pitching, sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate. This collection method provides detailed player data.

[0259] User

[0260] Players simply practice as they normally would, with no special operations required. The sensors automatically collect data and transfer it to the user's device during practice.

[0261] Data Transfer Method

[0262] Device (smartphone or tablet)

[0263] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, and a dedicated application is installed on the user's device to receive and manage the data.

[0264] Data transmission method

[0265] Terminal

[0266] Once the user's training session is over, the collected data is sent to the cloud server automatically, without the user needing to be aware of it.

[0267] Collecting Emotional Data

[0268] Device (smartphone or tablet)

[0269] The user's device is equipped with an emotion engine that acquires emotional data in real time through facial expression recognition and voice analysis, thereby understanding the player's emotional state.

[0270] Data analysis and feedback generation

[0271] server

[0272] The cloud server receives the transmitted motion data and first checks the data for consistency. If any abnormal values ​​or missing data are found, correction processing is performed. Next, the generation AI is used to analyze the player's motion data.

[0273] Specifically, the system compares a player's data with a database of professional players to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional players, the system will identify the specific movements and muscle strength deficiencies that are causing this.

[0274] generation means

[0275] Based on the results of the analysis, the AI ​​generates personalized feedback that is optimized for each player. This generation method suggests specific ways to improve and daily practice plans for each player.

[0276] Feedback adjustment using emotional data

[0277] server

[0278] The cloud server also takes into account the player's emotional data acquired by the emotion engine and customizes the feedback content. For example, if a player feels tired or impatient during practice, it generates encouraging messages or feedback suggesting appropriate breaks.

[0279] How to provide feedback

[0280] Device (user's smartphone or tablet)

[0281] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to view it and reflect it in their next practice.

[0282] Coaching Support

[0283] User

[0284] During practice, users can ask the AI ​​generator questions in real time, such as "Is this swing correct?" or "What kind of practice should I do next?", and the AI ​​generator will respond with immediate advice.

[0285] Terminal

[0286] The user's question is sent from the device to the server and analyzed by the generating AI.

[0287] server

[0288] The generative AI generates appropriate answers to questions and sends them to the user's device, allowing the user to receive real-time coaching and maximize the effectiveness of their practice.

[0289] Specific examples

[0290] Example 1: Batting practice

[0291] As a player takes batting practice, IoT sensors collect swing speed and angle. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. Using an emotion engine, encouraging messages such as "pay attention to this point in your next practice" are also added. The user can then see this and consciously correct their swing angle in their next practice.

[0292] Example 2: Pitching practice

[0293] As the player practices pitching, the IoT sensor collects ball speed and spin rate. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The emotion engine may also suggest things like "Take a short break." This allows the user to practice while paying attention to the spin rate.

[0294] This system not only allows players to receive specific and effective feedback in real time to improve their performance, but also provides appropriate support based on their emotional state. It also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[0295] The processing flow will be explained below.

[0296] Step 1:

[0297] The user begins batting or pitching practice. As the player practices as usual, the IoT sensors collect motion data, such as the player's bat swing speed and angle, as well as the ball's speed and spin rate.

[0298] Step 2:

[0299] The device (IoT device) collects player movement data in real time, and the collected data is transferred to the user's device via Bluetooth or WiFi via sensors attached to the bat and ball.

[0300] Step 3:

[0301] The device (user's smartphone or tablet) temporarily stores the motion data received from the IoT device. A dedicated application displays the data, allowing the user to check their performance during practice. The device's built-in emotion engine also simultaneously collects emotional data through facial recognition and voice analysis of the player.

[0302] Step 4:

[0303] The device (user's smartphone or tablet) transmits the accumulated movement and emotion data to a cloud server. This is usually done automatically after the practice session is completed. The data is uploaded to the server via the internet.

[0304] Step 5:

[0305] The server receives the motion and emotion data sent from the device. First, it checks the consistency of the data and corrects any outliers or missing data. It also verifies that the motion and emotion data are properly linked.

[0306] Step 6:

[0307] The server uses the generated AI to compare the analyzed motion data with a database of experienced professional players, specifically comparing the player's performance, such as swing speed, angle, ball speed, and spin rate, with those of professional players to identify differences and areas for improvement.

[0308] Step 7:

[0309] The server evaluates the player's mental state based on emotional data, and if the player is feeling tired or impatient, this information is reflected in the analysis results.

[0310] Step 8:

[0311] The server generates personalized, optimized feedback based on the analysis results. The AI ​​generator then suggests specific ways to improve and practice to the player. Furthermore, it adjusts the feedback based on emotional data, suggesting a break for tired players and encouraging active practice for energetic players.

[0312] Step 9:

[0313] The server sends the generated feedback to the user's device, where it is provided in a form that can be easily viewed by the user through a dedicated application.

[0314] Step 10:

[0315] The user opens the app and checks the feedback from the AI, understands specific ways to improve, and what to focus on in the next practice session, and practices accordingly.

[0316] Step 11:

[0317] Users can ask the generated AI questions in real time while practicing, such as "Is this swing correct?" or "What kind of practice should I do next?" through the app.

[0318] Step 12:

[0319] The device receives the user's question and sends it to the cloud server, where the application processes the question and forwards it to the server in real time.

[0320] Step 13:

[0321] The server receives questions from users, and the AI ​​generates appropriate answers for those questions, providing specific and applicable advice by referencing the player's data and a database of professional players.

[0322] Step 14:

[0323] The server sends the generated answer to the user's device, providing real-time feedback to the user.

[0324] Step 15:

[0325] The user can check the answers through the application and reflect them in their next action. Real-time coaching support can improve the player's performance.

[0326] By implementing the above steps, the present invention realizes a system that provides effective, individualized guidance to each player and supports their growth. By taking emotion data into consideration, it becomes possible to provide more flexible feedback that is tailored to the player's psychological state.

[0327] Example 2

[0328] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0329] While conventional sports training systems collect and analyze player movement data, it is difficult to grasp the player's emotional state in real time and provide appropriate feedback. Furthermore, the process of generating individually optimized feedback is unable to reflect the player's emotions, making effective instruction difficult.

[0330] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a collection means for collecting player's motion data, a generation means for analyzing the collected data and generating feedback, an emotion collection means for collecting user's emotion data, and an adjustment means for adjusting the feedback using the collected emotion data. This makes it possible to provide individually optimized feedback by taking into account both the player's motion data and emotion data.

[0331] "Collection means" refers to a means for acquiring player movement data, such as a sensor or other device.

[0332] The "transfer means" is a means for transmitting the data acquired by the collection means to the user's terminal.

[0333] "Transmission means" refers to a means for transmitting data from a user's terminal to a cloud server.

[0334] The "generation means" is a means in the cloud server that analyzes the data transmitted by the transmission means and generates optimal feedback for the player.

[0335] "Emotion collection means" refers to means for acquiring user emotional data, and includes facial expression recognition and voice analysis technologies.

[0336] The "adjustment means" is a means for optimizing and adjusting the generated feedback using the emotion data collected by the emotion collection means.

[0337] The "providing means" is a means for transmitting the feedback generated by the generating means and adjusting means to the user's terminal and providing the feedback.

[0338] "Motion data" refers to data that measures the player's movements, including speed, angle, amount of movement, number of rotations, etc.

[0339] "Emotional data" is data that indicates the user's emotional state and is obtained from facial expressions and voice.

[0340] A "cloud server" refers to a server on the Internet used for analyzing and storing data.

[0341] This invention is a system that collects and analyzes player movement data, recognizes and utilizes the user's emotional data, and provides personalized and optimal feedback. This system consists of a player-dedicated IoT device (including sensors), the user's device (smartphone or tablet), a cloud server, and an emotion engine that recognizes the user's emotions.

[0342] Data collection

[0343] Terminal (IoT device) processing:

[0344] As players practice batting and pitching, sensors attached to the bat and ball collect real-time data such as swing speed, angle, ball speed, and spin rate, which is then transmitted to the user's device via Bluetooth or Wi-Fi.

[0345] User Action:

[0346] Players practice as usual, with no special operations required. The sensors automatically collect data and transmit it to the user's device during practice.

[0347] Data Transfer

[0348] Device (smartphone or tablet) processing:

[0349] The collected data is received and managed in real time by a dedicated application via Bluetooth or WiFi. The received data is temporarily stored on the device and can be viewed by the user at any time.

[0350] Data transmission

[0351] Terminal handling:

[0352] Once the user's training is complete, the collected data is sent to the cloud server. This data transfer occurs in the background, so the user does not need to be aware of it.

[0353] Collecting Emotional Data

[0354] Device (smartphone or tablet) processing:

[0355] The user's device is equipped with an emotion engine that uses a camera and microphone to analyze the player's facial expressions and voice, thereby obtaining the player's emotional data in real time.

[0356] Data analysis and feedback generation

[0357] Server Action:

[0358] The cloud server receives the motion data sent from the user's device. First, it checks the data for consistency and corrects any outliers or missing data. It then analyzes the motion data using a generative AI model and compares the player's data with a database of professional golfers to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional golfers, the cloud server will specifically identify the underlying motions and muscle weaknesses.

[0359] Feedback adjustment using emotional data

[0360] Server Action:

[0361] The cloud server also takes into account the player's emotional data acquired by the emotion engine and customizes the content of the feedback. For example, if a player feels fatigued or impatient during practice, it generates encouraging messages or feedback suggesting appropriate breaks.

[0362] Providing Feedback

[0363] Device (user's smartphone or tablet) processing:

[0364] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to incorporate this feedback into their next practice.

[0365] Coaching Support

[0366] User Action:

[0367] Users can ask the generative AI model questions in real time while practicing, such as "Is this swing correct?" or "What practice should I do next?"

[0368] Terminal handling:

[0369] The user's question is sent from the device to a cloud server and analyzed by a generative AI model.

[0370] Server Action:

[0371] The generative AI model generates appropriate answers to the questions, which are then sent back to the user's device, allowing them to receive real-time coaching and maximize the effectiveness of their practice.

[0372] Specific examples

[0373] Batting practice example:

[0374] When a user takes batting practice, sensors collect swing speed and angle, and the data is transferred to the user's device. After practice is completed, the data is sent to a cloud server, which generates analysis results and feedback such as "your swing speed is good, but your angle needs improvement." Based on the user's emotional data, an encouraging message is also added, such as "pay attention to this point in your next practice." This encourages the user to be conscious of their swing angle and try to correct it in their next practice.

[0375] Pitching practice example:

[0376] When a user practices pitching, sensors collect ball speed and spin rate, and the data is transferred to the user's device. After practice, the data is sent to a cloud server, which generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient." Based on emotional data, the feedback may include suggestions such as "Take a short break." The user can then practice with an awareness of the spin rate.

[0377] Prompt Sentence Examples

[0378] Batting Practice Prompts

[0379] "Analyze swing speed and angle data during batting practice and provide feedback on areas for improvement."

[0380] Pitching Practice Prompts

[0381] "Please analyze the ball speed and spin rate data during pitching practice and tell me how to improve."

[0382] This system not only allows players to receive specific and effective feedback in real time to improve their performance, but also provides appropriate support based on their emotional state. It also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[0383] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0384] Step 1:

[0385] Data collection

[0386] Terminal (IoT device) processing:

[0387] 1. Players begin batting and pitching practice.

[0388] 2. Sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate.

[0389] 3. Input: Player Actions

[0390] 4. Output: swing speed, angle, ball speed, spin rate data

[0391] 5. The data acquired by the sensor is transferred to the user's device via Bluetooth or WiFi.

[0392] Step 2:

[0393] Data Transfer

[0394] Device (smartphone or tablet) processing:

[0395] 1. A dedicated application receives data from the sensor in real time via Bluetooth or WiFi.

[0396] 2. The received data is temporarily stored on the device.

[0397] 3. Input: Motion data from sensors

[0398] 4. Output: Temporarily saved data on the device

[0399] 5. Users can check the data at any time through a dedicated application.

[0400] Step 3:

[0401] Data transmission

[0402] Terminal handling:

[0403] 1. After the practice session, the device automatically sends the collected movement data to the cloud server.

[0404] 2. Input: Saved operating data

[0405] 3. Output: Data sent to the cloud server

[0406] 4. Data transmission occurs in the background, so users do not need to be aware of it.

[0407] Step 4:

[0408] Collecting Emotional Data

[0409] Device (smartphone or tablet) processing:

[0410] 1. The user's device is equipped with an emotion engine that uses the camera and microphone to analyze the player's facial expressions and voice.

[0411] 2. Obtain player emotional data in real time through facial expression recognition and voice analysis.

[0412] 3. Input: Player's facial expressions and voice

[0413] 4. Output: Emotion data

[0414] Step 5:

[0415] Data analysis and feedback generation

[0416] Server Action:

[0417] 1. The cloud server receives the operation data sent from the user's device.

[0418] 2. The server checks the consistency of the data and performs correction processing if abnormal values ​​or missing data are found.

[0419] 3. Input: Operation data sent to the cloud server

[0420] 4. Output: Consistent operational data

[0421] 5. A generative AI model analyzes the data and compares the player's data with a database of professional athletes.

[0422] 6. Identify performance gaps and areas for improvement.

[0423] 7. Input: Consistent operational data

[0424] 8. Output: Analysis results (performance differences, areas for improvement)

[0425] 9. The generation means generates individually optimized feedback based on the analysis results.

[0426] 10. Input: Analysis results

[0427] 11. Output: Feedback data

[0428] Step 6:

[0429] Feedback adjustment using emotional data

[0430] Server Action:

[0431] 1. The cloud server receives the player's emotion data obtained by the emotion engine.

[0432] 2. The server analyzes the emotional data and customizes the content of the generated feedback.

[0433] 3. If a player feels fatigued or impatient during practice, generate encouraging messages and feedback suggesting appropriate breaks.

[0434] 4. Input: Emotion data, feedback data

[0435] 5. Output: Customized feedback

[0436] Step 7:

[0437] Providing Feedback

[0438] Device (user's smartphone or tablet) processing:

[0439] 1. Customized feedback is sent from the cloud server to the user's device.

[0440] 2. Feedback is provided to users in real time through a dedicated application.

[0441] 3. Input: Customized Feedback

[0442] 4. Output: Present feedback to the user

[0443] Step 8:

[0444] Coaching Support

[0445] User Action:

[0446] 1. Users can ask questions to the generative AI model in real time while practicing, such as "Is this swing correct?" or "What practice should I do next?"

[0447] 2. Input: User Question

[0448] 3. Output: Query data to the server

[0449] Terminal handling:

[0450] 1. The user's question is sent from the device to the cloud server.

[0451] 2. Input: User's question data

[0452] 3. Output: Data sent to the cloud server

[0453] Server Action:

[0454] 1. The generative AI model receives the question, analyzes it, and generates an appropriate answer.

[0455] 2. The answer is sent back to the user's device.

[0456] 3. Input: User's question data

[0457] 4. Output: Generated answers

[0458] Terminal handling:

[0459] 1. The user's device receives the answer sent from the cloud server.

[0460] 2. Present to the user through a dedicated application.

[0461] 3. Input: Response data from the cloud server

[0462] 4. Output: Answer presented to the user

[0463] (Application example 2)

[0464] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0465] In factories, it is desirable to monitor the operating status of automated equipment such as robot arms in real time to enable efficient maintenance and operation optimization. However, current systems take time to collect and analyze operation data, making it difficult to provide appropriate feedback quickly. In addition, feedback does not take into account the emotional state of the operator, which increases the risk of fatigue and operational errors during work.

[0466] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a collection means for collecting operation data of the robot arm, a transfer means for transferring the data collected by the collection means to a user's terminal, a transmission means for transmitting the data transferred by the transfer means to a cloud server, a generation means in the cloud server for analyzing the data transmitted by the transmission means and generating feedback for optimizing the operation efficiency of the robot arm, a providing means for transmitting the feedback generated by the generation means to the user's terminal, and a means for the generation means to acquire emotion data and adjust the feedback based on the analysis results. This makes it possible to grasp the operating status of automated equipment in a factory in real time and quickly provide appropriate feedback that takes into account the emotional state of operators.

[0467] "Motion data" refers to information such as speeds, angles, and forces generated by a robotic arm or other automated device during operation.

[0468] "Collection means" refers to a device or system for acquiring operational data using a robotic arm or other sensor.

[0469] "Transportation Method" refers to the method or protocol for moving or transmitting collected data to a user's device.

[0470] "Transmission means" refers to a device or method for transmitting data from a user's terminal to a cloud server.

[0471] A "cloud server" refers to a remote server that can be accessed by multiple users via the Internet and is used to store and analyze data.

[0472] "Analysis" refers to the process of processing collected operational data to extract useful information.

[0473] "Generator" refers to a device or algorithm for generating feedback based on the analysis results.

[0474] "Providing means" refers to a device or method for delivering the generated feedback to the user's terminal.

[0475] "Emotional data" refers to data that indicates the emotional state of an operator obtained through facial expressions and voice analysis.

[0476] A "generative AI model" refers to an artificial intelligence model that uses machine learning technology to analyze data and generate optimal feedback.

[0477] A "prompt sentence" refers to an input sentence provided to a generative AI model to perform a specific task.

[0478] To implement this invention, the following system must be configured. The system is composed of a collection means for collecting operation data of the robot arm, a transfer means for transferring the collected data to a user's terminal, and a transmission means for transmitting the transferred data to a cloud server. The cloud server also requires a generation means for analyzing the transferred data and generating feedback that optimizes the operational efficiency of the robot arm. The system also includes a provision means for providing the generated feedback to the user's terminal. Means for acquiring emotion data and adjusting the feedback based on the analysis results are also important elements.

[0479] Hardware and software used

[0480] Robot arm with sensors: The robot arm is equipped with force, speed, and angle sensors that collect movement data.

[0481] User device (smartphone / tablet): A dedicated application is installed on the device, which receives and transfers collected data.

[0482] Cloud server: Uses an EC2 instance from Amazon Web Services (AWS) and DynamoDB as the database.

[0483] Emotion engine: Uses facial recognition and speech analysis APIs like Amazon Rekognition and Google Cloud Vision to collect operator emotion data.

[0484] Generative AI model: Analyzes data using the OpenAI GPT model and generates optimal feedback.

[0485] Data processing and calculation

[0486] Data collection: Sensors mounted on the robot arm measure speed, angle, and force during movement, collecting data in real time.

[0487] Data transfer: The collected data is transferred to the user device via Bluetooth or WiFi. After transfer, the data is sent from the user device to the cloud server.

[0488] Data analysis: The data sent to the cloud server is checked for consistency and analyzed by the generative AI model. Based on the analysis results, feedback is generated to optimize the operation of the robot arm.

[0489] Emotion data acquisition: The emotion engine installed in the user device recognizes the operator's facial expressions and analyzes their voice to acquire emotion data.

[0490] Feedback generation: The generative AI model generates feedback based on operation data and emotional data, and adjusts according to the user's emotional state.

[0491] Feedback provision: The generated feedback is sent to the user's terminal and provided to the operator through a dedicated application.

[0492] Specific examples

[0493] Analysis of behavioral data:

[0494] When the robot arm performs welding work, the speed sensor measures the speed of the movement, which is collected in real time. For example, if the speed data is not within the specified range, the robot will generate feedback such as "The speed is too fast, please reduce it to within the set range."

[0495] Adjustment based on emotional data:

[0496] If the operator is tired, feedback such as "Take a short break" is added.

[0497] Prompt Sentence Examples

[0498] "Analyze the following robot arm motion data and generate appropriate feedback:

[0499] Operating speed: 10m / s

[0500] Operating angle: 45 degrees

[0501] Operating force: 20N

[0502] Operator's emotional state: Fatigue

[0503] Appropriate feedback: You're going too fast, slow down within the limits. Take a break.

[0504] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0505] Step 1:

[0506] Users collect operation data of robot arms in factories. Sensors mounted on the robot arms measure speed, angle, and force data in real time. No special operation is required by the user. Collected data input: speed, angle, force. Output: collected operation data.

[0507] Step 2:

[0508] The device transfers the collected data to the user's smartphone or tablet via Bluetooth or WiFi. During this process, the device receives data from the sensor and transfers the data to the device via stable communication. Input: Operational data from the sensor. Output: Operational data transferred to the device.

[0509] Step 3:

[0510] The device sends data to the cloud server. In this process, data is sent in real time from the user's device to the cloud server through a dedicated application. Input: Transferred operation data. Output: Operation data sent to the cloud server.

[0511] Step 4:

[0512] The server receives the data sent and checks its integrity. If outliers or missing data are identified, corrections and data cleaning are performed. Input: Operational data sent to the cloud server. Output: Data whose integrity has been checked.

[0513] Step 5:

[0514] The server analyzes the data using analytical tools. It uses a generative AI model (OpenAI GPT model) to analyze the movement data by comparing it with a database of professional athletes. Input: Data with verified consistency. Output: Analysis results.

[0515] Step 6:

[0516] The server uses facial recognition and voice analysis APIs to obtain the user's emotional data, which is taken into account when generating feedback. Input: User's facial and voice data. Output: Emotional data.

[0517] Step 7:

[0518] The server generates optimal feedback based on the analysis results and emotion data. A generative AI model is used to create specific feedback based on behavioral and emotion data. Feedback is obtained by generating prompt sentences and inputting them into the model. Input: Analysis results, emotion data. Output: Generated feedback.

[0519] Step 8:

[0520] The server sends the generated feedback to the user's terminal, which displays it. The user receives the feedback and reflects it in their next operation. Input: Generated feedback. Output: Sending and displaying feedback to the user's terminal.

[0521] Specific prompt examples

[0522] "Analyze the following robot arm motion data and generate appropriate feedback:

[0523] Operating speed: 10m / s

[0524] Operating angle: 45 degrees

[0525] Operating force: 20N

[0526] Operator's emotional state: Fatigue

[0527] Appropriate feedback: You're going too fast, slow down within the limits. Take a break.

[0528] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0529] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0530] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0531] [Second embodiment]

[0532] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0533] 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.

[0534] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0535] 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.

[0536] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0537] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0538] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0539] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0540] 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.

[0541] 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.

[0542] 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.

[0543] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0544] This invention proposes a system that collects and analyzes player motion data and provides optimal feedback to each player. This system is realized through the following steps.

[0545] System Configuration

[0546] The main elements of the system are IoT devices (including sensors) dedicated to the player, the user's terminal (smartphone or tablet), and a cloud server.

[0547] Data collection method

[0548] Terminal (IoT device)

[0549] As players practice batting and pitching, sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate. This collection method provides detailed player data.

[0550] User

[0551] Players simply practice as they normally would, with no special operations required. The sensors automatically collect data and transfer it to the user's device during practice.

[0552] Data Transfer Method

[0553] Device (smartphone or tablet)

[0554] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, and a dedicated application is installed on the user's device to receive and manage the data.

[0555] Data transmission method

[0556] Terminal

[0557] Once the user's training session is over, the collected data is sent to the cloud server automatically, without the user needing to be aware of it.

[0558] Data analysis and feedback generation

[0559] server

[0560] The cloud server receives the transmitted data and first checks the data for consistency. If any outliers or missing data are found, corrections are made. Next, the generated AI is used to analyze the player's movement data.

[0561] Specifically, the system compares a player's data with a database of professional players to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional players, the system will identify the specific movements and muscle strength deficiencies that are causing this.

[0562] generation means

[0563] Based on the results of the analysis, the AI ​​generates an individually optimized training menu and feedback, proposing specific improvement methods and daily training plans to the player.

[0564] How to provide feedback

[0565] Device (user's smartphone or tablet)

[0566] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to view it and reflect it in their next practice.

[0567] Coaching Support

[0568] User

[0569] During practice, users can ask the AI ​​generator questions in real time, such as "Is this swing correct?" or "What kind of practice should I do next?", and the AI ​​generator will respond with immediate advice.

[0570] Terminal

[0571] The user's question is sent from the device to the server and analyzed by the generating AI.

[0572] server

[0573] The generative AI generates appropriate answers to questions and sends them to the user's device, allowing the user to receive real-time coaching and maximize the effectiveness of their practice.

[0574] Specific examples

[0575] Example 1: Batting practice

[0576] As a player takes batting practice, IoT sensors collect swing speed and angle. The data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. The user can then review this feedback and consciously adjust their swing angle during their next practice session.

[0577] Example 2: Pitching practice

[0578] As a player practices pitching, IoT sensors collect ball speed and spin rate. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The user then practices while paying attention to the spin rate.

[0579] This system allows players to receive specific and effective feedback in real time to improve their performance, and also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[0580] The processing flow will be explained below.

[0581] Step 1:

[0582] The user begins batting or pitching practice. As the player practices as usual, the IoT sensors collect motion data, such as the player's bat swing speed and angle, as well as the ball's speed and spin rate.

[0583] Step 2:

[0584] The device (IoT device) collects player movement data in real time, and the collected data is transferred to the user's device via Bluetooth or WiFi via sensors attached to the bat and ball.

[0585] Step 3:

[0586] The terminal (user's smartphone or tablet) temporarily stores the movement data received from the IoT device, and a dedicated application displays the data, allowing the user to check their performance during practice.

[0587] Step 4:

[0588] The device (user's smartphone or tablet) sends the accumulated data to a cloud server. This is usually done automatically after the practice session is completed. The data is uploaded to the server via the Internet.

[0589] Step 5:

[0590] The server receives the operational data sent from the device, first checks the consistency of the data, and corrects any abnormal or missing values.

[0591] Step 6:

[0592] The server uses the generated AI to compare the analyzed motion data with a database of experienced professional players, specifically comparing the player's performance, such as swing speed, angle, ball speed, and spin rate, with those of professional players to identify differences and areas for improvement.

[0593] Step 7:

[0594] The server generates personalized, optimized feedback based on the analysis results. The AI ​​generator then suggests specific ways to improve and practice to the player. For example, "Your swing speed is good, but your swing angle is 10 degrees outward. Here's a practice menu to correct that."

[0595] Step 8:

[0596] The server sends the generated feedback to the user's device, where it is provided in a form that can be easily viewed by the user through a dedicated application.

[0597] Step 9:

[0598] The user opens the app and checks the feedback from the AI, understands specific ways to improve, and what to focus on in the next practice session, and practices accordingly.

[0599] Step 10:

[0600] Users can ask the generated AI questions in real time while practicing, such as "Is this swing correct?" or "What kind of practice should I do next?" through the app.

[0601] Step 11:

[0602] The device receives the user's question and sends it to the cloud server, where the application processes the question and forwards it to the server in real time.

[0603] Step 12:

[0604] The server receives questions from users, and the AI ​​generates appropriate answers for those questions, providing specific and applicable advice by referencing the player's data and a database of professional players.

[0605] Step 13:

[0606] The server sends the generated answer to the user's device, providing real-time feedback to the user.

[0607] Step 14:

[0608] The user can check the answers through the application and reflect them in their next action. Real-time coaching support can improve the player's performance.

[0609] Through the above steps, the present invention realizes a system that provides effective individualized optimal instruction to each player and supports the player's growth.

[0610] Example 1

[0611] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0612] Current training systems for players often collect and analyze motion data manually, making it difficult to obtain fast and effective feedback. Furthermore, these systems are unable to provide optimized feedback for individual players, making it difficult to accurately identify areas for improvement. Furthermore, a lack of real-time coaching support means that players are unable to receive immediate advice during practice.

[0613] 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.

[0614] In this invention, the server includes a correction means for checking the consistency of the transmitted data and correcting it, an analysis means for analyzing the corrected data, and a generation means for generating optimal feedback for the player using a generative AI model based on the analyzed data. This automates the entire process from collecting and analyzing player movement data, generating feedback, and providing real-time coaching, making it possible to provide quick, individually optimized feedback to the player.

[0615] "Collection means" refers to devices and sensors used to collect player movement data.

[0616] "Transfer means" refers to the technology or mechanism used to send collected data to the user's device.

[0617] "Transmission means" refers to the technology or mechanism for sending data from the user's device to the cloud server.

[0618] "Correction means" refers to the technology or mechanism used to check the consistency of data sent to the cloud server and correct abnormal values ​​or missing data.

[0619] "Analysis tools" refers to the technology or mechanisms used to analyze the corrected data and compare the motion data with a database of professional athletes or other standards.

[0620] "Generation means" refers to the technology or mechanism that uses a generative AI model to generate optimal feedback for the player based on the analyzed data.

[0621] "Provision means" refers to the technology or mechanism for transmitting the generated feedback to the user's device and providing it to the user.

[0622] "Motion Data" refers to performance data such as swing speed, angle, ball speed, and spin rate collected during a player's training.

[0623] A "generative AI model" is an artificial intelligence model used in the process of data analysis and feedback generation.

[0624] A "prompt" is a question or request input to a generative AI model, and is the text that serves as the basis for the AI ​​to analyze and generate an answer.

[0625] This invention is a system that collects and analyzes player motion data and provides personalized, optimized feedback. This system consists of a player-dedicated IoT device, a user terminal (smartphone or tablet), and a cloud server.

[0626] Data collection method

[0627] Terminal (IoT device)

[0628] When a user practices batting or pitching as a player, IoT sensors collect real-time motion data such as swing speed, angle, ball speed, and spin rate. The sensors are attached to the bat or ball and collect detailed player data during practice.

[0629] User

[0630] Players simply practice as they normally would without any special operations, and the sensors automatically collect and transmit movement data to the user's device during practice.

[0631] Data Transfer Method

[0632] Device (smartphone or tablet)

[0633] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, where a dedicated application is installed to receive and manage the data.

[0634] Data transmission method

[0635] Terminal

[0636] After the practice session, the user's device automatically sends the collected data to the cloud server. This process is transparent to the user. A dedicated application automatically sends the data to the cloud and stores it on the cloud server.

[0637] Data analysis and feedback generation

[0638] server

[0639] The cloud server checks the integrity of the transmitted data and corrects any abnormal values ​​or missing data. The corrected data is then analyzed using analytical tools, and the player's motion data is compared with a database of other players. For example, if a player's swing speed is slower than that of other players, the underlying motions and muscle strength deficiencies are specifically identified.

[0640] Generation AI

[0641] Based on the analysis results, the generative AI model generates personalized training menus and feedback, suggesting specific ways to improve and daily training plans for each player.

[0642] How to provide feedback

[0643] Device (user's smartphone or tablet)

[0644] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to refer to this feedback for their next practice.

[0645] Coaching Support

[0646] User

[0647] If a player has questions during practice, they can ask the generative AI model questions in real time, such as "Is this swing correct?" or "What practice should I do next?"

[0648] Terminal

[0649] The user's question is sent from the device to a cloud server and analyzed by a generative AI model.

[0650] server

[0651] The generative AI model generates appropriate answers to questions and sends them to the user's device, allowing them to receive real-time coaching and maximize the effectiveness of their practice.

[0652] Specific examples

[0653] Example 1: Batting practice

[0654] When a user takes batting practice, IoT sensors collect swing speed and angle. The collected data is transferred to the user's device and sent to a cloud server. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. The user can then use this feedback to consciously adjust their swing angle during their next practice session.

[0655] Example 2: Pitching practice

[0656] When a user practices pitching, the IoT sensor collects the ball's speed and spin rate. The collected data is transferred to the user's device and sent to a cloud server. The cloud server analyzes the data and generates feedback such as "the ball's speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The user can use this feedback to practice while focusing on the spin rate.

[0657] Prompt Sentence Examples

[0658] "A player has good swing speed, but the swing angle is not right. How do I fix it?"

[0659] "My player's ball velocity is adequate, but he lacks spin. Can you tell me some specific practice methods to increase the spin?"

[0660] This system allows users to receive specific and effective feedback in real time to improve their performance, and also allows coaches to provide accurate guidance to each player, which is expected to improve overall performance.

[0661] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0662] Step 1: Data collection

[0663] The device uses IoT sensors to collect real-time motion data such as swing speed, angle, ball speed, and spin rate when a player practices batting or pitching. Each data point detected by the sensor (e.g., swing speed) is sent to the user's device via Bluetooth or WiFi. The input is the motion data detected by the sensor, and the output is the data sent to the user's device. Specifically, the sensor records the swing speed every time the player swings the bat and sends it wirelessly to the device.

[0664] Step 2: Data Transfer

[0665] The user's device manages the received motion data using a dedicated application. This application stores the data in local storage immediately after receiving it via Bluetooth or WiFi. The input is motion data from the sensor, and the output is data stored in the device's local storage. Specifically, every time the player swings, data is displayed on the device and immediately accumulated within the application.

[0666] Step 3: Send data

[0667] When the user's device finishes practicing, it automatically sends the collected data to a cloud server. This is often done via Wi-Fi. The input is the movement data stored in the local storage, and the output is the data sent to the cloud server. Specifically, when the practice is finished, the application displays "Data transmission completed."

[0668] Step 4: Data integrity check

[0669] The server checks the integrity of the data it receives and performs corrections if outliers or missing data are found. The input is the raw data sent to the cloud server, and the output is the corrected data that has been checked for integrity. Specifically, if a data point sent to the database is outside the abnormal range, the data is automatically corrected.

[0670] Step 5: Data analysis

[0671] The server analyzes the corrected data and compares the player's motion data with a database of other players. A generative AI model is used for the analysis. The input is the corrected data, and the output is the analysis results. Specifically, the swing speed and angle are compared with other players' data to detect any differences.

[0672] Step 6: Feedback generation

[0673] The server uses a generative AI model based on the analysis results to generate optimal feedback for the player. The input is the analysis results, and the output is the generated feedback. Specific actions are suggested for improvement, such as "your swing speed is good, but your angle is too high."

[0674] Step 7: Provide feedback

[0675] The server sends the generated feedback to the user's device, which then displays it through a dedicated application. The input is the generated feedback, and the output is the feedback displayed on the user's device. Specifically, a notification in the application notifies the user that feedback has been received, allowing them to view the details.

[0676] Step 8: Real-time questions and coaching support

[0677] Users can pose questions to the generative AI model in real time through a dedicated application. For example, they can ask, "Is this swing correct?" This question is sent to the server via the device, and the generative AI model analyzes it. Appropriate advice is generated from the analysis results and sent to the device. The input is the question from the user, and the output is the answer generated by the generative AI model. Specifically, when a question is entered, the server analyzes it and the results are displayed on the device in real time, allowing the user to receive immediate feedback.

[0678] (Application example 1)

[0679] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0680] While automation using robots is progressing in modern factories, issues remain with regard to the efficiency and quality control of robot operations. In particular, there is a demand for systems that can collect and analyze each robot's operation data in real time and provide optimal feedback each time. However, existing systems have problems such as low data collection accuracy and time-consuming analysis. The present invention aims to solve these problems and improve the efficiency and quality of robot operations in factories.

[0681] 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.

[0682] In this invention, the server includes a collection means for collecting robot operation data, a transfer means for transferring the data collected by the collection means to a user's terminal, a transmission means for transmitting the data transferred by the transfer means to a cloud server, a generation means in the cloud server for analyzing the data transmitted by the transmission means and generating optimal feedback for the robot, and a providing means for transmitting the feedback generated by the generation means to the user's terminal, thereby making it possible to collect and analyze robot operation data in real time and provide accurate feedback.

[0683] A "robot" is a mechanical device used to perform automated work in factories and the like, and is a general term for mechanical devices that can execute motion control.

[0684] "Motion data" refers to data relating to the robot's motion, and specifically includes data on motion speed, motion angle, and force.

[0685] "Collection means" refers to a means for collecting motion data using sensors and devices attached to the robot.

[0686] "Transfer means" refers to the means for transferring collected operational data to the user's device, and generally uses communication technologies such as Bluetooth or WiFi.

[0687] The "transmission means" is a means for transmitting the data transferred to the user's terminal by the transfer means to the cloud server.

[0688] A "cloud server" is a remote server device accessible via the Internet, and is a computer resource that can store and analyze large amounts of data.

[0689] The "generation means" is a means for analyzing the data transmitted by the transmission means in the cloud server and generating optimal feedback for the robot.

[0690] The "providing means" is a means for transmitting the feedback generated by the generating means to the user's terminal.

[0691] This invention relates to a system that collects and analyzes the operation data of factory robots and provides individual optimal feedback. This system consists of the following main elements:

[0692] System Configuration

[0693] The system consists of sensors attached to the robot, the user's device (e.g., a smartphone or tablet), and a cloud server.

[0694] Data collection method

[0695] Collection Method

[0696] Sensors attached to the robot collect real-time operational data such as movement speed, movement angle, and force. For example, pressure sensors, acceleration sensors, gyro sensors, etc. can be attached to robots working on factory production lines to obtain various types of data.

[0697] User

[0698] Without any special operations by factory managers or engineers, the robots simply continue to operate as usual, and the sensors automatically collect data and transfer it to the user's device.

[0699] Data Transfer Method

[0700] Transfer Method

[0701] Collected data is transmitted to the user's device in real time via Bluetooth or WiFi, simplifying on-site operation and improving data collection efficiency.

[0702] User

[0703] A dedicated application is installed on the user's device, and this application receives and manages the data. For example, by installing the dedicated application on a smartphone, you can check the operation data of a robot in a factory.

[0704] Data transmission method

[0705] Transmission method

[0706] The user's device sends the collected data to a cloud server. This happens automatically, so the user does not need to be aware of it. For example, a smartphone app automatically uploads data to the cloud.

[0707] Data analysis and feedback generation

[0708] Cloud Server

[0709] The cloud server receives the transmitted data and first checks its integrity. If any outliers or missing data are identified, corrections are made. Next, the data is analyzed using a generative AI model to evaluate the robot's operational efficiency and quality.

[0710] generation means

[0711] Based on the analysis results, the generative AI model identifies the optimal individual movement method and areas for improvement, and generates feedback. For example, if the robot's movement speed is appropriate but the movement angle is inappropriate, it will generate feedback that "the movement angle needs to be corrected."

[0712] How to provide feedback

[0713] Providing means

[0714] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to adjust the robot's behavior based on this feedback.

[0715] Coaching Support

[0716] User

[0717] Users can ask the generative AI model questions in real time, such as "Is this action efficient?" or "What should I do next?", and the generative AI model will respond with immediate advice.

[0718] Prompt Sentence Examples

[0719] For example, you can enter the following prompt:

[0720] "Analyze the robot's motion data and generate feedback to optimize efficiency and reduce errors."

[0721] "Tell me what adjustments I should make next."

[0722] The above system enables robots in the factory to operate efficiently, improving overall productivity and quality.

[0723] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0724] Step 1:

[0725] Collecting robot movement data

[0726] Input: Sensors attached to the robot acquire movement data (movement speed, movement angle, force).

[0727] Output: Raw motion speed, motion angle and force dataset.

[0728] Specific behavior: Sensors monitor the robot's behavior in real time and measure and record the necessary physical parameters, for example, pressure sensors measure the robot's movement force, and gyro sensors measure the movement angle.

[0729] Step 2:

[0730] Data Transfer

[0731] Input: Collected behavioral data.

[0732] Output: Data transfer to the user's device.

[0733] How it works: Data collected from sensors is transmitted to the user's device via Bluetooth or WiFi, where a dedicated application is installed. This application receives and temporarily stores the data.

[0734] Step 3:

[0735] Sending data to a cloud server

[0736] Input: Operational data transferred to the user's device.

[0737] Output: Data sent to the cloud server.

[0738] How it works: A dedicated application on the user's device automatically sends the collected data to a cloud server via the Internet, allowing the cloud server to receive the data for analysis.

[0739] Step 4:

[0740] Data Integrity Check

[0741] Input: The motion data sent to the cloud server.

[0742] Output: Data that has been checked for consistency or corrected.

[0743] Specific operation: The cloud server first checks the integrity of the received data. If outliers or missing data are found, the outliers are filtered out and missing values ​​are imputed.

[0744] Step 5:

[0745] Data analysis and feedback generation

[0746] Input: Data whose integrity has been checked.

[0747] Output: Analysis of the robot's operation efficiency and quality, along with optimal feedback.

[0748] Specific operation: A generative AI model installed on a cloud server analyzes the data whose consistency has been confirmed. For example, it evaluates whether the movement speed is appropriate or whether there are any problems with the movement angle, and based on that, it generates areas for improvement and optimal operation methods.

[0749] Step 6:

[0750] Providing Feedback

[0751] Input: Feedback from the generative AI model.

[0752] Output: Feedback sent to the user's device.

[0753] Specific behavior: The cloud server sends the generated feedback to the user's device, where it is displayed by a dedicated application. The user can then adjust the robot's behavior based on this feedback.

[0754] Step 7:

[0755] Real-time coaching support

[0756] Input: The user's question (prompt sentence).

[0757] Output: The answer from the generative AI model.

[0758] Specific Actions: When a user sends a question to the generative AI model in real time, the cloud server analyzes the question, generates an appropriate answer, and delivers it to the user's device. For example, in response to a question such as "Is this action efficient?", it is possible to provide specific feedback such as "The speed of the action is appropriate, but the angle of the action should be improved by 10 degrees."

[0759] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0760] This invention proposes a system that collects and analyzes player movement data, and recognizes and utilizes the user's emotional data to provide personalized and optimal feedback. This system is realized through the following steps.

[0761] System Configuration

[0762] The main elements of the system are a player-dedicated IoT device (including sensors), the user's device (smartphone or tablet), a cloud server, and an emotion engine that recognizes the user's emotions.

[0763] Data collection method

[0764] Terminal (IoT device)

[0765] As players practice batting and pitching, sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate. This collection method provides detailed player data.

[0766] User

[0767] Players simply practice as they normally would, with no special operations required. The sensors automatically collect data and transfer it to the user's device during practice.

[0768] Data Transfer Method

[0769] Device (smartphone or tablet)

[0770] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, and a dedicated application is installed on the user's device to receive and manage the data.

[0771] Data transmission method

[0772] Terminal

[0773] Once the user's training session is over, the collected data is sent to the cloud server automatically, without the user needing to be aware of it.

[0774] Collecting Emotional Data

[0775] Device (smartphone or tablet)

[0776] The user's device is equipped with an emotion engine that acquires emotional data in real time through facial expression recognition and voice analysis, thereby understanding the player's emotional state.

[0777] Data analysis and feedback generation

[0778] server

[0779] The cloud server receives the transmitted motion data and first checks the data for consistency. If any abnormal values ​​or missing data are found, correction processing is performed. Next, the generation AI is used to analyze the player's motion data.

[0780] Specifically, the system compares a player's data with a database of professional players to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional players, the system will identify the specific movements and muscle strength deficiencies that are causing this.

[0781] generation means

[0782] Based on the results of the analysis, the AI ​​generates personalized feedback that is optimized for each player. This generation method suggests specific ways to improve and daily practice plans for each player.

[0783] Feedback adjustment using emotional data

[0784] server

[0785] The cloud server also takes into account the player's emotional data acquired by the emotion engine and customizes the feedback content. For example, if a player feels tired or impatient during practice, it generates encouraging messages or feedback suggesting appropriate breaks.

[0786] How to provide feedback

[0787] Device (user's smartphone or tablet)

[0788] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to view it and reflect it in their next practice.

[0789] Coaching Support

[0790] User

[0791] During practice, users can ask the AI ​​generator questions in real time, such as "Is this swing correct?" or "What kind of practice should I do next?", and the AI ​​generator will respond with immediate advice.

[0792] Terminal

[0793] The user's question is sent from the device to the server and analyzed by the generating AI.

[0794] server

[0795] The generative AI generates appropriate answers to questions and sends them to the user's device, allowing the user to receive real-time coaching and maximize the effectiveness of their practice.

[0796] Specific examples

[0797] Example 1: Batting practice

[0798] As a player takes batting practice, IoT sensors collect swing speed and angle. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. Using an emotion engine, encouraging messages such as "pay attention to this point in your next practice" are also added. The user can then see this and consciously correct their swing angle in their next practice.

[0799] Example 2: Pitching practice

[0800] As the player practices pitching, the IoT sensor collects ball speed and spin rate. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The emotion engine may also suggest things like "Take a short break." This allows the user to practice while paying attention to the spin rate.

[0801] This system not only allows players to receive specific and effective feedback in real time to improve their performance, but also provides appropriate support based on their emotional state. It also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[0802] The processing flow will be explained below.

[0803] Step 1:

[0804] The user begins batting or pitching practice. As the player practices as usual, the IoT sensors collect motion data, such as the player's bat swing speed and angle, as well as the ball's speed and spin rate.

[0805] Step 2:

[0806] The device (IoT device) collects player movement data in real time, and the collected data is transferred to the user's device via Bluetooth or WiFi via sensors attached to the bat and ball.

[0807] Step 3:

[0808] The device (user's smartphone or tablet) temporarily stores the motion data received from the IoT device. A dedicated application displays the data, allowing the user to check their performance during practice. The device's built-in emotion engine also simultaneously collects emotional data through facial recognition and voice analysis of the player.

[0809] Step 4:

[0810] The device (user's smartphone or tablet) transmits the accumulated movement and emotion data to a cloud server. This is usually done automatically after the practice session is completed. The data is uploaded to the server via the internet.

[0811] Step 5:

[0812] The server receives the motion and emotion data sent from the device. First, it checks the consistency of the data and corrects any outliers or missing data. It also verifies that the motion and emotion data are properly linked.

[0813] Step 6:

[0814] The server uses the generated AI to compare the analyzed motion data with a database of experienced professional players, specifically comparing the player's performance, such as swing speed, angle, ball speed, and spin rate, with those of professional players to identify differences and areas for improvement.

[0815] Step 7:

[0816] The server evaluates the player's mental state based on emotional data, and if the player is feeling tired or impatient, this information is reflected in the analysis results.

[0817] Step 8:

[0818] The server generates personalized, optimized feedback based on the analysis results. The AI ​​generator then suggests specific ways to improve and practice to the player. Furthermore, it adjusts the feedback based on emotional data, suggesting a break for tired players and encouraging active practice for energetic players.

[0819] Step 9:

[0820] The server sends the generated feedback to the user's device, where it is provided in a form that can be easily viewed by the user through a dedicated application.

[0821] Step 10:

[0822] The user opens the app and checks the feedback from the AI, understands specific ways to improve, and what to focus on in the next practice session, and practices accordingly.

[0823] Step 11:

[0824] Users can ask the generated AI questions in real time while practicing, such as "Is this swing correct?" or "What kind of practice should I do next?" through the app.

[0825] Step 12:

[0826] The device receives the user's question and sends it to the cloud server, where the application processes the question and forwards it to the server in real time.

[0827] Step 13:

[0828] The server receives questions from users, and the AI ​​generates appropriate answers for those questions, providing specific and applicable advice by referencing the player's data and a database of professional players.

[0829] Step 14:

[0830] The server sends the generated answer to the user's device, providing real-time feedback to the user.

[0831] Step 15:

[0832] The user can check the answers through the application and reflect them in their next action. Real-time coaching support can improve the player's performance.

[0833] By implementing the above steps, the present invention realizes a system that provides effective, individualized guidance to each player and supports their growth. By taking emotion data into consideration, it becomes possible to provide more flexible feedback that is tailored to the player's psychological state.

[0834] Example 2

[0835] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0836] While conventional sports training systems collect and analyze player movement data, it is difficult to grasp the player's emotional state in real time and provide appropriate feedback. Furthermore, the process of generating individually optimized feedback is unable to reflect the player's emotions, making effective instruction difficult.

[0837] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a collection means for collecting player's motion data, a generation means for analyzing the collected data and generating feedback, an emotion collection means for collecting user's emotion data, and an adjustment means for adjusting the feedback using the collected emotion data. This makes it possible to provide individually optimized feedback by taking into account both the player's motion data and emotion data.

[0838] "Collection means" refers to a means for acquiring player movement data, such as a sensor or other device.

[0839] The "transfer means" is a means for transmitting the data acquired by the collection means to the user's terminal.

[0840] "Transmission means" refers to a means for transmitting data from a user's terminal to a cloud server.

[0841] The "generation means" is a means in the cloud server that analyzes the data transmitted by the transmission means and generates optimal feedback for the player.

[0842] "Emotion collection means" refers to means for acquiring user emotional data, and includes facial expression recognition and voice analysis technologies.

[0843] The "adjustment means" is a means for optimizing and adjusting the generated feedback using the emotion data collected by the emotion collection means.

[0844] The "providing means" is a means for transmitting the feedback generated by the generating means and adjusting means to the user's terminal and providing the feedback.

[0845] "Motion data" refers to data that measures the player's movements, including speed, angle, amount of movement, number of rotations, etc.

[0846] "Emotional data" is data that indicates the user's emotional state and is obtained from facial expressions and voice.

[0847] A "cloud server" refers to a server on the Internet used for analyzing and storing data.

[0848] This invention is a system that collects and analyzes player movement data, recognizes and utilizes the user's emotional data, and provides personalized and optimal feedback. This system consists of a player-dedicated IoT device (including sensors), the user's device (smartphone or tablet), a cloud server, and an emotion engine that recognizes the user's emotions.

[0849] Data collection

[0850] Terminal (IoT device) processing:

[0851] As players practice batting and pitching, sensors attached to the bat and ball collect real-time data such as swing speed, angle, ball speed, and spin rate, which is then transmitted to the user's device via Bluetooth or Wi-Fi.

[0852] User Action:

[0853] Players practice as usual, with no special operations required. The sensors automatically collect data and transmit it to the user's device during practice.

[0854] Data Transfer

[0855] Device (smartphone or tablet) processing:

[0856] The collected data is received and managed in real time by a dedicated application via Bluetooth or WiFi. The received data is temporarily stored on the device and can be viewed by the user at any time.

[0857] Data transmission

[0858] Terminal handling:

[0859] Once the user's training is complete, the collected data is sent to the cloud server. This data transfer occurs in the background, so the user does not need to be aware of it.

[0860] Collecting Emotional Data

[0861] Device (smartphone or tablet) processing:

[0862] The user's device is equipped with an emotion engine that uses a camera and microphone to analyze the player's facial expressions and voice, thereby obtaining the player's emotional data in real time.

[0863] Data analysis and feedback generation

[0864] Server Action:

[0865] The cloud server receives the motion data sent from the user's device. First, it checks the data for consistency and corrects any outliers or missing data. It then analyzes the motion data using a generative AI model and compares the player's data with a database of professional golfers to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional golfers, the cloud server will specifically identify the underlying motions and muscle weaknesses.

[0866] Feedback adjustment using emotional data

[0867] Server Action:

[0868] The cloud server also takes into account the player's emotional data acquired by the emotion engine and customizes the content of the feedback. For example, if a player feels fatigued or impatient during practice, it generates encouraging messages or feedback suggesting appropriate breaks.

[0869] Providing Feedback

[0870] Device (user's smartphone or tablet) processing:

[0871] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to incorporate this feedback into their next practice.

[0872] Coaching Support

[0873] User Action:

[0874] Users can ask the generative AI model questions in real time while practicing, such as "Is this swing correct?" or "What practice should I do next?"

[0875] Terminal handling:

[0876] The user's question is sent from the device to a cloud server and analyzed by a generative AI model.

[0877] Server Action:

[0878] The generative AI model generates appropriate answers to the questions, which are then sent back to the user's device, allowing them to receive real-time coaching and maximize the effectiveness of their practice.

[0879] Specific examples

[0880] Batting practice example:

[0881] When a user takes batting practice, sensors collect swing speed and angle, and the data is transferred to the user's device. After practice is completed, the data is sent to a cloud server, which generates analysis results and feedback such as "your swing speed is good, but your angle needs improvement." Based on the user's emotional data, an encouraging message is also added, such as "pay attention to this point in your next practice." This encourages the user to be conscious of their swing angle and try to correct it in their next practice.

[0882] Pitching practice example:

[0883] When a user practices pitching, sensors collect ball speed and spin rate, and the data is transferred to the user's device. After practice, the data is sent to a cloud server, which generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient." Based on emotional data, the feedback may include suggestions such as "Take a short break." The user can then practice with an awareness of the spin rate.

[0884] Prompt Sentence Examples

[0885] Batting Practice Prompts

[0886] "Analyze swing speed and angle data during batting practice and provide feedback on areas for improvement."

[0887] Pitching Practice Prompts

[0888] "Please analyze the ball speed and spin rate data during pitching practice and tell me how to improve."

[0889] This system not only allows players to receive specific and effective feedback in real time to improve their performance, but also provides appropriate support based on their emotional state. It also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[0890] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0891] Step 1:

[0892] Data collection

[0893] Terminal (IoT device) processing:

[0894] 1. Players begin batting and pitching practice.

[0895] 2. Sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate.

[0896] 3. Input: Player Actions

[0897] 4. Output: swing speed, angle, ball speed, spin rate data

[0898] 5. The data acquired by the sensor is transferred to the user's device via Bluetooth or WiFi.

[0899] Step 2:

[0900] Data Transfer

[0901] Device (smartphone or tablet) processing:

[0902] 1. A dedicated application receives data from the sensor in real time via Bluetooth or WiFi.

[0903] 2. The received data is temporarily stored on the device.

[0904] 3. Input: Motion data from sensors

[0905] 4. Output: Temporarily saved data on the device

[0906] 5. Users can check the data at any time through a dedicated application.

[0907] Step 3:

[0908] Data transmission

[0909] Terminal handling:

[0910] 1. After the practice session, the device automatically sends the collected movement data to the cloud server.

[0911] 2. Input: Saved operating data

[0912] 3. Output: Data sent to the cloud server

[0913] 4. Data transmission occurs in the background, so users do not need to be aware of it.

[0914] Step 4:

[0915] Collecting Emotional Data

[0916] Device (smartphone or tablet) processing:

[0917] 1. The user's device is equipped with an emotion engine that uses the camera and microphone to analyze the player's facial expressions and voice.

[0918] 2. Obtain player emotional data in real time through facial expression recognition and voice analysis.

[0919] 3. Input: Player's facial expressions and voice

[0920] 4. Output: Emotion data

[0921] Step 5:

[0922] Data analysis and feedback generation

[0923] Server Action:

[0924] 1. The cloud server receives the operation data sent from the user's device.

[0925] 2. The server checks the consistency of the data and performs correction processing if abnormal values ​​or missing data are found.

[0926] 3. Input: Operation data sent to the cloud server

[0927] 4. Output: Consistent operational data

[0928] 5. A generative AI model analyzes the data and compares the player's data with a database of professional athletes.

[0929] 6. Identify performance gaps and areas for improvement.

[0930] 7. Input: Consistent operational data

[0931] 8. Output: Analysis results (performance differences, areas for improvement)

[0932] 9. The generation means generates individually optimized feedback based on the analysis results.

[0933] 10. Input: Analysis results

[0934] 11. Output: Feedback data

[0935] Step 6:

[0936] Feedback adjustment using emotional data

[0937] Server Action:

[0938] 1. The cloud server receives the player's emotion data obtained by the emotion engine.

[0939] 2. The server analyzes the emotional data and customizes the content of the generated feedback.

[0940] 3. If a player feels fatigued or impatient during practice, generate encouraging messages and feedback suggesting appropriate breaks.

[0941] 4. Input: Emotion data, feedback data

[0942] 5. Output: Customized feedback

[0943] Step 7:

[0944] Providing Feedback

[0945] Device (user's smartphone or tablet) processing:

[0946] 1. Customized feedback is sent from the cloud server to the user's device.

[0947] 2. Feedback is provided to users in real time through a dedicated application.

[0948] 3. Input: Customized Feedback

[0949] 4. Output: Present feedback to the user

[0950] Step 8:

[0951] Coaching Support

[0952] User Action:

[0953] 1. Users can ask questions to the generative AI model in real time while practicing, such as "Is this swing correct?" or "What practice should I do next?"

[0954] 2. Input: User Question

[0955] 3. Output: Query data to the server

[0956] Terminal handling:

[0957] 1. The user's question is sent from the device to the cloud server.

[0958] 2. Input: User's question data

[0959] 3. Output: Data sent to the cloud server

[0960] Server Action:

[0961] 1. The generative AI model receives the question, analyzes it, and generates an appropriate answer.

[0962] 2. The answer is sent back to the user's device.

[0963] 3. Input: User's question data

[0964] 4. Output: Generated answers

[0965] Terminal handling:

[0966] 1. The user's device receives the answer sent from the cloud server.

[0967] 2. Present to the user through a dedicated application.

[0968] 3. Input: Response data from the cloud server

[0969] 4. Output: Answer presented to the user

[0970] (Application example 2)

[0971] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0972] In factories, it is desirable to monitor the operating status of automated equipment such as robot arms in real time to enable efficient maintenance and operation optimization. However, current systems take time to collect and analyze operation data, making it difficult to provide appropriate feedback quickly. In addition, feedback does not take into account the emotional state of the operator, which increases the risk of fatigue and operational errors during work.

[0973] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a collection means for collecting operation data of the robot arm, a transfer means for transferring the data collected by the collection means to a user's terminal, a transmission means for transmitting the data transferred by the transfer means to a cloud server, a generation means in the cloud server for analyzing the data transmitted by the transmission means and generating feedback for optimizing the operation efficiency of the robot arm, a providing means for transmitting the feedback generated by the generation means to the user's terminal, and a means for the generation means to acquire emotion data and adjust the feedback based on the analysis results. This makes it possible to grasp the operating status of automated equipment in a factory in real time and quickly provide appropriate feedback that takes into account the emotional state of operators.

[0974] "Motion data" refers to information such as speeds, angles, and forces generated by a robotic arm or other automated device during operation.

[0975] "Collection means" refers to a device or system for acquiring operational data using a robotic arm or other sensor.

[0976] "Transportation Method" refers to the method or protocol for moving or transmitting collected data to a user's device.

[0977] "Transmission means" refers to a device or method for transmitting data from a user's terminal to a cloud server.

[0978] A "cloud server" refers to a remote server that can be accessed by multiple users via the Internet and is used to store and analyze data.

[0979] "Analysis" refers to the process of processing collected operational data to extract useful information.

[0980] "Generator" refers to a device or algorithm for generating feedback based on the analysis results.

[0981] "Providing means" refers to a device or method for delivering the generated feedback to the user's terminal.

[0982] "Emotional data" refers to data that indicates the emotional state of an operator obtained through facial expressions and voice analysis.

[0983] A "generative AI model" refers to an artificial intelligence model that uses machine learning technology to analyze data and generate optimal feedback.

[0984] A "prompt sentence" refers to an input sentence provided to a generative AI model to perform a specific task.

[0985] To implement this invention, the following system must be configured. The system is composed of a collection means for collecting operation data of the robot arm, a transfer means for transferring the collected data to a user's terminal, and a transmission means for transmitting the transferred data to a cloud server. The cloud server also requires a generation means for analyzing the transferred data and generating feedback that optimizes the operational efficiency of the robot arm. The system also includes a provision means for providing the generated feedback to the user's terminal. Means for acquiring emotion data and adjusting the feedback based on the analysis results are also important elements.

[0986] Hardware and software used

[0987] Robot arm with sensors: The robot arm is equipped with force, speed, and angle sensors that collect movement data.

[0988] User device (smartphone / tablet): A dedicated application is installed on the device, which receives and transfers collected data.

[0989] Cloud server: Uses an EC2 instance from Amazon Web Services (AWS) and DynamoDB as the database.

[0990] Emotion engine: Uses facial recognition and speech analysis APIs like Amazon Rekognition and Google Cloud Vision to collect operator emotion data.

[0991] Generative AI model: Analyzes data using the OpenAI GPT model and generates optimal feedback.

[0992] Data processing and calculation

[0993] Data collection: Sensors mounted on the robot arm measure speed, angle, and force during movement, collecting data in real time.

[0994] Data transfer: The collected data is transferred to the user device via Bluetooth or WiFi. After transfer, the data is sent from the user device to the cloud server.

[0995] Data analysis: The data sent to the cloud server is checked for consistency and analyzed by the generative AI model. Based on the analysis results, feedback is generated to optimize the operation of the robot arm.

[0996] Emotion data acquisition: The emotion engine installed in the user device recognizes the operator's facial expressions and analyzes their voice to acquire emotion data.

[0997] Feedback generation: The generative AI model generates feedback based on operation data and emotional data, and adjusts according to the user's emotional state.

[0998] Feedback provision: The generated feedback is sent to the user's terminal and provided to the operator through a dedicated application.

[0999] Specific examples

[1000] Analysis of behavioral data:

[1001] When the robot arm performs welding work, the speed sensor measures the speed of the movement, which is collected in real time. For example, if the speed data is not within the specified range, the robot will generate feedback such as "The speed is too fast, please reduce it to within the set range."

[1002] Adjustment based on emotional data:

[1003] If the operator is tired, feedback such as "Take a short break" is added.

[1004] Prompt Sentence Examples

[1005] "Analyze the following robot arm motion data and generate appropriate feedback:

[1006] Operating speed: 10m / s

[1007] Operating angle: 45 degrees

[1008] Operating force: 20N

[1009] Operator's emotional state: Fatigue

[1010] Appropriate feedback: You're going too fast, slow down within the limits. Take a break.

[1011] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1012] Step 1:

[1013] Users collect operation data of robot arms in factories. Sensors mounted on the robot arms measure speed, angle, and force data in real time. No special operation is required by the user. Collected data input: speed, angle, force. Output: collected operation data.

[1014] Step 2:

[1015] The device transfers the collected data to the user's smartphone or tablet via Bluetooth or WiFi. During this process, the device receives data from the sensor and transfers the data to the device via stable communication. Input: Operational data from the sensor. Output: Operational data transferred to the device.

[1016] Step 3:

[1017] The device sends data to the cloud server. In this process, data is sent in real time from the user's device to the cloud server through a dedicated application. Input: Transferred operation data. Output: Operation data sent to the cloud server.

[1018] Step 4:

[1019] The server receives the data sent and checks its integrity. If outliers or missing data are identified, corrections and data cleaning are performed. Input: Operational data sent to the cloud server. Output: Data whose integrity has been checked.

[1020] Step 5:

[1021] The server analyzes the data using analytical tools. It uses a generative AI model (OpenAI GPT model) to analyze the movement data by comparing it with a database of professional athletes. Input: Data with verified consistency. Output: Analysis results.

[1022] Step 6:

[1023] The server uses facial recognition and voice analysis APIs to obtain the user's emotional data, which is taken into account when generating feedback. Input: User's facial and voice data. Output: Emotional data.

[1024] Step 7:

[1025] The server generates optimal feedback based on the analysis results and emotion data. A generative AI model is used to create specific feedback based on behavioral and emotion data. Feedback is obtained by generating prompt sentences and inputting them into the model. Input: Analysis results, emotion data. Output: Generated feedback.

[1026] Step 8:

[1027] The server sends the generated feedback to the user's terminal, which displays it. The user receives the feedback and reflects it in their next operation. Input: Generated feedback. Output: Sending and displaying feedback to the user's terminal.

[1028] Specific prompt examples

[1029] "Analyze the following robot arm motion data and generate appropriate feedback:

[1030] Operating speed: 10m / s

[1031] Operating angle: 45 degrees

[1032] Operating force: 20N

[1033] Operator's emotional state: Fatigue

[1034] Appropriate feedback: You're going too fast, slow down within the limits. Take a break.

[1035] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1036] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1037] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1038] [Third embodiment]

[1039] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1040] 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.

[1041] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1042] 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.

[1043] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1044] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1045] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1046] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1047] 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.

[1048] 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.

[1049] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1050] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1051] This invention proposes a system that collects and analyzes player motion data and provides optimal feedback to each player. This system is realized through the following steps.

[1052] System Configuration

[1053] The main elements of the system are IoT devices (including sensors) dedicated to the player, the user's terminal (smartphone or tablet), and a cloud server.

[1054] Data collection method

[1055] Terminal (IoT device)

[1056] As players practice batting and pitching, sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate. This collection method provides detailed player data.

[1057] User

[1058] Players simply practice as they normally would, with no special operations required. The sensors automatically collect data and transfer it to the user's device during practice.

[1059] Data Transfer Method

[1060] Device (smartphone or tablet)

[1061] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, and a dedicated application is installed on the user's device to receive and manage the data.

[1062] Data transmission method

[1063] Terminal

[1064] Once the user's training session is over, the collected data is sent to the cloud server automatically, without the user needing to be aware of it.

[1065] Data analysis and feedback generation

[1066] server

[1067] The cloud server receives the transmitted data and first checks the data for consistency. If any outliers or missing data are found, corrections are made. Next, the generated AI is used to analyze the player's movement data.

[1068] Specifically, the system compares a player's data with a database of professional players to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional players, the system will identify the specific movements and muscle strength deficiencies that are causing this.

[1069] generation means

[1070] Based on the results of the analysis, the AI ​​generates an individually optimized training menu and feedback, proposing specific improvement methods and daily training plans to the player.

[1071] How to provide feedback

[1072] Device (user's smartphone or tablet)

[1073] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to view it and reflect it in their next practice.

[1074] Coaching Support

[1075] User

[1076] During practice, users can ask the AI ​​generator questions in real time, such as "Is this swing correct?" or "What kind of practice should I do next?", and the AI ​​generator will respond with immediate advice.

[1077] Terminal

[1078] The user's question is sent from the device to the server and analyzed by the generating AI.

[1079] server

[1080] The generative AI generates appropriate answers to questions and sends them to the user's device, allowing the user to receive real-time coaching and maximize the effectiveness of their practice.

[1081] Specific examples

[1082] Example 1: Batting practice

[1083] As a player takes batting practice, IoT sensors collect swing speed and angle. The data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. The user can then review this feedback and consciously adjust their swing angle during their next practice session.

[1084] Example 2: Pitching practice

[1085] As a player practices pitching, IoT sensors collect ball speed and spin rate. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The user then practices while paying attention to the spin rate.

[1086] This system allows players to receive specific and effective feedback in real time to improve their performance, and also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[1087] The processing flow will be explained below.

[1088] Step 1:

[1089] The user begins batting or pitching practice. As the player practices as usual, the IoT sensors collect motion data, such as the player's bat swing speed and angle, as well as the ball's speed and spin rate.

[1090] Step 2:

[1091] The device (IoT device) collects player movement data in real time, and the collected data is transferred to the user's device via Bluetooth or WiFi via sensors attached to the bat and ball.

[1092] Step 3:

[1093] The terminal (user's smartphone or tablet) temporarily stores the movement data received from the IoT device, and a dedicated application displays the data, allowing the user to check their performance during practice.

[1094] Step 4:

[1095] The device (user's smartphone or tablet) sends the accumulated data to a cloud server. This is usually done automatically after the practice session is completed. The data is uploaded to the server via the Internet.

[1096] Step 5:

[1097] The server receives the operational data sent from the device, first checks the consistency of the data, and corrects any abnormal or missing values.

[1098] Step 6:

[1099] The server uses the generated AI to compare the analyzed motion data with a database of experienced professional players, specifically comparing the player's performance, such as swing speed, angle, ball speed, and spin rate, with those of professional players to identify differences and areas for improvement.

[1100] Step 7:

[1101] The server generates personalized, optimized feedback based on the analysis results. The AI ​​generator then suggests specific ways to improve and practice to the player. For example, "Your swing speed is good, but your swing angle is 10 degrees outward. Here's a practice menu to correct that."

[1102] Step 8:

[1103] The server sends the generated feedback to the user's device, where it is provided in a form that can be easily viewed by the user through a dedicated application.

[1104] Step 9:

[1105] The user opens the app and checks the feedback from the AI, understands specific ways to improve, and what to focus on in the next practice session, and practices accordingly.

[1106] Step 10:

[1107] Users can ask the generated AI questions in real time while practicing, such as "Is this swing correct?" or "What kind of practice should I do next?" through the app.

[1108] Step 11:

[1109] The device receives the user's question and sends it to the cloud server, where the application processes the question and forwards it to the server in real time.

[1110] Step 12:

[1111] The server receives questions from users, and the AI ​​generates appropriate answers for those questions, providing specific and applicable advice by referencing the player's data and a database of professional players.

[1112] Step 13:

[1113] The server sends the generated answer to the user's device, providing real-time feedback to the user.

[1114] Step 14:

[1115] The user can check the answers through the application and reflect them in their next action. Real-time coaching support can improve the player's performance.

[1116] Through the above steps, the present invention realizes a system that provides effective individualized optimal instruction to each player and supports the player's growth.

[1117] Example 1

[1118] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1119] Current training systems for players often collect and analyze motion data manually, making it difficult to obtain fast and effective feedback. Furthermore, these systems are unable to provide optimized feedback for individual players, making it difficult to accurately identify areas for improvement. Furthermore, a lack of real-time coaching support means that players are unable to receive immediate advice during practice.

[1120] 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.

[1121] In this invention, the server includes a correction means for checking the consistency of the transmitted data and correcting it, an analysis means for analyzing the corrected data, and a generation means for generating optimal feedback for the player using a generative AI model based on the analyzed data. This automates the entire process from collecting and analyzing player movement data, generating feedback, and providing real-time coaching, making it possible to provide quick, individually optimized feedback to the player.

[1122] "Collection means" refers to devices and sensors used to collect player movement data.

[1123] "Transfer means" refers to the technology or mechanism used to send collected data to the user's device.

[1124] "Transmission means" refers to the technology or mechanism for sending data from the user's device to the cloud server.

[1125] "Correction means" refers to the technology or mechanism used to check the consistency of data sent to the cloud server and correct abnormal values ​​or missing data.

[1126] "Analysis tools" refers to the technology or mechanisms used to analyze the corrected data and compare the motion data with a database of professional athletes or other standards.

[1127] "Generation means" refers to the technology or mechanism that uses a generative AI model to generate optimal feedback for the player based on the analyzed data.

[1128] "Provision means" refers to the technology or mechanism for transmitting the generated feedback to the user's device and providing it to the user.

[1129] "Motion Data" refers to performance data such as swing speed, angle, ball speed, and spin rate collected during a player's training.

[1130] A "generative AI model" is an artificial intelligence model used in the process of data analysis and feedback generation.

[1131] A "prompt" is a question or request input to a generative AI model, and is the text that serves as the basis for the AI ​​to analyze and generate an answer.

[1132] This invention is a system that collects and analyzes player motion data and provides personalized, optimized feedback. This system consists of a player-dedicated IoT device, a user terminal (smartphone or tablet), and a cloud server.

[1133] Data collection method

[1134] Terminal (IoT device)

[1135] When a user practices batting or pitching as a player, IoT sensors collect real-time motion data such as swing speed, angle, ball speed, and spin rate. The sensors are attached to the bat or ball and collect detailed player data during practice.

[1136] User

[1137] Players simply practice as they normally would without any special operations, and the sensors automatically collect and transmit movement data to the user's device during practice.

[1138] Data Transfer Method

[1139] Device (smartphone or tablet)

[1140] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, where a dedicated application is installed to receive and manage the data.

[1141] Data transmission method

[1142] Terminal

[1143] After the practice session, the user's device automatically sends the collected data to the cloud server. This process is transparent to the user. A dedicated application automatically sends the data to the cloud and stores it on the cloud server.

[1144] Data analysis and feedback generation

[1145] server

[1146] The cloud server checks the integrity of the transmitted data and corrects any abnormal values ​​or missing data. The corrected data is then analyzed using analytical tools, and the player's motion data is compared with a database of other players. For example, if a player's swing speed is slower than that of other players, the underlying motions and muscle strength deficiencies are specifically identified.

[1147] Generation AI

[1148] Based on the analysis results, the generative AI model generates personalized training menus and feedback, suggesting specific ways to improve and daily training plans for each player.

[1149] How to provide feedback

[1150] Device (user's smartphone or tablet)

[1151] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to refer to this feedback for their next practice.

[1152] Coaching Support

[1153] User

[1154] If a player has questions during practice, they can ask the generative AI model questions in real time, such as "Is this swing correct?" or "What practice should I do next?"

[1155] Terminal

[1156] The user's question is sent from the device to a cloud server and analyzed by a generative AI model.

[1157] server

[1158] The generative AI model generates appropriate answers to questions and sends them to the user's device, allowing them to receive real-time coaching and maximize the effectiveness of their practice.

[1159] Specific examples

[1160] Example 1: Batting practice

[1161] When a user takes batting practice, IoT sensors collect swing speed and angle. The collected data is transferred to the user's device and sent to a cloud server. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. The user can then use this feedback to consciously adjust their swing angle during their next practice session.

[1162] Example 2: Pitching practice

[1163] When a user practices pitching, the IoT sensor collects the ball's speed and spin rate. The collected data is transferred to the user's device and sent to a cloud server. The cloud server analyzes the data and generates feedback such as "the ball's speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The user can use this feedback to practice while focusing on the spin rate.

[1164] Prompt Sentence Examples

[1165] "A player has good swing speed, but the swing angle is not right. How do I fix it?"

[1166] "My player's ball velocity is adequate, but he lacks spin. Can you tell me some specific practice methods to increase the spin?"

[1167] This system allows users to receive specific and effective feedback in real time to improve their performance, and also allows coaches to provide accurate guidance to each player, which is expected to improve overall performance.

[1168] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1169] Step 1: Data collection

[1170] The device uses IoT sensors to collect real-time motion data such as swing speed, angle, ball speed, and spin rate when a player practices batting or pitching. Each data point detected by the sensor (e.g., swing speed) is sent to the user's device via Bluetooth or WiFi. The input is the motion data detected by the sensor, and the output is the data sent to the user's device. Specifically, the sensor records the swing speed every time the player swings the bat and sends it wirelessly to the device.

[1171] Step 2: Data Transfer

[1172] The user's device manages the received motion data using a dedicated application. This application stores the data in local storage immediately after receiving it via Bluetooth or WiFi. The input is motion data from the sensor, and the output is data stored in the device's local storage. Specifically, every time the player swings, data is displayed on the device and immediately accumulated within the application.

[1173] Step 3: Send data

[1174] When the user's device finishes practicing, it automatically sends the collected data to a cloud server. This is often done via Wi-Fi. The input is the movement data stored in the local storage, and the output is the data sent to the cloud server. Specifically, when the practice is finished, the application displays "Data transmission completed."

[1175] Step 4: Data integrity check

[1176] The server checks the integrity of the data it receives and performs corrections if outliers or missing data are found. The input is the raw data sent to the cloud server, and the output is the corrected data that has been checked for integrity. Specifically, if a data point sent to the database is outside the abnormal range, the data is automatically corrected.

[1177] Step 5: Data analysis

[1178] The server analyzes the corrected data and compares the player's motion data with a database of other players. A generative AI model is used for the analysis. The input is the corrected data, and the output is the analysis results. Specifically, the swing speed and angle are compared with other players' data to detect any differences.

[1179] Step 6: Feedback generation

[1180] The server uses a generative AI model based on the analysis results to generate optimal feedback for the player. The input is the analysis results, and the output is the generated feedback. Specific actions are suggested for improvement, such as "your swing speed is good, but your angle is too high."

[1181] Step 7: Provide feedback

[1182] The server sends the generated feedback to the user's device, which then displays it through a dedicated application. The input is the generated feedback, and the output is the feedback displayed on the user's device. Specifically, a notification in the application notifies the user that feedback has been received, allowing them to view the details.

[1183] Step 8: Real-time questions and coaching support

[1184] Users can pose questions to the generative AI model in real time through a dedicated application. For example, they can ask, "Is this swing correct?" This question is sent to the server via the device, and the generative AI model analyzes it. Appropriate advice is generated from the analysis results and sent to the device. The input is the question from the user, and the output is the answer generated by the generative AI model. Specifically, when a question is entered, the server analyzes it and the results are displayed on the device in real time, allowing the user to receive immediate feedback.

[1185] (Application example 1)

[1186] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1187] While automation using robots is progressing in modern factories, issues remain with regard to the efficiency and quality control of robot operations. In particular, there is a demand for systems that can collect and analyze each robot's operation data in real time and provide optimal feedback each time. However, existing systems have problems such as low data collection accuracy and time-consuming analysis. The present invention aims to solve these problems and improve the efficiency and quality of robot operations in factories.

[1188] 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.

[1189] In this invention, the server includes a collection means for collecting robot operation data, a transfer means for transferring the data collected by the collection means to a user's terminal, a transmission means for transmitting the data transferred by the transfer means to a cloud server, a generation means in the cloud server for analyzing the data transmitted by the transmission means and generating optimal feedback for the robot, and a providing means for transmitting the feedback generated by the generation means to the user's terminal, thereby making it possible to collect and analyze robot operation data in real time and provide accurate feedback.

[1190] A "robot" is a mechanical device used to perform automated work in factories and the like, and is a general term for mechanical devices that can execute motion control.

[1191] "Motion data" refers to data relating to the robot's motion, and specifically includes data on motion speed, motion angle, and force.

[1192] "Collection means" refers to a means for collecting motion data using sensors and devices attached to the robot.

[1193] "Transfer means" refers to the means for transferring collected operational data to the user's device, and generally uses communication technologies such as Bluetooth or WiFi.

[1194] The "transmission means" is a means for transmitting the data transferred to the user's terminal by the transfer means to the cloud server.

[1195] A "cloud server" is a remote server device accessible via the Internet, and is a computer resource that can store and analyze large amounts of data.

[1196] The "generation means" is a means for analyzing the data transmitted by the transmission means in the cloud server and generating optimal feedback for the robot.

[1197] The "providing means" is a means for transmitting the feedback generated by the generating means to the user's terminal.

[1198] This invention relates to a system that collects and analyzes the operation data of factory robots and provides individual optimal feedback. This system consists of the following main elements:

[1199] System Configuration

[1200] The system consists of sensors attached to the robot, the user's device (e.g., a smartphone or tablet), and a cloud server.

[1201] Data collection method

[1202] Collection Method

[1203] Sensors attached to the robot collect real-time operational data such as movement speed, movement angle, and force. For example, pressure sensors, acceleration sensors, gyro sensors, etc. can be attached to robots working on factory production lines to obtain various types of data.

[1204] User

[1205] Without any special operations by factory managers or engineers, the robots simply continue to operate as usual, and the sensors automatically collect data and transfer it to the user's device.

[1206] Data Transfer Method

[1207] Transfer Method

[1208] Collected data is transmitted to the user's device in real time via Bluetooth or WiFi, simplifying on-site operation and improving data collection efficiency.

[1209] User

[1210] A dedicated application is installed on the user's device, and this application receives and manages the data. For example, by installing the dedicated application on a smartphone, you can check the operation data of a robot in a factory.

[1211] Data transmission method

[1212] Transmission method

[1213] The user's device sends the collected data to a cloud server. This happens automatically, so the user does not need to be aware of it. For example, a smartphone app automatically uploads data to the cloud.

[1214] Data analysis and feedback generation

[1215] Cloud Server

[1216] The cloud server receives the transmitted data and first checks its integrity. If any outliers or missing data are identified, corrections are made. Next, the data is analyzed using a generative AI model to evaluate the robot's operational efficiency and quality.

[1217] generation means

[1218] Based on the analysis results, the generative AI model identifies the optimal individual movement method and areas for improvement, and generates feedback. For example, if the robot's movement speed is appropriate but the movement angle is inappropriate, it will generate feedback that "the movement angle needs to be corrected."

[1219] How to provide feedback

[1220] Providing means

[1221] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to adjust the robot's behavior based on this feedback.

[1222] Coaching Support

[1223] User

[1224] Users can ask the generative AI model questions in real time, such as "Is this action efficient?" or "What should I do next?", and the generative AI model will respond with immediate advice.

[1225] Prompt Sentence Examples

[1226] For example, you can enter the following prompt:

[1227] "Analyze the robot's motion data and generate feedback to optimize efficiency and reduce errors."

[1228] "Tell me what adjustments I should make next."

[1229] The above system enables robots in the factory to operate efficiently, improving overall productivity and quality.

[1230] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1231] Step 1:

[1232] Collecting robot movement data

[1233] Input: Sensors attached to the robot acquire movement data (movement speed, movement angle, force).

[1234] Output: Raw motion speed, motion angle and force dataset.

[1235] Specific behavior: Sensors monitor the robot's behavior in real time and measure and record the necessary physical parameters, for example, pressure sensors measure the robot's movement force, and gyro sensors measure the movement angle.

[1236] Step 2:

[1237] Data Transfer

[1238] Input: Collected behavioral data.

[1239] Output: Data transfer to the user's device.

[1240] How it works: Data collected from sensors is transmitted to the user's device via Bluetooth or WiFi, where a dedicated application is installed. This application receives and temporarily stores the data.

[1241] Step 3:

[1242] Sending data to a cloud server

[1243] Input: Operational data transferred to the user's device.

[1244] Output: Data sent to the cloud server.

[1245] How it works: A dedicated application on the user's device automatically sends the collected data to a cloud server via the Internet, allowing the cloud server to receive the data for analysis.

[1246] Step 4:

[1247] Data Integrity Check

[1248] Input: The motion data sent to the cloud server.

[1249] Output: Data that has been checked for consistency or corrected.

[1250] Specific operation: The cloud server first checks the integrity of the received data. If outliers or missing data are found, the outliers are filtered out and missing values ​​are imputed.

[1251] Step 5:

[1252] Data analysis and feedback generation

[1253] Input: Data whose integrity has been checked.

[1254] Output: Analysis of the robot's operation efficiency and quality, along with optimal feedback.

[1255] Specific operation: A generative AI model installed on a cloud server analyzes the data whose consistency has been confirmed. For example, it evaluates whether the movement speed is appropriate or whether there are any problems with the movement angle, and based on that, it generates areas for improvement and optimal operation methods.

[1256] Step 6:

[1257] Providing Feedback

[1258] Input: Feedback from the generative AI model.

[1259] Output: Feedback sent to the user's device.

[1260] Specific behavior: The cloud server sends the generated feedback to the user's device, where it is displayed by a dedicated application. The user can then adjust the robot's behavior based on this feedback.

[1261] Step 7:

[1262] Real-time coaching support

[1263] Input: The user's question (prompt sentence).

[1264] Output: The answer from the generative AI model.

[1265] Specific Actions: When a user sends a question to the generative AI model in real time, the cloud server analyzes the question, generates an appropriate answer, and delivers it to the user's device. For example, in response to a question such as "Is this action efficient?", it is possible to provide specific feedback such as "The speed of the action is appropriate, but the angle of the action should be improved by 10 degrees."

[1266] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1267] This invention proposes a system that collects and analyzes player movement data, and recognizes and utilizes the user's emotional data to provide personalized and optimal feedback. This system is realized through the following steps.

[1268] System Configuration

[1269] The main elements of the system are a player-dedicated IoT device (including sensors), the user's device (smartphone or tablet), a cloud server, and an emotion engine that recognizes the user's emotions.

[1270] Data collection method

[1271] Terminal (IoT device)

[1272] As players practice batting and pitching, sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate. This collection method provides detailed player data.

[1273] User

[1274] Players simply practice as they normally would, with no special operations required. The sensors automatically collect data and transfer it to the user's device during practice.

[1275] Data Transfer Method

[1276] Device (smartphone or tablet)

[1277] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, and a dedicated application is installed on the user's device to receive and manage the data.

[1278] Data transmission method

[1279] Terminal

[1280] Once the user's training session is over, the collected data is sent to the cloud server automatically, without the user needing to be aware of it.

[1281] Collecting Emotional Data

[1282] Device (smartphone or tablet)

[1283] The user's device is equipped with an emotion engine that acquires emotional data in real time through facial expression recognition and voice analysis, thereby understanding the player's emotional state.

[1284] Data analysis and feedback generation

[1285] server

[1286] The cloud server receives the transmitted motion data and first checks the data for consistency. If any abnormal values ​​or missing data are found, correction processing is performed. Next, the generation AI is used to analyze the player's motion data.

[1287] Specifically, the system compares a player's data with a database of professional players to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional players, the system will identify the specific movements and muscle strength deficiencies that are causing this.

[1288] generation means

[1289] Based on the results of the analysis, the AI ​​generates personalized feedback that is optimized for each player. This generation method suggests specific ways to improve and daily practice plans for each player.

[1290] Feedback adjustment using emotional data

[1291] server

[1292] The cloud server also takes into account the player's emotional data acquired by the emotion engine and customizes the feedback content. For example, if a player feels tired or impatient during practice, it generates encouraging messages or feedback suggesting appropriate breaks.

[1293] How to provide feedback

[1294] Device (user's smartphone or tablet)

[1295] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to view it and reflect it in their next practice.

[1296] Coaching Support

[1297] User

[1298] During practice, users can ask the AI ​​generator questions in real time, such as "Is this swing correct?" or "What kind of practice should I do next?", and the AI ​​generator will respond with immediate advice.

[1299] Terminal

[1300] The user's question is sent from the device to the server and analyzed by the generating AI.

[1301] server

[1302] The generative AI generates appropriate answers to questions and sends them to the user's device, allowing the user to receive real-time coaching and maximize the effectiveness of their practice.

[1303] Specific examples

[1304] Example 1: Batting practice

[1305] As a player takes batting practice, IoT sensors collect swing speed and angle. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. Using an emotion engine, encouraging messages such as "pay attention to this point in your next practice" are also added. The user can then see this and consciously correct their swing angle in their next practice.

[1306] Example 2: Pitching practice

[1307] As the player practices pitching, the IoT sensor collects ball speed and spin rate. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The emotion engine may also suggest things like "Take a short break." This allows the user to practice while paying attention to the spin rate.

[1308] This system not only allows players to receive specific and effective feedback in real time to improve their performance, but also provides appropriate support based on their emotional state. It also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[1309] The processing flow will be explained below.

[1310] Step 1:

[1311] The user begins batting or pitching practice. As the player practices as usual, the IoT sensors collect motion data, such as the player's bat swing speed and angle, as well as the ball's speed and spin rate.

[1312] Step 2:

[1313] The device (IoT device) collects player movement data in real time, and the collected data is transferred to the user's device via Bluetooth or WiFi via sensors attached to the bat and ball.

[1314] Step 3:

[1315] The device (user's smartphone or tablet) temporarily stores the motion data received from the IoT device. A dedicated application displays the data, allowing the user to check their performance during practice. The device's built-in emotion engine also simultaneously collects emotional data through facial recognition and voice analysis of the player.

[1316] Step 4:

[1317] The device (user's smartphone or tablet) transmits the accumulated movement and emotion data to a cloud server. This is usually done automatically after the practice session is completed. The data is uploaded to the server via the internet.

[1318] Step 5:

[1319] The server receives the motion and emotion data sent from the device. First, it checks the consistency of the data and corrects any outliers or missing data. It also verifies that the motion and emotion data are properly linked.

[1320] Step 6:

[1321] The server uses the generated AI to compare the analyzed motion data with a database of experienced professional players, specifically comparing the player's performance, such as swing speed, angle, ball speed, and spin rate, with those of professional players to identify differences and areas for improvement.

[1322] Step 7:

[1323] The server evaluates the player's mental state based on emotional data, and if the player is feeling tired or impatient, this information is reflected in the analysis results.

[1324] Step 8:

[1325] The server generates personalized, optimized feedback based on the analysis results. The AI ​​generator then suggests specific ways to improve and practice to the player. Furthermore, it adjusts the feedback based on emotional data, suggesting a break for tired players and encouraging active practice for energetic players.

[1326] Step 9:

[1327] The server sends the generated feedback to the user's device, where it is provided in a form that can be easily viewed by the user through a dedicated application.

[1328] Step 10:

[1329] The user opens the app and checks the feedback from the AI, understands specific ways to improve, and what to focus on in the next practice session, and practices accordingly.

[1330] Step 11:

[1331] Users can ask the generated AI questions in real time while practicing, such as "Is this swing correct?" or "What kind of practice should I do next?" through the app.

[1332] Step 12:

[1333] The device receives the user's question and sends it to the cloud server, where the application processes the question and forwards it to the server in real time.

[1334] Step 13:

[1335] The server receives questions from users, and the AI ​​generates appropriate answers for those questions, providing specific and applicable advice by referencing the player's data and a database of professional players.

[1336] Step 14:

[1337] The server sends the generated answer to the user's device, providing real-time feedback to the user.

[1338] Step 15:

[1339] The user can check the answers through the application and reflect them in their next action. Real-time coaching support can improve the player's performance.

[1340] By implementing the above steps, the present invention realizes a system that provides effective, individualized guidance to each player and supports their growth. By taking emotion data into consideration, it becomes possible to provide more flexible feedback that is tailored to the player's psychological state.

[1341] Example 2

[1342] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1343] While conventional sports training systems collect and analyze player movement data, it is difficult to grasp the player's emotional state in real time and provide appropriate feedback. Furthermore, the process of generating individually optimized feedback is unable to reflect the player's emotions, making effective instruction difficult.

[1344] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a collection means for collecting player's motion data, a generation means for analyzing the collected data and generating feedback, an emotion collection means for collecting user's emotion data, and an adjustment means for adjusting the feedback using the collected emotion data. This makes it possible to provide individually optimized feedback by taking into account both the player's motion data and emotion data.

[1345] "Collection means" refers to a means for acquiring player movement data, such as a sensor or other device.

[1346] The "transfer means" is a means for transmitting the data acquired by the collection means to the user's terminal.

[1347] "Transmission means" refers to a means for transmitting data from a user's terminal to a cloud server.

[1348] The "generation means" is a means in the cloud server that analyzes the data transmitted by the transmission means and generates optimal feedback for the player.

[1349] "Emotion collection means" refers to means for acquiring user emotional data, and includes facial expression recognition and voice analysis technologies.

[1350] The "adjustment means" is a means for optimizing and adjusting the generated feedback using the emotion data collected by the emotion collection means.

[1351] The "providing means" is a means for transmitting the feedback generated by the generating means and adjusting means to the user's terminal and providing the feedback.

[1352] "Motion data" refers to data that measures the player's movements, including speed, angle, amount of movement, number of rotations, etc.

[1353] "Emotional data" is data that indicates the user's emotional state and is obtained from facial expressions and voice.

[1354] A "cloud server" refers to a server on the Internet used for analyzing and storing data.

[1355] This invention is a system that collects and analyzes player movement data, recognizes and utilizes the user's emotional data, and provides personalized and optimal feedback. This system consists of a player-dedicated IoT device (including sensors), the user's device (smartphone or tablet), a cloud server, and an emotion engine that recognizes the user's emotions.

[1356] Data collection

[1357] Terminal (IoT device) processing:

[1358] As players practice batting and pitching, sensors attached to the bat and ball collect real-time data such as swing speed, angle, ball speed, and spin rate, which is then transmitted to the user's device via Bluetooth or Wi-Fi.

[1359] User Action:

[1360] Players practice as usual, with no special operations required. The sensors automatically collect data and transmit it to the user's device during practice.

[1361] Data Transfer

[1362] Device (smartphone or tablet) processing:

[1363] The collected data is received and managed in real time by a dedicated application via Bluetooth or WiFi. The received data is temporarily stored on the device and can be viewed by the user at any time.

[1364] Data transmission

[1365] Terminal handling:

[1366] Once the user's training is complete, the collected data is sent to the cloud server. This data transfer occurs in the background, so the user does not need to be aware of it.

[1367] Collecting Emotional Data

[1368] Device (smartphone or tablet) processing:

[1369] The user's device is equipped with an emotion engine that uses a camera and microphone to analyze the player's facial expressions and voice, thereby obtaining the player's emotional data in real time.

[1370] Data analysis and feedback generation

[1371] Server Action:

[1372] The cloud server receives the motion data sent from the user's device. First, it checks the data for consistency and corrects any outliers or missing data. It then analyzes the motion data using a generative AI model and compares the player's data with a database of professional golfers to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional golfers, the cloud server will specifically identify the underlying motions and muscle weaknesses.

[1373] Feedback adjustment using emotional data

[1374] Server Action:

[1375] The cloud server also takes into account the player's emotional data acquired by the emotion engine and customizes the content of the feedback. For example, if a player feels fatigued or impatient during practice, it generates encouraging messages or feedback suggesting appropriate breaks.

[1376] Providing Feedback

[1377] Device (user's smartphone or tablet) processing:

[1378] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to incorporate this feedback into their next practice.

[1379] Coaching Support

[1380] User Action:

[1381] Users can ask the generative AI model questions in real time while practicing, such as "Is this swing correct?" or "What practice should I do next?"

[1382] Terminal handling:

[1383] The user's question is sent from the device to a cloud server and analyzed by a generative AI model.

[1384] Server Action:

[1385] The generative AI model generates appropriate answers to the questions, which are then sent back to the user's device, allowing them to receive real-time coaching and maximize the effectiveness of their practice.

[1386] Specific examples

[1387] Batting practice example:

[1388] When a user takes batting practice, sensors collect swing speed and angle, and the data is transferred to the user's device. After practice is completed, the data is sent to a cloud server, which generates analysis results and feedback such as "your swing speed is good, but your angle needs improvement." Based on the user's emotional data, an encouraging message is also added, such as "pay attention to this point in your next practice." This encourages the user to be conscious of their swing angle and try to correct it in their next practice.

[1389] Pitching practice example:

[1390] When a user practices pitching, sensors collect ball speed and spin rate, and the data is transferred to the user's device. After practice, the data is sent to a cloud server, which generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient." Based on emotional data, the feedback may include suggestions such as "Take a short break." The user can then practice with an awareness of the spin rate.

[1391] Prompt Sentence Examples

[1392] Batting Practice Prompts

[1393] "Analyze swing speed and angle data during batting practice and provide feedback on areas for improvement."

[1394] Pitching Practice Prompts

[1395] "Please analyze the ball speed and spin rate data during pitching practice and tell me how to improve."

[1396] This system not only allows players to receive specific and effective feedback in real time to improve their performance, but also provides appropriate support based on their emotional state. It also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[1397] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1398] Step 1:

[1399] Data collection

[1400] Terminal (IoT device) processing:

[1401] 1. Players begin batting and pitching practice.

[1402] 2. Sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate.

[1403] 3. Input: Player Actions

[1404] 4. Output: swing speed, angle, ball speed, spin rate data

[1405] 5. The data acquired by the sensor is transferred to the user's device via Bluetooth or WiFi.

[1406] Step 2:

[1407] Data Transfer

[1408] Device (smartphone or tablet) processing:

[1409] 1. A dedicated application receives data from the sensor in real time via Bluetooth or WiFi.

[1410] 2. The received data is temporarily stored on the device.

[1411] 3. Input: Motion data from sensors

[1412] 4. Output: Temporarily saved data on the device

[1413] 5. Users can check the data at any time through a dedicated application.

[1414] Step 3:

[1415] Data transmission

[1416] Terminal handling:

[1417] 1. After the practice session, the device automatically sends the collected movement data to the cloud server.

[1418] 2. Input: Saved operating data

[1419] 3. Output: Data sent to the cloud server

[1420] 4. Data transmission occurs in the background, so users do not need to be aware of it.

[1421] Step 4:

[1422] Collecting Emotional Data

[1423] Device (smartphone or tablet) processing:

[1424] 1. The user's device is equipped with an emotion engine that uses the camera and microphone to analyze the player's facial expressions and voice.

[1425] 2. Obtain player emotional data in real time through facial expression recognition and voice analysis.

[1426] 3. Input: Player's facial expressions and voice

[1427] 4. Output: Emotion data

[1428] Step 5:

[1429] Data analysis and feedback generation

[1430] Server Action:

[1431] 1. The cloud server receives the operation data sent from the user's device.

[1432] 2. The server checks the consistency of the data and performs correction processing if abnormal values ​​or missing data are found.

[1433] 3. Input: Operation data sent to the cloud server

[1434] 4. Output: Consistent operational data

[1435] 5. A generative AI model analyzes the data and compares the player's data with a database of professional athletes.

[1436] 6. Identify performance gaps and areas for improvement.

[1437] 7. Input: Consistent operational data

[1438] 8. Output: Analysis results (performance differences, areas for improvement)

[1439] 9. The generation means generates individually optimized feedback based on the analysis results.

[1440] 10. Input: Analysis results

[1441] 11. Output: Feedback data

[1442] Step 6:

[1443] Feedback adjustment using emotional data

[1444] Server Action:

[1445] 1. The cloud server receives the player's emotion data obtained by the emotion engine.

[1446] 2. The server analyzes the emotional data and customizes the content of the generated feedback.

[1447] 3. If a player feels fatigued or impatient during practice, generate encouraging messages and feedback suggesting appropriate breaks.

[1448] 4. Input: Emotion data, feedback data

[1449] 5. Output: Customized feedback

[1450] Step 7:

[1451] Providing Feedback

[1452] Device (user's smartphone or tablet) processing:

[1453] 1. Customized feedback is sent from the cloud server to the user's device.

[1454] 2. Feedback is provided to users in real time through a dedicated application.

[1455] 3. Input: Customized Feedback

[1456] 4. Output: Present feedback to the user

[1457] Step 8:

[1458] Coaching Support

[1459] User Action:

[1460] 1. Users can ask questions to the generative AI model in real time while practicing, such as "Is this swing correct?" or "What practice should I do next?"

[1461] 2. Input: User Question

[1462] 3. Output: Query data to the server

[1463] Terminal handling:

[1464] 1. The user's question is sent from the device to the cloud server.

[1465] 2. Input: User's question data

[1466] 3. Output: Data sent to the cloud server

[1467] Server Action:

[1468] 1. The generative AI model receives the question, analyzes it, and generates an appropriate answer.

[1469] 2. The answer is sent back to the user's device.

[1470] 3. Input: User's question data

[1471] 4. Output: Generated answers

[1472] Terminal handling:

[1473] 1. The user's device receives the answer sent from the cloud server.

[1474] 2. Present to the user through a dedicated application.

[1475] 3. Input: Response data from the cloud server

[1476] 4. Output: Answer presented to the user

[1477] (Application example 2)

[1478] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1479] In factories, it is desirable to monitor the operating status of automated equipment such as robot arms in real time to enable efficient maintenance and operation optimization. However, current systems take time to collect and analyze operation data, making it difficult to provide appropriate feedback quickly. In addition, feedback does not take into account the emotional state of the operator, which increases the risk of fatigue and operational errors during work.

[1480] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a collection means for collecting operation data of the robot arm, a transfer means for transferring the data collected by the collection means to a user's terminal, a transmission means for transmitting the data transferred by the transfer means to a cloud server, a generation means in the cloud server for analyzing the data transmitted by the transmission means and generating feedback for optimizing the operation efficiency of the robot arm, a providing means for transmitting the feedback generated by the generation means to the user's terminal, and a means for the generation means to acquire emotion data and adjust the feedback based on the analysis results. This makes it possible to grasp the operating status of automated equipment in a factory in real time and quickly provide appropriate feedback that takes into account the emotional state of operators.

[1481] "Motion data" refers to information such as speeds, angles, and forces generated by a robotic arm or other automated device during operation.

[1482] "Collection means" refers to a device or system for acquiring operational data using a robotic arm or other sensor.

[1483] "Transportation Method" refers to the method or protocol for moving or transmitting collected data to a user's device.

[1484] "Transmission means" refers to a device or method for transmitting data from a user's terminal to a cloud server.

[1485] A "cloud server" refers to a remote server that can be accessed by multiple users via the Internet and is used to store and analyze data.

[1486] "Analysis" refers to the process of processing collected operational data to extract useful information.

[1487] "Generator" refers to a device or algorithm for generating feedback based on the analysis results.

[1488] "Providing means" refers to a device or method for delivering the generated feedback to the user's terminal.

[1489] "Emotional data" refers to data that indicates the emotional state of an operator obtained through facial expressions and voice analysis.

[1490] A "generative AI model" refers to an artificial intelligence model that uses machine learning technology to analyze data and generate optimal feedback.

[1491] A "prompt sentence" refers to an input sentence provided to a generative AI model to perform a specific task.

[1492] To implement this invention, the following system must be configured. The system is composed of a collection means for collecting operation data of the robot arm, a transfer means for transferring the collected data to a user's terminal, and a transmission means for transmitting the transferred data to a cloud server. The cloud server also requires a generation means for analyzing the transferred data and generating feedback that optimizes the operational efficiency of the robot arm. The system also includes a provision means for providing the generated feedback to the user's terminal. Means for acquiring emotion data and adjusting the feedback based on the analysis results are also important elements.

[1493] Hardware and software used

[1494] Robot arm with sensors: The robot arm is equipped with force, speed, and angle sensors that collect movement data.

[1495] User device (smartphone / tablet): A dedicated application is installed on the device, which receives and transfers collected data.

[1496] Cloud server: Uses an EC2 instance from Amazon Web Services (AWS) and DynamoDB as the database.

[1497] Emotion engine: Uses facial recognition and speech analysis APIs like Amazon Rekognition and Google Cloud Vision to collect operator emotion data.

[1498] Generative AI model: Analyzes data using the OpenAI GPT model and generates optimal feedback.

[1499] Data processing and calculation

[1500] Data collection: Sensors mounted on the robot arm measure speed, angle, and force during movement, collecting data in real time.

[1501] Data transfer: The collected data is transferred to the user device via Bluetooth or WiFi. After transfer, the data is sent from the user device to the cloud server.

[1502] Data analysis: The data sent to the cloud server is checked for consistency and analyzed by the generative AI model. Based on the analysis results, feedback is generated to optimize the operation of the robot arm.

[1503] Emotion data acquisition: The emotion engine installed in the user device recognizes the operator's facial expressions and analyzes their voice to acquire emotion data.

[1504] Feedback generation: The generative AI model generates feedback based on operation data and emotional data, and adjusts according to the user's emotional state.

[1505] Feedback provision: The generated feedback is sent to the user's terminal and provided to the operator through a dedicated application.

[1506] Specific examples

[1507] Analysis of behavioral data:

[1508] When the robot arm performs welding work, the speed sensor measures the speed of the movement, which is collected in real time. For example, if the speed data is not within the specified range, the robot will generate feedback such as "The speed is too fast, please reduce it to within the set range."

[1509] Adjustment based on emotional data:

[1510] If the operator is tired, feedback such as "Take a short break" is added.

[1511] Prompt Sentence Examples

[1512] "Analyze the following robot arm motion data and generate appropriate feedback:

[1513] Operating speed: 10m / s

[1514] Operating angle: 45 degrees

[1515] Operating force: 20N

[1516] Operator's emotional state: Fatigue

[1517] Appropriate feedback: You're going too fast, slow down within the limits. Take a break.

[1518] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1519] Step 1:

[1520] Users collect operation data of robot arms in factories. Sensors mounted on the robot arms measure speed, angle, and force data in real time. No special operation is required by the user. Collected data input: speed, angle, force. Output: collected operation data.

[1521] Step 2:

[1522] The device transfers the collected data to the user's smartphone or tablet via Bluetooth or WiFi. During this process, the device receives data from the sensor and transfers the data to the device via stable communication. Input: Operational data from the sensor. Output: Operational data transferred to the device.

[1523] Step 3:

[1524] The device sends data to the cloud server. In this process, data is sent in real time from the user's device to the cloud server through a dedicated application. Input: Transferred operation data. Output: Operation data sent to the cloud server.

[1525] Step 4:

[1526] The server receives the data sent and checks its integrity. If outliers or missing data are identified, corrections and data cleaning are performed. Input: Operational data sent to the cloud server. Output: Data whose integrity has been checked.

[1527] Step 5:

[1528] The server analyzes the data using analytical tools. It uses a generative AI model (OpenAI GPT model) to analyze the movement data by comparing it with a database of professional athletes. Input: Data with verified consistency. Output: Analysis results.

[1529] Step 6:

[1530] The server uses facial recognition and voice analysis APIs to obtain the user's emotional data, which is taken into account when generating feedback. Input: User's facial and voice data. Output: Emotional data.

[1531] Step 7:

[1532] The server generates optimal feedback based on the analysis results and emotion data. A generative AI model is used to create specific feedback based on behavioral and emotion data. Feedback is obtained by generating prompt sentences and inputting them into the model. Input: Analysis results, emotion data. Output: Generated feedback.

[1533] Step 8:

[1534] The server sends the generated feedback to the user's terminal, which displays it. The user receives the feedback and reflects it in their next operation. Input: Generated feedback. Output: Sending and displaying feedback to the user's terminal.

[1535] Specific prompt examples

[1536] "Analyze the following robot arm motion data and generate appropriate feedback:

[1537] Operating speed: 10m / s

[1538] Operating angle: 45 degrees

[1539] Operating force: 20N

[1540] Operator's emotional state: Fatigue

[1541] Appropriate feedback: You're going too fast, slow down within the limits. Take a break.

[1542] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1543] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1544] 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.

[1545] [Fourth embodiment]

[1546] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1547] 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.

[1548] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1549] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1550] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1551] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1552] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1553] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1554] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1555] 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.

[1556] 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.

[1557] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1558] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1559] This invention proposes a system that collects and analyzes player motion data and provides optimal feedback to each player. This system is realized through the following steps.

[1560] System Configuration

[1561] The main elements of the system are IoT devices (including sensors) dedicated to the player, the user's terminal (smartphone or tablet), and a cloud server.

[1562] Data collection method

[1563] Terminal (IoT device)

[1564] As players practice batting and pitching, sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate. This collection method provides detailed player data.

[1565] User

[1566] Players simply practice as they normally would, with no special operations required. The sensors automatically collect data and transfer it to the user's device during practice.

[1567] Data Transfer Method

[1568] Device (smartphone or tablet)

[1569] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, and a dedicated application is installed on the user's device to receive and manage the data.

[1570] Data transmission method

[1571] Terminal

[1572] Once the user's training session is over, the collected data is sent to the cloud server automatically, without the user needing to be aware of it.

[1573] Data analysis and feedback generation

[1574] server

[1575] The cloud server receives the transmitted data and first checks the data for consistency. If any outliers or missing data are found, corrections are made. Next, the generated AI is used to analyze the player's movement data.

[1576] Specifically, the system compares a player's data with a database of professional players to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional players, the system will identify the specific movements and muscle strength deficiencies that are causing this.

[1577] generation means

[1578] Based on the results of the analysis, the AI ​​generates an individually optimized training menu and feedback, proposing specific improvement methods and daily training plans to the player.

[1579] How to provide feedback

[1580] Device (user's smartphone or tablet)

[1581] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to view it and reflect it in their next practice.

[1582] Coaching Support

[1583] User

[1584] During practice, users can ask the AI ​​generator questions in real time, such as "Is this swing correct?" or "What kind of practice should I do next?", and the AI ​​generator will respond with immediate advice.

[1585] Terminal

[1586] The user's question is sent from the device to the server and analyzed by the generating AI.

[1587] server

[1588] The generative AI generates appropriate answers to questions and sends them to the user's device, allowing the user to receive real-time coaching and maximize the effectiveness of their practice.

[1589] Specific examples

[1590] Example 1: Batting practice

[1591] As a player takes batting practice, IoT sensors collect swing speed and angle. The data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. The user can then review this feedback and consciously adjust their swing angle during their next practice session.

[1592] Example 2: Pitching practice

[1593] As a player practices pitching, IoT sensors collect ball speed and spin rate. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The user then practices while paying attention to the spin rate.

[1594] This system allows players to receive specific and effective feedback in real time to improve their performance, and also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[1595] The processing flow will be explained below.

[1596] Step 1:

[1597] The user begins batting or pitching practice. As the player practices as usual, the IoT sensors collect motion data, such as the player's bat swing speed and angle, as well as the ball's speed and spin rate.

[1598] Step 2:

[1599] The device (IoT device) collects player movement data in real time, and the collected data is transferred to the user's device via Bluetooth or WiFi via sensors attached to the bat and ball.

[1600] Step 3:

[1601] The terminal (user's smartphone or tablet) temporarily stores the movement data received from the IoT device, and a dedicated application displays the data, allowing the user to check their performance during practice.

[1602] Step 4:

[1603] The device (user's smartphone or tablet) sends the accumulated data to a cloud server. This is usually done automatically after the practice session is completed. The data is uploaded to the server via the Internet.

[1604] Step 5:

[1605] The server receives the operational data sent from the device, first checks the consistency of the data, and corrects any abnormal or missing values.

[1606] Step 6:

[1607] The server uses the generated AI to compare the analyzed motion data with a database of experienced professional players, specifically comparing the player's performance, such as swing speed, angle, ball speed, and spin rate, with those of professional players to identify differences and areas for improvement.

[1608] Step 7:

[1609] The server generates personalized, optimized feedback based on the analysis results. The AI ​​generator then suggests specific ways to improve and practice to the player. For example, "Your swing speed is good, but your swing angle is 10 degrees outward. Here's a practice menu to correct that."

[1610] Step 8:

[1611] The server sends the generated feedback to the user's device, where it is provided in a form that can be easily viewed by the user through a dedicated application.

[1612] Step 9:

[1613] The user opens the app and checks the feedback from the AI, understands specific ways to improve, and what to focus on in the next practice session, and practices accordingly.

[1614] Step 10:

[1615] Users can ask the generated AI questions in real time while practicing, such as "Is this swing correct?" or "What kind of practice should I do next?" through the app.

[1616] Step 11:

[1617] The device receives the user's question and sends it to the cloud server, where the application processes the question and forwards it to the server in real time.

[1618] Step 12:

[1619] The server receives questions from users, and the AI ​​generates appropriate answers for those questions, providing specific and applicable advice by referencing the player's data and a database of professional players.

[1620] Step 13:

[1621] The server sends the generated answer to the user's device, providing real-time feedback to the user.

[1622] Step 14:

[1623] The user can check the answers through the application and reflect them in their next action. Real-time coaching support can improve the player's performance.

[1624] Through the above steps, the present invention realizes a system that provides effective individualized optimal instruction to each player and supports the player's growth.

[1625] Example 1

[1626] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1627] Current training systems for players often collect and analyze motion data manually, making it difficult to obtain fast and effective feedback. Furthermore, these systems are unable to provide optimized feedback for individual players, making it difficult to accurately identify areas for improvement. Furthermore, a lack of real-time coaching support means that players are unable to receive immediate advice during practice.

[1628] 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.

[1629] In this invention, the server includes a correction means for checking the consistency of the transmitted data and correcting it, an analysis means for analyzing the corrected data, and a generation means for generating optimal feedback for the player using a generative AI model based on the analyzed data. This automates the entire process from collecting and analyzing player movement data, generating feedback, and providing real-time coaching, making it possible to provide quick, individually optimized feedback to the player.

[1630] "Collection means" refers to devices and sensors used to collect player movement data.

[1631] "Transfer means" refers to the technology or mechanism used to send collected data to the user's device.

[1632] "Transmission means" refers to the technology or mechanism for sending data from the user's device to the cloud server.

[1633] "Correction means" refers to the technology or mechanism used to check the consistency of data sent to the cloud server and correct abnormal values ​​or missing data.

[1634] "Analysis tools" refers to the technology or mechanisms used to analyze the corrected data and compare the motion data with a database of professional athletes or other standards.

[1635] "Generation means" refers to the technology or mechanism that uses a generative AI model to generate optimal feedback for the player based on the analyzed data.

[1636] "Provision means" refers to the technology or mechanism for transmitting the generated feedback to the user's device and providing it to the user.

[1637] "Motion Data" refers to performance data such as swing speed, angle, ball speed, and spin rate collected during a player's training.

[1638] A "generative AI model" is an artificial intelligence model used in the process of data analysis and feedback generation.

[1639] A "prompt" is a question or request input to a generative AI model, and is the text that serves as the basis for the AI ​​to analyze and generate an answer.

[1640] This invention is a system that collects and analyzes player motion data and provides personalized, optimized feedback. This system consists of a player-dedicated IoT device, a user terminal (smartphone or tablet), and a cloud server.

[1641] Data collection method

[1642] Terminal (IoT device)

[1643] When a user practices batting or pitching as a player, IoT sensors collect real-time motion data such as swing speed, angle, ball speed, and spin rate. The sensors are attached to the bat or ball and collect detailed player data during practice.

[1644] User

[1645] Players simply practice as they normally would without any special operations, and the sensors automatically collect and transmit movement data to the user's device during practice.

[1646] Data Transfer Method

[1647] Device (smartphone or tablet)

[1648] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, where a dedicated application is installed to receive and manage the data.

[1649] Data transmission method

[1650] Terminal

[1651] After the practice session, the user's device automatically sends the collected data to the cloud server. This process is transparent to the user. A dedicated application automatically sends the data to the cloud and stores it on the cloud server.

[1652] Data analysis and feedback generation

[1653] server

[1654] The cloud server checks the integrity of the transmitted data and corrects any abnormal values ​​or missing data. The corrected data is then analyzed using analytical tools, and the player's motion data is compared with a database of other players. For example, if a player's swing speed is slower than that of other players, the underlying motions and muscle strength deficiencies are specifically identified.

[1655] Generation AI

[1656] Based on the analysis results, the generative AI model generates personalized training menus and feedback, suggesting specific ways to improve and daily training plans for each player.

[1657] How to provide feedback

[1658] Device (user's smartphone or tablet)

[1659] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to refer to this feedback for their next practice.

[1660] Coaching Support

[1661] User

[1662] If a player has questions during practice, they can ask the generative AI model questions in real time, such as "Is this swing correct?" or "What practice should I do next?"

[1663] Terminal

[1664] The user's question is sent from the device to a cloud server and analyzed by a generative AI model.

[1665] server

[1666] The generative AI model generates appropriate answers to questions and sends them to the user's device, allowing them to receive real-time coaching and maximize the effectiveness of their practice.

[1667] Specific examples

[1668] Example 1: Batting practice

[1669] When a user takes batting practice, IoT sensors collect swing speed and angle. The collected data is transferred to the user's device and sent to a cloud server. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. The user can then use this feedback to consciously adjust their swing angle during their next practice session.

[1670] Example 2: Pitching practice

[1671] When a user practices pitching, the IoT sensor collects the ball's speed and spin rate. The collected data is transferred to the user's device and sent to a cloud server. The cloud server analyzes the data and generates feedback such as "the ball's speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The user can use this feedback to practice while focusing on the spin rate.

[1672] Prompt Sentence Examples

[1673] "A player has good swing speed, but the swing angle is not right. How do I fix it?"

[1674] "My player's ball velocity is adequate, but he lacks spin. Can you tell me some specific practice methods to increase the spin?"

[1675] This system allows users to receive specific and effective feedback in real time to improve their performance, and also allows coaches to provide accurate guidance to each player, which is expected to improve overall performance.

[1676] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1677] Step 1: Data collection

[1678] The device uses IoT sensors to collect real-time motion data such as swing speed, angle, ball speed, and spin rate when a player practices batting or pitching. Each data point detected by the sensor (e.g., swing speed) is sent to the user's device via Bluetooth or WiFi. The input is the motion data detected by the sensor, and the output is the data sent to the user's device. Specifically, the sensor records the swing speed every time the player swings the bat and sends it wirelessly to the device.

[1679] Step 2: Data Transfer

[1680] The user's device manages the received motion data using a dedicated application. This application stores the data in local storage immediately after receiving it via Bluetooth or WiFi. The input is motion data from the sensor, and the output is data stored in the device's local storage. Specifically, every time the player swings, data is displayed on the device and immediately accumulated within the application.

[1681] Step 3: Send data

[1682] When the user's device finishes practicing, it automatically sends the collected data to a cloud server. This is often done via Wi-Fi. The input is the movement data stored in the local storage, and the output is the data sent to the cloud server. Specifically, when the practice is finished, the application displays "Data transmission completed."

[1683] Step 4: Data integrity check

[1684] The server checks the integrity of the data it receives and performs corrections if outliers or missing data are found. The input is the raw data sent to the cloud server, and the output is the corrected data that has been checked for integrity. Specifically, if a data point sent to the database is outside the abnormal range, the data is automatically corrected.

[1685] Step 5: Data analysis

[1686] The server analyzes the corrected data and compares the player's motion data with a database of other players. A generative AI model is used for the analysis. The input is the corrected data, and the output is the analysis results. Specifically, the swing speed and angle are compared with other players' data to detect any differences.

[1687] Step 6: Feedback generation

[1688] The server uses a generative AI model based on the analysis results to generate optimal feedback for the player. The input is the analysis results, and the output is the generated feedback. Specific actions are suggested for improvement, such as "your swing speed is good, but your angle is too high."

[1689] Step 7: Provide feedback

[1690] The server sends the generated feedback to the user's device, which then displays it through a dedicated application. The input is the generated feedback, and the output is the feedback displayed on the user's device. Specifically, a notification in the application notifies the user that feedback has been received, allowing them to view the details.

[1691] Step 8: Real-time questions and coaching support

[1692] Users can pose questions to the generative AI model in real time through a dedicated application. For example, they can ask, "Is this swing correct?" This question is sent to the server via the device, and the generative AI model analyzes it. Appropriate advice is generated from the analysis results and sent to the device. The input is the question from the user, and the output is the answer generated by the generative AI model. Specifically, when a question is entered, the server analyzes it and the results are displayed on the device in real time, allowing the user to receive immediate feedback.

[1693] (Application example 1)

[1694] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1695] While automation using robots is progressing in modern factories, issues remain with regard to the efficiency and quality control of robot operations. In particular, there is a demand for systems that can collect and analyze each robot's operation data in real time and provide optimal feedback each time. However, existing systems have problems such as low data collection accuracy and time-consuming analysis. The present invention aims to solve these problems and improve the efficiency and quality of robot operations in factories.

[1696] 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.

[1697] In this invention, the server includes a collection means for collecting robot operation data, a transfer means for transferring the data collected by the collection means to a user's terminal, a transmission means for transmitting the data transferred by the transfer means to a cloud server, a generation means in the cloud server for analyzing the data transmitted by the transmission means and generating optimal feedback for the robot, and a providing means for transmitting the feedback generated by the generation means to the user's terminal, thereby making it possible to collect and analyze robot operation data in real time and provide accurate feedback.

[1698] A "robot" is a mechanical device used to perform automated work in factories and the like, and is a general term for mechanical devices that can execute motion control.

[1699] "Motion data" refers to data relating to the robot's motion, and specifically includes data on motion speed, motion angle, and force.

[1700] "Collection means" refers to a means for collecting motion data using sensors and devices attached to the robot.

[1701] "Transfer means" refers to the means for transferring collected operational data to the user's device, and generally uses communication technologies such as Bluetooth or WiFi.

[1702] The "transmission means" is a means for transmitting the data transferred to the user's terminal by the transfer means to the cloud server.

[1703] A "cloud server" is a remote server device accessible via the Internet, and is a computer resource that can store and analyze large amounts of data.

[1704] The "generation means" is a means for analyzing the data transmitted by the transmission means in the cloud server and generating optimal feedback for the robot.

[1705] The "providing means" is a means for transmitting the feedback generated by the generating means to the user's terminal.

[1706] This invention relates to a system that collects and analyzes the operation data of factory robots and provides individual optimal feedback. This system consists of the following main elements:

[1707] System Configuration

[1708] The system consists of sensors attached to the robot, the user's device (e.g., a smartphone or tablet), and a cloud server.

[1709] Data collection method

[1710] Collection Method

[1711] Sensors attached to the robot collect real-time operational data such as movement speed, movement angle, and force. For example, pressure sensors, acceleration sensors, gyro sensors, etc. can be attached to robots working on factory production lines to obtain various types of data.

[1712] User

[1713] Without any special operations by factory managers or engineers, the robots simply continue to operate as usual, and the sensors automatically collect data and transfer it to the user's device.

[1714] Data Transfer Method

[1715] Transfer Method

[1716] Collected data is transmitted to the user's device in real time via Bluetooth or WiFi, simplifying on-site operation and improving data collection efficiency.

[1717] User

[1718] A dedicated application is installed on the user's device, and this application receives and manages the data. For example, by installing the dedicated application on a smartphone, you can check the operation data of a robot in a factory.

[1719] Data transmission method

[1720] Transmission method

[1721] The user's device sends the collected data to a cloud server. This happens automatically, so the user does not need to be aware of it. For example, a smartphone app automatically uploads data to the cloud.

[1722] Data analysis and feedback generation

[1723] Cloud Server

[1724] The cloud server receives the transmitted data and first checks its integrity. If any outliers or missing data are identified, corrections are made. Next, the data is analyzed using a generative AI model to evaluate the robot's operational efficiency and quality.

[1725] generation means

[1726] Based on the analysis results, the generative AI model identifies the optimal individual movement method and areas for improvement, and generates feedback. For example, if the robot's movement speed is appropriate but the movement angle is inappropriate, it will generate feedback that "the movement angle needs to be corrected."

[1727] How to provide feedback

[1728] Providing means

[1729] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to adjust the robot's behavior based on this feedback.

[1730] Coaching Support

[1731] User

[1732] Users can ask the generative AI model questions in real time, such as "Is this action efficient?" or "What should I do next?", and the generative AI model will respond with immediate advice.

[1733] Prompt Sentence Examples

[1734] For example, you can enter the following prompt:

[1735] "Analyze the robot's motion data and generate feedback to optimize efficiency and reduce errors."

[1736] "Tell me what adjustments I should make next."

[1737] The above system enables robots in the factory to operate efficiently, improving overall productivity and quality.

[1738] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1739] Step 1:

[1740] Collecting robot movement data

[1741] Input: Sensors attached to the robot acquire movement data (movement speed, movement angle, force).

[1742] Output: Raw motion speed, motion angle and force dataset.

[1743] Specific behavior: Sensors monitor the robot's behavior in real time and measure and record the necessary physical parameters, for example, pressure sensors measure the robot's movement force, and gyro sensors measure the movement angle.

[1744] Step 2:

[1745] Data Transfer

[1746] Input: Collected behavioral data.

[1747] Output: Data transfer to the user's device.

[1748] How it works: Data collected from sensors is transmitted to the user's device via Bluetooth or WiFi, where a dedicated application is installed. This application receives and temporarily stores the data.

[1749] Step 3:

[1750] Sending data to a cloud server

[1751] Input: Operational data transferred to the user's device.

[1752] Output: Data sent to the cloud server.

[1753] How it works: A dedicated application on the user's device automatically sends the collected data to a cloud server via the Internet, allowing the cloud server to receive the data for analysis.

[1754] Step 4:

[1755] Data Integrity Check

[1756] Input: The motion data sent to the cloud server.

[1757] Output: Data that has been checked for consistency or corrected.

[1758] Specific operation: The cloud server first checks the integrity of the received data. If outliers or missing data are found, the outliers are filtered out and missing values ​​are imputed.

[1759] Step 5:

[1760] Data analysis and feedback generation

[1761] Input: Data whose integrity has been checked.

[1762] Output: Analysis of the robot's operation efficiency and quality, along with optimal feedback.

[1763] Specific operation: A generative AI model installed on a cloud server analyzes the data whose consistency has been confirmed. For example, it evaluates whether the movement speed is appropriate or whether there are any problems with the movement angle, and based on that, it generates areas for improvement and optimal operation methods.

[1764] Step 6:

[1765] Providing Feedback

[1766] Input: Feedback from the generative AI model.

[1767] Output: Feedback sent to the user's device.

[1768] Specific behavior: The cloud server sends the generated feedback to the user's device, where it is displayed by a dedicated application. The user can then adjust the robot's behavior based on this feedback.

[1769] Step 7:

[1770] Real-time coaching support

[1771] Input: The user's question (prompt sentence).

[1772] Output: The answer from the generative AI model.

[1773] Specific Actions: When a user sends a question to the generative AI model in real time, the cloud server analyzes the question, generates an appropriate answer, and delivers it to the user's device. For example, in response to a question such as "Is this action efficient?", it is possible to provide specific feedback such as "The speed of the action is appropriate, but the angle of the action should be improved by 10 degrees."

[1774] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1775] This invention proposes a system that collects and analyzes player movement data, and recognizes and utilizes the user's emotional data to provide personalized and optimal feedback. This system is realized through the following steps.

[1776] System Configuration

[1777] The main elements of the system are a player-dedicated IoT device (including sensors), the user's device (smartphone or tablet), a cloud server, and an emotion engine that recognizes the user's emotions.

[1778] Data collection method

[1779] Terminal (IoT device)

[1780] As players practice batting and pitching, sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate. This collection method provides detailed player data.

[1781] User

[1782] Players simply practice as they normally would, with no special operations required. The sensors automatically collect data and transfer it to the user's device during practice.

[1783] Data Transfer Method

[1784] Device (smartphone or tablet)

[1785] The collected data is transferred in real time to the user's device via Bluetooth or Wi-Fi, and a dedicated application is installed on the user's device to receive and manage the data.

[1786] Data transmission method

[1787] Terminal

[1788] Once the user's training session is over, the collected data is sent to the cloud server automatically, without the user needing to be aware of it.

[1789] Collecting Emotional Data

[1790] Device (smartphone or tablet)

[1791] The user's device is equipped with an emotion engine that acquires emotional data in real time through facial expression recognition and voice analysis, thereby understanding the player's emotional state.

[1792] Data analysis and feedback generation

[1793] server

[1794] The cloud server receives the transmitted motion data and first checks the data for consistency. If any abnormal values ​​or missing data are found, correction processing is performed. Next, the generation AI is used to analyze the player's motion data.

[1795] Specifically, the system compares a player's data with a database of professional players to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional players, the system will identify the specific movements and muscle strength deficiencies that are causing this.

[1796] generation means

[1797] Based on the results of the analysis, the AI ​​generates personalized feedback that is optimized for each player. This generation method suggests specific ways to improve and daily practice plans for each player.

[1798] Feedback adjustment using emotional data

[1799] server

[1800] The cloud server also takes into account the player's emotional data acquired by the emotion engine and customizes the feedback content. For example, if a player feels tired or impatient during practice, it generates encouraging messages or feedback suggesting appropriate breaks.

[1801] How to provide feedback

[1802] Device (user's smartphone or tablet)

[1803] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to view it and reflect it in their next practice.

[1804] Coaching Support

[1805] User

[1806] During practice, users can ask the AI ​​generator questions in real time, such as "Is this swing correct?" or "What kind of practice should I do next?", and the AI ​​generator will respond with immediate advice.

[1807] Terminal

[1808] The user's question is sent from the device to the server and analyzed by the generating AI.

[1809] server

[1810] The generative AI generates appropriate answers to questions and sends them to the user's device, allowing the user to receive real-time coaching and maximize the effectiveness of their practice.

[1811] Specific examples

[1812] Example 1: Batting practice

[1813] As a player takes batting practice, IoT sensors collect swing speed and angle. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "your swing speed is good, but your angle needs improvement," which is sent to the user's device. Using an emotion engine, encouraging messages such as "pay attention to this point in your next practice" are also added. The user can then see this and consciously correct their swing angle in their next practice.

[1814] Example 2: Pitching practice

[1815] As the player practices pitching, the IoT sensor collects ball speed and spin rate. This data is transferred to the user's device and sent to the cloud. The cloud server analyzes the data and generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient," which is sent to the user's device. The emotion engine may also suggest things like "Take a short break." This allows the user to practice while paying attention to the spin rate.

[1816] This system not only allows players to receive specific and effective feedback in real time to improve their performance, but also provides appropriate support based on their emotional state. It also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[1817] The processing flow will be explained below.

[1818] Step 1:

[1819] The user begins batting or pitching practice. As the player practices as usual, the IoT sensors collect motion data, such as the player's bat swing speed and angle, as well as the ball's speed and spin rate.

[1820] Step 2:

[1821] The device (IoT device) collects player movement data in real time, and the collected data is transferred to the user's device via Bluetooth or WiFi via sensors attached to the bat and ball.

[1822] Step 3:

[1823] The device (user's smartphone or tablet) temporarily stores the motion data received from the IoT device. A dedicated application displays the data, allowing the user to check their performance during practice. The device's built-in emotion engine also simultaneously collects emotional data through facial recognition and voice analysis of the player.

[1824] Step 4:

[1825] The device (user's smartphone or tablet) transmits the accumulated movement and emotion data to a cloud server. This is usually done automatically after the practice session is completed. The data is uploaded to the server via the internet.

[1826] Step 5:

[1827] The server receives the motion and emotion data sent from the device. First, it checks the consistency of the data and corrects any outliers or missing data. It also verifies that the motion and emotion data are properly linked.

[1828] Step 6:

[1829] The server uses the generated AI to compare the analyzed motion data with a database of experienced professional players, specifically comparing the player's performance, such as swing speed, angle, ball speed, and spin rate, with those of professional players to identify differences and areas for improvement.

[1830] Step 7:

[1831] The server evaluates the player's mental state based on emotional data, and if the player is feeling tired or impatient, this information is reflected in the analysis results.

[1832] Step 8:

[1833] The server generates personalized, optimized feedback based on the analysis results. The AI ​​generator then suggests specific ways to improve and practice to the player. Furthermore, it adjusts the feedback based on emotional data, suggesting a break for tired players and encouraging active practice for energetic players.

[1834] Step 9:

[1835] The server sends the generated feedback to the user's device, where it is provided in a form that can be easily viewed by the user through a dedicated application.

[1836] Step 10:

[1837] The user opens the app and checks the feedback from the AI, understands specific ways to improve, and what to focus on in the next practice session, and practices accordingly.

[1838] Step 11:

[1839] Users can ask the generated AI questions in real time while practicing, such as "Is this swing correct?" or "What kind of practice should I do next?" through the app.

[1840] Step 12:

[1841] The device receives the user's question and sends it to the cloud server, where the application processes the question and forwards it to the server in real time.

[1842] Step 13:

[1843] The server receives questions from users, and the AI ​​generates appropriate answers for those questions, providing specific and applicable advice by referencing the player's data and a database of professional players.

[1844] Step 14:

[1845] The server sends the generated answer to the user's device, providing real-time feedback to the user.

[1846] Step 15:

[1847] The user can check the answers through the application and reflect them in their next action. Real-time coaching support can improve the player's performance.

[1848] By implementing the above steps, the present invention realizes a system that provides effective, individualized guidance to each player and supports their growth. By taking emotion data into consideration, it becomes possible to provide more flexible feedback that is tailored to the player's psychological state.

[1849] Example 2

[1850] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1851] While conventional sports training systems collect and analyze player movement data, it is difficult to grasp the player's emotional state in real time and provide appropriate feedback. Furthermore, the process of generating individually optimized feedback is unable to reflect the player's emotions, making effective instruction difficult.

[1852] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a collection means for collecting player's motion data, a generation means for analyzing the collected data and generating feedback, an emotion collection means for collecting user's emotion data, and an adjustment means for adjusting the feedback using the collected emotion data. This makes it possible to provide individually optimized feedback by taking into account both the player's motion data and emotion data.

[1853] "Collection means" refers to a means for acquiring player movement data, such as a sensor or other device.

[1854] The "transfer means" is a means for transmitting the data acquired by the collection means to the user's terminal.

[1855] "Transmission means" refers to a means for transmitting data from a user's terminal to a cloud server.

[1856] The "generation means" is a means in the cloud server that analyzes the data transmitted by the transmission means and generates optimal feedback for the player.

[1857] "Emotion collection means" refers to means for acquiring user emotional data, and includes facial expression recognition and voice analysis technologies.

[1858] The "adjustment means" is a means for optimizing and adjusting the generated feedback using the emotion data collected by the emotion collection means.

[1859] The "providing means" is a means for transmitting the feedback generated by the generating means and adjusting means to the user's terminal and providing the feedback.

[1860] "Motion data" refers to data that measures the player's movements, including speed, angle, amount of movement, number of rotations, etc.

[1861] "Emotional data" is data that indicates the user's emotional state and is obtained from facial expressions and voice.

[1862] A "cloud server" refers to a server on the Internet used for analyzing and storing data.

[1863] This invention is a system that collects and analyzes player movement data, recognizes and utilizes the user's emotional data, and provides personalized and optimal feedback. This system consists of a player-dedicated IoT device (including sensors), the user's device (smartphone or tablet), a cloud server, and an emotion engine that recognizes the user's emotions.

[1864] Data collection

[1865] Terminal (IoT device) processing:

[1866] As players practice batting and pitching, sensors attached to the bat and ball collect real-time data such as swing speed, angle, ball speed, and spin rate, which is then transmitted to the user's device via Bluetooth or Wi-Fi.

[1867] User Action:

[1868] Players practice as usual, with no special operations required. The sensors automatically collect data and transmit it to the user's device during practice.

[1869] Data Transfer

[1870] Device (smartphone or tablet) processing:

[1871] The collected data is received and managed in real time by a dedicated application via Bluetooth or WiFi. The received data is temporarily stored on the device and can be viewed by the user at any time.

[1872] Data transmission

[1873] Terminal handling:

[1874] Once the user's training is complete, the collected data is sent to the cloud server. This data transfer occurs in the background, so the user does not need to be aware of it.

[1875] Collecting Emotional Data

[1876] Device (smartphone or tablet) processing:

[1877] The user's device is equipped with an emotion engine that uses a camera and microphone to analyze the player's facial expressions and voice, thereby obtaining the player's emotional data in real time.

[1878] Data analysis and feedback generation

[1879] Server Action:

[1880] The cloud server receives the motion data sent from the user's device. First, it checks the data for consistency and corrects any outliers or missing data. It then analyzes the motion data using a generative AI model and compares the player's data with a database of professional golfers to identify performance differences and areas for improvement. For example, if a player's swing speed is slower than that of professional golfers, the cloud server will specifically identify the underlying motions and muscle weaknesses.

[1881] Feedback adjustment using emotional data

[1882] Server Action:

[1883] The cloud server also takes into account the player's emotional data acquired by the emotion engine and customizes the content of the feedback. For example, if a player feels fatigued or impatient during practice, it generates encouraging messages or feedback suggesting appropriate breaks.

[1884] Providing Feedback

[1885] Device (user's smartphone or tablet) processing:

[1886] The generated feedback is sent from the cloud server to the user's device and provided to the user through a dedicated application, allowing the user to incorporate this feedback into their next practice.

[1887] Coaching Support

[1888] User Action:

[1889] Users can ask the generative AI model questions in real time while practicing, such as "Is this swing correct?" or "What practice should I do next?"

[1890] Terminal handling:

[1891] The user's question is sent from the device to a cloud server and analyzed by a generative AI model.

[1892] Server Action:

[1893] The generative AI model generates appropriate answers to the questions, which are then sent back to the user's device, allowing them to receive real-time coaching and maximize the effectiveness of their practice.

[1894] Specific examples

[1895] Batting practice example:

[1896] When a user takes batting practice, sensors collect swing speed and angle, and the data is transferred to the user's device. After practice is completed, the data is sent to a cloud server, which generates analysis results and feedback such as "your swing speed is good, but your angle needs improvement." Based on the user's emotional data, an encouraging message is also added, such as "pay attention to this point in your next practice." This encourages the user to be conscious of their swing angle and try to correct it in their next practice.

[1897] Pitching practice example:

[1898] When a user practices pitching, sensors collect ball speed and spin rate, and the data is transferred to the user's device. After practice, the data is sent to a cloud server, which generates feedback such as "The ball speed is appropriate, but the spin rate is insufficient." Based on emotional data, the feedback may include suggestions such as "Take a short break." The user can then practice with an awareness of the spin rate.

[1899] Prompt Sentence Examples

[1900] Batting Practice Prompts

[1901] "Analyze swing speed and angle data during batting practice and provide feedback on areas for improvement."

[1902] Pitching Practice Prompts

[1903] "Please analyze the ball speed and spin rate data during pitching practice and tell me how to improve."

[1904] This system not only allows players to receive specific and effective feedback in real time to improve their performance, but also provides appropriate support based on their emotional state. It also allows coaches to provide accurate instruction to each player, which is expected to improve overall performance.

[1905] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1906] Step 1:

[1907] Data collection

[1908] Terminal (IoT device) processing:

[1909] 1. Players begin batting and pitching practice.

[1910] 2. Sensors attached to the bat and ball collect real-time motion data such as swing speed, angle, ball speed, and spin rate.

[1911] 3. Input: Player Actions

[1912] 4. Output: swing speed, angle, ball speed, spin rate data

[1913] 5. The data acquired by the sensor is transferred to the user's device via Bluetooth or WiFi.

[1914] Step 2:

[1915] Data Transfer

[1916] Device (smartphone or tablet) processing:

[1917] 1. A dedicated application receives data from the sensor in real time via Bluetooth or WiFi.

[1918] 2. The received data is temporarily stored on the device.

[1919] 3. Input: Motion data from sensors

[1920] 4. Output: Temporarily saved data on the device

[1921] 5. Users can check the data at any time through a dedicated application.

[1922] Step 3:

[1923] Data transmission

[1924] Terminal handling:

[1925] 1. After the practice session, the device automatically sends the collected movement data to the cloud server.

[1926] 2. Input: Saved operating data

[1927] 3. Output: Data sent to the cloud server

[1928] 4. Data transmission occurs in the background, so users do not need to be aware of it.

[1929] Step 4:

[1930] Collecting Emotional Data

[1931] Device (smartphone or tablet) processing:

[1932] 1. The user's device is equipped with an emotion engine that uses the camera and microphone to analyze the player's facial expressions and voice.

[1933] 2. Obtain player emotional data in real time through facial expression recognition and voice analysis.

[1934] 3. Input: Player's facial expressions and voice

[1935] 4. Output: Emotion data

[1936] Step 5:

[1937] Data analysis and feedback generation

[1938] Server Action:

[1939] 1. The cloud server receives the operation data sent from the user's device.

[1940] 2. The server checks the consistency of the data and performs correction processing if abnormal values ​​or missing data are found.

[1941] 3. Input: Operation data sent to the cloud server

[1942] 4. Output: Consistent operational data

[1943] 5. A generative AI model analyzes the data and compares the player's data with a database of professional athletes.

[1944] 6. Identify performance gaps and areas for improvement.

[1945] 7. Input: Consistent operational data

[1946] 8. Output: Analysis results (performance differences, areas for improvement)

[1947] 9. The generation means generates individually optimized feedback based on the analysis results.

[1948] 10. Input: Analysis results

[1949] 11. Output: Feedback data

[1950] Step 6:

[1951] Feedback adjustment using emotional data

[1952] Server Action:

[1953] 1. The cloud server receives the player's emotion data obtained by the emotion engine.

[1954] 2. The server analyzes the emotional data and customizes the content of the generated feedback.

[1955] 3. If a player feels fatigued or impatient during practice, generate encouraging messages and feedback suggesting appropriate breaks.

[1956] 4. Input: Emotion data, feedback data

[1957] 5. Output: Customized feedback

[1958] Step 7:

[1959] Providing Feedback

[1960] Device (user's smartphone or tablet) processing:

[1961] 1. Customized feedback is sent from the cloud server to the user's device.

[1962] 2. Feedback is provided to users in real time through a dedicated application.

[1963] 3. Input: Customized Feedback

[1964] 4. Output: Present feedback to the user

[1965] Step 8:

[1966] Coaching Support

[1967] User Action:

[1968] 1. Users can ask questions to the generative AI model in real time while practicing, such as "Is this swing correct?" or "What practice should I do next?"

[1969] 2. Input: User Question

[1970] 3. Output: Query data to the server

[1971] Terminal handling:

[1972] 1. The user's question is sent from the device to the cloud server.

[1973] 2. Input: User's question data

[1974] 3. Output: Data sent to the cloud server

[1975] Server Action:

[1976] 1. The generative AI model receives the question, analyzes it, and generates an appropriate answer.

[1977] 2. The answer is sent back to the user's device.

[1978] 3. Input: User's question data

[1979] 4. Output: Generated answers

[1980] Terminal handling:

[1981] 1. The user's device receives the answer sent from the cloud server.

[1982] 2. Present to the user through a dedicated application.

[1983] 3. Input: Response data from the cloud server

[1984] 4. Output: Answer presented to the user

[1985] (Application example 2)

[1986] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1987] In factories, it is desirable to monitor the operating status of automated equipment such as robot arms in real time to enable efficient maintenance and operation optimization. However, current systems take time to collect and analyze operation data, making it difficult to provide appropriate feedback quickly. In addition, feedback does not take into account the emotional state of the operator, which increases the risk of fatigue and operational errors during work.

[1988] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a collection means for collecting operation data of the robot arm, a transfer means for transferring the data collected by the collection means to a user's terminal, a transmission means for transmitting the data transferred by the transfer means to a cloud server, a generation means in the cloud server for analyzing the data transmitted by the transmission means and generating feedback for optimizing the operation efficiency of the robot arm, a providing means for transmitting the feedback generated by the generation means to the user's terminal, and a means for the generation means to acquire emotion data and adjust the feedback based on the analysis results. This makes it possible to grasp the operating status of automated equipment in a factory in real time and quickly provide appropriate feedback that takes into account the emotional state of operators.

[1989] "Motion data" refers to information such as speeds, angles, and forces generated by a robotic arm or other automated device during operation.

[1990] "Collection means" refers to a device or system for acquiring operational data using a robotic arm or other sensor.

[1991] "Transportation Method" refers to the method or protocol for moving or transmitting collected data to a user's device.

[1992] "Transmission means" refers to a device or method for transmitting data from a user's terminal to a cloud server.

[1993] A "cloud server" refers to a remote server that can be accessed by multiple users via the Internet and is used to store and analyze data.

[1994] "Analysis" refers to the process of processing collected operational data to extract useful information.

[1995] "Generator" refers to a device or algorithm for generating feedback based on the analysis results.

[1996] "Providing means" refers to a device or method for delivering the generated feedback to the user's terminal.

[1997] "Emotional data" refers to data that indicates the emotional state of an operator obtained through facial expressions and voice analysis.

[1998] A "generative AI model" refers to an artificial intelligence model that uses machine learning technology to analyze data and generate optimal feedback.

[1999] A "prompt sentence" refers to an input sentence provided to a generative AI model to perform a specific task.

[2000] To implement this invention, the following system must be configured. The system is composed of a collection means for collecting operation data of the robot arm, a transfer means for transferring the collected data to a user's terminal, and a transmission means for transmitting the transferred data to a cloud server. The cloud server also requires a generation means for analyzing the transferred data and generating feedback that optimizes the operational efficiency of the robot arm. The system also includes a provision means for providing the generated feedback to the user's terminal. Means for acquiring emotion data and adjusting the feedback based on the analysis results are also important elements.

[2001] Hardware and software used

[2002] Robot arm with sensors: The robot arm is equipped with force, speed, and angle sensors that collect movement data.

[2003] User device (smartphone / tablet): A dedicated application is installed on the device, which receives and transfers collected data.

[2004] Cloud server: Uses an EC2 instance from Amazon Web Services (AWS) and DynamoDB as the database.

[2005] Emotion engine: Uses facial recognition and speech analysis APIs like Amazon Rekognition and Google Cloud Vision to collect operator emotion data.

[2006] Generative AI model: Analyzes data using the OpenAI GPT model and generates optimal feedback.

[2007] Data processing and calculation

[2008] Data collection: Sensors mounted on the robot arm measure speed, angle, and force during movement, collecting data in real time.

[2009] Data transfer: The collected data is transferred to the user device via Bluetooth or WiFi. After transfer, the data is sent from the user device to the cloud server.

[2010] Data analysis: The data sent to the cloud server is checked for consistency and analyzed by the generative AI model. Based on the analysis results, feedback is generated to optimize the operation of the robot arm.

[2011] Emotion data acquisition: The emotion engine installed in the user device recognizes the operator's facial expressions and analyzes their voice to acquire emotion data.

[2012] Feedback generation: The generative AI model generates feedback based on operation data and emotional data, and adjusts according to the user's emotional state.

[2013] Feedback provision: The generated feedback is sent to the user's terminal and provided to the operator through a dedicated application.

[2014] Specific examples

[2015] Analysis of behavioral data:

[2016] When the robot arm performs welding work, the speed sensor measures the speed of the movement, which is collected in real time. For example, if the speed data is not within the specified range, the robot will generate feedback such as "The speed is too fast, please reduce it to within the set range."

[2017] Adjustment based on emotional data:

[2018] If the operator is tired, feedback such as "Take a short break" is added.

[2019] Prompt Sentence Examples

[2020] "Analyze the following robot arm motion data and generate appropriate feedback:

[2021] Operating speed: 10m / s

[2022] Operating angle: 45 degrees

[2023] Operating force: 20N

[2024] Operator's emotional state: Fatigue

[2025] Appropriate feedback: You're going too fast, slow down within the limits. Take a break.

[2026] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2027] Step 1:

[2028] Users collect operation data of robot arms in factories. Sensors mounted on the robot arms measure speed, angle, and force data in real time. No special operation is required by the user. Collected data input: speed, angle, force. Output: collected operation data.

[2029] Step 2:

[2030] The device transfers the collected data to the user's smartphone or tablet via Bluetooth or WiFi. During this process, the device receives data from the sensor and transfers the data to the device via stable communication. Input: Operational data from the sensor. Output: Operational data transferred to the device.

[2031] Step 3:

[2032] The device sends data to the cloud server. In this process, data is sent in real time from the user's device to the cloud server through a dedicated application. Input: Transferred operation data. Output: Operation data sent to the cloud server.

[2033] Step 4:

[2034] The server receives the data sent and checks its integrity. If outliers or missing data are identified, corrections and data cleaning are performed. Input: Operational data sent to the cloud server. Output: Data whose integrity has been checked.

[2035] Step 5:

[2036] The server analyzes the data using analytical tools. It uses a generative AI model (OpenAI GPT model) to analyze the movement data by comparing it with a database of professional athletes. Input: Data with verified consistency. Output: Analysis results.

[2037] Step 6:

[2038] The server uses facial recognition and voice analysis APIs to obtain the user's emotional data, which is taken into account when generating feedback. Input: User's facial and voice data. Output: Emotional data.

[2039] Step 7:

[2040] The server generates optimal feedback based on the analysis results and emotion data. A generative AI model is used to create specific feedback based on behavioral and emotion data. Feedback is obtained by generating prompt sentences and inputting them into the model. Input: Analysis results, emotion data. Output: Generated feedback.

[2041] Step 8:

[2042] The server sends the generated feedback to the user's terminal, which displays it. The user receives the feedback and reflects it in their next operation. Input: Generated feedback. Output: Sending and displaying feedback to the user's terminal.

[2043] Specific prompt examples

[2044] "Analyze the following robot arm motion data and generate appropriate feedback:

[2045] Operating speed: 10m / s

[2046] Operating angle: 45 degrees

[2047] Operating force: 20N

[2048] Operator's emotional state: Fatigue

[2049] Appropriate feedback: You're going too fast, slow down within the limits. Take a break.

[2050] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2051] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2052] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2053] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2054] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2055] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2056] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2057] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2058] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2059] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2060] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2061] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2062] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2063] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2064] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2065] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2066] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2067] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2068] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2069] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2070] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2071] The following is further disclosed regarding the above embodiment.

[2072] (Claim 1)

[2073] A collection means for collecting player action data;

[2074] a transfer means for transferring the data collected by the collection means to a user terminal;

[2075] a transmitting means for transmitting the data transferred by the transferring means to a cloud server;

[2076] a generating means in the cloud server that analyzes the data transmitted by the transmitting means and generates optimal feedback for the player;

[2077] providing means for transmitting the feedback generated by the generating means to a user terminal;

[2078] A system including:

[2079] (Claim 2)

[2080] 10. The system of claim 1, wherein the collecting means is a sensor attached to a player's bat or ball, and the motion data includes swing speed, angle, ball speed, and spin rate.

[2081] (Claim 3)

[2082] 2. The system according to claim 1, wherein the generating means compares the player's data with a database of professional players and proposes an individually optimal training method.

[2083] "Example 1"

[2084] (Claim 1)

[2085] A collection means for collecting player action data;

[2086] a transfer means for transferring the data collected by the collection means to a user terminal;

[2087] a transmitting means for transmitting the data transferred by the transferring means to a cloud server;

[2088] a correcting means in the cloud server for checking consistency of the data transmitted by the transmitting means and correcting the consistency;

[2089] an analysis means for analyzing the data corrected by the correction means;

[2090] a generating means for generating optimal feedback for a player using a generating AI model based on the data analyzed by the analyzing means;

[2091] providing means for transmitting the feedback generated by the generating means to a user terminal;

[2092] A system including:

[2093] (Claim 2)

[2094] 10. The system of claim 1, wherein the collecting means is a sensor attached to the player's equipment and the motion data includes speed, angle, velocity, and rotation rate.

[2095] (Claim 3)

[2096] 2. The system of claim 1, wherein the generating means compares the player's data with a database of other players and proposes an individually optimized practice method.

[2097] "Application Example 1"

[2098] (Claim 1)

[2099] a collection means for collecting operation data of the robot;

[2100] a transfer means for transferring the data collected by the collection means to a user terminal;

[2101] a transmitting means for transmitting the data transferred by the transferring means to a cloud server;

[2102] a generating means in the cloud server that analyzes the data transmitted by the transmitting means and generates optimal feedback for the robot;

[2103] providing means for transmitting the feedback generated by the generating means to a user terminal;

[2104] A system including:

[2105] (Claim 2)

[2106] The system of claim 1 , wherein the collecting means is a sensor attached to the robot, and the motion data includes motion speed, angle, and force.

[2107] (Claim 3)

[2108] 2. The system according to claim 1, wherein the generating means compares the robot's data with a database and proposes an individual optimal operation method.

[2109] "Example 2: Combining Emotion Engines"

[2110] (Claim 1)

[2111] A collection means for collecting player action data;

[2112] a transfer means for transferring the data collected by the collection means to a user terminal;

[2113] a transmitting means for transmitting the data transferred by the transferring means to a cloud server;

[2114] a generating means in the cloud server that analyzes the data transmitted by the transmitting means and generates optimal feedback for the player;

[2115] An emotion collection means for collecting emotion data of a user;

[2116] an adjustment means for adjusting the feedback generated by the generation means using the emotion data collected by the emotion collection means;

[2117] providing means for transmitting the feedback generated and adjusted by the generating means and the adjusting means to a user terminal;

[2118] A system including:

[2119] (Claim 2)

[2120] 10. The system of claim 1, wherein the collecting means is a sensor attached to a player's athletic equipment or gear, and the motion data includes speed, angle, object movement, and number of rotations.

[2121] (Claim 3)

[2122] 2. The system of claim 1, wherein the generating means compares the player's data with a database of professional players and proposes an individually optimized training method.

[2123] "Application example 2 when combining emotion engines"

[2124] (Claim 1)

[2125] A collection means for collecting player action data;

[2126] a transfer means for transferring the data collected by the collection means to a user terminal;

[2127] a transmitting means for transmitting the data transferred by the transferring means to a cloud server;

[2128] a generating means in the cloud server that analyzes the data transmitted by the transmitting means and generates optimal feedback for the player;

[2129] providing means for transmitting the feedback generated by the generating means to a user terminal;

[2130] the generating means acquires emotion data and adjusts feedback based on the analysis result;

[2131] A system including:

[2132] (Claim 2)

[2133] 10. The system of claim 1, wherein the collecting means is a sensor attached to a player's bat or ball, and the motion data includes swing speed, angle, ball speed, and spin rate.

[2134] (Claim 3)

[2135] The system of claim 1, wherein the generating means uses a generative AI model that compares the player's data with a database of professional players and suggests an individually optimal training method, and generates prompt sentences. [Explanation of symbols]

[2136] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A collection means for collecting player action data; a transfer means for transferring the data collected by the collection means to a user terminal; a transmitting means for transmitting the data transferred by the transferring means to a cloud server; a generating means in the cloud server that analyzes the data transmitted by the transmitting means and generates optimal feedback for the player; providing means for transmitting the feedback generated by the generating means to a user terminal; A system including:

2. 2. The system of claim 1, wherein the collecting means is a sensor attached to the player's bat or ball, and the motion data includes swing speed, angle, ball speed, and spin rate.

3. 2. The system according to claim 1, wherein the generating means compares the player's data with a database of professional players and proposes an individual optimal training method.

Images