system

Abstract

Provide a system. [Solution] a means for collecting running data from a user; A means of inputting and analyzing running data into a generative artificial intelligence model; means for generating training optimization advice based on the analysis results; A means for analyzing video data of running form and generating form improvement advice; The system includes means for providing the generated advice to a user's terminal.

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] With the recent rise in health consciousness, an increasing number of people are taking up running, but it is difficult to master effective training methods and correct running form. In particular, running on your own can increase the risk of injury and prevent you from achieving the desired performance improvement. Furthermore, while there is a vast amount of information available about running, there are few systems that can provide individually optimized advice. Therefore, there is a growing need for a system that can optimize training and improve form for each individual runner. [Means for solving the problem]

[0005] This invention provides a system that includes means for collecting running data from a user, means for inputting and analyzing the running data into a generative artificial intelligence model, means for generating training optimization advice based on the analysis results, means for analyzing video data of running form to generate form improvement advice, and means for providing the generated advice to the user's device. This system uses a skeletal detection algorithm to analyze running form, and by suggesting interval training and pace adjustments in the generated training optimization advice, it provides individually optimized advice, enabling the user to improve their running performance and prevent injuries.

[0006] "Running data" is information including location information, speed, heart rate, time, and video data collected by a user while running.

[0007] A "generative artificial intelligence model" is an artificial intelligence algorithm that analyzes collected running data and generates advice on optimizing training and improving running form.

[0008] "Training optimization advice" refers to specific training plans and schedules that the generative artificial intelligence model proposes to users based on the analysis results, with the aim of improving running performance.

[0009] "Running form video data" is video data that records the user's running motion.

[0010] "Form improvement advice" involves analyzing video data of the user's running form, pointing out problems with the user's running movements, and providing specific instructions and suggestions for improvement.

[0011] The "skeleton detection algorithm" is an algorithm for detecting a runner's skeleton from video data and analyzing the characteristics of their movements.

[0012] "Interval training" is a training method that alternates between high-intensity and low-intensity exercise, with the aim of improving cardiopulmonary function and endurance.

[0013] "Pace adjustment" is a technique for efficiently improving performance by appropriately changing speed while running. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. The system aims to improve the user's running performance and prevent injuries.

[0036] Data collection

[0037] The user launches the smartphone app and starts a running session. The device collects real-time data using the smartphone's GPS, heart rate sensor, and speedometer. In addition, the device records video data of the user's running form using the smartphone's camera.

[0038] Data upload

[0039] After completing a running session, the user presses the "stop" button on the smartphone app, and all data collected by the device is uploaded to a server, where it is compressed and transmitted using a secure protocol.

[0040] Data analysis

[0041] The server receives the uploaded data and inputs it into a generative AI model. The generative AI model analyzes the running data (location, speed, heart rate, and time) to evaluate the user's training performance. At the same time, the generative AI model analyzes the video data and evaluates running form using a skeletal detection algorithm.

[0042] Optimization Advice Generation

[0043] The generative AI model generates a training plan tailored to the user based on the analysis of running data. Specifically, it suggests interval training days and running pace adjustments. For example, it calculates the running speed needed to maintain a certain heart rate based on the user's heart rate and speed data.

[0044] Generate form improvement advice

[0045] The generative AI model evaluates running form based on video data and suggests specific improvements. For example, if the swing angle of the right arm is unnatural, the system will provide advice on how to swing both arms with the same amplitude to correct this.

[0046] Providing Feedback

[0047] The server organizes the generated optimization advice and form improvement advice and sends it to the device in JSON format, etc. The device displays the advice to the user and encourages them to put it into practice in their next running session.

[0048] Specific examples

[0049] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate, and the camera captures the user's running form. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Furthermore, analysis of the video data provides specific advice on improving the swing of the right arm. The device displays this advice to the user, who then puts it into practice during their next running session.

[0050] In this way, the system of the present invention can provide users with individually optimized training and form improvement advice, thereby improving running performance and preventing injuries.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] A user launches the smartphone app and starts a running session. The device acquires location information from the smartphone's GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The device also activates the camera and starts recording a video of the user's running form.

[0054] Step 2:

[0055] After finishing a running session, the user presses the "Stop" button on the smartphone app. The device then compresses all running data (location, speed, heart rate, time) and video data and uploads them to the server.

[0056] Step 3:

[0057] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0058] Step 4:

[0059] The generative AI model begins analyzing running data, specifically location, speed, and heart rate trends, to assess the user's running performance.

[0060] Step 5:

[0061] At the same time, a generative AI model analyzes the video data, analyzing the video frames and using a skeletal detection algorithm to extract the characteristics of the user's running form.

[0062] Step 6:

[0063] A generative AI model analyzes running data and generates training optimization advice, such as suggesting a specific interval training schedule and an appropriate running pace.

[0064] Step 7:

[0065] The generative AI model analyzes the video data and generates advice to improve form. For example, if the right arm swing is unnatural, the system will advise the player to swing both arms with the same amplitude.

[0066] Step 8:

[0067] The server organizes the generated optimization advice and form improvement advice and formats the data in JSON format, for example.

[0068] Step 9:

[0069] The server sends the formatted data to the device, and the device displays the received advice on the app's user interface.

[0070] Step 10:

[0071] The user then implements the provided advice during their next running session, collects data again, and repeats the process to continually optimize their training and improve their form.

[0072] Example 1

[0073] 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."

[0074] In modern society, improving athletic performance and preventing injuries are important challenges for many people. However, there are limited means for easily obtaining appropriate training and form improvement advice based on individual users' exercise and posture data. The present invention aims to solve these challenges by providing a system that allows users to easily obtain optimized training advice and form improvement advice.

[0075] 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.

[0076] In this invention, the server includes means for collecting exercise data from a user, means for collecting video data capturing posture during exercise, means for inputting the collected exercise data and video data into a generative artificial intelligence model for analysis, means for generating training optimization advice based on the analysis results, means for analyzing the video data and generating posture improvement advice, and means for providing the generated advice to the user's mobile device. This allows users to easily obtain individually optimized training and form improvement advice, enabling them to improve their exercise performance and prevent injuries.

[0077] "Exercise data" refers to data such as location information, speed, and heart rate acquired while the user is exercising.

[0078] "Video data" refers to video data captured while the user is exercising.

[0079] A "generative artificial intelligence model" is an artificial intelligence system that analyzes collected exercise data and video data and generates advice on training and form improvement.

[0080] The "skeleton detection algorithm" is an algorithm for detecting the user's skeletal position from video data.

[0081] "Training optimization advice" is advice on training methods and exercise schedules that is generated based on the user's exercise data.

[0082] "Form improvement advice" is advice that evaluates the user's exercise form based on video data and points out areas for improvement.

[0083] A "mobile terminal" is an electronic device that can be carried by a user, and primarily refers to a smartphone, but may also include other similar devices.

[0084] This invention is a system that collects a user's exercise data and video data of their exercise form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. The system aims to improve the user's exercise performance and prevent injuries.

[0085] Data collection

[0086] The user launches the smartphone app and begins an exercise session. The device collects data in real time using the smartphone's GPS, heart rate sensor, and speedometer. At the same time, the device uses the smartphone's camera to record video data of the exercise form. Specifically, the device records location information every second and collects heart rate and speed data.

[0087] Data upload

[0088] After the exercise session is over, the user presses the "Stop" button on the smartphone app, and the device compresses all collected data (location, heart rate, speed, and video data). The device compresses the data and sends it to a server using a secure protocol (e.g., HTTPS).

[0089] Data analysis

[0090] The server receives the uploaded data and inputs it into a generative AI model. The generative AI model analyzes the exercise data (position, speed, heart rate, and time) to evaluate the user's training performance. At the same time, it analyzes the video data and evaluates the exercise form using a skeletal detection algorithm. Specifically, the generative AI model extracts the position of the skeleton for each video frame and checks the consistency of the form.

[0091] Optimization Advice Generation

[0092] A generative AI model generates a training plan tailored to the user based on the analysis of the exercise data. For example, it calculates the running pace required to maintain a certain heart rate based on the user's heart rate and speed data. As a specific example, it suggests, "For your next workout, do interval training, covering a distance of 1 kilometer, at a speed of 10 kilometers per hour."

[0093] Generate form improvement advice

[0094] The generative AI model evaluates the exercise form based on the video data and suggests specific improvements. For example, if the swing angle of the right arm is unnatural, the model may suggest that the left and right arms should be swung with the same swing width.

[0095] Providing Feedback

[0096] The server organizes the generated optimization advice and form improvement advice and sends it to the device in a data format such as JSON. The device then displays this advice in an easy-to-read format to the user, encouraging them to put it into practice in their next exercise session. For example, it might suggest specific actions, such as, "Try the following advice during your next workout: 1. Set your speed to 9 kilometers per hour to maintain a stable heart rate. 2. Be conscious of swinging both arms evenly to improve your right arm swing."

[0097] In this way, the system of the present invention can provide users with individually optimized training and form improvement advice, thereby improving athletic performance and preventing injuries.

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1:

[0100] The user launches the smartphone app and performs an input operation to start a running session. This operation causes the device to detect that the app has been launched and activate the necessary sensors (GPS, heart rate sensor, speedometer). Specifically, the device checks the operation of the sensors and begins initial data collection.

[0101] Step 2:

[0102] The device uses the smartphone's GPS to obtain location information every second. It obtains heart rate data from the heart rate sensor and speed data in real time from the speedometer. At the same time, it records video data of the running form using the smartphone's camera. The input data includes location information, heart rate, speed, and video data, which are temporarily stored in the device's storage.

[0103] Step 3:

[0104] After completing a running session, the user presses the "Stop" button on the smartphone app. This action causes the device to compress all collected data. Specifically, the collected location information, heart rate, speed, and video data are combined into a single file using a compression algorithm. The compressed data is then output.

[0105] Step 4:

[0106] The device sends the compressed data to the server using a secure protocol (e.g. HTTPS). The input is the compressed file, which the device sends over a network connection. If successful, the device prints a message confirming that the data was sent.

[0107] Step 5:

[0108] The server receives the compressed file and decompresses it. The decompressed data (location, heart rate, speed, video data) is input into the generative AI model. Based on the input data, the generative AI model first analyzes the running data (location, speed, heart rate, time).

[0109] Step 6:

[0110] The generative AI model outputs the results of analyzing the running data, then analyzes the video data and evaluates running form using a skeletal detection algorithm. The video data is analyzed as input data, and the analysis results output the consistency of form and areas for improvement.

[0111] Step 7:

[0112] Based on the results of each data analysis, the generative AI model generates an optimal training plan and advice for improving form for the user. Specifically, it outputs interval training schedule suggestions, running speed suggestions, and specific instructions for improving form.

[0113] Step 8:

[0114] The server organizes the generated optimization advice and form improvement advice and sends it to the terminal in JSON or other appropriate data format. The input data is the generated advice, and the output is a submission confirmation message.

[0115] Step 9:

[0116] The device displays the received advice to the user in an easy-to-read format. Specifically, it presents the training plan displayed in the app and specific advice on form improvement, encouraging the user to implement it in their next running session. The output of this step is feedback that the user has acknowledged the advice.

[0117] (Application example 1)

[0118] 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."

[0119] In the modern food delivery industry, there is a need to simultaneously optimize the delivery efficiency and health of delivery workers. However, current systems lack the means to monitor not only delivery workers' location and speed, but also their physical movements and health status in real time, and provide specific efficiency and health advice. This often leads to fatigue and health problems among delivery workers, hindering efficient delivery.

[0120] 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.

[0121] In this invention, the server includes means for collecting movement data from users, means for inputting the movement data into a generative AI model and analyzing it, means for generating efficiency advice based on the analysis results, means for analyzing video data of movement form and generating form improvement advice, and means for providing the generated advice to the user's information terminal, thereby enabling delivery personnel to optimize their delivery routes, improve their physical movements, and maintain their health.

[0122] "Movement data" refers to data such as the user's location, speed, and heart rate, and records the user's movement status in real time.

[0123] A "generative artificial intelligence model" is an artificial intelligence system that learns patterns and trends based on collected data and generates analytical results.

[0124] "Efficiency advice" refers to specific suggestions and guidelines for improving work efficiency based on the results of analyzing the user's movement data.

[0125] "Movement form" refers to the body movements and postures that a user performs while moving, and is evaluated in particular for their appropriateness and efficiency.

[0126] "Video data" refers to footage of a user's motion form, and is used for analysis.

[0127] A "body feature detection algorithm" is a program that identifies the position of a user's bones and joints from video data and analyzes their movements.

[0128] An "information terminal" is an electronic device used to input and display data, such as a smartphone or tablet that a user has.

[0129] This invention is a system for simultaneously optimizing the delivery efficiency and health of delivery workers in the food delivery industry. This system collects video data of users' movements and motion forms, and analyzes them using a generative artificial intelligence model to provide specific and individualized advice on efficiency and form improvement. This system is realized using the following main hardware and software:

[0130] Hardware

[0131] 1. Information terminal: Electronic devices held by users, such as smartphones and tablets

[0132] 2. Sensor:

[0133] GPS: Get the user's location in real time

[0134] Heart rate sensor: Measures the user's heart rate

[0135] Speedometer: Measure your speed

[0136] 3. Camera: Records the user's movements as video

[0137] software

[0138] 1. Generative AI model: An AI model for analyzing collected movement data and video data

[0139] 2. Body feature detection algorithm: A program that detects the position of the user's bones and joints from video data and analyzes their movements.

[0140] Data processing and calculation

[0141] Data collection

[0142] The user launches the smartphone app and starts a delivery session. The smartphone uses GPS, a heart rate sensor, and a speedometer to obtain the user's location, heart rate, and speed in real time. The smartphone also uses a camera to record the user's movement form.

[0143] Data upload

[0144] After the delivery session is over, when the user hits the "Stop" button in the app, all collected data is uploaded to the server, compressed and transmitted using a secure protocol.

[0145] Data analysis

[0146] The server receives the uploaded data and analyzes it using a generative AI model. This AI model analyzes movement data (location, speed, heart rate, time) to evaluate the efficiency of the delivery route and the user's physical fitness. It also analyzes video data and evaluates movement form using a body feature detection algorithm.

[0147] Advice Generation

[0148] Based on the results of data analysis, a generative AI model generates efficiency advice and advice on improving the user's behavior, such as providing specific advice on optimizing delivery routes and improving carrying methods.

[0149] Providing Feedback

[0150] The server organizes the generated advice and sends it to the information terminal in JSON format, etc. The information terminal displays the advice to the user and encourages them to put it into practice in the next delivery session.

[0151] Specific examples

[0152] The user initiates a delivery session and performs multiple deliveries. The smartphone records location, speed, and heart rate, and the camera captures the user's movement form. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests route optimization for the next delivery and advice on how to hold the device to prevent fatigue. The device displays this advice to the user, who then puts it into practice during their next delivery session.

[0153] Prompt Sentence Examples

[0154] "Analyze data from delivery sessions to optimize routes and maintain health. Provide optimal recommendations based on the driver's GPS, speed, heart rate, and movement video."

[0155] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0156] Step 1:

[0157] A user launches the smartphone app and begins a delivery session. As input, the user activates the GPS, heart rate, speedometer, and camera. The output is real-time location, heart rate, speed, and video data captured by the smartphone. This data is stored locally during the session.

[0158] Step 2:

[0159] During the session, the device collects real-time location, speed, and heart rate data. The camera records the user's movements. The inputs are data obtained from various sensors and camera footage. The output is the collected data and a video file.

[0160] Step 3:

[0161] After the delivery session ends, the user presses the "Stop" button in the app. The device then compresses all collected data and uploads it to the server using a secure protocol (e.g., HTTPS). The inputs are the collected data and the video file. The outputs are the data sent to the server and the video file.

[0162] Step 4:

[0163] The server receives the uploaded data and prepares it for analysis. The inputs are location, speed, heart rate, and video data sent from the device. The output is data converted into an analyzable format.

[0164] Step 5:

[0165] The server analyzes the data using a generative AI model. Inputs include location information, speed, heart rate data, and video data. The generative AI model analyzes the movement data to evaluate the efficiency of the delivery route and the user's physical fitness, and analyzes the video data to evaluate the user's movement form. The output is the analysis of the movement data and advice on improving form.

[0166] Step 6:

[0167] The generative AI model generates efficiency advice and advice on improving movement form based on the analysis results. The inputs are the analysis results of movement data and video data. The output is efficiency advice and advice on improving movement form that are appropriate for the user.

[0168] Step 7:

[0169] The server organizes the generated advice in JSON format or similar and sends it to the terminal. The input is the generated advice. The output is advice organized in JSON format.

[0170] Step 8:

[0171] The device receives advice from the server and displays it to the user. The input is advice sent from the server. The output is efficiency advice and form improvement advice displayed on the smartphone screen. The user can put these advices into practice in the next delivery session.

[0172] 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.

[0173] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. In addition, by combining this with an emotion engine that recognizes the user's emotions, it provides more personalized advice. This system aims to improve the user's running performance, prevent injuries, and increase the user's motivation.

[0174] Data collection

[0175] A user launches the smartphone app and starts a running session. The device obtains location information from the smartphone's GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The device also activates the camera to start recording a video of the user's running form and records facial expression data for the emotion engine.

[0176] Data upload

[0177] After finishing a running session, the user presses the "Stop" button on the smartphone app. The device then compresses all running data (location, speed, heart rate, time) and video data and uploads them to the server.

[0178] Data analysis

[0179] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0180] Emotion analysis

[0181] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state, and also uses audio data, if available, for analysis.

[0182] Running data analysis

[0183] The generative AI model begins analyzing running data, specifically location, speed, and heart rate trends, to assess the user's running performance.

[0184] Optimization Advice Generation

[0185] A generative AI model generates training optimization advice based on the analysis of running data. For example, it suggests a specific interval training schedule and an appropriate running pace. Furthermore, it adjusts the content and wording of the advice based on the user's emotional state. For example, if the user is feeling fatigued or stressed, it will use a gentle tone of voice to motivate them and suggest taking a break.

[0186] Generate form improvement advice

[0187] The generative AI model generates advice to improve form based on the analysis of video data. For example, if the swing of the right arm is unnatural, the system will instruct the user to swing both arms with the same amplitude to correct this. Furthermore, the system takes the user's emotions into consideration and provides advice with encouraging words.

[0188] Providing Feedback

[0189] The server organizes the generated optimization advice and form improvement advice, takes into account the results of sentiment analysis, and formats the data in JSON format or other formats. The server then sends the formatted data to the device. The advice received by the device is then displayed in the app's user interface.

[0190] Specific examples

[0191] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate data, and the camera captures the user's running form and facial expressions. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Analysis of the video data also provides specific advice on improving the swing of the right arm. An emotion engine analyzes the user's facial expression data and, if the user feels fatigued or stressed, provides advice that takes rest into consideration. The device displays this advice to the user, who then puts it into practice during their next running session.

[0192] In this way, the system of the present invention provides users with individually optimized training and form improvement advice, improving running performance and preventing injuries, and also provides support to improve motivation by taking into account their emotional state.

[0193] The processing flow will be explained below.

[0194] Step 1:

[0195] The user launches the smartphone app and starts a running session. The device acquires location information from the smartphone's GPS module, receives real-time heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to capture the user's running form and facial expression.

[0196] Step 2:

[0197] After the device finishes running, the user presses the "Stop" button. The device compresses the location, speed, heart rate, and video data it has acquired, and uploads the data to a server using a secure protocol.

[0198] Step 3:

[0199] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0200] Step 4:

[0201] The generative AI model begins analyzing running data. Specifically, it analyzes trends in position, speed, and heart rate to evaluate the user's running performance. It also analyzes video data and uses a skeletal detection algorithm to extract form features.

[0202] Step 5:

[0203] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state, and if audio data is available, it can also be used in the analysis to more accurately determine emotions.

[0204] Step 6:

[0205] A generative AI model analyzes running data and generates training optimization advice, such as suggesting a specific timetable for interval training and an appropriate running pace.

[0206] Step 7:

[0207] The generative AI model reflects the analysis results of the emotion engine and adjusts the content and expression of the advice. For example, if the user is feeling fatigued or stressed, it may suggest reducing the intensity of their training or generate advice that includes an encouraging message.

[0208] Step 8:

[0209] The generative AI model generates advice on improving form based on the analysis of video data. For example, if the swing of the right arm is unnatural, it will suggest specific practice methods to correct it.

[0210] Step 9:

[0211] The server organizes the generated optimization advice and form improvement advice, and formats the customized advice data in JSON format or other formats based on the analysis results of the emotion engine.

[0212] Step 10:

[0213] The server sends the formatted data to the device, and the device displays the received advice on the user interface within the app. The advice includes an appropriate message that takes into account the user's emotional state.

[0214] Step 11:

[0215] The user then implements the provided advice during their next running session, collects data again, and repeats the process to continually optimize their training and improve their form.

[0216] The above are the detailed processing steps in the embodiment of the present invention, which allow users to receive scientifically and individually optimized training and form improvement advice, improve running performance, prevent injuries, and receive emotional support.

[0217] Example 2

[0218] 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."

[0219] Conventional running training systems focus on analyzing users' running data and running form, but it is difficult to provide advice that takes into account the user's emotional state. Furthermore, the data compression and uploading processes are sometimes inefficient, and real-time performance and data processing accuracy need to be improved. Furthermore, video analysis for form improvement requires the use of advanced algorithms, which presents challenges.

[0220] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0221] In this invention, the server includes means for collecting running data from the user, means for compressing the collected data by the terminal and uploading it to the server, means for the server to store the uploaded data in a database, means for inputting the running data into a generative artificial intelligence model for analysis, means for an emotion engine to analyze the video data and recognize the user's emotional state, means for generating training optimization advice based on the analysis results, means for analyzing the running form video data and generating form improvement advice, and means for providing the generated advice to the user's terminal. This not only improves the user's running performance, but also makes it possible to provide personalized advice based on the user's emotional state, achieving advanced data processing and real-time performance.

[0222] "Running data" refers to data including location information, speed data, heart rate data, and running time acquired while the user is running.

[0223] A "terminal" is an electronic device used by a user, such as a smartphone or a wearable device.

[0224] A "server" is a computer system that stores data, analyzes it, and runs generative artificial intelligence models.

[0225] A "generative artificial intelligence model" is an artificial intelligence model that analyzes a user's running data and generates advice on optimizing training and improving form.

[0226] An "emotion engine" is software that analyzes video data to recognize the user's emotional state.

[0227] "Training optimization advice" refers to specific training methods and schedule suggestions provided by the generative artificial intelligence model to improve the user's running performance.

[0228] "Form improvement advice" refers to specific instructions and suggestions provided by the generative artificial intelligence model to improve a user's running form.

[0229] A "skeleton detection algorithm" is an algorithm used to detect a user's skeleton and posture in video data analysis.

[0230] "Interval training" is a training method that alternates between high-intensity running and low-intensity running.

[0231] "Pace adjustment" refers to speed management that allows for effective training by appropriately controlling the user's running speed.

[0232] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. In addition, by combining this with an emotion engine that recognizes the user's emotions, it provides more personalized advice. This system aims to improve the user's running performance, prevent injuries, and increase the user's motivation.

[0233] Data collection

[0234] A user launches the smartphone app and starts a running session. The device acquires location information using the smartphone's GPS module, receives heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to start recording a video of the user's running form and also records facial expression data for the emotion engine.

[0235] Data upload

[0236] After finishing a running session, the user presses the "Stop" button on the smartphone app, which causes the device to compress all running data (location information, speed data, heart rate data, running time) and video data and upload them to the server.

[0237] Data analysis

[0238] The server receives the uploaded data and stores it in a database, after which the server inputs the data into a generative artificial intelligence model and begins analysis.

[0239] Emotion analysis

[0240] The emotion engine analyzes the video data to recognize the user's emotional state from their facial expressions, and also uses audio data, if available.

[0241] Running data analysis

[0242] A generative AI model analyzes running data, specifically trends in location, speed, and heart rate data, to assess a user's running performance.

[0243] Optimization Advice Generation

[0244] A generative AI model generates training optimization advice based on the analysis of running data. For example, it suggests a specific interval training schedule and an appropriate running pace. Furthermore, the content and wording of the advice can be adjusted based on the user's emotional state. For example, if the user is feeling fatigued or stressed, it can use a gentle tone of voice to motivate them or suggest taking a break.

[0245] Generate form improvement advice

[0246] The generative AI model generates advice to improve form based on the analysis of video data. For example, if the swing of the right arm is unnatural, the system will instruct the user to swing both arms with the same amplitude to correct this. Furthermore, the system takes the user's emotions into consideration and provides encouraging advice.

[0247] Providing Feedback

[0248] The server organizes the generated optimization advice and form improvement advice, formats the data taking into account the results of sentiment analysis, and sends the formatted data to the device, which then displays the advice received on the device in the app's user interface.

[0249] Specific examples

[0250] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate data, and the camera captures the user's running form and facial expressions. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Video data analysis also provides specific advice on improving the swing of the right arm. An emotion engine analyzes the user's facial expression data and, if the user feels fatigued or stressed, provides advice that takes rest into consideration. The device displays this advice to the user, who then puts it into practice in their next running session.

[0251] Examples of prompts:

[0252] Analyze the user's running performance based on the following data and generate optimal training advice and form improvement advice.

[0253] Data: location information, speed data, heart rate data, running time, running form video, user facial expression data

[0254] User's emotional state: Fatigue

[0255] In this way, the system of the present invention provides users with individually optimized training and advice on improving their form, improving their running performance and preventing injuries, and also provides support to improve motivation by taking into account their emotional state.

[0256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0257] Step 1:

[0258] The user starts the smartphone app and presses the "Start" button to begin a running session. The device acquires location information using the smartphone's GPS module, receives heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to begin recording video of the user's running form and records facial expression data for the emotion engine. By collecting these input data (location information, speed data, heart rate data, and video data), real-time data collection is performed from the start of the run.

[0259] Step 2:

[0260] The device obtains location information every second from the GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The camera continuously records the user's running form and facial expressions. This allows input data (location information, heart rate data, speed data, and video data) to be continuously accumulated. The collected data is stored in the internal memory and prepared for further processing.

[0261] Step 3:

[0262] When the running session is over, the user presses the "Stop" button on the smartphone app. This action causes the device to stop collecting data from the sensors and end the camera recording. This finalizes all data collected during the session (location, speed, heart rate, and video data) and prepares it for the next upload step.

[0263] Step 4:

[0264] All data collected by the device (location, speed, heart rate, and video data) is compressed into a single file. This compressed file becomes the input data for the next step. Compression improves data transmission efficiency, saving time and bandwidth for transfer.

[0265] Step 5:

[0266] The device uploads the compressed file to a server via the internet, sending the data collected and compressed so far to the server, where it is stored in a database and prepared for the next analysis step.

[0267] Step 6:

[0268] The server receives the compressed file and stores it in a database. It checks the data integrity and decompresses it if necessary. The decompressed data (location information, speed data, heart rate data, video data) is used for further analysis.

[0269] Step 7:

[0270] The server extracts the necessary data from the database and inputs it into the generative AI model. Based on this input data, the generative AI model begins analyzing the data. For example, it analyzes changes in location data and speed trends to evaluate the user's performance.

[0271] Step 8:

[0272] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state. If audio data is available, it is also used for analysis. The results of this analysis are classified into emotion categories (positive, negative, or neutral).

[0273] Step 9:

[0274] A generative AI model analyzes running data and evaluates trends in position, speed, and heart rate. Based on this, it quantitatively evaluates the user's running performance. This evaluation results form the basis for advice generated in the next step.

[0275] Step 10:

[0276] Based on the analysis results, the generative AI model generates training optimization advice. For example, it suggests the next interval training schedule or an appropriate running pace. It also adjusts the content and wording of advice based on the emotion analysis results. For example, if the emotional state indicates fatigue or stress, it may suggest a gentler tone of voice or rest to increase motivation.

[0277] Step 11:

[0278] The generative AI model generates advice on improving form based on the analysis of video data. For example, if the swing of the right arm is unnatural, it will suggest ways to correct it. It also takes into account the player's emotional state and provides encouraging advice.

[0279] Step 12:

[0280] The server organizes the generated optimization advice and form improvement advice, formats the data taking into account the results of sentiment analysis, and sends the formatted data in JSON format or other formats to the device.

[0281] Step 13:

[0282] The device analyzes the received feedback and displays it on the smartphone app's user interface, allowing users to review training optimization and form improvement advice and put it into practice during their next running session.

[0283] (Application example 2)

[0284] 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."

[0285] In modern factories, improving the efficiency and accuracy of robot operations is important. However, current systems are unable to provide optimization advice that takes into account operation data and the emotional state of workers, resulting in reduced work efficiency and increased worker stress. The present invention aims to solve these problems by optimizing the operation of factory robots, improving work efficiency, and providing personalized advice that takes into account the emotional state of workers.

[0286] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting running data from the user, means for inputting the running data into a generative AI model and analyzing it, means for generating training optimization advice based on the analysis results, means for analyzing video data of the running form and generating form improvement advice, means for providing the generated advice to the user's terminal, means for recognizing an emotional state from the video data using an emotion engine, and means for adjusting the content of the advice based on the recognized emotional state. This improves the operating efficiency of factory robots, reduces worker stress, and makes it possible to provide optimized work advice.

[0287] "User" refers to an individual or operator who uses this system.

[0288] "Running data" refers to data related to a user's exercise, such as location information, speed, heart rate, and time.

[0289] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that analyzes collected data and generates optimization and improvement advice.

[0290] "Video data" refers to video data captured using a camera or other imaging device.

[0291] "Emotion engine" refers to an engine that analyzes video and audio data to recognize and evaluate the user's emotional state.

[0292] "Advice" refers to instructions or suggestions generated based on the analysis results.

[0293] "Terminal" refers to a device, such as a smartphone or computer, that a user uses to operate this system.

[0294] A "skeleton detection algorithm" refers to an algorithm that detects human skeletons from video data and analyzes their movements.

[0295] "Interval training" refers to a training technique that alternates between high-intensity and low-intensity exercise.

[0296] "Pacing" refers to adjusting the speed and rhythm of your running or work.

[0297] This invention is a system that collects user motion data and analyzes it using a generative artificial intelligence model to provide training optimization advice and motion improvement advice. Furthermore, by combining it with an emotion engine, it is possible to provide personalized advice that takes into account the user's emotional state.

[0298] Data collection

[0299] The user starts the device and begins a movement session. The device acquires location information using the GPS module, speed data from the speedometer, and heart rate data from the heart rate sensor. It then activates the camera to begin video recording of the user's movements, which also records facial expression data. This allows the device to collect a variety of movement data from different angles.

[0300] Data upload

[0301] When the movement session is over, the user presses the "stop" button on the device, which causes the device to compress all collected data (location, speed, heart rate, time, and video data) and upload it to a server, where it is centrally aggregated and available for analysis.

[0302] Data and Sentiment Analysis

[0303] The server receives the uploaded data and stores it in a database. The server analyzes the data using a generative artificial intelligence model to evaluate the user's performance. It also uses an emotion engine to analyze the user's emotional state from video data. The emotion engine analyzes facial expression and voice data to recognize the user's emotional state. This analysis makes it possible to grasp in detail the state in which the user was operating.

[0304] Advice Generation

[0305] The generative AI model generates training optimization advice based on the analysis of movement data. For example, it suggests a specific schedule and appropriate speed for interval training. It also generates movement improvement advice based on analysis of video data. For example, it suggests ways to make the right arm move more smoothly. It also adjusts the content and expression of the advice based on the user's emotional state. If the user is feeling tired or stressed, it suggests gentle tone of voice to motivate them or suggests taking a rest.

[0306] Providing Feedback

[0307] The server organizes the generated optimization advice and behavior improvement advice, takes into account the results of sentiment analysis, and formats the data in JSON format or other formats. The formatted data is then sent to the device, which then displays the received advice on the app's user interface.

[0308] As a concrete example, when a user operates a robot in a factory, once the user's daily work exceeds a certain volume, the device records location information, speed, and heart rate data, and a video camera captures the user's movements and facial expressions. After the work is completed, the device uploads the data to a server, which analyzes it using a generative artificial intelligence model. Based on the next work schedule, the device proposes a new interval training schedule and appropriate movement timing, and provides detailed advice on how to smooth the movement of the right arm. An emotion engine analyzes the user's facial expression data and simultaneously provides advice, including advice on rest, if the user feels fatigued or stressed.

[0309] Prompt Sentence Examples

[0310] "A robot is performing a machine assembly task. Please automatically capture the worker's movements, analyze their behavior and their emotional state, and provide optimization advice for the next task."

[0311] In this way, the system of the present invention provides users with individually optimized advice on improving their movements and form, thereby improving their work performance and preventing injuries, and also provides support for improving motivation by taking into account their emotional state.

[0312] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0313] Step 1: Data collection

[0314] A user starts a work session on their device. The device acquires location information using the GPS module, speed data from the speedometer, and heart rate data from the heart rate sensor. The device also activates the camera to start video recording of the work, thereby capturing facial expression data. The inputs are the user's motion data, location information, speed, heart rate, and video data, and the output is the collection of these data.

[0315] Step 2: Upload data

[0316] When the operating session is over, the user presses the "Stop" button on the device, at which point the device will batch compress all collected data and upload it to the server. The input to this process is the data collected in step 1, and the output is the compressed data uploaded to the server.

[0317] Step 3: Data Receipt and Storage

[0318] The server receives the uploaded data and stores it in a database. The input is the data uploaded in step 2, and the output is the data stored in the database. This provides the foundation for analysis.

[0319] Step 4: Data analysis

[0320] The server uses a generative artificial intelligence model to analyze the data stored in the database. Specifically, it analyzes position data, speed data, and heart rate data to evaluate the user's movement performance. The input is the movement data read from the database, and the output is the performance evaluation result.

[0321] Step 5: Sentiment Analysis

[0322] The server uses an emotion engine to analyze the user's facial expressions from the video data and recognize their emotional state. Additionally, if audio data is available, it is also used for analysis. The input is video data and audio data, and the output is the evaluation result of the emotional state.

[0323] Step 6: Generate optimization advice

[0324] The server uses a generative AI model to generate training optimization advice based on the analysis of movement data. For example, it can suggest a specific interval training schedule or an appropriate movement speed. It also flexibly adjusts the advice based on the user's emotional state. The input is the results of performance evaluation and emotional evaluation, and the output is optimization advice.

[0325] Step 7: Generate behavior improvement advice

[0326] The server generates advice for improving behavior based on the results of analyzing the video data. For example, if a user's arm movements are unnatural while operating a machine, the server will instruct the user on how to correct them. The input is the results of analyzing the video data, and the output is advice for improving behavior.

[0327] Step 8: Formatting and delivering advice

[0328] The server organizes the generated optimization advice and behavior improvement advice, formats the data (e.g., JSON format) taking into account the results of sentiment analysis, and sends it to the user's device. The device displays the received advice on the user interface within the app. The input is the generated advice and the results of sentiment analysis, and the output is the formatted advice that the user receives.

[0329] This processing step enables the system to comprehensively analyze the user's motion data and emotional state, and provide individually optimized training and motion improvement advice.

[0330] 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.

[0331] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0332] 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.

[0333] [Second embodiment]

[0334] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0335] 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.

[0336] 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).

[0337] 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.

[0338] 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.

[0339] 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).

[0340] 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.

[0341] 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.

[0342] 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.

[0343] 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.

[0344] 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.

[0345] 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."

[0346] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. The system aims to improve the user's running performance and prevent injuries.

[0347] Data collection

[0348] The user launches the smartphone app and starts a running session. The device collects real-time data using the smartphone's GPS, heart rate sensor, and speedometer. In addition, the device records video data of the user's running form using the smartphone's camera.

[0349] Data upload

[0350] After completing a running session, the user presses the "stop" button on the smartphone app, and all data collected by the device is uploaded to a server, where it is compressed and transmitted using a secure protocol.

[0351] Data analysis

[0352] The server receives the uploaded data and inputs it into a generative AI model. The generative AI model analyzes the running data (location, speed, heart rate, and time) to evaluate the user's training performance. At the same time, the generative AI model analyzes the video data and evaluates running form using a skeletal detection algorithm.

[0353] Optimization Advice Generation

[0354] The generative AI model generates a training plan tailored to the user based on the analysis of running data. Specifically, it suggests interval training days and running pace adjustments. For example, it calculates the running speed needed to maintain a certain heart rate based on the user's heart rate and speed data.

[0355] Generate form improvement advice

[0356] The generative AI model evaluates running form based on video data and suggests specific improvements. For example, if the swing angle of the right arm is unnatural, the system will provide advice on how to swing both arms with the same amplitude to correct this.

[0357] Providing Feedback

[0358] The server organizes the generated optimization advice and form improvement advice and sends it to the device in JSON format, etc. The device displays the advice to the user and encourages them to put it into practice in their next running session.

[0359] Specific examples

[0360] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate, and the camera captures the user's running form. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Furthermore, analysis of the video data provides specific advice on improving the swing of the right arm. The device displays this advice to the user, who then puts it into practice during their next running session.

[0361] In this way, the system of the present invention can provide users with individually optimized training and form improvement advice, thereby improving running performance and preventing injuries.

[0362] The processing flow will be explained below.

[0363] Step 1:

[0364] A user launches the smartphone app and starts a running session. The device acquires location information from the smartphone's GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The device also activates the camera and starts recording a video of the user's running form.

[0365] Step 2:

[0366] After finishing a running session, the user presses the "Stop" button on the smartphone app. The device then compresses all running data (location, speed, heart rate, time) and video data and uploads them to the server.

[0367] Step 3:

[0368] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0369] Step 4:

[0370] The generative AI model begins analyzing running data, specifically location, speed, and heart rate trends, to assess the user's running performance.

[0371] Step 5:

[0372] At the same time, a generative AI model analyzes the video data, analyzing the video frames and using a skeletal detection algorithm to extract the characteristics of the user's running form.

[0373] Step 6:

[0374] A generative AI model analyzes running data and generates training optimization advice, such as suggesting a specific interval training schedule and an appropriate running pace.

[0375] Step 7:

[0376] The generative AI model analyzes the video data and generates advice to improve form. For example, if the right arm swing is unnatural, the system will advise the player to swing both arms with the same amplitude.

[0377] Step 8:

[0378] The server organizes the generated optimization advice and form improvement advice and formats the data in JSON format, for example.

[0379] Step 9:

[0380] The server sends the formatted data to the device, and the device displays the received advice on the app's user interface.

[0381] Step 10:

[0382] The user then implements the provided advice during their next running session, collects data again, and repeats the process to continually optimize their training and improve their form.

[0383] Example 1

[0384] 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."

[0385] In modern society, improving athletic performance and preventing injuries are important challenges for many people. However, there are limited means for easily obtaining appropriate training and form improvement advice based on individual users' exercise and posture data. The present invention aims to solve these challenges by providing a system that allows users to easily obtain optimized training advice and form improvement advice.

[0386] 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.

[0387] In this invention, the server includes means for collecting exercise data from a user, means for collecting video data capturing posture during exercise, means for inputting the collected exercise data and video data into a generative artificial intelligence model for analysis, means for generating training optimization advice based on the analysis results, means for analyzing the video data and generating posture improvement advice, and means for providing the generated advice to the user's mobile device. This allows users to easily obtain individually optimized training and form improvement advice, enabling them to improve their exercise performance and prevent injuries.

[0388] "Exercise data" refers to data such as location information, speed, and heart rate acquired while the user is exercising.

[0389] "Video data" refers to video data captured while the user is exercising.

[0390] A "generative artificial intelligence model" is an artificial intelligence system that analyzes collected exercise data and video data and generates advice on training and form improvement.

[0391] The "skeleton detection algorithm" is an algorithm for detecting the user's skeletal position from video data.

[0392] "Training optimization advice" is advice on training methods and exercise schedules that is generated based on the user's exercise data.

[0393] "Form improvement advice" is advice that evaluates the user's exercise form based on video data and points out areas for improvement.

[0394] A "mobile terminal" is an electronic device that can be carried by a user, and primarily refers to a smartphone, but may also include other similar devices.

[0395] This invention is a system that collects a user's exercise data and video data of their exercise form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. The system aims to improve the user's exercise performance and prevent injuries.

[0396] Data collection

[0397] The user launches the smartphone app and begins an exercise session. The device collects data in real time using the smartphone's GPS, heart rate sensor, and speedometer. At the same time, the device uses the smartphone's camera to record video data of the exercise form. Specifically, the device records location information every second and collects heart rate and speed data.

[0398] Data upload

[0399] After the exercise session is over, the user presses the "Stop" button on the smartphone app, and the device compresses all collected data (location, heart rate, speed, and video data). The device compresses the data and sends it to a server using a secure protocol (e.g., HTTPS).

[0400] Data analysis

[0401] The server receives the uploaded data and inputs it into a generative AI model. The generative AI model analyzes the exercise data (position, speed, heart rate, and time) to evaluate the user's training performance. At the same time, it analyzes the video data and evaluates the exercise form using a skeletal detection algorithm. Specifically, the generative AI model extracts the position of the skeleton for each video frame and checks the consistency of the form.

[0402] Optimization Advice Generation

[0403] A generative AI model generates a training plan tailored to the user based on the analysis of the exercise data. For example, it calculates the running pace required to maintain a certain heart rate based on the user's heart rate and speed data. As a specific example, it suggests, "For your next workout, do interval training, covering a distance of 1 kilometer, at a speed of 10 kilometers per hour."

[0404] Generate form improvement advice

[0405] The generative AI model evaluates the exercise form based on the video data and suggests specific improvements. For example, if the swing angle of the right arm is unnatural, the model may suggest that the left and right arms should be swung with the same swing width.

[0406] Providing Feedback

[0407] The server organizes the generated optimization advice and form improvement advice and sends it to the device in a data format such as JSON. The device then displays this advice in an easy-to-read format to the user, encouraging them to put it into practice in their next exercise session. For example, it might suggest specific actions, such as, "Try the following advice during your next workout: 1. Set your speed to 9 kilometers per hour to maintain a stable heart rate. 2. Be conscious of swinging both arms evenly to improve your right arm swing."

[0408] In this way, the system of the present invention can provide users with individually optimized training and form improvement advice, thereby improving athletic performance and preventing injuries.

[0409] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0410] Step 1:

[0411] The user launches the smartphone app and performs an input operation to start a running session. This operation causes the device to detect that the app has been launched and activate the necessary sensors (GPS, heart rate sensor, speedometer). Specifically, the device checks the operation of the sensors and begins initial data collection.

[0412] Step 2:

[0413] The device uses the smartphone's GPS to obtain location information every second. It obtains heart rate data from the heart rate sensor and speed data in real time from the speedometer. At the same time, it records video data of the running form using the smartphone's camera. The input data includes location information, heart rate, speed, and video data, which are temporarily stored in the device's storage.

[0414] Step 3:

[0415] After completing a running session, the user presses the "Stop" button on the smartphone app. This action causes the device to compress all collected data. Specifically, the collected location information, heart rate, speed, and video data are combined into a single file using a compression algorithm. The compressed data is then output.

[0416] Step 4:

[0417] The device sends the compressed data to the server using a secure protocol (e.g. HTTPS). The input is the compressed file, which the device sends over a network connection. If successful, the device prints a message confirming that the data was sent.

[0418] Step 5:

[0419] The server receives the compressed file and decompresses it. The decompressed data (location, heart rate, speed, video data) is input into the generative AI model. Based on the input data, the generative AI model first analyzes the running data (location, speed, heart rate, time).

[0420] Step 6:

[0421] The generative AI model outputs the results of analyzing the running data, then analyzes the video data and evaluates running form using a skeletal detection algorithm. The video data is analyzed as input data, and the analysis results output the consistency of form and areas for improvement.

[0422] Step 7:

[0423] Based on the results of each data analysis, the generative AI model generates an optimal training plan and advice for improving form for the user. Specifically, it outputs interval training schedule suggestions, running speed suggestions, and specific instructions for improving form.

[0424] Step 8:

[0425] The server organizes the generated optimization advice and form improvement advice and sends it to the terminal in JSON or other appropriate data format. The input data is the generated advice, and the output is a submission confirmation message.

[0426] Step 9:

[0427] The device displays the received advice to the user in an easy-to-read format. Specifically, it presents the training plan displayed in the app and specific advice on form improvement, encouraging the user to implement it in their next running session. The output of this step is feedback that the user has acknowledged the advice.

[0428] (Application example 1)

[0429] 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."

[0430] In the modern food delivery industry, there is a need to simultaneously optimize the delivery efficiency and health of delivery workers. However, current systems lack the means to monitor not only delivery workers' location and speed, but also their physical movements and health status in real time, and provide specific efficiency and health advice. This often leads to fatigue and health problems among delivery workers, hindering efficient delivery.

[0431] 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.

[0432] In this invention, the server includes means for collecting movement data from users, means for inputting the movement data into a generative AI model and analyzing it, means for generating efficiency advice based on the analysis results, means for analyzing video data of movement form and generating form improvement advice, and means for providing the generated advice to the user's information terminal, thereby enabling delivery personnel to optimize their delivery routes, improve their physical movements, and maintain their health.

[0433] "Movement data" refers to data such as the user's location, speed, and heart rate, and records the user's movement status in real time.

[0434] A "generative artificial intelligence model" is an artificial intelligence system that learns patterns and trends based on collected data and generates analytical results.

[0435] "Efficiency advice" refers to specific suggestions and guidelines for improving work efficiency based on the results of analyzing the user's movement data.

[0436] "Movement form" refers to the body movements and postures that a user performs while moving, and is evaluated in particular for their appropriateness and efficiency.

[0437] "Video data" refers to footage of a user's motion form, and is used for analysis.

[0438] A "body feature detection algorithm" is a program that identifies the position of a user's bones and joints from video data and analyzes their movements.

[0439] An "information terminal" is an electronic device used to input and display data, such as a smartphone or tablet that a user has.

[0440] This invention is a system for simultaneously optimizing the delivery efficiency and health of delivery workers in the food delivery industry. This system collects video data of users' movements and motion forms, and analyzes them using a generative artificial intelligence model to provide specific and individualized advice on efficiency and form improvement. This system is realized using the following main hardware and software:

[0441] Hardware

[0442] 1. Information terminal: Electronic devices held by users, such as smartphones and tablets

[0443] 2. Sensor:

[0444] GPS: Get the user's location in real time

[0445] Heart rate sensor: Measures the user's heart rate

[0446] Speedometer: Measure your speed

[0447] 3. Camera: Records the user's movements as video

[0448] software

[0449] 1. Generative AI model: An AI model for analyzing collected movement data and video data

[0450] 2. Body feature detection algorithm: A program that detects the position of the user's bones and joints from video data and analyzes their movements.

[0451] Data processing and calculation

[0452] Data collection

[0453] The user launches the smartphone app and starts a delivery session. The smartphone uses GPS, a heart rate sensor, and a speedometer to obtain the user's location, heart rate, and speed in real time. The smartphone also uses a camera to record the user's movement form.

[0454] Data upload

[0455] After the delivery session is over, when the user hits the "Stop" button in the app, all collected data is uploaded to the server, compressed and transmitted using a secure protocol.

[0456] Data analysis

[0457] The server receives the uploaded data and analyzes it using a generative AI model. This AI model analyzes movement data (location, speed, heart rate, time) to evaluate the efficiency of the delivery route and the user's physical fitness. It also analyzes video data and evaluates movement form using a body feature detection algorithm.

[0458] Advice Generation

[0459] Based on the results of data analysis, a generative AI model generates efficiency advice and advice on improving the user's behavior, such as providing specific advice on optimizing delivery routes and improving carrying methods.

[0460] Providing Feedback

[0461] The server organizes the generated advice and sends it to the information terminal in JSON format, etc. The information terminal displays the advice to the user and encourages them to put it into practice in the next delivery session.

[0462] Specific examples

[0463] The user initiates a delivery session and performs multiple deliveries. The smartphone records location, speed, and heart rate, and the camera captures the user's movement form. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests route optimization for the next delivery and advice on how to hold the device to prevent fatigue. The device displays this advice to the user, who then puts it into practice during their next delivery session.

[0464] Prompt Sentence Examples

[0465] "Analyze data from delivery sessions to optimize routes and maintain health. Provide optimal recommendations based on the driver's GPS, speed, heart rate, and movement video."

[0466] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0467] Step 1:

[0468] A user launches the smartphone app and begins a delivery session. As input, the user activates the GPS, heart rate, speedometer, and camera. The output is real-time location, heart rate, speed, and video data captured by the smartphone. This data is stored locally during the session.

[0469] Step 2:

[0470] During the session, the device collects real-time location, speed, and heart rate data. The camera records the user's movements. The inputs are data obtained from various sensors and camera footage. The output is the collected data and a video file.

[0471] Step 3:

[0472] After the delivery session ends, the user presses the "Stop" button in the app. The device then compresses all collected data and uploads it to the server using a secure protocol (e.g., HTTPS). The inputs are the collected data and the video file. The outputs are the data sent to the server and the video file.

[0473] Step 4:

[0474] The server receives the uploaded data and prepares it for analysis. The inputs are location, speed, heart rate, and video data sent from the device. The output is data converted into an analyzable format.

[0475] Step 5:

[0476] The server analyzes the data using a generative AI model. Inputs include location information, speed, heart rate data, and video data. The generative AI model analyzes the movement data to evaluate the efficiency of the delivery route and the user's physical fitness, and analyzes the video data to evaluate the user's movement form. The output is the analysis of the movement data and advice on improving form.

[0477] Step 6:

[0478] The generative AI model generates efficiency advice and advice on improving movement form based on the analysis results. The inputs are the analysis results of movement data and video data. The output is efficiency advice and advice on improving movement form that are appropriate for the user.

[0479] Step 7:

[0480] The server organizes the generated advice in JSON format or similar and sends it to the terminal. The input is the generated advice. The output is advice organized in JSON format.

[0481] Step 8:

[0482] The device receives advice from the server and displays it to the user. The input is advice sent from the server. The output is efficiency advice and form improvement advice displayed on the smartphone screen. The user can put these advices into practice in the next delivery session.

[0483] 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.

[0484] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. In addition, by combining this with an emotion engine that recognizes the user's emotions, it provides more personalized advice. This system aims to improve the user's running performance, prevent injuries, and increase the user's motivation.

[0485] Data collection

[0486] A user launches the smartphone app and starts a running session. The device obtains location information from the smartphone's GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The device also activates the camera to start recording a video of the user's running form and records facial expression data for the emotion engine.

[0487] Data upload

[0488] After finishing a running session, the user presses the "Stop" button on the smartphone app. The device then compresses all running data (location, speed, heart rate, time) and video data and uploads them to the server.

[0489] Data analysis

[0490] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0491] Emotion analysis

[0492] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state, and also uses audio data, if available, for analysis.

[0493] Running data analysis

[0494] The generative AI model begins analyzing running data, specifically location, speed, and heart rate trends, to assess the user's running performance.

[0495] Optimization Advice Generation

[0496] A generative AI model generates training optimization advice based on the analysis of running data. For example, it suggests a specific interval training schedule and an appropriate running pace. Furthermore, it adjusts the content and wording of the advice based on the user's emotional state. For example, if the user is feeling fatigued or stressed, it will use a gentle tone of voice to motivate them and suggest taking a break.

[0497] Generate form improvement advice

[0498] The generative AI model generates advice to improve form based on the analysis of video data. For example, if the swing of the right arm is unnatural, the system will instruct the user to swing both arms with the same amplitude to correct this. Furthermore, the system takes the user's emotions into consideration and provides advice with encouraging words.

[0499] Providing Feedback

[0500] The server organizes the generated optimization advice and form improvement advice, takes into account the results of sentiment analysis, and formats the data in JSON format or other formats. The server then sends the formatted data to the device. The advice received by the device is then displayed in the app's user interface.

[0501] Specific examples

[0502] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate data, and the camera captures the user's running form and facial expressions. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Analysis of the video data also provides specific advice on improving the swing of the right arm. An emotion engine analyzes the user's facial expression data and, if the user feels fatigued or stressed, provides advice that takes rest into consideration. The device displays this advice to the user, who then puts it into practice during their next running session.

[0503] In this way, the system of the present invention provides users with individually optimized training and form improvement advice, improving running performance and preventing injuries, and also provides support to improve motivation by taking into account their emotional state.

[0504] The processing flow will be explained below.

[0505] Step 1:

[0506] The user launches the smartphone app and starts a running session. The device acquires location information from the smartphone's GPS module, receives real-time heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to capture the user's running form and facial expression.

[0507] Step 2:

[0508] After the device finishes running, the user presses the "Stop" button. The device compresses the location, speed, heart rate, and video data it has acquired, and uploads the data to a server using a secure protocol.

[0509] Step 3:

[0510] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0511] Step 4:

[0512] The generative AI model begins analyzing running data. Specifically, it analyzes trends in position, speed, and heart rate to evaluate the user's running performance. It also analyzes video data and uses a skeletal detection algorithm to extract form features.

[0513] Step 5:

[0514] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state, and if audio data is available, it can also be used in the analysis to more accurately determine emotions.

[0515] Step 6:

[0516] A generative AI model analyzes running data and generates training optimization advice, such as suggesting a specific timetable for interval training and an appropriate running pace.

[0517] Step 7:

[0518] The generative AI model reflects the analysis results of the emotion engine and adjusts the content and expression of the advice. For example, if the user is feeling fatigued or stressed, it may suggest reducing the intensity of their training or generate advice that includes an encouraging message.

[0519] Step 8:

[0520] The generative AI model generates advice on improving form based on the analysis of video data. For example, if the swing of the right arm is unnatural, it will suggest specific practice methods to correct it.

[0521] Step 9:

[0522] The server organizes the generated optimization advice and form improvement advice, and formats the customized advice data in JSON format or other formats based on the analysis results of the emotion engine.

[0523] Step 10:

[0524] The server sends the formatted data to the device, and the device displays the received advice on the user interface within the app. The advice includes an appropriate message that takes into account the user's emotional state.

[0525] Step 11:

[0526] The user then implements the provided advice during their next running session, collects data again, and repeats the process to continually optimize their training and improve their form.

[0527] The above are the detailed processing steps in the embodiment of the present invention, which allow users to receive scientifically and individually optimized training and form improvement advice, improve running performance, prevent injuries, and receive emotional support.

[0528] Example 2

[0529] 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."

[0530] Conventional running training systems focus on analyzing users' running data and running form, but it is difficult to provide advice that takes into account the user's emotional state. Furthermore, the data compression and uploading processes are sometimes inefficient, and real-time performance and data processing accuracy need to be improved. Furthermore, video analysis for form improvement requires the use of advanced algorithms, which presents challenges.

[0531] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0532] In this invention, the server includes means for collecting running data from the user, means for compressing the collected data by the terminal and uploading it to the server, means for the server to store the uploaded data in a database, means for inputting the running data into a generative artificial intelligence model for analysis, means for an emotion engine to analyze the video data and recognize the user's emotional state, means for generating training optimization advice based on the analysis results, means for analyzing the running form video data and generating form improvement advice, and means for providing the generated advice to the user's terminal. This not only improves the user's running performance, but also makes it possible to provide personalized advice based on the user's emotional state, achieving advanced data processing and real-time performance.

[0533] "Running data" refers to data including location information, speed data, heart rate data, and running time acquired while the user is running.

[0534] A "terminal" is an electronic device used by a user, such as a smartphone or a wearable device.

[0535] A "server" is a computer system that stores data, analyzes it, and runs generative artificial intelligence models.

[0536] A "generative artificial intelligence model" is an artificial intelligence model that analyzes a user's running data and generates advice on optimizing training and improving form.

[0537] An "emotion engine" is software that analyzes video data to recognize the user's emotional state.

[0538] "Training optimization advice" refers to specific training methods and schedule suggestions provided by the generative artificial intelligence model to improve the user's running performance.

[0539] "Form improvement advice" refers to specific instructions and suggestions provided by the generative artificial intelligence model to improve a user's running form.

[0540] A "skeleton detection algorithm" is an algorithm used to detect a user's skeleton and posture in video data analysis.

[0541] "Interval training" is a training method that alternates between high-intensity running and low-intensity running.

[0542] "Pace adjustment" refers to speed management that allows for effective training by appropriately controlling the user's running speed.

[0543] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. In addition, by combining this with an emotion engine that recognizes the user's emotions, it provides more personalized advice. This system aims to improve the user's running performance, prevent injuries, and increase the user's motivation.

[0544] Data collection

[0545] A user launches the smartphone app and starts a running session. The device acquires location information using the smartphone's GPS module, receives heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to start recording a video of the user's running form and also records facial expression data for the emotion engine.

[0546] Data upload

[0547] After finishing a running session, the user presses the "Stop" button on the smartphone app, which causes the device to compress all running data (location information, speed data, heart rate data, running time) and video data and upload them to the server.

[0548] Data analysis

[0549] The server receives the uploaded data and stores it in a database, after which the server inputs the data into a generative artificial intelligence model and begins analysis.

[0550] Emotion analysis

[0551] The emotion engine analyzes the video data to recognize the user's emotional state from their facial expressions, and also uses audio data, if available.

[0552] Running data analysis

[0553] A generative AI model analyzes running data, specifically trends in location, speed, and heart rate data, to assess a user's running performance.

[0554] Optimization Advice Generation

[0555] A generative AI model generates training optimization advice based on the analysis of running data. For example, it suggests a specific interval training schedule and an appropriate running pace. Furthermore, the content and wording of the advice can be adjusted based on the user's emotional state. For example, if the user is feeling fatigued or stressed, it can use a gentle tone of voice to motivate them or suggest taking a break.

[0556] Generate form improvement advice

[0557] The generative AI model generates advice to improve form based on the analysis of video data. For example, if the swing of the right arm is unnatural, the system will instruct the user to swing both arms with the same amplitude to correct this. Furthermore, the system takes the user's emotions into consideration and provides encouraging advice.

[0558] Providing Feedback

[0559] The server organizes the generated optimization advice and form improvement advice, formats the data taking into account the results of sentiment analysis, and sends the formatted data to the device, which then displays the advice received on the device in the app's user interface.

[0560] Specific examples

[0561] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate data, and the camera captures the user's running form and facial expressions. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Video data analysis also provides specific advice on improving the swing of the right arm. An emotion engine analyzes the user's facial expression data and, if the user feels fatigued or stressed, provides advice that takes rest into consideration. The device displays this advice to the user, who then puts it into practice in their next running session.

[0562] Examples of prompts:

[0563] Analyze the user's running performance based on the following data and generate optimal training advice and form improvement advice.

[0564] Data: location information, speed data, heart rate data, running time, running form video, user facial expression data

[0565] User's emotional state: Fatigue

[0566] In this way, the system of the present invention provides users with individually optimized training and advice on improving their form, improving their running performance and preventing injuries, and also provides support to improve motivation by taking into account their emotional state.

[0567] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0568] Step 1:

[0569] The user starts the smartphone app and presses the "Start" button to begin a running session. The device acquires location information using the smartphone's GPS module, receives heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to begin recording video of the user's running form and records facial expression data for the emotion engine. By collecting these input data (location information, speed data, heart rate data, and video data), real-time data collection is performed from the start of the run.

[0570] Step 2:

[0571] The device obtains location information every second from the GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The camera continuously records the user's running form and facial expressions. This allows input data (location information, heart rate data, speed data, and video data) to be continuously accumulated. The collected data is stored in the internal memory and prepared for further processing.

[0572] Step 3:

[0573] When the running session is over, the user presses the "Stop" button on the smartphone app. This action causes the device to stop collecting data from the sensors and end the camera recording. This finalizes all data collected during the session (location, speed, heart rate, and video data) and prepares it for the next upload step.

[0574] Step 4:

[0575] All data collected by the device (location, speed, heart rate, and video data) is compressed into a single file. This compressed file becomes the input data for the next step. Compression improves data transmission efficiency, saving time and bandwidth for transfer.

[0576] Step 5:

[0577] The device uploads the compressed file to a server via the internet, sending the data collected and compressed so far to the server, where it is stored in a database and prepared for the next analysis step.

[0578] Step 6:

[0579] The server receives the compressed file and stores it in a database. It checks the data integrity and decompresses it if necessary. The decompressed data (location information, speed data, heart rate data, video data) is used for further analysis.

[0580] Step 7:

[0581] The server extracts the necessary data from the database and inputs it into the generative AI model. Based on this input data, the generative AI model begins analyzing the data. For example, it analyzes changes in location data and speed trends to evaluate the user's performance.

[0582] Step 8:

[0583] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state. If audio data is available, it is also used for analysis. The results of this analysis are classified into emotion categories (positive, negative, or neutral).

[0584] Step 9:

[0585] A generative AI model analyzes running data and evaluates trends in position, speed, and heart rate. Based on this, it quantitatively evaluates the user's running performance. This evaluation results form the basis for advice generated in the next step.

[0586] Step 10:

[0587] Based on the analysis results, the generative AI model generates training optimization advice. For example, it suggests the next interval training schedule or an appropriate running pace. It also adjusts the content and wording of advice based on the emotion analysis results. For example, if the emotional state indicates fatigue or stress, it may suggest a gentler tone of voice or rest to increase motivation.

[0588] Step 11:

[0589] The generative AI model generates advice on improving form based on the analysis of video data. For example, if the swing of the right arm is unnatural, it will suggest ways to correct it. It also takes into account the player's emotional state and provides encouraging advice.

[0590] Step 12:

[0591] The server organizes the generated optimization advice and form improvement advice, formats the data taking into account the results of sentiment analysis, and sends the formatted data in JSON format or other formats to the device.

[0592] Step 13:

[0593] The device analyzes the received feedback and displays it on the smartphone app's user interface, allowing users to review training optimization and form improvement advice and put it into practice during their next running session.

[0594] (Application example 2)

[0595] 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."

[0596] In modern factories, improving the efficiency and accuracy of robot operations is important. However, current systems are unable to provide optimization advice that takes into account operation data and the emotional state of workers, resulting in reduced work efficiency and increased worker stress. The present invention aims to solve these problems by optimizing the operation of factory robots, improving work efficiency, and providing personalized advice that takes into account the emotional state of workers.

[0597] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting running data from the user, means for inputting the running data into a generative AI model and analyzing it, means for generating training optimization advice based on the analysis results, means for analyzing video data of the running form and generating form improvement advice, means for providing the generated advice to the user's terminal, means for recognizing an emotional state from the video data using an emotion engine, and means for adjusting the content of the advice based on the recognized emotional state. This improves the operating efficiency of factory robots, reduces worker stress, and makes it possible to provide optimized work advice.

[0598] "User" refers to an individual or operator who uses this system.

[0599] "Running data" refers to data related to a user's exercise, such as location information, speed, heart rate, and time.

[0600] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that analyzes collected data and generates optimization and improvement advice.

[0601] "Video data" refers to video data captured using a camera or other imaging device.

[0602] "Emotion engine" refers to an engine that analyzes video and audio data to recognize and evaluate the user's emotional state.

[0603] "Advice" refers to instructions or suggestions generated based on the analysis results.

[0604] "Terminal" refers to a device, such as a smartphone or computer, that a user uses to operate this system.

[0605] A "skeleton detection algorithm" refers to an algorithm that detects human skeletons from video data and analyzes their movements.

[0606] "Interval training" refers to a training technique that alternates between high-intensity and low-intensity exercise.

[0607] "Pacing" refers to adjusting the speed and rhythm of your running or work.

[0608] This invention is a system that collects user motion data and analyzes it using a generative artificial intelligence model to provide training optimization advice and motion improvement advice. Furthermore, by combining it with an emotion engine, it is possible to provide personalized advice that takes into account the user's emotional state.

[0609] Data collection

[0610] The user starts the device and begins a movement session. The device acquires location information using the GPS module, speed data from the speedometer, and heart rate data from the heart rate sensor. It then activates the camera to begin video recording of the user's movements, which also records facial expression data. This allows the device to collect a variety of movement data from different angles.

[0611] Data upload

[0612] When the movement session is over, the user presses the "stop" button on the device, which causes the device to compress all collected data (location, speed, heart rate, time, and video data) and upload it to a server, where it is centrally aggregated and available for analysis.

[0613] Data and Sentiment Analysis

[0614] The server receives the uploaded data and stores it in a database. The server analyzes the data using a generative artificial intelligence model to evaluate the user's performance. It also uses an emotion engine to analyze the user's emotional state from video data. The emotion engine analyzes facial expression and voice data to recognize the user's emotional state. This analysis makes it possible to grasp in detail the state in which the user was operating.

[0615] Advice Generation

[0616] The generative AI model generates training optimization advice based on the analysis of movement data. For example, it suggests a specific schedule and appropriate speed for interval training. It also generates movement improvement advice based on analysis of video data. For example, it suggests ways to make the right arm move more smoothly. It also adjusts the content and expression of the advice based on the user's emotional state. If the user is feeling tired or stressed, it suggests gentle tone of voice to motivate them or suggests taking a rest.

[0617] Providing Feedback

[0618] The server organizes the generated optimization advice and behavior improvement advice, takes into account the results of sentiment analysis, and formats the data in JSON format or other formats. The formatted data is then sent to the device, which then displays the received advice on the app's user interface.

[0619] As a concrete example, when a user operates a robot in a factory, once the user's daily work exceeds a certain volume, the device records location information, speed, and heart rate data, and a video camera captures the user's movements and facial expressions. After the work is completed, the device uploads the data to a server, which analyzes it using a generative artificial intelligence model. Based on the next work schedule, the device proposes a new interval training schedule and appropriate movement timing, and provides detailed advice on how to smooth the movement of the right arm. An emotion engine analyzes the user's facial expression data and simultaneously provides advice, including advice on rest, if the user feels fatigued or stressed.

[0620] Prompt Sentence Examples

[0621] "A robot is performing a machine assembly task. Please automatically capture the worker's movements, analyze their behavior and their emotional state, and provide optimization advice for the next task."

[0622] In this way, the system of the present invention provides users with individually optimized advice on improving their movements and form, thereby improving their work performance and preventing injuries, and also provides support for improving motivation by taking into account their emotional state.

[0623] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0624] Step 1: Data collection

[0625] A user starts a work session on their device. The device acquires location information using the GPS module, speed data from the speedometer, and heart rate data from the heart rate sensor. The device also activates the camera to start video recording of the work, thereby capturing facial expression data. The inputs are the user's motion data, location information, speed, heart rate, and video data, and the output is the collection of these data.

[0626] Step 2: Upload data

[0627] When the operating session is over, the user presses the "Stop" button on the device, at which point the device will batch compress all collected data and upload it to the server. The input to this process is the data collected in step 1, and the output is the compressed data uploaded to the server.

[0628] Step 3: Data Receipt and Storage

[0629] The server receives the uploaded data and stores it in a database. The input is the data uploaded in step 2, and the output is the data stored in the database. This provides the foundation for analysis.

[0630] Step 4: Data analysis

[0631] The server uses a generative artificial intelligence model to analyze the data stored in the database. Specifically, it analyzes position data, speed data, and heart rate data to evaluate the user's movement performance. The input is the movement data read from the database, and the output is the performance evaluation result.

[0632] Step 5: Sentiment Analysis

[0633] The server uses an emotion engine to analyze the user's facial expressions from the video data and recognize their emotional state. Additionally, if audio data is available, it is also used for analysis. The input is video data and audio data, and the output is the evaluation result of the emotional state.

[0634] Step 6: Generate optimization advice

[0635] The server uses a generative AI model to generate training optimization advice based on the analysis of movement data. For example, it can suggest a specific interval training schedule or an appropriate movement speed. It also flexibly adjusts the advice based on the user's emotional state. The input is the results of performance evaluation and emotional evaluation, and the output is optimization advice.

[0636] Step 7: Generate behavior improvement advice

[0637] The server generates advice for improving behavior based on the results of analyzing the video data. For example, if a user's arm movements are unnatural while operating a machine, the server will instruct the user on how to correct them. The input is the results of analyzing the video data, and the output is advice for improving behavior.

[0638] Step 8: Formatting and delivering advice

[0639] The server organizes the generated optimization advice and behavior improvement advice, formats the data (e.g., JSON format) taking into account the results of sentiment analysis, and sends it to the user's device. The device displays the received advice on the user interface within the app. The input is the generated advice and the results of sentiment analysis, and the output is the formatted advice that the user receives.

[0640] This processing step enables the system to comprehensively analyze the user's motion data and emotional state, and provide individually optimized training and motion improvement advice.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] [Third embodiment]

[0645] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0646] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0647] 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).

[0648] 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.

[0649] 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.

[0650] 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).

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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."

[0657] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. The system aims to improve the user's running performance and prevent injuries.

[0658] Data collection

[0659] The user launches the smartphone app and starts a running session. The device collects real-time data using the smartphone's GPS, heart rate sensor, and speedometer. In addition, the device records video data of the user's running form using the smartphone's camera.

[0660] Data upload

[0661] After completing a running session, the user presses the "stop" button on the smartphone app, and all data collected by the device is uploaded to a server, where it is compressed and transmitted using a secure protocol.

[0662] Data analysis

[0663] The server receives the uploaded data and inputs it into a generative AI model. The generative AI model analyzes the running data (location, speed, heart rate, and time) to evaluate the user's training performance. At the same time, the generative AI model analyzes the video data and evaluates running form using a skeletal detection algorithm.

[0664] Optimization Advice Generation

[0665] The generative AI model generates a training plan tailored to the user based on the analysis of running data. Specifically, it suggests interval training days and running pace adjustments. For example, it calculates the running speed needed to maintain a certain heart rate based on the user's heart rate and speed data.

[0666] Generate form improvement advice

[0667] The generative AI model evaluates running form based on video data and suggests specific improvements. For example, if the swing angle of the right arm is unnatural, the system will provide advice on how to swing both arms with the same amplitude to correct this.

[0668] Providing Feedback

[0669] The server organizes the generated optimization advice and form improvement advice and sends it to the device in JSON format, etc. The device displays the advice to the user and encourages them to put it into practice in their next running session.

[0670] Specific examples

[0671] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate, and the camera captures the user's running form. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Furthermore, analysis of the video data provides specific advice on improving the swing of the right arm. The device displays this advice to the user, who then puts it into practice during their next running session.

[0672] In this way, the system of the present invention can provide users with individually optimized training and form improvement advice, thereby improving running performance and preventing injuries.

[0673] The processing flow will be explained below.

[0674] Step 1:

[0675] A user launches the smartphone app and starts a running session. The device acquires location information from the smartphone's GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The device also activates the camera and starts recording a video of the user's running form.

[0676] Step 2:

[0677] After finishing a running session, the user presses the "Stop" button on the smartphone app. The device then compresses all running data (location, speed, heart rate, time) and video data and uploads them to the server.

[0678] Step 3:

[0679] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0680] Step 4:

[0681] The generative AI model begins analyzing running data, specifically location, speed, and heart rate trends, to assess the user's running performance.

[0682] Step 5:

[0683] At the same time, a generative AI model analyzes the video data, analyzing the video frames and using a skeletal detection algorithm to extract the characteristics of the user's running form.

[0684] Step 6:

[0685] A generative AI model analyzes running data and generates training optimization advice, such as suggesting a specific interval training schedule and an appropriate running pace.

[0686] Step 7:

[0687] The generative AI model analyzes the video data and generates advice to improve form. For example, if the right arm swing is unnatural, the system will advise the player to swing both arms with the same amplitude.

[0688] Step 8:

[0689] The server organizes the generated optimization advice and form improvement advice and formats the data in JSON format, for example.

[0690] Step 9:

[0691] The server sends the formatted data to the device, and the device displays the received advice on the app's user interface.

[0692] Step 10:

[0693] The user then implements the provided advice during their next running session, collects data again, and repeats the process to continually optimize their training and improve their form.

[0694] Example 1

[0695] 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."

[0696] In modern society, improving athletic performance and preventing injuries are important challenges for many people. However, there are limited means for easily obtaining appropriate training and form improvement advice based on individual users' exercise and posture data. The present invention aims to solve these challenges by providing a system that allows users to easily obtain optimized training advice and form improvement advice.

[0697] 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.

[0698] In this invention, the server includes means for collecting exercise data from a user, means for collecting video data capturing posture during exercise, means for inputting the collected exercise data and video data into a generative artificial intelligence model for analysis, means for generating training optimization advice based on the analysis results, means for analyzing the video data and generating posture improvement advice, and means for providing the generated advice to the user's mobile device. This allows users to easily obtain individually optimized training and form improvement advice, enabling them to improve their exercise performance and prevent injuries.

[0699] "Exercise data" refers to data such as location information, speed, and heart rate acquired while the user is exercising.

[0700] "Video data" refers to video data captured while the user is exercising.

[0701] A "generative artificial intelligence model" is an artificial intelligence system that analyzes collected exercise data and video data and generates advice on training and form improvement.

[0702] The "skeleton detection algorithm" is an algorithm for detecting the user's skeletal position from video data.

[0703] "Training optimization advice" is advice on training methods and exercise schedules that is generated based on the user's exercise data.

[0704] "Form improvement advice" is advice that evaluates the user's exercise form based on video data and points out areas for improvement.

[0705] A "mobile terminal" is an electronic device that can be carried by a user, and primarily refers to a smartphone, but may also include other similar devices.

[0706] This invention is a system that collects a user's exercise data and video data of their exercise form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. The system aims to improve the user's exercise performance and prevent injuries.

[0707] Data collection

[0708] The user launches the smartphone app and begins an exercise session. The device collects data in real time using the smartphone's GPS, heart rate sensor, and speedometer. At the same time, the device uses the smartphone's camera to record video data of the exercise form. Specifically, the device records location information every second and collects heart rate and speed data.

[0709] Data upload

[0710] After the exercise session is over, the user presses the "Stop" button on the smartphone app, and the device compresses all collected data (location, heart rate, speed, and video data). The device compresses the data and sends it to a server using a secure protocol (e.g., HTTPS).

[0711] Data analysis

[0712] The server receives the uploaded data and inputs it into a generative AI model. The generative AI model analyzes the exercise data (position, speed, heart rate, and time) to evaluate the user's training performance. At the same time, it analyzes the video data and evaluates the exercise form using a skeletal detection algorithm. Specifically, the generative AI model extracts the position of the skeleton for each video frame and checks the consistency of the form.

[0713] Optimization Advice Generation

[0714] A generative AI model generates a training plan tailored to the user based on the analysis of the exercise data. For example, it calculates the running pace required to maintain a certain heart rate based on the user's heart rate and speed data. As a specific example, it suggests, "For your next workout, do interval training, covering a distance of 1 kilometer, at a speed of 10 kilometers per hour."

[0715] Generate form improvement advice

[0716] The generative AI model evaluates the exercise form based on the video data and suggests specific improvements. For example, if the swing angle of the right arm is unnatural, the model may suggest that the left and right arms should be swung with the same swing width.

[0717] Providing Feedback

[0718] The server organizes the generated optimization advice and form improvement advice and sends it to the device in a data format such as JSON. The device then displays this advice in an easy-to-read format to the user, encouraging them to put it into practice in their next exercise session. For example, it might suggest specific actions, such as, "Try the following advice during your next workout: 1. Set your speed to 9 kilometers per hour to maintain a stable heart rate. 2. Be conscious of swinging both arms evenly to improve your right arm swing."

[0719] In this way, the system of the present invention can provide users with individually optimized training and form improvement advice, thereby improving athletic performance and preventing injuries.

[0720] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0721] Step 1:

[0722] The user launches the smartphone app and performs an input operation to start a running session. This operation causes the device to detect that the app has been launched and activate the necessary sensors (GPS, heart rate sensor, speedometer). Specifically, the device checks the operation of the sensors and begins initial data collection.

[0723] Step 2:

[0724] The device uses the smartphone's GPS to obtain location information every second. It obtains heart rate data from the heart rate sensor and speed data in real time from the speedometer. At the same time, it records video data of the running form using the smartphone's camera. The input data includes location information, heart rate, speed, and video data, which are temporarily stored in the device's storage.

[0725] Step 3:

[0726] After completing a running session, the user presses the "Stop" button on the smartphone app. This action causes the device to compress all collected data. Specifically, the collected location information, heart rate, speed, and video data are combined into a single file using a compression algorithm. The compressed data is then output.

[0727] Step 4:

[0728] The device sends the compressed data to the server using a secure protocol (e.g. HTTPS). The input is the compressed file, which the device sends over a network connection. If successful, the device prints a message confirming that the data was sent.

[0729] Step 5:

[0730] The server receives the compressed file and decompresses it. The decompressed data (location, heart rate, speed, video data) is input into the generative AI model. Based on the input data, the generative AI model first analyzes the running data (location, speed, heart rate, time).

[0731] Step 6:

[0732] The generative AI model outputs the results of analyzing the running data, then analyzes the video data and evaluates running form using a skeletal detection algorithm. The video data is analyzed as input data, and the analysis results output the consistency of form and areas for improvement.

[0733] Step 7:

[0734] Based on the results of each data analysis, the generative AI model generates an optimal training plan and advice for improving form for the user. Specifically, it outputs interval training schedule suggestions, running speed suggestions, and specific instructions for improving form.

[0735] Step 8:

[0736] The server organizes the generated optimization advice and form improvement advice and sends it to the terminal in JSON or other appropriate data format. The input data is the generated advice, and the output is a submission confirmation message.

[0737] Step 9:

[0738] The device displays the received advice to the user in an easy-to-read format. Specifically, it presents the training plan displayed in the app and specific advice on form improvement, encouraging the user to implement it in their next running session. The output of this step is feedback that the user has acknowledged the advice.

[0739] (Application example 1)

[0740] 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."

[0741] In the modern food delivery industry, there is a need to simultaneously optimize the delivery efficiency and health of delivery workers. However, current systems lack the means to monitor not only delivery workers' location and speed, but also their physical movements and health status in real time, and provide specific efficiency and health advice. This often leads to fatigue and health problems among delivery workers, hindering efficient delivery.

[0742] 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.

[0743] In this invention, the server includes means for collecting movement data from users, means for inputting the movement data into a generative AI model and analyzing it, means for generating efficiency advice based on the analysis results, means for analyzing video data of movement form and generating form improvement advice, and means for providing the generated advice to the user's information terminal, thereby enabling delivery personnel to optimize their delivery routes, improve their physical movements, and maintain their health.

[0744] "Movement data" refers to data such as the user's location, speed, and heart rate, and records the user's movement status in real time.

[0745] A "generative artificial intelligence model" is an artificial intelligence system that learns patterns and trends based on collected data and generates analytical results.

[0746] "Efficiency advice" refers to specific suggestions and guidelines for improving work efficiency based on the results of analyzing the user's movement data.

[0747] "Movement form" refers to the body movements and postures that a user performs while moving, and is evaluated in particular for their appropriateness and efficiency.

[0748] "Video data" refers to footage of a user's motion form, and is used for analysis.

[0749] A "body feature detection algorithm" is a program that identifies the position of a user's bones and joints from video data and analyzes their movements.

[0750] An "information terminal" is an electronic device used to input and display data, such as a smartphone or tablet that a user has.

[0751] This invention is a system for simultaneously optimizing the delivery efficiency and health of delivery workers in the food delivery industry. This system collects video data of users' movements and motion forms, and analyzes them using a generative artificial intelligence model to provide specific and individualized advice on efficiency and form improvement. This system is realized using the following main hardware and software:

[0752] Hardware

[0753] 1. Information terminal: Electronic devices held by users, such as smartphones and tablets

[0754] 2. Sensor:

[0755] GPS: Get the user's location in real time

[0756] Heart rate sensor: Measures the user's heart rate

[0757] Speedometer: Measure your speed

[0758] 3. Camera: Records the user's movements as video

[0759] software

[0760] 1. Generative AI model: An AI model for analyzing collected movement data and video data

[0761] 2. Body feature detection algorithm: A program that detects the position of the user's bones and joints from video data and analyzes their movements.

[0762] Data processing and calculation

[0763] Data collection

[0764] The user launches the smartphone app and starts a delivery session. The smartphone uses GPS, a heart rate sensor, and a speedometer to obtain the user's location, heart rate, and speed in real time. The smartphone also uses a camera to record the user's movement form.

[0765] Data upload

[0766] After the delivery session is over, when the user hits the "Stop" button in the app, all collected data is uploaded to the server, compressed and transmitted using a secure protocol.

[0767] Data analysis

[0768] The server receives the uploaded data and analyzes it using a generative AI model. This AI model analyzes movement data (location, speed, heart rate, time) to evaluate the efficiency of the delivery route and the user's physical fitness. It also analyzes video data and evaluates movement form using a body feature detection algorithm.

[0769] Advice Generation

[0770] Based on the results of data analysis, a generative AI model generates efficiency advice and advice on improving the user's behavior, such as providing specific advice on optimizing delivery routes and improving carrying methods.

[0771] Providing Feedback

[0772] The server organizes the generated advice and sends it to the information terminal in JSON format, etc. The information terminal displays the advice to the user and encourages them to put it into practice in the next delivery session.

[0773] Specific examples

[0774] The user initiates a delivery session and performs multiple deliveries. The smartphone records location, speed, and heart rate, and the camera captures the user's movement form. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests route optimization for the next delivery and advice on how to hold the device to prevent fatigue. The device displays this advice to the user, who then puts it into practice during their next delivery session.

[0775] Prompt Sentence Examples

[0776] "Analyze data from delivery sessions to optimize routes and maintain health. Provide optimal recommendations based on the driver's GPS, speed, heart rate, and movement video."

[0777] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0778] Step 1:

[0779] A user launches the smartphone app and begins a delivery session. As input, the user activates the GPS, heart rate, speedometer, and camera. The output is real-time location, heart rate, speed, and video data captured by the smartphone. This data is stored locally during the session.

[0780] Step 2:

[0781] During the session, the device collects real-time location, speed, and heart rate data. The camera records the user's movements. The inputs are data obtained from various sensors and camera footage. The output is the collected data and a video file.

[0782] Step 3:

[0783] After the delivery session ends, the user presses the "Stop" button in the app. The device then compresses all collected data and uploads it to the server using a secure protocol (e.g., HTTPS). The inputs are the collected data and the video file. The outputs are the data sent to the server and the video file.

[0784] Step 4:

[0785] The server receives the uploaded data and prepares it for analysis. The inputs are location, speed, heart rate, and video data sent from the device. The output is data converted into an analyzable format.

[0786] Step 5:

[0787] The server analyzes the data using a generative AI model. Inputs include location information, speed, heart rate data, and video data. The generative AI model analyzes the movement data to evaluate the efficiency of the delivery route and the user's physical fitness, and analyzes the video data to evaluate the user's movement form. The output is the analysis of the movement data and advice on improving form.

[0788] Step 6:

[0789] The generative AI model generates efficiency advice and advice on improving movement form based on the analysis results. The inputs are the analysis results of movement data and video data. The output is efficiency advice and advice on improving movement form that are appropriate for the user.

[0790] Step 7:

[0791] The server organizes the generated advice in JSON format or similar and sends it to the terminal. The input is the generated advice. The output is advice organized in JSON format.

[0792] Step 8:

[0793] The device receives advice from the server and displays it to the user. The input is advice sent from the server. The output is efficiency advice and form improvement advice displayed on the smartphone screen. The user can put these advices into practice in the next delivery session.

[0794] 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.

[0795] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. In addition, by combining this with an emotion engine that recognizes the user's emotions, it provides more personalized advice. This system aims to improve the user's running performance, prevent injuries, and increase the user's motivation.

[0796] Data collection

[0797] A user launches the smartphone app and starts a running session. The device obtains location information from the smartphone's GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The device also activates the camera to start recording a video of the user's running form and records facial expression data for the emotion engine.

[0798] Data upload

[0799] After finishing a running session, the user presses the "Stop" button on the smartphone app. The device then compresses all running data (location, speed, heart rate, time) and video data and uploads them to the server.

[0800] Data analysis

[0801] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0802] Emotion analysis

[0803] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state, and also uses audio data, if available, for analysis.

[0804] Running data analysis

[0805] The generative AI model begins analyzing running data, specifically location, speed, and heart rate trends, to assess the user's running performance.

[0806] Optimization Advice Generation

[0807] A generative AI model generates training optimization advice based on the analysis of running data. For example, it suggests a specific interval training schedule and an appropriate running pace. Furthermore, it adjusts the content and wording of the advice based on the user's emotional state. For example, if the user is feeling fatigued or stressed, it will use a gentle tone of voice to motivate them and suggest taking a break.

[0808] Generate form improvement advice

[0809] The generative AI model generates advice to improve form based on the analysis of video data. For example, if the swing of the right arm is unnatural, the system will instruct the user to swing both arms with the same amplitude to correct this. Furthermore, the system takes the user's emotions into consideration and provides advice with encouraging words.

[0810] Providing Feedback

[0811] The server organizes the generated optimization advice and form improvement advice, takes into account the results of sentiment analysis, and formats the data in JSON format or other formats. The server then sends the formatted data to the device. The advice received by the device is then displayed in the app's user interface.

[0812] Specific examples

[0813] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate data, and the camera captures the user's running form and facial expressions. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Analysis of the video data also provides specific advice on improving the swing of the right arm. An emotion engine analyzes the user's facial expression data and, if the user feels fatigued or stressed, provides advice that takes rest into consideration. The device displays this advice to the user, who then puts it into practice during their next running session.

[0814] In this way, the system of the present invention provides users with individually optimized training and form improvement advice, improving running performance and preventing injuries, and also provides support to improve motivation by taking into account their emotional state.

[0815] The processing flow will be explained below.

[0816] Step 1:

[0817] The user launches the smartphone app and starts a running session. The device acquires location information from the smartphone's GPS module, receives real-time heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to capture the user's running form and facial expression.

[0818] Step 2:

[0819] After the device finishes running, the user presses the "Stop" button. The device compresses the location, speed, heart rate, and video data it has acquired, and uploads the data to a server using a secure protocol.

[0820] Step 3:

[0821] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0822] Step 4:

[0823] The generative AI model begins analyzing running data. Specifically, it analyzes trends in position, speed, and heart rate to evaluate the user's running performance. It also analyzes video data and uses a skeletal detection algorithm to extract form features.

[0824] Step 5:

[0825] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state, and if audio data is available, it can also be used in the analysis to more accurately determine emotions.

[0826] Step 6:

[0827] A generative AI model analyzes running data and generates training optimization advice, such as suggesting a specific timetable for interval training and an appropriate running pace.

[0828] Step 7:

[0829] The generative AI model reflects the analysis results of the emotion engine and adjusts the content and expression of the advice. For example, if the user is feeling fatigued or stressed, it may suggest reducing the intensity of their training or generate advice that includes an encouraging message.

[0830] Step 8:

[0831] The generative AI model generates advice on improving form based on the analysis of video data. For example, if the swing of the right arm is unnatural, it will suggest specific practice methods to correct it.

[0832] Step 9:

[0833] The server organizes the generated optimization advice and form improvement advice, and formats the customized advice data in JSON format or other formats based on the analysis results of the emotion engine.

[0834] Step 10:

[0835] The server sends the formatted data to the device, and the device displays the received advice on the user interface within the app. The advice includes an appropriate message that takes into account the user's emotional state.

[0836] Step 11:

[0837] The user then implements the provided advice during their next running session, collects data again, and repeats the process to continually optimize their training and improve their form.

[0838] The above are the detailed processing steps in the embodiment of the present invention, which allow users to receive scientifically and individually optimized training and form improvement advice, improve running performance, prevent injuries, and receive emotional support.

[0839] Example 2

[0840] 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."

[0841] Conventional running training systems focus on analyzing users' running data and running form, but it is difficult to provide advice that takes into account the user's emotional state. Furthermore, the data compression and uploading processes are sometimes inefficient, and real-time performance and data processing accuracy need to be improved. Furthermore, video analysis for form improvement requires the use of advanced algorithms, which presents challenges.

[0842] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0843] In this invention, the server includes means for collecting running data from the user, means for compressing the collected data by the terminal and uploading it to the server, means for the server to store the uploaded data in a database, means for inputting the running data into a generative artificial intelligence model for analysis, means for an emotion engine to analyze the video data and recognize the user's emotional state, means for generating training optimization advice based on the analysis results, means for analyzing the running form video data and generating form improvement advice, and means for providing the generated advice to the user's terminal. This not only improves the user's running performance, but also makes it possible to provide personalized advice based on the user's emotional state, achieving advanced data processing and real-time performance.

[0844] "Running data" refers to data including location information, speed data, heart rate data, and running time acquired while the user is running.

[0845] A "terminal" is an electronic device used by a user, such as a smartphone or a wearable device.

[0846] A "server" is a computer system that stores data, analyzes it, and runs generative artificial intelligence models.

[0847] A "generative artificial intelligence model" is an artificial intelligence model that analyzes a user's running data and generates advice on optimizing training and improving form.

[0848] An "emotion engine" is software that analyzes video data to recognize the user's emotional state.

[0849] "Training optimization advice" refers to specific training methods and schedule suggestions provided by the generative artificial intelligence model to improve the user's running performance.

[0850] "Form improvement advice" refers to specific instructions and suggestions provided by the generative artificial intelligence model to improve a user's running form.

[0851] A "skeleton detection algorithm" is an algorithm used to detect a user's skeleton and posture in video data analysis.

[0852] "Interval training" is a training method that alternates between high-intensity running and low-intensity running.

[0853] "Pace adjustment" refers to speed management that allows for effective training by appropriately controlling the user's running speed.

[0854] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. In addition, by combining this with an emotion engine that recognizes the user's emotions, it provides more personalized advice. This system aims to improve the user's running performance, prevent injuries, and increase the user's motivation.

[0855] Data collection

[0856] A user launches the smartphone app and starts a running session. The device acquires location information using the smartphone's GPS module, receives heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to start recording a video of the user's running form and also records facial expression data for the emotion engine.

[0857] Data upload

[0858] After finishing a running session, the user presses the "Stop" button on the smartphone app, which causes the device to compress all running data (location information, speed data, heart rate data, running time) and video data and upload them to the server.

[0859] Data analysis

[0860] The server receives the uploaded data and stores it in a database, after which the server inputs the data into a generative artificial intelligence model and begins analysis.

[0861] Emotion analysis

[0862] The emotion engine analyzes the video data to recognize the user's emotional state from their facial expressions, and also uses audio data, if available.

[0863] Running data analysis

[0864] A generative AI model analyzes running data, specifically trends in location, speed, and heart rate data, to assess a user's running performance.

[0865] Optimization Advice Generation

[0866] A generative AI model generates training optimization advice based on the analysis of running data. For example, it suggests a specific interval training schedule and an appropriate running pace. Furthermore, the content and wording of the advice can be adjusted based on the user's emotional state. For example, if the user is feeling fatigued or stressed, it can use a gentle tone of voice to motivate them or suggest taking a break.

[0867] Generate form improvement advice

[0868] The generative AI model generates advice to improve form based on the analysis of video data. For example, if the swing of the right arm is unnatural, the system will instruct the user to swing both arms with the same amplitude to correct this. Furthermore, the system takes the user's emotions into consideration and provides encouraging advice.

[0869] Providing Feedback

[0870] The server organizes the generated optimization advice and form improvement advice, formats the data taking into account the results of sentiment analysis, and sends the formatted data to the device, which then displays the advice received on the device in the app's user interface.

[0871] Specific examples

[0872] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate data, and the camera captures the user's running form and facial expressions. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Video data analysis also provides specific advice on improving the swing of the right arm. An emotion engine analyzes the user's facial expression data and, if the user feels fatigued or stressed, provides advice that takes rest into consideration. The device displays this advice to the user, who then puts it into practice in their next running session.

[0873] Examples of prompts:

[0874] Analyze the user's running performance based on the following data and generate optimal training advice and form improvement advice.

[0875] Data: location information, speed data, heart rate data, running time, running form video, user facial expression data

[0876] User's emotional state: Fatigue

[0877] In this way, the system of the present invention provides users with individually optimized training and advice on improving their form, improving their running performance and preventing injuries, and also provides support to improve motivation by taking into account their emotional state.

[0878] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0879] Step 1:

[0880] The user starts the smartphone app and presses the "Start" button to begin a running session. The device acquires location information using the smartphone's GPS module, receives heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to begin recording video of the user's running form and records facial expression data for the emotion engine. By collecting these input data (location information, speed data, heart rate data, and video data), real-time data collection is performed from the start of the run.

[0881] Step 2:

[0882] The device obtains location information every second from the GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The camera continuously records the user's running form and facial expressions. This allows input data (location information, heart rate data, speed data, and video data) to be continuously accumulated. The collected data is stored in the internal memory and prepared for further processing.

[0883] Step 3:

[0884] When the running session is over, the user presses the "Stop" button on the smartphone app. This action causes the device to stop collecting data from the sensors and end the camera recording. This finalizes all data collected during the session (location, speed, heart rate, and video data) and prepares it for the next upload step.

[0885] Step 4:

[0886] All data collected by the device (location, speed, heart rate, and video data) is compressed into a single file. This compressed file becomes the input data for the next step. Compression improves data transmission efficiency, saving time and bandwidth for transfer.

[0887] Step 5:

[0888] The device uploads the compressed file to a server via the internet, sending the data collected and compressed so far to the server, where it is stored in a database and prepared for the next analysis step.

[0889] Step 6:

[0890] The server receives the compressed file and stores it in a database. It checks the data integrity and decompresses it if necessary. The decompressed data (location information, speed data, heart rate data, video data) is used for further analysis.

[0891] Step 7:

[0892] The server extracts the necessary data from the database and inputs it into the generative AI model. Based on this input data, the generative AI model begins analyzing the data. For example, it analyzes changes in location data and speed trends to evaluate the user's performance.

[0893] Step 8:

[0894] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state. If audio data is available, it is also used for analysis. The results of this analysis are classified into emotion categories (positive, negative, or neutral).

[0895] Step 9:

[0896] A generative AI model analyzes running data and evaluates trends in position, speed, and heart rate. Based on this, it quantitatively evaluates the user's running performance. This evaluation results form the basis for advice generated in the next step.

[0897] Step 10:

[0898] Based on the analysis results, the generative AI model generates training optimization advice. For example, it suggests the next interval training schedule or an appropriate running pace. It also adjusts the content and wording of advice based on the emotion analysis results. For example, if the emotional state indicates fatigue or stress, it may suggest a gentler tone of voice or rest to increase motivation.

[0899] Step 11:

[0900] The generative AI model generates advice on improving form based on the analysis of video data. For example, if the swing of the right arm is unnatural, it will suggest ways to correct it. It also takes into account the player's emotional state and provides encouraging advice.

[0901] Step 12:

[0902] The server organizes the generated optimization advice and form improvement advice, formats the data taking into account the results of sentiment analysis, and sends the formatted data in JSON format or other formats to the device.

[0903] Step 13:

[0904] The device analyzes the received feedback and displays it on the smartphone app's user interface, allowing users to review training optimization and form improvement advice and put it into practice during their next running session.

[0905] (Application example 2)

[0906] 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."

[0907] In modern factories, improving the efficiency and accuracy of robot operations is important. However, current systems are unable to provide optimization advice that takes into account operation data and the emotional state of workers, resulting in reduced work efficiency and increased worker stress. The present invention aims to solve these problems by optimizing the operation of factory robots, improving work efficiency, and providing personalized advice that takes into account the emotional state of workers.

[0908] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting running data from the user, means for inputting the running data into a generative AI model and analyzing it, means for generating training optimization advice based on the analysis results, means for analyzing video data of the running form and generating form improvement advice, means for providing the generated advice to the user's terminal, means for recognizing an emotional state from the video data using an emotion engine, and means for adjusting the content of the advice based on the recognized emotional state. This improves the operating efficiency of factory robots, reduces worker stress, and makes it possible to provide optimized work advice.

[0909] "User" refers to an individual or operator who uses this system.

[0910] "Running data" refers to data related to a user's exercise, such as location information, speed, heart rate, and time.

[0911] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that analyzes collected data and generates optimization and improvement advice.

[0912] "Video data" refers to video data captured using a camera or other imaging device.

[0913] "Emotion engine" refers to an engine that analyzes video and audio data to recognize and evaluate the user's emotional state.

[0914] "Advice" refers to instructions or suggestions generated based on the analysis results.

[0915] "Terminal" refers to a device, such as a smartphone or computer, that a user uses to operate this system.

[0916] A "skeleton detection algorithm" refers to an algorithm that detects human skeletons from video data and analyzes their movements.

[0917] "Interval training" refers to a training technique that alternates between high-intensity and low-intensity exercise.

[0918] "Pacing" refers to adjusting the speed and rhythm of your running or work.

[0919] This invention is a system that collects user motion data and analyzes it using a generative artificial intelligence model to provide training optimization advice and motion improvement advice. Furthermore, by combining it with an emotion engine, it is possible to provide personalized advice that takes into account the user's emotional state.

[0920] Data collection

[0921] The user starts the device and begins a movement session. The device acquires location information using the GPS module, speed data from the speedometer, and heart rate data from the heart rate sensor. It then activates the camera to begin video recording of the user's movements, which also records facial expression data. This allows the device to collect a variety of movement data from different angles.

[0922] Data upload

[0923] When the movement session is over, the user presses the "stop" button on the device, which causes the device to compress all collected data (location, speed, heart rate, time, and video data) and upload it to a server, where it is centrally aggregated and available for analysis.

[0924] Data and Sentiment Analysis

[0925] The server receives the uploaded data and stores it in a database. The server analyzes the data using a generative artificial intelligence model to evaluate the user's performance. It also uses an emotion engine to analyze the user's emotional state from video data. The emotion engine analyzes facial expression and voice data to recognize the user's emotional state. This analysis makes it possible to grasp in detail the state in which the user was operating.

[0926] Advice Generation

[0927] The generative AI model generates training optimization advice based on the analysis of movement data. For example, it suggests a specific schedule and appropriate speed for interval training. It also generates movement improvement advice based on analysis of video data. For example, it suggests ways to make the right arm move more smoothly. It also adjusts the content and expression of the advice based on the user's emotional state. If the user is feeling tired or stressed, it suggests gentle tone of voice to motivate them or suggests taking a rest.

[0928] Providing Feedback

[0929] The server organizes the generated optimization advice and behavior improvement advice, takes into account the results of sentiment analysis, and formats the data in JSON format or other formats. The formatted data is then sent to the device, which then displays the received advice on the app's user interface.

[0930] As a concrete example, when a user operates a robot in a factory, once the user's daily work exceeds a certain volume, the device records location information, speed, and heart rate data, and a video camera captures the user's movements and facial expressions. After the work is completed, the device uploads the data to a server, which analyzes it using a generative artificial intelligence model. Based on the next work schedule, the device proposes a new interval training schedule and appropriate movement timing, and provides detailed advice on how to smooth the movement of the right arm. An emotion engine analyzes the user's facial expression data and simultaneously provides advice, including advice on rest, if the user feels fatigued or stressed.

[0931] Prompt Sentence Examples

[0932] "A robot is performing a machine assembly task. Please automatically capture the worker's movements, analyze their behavior and their emotional state, and provide optimization advice for the next task."

[0933] In this way, the system of the present invention provides users with individually optimized advice on improving their movements and form, thereby improving their work performance and preventing injuries, and also provides support for improving motivation by taking into account their emotional state.

[0934] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0935] Step 1: Data collection

[0936] A user starts a work session on their device. The device acquires location information using the GPS module, speed data from the speedometer, and heart rate data from the heart rate sensor. The device also activates the camera to start video recording of the work, thereby capturing facial expression data. The inputs are the user's motion data, location information, speed, heart rate, and video data, and the output is the collection of these data.

[0937] Step 2: Upload data

[0938] When the operating session is over, the user presses the "Stop" button on the device, at which point the device will batch compress all collected data and upload it to the server. The input to this process is the data collected in step 1, and the output is the compressed data uploaded to the server.

[0939] Step 3: Data Receipt and Storage

[0940] The server receives the uploaded data and stores it in a database. The input is the data uploaded in step 2, and the output is the data stored in the database. This provides the foundation for analysis.

[0941] Step 4: Data analysis

[0942] The server uses a generative artificial intelligence model to analyze the data stored in the database. Specifically, it analyzes position data, speed data, and heart rate data to evaluate the user's movement performance. The input is the movement data read from the database, and the output is the performance evaluation result.

[0943] Step 5: Sentiment Analysis

[0944] The server uses an emotion engine to analyze the user's facial expressions from the video data and recognize their emotional state. Additionally, if audio data is available, it is also used for analysis. The input is video data and audio data, and the output is the evaluation result of the emotional state.

[0945] Step 6: Generate optimization advice

[0946] The server uses a generative AI model to generate training optimization advice based on the analysis of movement data. For example, it can suggest a specific interval training schedule or an appropriate movement speed. It also flexibly adjusts the advice based on the user's emotional state. The input is the results of performance evaluation and emotional evaluation, and the output is optimization advice.

[0947] Step 7: Generate behavior improvement advice

[0948] The server generates advice for improving behavior based on the results of analyzing the video data. For example, if a user's arm movements are unnatural while operating a machine, the server will instruct the user on how to correct them. The input is the results of analyzing the video data, and the output is advice for improving behavior.

[0949] Step 8: Formatting and delivering advice

[0950] The server organizes the generated optimization advice and behavior improvement advice, formats the data (e.g., JSON format) taking into account the results of sentiment analysis, and sends it to the user's device. The device displays the received advice on the user interface within the app. The input is the generated advice and the results of sentiment analysis, and the output is the formatted advice that the user receives.

[0951] This processing step enables the system to comprehensively analyze the user's motion data and emotional state, and provide individually optimized training and motion improvement advice.

[0952] 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.

[0953] 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.

[0954] 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.

[0955] [Fourth embodiment]

[0956] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0957] 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.

[0958] 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).

[0959] 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.

[0960] 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.

[0961] 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).

[0962] 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.

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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."

[0969] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. The system aims to improve the user's running performance and prevent injuries.

[0970] Data collection

[0971] The user launches the smartphone app and starts a running session. The device collects real-time data using the smartphone's GPS, heart rate sensor, and speedometer. In addition, the device records video data of the user's running form using the smartphone's camera.

[0972] Data upload

[0973] After completing a running session, the user presses the "stop" button on the smartphone app, and all data collected by the device is uploaded to a server, where it is compressed and transmitted using a secure protocol.

[0974] Data analysis

[0975] The server receives the uploaded data and inputs it into a generative AI model. The generative AI model analyzes the running data (location, speed, heart rate, and time) to evaluate the user's training performance. At the same time, the generative AI model analyzes the video data and evaluates running form using a skeletal detection algorithm.

[0976] Optimization Advice Generation

[0977] The generative AI model generates a training plan tailored to the user based on the analysis of running data. Specifically, it suggests interval training days and running pace adjustments. For example, it calculates the running speed needed to maintain a certain heart rate based on the user's heart rate and speed data.

[0978] Generate form improvement advice

[0979] The generative AI model evaluates running form based on video data and suggests specific improvements. For example, if the swing angle of the right arm is unnatural, the system will provide advice on how to swing both arms with the same amplitude to correct this.

[0980] Providing Feedback

[0981] The server organizes the generated optimization advice and form improvement advice and sends it to the device in JSON format, etc. The device displays the advice to the user and encourages them to put it into practice in their next running session.

[0982] Specific examples

[0983] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate, and the camera captures the user's running form. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Furthermore, analysis of the video data provides specific advice on improving the swing of the right arm. The device displays this advice to the user, who then puts it into practice during their next running session.

[0984] In this way, the system of the present invention can provide users with individually optimized training and form improvement advice, thereby improving running performance and preventing injuries.

[0985] The processing flow will be explained below.

[0986] Step 1:

[0987] A user launches the smartphone app and starts a running session. The device acquires location information from the smartphone's GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The device also activates the camera and starts recording a video of the user's running form.

[0988] Step 2:

[0989] After finishing a running session, the user presses the "Stop" button on the smartphone app. The device then compresses all running data (location, speed, heart rate, time) and video data and uploads them to the server.

[0990] Step 3:

[0991] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[0992] Step 4:

[0993] The generative AI model begins analyzing running data, specifically location, speed, and heart rate trends, to assess the user's running performance.

[0994] Step 5:

[0995] At the same time, a generative AI model analyzes the video data, analyzing the video frames and using a skeletal detection algorithm to extract the characteristics of the user's running form.

[0996] Step 6:

[0997] A generative AI model analyzes running data and generates training optimization advice, such as suggesting a specific interval training schedule and an appropriate running pace.

[0998] Step 7:

[0999] The generative AI model analyzes the video data and generates advice to improve form. For example, if the right arm swing is unnatural, the system will advise the player to swing both arms with the same amplitude.

[1000] Step 8:

[1001] The server organizes the generated optimization advice and form improvement advice and formats the data in JSON format, for example.

[1002] Step 9:

[1003] The server sends the formatted data to the device, and the device displays the received advice on the app's user interface.

[1004] Step 10:

[1005] The user then implements the provided advice during their next running session, collects data again, and repeats the process to continually optimize their training and improve their form.

[1006] Example 1

[1007] 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."

[1008] In modern society, improving athletic performance and preventing injuries are important challenges for many people. However, there are limited means for easily obtaining appropriate training and form improvement advice based on individual users' exercise and posture data. The present invention aims to solve these challenges by providing a system that allows users to easily obtain optimized training advice and form improvement advice.

[1009] 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.

[1010] In this invention, the server includes means for collecting exercise data from a user, means for collecting video data capturing posture during exercise, means for inputting the collected exercise data and video data into a generative artificial intelligence model for analysis, means for generating training optimization advice based on the analysis results, means for analyzing the video data and generating posture improvement advice, and means for providing the generated advice to the user's mobile device. This allows users to easily obtain individually optimized training and form improvement advice, enabling them to improve their exercise performance and prevent injuries.

[1011] "Exercise data" refers to data such as location information, speed, and heart rate acquired while the user is exercising.

[1012] "Video data" refers to video data captured while the user is exercising.

[1013] A "generative artificial intelligence model" is an artificial intelligence system that analyzes collected exercise data and video data and generates advice on training and form improvement.

[1014] The "skeleton detection algorithm" is an algorithm for detecting the user's skeletal position from video data.

[1015] "Training optimization advice" is advice on training methods and exercise schedules that is generated based on the user's exercise data.

[1016] "Form improvement advice" is advice that evaluates the user's exercise form based on video data and points out areas for improvement.

[1017] A "mobile terminal" is an electronic device that can be carried by a user, and primarily refers to a smartphone, but may also include other similar devices.

[1018] This invention is a system that collects a user's exercise data and video data of their exercise form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. The system aims to improve the user's exercise performance and prevent injuries.

[1019] Data collection

[1020] The user launches the smartphone app and begins an exercise session. The device collects data in real time using the smartphone's GPS, heart rate sensor, and speedometer. At the same time, the device uses the smartphone's camera to record video data of the exercise form. Specifically, the device records location information every second and collects heart rate and speed data.

[1021] Data upload

[1022] After the exercise session is over, the user presses the "Stop" button on the smartphone app, and the device compresses all collected data (location, heart rate, speed, and video data). The device compresses the data and sends it to a server using a secure protocol (e.g., HTTPS).

[1023] Data analysis

[1024] The server receives the uploaded data and inputs it into a generative AI model. The generative AI model analyzes the exercise data (position, speed, heart rate, and time) to evaluate the user's training performance. At the same time, it analyzes the video data and evaluates the exercise form using a skeletal detection algorithm. Specifically, the generative AI model extracts the position of the skeleton for each video frame and checks the consistency of the form.

[1025] Optimization Advice Generation

[1026] A generative AI model generates a training plan tailored to the user based on the analysis of the exercise data. For example, it calculates the running pace required to maintain a certain heart rate based on the user's heart rate and speed data. As a specific example, it suggests, "For your next workout, do interval training, covering a distance of 1 kilometer, at a speed of 10 kilometers per hour."

[1027] Generate form improvement advice

[1028] The generative AI model evaluates the exercise form based on the video data and suggests specific improvements. For example, if the swing angle of the right arm is unnatural, the model may suggest that the left and right arms should be swung with the same swing width.

[1029] Providing Feedback

[1030] The server organizes the generated optimization advice and form improvement advice and sends it to the device in a data format such as JSON. The device then displays this advice in an easy-to-read format to the user, encouraging them to put it into practice in their next exercise session. For example, it might suggest specific actions, such as, "Try the following advice during your next workout: 1. Set your speed to 9 kilometers per hour to maintain a stable heart rate. 2. Be conscious of swinging both arms evenly to improve your right arm swing."

[1031] In this way, the system of the present invention can provide users with individually optimized training and form improvement advice, thereby improving athletic performance and preventing injuries.

[1032] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1033] Step 1:

[1034] The user launches the smartphone app and performs an input operation to start a running session. This operation causes the device to detect that the app has been launched and activate the necessary sensors (GPS, heart rate sensor, speedometer). Specifically, the device checks the operation of the sensors and begins initial data collection.

[1035] Step 2:

[1036] The device uses the smartphone's GPS to obtain location information every second. It obtains heart rate data from the heart rate sensor and speed data in real time from the speedometer. At the same time, it records video data of the running form using the smartphone's camera. The input data includes location information, heart rate, speed, and video data, which are temporarily stored in the device's storage.

[1037] Step 3:

[1038] After completing a running session, the user presses the "Stop" button on the smartphone app. This action causes the device to compress all collected data. Specifically, the collected location information, heart rate, speed, and video data are combined into a single file using a compression algorithm. The compressed data is then output.

[1039] Step 4:

[1040] The device sends the compressed data to the server using a secure protocol (e.g. HTTPS). The input is the compressed file, which the device sends over a network connection. If successful, the device prints a message confirming that the data was sent.

[1041] Step 5:

[1042] The server receives the compressed file and decompresses it. The decompressed data (location, heart rate, speed, video data) is input into the generative AI model. Based on the input data, the generative AI model first analyzes the running data (location, speed, heart rate, time).

[1043] Step 6:

[1044] The generative AI model outputs the results of analyzing the running data, then analyzes the video data and evaluates running form using a skeletal detection algorithm. The video data is analyzed as input data, and the analysis results output the consistency of form and areas for improvement.

[1045] Step 7:

[1046] Based on the results of each data analysis, the generative AI model generates an optimal training plan and advice for improving form for the user. Specifically, it outputs interval training schedule suggestions, running speed suggestions, and specific instructions for improving form.

[1047] Step 8:

[1048] The server organizes the generated optimization advice and form improvement advice and sends it to the terminal in JSON or other appropriate data format. The input data is the generated advice, and the output is a submission confirmation message.

[1049] Step 9:

[1050] The device displays the received advice to the user in an easy-to-read format. Specifically, it presents the training plan displayed in the app and specific advice on form improvement, encouraging the user to implement it in their next running session. The output of this step is feedback that the user has acknowledged the advice.

[1051] (Application example 1)

[1052] 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."

[1053] In the modern food delivery industry, there is a need to simultaneously optimize the delivery efficiency and health of delivery workers. However, current systems lack the means to monitor not only delivery workers' location and speed, but also their physical movements and health status in real time, and provide specific efficiency and health advice. This often leads to fatigue and health problems among delivery workers, hindering efficient delivery.

[1054] 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.

[1055] In this invention, the server includes means for collecting movement data from users, means for inputting the movement data into a generative AI model and analyzing it, means for generating efficiency advice based on the analysis results, means for analyzing video data of movement form and generating form improvement advice, and means for providing the generated advice to the user's information terminal, thereby enabling delivery personnel to optimize their delivery routes, improve their physical movements, and maintain their health.

[1056] "Movement data" refers to data such as the user's location, speed, and heart rate, and records the user's movement status in real time.

[1057] A "generative artificial intelligence model" is an artificial intelligence system that learns patterns and trends based on collected data and generates analytical results.

[1058] "Efficiency advice" refers to specific suggestions and guidelines for improving work efficiency based on the results of analyzing the user's movement data.

[1059] "Movement form" refers to the body movements and postures that a user performs while moving, and is evaluated in particular for their appropriateness and efficiency.

[1060] "Video data" refers to footage of a user's motion form, and is used for analysis.

[1061] A "body feature detection algorithm" is a program that identifies the position of a user's bones and joints from video data and analyzes their movements.

[1062] An "information terminal" is an electronic device used to input and display data, such as a smartphone or tablet that a user has.

[1063] This invention is a system for simultaneously optimizing the delivery efficiency and health of delivery workers in the food delivery industry. This system collects video data of users' movements and motion forms, and analyzes them using a generative artificial intelligence model to provide specific and individualized advice on efficiency and form improvement. This system is realized using the following main hardware and software:

[1064] Hardware

[1065] 1. Information terminal: Electronic devices held by users, such as smartphones and tablets

[1066] 2. Sensor:

[1067] GPS: Get the user's location in real time

[1068] Heart rate sensor: Measures the user's heart rate

[1069] Speedometer: Measure your speed

[1070] 3. Camera: Records the user's movements as video

[1071] software

[1072] 1. Generative AI model: An AI model for analyzing collected movement data and video data

[1073] 2. Body feature detection algorithm: A program that detects the position of the user's bones and joints from video data and analyzes their movements.

[1074] Data processing and calculation

[1075] Data collection

[1076] The user launches the smartphone app and starts a delivery session. The smartphone uses GPS, a heart rate sensor, and a speedometer to obtain the user's location, heart rate, and speed in real time. The smartphone also uses a camera to record the user's movement form.

[1077] Data upload

[1078] After the delivery session is over, when the user hits the "Stop" button in the app, all collected data is uploaded to the server, compressed and transmitted using a secure protocol.

[1079] Data analysis

[1080] The server receives the uploaded data and analyzes it using a generative AI model. This AI model analyzes movement data (location, speed, heart rate, time) to evaluate the efficiency of the delivery route and the user's physical fitness. It also analyzes video data and evaluates movement form using a body feature detection algorithm.

[1081] Advice Generation

[1082] Based on the results of data analysis, a generative AI model generates efficiency advice and advice on improving the user's behavior, such as providing specific advice on optimizing delivery routes and improving carrying methods.

[1083] Providing Feedback

[1084] The server organizes the generated advice and sends it to the information terminal in JSON format, etc. The information terminal displays the advice to the user and encourages them to put it into practice in the next delivery session.

[1085] Specific examples

[1086] The user initiates a delivery session and performs multiple deliveries. The smartphone records location, speed, and heart rate, and the camera captures the user's movement form. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests route optimization for the next delivery and advice on how to hold the device to prevent fatigue. The device displays this advice to the user, who then puts it into practice during their next delivery session.

[1087] Prompt Sentence Examples

[1088] "Analyze data from delivery sessions to optimize routes and maintain health. Provide optimal recommendations based on the driver's GPS, speed, heart rate, and movement video."

[1089] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1090] Step 1:

[1091] A user launches the smartphone app and begins a delivery session. As input, the user activates the GPS, heart rate, speedometer, and camera. The output is real-time location, heart rate, speed, and video data captured by the smartphone. This data is stored locally during the session.

[1092] Step 2:

[1093] During the session, the device collects real-time location, speed, and heart rate data. The camera records the user's movements. The inputs are data obtained from various sensors and camera footage. The output is the collected data and a video file.

[1094] Step 3:

[1095] After the delivery session ends, the user presses the "Stop" button in the app. The device then compresses all collected data and uploads it to the server using a secure protocol (e.g., HTTPS). The inputs are the collected data and the video file. The outputs are the data sent to the server and the video file.

[1096] Step 4:

[1097] The server receives the uploaded data and prepares it for analysis. The inputs are location, speed, heart rate, and video data sent from the device. The output is data converted into an analyzable format.

[1098] Step 5:

[1099] The server analyzes the data using a generative AI model. Inputs include location information, speed, heart rate data, and video data. The generative AI model analyzes the movement data to evaluate the efficiency of the delivery route and the user's physical fitness, and analyzes the video data to evaluate the user's movement form. The output is the analysis of the movement data and advice on improving form.

[1100] Step 6:

[1101] The generative AI model generates efficiency advice and advice on improving movement form based on the analysis results. The inputs are the analysis results of movement data and video data. The output is efficiency advice and advice on improving movement form that are appropriate for the user.

[1102] Step 7:

[1103] The server organizes the generated advice in JSON format or similar and sends it to the terminal. The input is the generated advice. The output is advice organized in JSON format.

[1104] Step 8:

[1105] The device receives advice from the server and displays it to the user. The input is advice sent from the server. The output is efficiency advice and form improvement advice displayed on the smartphone screen. The user can put these advices into practice in the next delivery session.

[1106] 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.

[1107] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. In addition, by combining this with an emotion engine that recognizes the user's emotions, it provides more personalized advice. This system aims to improve the user's running performance, prevent injuries, and increase the user's motivation.

[1108] Data collection

[1109] A user launches the smartphone app and starts a running session. The device obtains location information from the smartphone's GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The device also activates the camera to start recording a video of the user's running form and records facial expression data for the emotion engine.

[1110] Data upload

[1111] After finishing a running session, the user presses the "Stop" button on the smartphone app. The device then compresses all running data (location, speed, heart rate, time) and video data and uploads them to the server.

[1112] Data analysis

[1113] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[1114] Emotion analysis

[1115] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state, and also uses audio data, if available, for analysis.

[1116] Running data analysis

[1117] The generative AI model begins analyzing running data, specifically location, speed, and heart rate trends, to assess the user's running performance.

[1118] Optimization Advice Generation

[1119] A generative AI model generates training optimization advice based on the analysis of running data. For example, it suggests a specific interval training schedule and an appropriate running pace. Furthermore, it adjusts the content and wording of the advice based on the user's emotional state. For example, if the user is feeling fatigued or stressed, it will use a gentle tone of voice to motivate them and suggest taking a break.

[1120] Generate form improvement advice

[1121] The generative AI model generates advice to improve form based on the analysis of video data. For example, if the swing of the right arm is unnatural, the system will instruct the user to swing both arms with the same amplitude to correct this. Furthermore, the system takes the user's emotions into consideration and provides advice with encouraging words.

[1122] Providing Feedback

[1123] The server organizes the generated optimization advice and form improvement advice, takes into account the results of sentiment analysis, and formats the data in JSON format or other formats. The server then sends the formatted data to the device. The advice received by the device is then displayed in the app's user interface.

[1124] Specific examples

[1125] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate data, and the camera captures the user's running form and facial expressions. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Analysis of the video data also provides specific advice on improving the swing of the right arm. An emotion engine analyzes the user's facial expression data and, if the user feels fatigued or stressed, provides advice that takes rest into consideration. The device displays this advice to the user, who then puts it into practice during their next running session.

[1126] In this way, the system of the present invention provides users with individually optimized training and form improvement advice, improving running performance and preventing injuries, and also provides support to improve motivation by taking into account their emotional state.

[1127] The processing flow will be explained below.

[1128] Step 1:

[1129] The user launches the smartphone app and starts a running session. The device acquires location information from the smartphone's GPS module, receives real-time heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to capture the user's running form and facial expression.

[1130] Step 2:

[1131] After the device finishes running, the user presses the "Stop" button. The device compresses the location, speed, heart rate, and video data it has acquired, and uploads the data to a server using a secure protocol.

[1132] Step 3:

[1133] The server receives the uploaded data, stores it in a database, and inputs it into the generative AI model.

[1134] Step 4:

[1135] The generative AI model begins analyzing running data. Specifically, it analyzes trends in position, speed, and heart rate to evaluate the user's running performance. It also analyzes video data and uses a skeletal detection algorithm to extract form features.

[1136] Step 5:

[1137] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state, and if audio data is available, it can also be used in the analysis to more accurately determine emotions.

[1138] Step 6:

[1139] A generative AI model analyzes running data and generates training optimization advice, such as suggesting a specific timetable for interval training and an appropriate running pace.

[1140] Step 7:

[1141] The generative AI model reflects the analysis results of the emotion engine and adjusts the content and expression of the advice. For example, if the user is feeling fatigued or stressed, it may suggest reducing the intensity of their training or generate advice that includes an encouraging message.

[1142] Step 8:

[1143] The generative AI model generates advice on improving form based on the analysis of video data. For example, if the swing of the right arm is unnatural, it will suggest specific practice methods to correct it.

[1144] Step 9:

[1145] The server organizes the generated optimization advice and form improvement advice, and formats the customized advice data in JSON format or other formats based on the analysis results of the emotion engine.

[1146] Step 10:

[1147] The server sends the formatted data to the device, and the device displays the received advice on the user interface within the app. The advice includes an appropriate message that takes into account the user's emotional state.

[1148] Step 11:

[1149] The user then implements the provided advice during their next running session, collects data again, and repeats the process to continually optimize their training and improve their form.

[1150] The above are the detailed processing steps in the embodiment of the present invention, which allow users to receive scientifically and individually optimized training and form improvement advice, improve running performance, prevent injuries, and receive emotional support.

[1151] Example 2

[1152] 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."

[1153] Conventional running training systems focus on analyzing users' running data and running form, but it is difficult to provide advice that takes into account the user's emotional state. Furthermore, the data compression and uploading processes are sometimes inefficient, and real-time performance and data processing accuracy need to be improved. Furthermore, video analysis for form improvement requires the use of advanced algorithms, which presents challenges.

[1154] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1155] In this invention, the server includes means for collecting running data from the user, means for compressing the collected data by the terminal and uploading it to the server, means for the server to store the uploaded data in a database, means for inputting the running data into a generative artificial intelligence model for analysis, means for an emotion engine to analyze the video data and recognize the user's emotional state, means for generating training optimization advice based on the analysis results, means for analyzing the running form video data and generating form improvement advice, and means for providing the generated advice to the user's terminal. This not only improves the user's running performance, but also makes it possible to provide personalized advice based on the user's emotional state, achieving advanced data processing and real-time performance.

[1156] "Running data" refers to data including location information, speed data, heart rate data, and running time acquired while the user is running.

[1157] A "terminal" is an electronic device used by a user, such as a smartphone or a wearable device.

[1158] A "server" is a computer system that stores data, analyzes it, and runs generative artificial intelligence models.

[1159] A "generative artificial intelligence model" is an artificial intelligence model that analyzes a user's running data and generates advice on optimizing training and improving form.

[1160] An "emotion engine" is software that analyzes video data to recognize the user's emotional state.

[1161] "Training optimization advice" refers to specific training methods and schedule suggestions provided by the generative artificial intelligence model to improve the user's running performance.

[1162] "Form improvement advice" refers to specific instructions and suggestions provided by the generative artificial intelligence model to improve a user's running form.

[1163] A "skeleton detection algorithm" is an algorithm used to detect a user's skeleton and posture in video data analysis.

[1164] "Interval training" is a training method that alternates between high-intensity running and low-intensity running.

[1165] "Pace adjustment" refers to speed management that allows for effective training by appropriately controlling the user's running speed.

[1166] This invention is a system that collects a user's running data and video data of their running form, analyzes them using a generative artificial intelligence model, and provides advice on optimizing training and improving form. In addition, by combining this with an emotion engine that recognizes the user's emotions, it provides more personalized advice. This system aims to improve the user's running performance, prevent injuries, and increase the user's motivation.

[1167] Data collection

[1168] A user launches the smartphone app and starts a running session. The device acquires location information using the smartphone's GPS module, receives heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to start recording a video of the user's running form and also records facial expression data for the emotion engine.

[1169] Data upload

[1170] After finishing a running session, the user presses the "Stop" button on the smartphone app, which causes the device to compress all running data (location information, speed data, heart rate data, running time) and video data and upload them to the server.

[1171] Data analysis

[1172] The server receives the uploaded data and stores it in a database, after which the server inputs the data into a generative artificial intelligence model and begins analysis.

[1173] Emotion analysis

[1174] The emotion engine analyzes the video data to recognize the user's emotional state from their facial expressions, and also uses audio data, if available.

[1175] Running data analysis

[1176] A generative AI model analyzes running data, specifically trends in location, speed, and heart rate data, to assess a user's running performance.

[1177] Optimization Advice Generation

[1178] A generative AI model generates training optimization advice based on the analysis of running data. For example, it suggests a specific interval training schedule and an appropriate running pace. Furthermore, the content and wording of the advice can be adjusted based on the user's emotional state. For example, if the user is feeling fatigued or stressed, it can use a gentle tone of voice to motivate them or suggest taking a break.

[1179] Generate form improvement advice

[1180] The generative AI model generates advice to improve form based on the analysis of video data. For example, if the swing of the right arm is unnatural, the system will instruct the user to swing both arms with the same amplitude to correct this. Furthermore, the system takes the user's emotions into consideration and provides encouraging advice.

[1181] Providing Feedback

[1182] The server organizes the generated optimization advice and form improvement advice, formats the data taking into account the results of sentiment analysis, and sends the formatted data to the device, which then displays the advice received on the device in the app's user interface.

[1183] Specific examples

[1184] The user starts a running session and runs 5 kilometers. The smartphone records location, speed, and heart rate data, and the camera captures the user's running form and facial expressions. After the session ends, the device uploads all data to a server. A generative AI model analyzes the data and suggests interval training for the next workout. Video data analysis also provides specific advice on improving the swing of the right arm. An emotion engine analyzes the user's facial expression data and, if the user feels fatigued or stressed, provides advice that takes rest into consideration. The device displays this advice to the user, who then puts it into practice in their next running session.

[1185] Examples of prompts:

[1186] Analyze the user's running performance based on the following data and generate optimal training advice and form improvement advice.

[1187] Data: location information, speed data, heart rate data, running time, running form video, user facial expression data

[1188] User's emotional state: Fatigue

[1189] In this way, the system of the present invention provides users with individually optimized training and advice on improving their form, improving their running performance and preventing injuries, and also provides support to improve motivation by taking into account their emotional state.

[1190] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1191] Step 1:

[1192] The user starts the smartphone app and presses the "Start" button to begin a running session. The device acquires location information using the smartphone's GPS module, receives heart rate data from the heart rate sensor, and acquires speed data from the speedometer. The device then activates the camera to begin recording video of the user's running form and records facial expression data for the emotion engine. By collecting these input data (location information, speed data, heart rate data, and video data), real-time data collection is performed from the start of the run.

[1193] Step 2:

[1194] The device obtains location information every second from the GPS module, receives heart rate data from the heart rate sensor, and speed data from the speedometer. The camera continuously records the user's running form and facial expressions. This allows input data (location information, heart rate data, speed data, and video data) to be continuously accumulated. The collected data is stored in the internal memory and prepared for further processing.

[1195] Step 3:

[1196] When the running session is over, the user presses the "Stop" button on the smartphone app. This action causes the device to stop collecting data from the sensors and end the camera recording. This finalizes all data collected during the session (location, speed, heart rate, and video data) and prepares it for the next upload step.

[1197] Step 4:

[1198] All data collected by the device (location, speed, heart rate, and video data) is compressed into a single file. This compressed file becomes the input data for the next step. Compression improves data transmission efficiency, saving time and bandwidth for transfer.

[1199] Step 5:

[1200] The device uploads the compressed file to a server via the internet, sending the data collected and compressed so far to the server, where it is stored in a database and prepared for the next analysis step.

[1201] Step 6:

[1202] The server receives the compressed file and stores it in a database. It checks the data integrity and decompresses it if necessary. The decompressed data (location information, speed data, heart rate data, video data) is used for further analysis.

[1203] Step 7:

[1204] The server extracts the necessary data from the database and inputs it into the generative AI model. Based on this input data, the generative AI model begins analyzing the data. For example, it analyzes changes in location data and speed trends to evaluate the user's performance.

[1205] Step 8:

[1206] The emotion engine analyzes the user's facial expressions from video data to recognize their emotional state. If audio data is available, it is also used for analysis. The results of this analysis are classified into emotion categories (positive, negative, or neutral).

[1207] Step 9:

[1208] A generative AI model analyzes running data and evaluates trends in position, speed, and heart rate. Based on this, it quantitatively evaluates the user's running performance. This evaluation results form the basis for advice generated in the next step.

[1209] Step 10:

[1210] Based on the analysis results, the generative AI model generates training optimization advice. For example, it suggests the next interval training schedule or an appropriate running pace. It also adjusts the content and wording of advice based on the emotion analysis results. For example, if the emotional state indicates fatigue or stress, it may suggest a gentler tone of voice or rest to increase motivation.

[1211] Step 11:

[1212] The generative AI model generates advice on improving form based on the analysis of video data. For example, if the swing of the right arm is unnatural, it will suggest ways to correct it. It also takes into account the player's emotional state and provides encouraging advice.

[1213] Step 12:

[1214] The server organizes the generated optimization advice and form improvement advice, formats the data taking into account the results of sentiment analysis, and sends the formatted data in JSON format or other formats to the device.

[1215] Step 13:

[1216] The device analyzes the received feedback and displays it on the smartphone app's user interface, allowing users to review training optimization and form improvement advice and put it into practice during their next running session.

[1217] (Application example 2)

[1218] 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."

[1219] In modern factories, improving the efficiency and accuracy of robot operations is important. However, current systems are unable to provide optimization advice that takes into account operation data and the emotional state of workers, resulting in reduced work efficiency and increased worker stress. The present invention aims to solve these problems by optimizing the operation of factory robots, improving work efficiency, and providing personalized advice that takes into account the emotional state of workers.

[1220] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting running data from the user, means for inputting the running data into a generative AI model and analyzing it, means for generating training optimization advice based on the analysis results, means for analyzing video data of the running form and generating form improvement advice, means for providing the generated advice to the user's terminal, means for recognizing an emotional state from the video data using an emotion engine, and means for adjusting the content of the advice based on the recognized emotional state. This improves the operating efficiency of factory robots, reduces worker stress, and makes it possible to provide optimized work advice.

[1221] "User" refers to an individual or operator who uses this system.

[1222] "Running data" refers to data related to a user's exercise, such as location information, speed, heart rate, and time.

[1223] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that analyzes collected data and generates optimization and improvement advice.

[1224] "Video data" refers to video data captured using a camera or other imaging device.

[1225] "Emotion engine" refers to an engine that analyzes video and audio data to recognize and evaluate the user's emotional state.

[1226] "Advice" refers to instructions or suggestions generated based on the analysis results.

[1227] "Terminal" refers to a device, such as a smartphone or computer, that a user uses to operate this system.

[1228] A "skeleton detection algorithm" refers to an algorithm that detects human skeletons from video data and analyzes their movements.

[1229] "Interval training" refers to a training technique that alternates between high-intensity and low-intensity exercise.

[1230] "Pacing" refers to adjusting the speed and rhythm of your running or work.

[1231] This invention is a system that collects user motion data and analyzes it using a generative artificial intelligence model to provide training optimization advice and motion improvement advice. Furthermore, by combining it with an emotion engine, it is possible to provide personalized advice that takes into account the user's emotional state.

[1232] Data collection

[1233] The user starts the device and begins a movement session. The device acquires location information using the GPS module, speed data from the speedometer, and heart rate data from the heart rate sensor. It then activates the camera to begin video recording of the user's movements, which also records facial expression data. This allows the device to collect a variety of movement data from different angles.

[1234] Data upload

[1235] When the movement session is over, the user presses the "stop" button on the device, which causes the device to compress all collected data (location, speed, heart rate, time, and video data) and upload it to a server, where it is centrally aggregated and available for analysis.

[1236] Data and Sentiment Analysis

[1237] The server receives the uploaded data and stores it in a database. The server analyzes the data using a generative artificial intelligence model to evaluate the user's performance. It also uses an emotion engine to analyze the user's emotional state from video data. The emotion engine analyzes facial expression and voice data to recognize the user's emotional state. This analysis makes it possible to grasp in detail the state in which the user was operating.

[1238] Advice Generation

[1239] The generative AI model generates training optimization advice based on the analysis of movement data. For example, it suggests a specific schedule and appropriate speed for interval training. It also generates movement improvement advice based on analysis of video data. For example, it suggests ways to make the right arm move more smoothly. It also adjusts the content and expression of the advice based on the user's emotional state. If the user is feeling tired or stressed, it suggests gentle tone of voice to motivate them or suggests taking a rest.

[1240] Providing Feedback

[1241] The server organizes the generated optimization advice and behavior improvement advice, takes into account the results of sentiment analysis, and formats the data in JSON format or other formats. The formatted data is then sent to the device, which then displays the received advice on the app's user interface.

[1242] As a concrete example, when a user operates a robot in a factory, once the user's daily work exceeds a certain volume, the device records location information, speed, and heart rate data, and a video camera captures the user's movements and facial expressions. After the work is completed, the device uploads the data to a server, which analyzes it using a generative artificial intelligence model. Based on the next work schedule, the device proposes a new interval training schedule and appropriate movement timing, and provides detailed advice on how to smooth the movement of the right arm. An emotion engine analyzes the user's facial expression data and simultaneously provides advice, including advice on rest, if the user feels fatigued or stressed.

[1243] Prompt Sentence Examples

[1244] "A robot is performing a machine assembly task. Please automatically capture the worker's movements, analyze their behavior and their emotional state, and provide optimization advice for the next task."

[1245] In this way, the system of the present invention provides users with individually optimized advice on improving their movements and form, thereby improving their work performance and preventing injuries, and also provides support for improving motivation by taking into account their emotional state.

[1246] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1247] Step 1: Data collection

[1248] A user starts a work session on their device. The device acquires location information using the GPS module, speed data from the speedometer, and heart rate data from the heart rate sensor. The device also activates the camera to start video recording of the work, thereby capturing facial expression data. The inputs are the user's motion data, location information, speed, heart rate, and video data, and the output is the collection of these data.

[1249] Step 2: Upload data

[1250] When the operating session is over, the user presses the "Stop" button on the device, at which point the device will batch compress all collected data and upload it to the server. The input to this process is the data collected in step 1, and the output is the compressed data uploaded to the server.

[1251] Step 3: Data Receipt and Storage

[1252] The server receives the uploaded data and stores it in a database. The input is the data uploaded in step 2, and the output is the data stored in the database. This provides the foundation for analysis.

[1253] Step 4: Data analysis

[1254] The server uses a generative artificial intelligence model to analyze the data stored in the database. Specifically, it analyzes position data, speed data, and heart rate data to evaluate the user's movement performance. The input is the movement data read from the database, and the output is the performance evaluation result.

[1255] Step 5: Sentiment Analysis

[1256] The server uses an emotion engine to analyze the user's facial expressions from the video data and recognize their emotional state. Additionally, if audio data is available, it is also used for analysis. The input is video data and audio data, and the output is the evaluation result of the emotional state.

[1257] Step 6: Generate optimization advice

[1258] The server uses a generative AI model to generate training optimization advice based on the analysis of movement data. For example, it can suggest a specific interval training schedule or an appropriate movement speed. It also flexibly adjusts the advice based on the user's emotional state. The input is the results of performance evaluation and emotional evaluation, and the output is optimization advice.

[1259] Step 7: Generate behavior improvement advice

[1260] The server generates advice for improving behavior based on the results of analyzing the video data. For example, if a user's arm movements are unnatural while operating a machine, the server will instruct the user on how to correct them. The input is the results of analyzing the video data, and the output is advice for improving behavior.

[1261] Step 8: Formatting and delivering advice

[1262] The server organizes the generated optimization advice and behavior improvement advice, formats the data (e.g., JSON format) taking into account the results of sentiment analysis, and sends it to the user's device. The device displays the received advice on the user interface within the app. The input is the generated advice and the results of sentiment analysis, and the output is the formatted advice that the user receives.

[1263] This processing step enables the system to comprehensively analyze the user's motion data and emotional state, and provide individually optimized training and motion improvement advice.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] 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.

[1268] 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.

[1269] 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.

[1270] 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).

[1271] 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.

[1272] 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."

[1273] 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.

[1274] 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).

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] The following is further disclosed regarding the above embodiment.

[1286] (Claim 1)

[1287] a means for collecting running data from a user;

[1288] A means of inputting and analyzing running data into a generative artificial intelligence model;

[1289] means for generating training optimization advice based on the analysis results;

[1290] A means for analyzing video data of running form and generating form improvement advice;

[1291] The system includes means for providing the generated advice to a user's terminal.

[1292] (Claim 2)

[1293] 10. The system of claim 1, wherein the analysis of the video data uses a skeleton detection algorithm.

[1294] (Claim 3)

[1295] 10. The system of claim 1, wherein the generated training optimization advice suggests interval training and pacing adjustments.

[1296] "Example 1"

[1297] (Claim 1)

[1298] means for collecting exercise data from a user;

[1299] A means for collecting video data capturing posture during exercise;

[1300] A means for inputting the collected motion data and video data into a generative artificial intelligence model for analysis;

[1301] means for generating training optimization advice based on the analysis results;

[1302] A means for analyzing the video data and generating posture improvement advice;

[1303] The system includes means for providing the generated advice to a user's mobile device.

[1304] (Claim 2)

[1305] 10. The system of claim 1, wherein the analysis of the video data uses a skeleton detection algorithm.

[1306] (Claim 3)

[1307] 10. The system of claim 1, wherein the generated training optimization advice suggests interval training and adjustments to exercise speed.

[1308] "Application Example 1"

[1309] (Claim 1)

[1310] means for collecting movement data from a user;

[1311] A means for inputting and analyzing movement data into a generative artificial intelligence model;

[1312] a means for generating efficiency advice based on the analysis results;

[1313] A means for analyzing video data of a motion form and generating form improvement advice;

[1314] The system includes means for providing the generated advice to a user's information terminal.

[1315] (Claim 2)

[1316] 10. The system of claim 1, wherein the analysis of the video data uses a physical feature detection algorithm.

[1317] (Claim 3)

[1318] 10. The system of claim 1, wherein the generated efficiency advice suggests route optimization and adjustments to physical movements.

[1319] "Example 2: Combining Emotion Engines"

[1320] (Claim 1)

[1321] a means for collecting running data from a user;

[1322] A means for compressing the data collected by the terminal and uploading it to a server;

[1323] a means for the server to store the uploaded data in a database;

[1324] A means of inputting and analyzing running data into a generative artificial intelligence model;

[1325] means for the emotion engine to analyze the video data to recognize the user's emotional state;

[1326] means for generating training optimization advice based on the analysis results;

[1327] A means for analyzing video data of running form and generating form improvement advice;

[1328] The system includes means for providing the generated advice to a user's terminal.

[1329] (Claim 2)

[1330] 10. The system of claim 1, further comprising means for using a skeleton detection algorithm to analyze the video data.

[1331] (Claim 3)

[1332] 10. The system of claim 1, further comprising means for adjusting the training optimization advice based on the sentiment analysis results.

[1333] "Application example 2 when combining emotion engines"

[1334] (Claim 1)

[1335] a means for collecting running data from a user;

[1336] A means of inputting and analyzing running data into a generative artificial intelligence model;

[1337] means for generating training optimization advice based on the analysis results;

[1338] A means for analyzing video data of running form and generating form improvement advice;

[1339] means for providing the generated advice to a user's terminal;

[1340] means for recognizing an emotional state from video data using an emotion engine;

[1341] The system includes a means for tailoring advice content based on the perceived emotional state.

[1342] (Claim 2)

[1343] 10. The system of claim 1, wherein the analysis of the video data uses a skeleton detection algorithm.

[1344] (Claim 3)

[1345] 10. The system of claim 1, wherein the generated training optimization advice suggests interval training and pacing adjustments. [Explanation of symbols]

[1346] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting running data from a user; A means of inputting and analyzing running data into a generative artificial intelligence model; means for generating training optimization advice based on the analysis results; A means for analyzing video data of running form and generating form improvement advice; The system includes means for providing the generated advice to a user's terminal.

2. 10. The system of claim 1, wherein the analysis of the video data uses a skeleton detection algorithm.

3. The system of claim 1 , wherein the generated training optimization advice suggests interval training and pacing adjustments.

Images