system

Abstract

Provide a system. [Solution] A means for collecting player play data; A means for preprocessing the collected play data; a means for performing real-time analysis using generative artificial intelligence to analyze the pre-processed data; means for generating improvements and strategies for the player based on the analysis results; a means of informing players of the improvements and strategies generated; A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, e-sports has been gaining attention as a new type of extracurricular activity. However, due to the lack of specialized coaches, it is difficult to receive specific feedback on play and ways to improve. Furthermore, analyzing opponent data and formulating strategies takes a significant amount of time, making efficient practice difficult. Furthermore, it places a heavy burden on busy and understaffed teachers. This makes it difficult for students to fully experience effective extracurricular activities. [Means for solving the problem]

[0005] This invention provides an e-sports club activity support system using generative artificial intelligence. The system includes a means for collecting player play data, a means for preprocessing the collected play data, a means for performing real-time analysis using generative artificial intelligence to analyze the preprocessed data, a means for generating improvements and strategies for the player based on the analysis results, and a means for notifying the player of the generated improvements and strategies. This system reduces the burden on busy teachers and supports students in practicing more effectively and competing based on strategy.

[0006] "Player" refers to an individual or team member participating in an esport.

[0007] "Play data" refers to information such as video, audio, and operation history generated when a player plays a game.

[0008] "Collection Method" refers to any device or software used to capture and record player play data.

[0009] "Preprocessing means" refers to a device or software that formats the collected play data into a format suitable for analysis and extracts the necessary features.

[0010] "Generative AI" refers to AI that has the ability to analyze and make predictions in real time based on collected data.

[0011] "Means for performing real-time analysis" refers to a device or software for instantly analyzing collected and pre-processed play data using generative artificial intelligence.

[0012] "Improvement and Strategy Generator" means any device or software that generates specific advice and strategies to improve a player's performance based on the analysis results.

[0013] "Means for Informing" means any device or software used to inform players of improvements and strategies that have been developed.

[0014] "Opponent Play Data" refers to information regarding the gameplay of the opponent against whom the player is playing.

[0015] "Competitive strategy" refers to tactics and strategies devised based on the opponent's playing data. [Brief explanation of the drawings]

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

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

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

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

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

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

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

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

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

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

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

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

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

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

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

[0037] This invention relates to an e-sports club activity support system that uses generative artificial intelligence. The purpose of this system is to collect and analyze players' play data and provide them with specific improvements and strategies. This system consists of a collection means, a pre-processing means, a real-time analysis means, a means for generating improvements and strategies, and a notification means.

[0038] Explanation of program processing

[0039] 1. Data Collection

[0040] The device collects the player's video and audio data, which is then sent to the server in real time. Furthermore, the user uploads their opponent's gameplay data, which is then sent to the server by the device.

[0041] 2. Data Preprocessing

[0042] The server preprocesses the received video and audio data and converts it into a format suitable for analysis. This preprocessing includes splitting the video data into frames and extracting features. The opponent's data is also preprocessed in the same way.

[0043] 3. Real-time analysis

[0044] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time, identifying their strengths and weaknesses. Opponents' data is also analyzed to extract their playing styles and tendencies.

[0045] 4. Improvements and Strategy Generation

[0046] Based on the analysis results, the server generates specific improvements for the player. For example, if a player's reaction time is slow, it will suggest training to improve their reaction time. It will also generate effective strategies against the opponent. For example, if the opponent is weak against attacks from the left, it will suggest tactics to strengthen attacks from that direction.

[0047] 5. Notification

[0048] The device displays the generated improvements and strategies to the player in real time and provides specific instructions, such as "Practice strengthening your attacks from the left side." This allows the player to instantly improve their playing style.

[0049] Specific examples

[0050] Example 1: Real-time analysis and feedback of play

[0051] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. Based on the analysis results, it is determined that the player's reaction time is slower than other players. The server then generates an improvement plan, suggesting that the player "perform specific training for 10 minutes to improve their reaction time." The device then notifies the player of this improvement plan and supports their practice.

[0052] Example 2: Opponent data analysis and strategy suggestions

[0053] The user uploads the replay video of their opponent to their device, and the device sends this data to the server. The server preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. For example, it learns that the opponent is weak against left-sided defense. The server generates a specific strategy, such as "strengthen attacks from the left side," and the device notifies the player. This allows the player to take effective countermeasures.

[0054] In this way, the e-sports club activity support system that uses generative artificial intelligence provides specific improvements and strategies to improve players' performance, supporting efficient practice and growth.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The device collects the player's gameplay video and audio data and transmits it to the server in real time.

[0058] Step 2:

[0059] The user uploads the opponent's play data to the terminal, and the terminal transmits this data to the server.

[0060] Step 3:

[0061] The server divides the received play data into frames and extracts the necessary video and audio features, specifically identifying the player's movement trajectory and attack timing.

[0062] Step 4:

[0063] The server formats the opponent's data into a unified format that can be analyzed, making it easier to analyze the opponent's behavior patterns.

[0064] Step 5:

[0065] The server uses generative artificial intelligence to analyze the player's playing style in real time, specifically assessing the player's attack success rate, movement speed, and reaction time to identify their strengths and weaknesses.

[0066] Step 6:

[0067] The server analyzes the opponent's playing style and tendencies, extracting their strengths, weaknesses, and favorite techniques.

[0068] Step 7:

[0069] Based on the analysis, the server generates specific improvements for the player, such as suggesting training to improve reaction speed.

[0070] Step 8:

[0071] The server generates strategies for the opponent. For example, if the opponent is weak to attacks from the left, it will suggest tactics to strengthen attacks from that direction.

[0072] Step 9:

[0073] The device displays generated improvements and strategies to the player in real time, and provides specific instructions and advice via text and voice.

[0074] Step 10:

[0075] Users practice and play based on the improvements and strategies provided by the user. The server collects new play data again and performs repeated processing to improve the player's performance.

[0076] The above is the specific processing flow of the e-sports club activity support system using generative artificial intelligence.

[0077] Example 1

[0078] 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."

[0079] Traditionally, practice and preparation for esports have relied primarily on the experience and intuition of players. This has made it difficult to find efficient practice methods and specific strategies for matches. In particular, improving a player's performance and analyzing their opponents takes time and effort, making it difficult to immediately identify areas for improvement or strategies.

[0080] 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.

[0081] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, and means and methods for collecting video data and audio data as player play data and preprocessing them, thereby enabling players to quickly and efficiently receive specific advice and battle strategies to improve their own playing style.

[0082] "Play data" is a general term for video data and audio data generated while a player is playing a game.

[0083] "Means for collection" refers to the equipment and methods for acquiring gameplay data and transmitting it to the server, including capture devices and microphones, as well as data streaming protocols.

[0084] "Preprocessing means" refers to the techniques and methods used to convert collected gameplay data into a format suitable for analysis. Specifically, this includes frame division and feature extraction of video data, and spectral analysis of audio data.

[0085] "Generative artificial intelligence" refers to artificial intelligence technology that can generate new information and patterns from input data using techniques such as deep learning.

[0086] "Means for real-time analysis" refers to systems and algorithms that use generative artificial intelligence to instantly analyze play data.

[0087] "Means for generating improvements and strategies" refers to techniques and methods for devising specific improvements and playing strategies for players based on the analysis results.

[0088] "Means of notification" refers to the techniques and methods used to communicate generated improvements and strategies to players, including user interfaces and notification systems.

[0089] "Video Data" refers to the sequence of image frames captured during gameplay.

[0090] "Audio Data" refers to audio information recorded during game play.

[0091] "Opponent's play data" refers to video data and audio data related to the gameplay of the opponent against whom the player is playing.

[0092] "Competitive strategy" refers to specific methods and tactics for analyzing an opponent's playing style and weaknesses and devising effective countermeasures.

[0093] The present invention relates to an e-sports club activity support system that uses generative artificial intelligence. The purpose of this system is to collect and analyze players' play data and provide them with specific improvements and strategies. The following describes in detail the embodiments of the present invention.

[0094] This system consists of a collection means, a pre-processing means, a real-time analysis means, a means for generating improvements and strategies, and a means for notification. To realize these means, various software libraries and protocols are utilized.

[0095] Collection Method

[0096] The device collects the player's gameplay video and audio data. Specifically, it uses a dedicated capture device and microphone to capture data during gameplay. The captured data is sent to the server in real time. RTMP (Real-Time Messaging Protocol) is used for data streaming. Furthermore, the user uploads their opponent's gameplay data via a web interface, and the device uses an HTTP request to send this data to the server.

[0097] Pretreatment means

[0098] The server pre-processes the received video and audio data and converts it into a format suitable for analysis. The pre-processing includes the following specific steps:

[0099] Video data frame division: Video data is divided into frames using the OpenCV library.

[0100] Feature extraction: Extract keyframes from multiple frames and extract features (edges, motion, color, etc.) from those frames.

[0101] Spectral analysis of audio data: Using the Librosa library, we extract spectral features from audio data, which prepares us to analyze important sounds in the game (e.g., footsteps to determine enemy positions).

[0102] Real-time analysis tools

[0103] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time, including the following techniques:

[0104] Utilizing deep learning models: Analyzing player play data using models created using TENSORFLOW (registered trademark) and PyTorch. For example, using models such as ResNet and Transformers, we evaluate player behavior patterns and reaction times.

[0105] Identifying strengths and weaknesses: The analysis results output by the model identify a player's strengths (e.g., high accuracy shooting) and weaknesses (e.g., slow reaction time).

[0106] Opponent Playstyle Analysis: Using the same generative AI, we analyze your opponents' movements to find their most frequently used tactics and weaknesses.

[0107] Improvements and Strategy Generation Tools

[0108] The server generates specific improvements for the player based on the analysis, including specific actions such as:

[0109] Suggestions for improvement: For example, if the analysis shows that a player has a slow reaction time, we will suggest specific training exercises (such as reflex training games) to improve that speed.

[0110] Strategy Generation: Generate tactics based on the opponent's weaknesses. For example, if the opponent is weak to attacks from the left, the system will suggest a specific tactic to the player: "Strengthen attacks from the left side."

[0111] Notification means

[0112] The device will display generated improvements and strategies to the player in real time and provide specific instructions, including the following specific actions:

[0113] Displaying Notifications: Displaying specific advice or tactics to players through the user interface (UI), such as "Spend the next 10 minutes training to improve your reaction speed."

[0114] Get feedback: See if players have implemented the suggested training or tactics and gather feedback.

[0115] Specific examples

[0116] Example 1: Real-time analysis and feedback of play

[0117] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. For example, it may identify that the player's reaction time is slower than other players. The server then generates an improvement plan, such as "perform specific training for 10 minutes to improve reaction time." The device then notifies the player of this improvement plan and supports their practice.

[0118] Example 2: Opponent data analysis and strategy suggestions

[0119] The user uploads the replay video of their opponent to their device, and the device sends this data to the server. The server preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. For example, it learns that the opponent is weak against left-sided defense. The server generates a specific strategy, such as "strengthen attacks from the left side," and the device notifies the player. This allows the player to take effective countermeasures.

[0120] Prompt example (play data analysis)

[0121] input:

[0122] "Analyze player A's play data and evaluate his reaction time and shooting accuracy. Player B's (opponent's) play data is also provided, so find his weaknesses and propose effective strategies."

[0123] output:

[0124] "Player A's reaction time is 20% slower than average. They have good shooting accuracy, but their accuracy decreases while moving."

[0125] "Your opponent's data has identified a weakness to attacks from the left. Employ tactics that strengthen attacks from the left."

[0126] In this way, generative AI models can be used to provide detailed and specific playstyle improvements and strategy suggestions.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Step 1: Data collection

[0129] The device collects the player's gameplay video and audio data. Specifically, it captures video and audio during gameplay in real time using a capture device or microphone. The input is the player's gameplay data, and the output is the collected video and audio data. The collected data is sent to the server using the RTMP protocol. The user can also upload their opponent's gameplay data via a web interface, and the device sends this data to the server via an HTTP request.

[0130] Step 2: Data Preprocessing

[0131] The server preprocesses the video and audio data it receives and converts it into a format suitable for analysis. The input is raw data sent via RTMP or HTTP, and the output is preprocessed data. Specific operations include:

[0132] Video data frame division: Use the OpenCV library to divide the video data into frames and extract keyframes.

[0133] Feature extraction: Extract features such as edges, motion, and color from each keyframe.

[0134] Spectral analysis of audio data: We use the Librosa library to extract spectral features from audio data, which prepares us for analyzing important sounds in the game (e.g., enemy footsteps).

[0135] Step 3: Real-time analysis

[0136] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time. The input is pre-processed data, and the output is the analysis results. Specific operations include:

[0137] Utilizing deep learning models: Using models created using TensorFlow or PyTorch (e.g., ResNet or Transformers), we evaluate players' behavioral patterns and reaction times.

[0138] Identifying strengths and weaknesses: The strengths and weaknesses of players are extracted from the analysis results output by the model.

[0139] Opponent Playstyle Analysis: Similarly, generative AI is used to analyze opponents' movement patterns, weaknesses, and strategies.

[0140] Step 4: Improvements and strategy generation

[0141] The server generates specific improvements and strategies for the player based on the analysis results. The input is the analysis results, and the output is suggested improvements and strategies. Specific operations include:

[0142] Suggestions for improvement: For example, if your reaction time is slower than other players, we will suggest specific training exercises to improve your reaction time.

[0143] Strategy generation: Based on the opponent's weaknesses (e.g., weak defense on the left side), the system suggests specific tactics to the player, such as "strengthen attack from the left side."

[0144] Step 5: Notification

[0145] The terminal displays the generated improvements and strategies to the player in real time and provides specific instructions. The input is the improvement and strategy suggestions, and the output is the notification to the player. Specific actions include:

[0146] Displaying Notifications: Displaying improvements and strategies to players through the user interface, for example, "Spend the next 10 minutes practicing to improve your reaction speed."

[0147] Gather feedback: By checking whether players have implemented the suggested training and tactics and collecting their feedback, we can provide more accurate analysis and recommendations.

[0148] (Application example 1)

[0149] 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."

[0150] Conventional systems were specialized in improving player performance, but their application was limited to sports and games, and they could not be adapted to improving or optimizing the work efficiency of robots in factories. In particular, there was a lack of technology that could evaluate robot work performance in real time and provide specific improvements and strategies, which made it difficult to establish efficient work processes.

[0151] 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.

[0152] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using a generative artificial intelligence (AI) that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, means for collecting robot task data, means for preprocessing the collected task data, means for performing real-time analysis using a generative AI that analyzes the preprocessed data and evaluating task performance, means for generating specific improvements and strategies to improve the robot's task efficiency based on the analysis results, and means for notifying the robot of the generated improvements and strategies, thereby enabling performance improvements for both the player and the robot.

[0153] "Player play data" refers to information related to the actions and operations performed by a player in a game or simulation, etc. This includes video data, audio data, operation history, etc.

[0154] "Preprocessing methods" refer to processes or techniques that transform raw data into a form suitable for analysis, such as data cleaning, frame segmentation, and feature extraction.

[0155] "Means for real-time analysis using generative artificial intelligence" refers to a process that uses generative artificial intelligence (AI) algorithms to analyze input data in real time and output results, allowing for immediate identification of data features and patterns.

[0156] "Improvement and strategy generation measures" refers to the process of generating specific performance improvement recommendations and strategies based on the analysis results, including operational improvement recommendations and tactical advice.

[0157] "Means of notifying players" refers to the methods used to communicate generated improvements and strategies to players, including display and audio messages.

[0158] "Robot work data" refers to information related to the movements and work that robots perform in factories, manufacturing sites, etc. This includes movement patterns, work results, sensor data, etc.

[0159] "Means of notifying the robot" refers to the methods of communicating generated improvements and strategies to the robot and having it adjust its operations, including sending control signals and updating its program.

[0160] The present invention relates to a system for improving the performance of players and robots. Specific embodiments for carrying out the present invention will be described below.

[0161] System Configuration

[0162] This system consists of the following main components:

[0163] 1. Data Collection Methods

[0164] 2. Data preprocessing methods

[0165] 3. Real-time analysis using generative artificial intelligence

[0166] 4. Improvements and Strategy Generation

[0167] 5. Means of notification

[0168] Data collection methods

[0169] The server collects the player's play data and the robot's work data. The player's play data includes video and audio data, which the user sends to the server via their device. The robot's work data is also obtained from sensors and cameras installed on the robot and sent to the server.

[0170] Data preprocessing measures

[0171] The server preprocesses the received data. This includes splitting the video data into frames, extracting features, and cleaning the data. This converts the data into a format suitable for analysis. For example, OpenCV is used to split the video data into frames, and Scikit-learn is used to extract features.

[0172] Real-time analysis using generative artificial intelligence

[0173] The server uses generative artificial intelligence (AI) to analyze player and robot data in real time. During the analysis process, the server evaluates the player's control patterns and the robot's performance to identify strengths and weaknesses. The AI ​​algorithms used here include TensorFlow and PyTorch.

[0174] Improvements and Strategy Generation Tools

[0175] The server generates specific improvements and strategies based on the results of real-time analysis. For example, it generates a training plan for the player to improve reaction speed, and suggests motion instructions for the robot to handle parts from a specific angle. It processes the analysis results using Pandas and NumPy to generate improvements and strategies.

[0176] Notification means

[0177] The server notifies the player and robot of the improvements and strategies that have been generated. The player is notified by display and voice message, and control signals are sent to the robot using ROS (Robot Operating System). The player and robot receive this notification and can immediately improve their playing style and work content.

[0178] Specific examples

[0179] 1. Real-time player analysis and feedback:

[0180] The player's play data is sent to a server in real time and analyzed by a generative AI model. As a result, it is determined that the player's reaction time is slower than other players, and an improvement plan is generated, such as "performing specific training for 10 minutes to improve reaction time."

[0181] Example prompt: "Suggest specific training to improve reaction speed."

[0182] 2. Robot performance analysis and improvement proposals:

[0183] The robot's work data is sent to a server in real time and analyzed by a generative AI model. As a result, it is determined that a particular part handling method is inefficient, and specific operational instructions such as "handle the part from a specific angle" are generated.

[0184] Example prompt: "Suggest the optimal working angle and speed for each type of part being handled."

[0185] As a result, the present invention provides a system for improving the performance of both the player and the robot.

[0186] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0187] Step 1:

[0188] The server collects player play data and robot operation data from the device. Input data includes video data, audio data, sensor data, etc. The collected data is stored on the server as raw data.

[0189] Step 2:

[0190] The server preprocesses the collected raw data. In this step, the video data is split into frames using OpenCV and features are extracted using Scikit-learn. The input is the frame-split video and audio data, and the output is data converted into a format suitable for analysis.

[0191] Step 3:

[0192] The server uses generative artificial intelligence to analyze preprocessed data in real time. It uses TensorFlow and PyTorch to evaluate the player's control patterns and the robot's work performance to identify strengths and weaknesses. The input is the preprocessed data, and the output is the analysis results.

[0193] Step 4:

[0194] The server generates specific improvements and strategies based on the analysis results. It processes the analysis results using Pandas and NumPy and makes suggestions to improve the performance of the player and robot. The input is the analysis results, and the output is improvements and strategies. For example, "specific training to improve reaction speed" or "motion instructions for handling parts from a specific angle" are generated.

[0195] Step 5:

[0196] The server notifies the player and robot of the generated improvements and strategies. The player is notified by displaying the improvements and voice messages, and the robot is sent control signals using ROS. The input is the generated improvements and strategies, and the output is a notification. The player and robot receive this notification and respond in real time.

[0197] 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.

[0198] This invention relates to an e-sports club activity support system that uses generative artificial intelligence and an emotion engine. This system collects and analyzes players' play data and emotional states, and provides them with optimal improvements and strategies. This system consists of a play data collection means, preprocessing means, real-time analysis means, improvement and strategy generation means, notification means, and an emotion engine that recognizes the user's emotions.

[0199] Explanation of program processing

[0200] Data collection

[0201] The device collects the player's gameplay video and audio data and transmits it to the server in real time. The collected data also includes information about the player's gameplay. The user also uploads the opponent's gameplay data, which the device then transmits to the server.

[0202] Data Preprocessing

[0203] The server preprocesses the video and audio data it receives, splitting the video data into frames and extracting features from the audio data. The server also preprocesses the opponent's data and converts it into a format suitable for analysis.

[0204] emotion recognition

[0205] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data, thereby recognizing their emotional state (e.g., stress, anxiety, concentration, etc.).

[0206] Real-time analytics

[0207] The server uses generative artificial intelligence to analyze the player's playing style and performance in real time, and also uses emotional information provided by the emotion engine to comprehensively evaluate the player's state.

[0208] Improvements and Strategy Generation

[0209] Based on the analysis results, the server generates specific improvements for the player. For example, if stress levels are high, it suggests ways to relax. It also generates strategies for dealing with opponents. For example, if an opponent is weak against attacks from the left, it suggests tactics to strengthen attacks from that direction.

[0210] notification

[0211] The device displays generated improvements and strategies to the player in real time, providing specific instructions and feedback in the form of voice and text.

[0212] Specific examples

[0213] Example 1: Real-time analysis and feedback of play

[0214] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. An emotion engine then analyzes the player's emotional state (for example, concentration and stress level). Based on the analysis results, it is determined that the player's reaction time is slower than other players and that they are under high stress. The server then generates an improvement plan, suggesting that the player "do 10 minutes of training to improve their reaction time and incorporate deep breathing exercises to reduce stress." The device then notifies the player of this improvement plan and supports their practice.

[0215] Example 2: Opponent data analysis and strategy suggestions

[0216] The user uploads a replay video of their opponent to their device, which then sends the data to the server. The server then preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. The system also takes into account the player's emotional state. For example, if the player is feeling anxious, the system will suggest a simple strategy to exploit the opponent's weaknesses. Specifically, the system generates a tactic such as "strengthen attacks from the left side," and notifies the player. This allows the player to take effective countermeasures.

[0217] In this way, the e-sports club activity support system, which combines generative artificial intelligence and an emotion engine, not only improves players' performance but also provides optimal improvements and strategies that take into account their emotional state.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] The device collects the player's gameplay video and audio data and transmits it to the server in real time.

[0221] Step 2:

[0222] The user uploads the opponent's play data to the terminal, and the terminal transmits this data to the server.

[0223] Step 3:

[0224] The server divides the gameplay video data it receives into frames and extracts the necessary features, including analyzing the player's movement trajectory and attack timing.

[0225] Step 4:

[0226] The server preprocesses the received voice data and analyzes the tone and vocal patterns of the voice, which provides the basis for inferring the player's emotional state.

[0227] Step 5:

[0228] The server formats the opponent's data into a unified format and converts it into a form suitable for analysis.

[0229] Step 6:

[0230] The server uses an emotion engine to detect the player's emotional state from real-time video and audio data, for example, analyzing stress and concentration levels from facial expressions and voice tones.

[0231] Step 7:

[0232] The server uses generative artificial intelligence to analyze players' playstyles and performance in real time, including assessing their attack success rate, movement speed, reaction time, and more.

[0233] Step 8:

[0234] The server analyzes the opponent's playing style and tendencies to extract their strengths and weaknesses, thereby identifying their special moves and attack patterns.

[0235] Step 9:

[0236] The server will generate specific improvements for the player based on the analysis results, for example, if the player has a slow reaction time, it will suggest specific reflex training.

[0237] Step 10:

[0238] The server generates strategies for the opponent and proposes the optimal strategy taking into account the results of the emotion engine. For example, if the opponent is weak to attacks from the left side and the player is concentrating, the server proposes a tactic to strengthen attacks from the left side.

[0239] Step 11:

[0240] The device displays generated improvements and strategies to the player in real time, with specific instructions and advice provided via text and audio.

[0241] Step 12:

[0242] Users practice and play based on the improvements and strategies provided by the user. The server continuously collects new play data and emotional data, and the program is dynamically adjusted.

[0243] The above is the specific processing flow of the e-sports club activity support system that combines generative artificial intelligence and an emotion engine.

[0244] Example 2

[0245] 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."

[0246] While conventional e-sports club support systems were able to collect players' play data and generate improvements and strategies based on the analysis results, they were unable to recognize the players' emotional state in real time and incorporate that information into the analysis. This made it difficult to provide optimal feedback and strategies that took the players' mental state into account, preventing the maximum improvement of player performance.

[0247] 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. In this invention, the server includes means for collecting play data of players, means for pre-processing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the pre-processed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, and means including an emotion engine that analyzes the player's emotional state in real time. This enables analysis and feedback that takes the player's emotional state into consideration.

[0248] "Play data" refers to video data and audio data that includes information about the player's game operations.

[0249] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis, and includes splitting video data into frames and removing noise from audio data.

[0250] "Generative AI" refers to artificial intelligence technology that analyzes collected data in real time and generates improvements and strategies for players.

[0251] "Emotion engine" refers to technology that analyzes the player's emotional state in real time from video and audio data.

[0252] "Areas for Improvement" refers to specific actions or training methods recommended to improve a player's performance.

[0253] "Strategy" refers to specific tactics proposed to players based on the characteristics and weaknesses of their opponents.

[0254] "Notification" refers to the act of communicating generated improvements and strategies to players in audio or text format.

[0255] This invention relates to an e-sports club activity support system that uses generative artificial intelligence and an emotion engine. This system collects and analyzes players' play data and emotional states, and provides them with optimal improvements and strategies. This system consists of a play data collection means, a preprocessing means, a real-time analysis means, a means for generating improvements and strategies, a notification means, and an emotion engine that recognizes the user's emotions.

[0256] The device collects the player's gameplay video and audio data and sends it to the server in real time. The device is equipped with a high-resolution camera and microphone, which capture data using this hardware. The collected data also includes information about the player's game operations (keyboard and mouse input). The user also uploads their opponent's gameplay data to the device, which then sends this data to the server.

[0257] The server preprocesses the video and audio data it receives. It divides the video data into frames and extracts features from the audio data. The opponent's data is also preprocessed and converted into a format suitable for analysis. For video data, the video is divided into a set number of frames and important features are extracted using an image processing algorithm. For audio data, background noise and other noise are removed to obtain clear audio information.

[0258] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data, including facial expression analysis and tone of voice analysis, to accurately recognize the player's emotional state (stress, anxiety, concentration, etc.).

[0259] The server uses a generative artificial intelligence (AI) model to analyze the player's playing style and performance in real time. Based on in-game movements and input information, the server evaluates the player's performance indicators (reaction speed, accuracy, decision-making ability). In addition, it integrates emotional information provided by an emotion engine to comprehensively evaluate the player's state.

[0260] Based on the analysis results, the server generates specific suggestions for improvement for the player, such as "Spend 10 minutes of training to improve your reaction speed" or "Take deep breaths to reduce stress." Analyzing the opponent's data, the server generates strategies such as "Your opponent is weak against attacks from the left, so strengthen your attacks from the left."

[0261] The device displays generated improvements and strategies to the player in real time, using on-screen pop-ups and audio notifications to provide specific advice and feedback to the player. For example, the following prompts are available:

[0262] "Your reaction time is slow, so do 10 minutes of training. Incorporating deep breathing techniques can also help reduce stress."

[0263] "Your opponent is weak to attacks from the left, so strengthen your attacks from the left."

[0264] This system not only improves players' performance but also provides optimal improvements and strategies that take into account their emotional state. As a result, players can take effective measures and properly manage their mental state, thereby supporting them in achieving their best performance.

[0265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0266] Step 1: Data collection

[0267] The device collects video and audio data of the player's gameplay. A high-resolution camera and microphone connected to the device capture video and audio data in real time. It also collects log data of the player's game operations (keyboard and mouse input). This data is sent to the server in real time. Input: video data, audio data, operation log. Output: raw data set sent to the server.

[0268] Step 2: Gather opponent data

[0269] The user uploads the opponent's play data (such as a replay video) to their device. The device detects this and sends the video data to the server. Input: Replay video of the opponent. Output: Data of the opponent sent to the server.

[0270] Step 3: Data Preprocessing

[0271] The server preprocesses the video and audio data it receives. Specifically, it divides the video data into frames and extracts important features from each frame. It also removes noise from the audio data and extracts features. The opponent's data is similarly preprocessed and converted into a format suitable for analysis. Input: Raw play data and opponent data. Output: Preprocessed dataset.

[0272] Step 4: Emotion Recognition

[0273] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data. By analyzing their facial expressions and tone of voice, it can recognize their stress, anxiety, concentration, etc. Input: Preprocessed video and audio data. Output: Player's emotional state data.

[0274] Step 5: Real-time analysis

[0275] The server uses a generative artificial intelligence (AI) model to analyze the player's playing style and performance in real time. Based on in-game movements and input information, the server evaluates the player's performance indicators (reaction speed, accuracy, decision-making ability). At the same time, it integrates emotional information provided by the emotion engine to comprehensively evaluate the player's state. Input: Preprocessed dataset, emotional state data. Output: Analysis result data.

[0276] Step 6: Improvements and strategy generation

[0277] Based on the analysis results, the server generates specific areas for improvement and strategies for the player. For example, if a player's reaction time is slow, it will suggest "Let's practice for 10 minutes to improve our reaction time." It will also generate strategies for the opponent, proposing tactics to exploit the opponent's weaknesses (for example, weakness to attacks from the left side). Input: Analysis result data. Output: Data on areas for improvement and strategies.

[0278] Step 7: Notification

[0279] The device displays the generated improvements and strategies to the player in real time. Specific advice and feedback is provided during play and practice via on-screen pop-ups and voice notifications. For example, "Your reaction time is slow, so practice for 10 minutes. Deep breathing can also help reduce stress," or "Your opponent is weak against attacks from the left side, so strengthen your attacks from the left side." Input: Data on improvements and strategies. Output: Feedback notified to the player.

[0280] (Application example 2)

[0281] 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."

[0282] Existing e-sports club activity support systems collect players' play data and emotional state and provide improvements and strategies based on that data. However, they have not yet been applied to industrial applications such as improving the efficiency of robotic work in factories or detecting anomalies. Factories require real-time analysis of robot operation data and information about the work environment to identify efficient work methods and detect anomalies early, but no effective system exists for this purpose. Therefore, technology is needed to improve the efficiency of robotic work in factories and detect anomalies.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0284] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, means for collecting, preprocessing, and analyzing robot operation data, means for generating efficient work methods and strategies for the robot based on the analysis results, and means for notifying factory staff of the generated work methods and strategies, thereby enabling efficient robot work in factories and abnormality detection.

[0285] "Play data" refers to information related to the actions and operations of a player or robot, and includes video data and audio data.

[0286] "Preprocessing" refers to the process of converting collected play data and action data into a format suitable for analysis, and includes dividing the data into frames and extracting features.

[0287] "Generative AI" is an artificial intelligence technology used to generate improvements and strategies based on collected and pre-processed data, analyzed in real time.

[0288] "Real-time analysis" is a process that involves collecting and analyzing data without any time delay, and provides immediate evaluation and suggestions based on operating conditions and emotional state.

[0289] "Improvements and strategies" are specific guidelines and tactics for improving the performance of the player or robot based on the analysis results.

[0290] "Notification" is an action that notifies the user of generated improvements or strategies, and is provided in audio or text format.

[0291] "Operation data" refers to data that includes information such as the operating status of the robot, the success or failure of the operation, error information, and the working speed.

[0292] "Efficient work methods" are specific techniques and procedures for maximizing the work efficiency of robots, and are derived using generative artificial intelligence.

[0293] "Anomaly detection" is the process of detecting abnormal behavior or conditions that deviate from normal operating conditions, and is important for maintaining safety and efficiency.

[0294] "Factory staff" refers to the people who operate and monitor robots in the factory and who are notified of the generated work methods and strategies.

[0295] System Configuration

[0296] The system includes the following means:

[0297] 1. Means of collecting player and robot behavior data

[0298] 2. Means of preprocessing the collected data

[0299] 3. A means of real-time analysis using generative artificial intelligence to analyze pre-processed data

[0300] 4. A means of generating improvements and strategies for players and robots based on the analysis results.

[0301] 5. A means to inform generated improvements and strategies

[0302] Program processing explanation

[0303] Hardware

[0304] Smartphone: Collects player and robot movement data (video and audio) and sends it to the server.

[0305] Cloud Server: The main computing resource for data analysis and strategy generation.

[0306] software

[0307] OpenCV: Used for preprocessing video data and frame segmentation.

[0308] Generative artificial intelligence models: Used for data analysis and strategy generation.

[0309] EmotionAnalyzer: Used to analyze emotional states.

[0310] Operation flow

[0311] 1. Data collection: A smartphone collects video and audio data of the player and robot's movements in real time. The video data is divided into frames, and features are extracted from the audio data in the same way.

[0312] 2. Preprocessing: The cloud server divides the video data into frames and extracts features from the audio data, converting the data into a format suitable for analysis.

[0313] 3. Emotion Recognition: The cloud server uses the EmotionAnalyzer to analyze the emotional state of the player and robot, thereby recognizing emotional states such as stress and concentration.

[0314] 4. Real-time analysis: A cloud server uses generative artificial intelligence to analyze player and robot behavior data in real time, including emotional state information.

[0315] 5. Improvements and Strategy Generation: Based on the analysis results, the cloud server generates specific improvements and strategies for players and robots. For example, it can propose specific methods to improve work efficiency.

[0316] 6. Notification: Smartphones will notify players and factory staff of generated improvements and strategies in voice and text format.

[0317] Specific examples

[0318] If a specific player is experiencing high stress

[0319] The system collects video and audio data from the player and uses the Emotion Analyzer to detect high stress levels. Generative AI takes this information into account and generates specific improvements to reduce stress (e.g., practicing deep breathing). The player is notified of this via their smartphone.

[0320] When there are many errors in the robot's work

[0321] The system collects data on the robot's operations and uses generative artificial intelligence to analyze its movements in real time. If it determines that frequent errors are due to human error, it generates efficient work methods (e.g., changing the order of certain operations) and notifies factory staff via their smartphones.

[0322] Prompt Sentence Examples

[0323] Analyze the operation data of a factory robot and propose ways to improve the error rate and work efficiency of specific tasks in real time. Also, evaluate the emotional state of the robot through its actions and detect anomalies.

[0324] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0325] Step 1:

[0326] Data collection

[0327] The device collects video and audio data of the player and robot's movements. Specifically, the smartphone captures video data through the camera and audio data through the microphone. This data is sent to the server in real time.

[0328] Input: Video data, audio data

[0329] Output: Raw data stored on the server

[0330] Step 2:

[0331] Pretreatment

[0332] The server preprocesses the video and audio data it receives. The video data is split into frames, and features (e.g., frequency components) are extracted from the audio data. OpenCV is used to split the video data into frames, and a Python audio processing library is used to preprocess the audio data.

[0333] Input: Raw data stored on the server

[0334] Output: Preprocessed frame-by-frame video data, feature-extracted audio data

[0335] Step 3:

[0336] emotion recognition

[0337] The server uses an emotion engine (EmotionAnalyzer) to analyze the emotional state of the player or robot from pre-processed video and audio data. Specifically, the emotional state (e.g., concentration, stress) is recognized by analyzing facial expressions and tone of voice.

[0338] Input: Preprocessed frame-by-frame video data, feature-extracted audio data

[0339] Output: Emotional state information (concentration, stress level, etc.)

[0340] Step 4:

[0341] Real-time analytics

[0342] The server analyzes the pre-processed data and emotional state information using a generative artificial intelligence model, which evaluates the movement performance of the player and robot and determines efficient tasks and playing styles.

[0343] Input: Preprocessed data, emotional state information

[0344] Output: Performance evaluation results

[0345] Step 5:

[0346] Improvements and Strategy Generation

[0347] Based on the analysis results, the server generates specific improvements and strategies for the player and robot. For example, if it detects high stress levels, it will suggest relaxation methods, and if the robot is making a lot of errors, it will suggest changes to its operation procedures.

[0348] Input: Performance evaluation results

[0349] Output: Improvements and strategies

[0350] Step 6:

[0351] notification

[0352] The device notifies players and factory staff of the improvements and strategies received from the server. Specifically, the smartphone displays and announces the improvements and strategies in voice and text format.

[0353] Input: Improvements and Strategies

[0354] Output: Notification to players and factory staff

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

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

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

[0358] [Second embodiment]

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

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

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

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

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

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

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

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

[0367] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

[0370] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0371] This invention relates to an e-sports club activity support system that uses generative artificial intelligence. The purpose of this system is to collect and analyze players' play data and provide them with specific improvements and strategies. This system consists of a collection means, a pre-processing means, a real-time analysis means, a means for generating improvements and strategies, and a notification means.

[0372] Explanation of program processing

[0373] 1. Data Collection

[0374] The device collects the player's video and audio data, which is then sent to the server in real time. Furthermore, the user uploads their opponent's gameplay data, which is then sent to the server by the device.

[0375] 2. Data Preprocessing

[0376] The server preprocesses the received video and audio data and converts it into a format suitable for analysis. This preprocessing includes splitting the video data into frames and extracting features. The opponent's data is also preprocessed in the same way.

[0377] 3. Real-time analysis

[0378] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time, identifying their strengths and weaknesses. Opponents' data is also analyzed to extract their playing styles and tendencies.

[0379] 4. Improvements and Strategy Generation

[0380] Based on the analysis results, the server generates specific improvements for the player. For example, if a player's reaction time is slow, it will suggest training to improve their reaction time. It will also generate effective strategies against the opponent. For example, if the opponent is weak against attacks from the left, it will suggest tactics to strengthen attacks from that direction.

[0381] 5. Notification

[0382] The device displays the generated improvements and strategies to the player in real time and provides specific instructions, such as "Practice strengthening your attacks from the left side." This allows the player to instantly improve their playing style.

[0383] Specific examples

[0384] Example 1: Real-time analysis and feedback of play

[0385] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. Based on the analysis results, it is determined that the player's reaction time is slower than other players. The server then generates an improvement plan, suggesting that the player "perform specific training for 10 minutes to improve their reaction time." The device then notifies the player of this improvement plan and supports their practice.

[0386] Example 2: Opponent data analysis and strategy suggestions

[0387] The user uploads the replay video of their opponent to their device, and the device sends this data to the server. The server preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. For example, it learns that the opponent is weak against left-sided defense. The server generates a specific strategy, such as "strengthen attacks from the left side," and the device notifies the player. This allows the player to take effective countermeasures.

[0388] In this way, the e-sports club activity support system that uses generative artificial intelligence provides specific improvements and strategies to improve players' performance, supporting efficient practice and growth.

[0389] The processing flow will be explained below.

[0390] Step 1:

[0391] The device collects the player's gameplay video and audio data and transmits it to the server in real time.

[0392] Step 2:

[0393] The user uploads the opponent's play data to the terminal, and the terminal transmits this data to the server.

[0394] Step 3:

[0395] The server divides the received play data into frames and extracts the necessary video and audio features, specifically identifying the player's movement trajectory and attack timing.

[0396] Step 4:

[0397] The server formats the opponent's data into a unified format that can be analyzed, making it easier to analyze the opponent's behavior patterns.

[0398] Step 5:

[0399] The server uses generative artificial intelligence to analyze the player's playing style in real time, specifically assessing the player's attack success rate, movement speed, and reaction time to identify their strengths and weaknesses.

[0400] Step 6:

[0401] The server analyzes the opponent's playing style and tendencies, extracting their strengths, weaknesses, and favorite techniques.

[0402] Step 7:

[0403] Based on the analysis, the server generates specific improvements for the player, such as suggesting training to improve reaction speed.

[0404] Step 8:

[0405] The server generates strategies for the opponent. For example, if the opponent is weak to attacks from the left, it will suggest tactics to strengthen attacks from that direction.

[0406] Step 9:

[0407] The device displays generated improvements and strategies to the player in real time, and provides specific instructions and advice via text and voice.

[0408] Step 10:

[0409] Users practice and play based on the improvements and strategies provided by the user. The server collects new play data again and performs repeated processing to improve the player's performance.

[0410] The above is the specific processing flow of the e-sports club activity support system using generative artificial intelligence.

[0411] Example 1

[0412] 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."

[0413] Traditionally, practice and preparation for esports have relied primarily on the experience and intuition of players. This has made it difficult to find efficient practice methods and specific strategies for matches. In particular, improving a player's performance and analyzing their opponents takes time and effort, making it difficult to immediately identify areas for improvement or strategies.

[0414] 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.

[0415] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, and means and methods for collecting video data and audio data as player play data and preprocessing them, thereby enabling players to quickly and efficiently receive specific advice and battle strategies to improve their own playing style.

[0416] "Play data" is a general term for video data and audio data generated while a player is playing a game.

[0417] "Means for collection" refers to the equipment and methods for acquiring gameplay data and transmitting it to the server, including capture devices and microphones, as well as data streaming protocols.

[0418] "Preprocessing means" refers to the techniques and methods used to convert collected gameplay data into a format suitable for analysis. Specifically, this includes frame division and feature extraction of video data, and spectral analysis of audio data.

[0419] "Generative artificial intelligence" refers to artificial intelligence technology that can generate new information and patterns from input data using techniques such as deep learning.

[0420] "Means for real-time analysis" refers to systems and algorithms that use generative artificial intelligence to instantly analyze play data.

[0421] "Means for generating improvements and strategies" refers to techniques and methods for devising specific improvements and playing strategies for players based on the analysis results.

[0422] "Means of notification" refers to the techniques and methods used to communicate generated improvements and strategies to players, including user interfaces and notification systems.

[0423] "Video Data" refers to the sequence of image frames captured during gameplay.

[0424] "Audio Data" refers to audio information recorded during game play.

[0425] "Opponent's play data" refers to video data and audio data related to the gameplay of the opponent against whom the player is playing.

[0426] "Competitive strategy" refers to specific methods and tactics for analyzing an opponent's playing style and weaknesses and devising effective countermeasures.

[0427] The present invention relates to an e-sports club activity support system that uses generative artificial intelligence. The purpose of this system is to collect and analyze players' play data and provide them with specific improvements and strategies. The following describes in detail the embodiments of the present invention.

[0428] This system consists of a collection means, a pre-processing means, a real-time analysis means, a means for generating improvements and strategies, and a means for notification. To realize these means, various software libraries and protocols are utilized.

[0429] Collection Method

[0430] The device collects the player's gameplay video and audio data. Specifically, it uses a dedicated capture device and microphone to capture data during gameplay. The captured data is sent to the server in real time. RTMP (Real-Time Messaging Protocol) is used for data streaming. Furthermore, the user uploads their opponent's gameplay data via a web interface, and the device uses an HTTP request to send this data to the server.

[0431] Pretreatment means

[0432] The server pre-processes the received video and audio data and converts it into a format suitable for analysis. The pre-processing includes the following specific steps:

[0433] Video data frame division: Video data is divided into frames using the OpenCV library.

[0434] Feature extraction: Extract keyframes from multiple frames and extract features (edges, motion, color, etc.) from those frames.

[0435] Spectral analysis of audio data: Using the Librosa library, we extract spectral features from audio data, which prepares us to analyze important sounds in the game (e.g., footsteps to determine enemy positions).

[0436] Real-time analysis tools

[0437] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time, including the following techniques:

[0438] Utilizing deep learning models: Analyzing player play data using models created using TensorFlow and PyTorch. For example, using models such as ResNet and Transformers, we evaluate player behavior patterns and reaction times.

[0439] Identifying strengths and weaknesses: The analysis results output by the model identify a player's strengths (e.g., high accuracy shooting) and weaknesses (e.g., slow reaction time).

[0440] Opponent Playstyle Analysis: Using the same generative AI, we analyze your opponents' movements to find their most frequently used tactics and weaknesses.

[0441] Improvements and Strategy Generation Tools

[0442] The server generates specific improvements for the player based on the analysis, including specific actions such as:

[0443] Suggestions for improvement: For example, if the analysis shows that a player has a slow reaction time, we will suggest specific training exercises (such as reflex training games) to improve that speed.

[0444] Strategy Generation: Generate tactics based on the opponent's weaknesses. For example, if the opponent is weak to attacks from the left, the system will suggest a specific tactic to the player: "Strengthen attacks from the left side."

[0445] Notification means

[0446] The device will display generated improvements and strategies to the player in real time and provide specific instructions, including the following specific actions:

[0447] Displaying Notifications: Displaying specific advice or tactics to players through the user interface (UI), such as "Spend the next 10 minutes training to improve your reaction speed."

[0448] Get feedback: See if players have implemented the suggested training or tactics and gather feedback.

[0449] Specific examples

[0450] Example 1: Real-time analysis and feedback of play

[0451] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. For example, it may identify that the player's reaction time is slower than other players. The server then generates an improvement plan, such as "perform specific training for 10 minutes to improve reaction time." The device then notifies the player of this improvement plan and supports their practice.

[0452] Example 2: Opponent data analysis and strategy suggestions

[0453] The user uploads the replay video of their opponent to their device, and the device sends this data to the server. The server preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. For example, it learns that the opponent is weak against left-sided defense. The server generates a specific strategy, such as "strengthen attacks from the left side," and the device notifies the player. This allows the player to take effective countermeasures.

[0454] Prompt example (play data analysis)

[0455] input:

[0456] "Analyze player A's play data and evaluate his reaction time and shooting accuracy. Player B's (opponent's) play data is also provided, so find his weaknesses and propose effective strategies."

[0457] output:

[0458] "Player A's reaction time is 20% slower than average. They have good shooting accuracy, but their accuracy decreases while moving."

[0459] "Your opponent's data has identified a weakness to attacks from the left. Employ tactics that strengthen attacks from the left."

[0460] In this way, generative AI models can be used to provide detailed and specific playstyle improvements and strategy suggestions.

[0461] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0462] Step 1: Data collection

[0463] The device collects the player's gameplay video and audio data. Specifically, it captures video and audio during gameplay in real time using a capture device or microphone. The input is the player's gameplay data, and the output is the collected video and audio data. The collected data is sent to the server using the RTMP protocol. The user can also upload their opponent's gameplay data via a web interface, and the device sends this data to the server via an HTTP request.

[0464] Step 2: Data Preprocessing

[0465] The server preprocesses the video and audio data it receives and converts it into a format suitable for analysis. The input is raw data sent via RTMP or HTTP, and the output is preprocessed data. Specific operations include:

[0466] Video data frame division: Use the OpenCV library to divide the video data into frames and extract keyframes.

[0467] Feature extraction: Extract features such as edges, motion, and color from each keyframe.

[0468] Spectral analysis of audio data: We use the Librosa library to extract spectral features from audio data, which prepares us for analyzing important sounds in the game (e.g., enemy footsteps).

[0469] Step 3: Real-time analysis

[0470] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time. The input is pre-processed data, and the output is the analysis results. Specific operations include:

[0471] Utilizing deep learning models: Using models created using TensorFlow or PyTorch (e.g., ResNet or Transformers), we evaluate players' behavioral patterns and reaction times.

[0472] Identifying strengths and weaknesses: The strengths and weaknesses of players are extracted from the analysis results output by the model.

[0473] Opponent Playstyle Analysis: Similarly, generative AI is used to analyze opponents' movement patterns, weaknesses, and strategies.

[0474] Step 4: Improvements and strategy generation

[0475] The server generates specific improvements and strategies for the player based on the analysis results. The input is the analysis results, and the output is suggested improvements and strategies. Specific operations include:

[0476] Suggestions for improvement: For example, if your reaction time is slower than other players, we will suggest specific training exercises to improve your reaction time.

[0477] Strategy generation: Based on the opponent's weaknesses (e.g., weak defense on the left side), the system suggests specific tactics to the player, such as "strengthen attack from the left side."

[0478] Step 5: Notification

[0479] The terminal displays the generated improvements and strategies to the player in real time and provides specific instructions. The input is the improvement and strategy suggestions, and the output is the notification to the player. Specific actions include:

[0480] Displaying Notifications: Displaying improvements and strategies to players through the user interface, for example, "Spend the next 10 minutes practicing to improve your reaction speed."

[0481] Gather feedback: By checking whether players have implemented the suggested training and tactics and collecting their feedback, we can provide more accurate analysis and recommendations.

[0482] (Application example 1)

[0483] 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."

[0484] Conventional systems were specialized in improving player performance, but their application was limited to sports and games, and they could not be adapted to improving or optimizing the work efficiency of robots in factories. In particular, there was a lack of technology that could evaluate robot work performance in real time and provide specific improvements and strategies, which made it difficult to establish efficient work processes.

[0485] 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.

[0486] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using a generative artificial intelligence (AI) that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, means for collecting robot task data, means for preprocessing the collected task data, means for performing real-time analysis using a generative AI that analyzes the preprocessed data and evaluating task performance, means for generating specific improvements and strategies to improve the robot's task efficiency based on the analysis results, and means for notifying the robot of the generated improvements and strategies, thereby enabling performance improvements for both the player and the robot.

[0487] "Player play data" refers to information related to the actions and operations performed by a player in a game or simulation, etc. This includes video data, audio data, operation history, etc.

[0488] "Preprocessing methods" refer to processes or techniques that transform raw data into a form suitable for analysis, such as data cleaning, frame segmentation, and feature extraction.

[0489] "Means for real-time analysis using generative artificial intelligence" refers to a process that uses generative artificial intelligence (AI) algorithms to analyze input data in real time and output results, allowing for immediate identification of data features and patterns.

[0490] "Improvement and strategy generation measures" refers to the process of generating specific performance improvement recommendations and strategies based on the analysis results, including operational improvement recommendations and tactical advice.

[0491] "Means of notifying players" refers to the methods used to communicate generated improvements and strategies to players, including display and audio messages.

[0492] "Robot work data" refers to information related to the movements and work that robots perform in factories, manufacturing sites, etc. This includes movement patterns, work results, sensor data, etc.

[0493] "Means of notifying the robot" refers to the methods of communicating generated improvements and strategies to the robot and having it adjust its operations, including sending control signals and updating its program.

[0494] The present invention relates to a system for improving the performance of players and robots. Specific embodiments for carrying out the present invention will be described below.

[0495] System Configuration

[0496] This system consists of the following main components:

[0497] 1. Data Collection Methods

[0498] 2. Data preprocessing methods

[0499] 3. Real-time analysis using generative artificial intelligence

[0500] 4. Improvements and Strategy Generation

[0501] 5. Means of notification

[0502] Data collection methods

[0503] The server collects the player's play data and the robot's work data. The player's play data includes video and audio data, which the user sends to the server via their device. The robot's work data is also obtained from sensors and cameras installed on the robot and sent to the server.

[0504] Data preprocessing measures

[0505] The server preprocesses the received data. This includes splitting the video data into frames, extracting features, and cleaning the data. This converts the data into a format suitable for analysis. For example, OpenCV is used to split the video data into frames, and Scikit-learn is used to extract features.

[0506] Real-time analysis using generative artificial intelligence

[0507] The server uses generative artificial intelligence (AI) to analyze player and robot data in real time. During the analysis process, the server evaluates the player's control patterns and the robot's performance to identify strengths and weaknesses. The AI ​​algorithms used here include TensorFlow and PyTorch.

[0508] Improvements and Strategy Generation Tools

[0509] The server generates specific improvements and strategies based on the results of real-time analysis. For example, it generates a training plan for the player to improve reaction speed, and suggests motion instructions for the robot to handle parts from a specific angle. It processes the analysis results using Pandas and NumPy to generate improvements and strategies.

[0510] Notification means

[0511] The server notifies the player and robot of the improvements and strategies that have been generated. The player is notified by display and voice message, and control signals are sent to the robot using ROS (Robot Operating System). The player and robot receive this notification and can immediately improve their playing style and work content.

[0512] Specific examples

[0513] 1. Real-time player analysis and feedback:

[0514] The player's play data is sent to a server in real time and analyzed by a generative AI model. As a result, it is determined that the player's reaction time is slower than other players, and an improvement plan is generated, such as "performing specific training for 10 minutes to improve reaction time."

[0515] Example prompt: "Suggest specific training to improve reaction speed."

[0516] 2. Robot performance analysis and improvement proposals:

[0517] The robot's work data is sent to a server in real time and analyzed by a generative AI model. As a result, it is determined that a particular part handling method is inefficient, and specific operational instructions such as "handle the part from a specific angle" are generated.

[0518] Example prompt: "Suggest the optimal working angle and speed for each type of part being handled."

[0519] As a result, the present invention provides a system for improving the performance of both the player and the robot.

[0520] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0521] Step 1:

[0522] The server collects player play data and robot operation data from the device. Input data includes video data, audio data, sensor data, etc. The collected data is stored on the server as raw data.

[0523] Step 2:

[0524] The server preprocesses the collected raw data. In this step, the video data is split into frames using OpenCV and features are extracted using Scikit-learn. The input is the frame-split video and audio data, and the output is data converted into a format suitable for analysis.

[0525] Step 3:

[0526] The server uses generative artificial intelligence to analyze preprocessed data in real time. It uses TensorFlow and PyTorch to evaluate the player's control patterns and the robot's work performance to identify strengths and weaknesses. The input is the preprocessed data, and the output is the analysis results.

[0527] Step 4:

[0528] The server generates specific improvements and strategies based on the analysis results. It processes the analysis results using Pandas and NumPy and makes suggestions to improve the performance of the player and robot. The input is the analysis results, and the output is improvements and strategies. For example, "specific training to improve reaction speed" or "motion instructions for handling parts from a specific angle" are generated.

[0529] Step 5:

[0530] The server notifies the player and robot of the generated improvements and strategies. The player is notified by displaying the improvements and voice messages, and the robot is sent control signals using ROS. The input is the generated improvements and strategies, and the output is a notification. The player and robot receive this notification and respond in real time.

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

[0532] This invention relates to an e-sports club activity support system that uses generative artificial intelligence and an emotion engine. This system collects and analyzes players' play data and emotional states, and provides them with optimal improvements and strategies. This system consists of a play data collection means, preprocessing means, real-time analysis means, improvement and strategy generation means, notification means, and an emotion engine that recognizes the user's emotions.

[0533] Explanation of program processing

[0534] Data collection

[0535] The device collects the player's gameplay video and audio data and transmits it to the server in real time. The collected data also includes information about the player's gameplay. The user also uploads the opponent's gameplay data, which the device then transmits to the server.

[0536] Data Preprocessing

[0537] The server preprocesses the video and audio data it receives, splitting the video data into frames and extracting features from the audio data. The server also preprocesses the opponent's data and converts it into a format suitable for analysis.

[0538] emotion recognition

[0539] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data, thereby recognizing their emotional state (e.g., stress, anxiety, concentration, etc.).

[0540] Real-time analytics

[0541] The server uses generative artificial intelligence to analyze the player's playing style and performance in real time, and also uses emotional information provided by the emotion engine to comprehensively evaluate the player's state.

[0542] Improvements and Strategy Generation

[0543] Based on the analysis results, the server generates specific improvements for the player. For example, if stress levels are high, it suggests ways to relax. It also generates strategies for dealing with opponents. For example, if an opponent is weak against attacks from the left, it suggests tactics to strengthen attacks from that direction.

[0544] notification

[0545] The device displays generated improvements and strategies to the player in real time, providing specific instructions and feedback in the form of voice and text.

[0546] Specific examples

[0547] Example 1: Real-time analysis and feedback of play

[0548] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. An emotion engine then analyzes the player's emotional state (for example, concentration and stress level). Based on the analysis results, it is determined that the player's reaction time is slower than other players and that they are under high stress. The server then generates an improvement plan, suggesting that the player "do 10 minutes of training to improve their reaction time and incorporate deep breathing exercises to reduce stress." The device then notifies the player of this improvement plan and supports their practice.

[0549] Example 2: Opponent data analysis and strategy suggestions

[0550] The user uploads a replay video of their opponent to their device, which then sends the data to the server. The server then preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. The system also takes into account the player's emotional state. For example, if the player is feeling anxious, the system will suggest a simple strategy to exploit the opponent's weaknesses. Specifically, the system generates a tactic such as "strengthen attacks from the left side," and notifies the player. This allows the player to take effective countermeasures.

[0551] In this way, the e-sports club activity support system, which combines generative artificial intelligence and an emotion engine, not only improves players' performance but also provides optimal improvements and strategies that take into account their emotional state.

[0552] The processing flow will be explained below.

[0553] Step 1:

[0554] The device collects the player's gameplay video and audio data and transmits it to the server in real time.

[0555] Step 2:

[0556] The user uploads the opponent's play data to the terminal, and the terminal transmits this data to the server.

[0557] Step 3:

[0558] The server divides the gameplay video data it receives into frames and extracts the necessary features, including analyzing the player's movement trajectory and attack timing.

[0559] Step 4:

[0560] The server preprocesses the received voice data and analyzes the tone and vocal patterns of the voice, which provides the basis for inferring the player's emotional state.

[0561] Step 5:

[0562] The server formats the opponent's data into a unified format and converts it into a form suitable for analysis.

[0563] Step 6:

[0564] The server uses an emotion engine to detect the player's emotional state from real-time video and audio data, for example, analyzing stress and concentration levels from facial expressions and voice tones.

[0565] Step 7:

[0566] The server uses generative artificial intelligence to analyze players' playstyles and performance in real time, including assessing their attack success rate, movement speed, reaction time, and more.

[0567] Step 8:

[0568] The server analyzes the opponent's playing style and tendencies to extract their strengths and weaknesses, thereby identifying their special moves and attack patterns.

[0569] Step 9:

[0570] The server will generate specific improvements for the player based on the analysis results, for example, if the player has a slow reaction time, it will suggest specific reflex training.

[0571] Step 10:

[0572] The server generates strategies for the opponent and proposes the optimal strategy taking into account the results of the emotion engine. For example, if the opponent is weak to attacks from the left side and the player is concentrating, the server proposes a tactic to strengthen attacks from the left side.

[0573] Step 11:

[0574] The device displays generated improvements and strategies to the player in real time, with specific instructions and advice provided via text and audio.

[0575] Step 12:

[0576] Users practice and play based on the improvements and strategies provided by the user. The server continuously collects new play data and emotional data, and the program is dynamically adjusted.

[0577] The above is the specific processing flow of the e-sports club activity support system that combines generative artificial intelligence and an emotion engine.

[0578] Example 2

[0579] 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."

[0580] While conventional e-sports club support systems were able to collect players' play data and generate improvements and strategies based on the analysis results, they were unable to recognize the players' emotional state in real time and incorporate that information into the analysis. This made it difficult to provide optimal feedback and strategies that took the players' mental state into account, preventing the maximum improvement of player performance.

[0581] 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. In this invention, the server includes means for collecting play data of players, means for pre-processing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the pre-processed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, and means including an emotion engine that analyzes the player's emotional state in real time. This enables analysis and feedback that takes the player's emotional state into consideration.

[0582] "Play data" refers to video data and audio data that includes information about the player's game operations.

[0583] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis, and includes splitting video data into frames and removing noise from audio data.

[0584] "Generative AI" refers to artificial intelligence technology that analyzes collected data in real time and generates improvements and strategies for players.

[0585] "Emotion engine" refers to technology that analyzes the player's emotional state in real time from video and audio data.

[0586] "Areas for Improvement" refers to specific actions or training methods recommended to improve a player's performance.

[0587] "Strategy" refers to specific tactics proposed to players based on the characteristics and weaknesses of their opponents.

[0588] "Notification" refers to the act of communicating generated improvements and strategies to players in audio or text format.

[0589] This invention relates to an e-sports club activity support system that uses generative artificial intelligence and an emotion engine. This system collects and analyzes players' play data and emotional states, and provides them with optimal improvements and strategies. This system consists of a play data collection means, a preprocessing means, a real-time analysis means, a means for generating improvements and strategies, a notification means, and an emotion engine that recognizes the user's emotions.

[0590] The device collects the player's gameplay video and audio data and sends it to the server in real time. The device is equipped with a high-resolution camera and microphone, which capture data using this hardware. The collected data also includes information about the player's game operations (keyboard and mouse input). The user also uploads their opponent's gameplay data to the device, which then sends this data to the server.

[0591] The server preprocesses the video and audio data it receives. It divides the video data into frames and extracts features from the audio data. The opponent's data is also preprocessed and converted into a format suitable for analysis. For video data, the video is divided into a set number of frames and important features are extracted using an image processing algorithm. For audio data, background noise and other noise are removed to obtain clear audio information.

[0592] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data, including facial expression analysis and tone of voice analysis, to accurately recognize the player's emotional state (stress, anxiety, concentration, etc.).

[0593] The server uses a generative artificial intelligence (AI) model to analyze the player's playing style and performance in real time. Based on in-game movements and input information, the server evaluates the player's performance indicators (reaction speed, accuracy, decision-making ability). In addition, it integrates emotional information provided by an emotion engine to comprehensively evaluate the player's state.

[0594] Based on the analysis results, the server generates specific suggestions for improvement for the player, such as "Spend 10 minutes of training to improve your reaction speed" or "Take deep breaths to reduce stress." Analyzing the opponent's data, the server generates strategies such as "Your opponent is weak against attacks from the left, so strengthen your attacks from the left."

[0595] The device displays generated improvements and strategies to the player in real time, using on-screen pop-ups and audio notifications to provide specific advice and feedback to the player. For example, the following prompts are available:

[0596] "Your reaction time is slow, so do 10 minutes of training. Incorporating deep breathing techniques can also help reduce stress."

[0597] "Your opponent is weak to attacks from the left, so strengthen your attacks from the left."

[0598] This system not only improves players' performance but also provides optimal improvements and strategies that take into account their emotional state. As a result, players can take effective measures and properly manage their mental state, thereby supporting them in achieving their best performance.

[0599] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0600] Step 1: Data collection

[0601] The device collects video and audio data of the player's gameplay. A high-resolution camera and microphone connected to the device capture video and audio data in real time. It also collects log data of the player's game operations (keyboard and mouse input). This data is sent to the server in real time. Input: video data, audio data, operation log. Output: raw data set sent to the server.

[0602] Step 2: Gather opponent data

[0603] The user uploads the opponent's play data (such as a replay video) to their device. The device detects this and sends the video data to the server. Input: Replay video of the opponent. Output: Data of the opponent sent to the server.

[0604] Step 3: Data Preprocessing

[0605] The server preprocesses the video and audio data it receives. Specifically, it divides the video data into frames and extracts important features from each frame. It also removes noise from the audio data and extracts features. The opponent's data is similarly preprocessed and converted into a format suitable for analysis. Input: Raw play data and opponent data. Output: Preprocessed dataset.

[0606] Step 4: Emotion Recognition

[0607] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data. By analyzing their facial expressions and tone of voice, it can recognize their stress, anxiety, concentration, etc. Input: Preprocessed video and audio data. Output: Player's emotional state data.

[0608] Step 5: Real-time analysis

[0609] The server uses a generative artificial intelligence (AI) model to analyze the player's playing style and performance in real time. Based on in-game movements and input information, the server evaluates the player's performance indicators (reaction speed, accuracy, decision-making ability). At the same time, it integrates emotional information provided by the emotion engine to comprehensively evaluate the player's state. Input: Preprocessed dataset, emotional state data. Output: Analysis result data.

[0610] Step 6: Improvements and strategy generation

[0611] Based on the analysis results, the server generates specific areas for improvement and strategies for the player. For example, if a player's reaction time is slow, it will suggest "Let's practice for 10 minutes to improve our reaction time." It will also generate strategies for the opponent, proposing tactics to exploit the opponent's weaknesses (for example, weakness to attacks from the left side). Input: Analysis result data. Output: Data on areas for improvement and strategies.

[0612] Step 7: Notification

[0613] The device displays the generated improvements and strategies to the player in real time. Specific advice and feedback is provided during play and practice via on-screen pop-ups and voice notifications. For example, "Your reaction time is slow, so practice for 10 minutes. Deep breathing can also help reduce stress," or "Your opponent is weak against attacks from the left side, so strengthen your attacks from the left side." Input: Data on improvements and strategies. Output: Feedback notified to the player.

[0614] (Application example 2)

[0615] 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."

[0616] Existing e-sports club activity support systems collect players' play data and emotional state and provide improvements and strategies based on that data. However, they have not yet been applied to industrial applications such as improving the efficiency of robotic work in factories or detecting anomalies. Factories require real-time analysis of robot operation data and information about the work environment to identify efficient work methods and detect anomalies early, but no effective system exists for this purpose. Therefore, technology is needed to improve the efficiency of robotic work in factories and detect anomalies.

[0617] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0618] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, means for collecting, preprocessing, and analyzing robot operation data, means for generating efficient work methods and strategies for the robot based on the analysis results, and means for notifying factory staff of the generated work methods and strategies, thereby enabling efficient robot work in factories and abnormality detection.

[0619] "Play data" refers to information related to the actions and operations of a player or robot, and includes video data and audio data.

[0620] "Preprocessing" refers to the process of converting collected play data and action data into a format suitable for analysis, and includes dividing the data into frames and extracting features.

[0621] "Generative AI" is an artificial intelligence technology used to generate improvements and strategies based on collected and pre-processed data, analyzed in real time.

[0622] "Real-time analysis" is a process that involves collecting and analyzing data without any time delay, and provides immediate evaluation and suggestions based on operating conditions and emotional state.

[0623] "Improvements and strategies" are specific guidelines and tactics for improving the performance of the player or robot based on the analysis results.

[0624] "Notification" is an action that notifies the user of generated improvements or strategies, and is provided in audio or text format.

[0625] "Operation data" refers to data that includes information such as the operating status of the robot, the success or failure of the operation, error information, and the working speed.

[0626] "Efficient work methods" are specific techniques and procedures for maximizing the work efficiency of robots, and are derived using generative artificial intelligence.

[0627] "Anomaly detection" is the process of detecting abnormal behavior or conditions that deviate from normal operating conditions, and is important for maintaining safety and efficiency.

[0628] "Factory staff" refers to the people who operate and monitor robots in the factory and who are notified of the generated work methods and strategies.

[0629] System Configuration

[0630] The system includes the following means:

[0631] 1. Means of collecting player and robot behavior data

[0632] 2. Means of preprocessing the collected data

[0633] 3. A means of real-time analysis using generative artificial intelligence to analyze pre-processed data

[0634] 4. A means of generating improvements and strategies for players and robots based on the analysis results.

[0635] 5. A means to inform generated improvements and strategies

[0636] Program processing explanation

[0637] Hardware

[0638] Smartphone: Collects player and robot movement data (video and audio) and sends it to the server.

[0639] Cloud Server: The main computing resource for data analysis and strategy generation.

[0640] software

[0641] OpenCV: Used for preprocessing video data and frame segmentation.

[0642] Generative artificial intelligence models: Used for data analysis and strategy generation.

[0643] EmotionAnalyzer: Used to analyze emotional states.

[0644] Operation flow

[0645] 1. Data collection: A smartphone collects video and audio data of the player and robot's movements in real time. The video data is divided into frames, and features are extracted from the audio data in the same way.

[0646] 2. Preprocessing: The cloud server divides the video data into frames and extracts features from the audio data, converting the data into a format suitable for analysis.

[0647] 3. Emotion Recognition: The cloud server uses the EmotionAnalyzer to analyze the emotional state of the player and robot, thereby recognizing emotional states such as stress and concentration.

[0648] 4. Real-time analysis: A cloud server uses generative artificial intelligence to analyze player and robot behavior data in real time, including emotional state information.

[0649] 5. Improvements and Strategy Generation: Based on the analysis results, the cloud server generates specific improvements and strategies for players and robots. For example, it can propose specific methods to improve work efficiency.

[0650] 6. Notification: Smartphones will notify players and factory staff of generated improvements and strategies in voice and text format.

[0651] Specific examples

[0652] If a specific player is experiencing high stress

[0653] The system collects video and audio data from the player and uses the Emotion Analyzer to detect high stress levels. Generative AI takes this information into account and generates specific improvements to reduce stress (e.g., practicing deep breathing). The player is notified of this via their smartphone.

[0654] When there are many errors in the robot's work

[0655] The system collects data on the robot's operations and uses generative artificial intelligence to analyze its movements in real time. If it determines that frequent errors are due to human error, it generates efficient work methods (e.g., changing the order of certain operations) and notifies factory staff via their smartphones.

[0656] Prompt Sentence Examples

[0657] Analyze the operation data of a factory robot and propose ways to improve the error rate and work efficiency of specific tasks in real time. Also, evaluate the emotional state of the robot through its actions and detect anomalies.

[0658] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0659] Step 1:

[0660] Data collection

[0661] The device collects video and audio data of the player and robot's movements. Specifically, the smartphone captures video data through the camera and audio data through the microphone. This data is sent to the server in real time.

[0662] Input: Video data, audio data

[0663] Output: Raw data stored on the server

[0664] Step 2:

[0665] Pretreatment

[0666] The server preprocesses the video and audio data it receives. The video data is split into frames, and features (e.g., frequency components) are extracted from the audio data. OpenCV is used to split the video data into frames, and a Python audio processing library is used to preprocess the audio data.

[0667] Input: Raw data stored on the server

[0668] Output: Preprocessed frame-by-frame video data, feature-extracted audio data

[0669] Step 3:

[0670] emotion recognition

[0671] The server uses an emotion engine (EmotionAnalyzer) to analyze the emotional state of the player or robot from pre-processed video and audio data. Specifically, the emotional state (e.g., concentration, stress) is recognized by analyzing facial expressions and tone of voice.

[0672] Input: Preprocessed frame-by-frame video data, feature-extracted audio data

[0673] Output: Emotional state information (concentration, stress level, etc.)

[0674] Step 4:

[0675] Real-time analytics

[0676] The server analyzes the pre-processed data and emotional state information using a generative artificial intelligence model, which evaluates the movement performance of the player and robot and determines efficient tasks and playing styles.

[0677] Input: Preprocessed data, emotional state information

[0678] Output: Performance evaluation results

[0679] Step 5:

[0680] Improvements and Strategy Generation

[0681] Based on the analysis results, the server generates specific improvements and strategies for the player and robot. For example, if it detects high stress levels, it will suggest relaxation methods, and if the robot is making a lot of errors, it will suggest changes to its operation procedures.

[0682] Input: Performance evaluation results

[0683] Output: Improvements and strategies

[0684] Step 6:

[0685] notification

[0686] The device notifies players and factory staff of the improvements and strategies received from the server. Specifically, the smartphone displays and announces the improvements and strategies in voice and text format.

[0687] Input: Improvements and Strategies

[0688] Output: Notification to players and factory staff

[0689] 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.

[0690] 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.

[0691] 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.

[0692] [Third embodiment]

[0693] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0694] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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."

[0705] This invention relates to an e-sports club activity support system that uses generative artificial intelligence. The purpose of this system is to collect and analyze players' play data and provide them with specific improvements and strategies. This system consists of a collection means, a pre-processing means, a real-time analysis means, a means for generating improvements and strategies, and a notification means.

[0706] Explanation of program processing

[0707] 1. Data Collection

[0708] The device collects the player's video and audio data, which is then sent to the server in real time. Furthermore, the user uploads their opponent's gameplay data, which is then sent to the server by the device.

[0709] 2. Data Preprocessing

[0710] The server preprocesses the received video and audio data and converts it into a format suitable for analysis. This preprocessing includes splitting the video data into frames and extracting features. The opponent's data is also preprocessed in the same way.

[0711] 3. Real-time analysis

[0712] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time, identifying their strengths and weaknesses. Opponents' data is also analyzed to extract their playing styles and tendencies.

[0713] 4. Improvements and Strategy Generation

[0714] Based on the analysis results, the server generates specific improvements for the player. For example, if a player's reaction time is slow, it will suggest training to improve their reaction time. It will also generate effective strategies against the opponent. For example, if the opponent is weak against attacks from the left, it will suggest tactics to strengthen attacks from that direction.

[0715] 5. Notification

[0716] The device displays the generated improvements and strategies to the player in real time and provides specific instructions, such as "Practice strengthening your attacks from the left side." This allows the player to instantly improve their playing style.

[0717] Specific examples

[0718] Example 1: Real-time analysis and feedback of play

[0719] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. Based on the analysis results, it is determined that the player's reaction time is slower than other players. The server then generates an improvement plan, suggesting that the player "perform specific training for 10 minutes to improve their reaction time." The device then notifies the player of this improvement plan and supports their practice.

[0720] Example 2: Opponent data analysis and strategy suggestions

[0721] The user uploads the replay video of their opponent to their device, and the device sends this data to the server. The server preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. For example, it learns that the opponent is weak against left-sided defense. The server generates a specific strategy, such as "strengthen attacks from the left side," and the device notifies the player. This allows the player to take effective countermeasures.

[0722] In this way, the e-sports club activity support system that uses generative artificial intelligence provides specific improvements and strategies to improve players' performance, supporting efficient practice and growth.

[0723] The processing flow will be explained below.

[0724] Step 1:

[0725] The device collects the player's gameplay video and audio data and transmits it to the server in real time.

[0726] Step 2:

[0727] The user uploads the opponent's play data to the terminal, and the terminal transmits this data to the server.

[0728] Step 3:

[0729] The server divides the received play data into frames and extracts the necessary video and audio features, specifically identifying the player's movement trajectory and attack timing.

[0730] Step 4:

[0731] The server formats the opponent's data into a unified format that can be analyzed, making it easier to analyze the opponent's behavior patterns.

[0732] Step 5:

[0733] The server uses generative artificial intelligence to analyze the player's playing style in real time, specifically assessing the player's attack success rate, movement speed, and reaction time to identify their strengths and weaknesses.

[0734] Step 6:

[0735] The server analyzes the opponent's playing style and tendencies, extracting their strengths, weaknesses, and favorite techniques.

[0736] Step 7:

[0737] Based on the analysis, the server generates specific improvements for the player, such as suggesting training to improve reaction speed.

[0738] Step 8:

[0739] The server generates strategies for the opponent. For example, if the opponent is weak to attacks from the left, it will suggest tactics to strengthen attacks from that direction.

[0740] Step 9:

[0741] The device displays generated improvements and strategies to the player in real time, and provides specific instructions and advice via text and voice.

[0742] Step 10:

[0743] Users practice and play based on the improvements and strategies provided by the user. The server collects new play data again and performs repeated processing to improve the player's performance.

[0744] The above is the specific processing flow of the e-sports club activity support system using generative artificial intelligence.

[0745] Example 1

[0746] 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."

[0747] Traditionally, practice and preparation for esports have relied primarily on the experience and intuition of players. This has made it difficult to find efficient practice methods and specific strategies for matches. In particular, improving a player's performance and analyzing their opponents takes time and effort, making it difficult to immediately identify areas for improvement or strategies.

[0748] 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.

[0749] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, and means and methods for collecting video data and audio data as player play data and preprocessing them, thereby enabling players to quickly and efficiently receive specific advice and battle strategies to improve their own playing style.

[0750] "Play data" is a general term for video data and audio data generated while a player is playing a game.

[0751] "Means for collection" refers to the equipment and methods for acquiring gameplay data and transmitting it to the server, including capture devices and microphones, as well as data streaming protocols.

[0752] "Preprocessing means" refers to the techniques and methods used to convert collected gameplay data into a format suitable for analysis. Specifically, this includes frame division and feature extraction of video data, and spectral analysis of audio data.

[0753] "Generative artificial intelligence" refers to artificial intelligence technology that can generate new information and patterns from input data using techniques such as deep learning.

[0754] "Means for real-time analysis" refers to systems and algorithms that use generative artificial intelligence to instantly analyze play data.

[0755] "Means for generating improvements and strategies" refers to techniques and methods for devising specific improvements and playing strategies for players based on the analysis results.

[0756] "Means of notification" refers to the techniques and methods used to communicate generated improvements and strategies to players, including user interfaces and notification systems.

[0757] "Video Data" refers to the sequence of image frames captured during gameplay.

[0758] "Audio Data" refers to audio information recorded during game play.

[0759] "Opponent's play data" refers to video data and audio data related to the gameplay of the opponent against whom the player is playing.

[0760] "Competitive strategy" refers to specific methods and tactics for analyzing an opponent's playing style and weaknesses and devising effective countermeasures.

[0761] The present invention relates to an e-sports club activity support system that uses generative artificial intelligence. The purpose of this system is to collect and analyze players' play data and provide them with specific improvements and strategies. The following describes in detail the embodiments of the present invention.

[0762] This system consists of a collection means, a pre-processing means, a real-time analysis means, a means for generating improvements and strategies, and a means for notification. To realize these means, various software libraries and protocols are utilized.

[0763] Collection Method

[0764] The device collects the player's gameplay video and audio data. Specifically, it uses a dedicated capture device and microphone to capture data during gameplay. The captured data is sent to the server in real time. RTMP (Real-Time Messaging Protocol) is used for data streaming. Furthermore, the user uploads their opponent's gameplay data via a web interface, and the device uses an HTTP request to send this data to the server.

[0765] Pretreatment means

[0766] The server pre-processes the received video and audio data and converts it into a format suitable for analysis. The pre-processing includes the following specific steps:

[0767] Video data frame division: Video data is divided into frames using the OpenCV library.

[0768] Feature extraction: Extract keyframes from multiple frames and extract features (edges, motion, color, etc.) from those frames.

[0769] Spectral analysis of audio data: Using the Librosa library, we extract spectral features from audio data, which prepares us to analyze important sounds in the game (e.g., footsteps to determine enemy positions).

[0770] Real-time analysis tools

[0771] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time, including the following techniques:

[0772] Utilizing deep learning models: Analyzing player play data using models created using TensorFlow and PyTorch. For example, using models such as ResNet and Transformers, we evaluate player behavior patterns and reaction times.

[0773] Identifying strengths and weaknesses: The analysis results output by the model identify a player's strengths (e.g., high accuracy shooting) and weaknesses (e.g., slow reaction time).

[0774] Opponent Playstyle Analysis: Using the same generative AI, we analyze your opponents' movements to find their most frequently used tactics and weaknesses.

[0775] Improvements and Strategy Generation Tools

[0776] The server generates specific improvements for the player based on the analysis, including specific actions such as:

[0777] Suggestions for improvement: For example, if the analysis shows that a player has a slow reaction time, we will suggest specific training exercises (such as reflex training games) to improve that speed.

[0778] Strategy Generation: Generate tactics based on the opponent's weaknesses. For example, if the opponent is weak to attacks from the left, the system will suggest a specific tactic to the player: "Strengthen attacks from the left side."

[0779] Notification means

[0780] The device will display generated improvements and strategies to the player in real time and provide specific instructions, including the following specific actions:

[0781] Displaying Notifications: Displaying specific advice or tactics to players through the user interface (UI), such as "Spend the next 10 minutes training to improve your reaction speed."

[0782] Get feedback: See if players have implemented the suggested training or tactics and gather feedback.

[0783] Specific examples

[0784] Example 1: Real-time analysis and feedback of play

[0785] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. For example, it may identify that the player's reaction time is slower than other players. The server then generates an improvement plan, such as "perform specific training for 10 minutes to improve reaction time." The device then notifies the player of this improvement plan and supports their practice.

[0786] Example 2: Opponent data analysis and strategy suggestions

[0787] The user uploads the replay video of their opponent to their device, and the device sends this data to the server. The server preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. For example, it learns that the opponent is weak against left-sided defense. The server generates a specific strategy, such as "strengthen attacks from the left side," and the device notifies the player. This allows the player to take effective countermeasures.

[0788] Prompt example (play data analysis)

[0789] input:

[0790] "Analyze player A's play data and evaluate his reaction time and shooting accuracy. Player B's (opponent's) play data is also provided, so find his weaknesses and propose effective strategies."

[0791] output:

[0792] "Player A's reaction time is 20% slower than average. They have good shooting accuracy, but their accuracy decreases while moving."

[0793] "Your opponent's data has identified a weakness to attacks from the left. Employ tactics that strengthen attacks from the left."

[0794] In this way, generative AI models can be used to provide detailed and specific playstyle improvements and strategy suggestions.

[0795] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0796] Step 1: Data collection

[0797] The device collects the player's gameplay video and audio data. Specifically, it captures video and audio during gameplay in real time using a capture device or microphone. The input is the player's gameplay data, and the output is the collected video and audio data. The collected data is sent to the server using the RTMP protocol. The user can also upload their opponent's gameplay data via a web interface, and the device sends this data to the server via an HTTP request.

[0798] Step 2: Data Preprocessing

[0799] The server preprocesses the video and audio data it receives and converts it into a format suitable for analysis. The input is raw data sent via RTMP or HTTP, and the output is preprocessed data. Specific operations include:

[0800] Video data frame division: Use the OpenCV library to divide the video data into frames and extract keyframes.

[0801] Feature extraction: Extract features such as edges, motion, and color from each keyframe.

[0802] Spectral analysis of audio data: We use the Librosa library to extract spectral features from audio data, which prepares us for analyzing important sounds in the game (e.g., enemy footsteps).

[0803] Step 3: Real-time analysis

[0804] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time. The input is pre-processed data, and the output is the analysis results. Specific operations include:

[0805] Utilizing deep learning models: Using models created using TensorFlow or PyTorch (e.g., ResNet or Transformers), we evaluate players' behavioral patterns and reaction times.

[0806] Identifying strengths and weaknesses: The strengths and weaknesses of players are extracted from the analysis results output by the model.

[0807] Opponent Playstyle Analysis: Similarly, generative AI is used to analyze opponents' movement patterns, weaknesses, and strategies.

[0808] Step 4: Improvements and strategy generation

[0809] The server generates specific improvements and strategies for the player based on the analysis results. The input is the analysis results, and the output is suggested improvements and strategies. Specific operations include:

[0810] Suggestions for improvement: For example, if your reaction time is slower than other players, we will suggest specific training exercises to improve your reaction time.

[0811] Strategy generation: Based on the opponent's weaknesses (e.g., weak defense on the left side), the system suggests specific tactics to the player, such as "strengthen attack from the left side."

[0812] Step 5: Notification

[0813] The terminal displays the generated improvements and strategies to the player in real time and provides specific instructions. The input is the improvement and strategy suggestions, and the output is the notification to the player. Specific actions include:

[0814] Displaying Notifications: Displaying improvements and strategies to players through the user interface, for example, "Spend the next 10 minutes practicing to improve your reaction speed."

[0815] Gather feedback: By checking whether players have implemented the suggested training and tactics and collecting their feedback, we can provide more accurate analysis and recommendations.

[0816] (Application example 1)

[0817] 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."

[0818] Conventional systems were specialized in improving player performance, but their application was limited to sports and games, and they could not be adapted to improving or optimizing the work efficiency of robots in factories. In particular, there was a lack of technology that could evaluate robot work performance in real time and provide specific improvements and strategies, which made it difficult to establish efficient work processes.

[0819] 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.

[0820] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using a generative artificial intelligence (AI) that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, means for collecting robot task data, means for preprocessing the collected task data, means for performing real-time analysis using a generative AI that analyzes the preprocessed data and evaluating task performance, means for generating specific improvements and strategies to improve the robot's task efficiency based on the analysis results, and means for notifying the robot of the generated improvements and strategies, thereby enabling performance improvements for both the player and the robot.

[0821] "Player play data" refers to information related to the actions and operations performed by a player in a game or simulation, etc. This includes video data, audio data, operation history, etc.

[0822] "Preprocessing methods" refer to processes or techniques that transform raw data into a form suitable for analysis, such as data cleaning, frame segmentation, and feature extraction.

[0823] "Means for real-time analysis using generative artificial intelligence" refers to a process that uses generative artificial intelligence (AI) algorithms to analyze input data in real time and output results, allowing for immediate identification of data features and patterns.

[0824] "Improvement and strategy generation measures" refers to the process of generating specific performance improvement recommendations and strategies based on the analysis results, including operational improvement recommendations and tactical advice.

[0825] "Means of notifying players" refers to the methods used to communicate generated improvements and strategies to players, including display and audio messages.

[0826] "Robot work data" refers to information related to the movements and work that robots perform in factories, manufacturing sites, etc. This includes movement patterns, work results, sensor data, etc.

[0827] "Means of notifying the robot" refers to the methods of communicating generated improvements and strategies to the robot and having it adjust its operations, including sending control signals and updating its program.

[0828] The present invention relates to a system for improving the performance of players and robots. Specific embodiments for carrying out the present invention will be described below.

[0829] System Configuration

[0830] This system consists of the following main components:

[0831] 1. Data Collection Methods

[0832] 2. Data preprocessing methods

[0833] 3. Real-time analysis using generative artificial intelligence

[0834] 4. Improvements and Strategy Generation

[0835] 5. Means of notification

[0836] Data collection methods

[0837] The server collects the player's play data and the robot's work data. The player's play data includes video and audio data, which the user sends to the server via their device. The robot's work data is also obtained from sensors and cameras installed on the robot and sent to the server.

[0838] Data preprocessing measures

[0839] The server preprocesses the received data. This includes splitting the video data into frames, extracting features, and cleaning the data. This converts the data into a format suitable for analysis. For example, OpenCV is used to split the video data into frames, and Scikit-learn is used to extract features.

[0840] Real-time analysis using generative artificial intelligence

[0841] The server uses generative artificial intelligence (AI) to analyze player and robot data in real time. During the analysis process, the server evaluates the player's control patterns and the robot's performance to identify strengths and weaknesses. The AI ​​algorithms used here include TensorFlow and PyTorch.

[0842] Improvements and Strategy Generation Tools

[0843] The server generates specific improvements and strategies based on the results of real-time analysis. For example, it generates a training plan for the player to improve reaction speed, and suggests motion instructions for the robot to handle parts from a specific angle. It processes the analysis results using Pandas and NumPy to generate improvements and strategies.

[0844] Notification means

[0845] The server notifies the player and robot of the improvements and strategies that have been generated. The player is notified by display and voice message, and control signals are sent to the robot using ROS (Robot Operating System). The player and robot receive this notification and can immediately improve their playing style and work content.

[0846] Specific examples

[0847] 1. Real-time player analysis and feedback:

[0848] The player's play data is sent to a server in real time and analyzed by a generative AI model. As a result, it is determined that the player's reaction time is slower than other players, and an improvement plan is generated, such as "performing specific training for 10 minutes to improve reaction time."

[0849] Example prompt: "Suggest specific training to improve reaction speed."

[0850] 2. Robot performance analysis and improvement proposals:

[0851] The robot's work data is sent to a server in real time and analyzed by a generative AI model. As a result, it is determined that a particular part handling method is inefficient, and specific operational instructions such as "handle the part from a specific angle" are generated.

[0852] Example prompt: "Suggest the optimal working angle and speed for each type of part being handled."

[0853] As a result, the present invention provides a system for improving the performance of both the player and the robot.

[0854] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0855] Step 1:

[0856] The server collects player play data and robot operation data from the device. Input data includes video data, audio data, sensor data, etc. The collected data is stored on the server as raw data.

[0857] Step 2:

[0858] The server preprocesses the collected raw data. In this step, the video data is split into frames using OpenCV and features are extracted using Scikit-learn. The input is the frame-split video and audio data, and the output is data converted into a format suitable for analysis.

[0859] Step 3:

[0860] The server uses generative artificial intelligence to analyze preprocessed data in real time. It uses TensorFlow and PyTorch to evaluate the player's control patterns and the robot's work performance to identify strengths and weaknesses. The input is the preprocessed data, and the output is the analysis results.

[0861] Step 4:

[0862] The server generates specific improvements and strategies based on the analysis results. It processes the analysis results using Pandas and NumPy and makes suggestions to improve the performance of the player and robot. The input is the analysis results, and the output is improvements and strategies. For example, "specific training to improve reaction speed" or "motion instructions for handling parts from a specific angle" are generated.

[0863] Step 5:

[0864] The server notifies the player and robot of the generated improvements and strategies. The player is notified by displaying the improvements and voice messages, and the robot is sent control signals using ROS. The input is the generated improvements and strategies, and the output is a notification. The player and robot receive this notification and respond in real time.

[0865] 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.

[0866] This invention relates to an e-sports club activity support system that uses generative artificial intelligence and an emotion engine. This system collects and analyzes players' play data and emotional states, and provides them with optimal improvements and strategies. This system consists of a play data collection means, preprocessing means, real-time analysis means, improvement and strategy generation means, notification means, and an emotion engine that recognizes the user's emotions.

[0867] Explanation of program processing

[0868] Data collection

[0869] The device collects the player's gameplay video and audio data and transmits it to the server in real time. The collected data also includes information about the player's gameplay. The user also uploads the opponent's gameplay data, which the device then transmits to the server.

[0870] Data Preprocessing

[0871] The server preprocesses the video and audio data it receives, splitting the video data into frames and extracting features from the audio data. The server also preprocesses the opponent's data and converts it into a format suitable for analysis.

[0872] emotion recognition

[0873] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data, thereby recognizing their emotional state (e.g., stress, anxiety, concentration, etc.).

[0874] Real-time analytics

[0875] The server uses generative artificial intelligence to analyze the player's playing style and performance in real time, and also uses emotional information provided by the emotion engine to comprehensively evaluate the player's state.

[0876] Improvements and Strategy Generation

[0877] Based on the analysis results, the server generates specific improvements for the player. For example, if stress levels are high, it suggests ways to relax. It also generates strategies for dealing with opponents. For example, if an opponent is weak against attacks from the left, it suggests tactics to strengthen attacks from that direction.

[0878] notification

[0879] The device displays generated improvements and strategies to the player in real time, providing specific instructions and feedback in the form of voice and text.

[0880] Specific examples

[0881] Example 1: Real-time analysis and feedback of play

[0882] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. An emotion engine then analyzes the player's emotional state (for example, concentration and stress level). Based on the analysis results, it is determined that the player's reaction time is slower than other players and that they are under high stress. The server then generates an improvement plan, suggesting that the player "do 10 minutes of training to improve their reaction time and incorporate deep breathing exercises to reduce stress." The device then notifies the player of this improvement plan and supports their practice.

[0883] Example 2: Opponent data analysis and strategy suggestions

[0884] The user uploads a replay video of their opponent to their device, which then sends the data to the server. The server then preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. The system also takes into account the player's emotional state. For example, if the player is feeling anxious, the system will suggest a simple strategy to exploit the opponent's weaknesses. Specifically, the system generates a tactic such as "strengthen attacks from the left side," and notifies the player. This allows the player to take effective countermeasures.

[0885] In this way, the e-sports club activity support system, which combines generative artificial intelligence and an emotion engine, not only improves players' performance but also provides optimal improvements and strategies that take into account their emotional state.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] The device collects the player's gameplay video and audio data and transmits it to the server in real time.

[0889] Step 2:

[0890] The user uploads the opponent's play data to the terminal, and the terminal transmits this data to the server.

[0891] Step 3:

[0892] The server divides the gameplay video data it receives into frames and extracts the necessary features, including analyzing the player's movement trajectory and attack timing.

[0893] Step 4:

[0894] The server preprocesses the received voice data and analyzes the tone and vocal patterns of the voice, which provides the basis for inferring the player's emotional state.

[0895] Step 5:

[0896] The server formats the opponent's data into a unified format and converts it into a form suitable for analysis.

[0897] Step 6:

[0898] The server uses an emotion engine to detect the player's emotional state from real-time video and audio data, for example, analyzing stress and concentration levels from facial expressions and voice tones.

[0899] Step 7:

[0900] The server uses generative artificial intelligence to analyze players' playstyles and performance in real time, including assessing their attack success rate, movement speed, reaction time, and more.

[0901] Step 8:

[0902] The server analyzes the opponent's playing style and tendencies to extract their strengths and weaknesses, thereby identifying their special moves and attack patterns.

[0903] Step 9:

[0904] The server will generate specific improvements for the player based on the analysis results, for example, if the player has a slow reaction time, it will suggest specific reflex training.

[0905] Step 10:

[0906] The server generates strategies for the opponent and proposes the optimal strategy taking into account the results of the emotion engine. For example, if the opponent is weak to attacks from the left side and the player is concentrating, the server proposes a tactic to strengthen attacks from the left side.

[0907] Step 11:

[0908] The device displays generated improvements and strategies to the player in real time, with specific instructions and advice provided via text and audio.

[0909] Step 12:

[0910] Users practice and play based on the improvements and strategies provided by the user. The server continuously collects new play data and emotional data, and the program is dynamically adjusted.

[0911] The above is the specific processing flow of the e-sports club activity support system that combines generative artificial intelligence and an emotion engine.

[0912] Example 2

[0913] 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."

[0914] While conventional e-sports club support systems were able to collect players' play data and generate improvements and strategies based on the analysis results, they were unable to recognize the players' emotional state in real time and incorporate that information into the analysis. This made it difficult to provide optimal feedback and strategies that took the players' mental state into account, preventing the maximum improvement of player performance.

[0915] 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. In this invention, the server includes means for collecting play data of players, means for pre-processing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the pre-processed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, and means including an emotion engine that analyzes the player's emotional state in real time. This enables analysis and feedback that takes the player's emotional state into consideration.

[0916] "Play data" refers to video data and audio data that includes information about the player's game operations.

[0917] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis, and includes splitting video data into frames and removing noise from audio data.

[0918] "Generative AI" refers to artificial intelligence technology that analyzes collected data in real time and generates improvements and strategies for players.

[0919] "Emotion engine" refers to technology that analyzes the player's emotional state in real time from video and audio data.

[0920] "Areas for Improvement" refers to specific actions or training methods recommended to improve a player's performance.

[0921] "Strategy" refers to specific tactics proposed to players based on the characteristics and weaknesses of their opponents.

[0922] "Notification" refers to the act of communicating generated improvements and strategies to players in audio or text format.

[0923] This invention relates to an e-sports club activity support system that uses generative artificial intelligence and an emotion engine. This system collects and analyzes players' play data and emotional states, and provides them with optimal improvements and strategies. This system consists of a play data collection means, a preprocessing means, a real-time analysis means, a means for generating improvements and strategies, a notification means, and an emotion engine that recognizes the user's emotions.

[0924] The device collects the player's gameplay video and audio data and sends it to the server in real time. The device is equipped with a high-resolution camera and microphone, which capture data using this hardware. The collected data also includes information about the player's game operations (keyboard and mouse input). The user also uploads their opponent's gameplay data to the device, which then sends this data to the server.

[0925] The server preprocesses the video and audio data it receives. It divides the video data into frames and extracts features from the audio data. The opponent's data is also preprocessed and converted into a format suitable for analysis. For video data, the video is divided into a set number of frames and important features are extracted using an image processing algorithm. For audio data, background noise and other noise are removed to obtain clear audio information.

[0926] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data, including facial expression analysis and tone of voice analysis, to accurately recognize the player's emotional state (stress, anxiety, concentration, etc.).

[0927] The server uses a generative artificial intelligence (AI) model to analyze the player's playing style and performance in real time. Based on in-game movements and input information, the server evaluates the player's performance indicators (reaction speed, accuracy, decision-making ability). In addition, it integrates emotional information provided by an emotion engine to comprehensively evaluate the player's state.

[0928] Based on the analysis results, the server generates specific suggestions for improvement for the player, such as "Spend 10 minutes of training to improve your reaction speed" or "Take deep breaths to reduce stress." Analyzing the opponent's data, the server generates strategies such as "Your opponent is weak against attacks from the left, so strengthen your attacks from the left."

[0929] The device displays generated improvements and strategies to the player in real time, using on-screen pop-ups and audio notifications to provide specific advice and feedback to the player. For example, the following prompts are available:

[0930] "Your reaction time is slow, so do 10 minutes of training. Incorporating deep breathing techniques can also help reduce stress."

[0931] "Your opponent is weak to attacks from the left, so strengthen your attacks from the left."

[0932] This system not only improves players' performance but also provides optimal improvements and strategies that take into account their emotional state. As a result, players can take effective measures and properly manage their mental state, thereby supporting them in achieving their best performance.

[0933] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0934] Step 1: Data collection

[0935] The device collects video and audio data of the player's gameplay. A high-resolution camera and microphone connected to the device capture video and audio data in real time. It also collects log data of the player's game operations (keyboard and mouse input). This data is sent to the server in real time. Input: video data, audio data, operation log. Output: raw data set sent to the server.

[0936] Step 2: Gather opponent data

[0937] The user uploads the opponent's play data (such as a replay video) to their device. The device detects this and sends the video data to the server. Input: Replay video of the opponent. Output: Data of the opponent sent to the server.

[0938] Step 3: Data Preprocessing

[0939] The server preprocesses the video and audio data it receives. Specifically, it divides the video data into frames and extracts important features from each frame. It also removes noise from the audio data and extracts features. The opponent's data is similarly preprocessed and converted into a format suitable for analysis. Input: Raw play data and opponent data. Output: Preprocessed dataset.

[0940] Step 4: Emotion Recognition

[0941] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data. By analyzing their facial expressions and tone of voice, it can recognize their stress, anxiety, concentration, etc. Input: Preprocessed video and audio data. Output: Player's emotional state data.

[0942] Step 5: Real-time analysis

[0943] The server uses a generative artificial intelligence (AI) model to analyze the player's playing style and performance in real time. Based on in-game movements and input information, the server evaluates the player's performance indicators (reaction speed, accuracy, decision-making ability). At the same time, it integrates emotional information provided by the emotion engine to comprehensively evaluate the player's state. Input: Preprocessed dataset, emotional state data. Output: Analysis result data.

[0944] Step 6: Improvements and strategy generation

[0945] Based on the analysis results, the server generates specific areas for improvement and strategies for the player. For example, if a player's reaction time is slow, it will suggest "Let's practice for 10 minutes to improve our reaction time." It will also generate strategies for the opponent, proposing tactics to exploit the opponent's weaknesses (for example, weakness to attacks from the left side). Input: Analysis result data. Output: Data on areas for improvement and strategies.

[0946] Step 7: Notification

[0947] The device displays the generated improvements and strategies to the player in real time. Specific advice and feedback is provided during play and practice via on-screen pop-ups and voice notifications. For example, "Your reaction time is slow, so practice for 10 minutes. Deep breathing can also help reduce stress," or "Your opponent is weak against attacks from the left side, so strengthen your attacks from the left side." Input: Data on improvements and strategies. Output: Feedback notified to the player.

[0948] (Application example 2)

[0949] 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."

[0950] Existing e-sports club activity support systems collect players' play data and emotional state and provide improvements and strategies based on that data. However, they have not yet been applied to industrial applications such as improving the efficiency of robotic work in factories or detecting anomalies. Factories require real-time analysis of robot operation data and information about the work environment to identify efficient work methods and detect anomalies early, but no effective system exists for this purpose. Therefore, technology is needed to improve the efficiency of robotic work in factories and detect anomalies.

[0951] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0952] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, means for collecting, preprocessing, and analyzing robot operation data, means for generating efficient work methods and strategies for the robot based on the analysis results, and means for notifying factory staff of the generated work methods and strategies, thereby enabling efficient robot work in factories and abnormality detection.

[0953] "Play data" refers to information related to the actions and operations of a player or robot, and includes video data and audio data.

[0954] "Preprocessing" refers to the process of converting collected play data and action data into a format suitable for analysis, and includes dividing the data into frames and extracting features.

[0955] "Generative AI" is an artificial intelligence technology used to generate improvements and strategies based on collected and pre-processed data, analyzed in real time.

[0956] "Real-time analysis" is a process that involves collecting and analyzing data without any time delay, and provides immediate evaluation and suggestions based on operating conditions and emotional state.

[0957] "Improvements and strategies" are specific guidelines and tactics for improving the performance of the player or robot based on the analysis results.

[0958] "Notification" is an action that notifies the user of generated improvements or strategies, and is provided in audio or text format.

[0959] "Operation data" refers to data that includes information such as the operating status of the robot, the success or failure of the operation, error information, and the working speed.

[0960] "Efficient work methods" are specific techniques and procedures for maximizing the work efficiency of robots, and are derived using generative artificial intelligence.

[0961] "Anomaly detection" is the process of detecting abnormal behavior or conditions that deviate from normal operating conditions, and is important for maintaining safety and efficiency.

[0962] "Factory staff" refers to the people who operate and monitor robots in the factory and who are notified of the generated work methods and strategies.

[0963] System Configuration

[0964] The system includes the following means:

[0965] 1. Means of collecting player and robot behavior data

[0966] 2. Means of preprocessing the collected data

[0967] 3. A means of real-time analysis using generative artificial intelligence to analyze pre-processed data

[0968] 4. A means of generating improvements and strategies for players and robots based on the analysis results.

[0969] 5. A means to inform generated improvements and strategies

[0970] Program processing explanation

[0971] Hardware

[0972] Smartphone: Collects player and robot movement data (video and audio) and sends it to the server.

[0973] Cloud Server: The main computing resource for data analysis and strategy generation.

[0974] software

[0975] OpenCV: Used for preprocessing video data and frame segmentation.

[0976] Generative artificial intelligence models: Used for data analysis and strategy generation.

[0977] EmotionAnalyzer: Used to analyze emotional states.

[0978] Operation flow

[0979] 1. Data collection: A smartphone collects video and audio data of the player and robot's movements in real time. The video data is divided into frames, and features are extracted from the audio data in the same way.

[0980] 2. Preprocessing: The cloud server divides the video data into frames and extracts features from the audio data, converting the data into a format suitable for analysis.

[0981] 3. Emotion Recognition: The cloud server uses the EmotionAnalyzer to analyze the emotional state of the player and robot, thereby recognizing emotional states such as stress and concentration.

[0982] 4. Real-time analysis: A cloud server uses generative artificial intelligence to analyze player and robot behavior data in real time, including emotional state information.

[0983] 5. Improvements and Strategy Generation: Based on the analysis results, the cloud server generates specific improvements and strategies for players and robots. For example, it can propose specific methods to improve work efficiency.

[0984] 6. Notification: Smartphones will notify players and factory staff of generated improvements and strategies in voice and text format.

[0985] Specific examples

[0986] If a specific player is experiencing high stress

[0987] The system collects video and audio data from the player and uses the Emotion Analyzer to detect high stress levels. Generative AI takes this information into account and generates specific improvements to reduce stress (e.g., practicing deep breathing). The player is notified of this via their smartphone.

[0988] When there are many errors in the robot's work

[0989] The system collects data on the robot's operations and uses generative artificial intelligence to analyze its movements in real time. If it determines that frequent errors are due to human error, it generates efficient work methods (e.g., changing the order of certain operations) and notifies factory staff via their smartphones.

[0990] Prompt Sentence Examples

[0991] Analyze the operation data of a factory robot and propose ways to improve the error rate and work efficiency of specific tasks in real time. Also, evaluate the emotional state of the robot through its actions and detect anomalies.

[0992] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0993] Step 1:

[0994] Data collection

[0995] The device collects video and audio data of the player and robot's movements. Specifically, the smartphone captures video data through the camera and audio data through the microphone. This data is sent to the server in real time.

[0996] Input: Video data, audio data

[0997] Output: Raw data stored on the server

[0998] Step 2:

[0999] Pretreatment

[1000] The server preprocesses the video and audio data it receives. The video data is split into frames, and features (e.g., frequency components) are extracted from the audio data. OpenCV is used to split the video data into frames, and a Python audio processing library is used to preprocess the audio data.

[1001] Input: Raw data stored on the server

[1002] Output: Preprocessed frame-by-frame video data, feature-extracted audio data

[1003] Step 3:

[1004] emotion recognition

[1005] The server uses an emotion engine (EmotionAnalyzer) to analyze the emotional state of the player or robot from pre-processed video and audio data. Specifically, the emotional state (e.g., concentration, stress) is recognized by analyzing facial expressions and tone of voice.

[1006] Input: Preprocessed frame-by-frame video data, feature-extracted audio data

[1007] Output: Emotional state information (concentration, stress level, etc.)

[1008] Step 4:

[1009] Real-time analytics

[1010] The server analyzes the pre-processed data and emotional state information using a generative artificial intelligence model, which evaluates the movement performance of the player and robot and determines efficient tasks and playing styles.

[1011] Input: Preprocessed data, emotional state information

[1012] Output: Performance evaluation results

[1013] Step 5:

[1014] Improvements and Strategy Generation

[1015] Based on the analysis results, the server generates specific improvements and strategies for the player and robot. For example, if it detects high stress levels, it will suggest relaxation methods, and if the robot is making a lot of errors, it will suggest changes to its operation procedures.

[1016] Input: Performance evaluation results

[1017] Output: Improvements and strategies

[1018] Step 6:

[1019] notification

[1020] The device notifies players and factory staff of the improvements and strategies received from the server. Specifically, the smartphone displays and announces the improvements and strategies in voice and text format.

[1021] Input: Improvements and Strategies

[1022] Output: Notification to players and factory staff

[1023] 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.

[1024] 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.

[1025] 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.

[1026] [Fourth embodiment]

[1027] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1028] 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.

[1029] 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).

[1030] 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.

[1031] 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.

[1032] 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).

[1033] 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.

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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.

[1038] 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.

[1039] 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."

[1040] This invention relates to an e-sports club activity support system that uses generative artificial intelligence. The purpose of this system is to collect and analyze players' play data and provide them with specific improvements and strategies. This system consists of a collection means, a pre-processing means, a real-time analysis means, a means for generating improvements and strategies, and a notification means.

[1041] Explanation of program processing

[1042] 1. Data Collection

[1043] The device collects the player's video and audio data, which is then sent to the server in real time. Furthermore, the user uploads their opponent's gameplay data, which is then sent to the server by the device.

[1044] 2. Data Preprocessing

[1045] The server preprocesses the received video and audio data and converts it into a format suitable for analysis. This preprocessing includes splitting the video data into frames and extracting features. The opponent's data is also preprocessed in the same way.

[1046] 3. Real-time analysis

[1047] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time, identifying their strengths and weaknesses. Opponents' data is also analyzed to extract their playing styles and tendencies.

[1048] 4. Improvements and Strategy Generation

[1049] Based on the analysis results, the server generates specific improvements for the player. For example, if a player's reaction time is slow, it will suggest training to improve their reaction time. It will also generate effective strategies against the opponent. For example, if the opponent is weak against attacks from the left, it will suggest tactics to strengthen attacks from that direction.

[1050] 5. Notification

[1051] The device displays the generated improvements and strategies to the player in real time and provides specific instructions, such as "Practice strengthening your attacks from the left side." This allows the player to instantly improve their playing style.

[1052] Specific examples

[1053] Example 1: Real-time analysis and feedback of play

[1054] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. Based on the analysis results, it is determined that the player's reaction time is slower than other players. The server then generates an improvement plan, suggesting that the player "perform specific training for 10 minutes to improve their reaction time." The device then notifies the player of this improvement plan and supports their practice.

[1055] Example 2: Opponent data analysis and strategy suggestions

[1056] The user uploads the replay video of their opponent to their device, and the device sends this data to the server. The server preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. For example, it learns that the opponent is weak against left-sided defense. The server generates a specific strategy, such as "strengthen attacks from the left side," and the device notifies the player. This allows the player to take effective countermeasures.

[1057] In this way, the e-sports club activity support system that uses generative artificial intelligence provides specific improvements and strategies to improve players' performance, supporting efficient practice and growth.

[1058] The processing flow will be explained below.

[1059] Step 1:

[1060] The device collects the player's gameplay video and audio data and transmits it to the server in real time.

[1061] Step 2:

[1062] The user uploads the opponent's play data to the terminal, and the terminal transmits this data to the server.

[1063] Step 3:

[1064] The server divides the received play data into frames and extracts the necessary video and audio features, specifically identifying the player's movement trajectory and attack timing.

[1065] Step 4:

[1066] The server formats the opponent's data into a unified format that can be analyzed, making it easier to analyze the opponent's behavior patterns.

[1067] Step 5:

[1068] The server uses generative artificial intelligence to analyze the player's playing style in real time, specifically assessing the player's attack success rate, movement speed, and reaction time to identify their strengths and weaknesses.

[1069] Step 6:

[1070] The server analyzes the opponent's playing style and tendencies, extracting their strengths, weaknesses, and favorite techniques.

[1071] Step 7:

[1072] Based on the analysis, the server generates specific improvements for the player, such as suggesting training to improve reaction speed.

[1073] Step 8:

[1074] The server generates strategies for the opponent. For example, if the opponent is weak to attacks from the left, it will suggest tactics to strengthen attacks from that direction.

[1075] Step 9:

[1076] The device displays generated improvements and strategies to the player in real time, and provides specific instructions and advice via text and voice.

[1077] Step 10:

[1078] Users practice and play based on the improvements and strategies provided by the user. The server collects new play data again and performs repeated processing to improve the player's performance.

[1079] The above is the specific processing flow of the e-sports club activity support system using generative artificial intelligence.

[1080] Example 1

[1081] 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."

[1082] Traditionally, practice and preparation for esports have relied primarily on the experience and intuition of players. This has made it difficult to find efficient practice methods and specific strategies for matches. In particular, improving a player's performance and analyzing their opponents takes time and effort, making it difficult to immediately identify areas for improvement or strategies.

[1083] 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.

[1084] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, and means and methods for collecting video data and audio data as player play data and preprocessing them, thereby enabling players to quickly and efficiently receive specific advice and battle strategies to improve their own playing style.

[1085] "Play data" is a general term for video data and audio data generated while a player is playing a game.

[1086] "Means for collection" refers to the equipment and methods for acquiring gameplay data and transmitting it to the server, including capture devices and microphones, as well as data streaming protocols.

[1087] "Preprocessing means" refers to the techniques and methods used to convert collected gameplay data into a format suitable for analysis. Specifically, this includes frame division and feature extraction of video data, and spectral analysis of audio data.

[1088] "Generative artificial intelligence" refers to artificial intelligence technology that can generate new information and patterns from input data using techniques such as deep learning.

[1089] "Means for real-time analysis" refers to systems and algorithms that use generative artificial intelligence to instantly analyze play data.

[1090] "Means for generating improvements and strategies" refers to techniques and methods for devising specific improvements and playing strategies for players based on the analysis results.

[1091] "Means of notification" refers to the techniques and methods used to communicate generated improvements and strategies to players, including user interfaces and notification systems.

[1092] "Video Data" refers to the sequence of image frames captured during gameplay.

[1093] "Audio Data" refers to audio information recorded during game play.

[1094] "Opponent's play data" refers to video data and audio data related to the gameplay of the opponent against whom the player is playing.

[1095] "Competitive strategy" refers to specific methods and tactics for analyzing an opponent's playing style and weaknesses and devising effective countermeasures.

[1096] The present invention relates to an e-sports club activity support system that uses generative artificial intelligence. The purpose of this system is to collect and analyze players' play data and provide them with specific improvements and strategies. The following describes in detail the embodiments of the present invention.

[1097] This system consists of a collection means, a pre-processing means, a real-time analysis means, a means for generating improvements and strategies, and a means for notification. To realize these means, various software libraries and protocols are utilized.

[1098] Collection Method

[1099] The device collects the player's gameplay video and audio data. Specifically, it uses a dedicated capture device and microphone to capture data during gameplay. The captured data is sent to the server in real time. RTMP (Real-Time Messaging Protocol) is used for data streaming. Furthermore, the user uploads their opponent's gameplay data via a web interface, and the device uses an HTTP request to send this data to the server.

[1100] Pretreatment means

[1101] The server pre-processes the received video and audio data and converts it into a format suitable for analysis. The pre-processing includes the following specific steps:

[1102] Video data frame division: Video data is divided into frames using the OpenCV library.

[1103] Feature extraction: Extract keyframes from multiple frames and extract features (edges, motion, color, etc.) from those frames.

[1104] Spectral analysis of audio data: Using the Librosa library, we extract spectral features from audio data, which prepares us to analyze important sounds in the game (e.g., footsteps to determine enemy positions).

[1105] Real-time analysis tools

[1106] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time, including the following techniques:

[1107] Utilizing deep learning models: Analyzing player play data using models created using TensorFlow and PyTorch. For example, using models such as ResNet and Transformers, we evaluate player behavior patterns and reaction times.

[1108] Identifying strengths and weaknesses: The analysis results output by the model identify a player's strengths (e.g., high accuracy shooting) and weaknesses (e.g., slow reaction time).

[1109] Opponent Playstyle Analysis: Using the same generative AI, we analyze your opponents' movements to find their most frequently used tactics and weaknesses.

[1110] Improvements and Strategy Generation Tools

[1111] The server generates specific improvements for the player based on the analysis, including specific actions such as:

[1112] Suggestions for improvement: For example, if the analysis shows that a player has a slow reaction time, we will suggest specific training exercises (such as reflex training games) to improve that speed.

[1113] Strategy Generation: Generate tactics based on the opponent's weaknesses. For example, if the opponent is weak to attacks from the left, the system will suggest a specific tactic to the player: "Strengthen attacks from the left side."

[1114] Notification means

[1115] The device will display generated improvements and strategies to the player in real time and provide specific instructions, including the following specific actions:

[1116] Displaying Notifications: Displaying specific advice or tactics to players through the user interface (UI), such as "Spend the next 10 minutes training to improve your reaction speed."

[1117] Get feedback: See if players have implemented the suggested training or tactics and gather feedback.

[1118] Specific examples

[1119] Example 1: Real-time analysis and feedback of play

[1120] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. For example, it may identify that the player's reaction time is slower than other players. The server then generates an improvement plan, such as "perform specific training for 10 minutes to improve reaction time." The device then notifies the player of this improvement plan and supports their practice.

[1121] Example 2: Opponent data analysis and strategy suggestions

[1122] The user uploads the replay video of their opponent to their device, and the device sends this data to the server. The server preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. For example, it learns that the opponent is weak against left-sided defense. The server generates a specific strategy, such as "strengthen attacks from the left side," and the device notifies the player. This allows the player to take effective countermeasures.

[1123] Prompt example (play data analysis)

[1124] input:

[1125] "Analyze player A's play data and evaluate his reaction time and shooting accuracy. Player B's (opponent's) play data is also provided, so find his weaknesses and propose effective strategies."

[1126] output:

[1127] "Player A's reaction time is 20% slower than average. They have good shooting accuracy, but their accuracy decreases while moving."

[1128] "Your opponent's data has identified a weakness to attacks from the left. Employ tactics that strengthen attacks from the left."

[1129] In this way, generative AI models can be used to provide detailed and specific playstyle improvements and strategy suggestions.

[1130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1131] Step 1: Data collection

[1132] The device collects the player's gameplay video and audio data. Specifically, it captures video and audio during gameplay in real time using a capture device or microphone. The input is the player's gameplay data, and the output is the collected video and audio data. The collected data is sent to the server using the RTMP protocol. The user can also upload their opponent's gameplay data via a web interface, and the device sends this data to the server via an HTTP request.

[1133] Step 2: Data Preprocessing

[1134] The server preprocesses the video and audio data it receives and converts it into a format suitable for analysis. The input is raw data sent via RTMP or HTTP, and the output is preprocessed data. Specific operations include:

[1135] Video data frame division: Use the OpenCV library to divide the video data into frames and extract keyframes.

[1136] Feature extraction: Extract features such as edges, motion, and color from each keyframe.

[1137] Spectral analysis of audio data: We use the Librosa library to extract spectral features from audio data, which prepares us for analyzing important sounds in the game (e.g., enemy footsteps).

[1138] Step 3: Real-time analysis

[1139] The server uses generative artificial intelligence to analyze players' playing styles and performance in real time. The input is pre-processed data, and the output is the analysis results. Specific operations include:

[1140] Utilizing deep learning models: Using models created using TensorFlow or PyTorch (e.g., ResNet or Transformers), we evaluate players' behavioral patterns and reaction times.

[1141] Identifying strengths and weaknesses: The strengths and weaknesses of players are extracted from the analysis results output by the model.

[1142] Opponent Playstyle Analysis: Similarly, generative AI is used to analyze opponents' movement patterns, weaknesses, and strategies.

[1143] Step 4: Improvements and strategy generation

[1144] The server generates specific improvements and strategies for the player based on the analysis results. The input is the analysis results, and the output is suggested improvements and strategies. Specific operations include:

[1145] Suggestions for improvement: For example, if your reaction time is slower than other players, we will suggest specific training exercises to improve your reaction time.

[1146] Strategy generation: Based on the opponent's weaknesses (e.g., weak defense on the left side), the system suggests specific tactics to the player, such as "strengthen attack from the left side."

[1147] Step 5: Notification

[1148] The terminal displays the generated improvements and strategies to the player in real time and provides specific instructions. The input is the improvement and strategy suggestions, and the output is the notification to the player. Specific actions include:

[1149] Displaying Notifications: Displaying improvements and strategies to players through the user interface, for example, "Spend the next 10 minutes practicing to improve your reaction speed."

[1150] Gather feedback: By checking whether players have implemented the suggested training and tactics and collecting their feedback, we can provide more accurate analysis and recommendations.

[1151] (Application example 1)

[1152] 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."

[1153] Conventional systems were specialized in improving player performance, but their application was limited to sports and games, and they could not be adapted to improving or optimizing the work efficiency of robots in factories. In particular, there was a lack of technology that could evaluate robot work performance in real time and provide specific improvements and strategies, which made it difficult to establish efficient work processes.

[1154] 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.

[1155] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using a generative artificial intelligence (AI) that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, means for collecting robot task data, means for preprocessing the collected task data, means for performing real-time analysis using a generative AI that analyzes the preprocessed data and evaluating task performance, means for generating specific improvements and strategies to improve the robot's task efficiency based on the analysis results, and means for notifying the robot of the generated improvements and strategies, thereby enabling performance improvements for both the player and the robot.

[1156] "Player play data" refers to information related to the actions and operations performed by a player in a game or simulation, etc. This includes video data, audio data, operation history, etc.

[1157] "Preprocessing methods" refer to processes or techniques that transform raw data into a form suitable for analysis, such as data cleaning, frame segmentation, and feature extraction.

[1158] "Means for real-time analysis using generative artificial intelligence" refers to a process that uses generative artificial intelligence (AI) algorithms to analyze input data in real time and output results, allowing for immediate identification of data features and patterns.

[1159] "Improvement and strategy generation measures" refers to the process of generating specific performance improvement recommendations and strategies based on the analysis results, including operational improvement recommendations and tactical advice.

[1160] "Means of notifying players" refers to the methods used to communicate generated improvements and strategies to players, including display and audio messages.

[1161] "Robot work data" refers to information related to the movements and work that robots perform in factories, manufacturing sites, etc. This includes movement patterns, work results, sensor data, etc.

[1162] "Means of notifying the robot" refers to the methods of communicating generated improvements and strategies to the robot and having it adjust its operations, including sending control signals and updating its program.

[1163] The present invention relates to a system for improving the performance of players and robots. Specific embodiments for carrying out the present invention will be described below.

[1164] System Configuration

[1165] This system consists of the following main components:

[1166] 1. Data Collection Methods

[1167] 2. Data preprocessing methods

[1168] 3. Real-time analysis using generative artificial intelligence

[1169] 4. Improvements and Strategy Generation

[1170] 5. Means of notification

[1171] Data collection methods

[1172] The server collects the player's play data and the robot's work data. The player's play data includes video and audio data, which the user sends to the server via their device. The robot's work data is also obtained from sensors and cameras installed on the robot and sent to the server.

[1173] Data preprocessing measures

[1174] The server preprocesses the received data. This includes splitting the video data into frames, extracting features, and cleaning the data. This converts the data into a format suitable for analysis. For example, OpenCV is used to split the video data into frames, and Scikit-learn is used to extract features.

[1175] Real-time analysis using generative artificial intelligence

[1176] The server uses generative artificial intelligence (AI) to analyze player and robot data in real time. During the analysis process, the server evaluates the player's control patterns and the robot's performance to identify strengths and weaknesses. The AI ​​algorithms used here include TensorFlow and PyTorch.

[1177] Improvements and Strategy Generation Tools

[1178] The server generates specific improvements and strategies based on the results of real-time analysis. For example, it generates a training plan for the player to improve reaction speed, and suggests motion instructions for the robot to handle parts from a specific angle. It processes the analysis results using Pandas and NumPy to generate improvements and strategies.

[1179] Notification means

[1180] The server notifies the player and robot of the improvements and strategies that have been generated. The player is notified by display and voice message, and control signals are sent to the robot using ROS (Robot Operating System). The player and robot receive this notification and can immediately improve their playing style and work content.

[1181] Specific examples

[1182] 1. Real-time player analysis and feedback:

[1183] The player's play data is sent to a server in real time and analyzed by a generative AI model. As a result, it is determined that the player's reaction time is slower than other players, and an improvement plan is generated, such as "performing specific training for 10 minutes to improve reaction time."

[1184] Example prompt: "Suggest specific training to improve reaction speed."

[1185] 2. Robot performance analysis and improvement proposals:

[1186] The robot's work data is sent to a server in real time and analyzed by a generative AI model. As a result, it is determined that a particular part handling method is inefficient, and specific operational instructions such as "handle the part from a specific angle" are generated.

[1187] Example prompt: "Suggest the optimal working angle and speed for each type of part being handled."

[1188] As a result, the present invention provides a system for improving the performance of both the player and the robot.

[1189] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1190] Step 1:

[1191] The server collects player play data and robot operation data from the device. Input data includes video data, audio data, sensor data, etc. The collected data is stored on the server as raw data.

[1192] Step 2:

[1193] The server preprocesses the collected raw data. In this step, the video data is split into frames using OpenCV and features are extracted using Scikit-learn. The input is the frame-split video and audio data, and the output is data converted into a format suitable for analysis.

[1194] Step 3:

[1195] The server uses generative artificial intelligence to analyze preprocessed data in real time. It uses TensorFlow and PyTorch to evaluate the player's control patterns and the robot's work performance to identify strengths and weaknesses. The input is the preprocessed data, and the output is the analysis results.

[1196] Step 4:

[1197] The server generates specific improvements and strategies based on the analysis results. It processes the analysis results using Pandas and NumPy and makes suggestions to improve the performance of the player and robot. The input is the analysis results, and the output is improvements and strategies. For example, "specific training to improve reaction speed" or "motion instructions for handling parts from a specific angle" are generated.

[1198] Step 5:

[1199] The server notifies the player and robot of the generated improvements and strategies. The player is notified by displaying the improvements and voice messages, and the robot is sent control signals using ROS. The input is the generated improvements and strategies, and the output is a notification. The player and robot receive this notification and respond in real time.

[1200] 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.

[1201] This invention relates to an e-sports club activity support system that uses generative artificial intelligence and an emotion engine. This system collects and analyzes players' play data and emotional states, and provides them with optimal improvements and strategies. This system consists of a play data collection means, preprocessing means, real-time analysis means, improvement and strategy generation means, notification means, and an emotion engine that recognizes the user's emotions.

[1202] Explanation of program processing

[1203] Data collection

[1204] The device collects the player's gameplay video and audio data and transmits it to the server in real time. The collected data also includes information about the player's gameplay. The user also uploads the opponent's gameplay data, which the device then transmits to the server.

[1205] Data Preprocessing

[1206] The server preprocesses the video and audio data it receives, splitting the video data into frames and extracting features from the audio data. The server also preprocesses the opponent's data and converts it into a format suitable for analysis.

[1207] emotion recognition

[1208] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data, thereby recognizing their emotional state (e.g., stress, anxiety, concentration, etc.).

[1209] Real-time analytics

[1210] The server uses generative artificial intelligence to analyze the player's playing style and performance in real time, and also uses emotional information provided by the emotion engine to comprehensively evaluate the player's state.

[1211] Improvements and Strategy Generation

[1212] Based on the analysis results, the server generates specific improvements for the player. For example, if stress levels are high, it suggests ways to relax. It also generates strategies for dealing with opponents. For example, if an opponent is weak against attacks from the left, it suggests tactics to strengthen attacks from that direction.

[1213] notification

[1214] The device displays generated improvements and strategies to the player in real time, providing specific instructions and feedback in the form of voice and text.

[1215] Specific examples

[1216] Example 1: Real-time analysis and feedback of play

[1217] The device sends the player's play data to the server in real time. The server preprocesses the data and analyzes it in real time using generative artificial intelligence. An emotion engine then analyzes the player's emotional state (for example, concentration and stress level). Based on the analysis results, it is determined that the player's reaction time is slower than other players and that they are under high stress. The server then generates an improvement plan, suggesting that the player "do 10 minutes of training to improve their reaction time and incorporate deep breathing exercises to reduce stress." The device then notifies the player of this improvement plan and supports their practice.

[1218] Example 2: Opponent data analysis and strategy suggestions

[1219] The user uploads a replay video of their opponent to their device, which then sends the data to the server. The server then preprocesses the data and analyzes the opponent's weaknesses and preferred playing styles. The system also takes into account the player's emotional state. For example, if the player is feeling anxious, the system will suggest a simple strategy to exploit the opponent's weaknesses. Specifically, the system generates a tactic such as "strengthen attacks from the left side," and notifies the player. This allows the player to take effective countermeasures.

[1220] In this way, the e-sports club activity support system, which combines generative artificial intelligence and an emotion engine, not only improves players' performance but also provides optimal improvements and strategies that take into account their emotional state.

[1221] The processing flow will be explained below.

[1222] Step 1:

[1223] The device collects the player's gameplay video and audio data and transmits it to the server in real time.

[1224] Step 2:

[1225] The user uploads the opponent's play data to the terminal, and the terminal transmits this data to the server.

[1226] Step 3:

[1227] The server divides the gameplay video data it receives into frames and extracts the necessary features, including analyzing the player's movement trajectory and attack timing.

[1228] Step 4:

[1229] The server preprocesses the received voice data and analyzes the tone and vocal patterns of the voice, which provides the basis for inferring the player's emotional state.

[1230] Step 5:

[1231] The server formats the opponent's data into a unified format and converts it into a form suitable for analysis.

[1232] Step 6:

[1233] The server uses an emotion engine to detect the player's emotional state from real-time video and audio data, for example, analyzing stress and concentration levels from facial expressions and voice tones.

[1234] Step 7:

[1235] The server uses generative artificial intelligence to analyze players' playstyles and performance in real time, including assessing their attack success rate, movement speed, reaction time, and more.

[1236] Step 8:

[1237] The server analyzes the opponent's playing style and tendencies to extract their strengths and weaknesses, thereby identifying their special moves and attack patterns.

[1238] Step 9:

[1239] The server will generate specific improvements for the player based on the analysis results, for example, if the player has a slow reaction time, it will suggest specific reflex training.

[1240] Step 10:

[1241] The server generates strategies for the opponent and proposes the optimal strategy taking into account the results of the emotion engine. For example, if the opponent is weak to attacks from the left side and the player is concentrating, the server proposes a tactic to strengthen attacks from the left side.

[1242] Step 11:

[1243] The device displays generated improvements and strategies to the player in real time, with specific instructions and advice provided via text and audio.

[1244] Step 12:

[1245] Users practice and play based on the improvements and strategies provided by the user. The server continuously collects new play data and emotional data, and the program is dynamically adjusted.

[1246] The above is the specific processing flow of the e-sports club activity support system that combines generative artificial intelligence and an emotion engine.

[1247] Example 2

[1248] 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."

[1249] While conventional e-sports club support systems were able to collect players' play data and generate improvements and strategies based on the analysis results, they were unable to recognize the players' emotional state in real time and incorporate that information into the analysis. This made it difficult to provide optimal feedback and strategies that took the players' mental state into account, preventing the maximum improvement of player performance.

[1250] 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. In this invention, the server includes means for collecting play data of players, means for pre-processing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the pre-processed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, and means including an emotion engine that analyzes the player's emotional state in real time. This enables analysis and feedback that takes the player's emotional state into consideration.

[1251] "Play data" refers to video data and audio data that includes information about the player's game operations.

[1252] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis, and includes splitting video data into frames and removing noise from audio data.

[1253] "Generative AI" refers to artificial intelligence technology that analyzes collected data in real time and generates improvements and strategies for players.

[1254] "Emotion engine" refers to technology that analyzes the player's emotional state in real time from video and audio data.

[1255] "Areas for Improvement" refers to specific actions or training methods recommended to improve a player's performance.

[1256] "Strategy" refers to specific tactics proposed to players based on the characteristics and weaknesses of their opponents.

[1257] "Notification" refers to the act of communicating generated improvements and strategies to players in audio or text format.

[1258] This invention relates to an e-sports club activity support system that uses generative artificial intelligence and an emotion engine. This system collects and analyzes players' play data and emotional states, and provides them with optimal improvements and strategies. This system consists of a play data collection means, a preprocessing means, a real-time analysis means, a means for generating improvements and strategies, a notification means, and an emotion engine that recognizes the user's emotions.

[1259] The device collects the player's gameplay video and audio data and sends it to the server in real time. The device is equipped with a high-resolution camera and microphone, which capture data using this hardware. The collected data also includes information about the player's game operations (keyboard and mouse input). The user also uploads their opponent's gameplay data to the device, which then sends this data to the server.

[1260] The server preprocesses the video and audio data it receives. It divides the video data into frames and extracts features from the audio data. The opponent's data is also preprocessed and converted into a format suitable for analysis. For video data, the video is divided into a set number of frames and important features are extracted using an image processing algorithm. For audio data, background noise and other noise are removed to obtain clear audio information.

[1261] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data, including facial expression analysis and tone of voice analysis, to accurately recognize the player's emotional state (stress, anxiety, concentration, etc.).

[1262] The server uses a generative artificial intelligence (AI) model to analyze the player's playing style and performance in real time. Based on in-game movements and input information, the server evaluates the player's performance indicators (reaction speed, accuracy, decision-making ability). In addition, it integrates emotional information provided by an emotion engine to comprehensively evaluate the player's state.

[1263] Based on the analysis results, the server generates specific suggestions for improvement for the player, such as "Spend 10 minutes of training to improve your reaction speed" or "Take deep breaths to reduce stress." Analyzing the opponent's data, the server generates strategies such as "Your opponent is weak against attacks from the left, so strengthen your attacks from the left."

[1264] The device displays generated improvements and strategies to the player in real time, using on-screen pop-ups and audio notifications to provide specific advice and feedback to the player. For example, the following prompts are available:

[1265] "Your reaction time is slow, so do 10 minutes of training. Incorporating deep breathing techniques can also help reduce stress."

[1266] "Your opponent is weak to attacks from the left, so strengthen your attacks from the left."

[1267] This system not only improves players' performance but also provides optimal improvements and strategies that take into account their emotional state. As a result, players can take effective measures and properly manage their mental state, thereby supporting them in achieving their best performance.

[1268] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1269] Step 1: Data collection

[1270] The device collects video and audio data of the player's gameplay. A high-resolution camera and microphone connected to the device capture video and audio data in real time. It also collects log data of the player's game operations (keyboard and mouse input). This data is sent to the server in real time. Input: video data, audio data, operation log. Output: raw data set sent to the server.

[1271] Step 2: Gather opponent data

[1272] The user uploads the opponent's play data (such as a replay video) to their device. The device detects this and sends the video data to the server. Input: Replay video of the opponent. Output: Data of the opponent sent to the server.

[1273] Step 3: Data Preprocessing

[1274] The server preprocesses the video and audio data it receives. Specifically, it divides the video data into frames and extracts important features from each frame. It also removes noise from the audio data and extracts features. The opponent's data is similarly preprocessed and converted into a format suitable for analysis. Input: Raw play data and opponent data. Output: Preprocessed dataset.

[1275] Step 4: Emotion Recognition

[1276] The server uses an emotion engine to analyze the player's emotional state in real time from their video and audio data. By analyzing their facial expressions and tone of voice, it can recognize their stress, anxiety, concentration, etc. Input: Preprocessed video and audio data. Output: Player's emotional state data.

[1277] Step 5: Real-time analysis

[1278] The server uses a generative artificial intelligence (AI) model to analyze the player's playing style and performance in real time. Based on in-game movements and input information, the server evaluates the player's performance indicators (reaction speed, accuracy, decision-making ability). At the same time, it integrates emotional information provided by the emotion engine to comprehensively evaluate the player's state. Input: Preprocessed dataset, emotional state data. Output: Analysis result data.

[1279] Step 6: Improvements and strategy generation

[1280] Based on the analysis results, the server generates specific areas for improvement and strategies for the player. For example, if a player's reaction time is slow, it will suggest "Let's practice for 10 minutes to improve our reaction time." It will also generate strategies for the opponent, proposing tactics to exploit the opponent's weaknesses (for example, weakness to attacks from the left side). Input: Analysis result data. Output: Data on areas for improvement and strategies.

[1281] Step 7: Notification

[1282] The device displays the generated improvements and strategies to the player in real time. Specific advice and feedback is provided during play and practice via on-screen pop-ups and voice notifications. For example, "Your reaction time is slow, so practice for 10 minutes. Deep breathing can also help reduce stress," or "Your opponent is weak against attacks from the left side, so strengthen your attacks from the left side." Input: Data on improvements and strategies. Output: Feedback notified to the player.

[1283] (Application example 2)

[1284] 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."

[1285] Existing e-sports club activity support systems collect players' play data and emotional state and provide improvements and strategies based on that data. However, they have not yet been applied to industrial applications such as improving the efficiency of robotic work in factories or detecting anomalies. Factories require real-time analysis of robot operation data and information about the work environment to identify efficient work methods and detect anomalies early, but no effective system exists for this purpose. Therefore, technology is needed to improve the efficiency of robotic work in factories and detect anomalies.

[1286] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1287] In this invention, the server includes means for collecting player play data, means for preprocessing the collected play data, means for performing real-time analysis using generative artificial intelligence that analyzes the preprocessed data, means for generating improvements and strategies for the player based on the analysis results, means for notifying the player of the generated improvements and strategies, means for collecting, preprocessing, and analyzing robot operation data, means for generating efficient work methods and strategies for the robot based on the analysis results, and means for notifying factory staff of the generated work methods and strategies, thereby enabling efficient robot work in factories and abnormality detection.

[1288] "Play data" refers to information related to the actions and operations of a player or robot, and includes video data and audio data.

[1289] "Preprocessing" refers to the process of converting collected play data and action data into a format suitable for analysis, and includes dividing the data into frames and extracting features.

[1290] "Generative AI" is an artificial intelligence technology used to generate improvements and strategies based on collected and pre-processed data, analyzed in real time.

[1291] "Real-time analysis" is a process that involves collecting and analyzing data without any time delay, and provides immediate evaluation and suggestions based on operating conditions and emotional state.

[1292] "Improvements and strategies" are specific guidelines and tactics for improving the performance of the player or robot based on the analysis results.

[1293] "Notification" is an action that notifies the user of generated improvements or strategies, and is provided in audio or text format.

[1294] "Operation data" refers to data that includes information such as the operating status of the robot, the success or failure of the operation, error information, and the working speed.

[1295] "Efficient work methods" are specific techniques and procedures for maximizing the work efficiency of robots, and are derived using generative artificial intelligence.

[1296] "Anomaly detection" is the process of detecting abnormal behavior or conditions that deviate from normal operating conditions, and is important for maintaining safety and efficiency.

[1297] "Factory staff" refers to the people who operate and monitor robots in the factory and who are notified of the generated work methods and strategies.

[1298] System Configuration

[1299] The system includes the following means:

[1300] 1. Means of collecting player and robot behavior data

[1301] 2. Means of preprocessing the collected data

[1302] 3. A means of real-time analysis using generative artificial intelligence to analyze pre-processed data

[1303] 4. A means of generating improvements and strategies for players and robots based on the analysis results.

[1304] 5. A means to inform generated improvements and strategies

[1305] Program processing explanation

[1306] Hardware

[1307] Smartphone: Collects player and robot movement data (video and audio) and sends it to the server.

[1308] Cloud Server: The main computing resource for data analysis and strategy generation.

[1309] software

[1310] OpenCV: Used for preprocessing video data and frame segmentation.

[1311] Generative artificial intelligence models: Used for data analysis and strategy generation.

[1312] EmotionAnalyzer: Used to analyze emotional states.

[1313] Operation flow

[1314] 1. Data collection: A smartphone collects video and audio data of the player and robot's movements in real time. The video data is divided into frames, and features are extracted from the audio data in the same way.

[1315] 2. Preprocessing: The cloud server divides the video data into frames and extracts features from the audio data, converting the data into a format suitable for analysis.

[1316] 3. Emotion Recognition: The cloud server uses the EmotionAnalyzer to analyze the emotional state of the player and robot, thereby recognizing emotional states such as stress and concentration.

[1317] 4. Real-time analysis: A cloud server uses generative artificial intelligence to analyze player and robot behavior data in real time, including emotional state information.

[1318] 5. Improvements and Strategy Generation: Based on the analysis results, the cloud server generates specific improvements and strategies for players and robots. For example, it can propose specific methods to improve work efficiency.

[1319] 6. Notification: Smartphones will notify players and factory staff of generated improvements and strategies in voice and text format.

[1320] Specific examples

[1321] If a specific player is experiencing high stress

[1322] The system collects video and audio data from the player and uses the Emotion Analyzer to detect high stress levels. Generative AI takes this information into account and generates specific improvements to reduce stress (e.g., practicing deep breathing). The player is notified of this via their smartphone.

[1323] When there are many errors in the robot's work

[1324] The system collects data on the robot's operations and uses generative artificial intelligence to analyze its movements in real time. If it determines that frequent errors are due to human error, it generates efficient work methods (e.g., changing the order of certain operations) and notifies factory staff via their smartphones.

[1325] Prompt Sentence Examples

[1326] Analyze the operation data of a factory robot and propose ways to improve the error rate and work efficiency of specific tasks in real time. Also, evaluate the emotional state of the robot through its actions and detect anomalies.

[1327] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1328] Step 1:

[1329] Data collection

[1330] The device collects video and audio data of the player and robot's movements. Specifically, the smartphone captures video data through the camera and audio data through the microphone. This data is sent to the server in real time.

[1331] Input: Video data, audio data

[1332] Output: Raw data stored on the server

[1333] Step 2:

[1334] Pretreatment

[1335] The server preprocesses the video and audio data it receives. The video data is split into frames, and features (e.g., frequency components) are extracted from the audio data. OpenCV is used to split the video data into frames, and a Python audio processing library is used to preprocess the audio data.

[1336] Input: Raw data stored on the server

[1337] Output: Preprocessed frame-by-frame video data, feature-extracted audio data

[1338] Step 3:

[1339] emotion recognition

[1340] The server uses an emotion engine (EmotionAnalyzer) to analyze the emotional state of the player or robot from pre-processed video and audio data. Specifically, the emotional state (e.g., concentration, stress) is recognized by analyzing facial expressions and tone of voice.

[1341] Input: Preprocessed frame-by-frame video data, feature-extracted audio data

[1342] Output: Emotional state information (concentration, stress level, etc.)

[1343] Step 4:

[1344] Real-time analytics

[1345] The server analyzes the pre-processed data and emotional state information using a generative artificial intelligence model, which evaluates the movement performance of the player and robot and determines efficient tasks and playing styles.

[1346] Input: Preprocessed data, emotional state information

[1347] Output: Performance evaluation results

[1348] Step 5:

[1349] Improvements and Strategy Generation

[1350] Based on the analysis results, the server generates specific improvements and strategies for the player and robot. For example, if it detects high stress levels, it will suggest relaxation methods, and if the robot is making a lot of errors, it will suggest changes to its operation procedures.

[1351] Input: Performance evaluation results

[1352] Output: Improvements and strategies

[1353] Step 6:

[1354] notification

[1355] The device notifies players and factory staff of the improvements and strategies received from the server. Specifically, the smartphone displays and announces the improvements and strategies in voice and text format.

[1356] Input: Improvements and Strategies

[1357] Output: Notification to players and factory staff

[1358] 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.

[1359] 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.

[1360] 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.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] 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).

[1365] 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.

[1366] 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."

[1367] 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.

[1368] 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).

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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.

[1378] 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.

[1379] The following is further disclosed regarding the above embodiment.

[1380] (Claim 1)

[1381] A means for collecting player play data;

[1382] A means for preprocessing the collected play data;

[1383] a means for performing real-time analysis using generative artificial intelligence to analyze the pre-processed data;

[1384] means for generating improvements and strategies for the player based on the analysis results;

[1385] a means of informing players of the improvements and strategies generated;

[1386] A system including:

[1387] (Claim 2)

[1388] 2. The system according to claim 1, wherein video data and audio data are collected as the player's play data.

[1389] (Claim 3)

[1390] a means for collecting and preprocessing opponent play data;

[1391] A means for performing real-time analysis using generative artificial intelligence to analyze opponent data;

[1392] 10. The system of claim 1, further comprising means for generating a playing strategy for the player based on the analysis results.

[1393] "Example 1"

[1394] (Claim 1)

[1395] A means for collecting player play data;

[1396] A means for preprocessing the collected play data;

[1397] a means for performing real-time analysis using generative artificial intelligence to analyze the pre-processed data;

[1398] means for generating improvements and strategies for the player based on the analysis results;

[1399] a means of informing players of the improvements and strategies generated;

[1400] A system including a means and a method for collecting and preprocessing video data and audio data as player play data.

[1401] (Claim 2)

[1402] a means for collecting and preprocessing opponent play data;

[1403] A means for performing real-time analysis using generative artificial intelligence to analyze opponent data;

[1404] 10. The system of claim 1, further comprising means for generating a playing strategy for the player based on the analysis results.

[1405] (Claim 3)

[1406] 10. The system of claim 1, further comprising means for informing the player of the generated improvements and strategies and providing specific instructions.

[1407] "Application Example 1"

[1408] (Claim 1)

[1409] A means for collecting player play data;

[1410] A means for preprocessing the collected play data;

[1411] a means for performing real-time analysis using generative artificial intelligence to analyze the pre-processed data;

[1412] means for generating improvements and strategies for the player based on the analysis results;

[1413] a means of informing players of the improvements and strategies generated;

[1414] A means for collecting work data of the robot;

[1415] means for preprocessing the collected work data;

[1416] a means for performing real-time analysis using generative artificial intelligence to analyze pre-processed data and evaluate work performance;

[1417] A means for generating specific improvements and strategies for improving the work efficiency of the robot based on the analysis results;

[1418] means for informing the robot of the generated improvements and strategies;

[1419] A system including:

[1420] (Claim 2)

[1421] 2. The system according to claim 1, wherein video data and audio data are collected as the player's play data.

[1422] (Claim 3)

[1423] a means for collecting and preprocessing opponent play data;

[1424] A means for performing real-time analysis using generative artificial intelligence to analyze opponent data;

[1425] 10. The system of claim 1, further comprising means for generating a playing strategy for the player based on the analysis results.

[1426] "Example 2: Combining Emotion Engines"

[1427] (Claim 1)

[1428] A means for collecting player play data;

[1429] A means for preprocessing the collected play data;

[1430] a means for performing real-time analysis using generative artificial intelligence to analyze the pre-processed data;

[1431] means for generating improvements and strategies for the player based on the analysis results;

[1432] a means of informing players of the improvements and strategies generated;

[1433] means including an emotion engine for analyzing the player's emotional state in real time;

[1434] A system including:

[1435] (Claim 2)

[1436] 2. The system according to claim 1, wherein video data and audio data are collected as the player's play data.

[1437] (Claim 3)

[1438] a means for collecting and preprocessing opponent play data;

[1439] A means for performing real-time analysis using generative artificial intelligence to analyze opponent data;

[1440] 10. The system of claim 1, further comprising means for generating a playing strategy for the player based on the analysis results.

[1441] "Application example 2 when combining emotion engines"

[1442] (Claim 1)

[1443] A means for collecting player play data;

[1444] A means for preprocessing the collected play data;

[1445] a means for performing real-time analysis using generative artificial intelligence to analyze the pre-processed data;

[1446] means for generating improvements and strategies for the player based on the analysis results;

[1447] a means of informing players of the improvements and strategies generated;

[1448] means for collecting, preprocessing, and analyzing robot motion data;

[1449] means for generating efficient work methods and strategies for the robot based on the analysis results;

[1450] a means of communicating the generated work methods and strategies to factory staff;

[1451] A system including:

[1452] (Claim 2)

[1453] 2. The system according to claim 1, wherein video data and audio data are collected as the player's play data.

[1454] (Claim 3)

[1455] a means for collecting and preprocessing opponent play data;

[1456] A means for performing real-time analysis using generative artificial intelligence to analyze opponent data;

[1457] 10. The system of claim 1, further comprising means for generating a playing strategy for the player based on the analysis results. [Explanation of symbols]

[1458] 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 player play data; A means for preprocessing the collected play data; a means for performing real-time analysis using generative artificial intelligence to analyze the pre-processed data; means for generating improvements and strategies for the player based on the analysis results; a means of informing players of the improvements and strategies generated; A system including:

2. 2. The system according to claim 1, wherein video data and audio data are collected as the player's play data.

3. a means for collecting and preprocessing opponent play data; A means for performing real-time analysis using generative artificial intelligence to analyze opponent data; The system of claim 1 further comprising means for generating a playing strategy for the player based on the analysis results.

Images