system

Abstract

We provide the system. [Solution] A means for collecting match data from professional players and training a generative AI model that learns strategies using said data, To promote interaction at local events, a means of providing a system that allows participation in community conventions, A means to activate an AI agent corresponding to the game selected by the user and prepare for battle, A means for an AI agent to analyze the moves entered by the user in a game and calculate the next move, A means of generating and providing feedback to users after the game ends, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional game learning systems, there has been a problem that it is difficult for players of board games or card games to easily play against professional-level opponents and obtain an effective learning environment for improving their skills. In particular, real-time feedback and presentation of improvement measures during the game are insufficient, and the user has limited opportunities to objectively evaluate and improve their own playing style.

Means for Solving the Problems

[0005] This invention provides a system that offers professional-level matches at any time by training a generated AI model based on professional players' match data and activating an AI agent corresponding to the game selected by the user. Furthermore, it realizes a real-time match experience by analyzing the moves entered by the user during the game and having the AI ​​agent calculate the next move. In addition, it has means to support the user's skill improvement by generating and providing specific feedback to the user after the game ends. In this way, the user can analyze their own characteristics and continuously improve their skills.

[0006] "Professional player match data" refers to information about board games and card games, including the past match history of players recognized as professionals, as well as patterns of tactics and strategies used in each game situation.

[0007] A "generative AI model" is an artificial intelligence model that is trained using machine learning based on the game data of professional players and has the ability to imitate the strategies of professional players.

[0008] An "AI agent" is a virtual opponent that uses a generative AI model to play against the user in selected games and make professional-level decisions.

[0009] "User-inputted game moves" refers to the specific actions that a user chooses and performs during their turn in a board game or card game.

[0010] "Feedback" refers to information provided to users after a match ends, including an evaluation of their actions during the game and specific suggestions for improving their skills.

[0011] "Skill improvement" refers to users improving their tactical, strategic, and decision-making abilities to a higher level through gameplay. [Brief explanation of the drawing]

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

[0013] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

[0018] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

[0020] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0033] In order to implement this invention, it is necessary to construct a competitive game system using an AI agent through the interaction of a server, a terminal, and a user.

[0034] Server-side processing

[0035] The server first collects game data from professional players via the internet and datasets, and uses this data to train a generative AI model. Because this model has the ability to mimic the strategies of professional players, it can provide users with a realistic game experience. The server receives game selections from users and activates the corresponding AI agent. During a game, the server receives the user's moves, and the AI ​​agent calculates the next move based on those moves and sends it to the user's terminal. This process is performed in real time, resulting in smooth gameplay.

[0036] Terminal-side processing

[0037] The user's device receives a notification from the server and confirms that it is ready for a match. When the user enters a move in the game, that information is sent to the server. The next move from the AI ​​agent is displayed on the device, allowing the user to experience a realistic match against a professional-level player. After the game ends, feedback provided by the server is displayed on the device, allowing the user to evaluate their own performance.

[0038] User experience

[0039] Users can play against an AI agent anytime, anywhere, from a device that runs smoothly. For example, suppose user B starts a chess game and chooses a standard opening as their first move. The server-trained AI agent responds to this and develops a strategy in the middle game. After the game ends, the server provides feedback on user B's strengths and areas for improvement in that game, allowing user B to plan how to improve their tactics for their next game.

[0040] Thus, this system has a specific operational model that provides professional-level competitive opportunities through AI agents and supports the improvement of users' skills.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects professional players' game data from the internet and existing datasets. It then cleans the collected data and converts it into a format suitable for training AI models.

[0044] Step 2:

[0045] The server uses the collected data to train a generative AI model. Through this training, the model learns the strategies of professional players and acquires the ability to predict appropriate moves.

[0046] Step 3:

[0047] Users access the system using their devices and select the game they wish to play. They can also set the opponent's strength and the scenario.

[0048] Step 4:

[0049] The server activates the corresponding AI agent based on the user's selection. It performs the initial game setup and notifies the user's device that the match is ready.

[0050] Step 5:

[0051] The user inputs their next move via their device and sends it to the server. The server receives this information.

[0052] Step 6:

[0053] The server uses the user's input to have an AI agent calculate the optimal next move. The calculation result is then sent to the user's terminal and displayed.

[0054] Step 7:

[0055] The user looks at the moves suggested by the AI ​​agent, considers their next move, and inputs it. This process is repeated until the end of the game.

[0056] Step 8:

[0057] After the game ends, the server analyzes the data collected during the match and generates feedback on the user's gameplay.

[0058] Step 9:

[0059] The server generates feedback and sends it to the user's device. Based on this feedback, the user reviews their play style and strategy and prepares for the next match.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] The challenge lies in providing users with a realistic and effective competitive experience using professional players' match data, and in appropriately generating evaluation information to support users' skill improvement. In particular, it is necessary to go beyond simply imitating matches and understand the characteristics of each user, providing feedback based on those characteristics. Furthermore, it is important to continuously do this, aiming to improve users' skills while reflecting the latest strategies and techniques in real time.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for acquiring professional player match data using an information processing device and creating a generative AI model that learns strategies using said data; means for executing an AI agent corresponding to a game selected by the user and building game preparations; and means for analyzing the moves of the game entered by the user and having the AI ​​agent calculate the next move. This makes it possible to provide the user with individualized and effective evaluation information while mimicking professional-level strategies in real time.

[0065] An "information processing device" is a device for efficiently acquiring, processing, and analyzing data, and includes computers, servers, or similar technological systems.

[0066] "Professional player match data" refers to a dataset that shows the match results and strategies of skilled or expert players in competitive chess.

[0067] A "generative AI model" is an algorithm or system that uses machine learning techniques to mimic performance based on specific data.

[0068] An "AI agent" is an artificial intelligence program designed to operate automatically and determine appropriate strategies and actions in a specific sport.

[0069] "Means of preparing for competition" refers to the methods and processes for setting up the necessary configurations and environment before a competition begins.

[0070] "Game moves" refers to the specific sequence or content of actions or movements chosen by a player during a game.

[0071] "Evaluation information" refers to feedback data regarding areas for improvement and strengths, provided based on the user's competition results and performance.

[0072] This invention aims to provide users with a realistic competitive experience by utilizing match data from professional players, thereby supporting skill improvement. Specific embodiments of this system are described below.

[0073] Server Role

[0074] The server first collects match data from professional players via the internet and cloud storage services. This process utilizes information processing equipment to efficiently acquire and analyze the data. After data collection, the server trains a generative AI model. This training uses machine learning libraries (e.g., TENSORFLOW® and PyTorch), and Python's pandas and NumPy are used for data processing. The generative AI model is trained to mimic the strategies of professional players and provide users with a highly accurate match experience.

[0075] Once a game is selected, the server runs an AI agent corresponding to that game. Here, independent AI agents are used depending on the type of game, each executing an appropriate strategy based on a generated AI model.

[0076] Terminal role

[0077] The user's device receives notifications from the server and confirms that it is ready for the match. When the user selects a specific move during the game, that information is immediately sent to the server. When information about the next move is returned from the server, it is displayed in the user interface to facilitate a smooth match.

[0078] User experience

[0079] Users can experience professional-level matches anywhere through their devices. For example, if user B starts a chess game, they might choose a standard chess opening. The server activates an AI agent for chess, calculates the next move in response to the user's move, and develops a mid-game strategy. After the match ends, the server evaluates the user's play and provides feedback on their strengths and areas for improvement. This allows user B to improve their tactics for future games.

[0080] A specific example of a prompt message would be, "When predicting your next move, refer to data from past professional players and choose the most effective strategy in the middle game." The overall structure of this system allows users to improve their skills while gaining near-professional match experience.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The server begins collecting game data from professional players. It specifies available internet and cloud storage data sources as input and retrieves the data. Data processing software is used to structure the collected data and convert it into a format suitable for training a generative AI model. The output is a trainable dataset.

[0084] Step 2:

[0085] The server trains a generative AI model. It uses a formatted dataset as input and leverages machine learning libraries (e.g., TensorFlow or PyTorch) to train the model. Here, a multi-layer neural network is commonly used to learn the strategic patterns of professional players from the data. The output is a trained AI model capable of mimicking the strategies of professional players.

[0086] Step 3:

[0087] The server launches a specific AI agent based on the user's selection. The input includes the type of game selected by the user and its settings. Based on this information, the server loads and executes the corresponding AI agent program. The output is the initialized state of the AI ​​agent corresponding to the game.

[0088] Step 4:

[0089] The user's device receives notifications from the server and displays the readiness status for the match. It receives notification data from the server as input and displays it on the user interface. Here, it signals the user to start the game. The output is a screen display indicating that the match is ready.

[0090] Step 5:

[0091] The user inputs their moves in the game using a terminal. The terminal sends the input data from the user to the server. It receives information about the user's moves as input and converts that data into packets for transmission to the server. The output is the move data sent to the server.

[0092] Step 6:

[0093] The server receives move data from the user and calculates the next move using a generated AI model. It receives data about the user's moves and the current game situation as input and performs calculations based on the AI ​​model. The output is decision information regarding the next move.

[0094] Step 7:

[0095] The server sends the calculated next move information to the user's terminal. It uses move data calculated by the AI ​​model as input, converts it into a format the user can understand, and then sends it. The output is the next move information received by the terminal.

[0096] Step 8:

[0097] The user's device displays the information about the next move it has received on the screen. It receives move information from the server as input and renders it to reflect on the game screen. The output is the current game display that the user can visually confirm.

[0098] Step 9:

[0099] After the game ends, the server analyzes the game data and generates feedback for the user. It takes the user's and AI agent's game history as input and performs analysis using an evaluation algorithm. The output is feedback information highlighting the user's strengths and areas for improvement.

[0100] Step 10:

[0101] The user's device receives feedback from the server and displays it to the user. It receives feedback data from the server as input and displays it on the device. The output is a screen display of evaluation information useful to the user.

[0102] (Application Example 1)

[0103] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0104] In modern society, as local communities become increasingly ties, there is a growing need to increase opportunities for interaction among residents and enhance a sense of community. However, traditional methods are limited in their ability to plan events that initiate interaction and in engaging participants, making it difficult to efficiently promote community interaction. In particular, providing opportunities for interaction that can be enjoyed by a wide range of generations, from young people to the elderly, is a crucial issue that contributes to the sustainable development of communities.

[0105] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0106] This invention includes a server that collects match data from professional players and trains a generative AI model that learns strategies using the data; a system that allows participation in community tournaments to promote interaction at local events; and a system that activates an AI agent corresponding to a game selected by the user and prepares it for battle. This makes it possible to promote interaction among residents and enhance a sense of community unity through local events that can be participated in by a wide range of generations.

[0107] "Professional player match data" refers to records of matches played by advanced players with competitive experience and knowledge, and this data serves as foundational material for AI to learn strategies.

[0108] A "generative AI model" is an algorithm that uses machine learning techniques to imitate and learn the skills and strategies of professional players, providing users with an advanced competitive experience.

[0109] "Community events" are various participatory activities aimed at promoting interaction among residents and enhancing a sense of unity within a specific area.

[0110] An "AI agent" is a software component that automatically calculates strategies in a game selected by the user and plays against the user in that game.

[0111] A "community tournament" is an event involving competitions and games that local residents participate in, serving as a place to revitalize interaction among residents.

[0112] To implement this invention, it is necessary to build a system centered around the interaction between a server, a terminal, and a user. The server is responsible for collecting and analyzing professional player match data to train a generative AI model that forms the basis of game matches. This training utilizes machine learning frameworks such as TensorFlow to create an AI model that mimics professional-level strategies.

[0113] The server provides a means to activate an AI agent corresponding to the game selected by participants when planning local events. The server receives game moves from users, and based on these, the AI ​​agent calculates the next move in real time and sends it to the user's terminal. This communication and processing uses internet-based real-time communication technology with FastAPI.

[0114] The device will have an application developed with Flutter®, which enables multi-platform compatibility, installed, allowing users to register for community tournaments. After each game, the application will receive and display feedback from the server. This helps users improve their skills and facilitates knowledge sharing within the community.

[0115] Through this, users can participate in local community tournaments held as smart city events and learn professional strategies by playing against AI. For example, a chess tournament could be held at a local social event, and participants could enjoy playing against an AI agent. An example of a prompt to the generated AI model would be an instruction such as, "Generate a standard chess opening and a mid-game strategy based on it." This helps users to gain opportunities for further skill improvement.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server collects match data from professional players. Its input is match records obtained from internet databases and online game platforms. This data is then analyzed and processed to extract player behavior history and strategies. The output is a training dataset for a generative AI model.

[0119] Step 2:

[0120] The server trains the generated AI model. It uses the training dataset generated in step 1 as input. Based on this dataset, it performs data computations to train the AI ​​model using machine learning frameworks such as TensorFlow. The output is an AI model capable of mimicking the strategies of professional players.

[0121] Step 3:

[0122] Users apply to participate in community tournaments via their devices. Input involves using the interface of an application installed on the device to select a game and enter user information. Output is that the application is recorded on the server, and a corresponding AI agent is prepared.

[0123] Step 4:

[0124] The server activates an AI agent corresponding to the game selected by the user. It receives the user's game selection information as input. The AI ​​agent loads the necessary data to execute a strategy using a generated AI model and prepares for the match. The output is the activation of a playable AI agent.

[0125] Step 5:

[0126] The user plays the game on their device and inputs their moves. The user's moves during the game are transmitted from the device as input. This information is sent to a server, where the AI ​​agent performs real-time calculations to determine the next move. The AI ​​agent's move is then displayed on the user's device as output.

[0127] Step 6:

[0128] The server generates and provides feedback to the user after the game ends. As input, it analyzes the user's hand movements and action history during the game. Based on this, it processes the data to identify the user's strengths and areas for improvement. As output, the feedback information is displayed on the user's device, and advice for the next game is provided.

[0129] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0130] A specific embodiment of this invention requires the construction of an AI agent system that combines an emotion engine. The details are shown below.

[0131] Server-side processing

[0132] The server collects game data from professional players and trains a generative AI model that can mimic professional tactics. Furthermore, the server is equipped with an emotion engine that analyzes emotions in real time from camera images and audio data based on the user's input and actions during gameplay. The output of this emotion engine is reflected in the AI ​​agent's responses and feedback.

[0133] Terminal-side processing

[0134] The user's device runs the game and sends user input to the server. Furthermore, the device provides the user's voice and facial expressions to the emotion engine, transferring this information to the server. The device uses this data to recognize the user's emotional state, thereby personalizing the game experience.

[0135] User experience

[0136] When a user starts a game using their device, an AI agent takes over as an opponent. For example, suppose user C selects a shogi (Japanese chess) game and enters the opening round. The server analyzes user C's emotions in real time, reading their facial expressions and voice. If user C shows signs of confusion, the server can use its emotion engine to slightly adjust the AI's moves to make them easier for user C to understand, or even offer advice in a conversational format.

[0137] After a game ends, the server provides the user with emotion-based feedback based on the emotion and gameplay data collected during the match. For example, it analyzes which situations tend to cause the user stress and provides advice to help improve future strategies. In this way, by combining an AI agent and an emotion engine, this system can provide users with a more interactive and customized learning environment.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server collects game data from professional players and trains an AI model. The data is cleaned and transformed so that the model can learn professional-level strategies. Once the training is complete, the model is ready to operate as an AI agent.

[0141] Step 2:

[0142] The server sets up an emotion engine and configures it to analyze the user's emotions in real time. This engine has the function of determining the emotional state by analyzing the user's voice and facial expression data.

[0143] Step 3:

[0144] The user operates the device to access the system and select the type of game. They also grant access to the camera and microphone to reflect their emotional state.

[0145] Step 4:

[0146] The device sends the user's selection to the server, which then activates the corresponding AI agent. The game's initial setup is completed, and the user is notified that they are ready to play.

[0147] Step 5:

[0148] The user starts the game through their device and selects and inputs hand movements during gameplay. The device sends this input to the server and also transfers voice and facial expression data to the emotion engine.

[0149] Step 6:

[0150] The server uses the user's input to have the AI ​​agent calculate the optimal next move. Additionally, an emotion engine analyzes the user's emotional state and reflects the results in the AI ​​agent. The AI ​​agent then responds according to the emotional state, for example, by providing gentle advice to reduce stress.

[0151] Step 7:

[0152] The device displays the AI ​​agent's calculation results and suggestions to the user. The user reviews the AI ​​agent's actions and continues playing the game.

[0153] Step 8:

[0154] After the game ends, the server generates feedback on the user's performance based on match data and emotional data. The analysis results, including emotional fluctuations and stress points, are sent to the user's device.

[0155] Step 9:

[0156] The device provides feedback to the user. Based on the information provided, the user analyzes their play style and revises their strategy for the next match.

[0157] (Example 2)

[0158] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0159] Conventional AI-based competitive gaming systems suffer from a lack of dynamic responses that take into account the user's emotional state, resulting in a limited user experience. Furthermore, insufficient feedback tailored to the user's skill level and proficiency level hinders skill improvement.

[0160] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0161] In this invention, the server includes means for collecting match records obtained from professional athletes and using those records to train an artificial intelligence model for learning tactics; means for analyzing the user's emotions and adjusting the AI ​​program's response based on emotion recognition; and means for saving the user's operation records multiple times and evaluating technical improvements. This enables interactive feedback that responds to the user's emotional state and effectively supports the user's skill improvement.

[0162] A "professional athlete" refers to an individual or group that possesses advanced skills in a particular sport and has been recognized for achieving a certain level of success within that sport.

[0163] "Match record" refers to data that records each step, action, and result in a match between players in a competitive game.

[0164] An "artificial intelligence model" is a software structure that autonomously makes decisions and predictions by learning from data, and often includes machine learning algorithms.

[0165] "Competition" refers to matches or contests between players conducted according to rules, and includes a wide variety of genres and activities that involve unusual behavior.

[0166] "Users" refer to individuals or groups who use this system to participate in competitions or gain experiences.

[0167] "Information" refers to knowledge, data, or advice generated or provided by a system, and the content conveyed to the user.

[0168] "Emotion recognition" refers to a technology that detects and identifies a user's emotional state by analyzing their digital data.

[0169] "Attributes" refer to the individual characteristics and traits of users, and include elements that may affect the system's operation and feedback.

[0170] This invention provides an artificial intelligence agent system that utilizes emotion recognition technology. The specific implementation method is described below.

[0171] Server-side processing:

[0172] The server collects a large amount of match records provided by professional players and uses this data to train a generative AI model using a machine learning framework. Specifically, it utilizes frameworks such as TensorFlow and PyTorch to train the model to find the optimal moves in various situations within a match. The server also processes image and audio data sent by users in real time and analyzes the user's emotional state through an emotion recognition API. This analysis process typically uses Microsoft® Azure® Face API or Google® Cloud Speech-to-Text.

[0173] Terminal-side processing:

[0174] The terminal functions as a platform where users participate in the competition via an interface, instantly transmitting user actions and inputs to the server. The terminal is also equipped with a camera and microphone, which collect the user's facial expressions and voice. This allows the terminal to acquire user emotion data and transmit it to the server in real time. Typically, high-performance personal computers or smart devices are used as the terminals.

[0175] User experience:

[0176] When a user starts a game using their device, an artificial intelligence agent is assigned as their opponent. For example, if the user chooses chess, the AI ​​agent will make moves based on professional tactics in the opening stages. If the user shows signs of confusion, the server performs emotion analysis, allowing the AI ​​agent to adjust its reaction and provide advice.

[0177] Examples of specific cases and prompt statements:

[0178] For example, the system can analyze where users tend to feel stressed during the process of improving their skills through the game, and then advise them to pay attention to different tactics next time. An example of a prompt message might be, "Please explain how a system can utilize professional match records to provide feedback that takes user emotions into account."

[0179] Thus, the present invention makes it possible to construct a system that provides dynamic feedback corresponding to the user's emotional state and supports an individualized learning experience.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The server collects match records from professional players into a database. The input data includes the moves and results for each phase of the game. This data is then fed into a machine learning framework to train a generative AI model. The output is an AI model that has learned to identify the optimal moves within a game. Specifically, the dataset is preprocessed, converted into a format suitable for the model, and then the training process is executed.

[0183] Step 2:

[0184] When a user starts a game, the device uses its camera and microphone to capture the user's facial expressions and voice data. This data becomes input and is sent to the server for emotion recognition API analysis. The server inputs information obtained from facial feature points and voice tone into the emotion engine and performs analysis. The output is the user's current emotional state. Specifically, data collection begins when the user clicks the mouse to start the game.

[0185] Step 3:

[0186] The server adjusts the AI ​​agent's actions in real time based on emotional data and game progress information sent from the terminal. Input data includes the user's emotional state and the current game situation. Based on this, a generative AI model is used to calculate the next action, generating the adjusted AI agent's behavior as output. Specifically, if the user is confused, the AI ​​can choose a gentler move or offer advice.

[0187] Step 4:

[0188] At the end of a game, the server analyzes the acquired emotional and gameplay data to generate feedback that helps improve the user's skills. Input data includes the player's action log and emotional state during the match. The server aggregates this data and generates feedback that includes where the user struggled and areas for improvement. Specifically, after the analysis, advice for the next game is displayed on the user's screen.

[0189] (Application Example 2)

[0190] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0191] Many modern AI game systems provide a uniform competitive experience without considering the user's emotional changes, resulting in a poor user experience and making it difficult to provide learning support and skill improvement tailored to individual users. In this situation, there is a need to provide a personalized experience that takes into account the emotional state of each user, thereby realizing a more effective learning environment.

[0192] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0193] This invention includes a server that collects game data from professional players and uses this data to train a generative AI model that learns strategies; a server that recognizes the user's emotional state and personalizes the game experience; and a server that provides emotion-based learning support after the game ends. This not only promotes the user's skill improvement but also provides a more user-friendly and effective learning experience.

[0194] "Professional player match data" refers to record data about matches and games played by highly skilled, professional players in a particular sport or game.

[0195] A "generative AI model" is an artificial intelligence system that uses a large dataset to learn and generate responses with high accuracy to specific tasks or strategies.

[0196] An "AI agent" is a program equipped with artificial intelligence that automatically determines and executes actions in response to specific environments and user input.

[0197] "User emotional state" refers to the state in which a user exhibits psychological and emotional responses at a particular moment, which can be detected from facial expressions, tone of voice, and other factors.

[0198] "Feedback" refers to evaluations, advice, or guidelines for learning improvement that a system provides based on the user's actions and results.

[0199] Personalization refers to optimizing content to provide information and experiences tailored to the individual characteristics and needs of each user.

[0200] "Learning support" refers to support and guidance provided to facilitate the acquisition of specific content or skills.

[0201] To implement this invention, it is necessary to build a system in which a server and a terminal work together. The server collects game data from professional players and uses this data to train a generative AI model. This generative AI model calculates strategies and next moves in the game selected by the user. The server is also equipped with emotion recognition capabilities and analyzes image and audio data transmitted from the user's terminal in real time. Emotion recognition APIs such as the Google Cloud Vision API can be used for emotion recognition.

[0202] On the device, the user runs the game using the device and sends input data and data acquired from the camera and microphone to the server. The feedback provided by the server reflects the user's emotional state and personalizes the user's gaming experience.

[0203] A concrete example of this system is a scenario where a user wears smart glasses and interacts with an AI robot designed to assist with studying. The robot can present math problems, read the user's facial expressions, and provide hints while adjusting the difficulty level. In this scenario, the use of a generative AI model ensures that appropriate advice and problems tailored to the user are provided in real time.

[0204] An example of a prompt message is, "The user appears confused. Please advise on the most effective way to explain the math problem to the user." In this way, it is possible to provide an interactive support environment tailored to each individual user.

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The user starts the device and begins the game. The device uses its camera and microphone to capture the user's facial expressions and voice, and sends this data to the server as input. On the server side, the received data is used to analyze the user's emotional state in real time.

[0208] Step 2:

[0209] The server uses an emotion recognition API to analyze the user's emotions and inputs the results into a generative AI model. The generative AI model calculates the optimal next move based on the analysis results and professional player game data. This analysis result is then reflected in the user's strategy within the game.

[0210] Step 3:

[0211] When users decide to continue or retry a game, they receive strategic and emotionally-based advice from the server. The server provides this advice to the user as voice using a speech synthesis API, allowing users to receive real-time feedback on their next actions.

[0212] Step 4:

[0213] After a game ends, the server records play data and emotional data to measure the user's skill improvement. Based on this, it generates appropriate feedback for the next game and provides it to the user via email or in-app notification. This data allows for adjustments to the long-term learning plan.

[0214] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0215] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0230] In order to implement this invention, it is necessary to construct a competitive game system using an AI agent through the interaction of a server, a terminal, and a user.

[0231] Server-side processing

[0232] The server first collects game data from professional players via the internet and datasets, and uses this data to train a generative AI model. Because this model has the ability to mimic the strategies of professional players, it can provide users with a realistic game experience. The server receives game selections from users and activates the corresponding AI agent. During a game, the server receives the user's moves, and the AI ​​agent calculates the next move based on those moves and sends it to the user's terminal. This process is performed in real time, resulting in smooth gameplay.

[0233] Terminal-side processing

[0234] The user's device receives a notification from the server and confirms that it is ready for a match. When the user enters a move in the game, that information is sent to the server. The next move from the AI ​​agent is displayed on the device, allowing the user to experience a realistic match against a professional-level player. After the game ends, feedback provided by the server is displayed on the device, allowing the user to evaluate their own performance.

[0235] User experience

[0236] Users can play against an AI agent anytime, anywhere, from a device that runs smoothly. For example, suppose user B starts a chess game and chooses a standard opening as their first move. The server-trained AI agent responds to this and develops a strategy in the middle game. After the game ends, the server provides feedback on user B's strengths and areas for improvement in that game, allowing user B to plan how to improve their tactics for their next game.

[0237] Thus, this system has a specific operational model that provides professional-level competitive opportunities through AI agents and supports the improvement of users' skills.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The server collects professional players' game data from the internet and existing datasets. It then cleans the collected data and converts it into a format suitable for training AI models.

[0241] Step 2:

[0242] The server uses the collected data to train a generative AI model. Through this training, the model learns the strategies of professional players and acquires the ability to predict appropriate moves.

[0243] Step 3:

[0244] Users access the system using their devices and select the game they wish to play. They can also set the opponent's strength and the scenario.

[0245] Step 4:

[0246] The server activates the corresponding AI agent based on the user's selection. It performs the initial game setup and notifies the user's device that the match is ready.

[0247] Step 5:

[0248] The user inputs their next move via their device and sends it to the server. The server receives this information.

[0249] Step 6:

[0250] The server uses the user's input to have an AI agent calculate the optimal next move. The calculation result is then sent to the user's terminal and displayed.

[0251] Step 7:

[0252] The user looks at the moves suggested by the AI ​​agent, considers their next move, and inputs it. This process is repeated until the end of the game.

[0253] Step 8:

[0254] After the game ends, the server analyzes the data collected during the match and generates feedback on the user's gameplay.

[0255] Step 9:

[0256] The server generates feedback and sends it to the user's device. Based on this feedback, the user reviews their play style and strategy and prepares for the next match.

[0257] (Example 1)

[0258] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0259] The challenge lies in providing users with a realistic and effective competitive experience using professional players' match data, and in appropriately generating evaluation information to support users' skill improvement. In particular, it is necessary to go beyond simply imitating matches and understand the characteristics of each user, providing feedback based on those characteristics. Furthermore, it is important to continuously do this, aiming to improve users' skills while reflecting the latest strategies and techniques in real time.

[0260] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0261] In this invention, the server includes means for acquiring professional player match data using an information processing device and creating a generative AI model that learns strategies using said data; means for executing an AI agent corresponding to a game selected by the user and building game preparations; and means for analyzing the moves of the game entered by the user and having the AI ​​agent calculate the next move. This makes it possible to provide the user with individualized and effective evaluation information while mimicking professional-level strategies in real time.

[0262] An "information processing device" is a device for efficiently acquiring, processing, and analyzing data, and includes computers, servers, or similar technological systems.

[0263] "Professional player match data" refers to a dataset that shows the match results and strategies of skilled or expert players in competitive chess.

[0264] A "generative AI model" is an algorithm or system that uses machine learning techniques to mimic performance based on specific data.

[0265] An "AI agent" is an artificial intelligence program designed to operate automatically and determine appropriate strategies and actions in a specific sport.

[0266] "Means of preparing for competition" refers to the methods and processes for setting up the necessary configurations and environment before a competition begins.

[0267] "Game moves" refers to the specific sequence or content of actions or movements chosen by a player during a game.

[0268] "Evaluation information" refers to feedback data regarding areas for improvement and strengths, provided based on the user's competition results and performance.

[0269] This invention aims to provide users with a realistic competitive experience by utilizing match data from professional players, thereby supporting skill improvement. Specific embodiments of this system are described below.

[0270] Server Role

[0271] The server first collects match data from professional players via the internet and cloud storage services. This process utilizes information processing equipment to efficiently acquire and analyze the data. After data collection, the server trains a generative AI model. This training uses machine learning libraries (e.g., TensorFlow and PyTorch), and Python's pandas and NumPy are used for data processing. The generative AI model is trained to mimic the strategies of professional players and provide users with a highly accurate match experience.

[0272] Once a game is selected, the server runs an AI agent corresponding to that game. Here, independent AI agents are used depending on the type of game, each executing an appropriate strategy based on a generated AI model.

[0273] Terminal role

[0274] The user's device receives notifications from the server and confirms that it is ready for the match. When the user selects a specific move during the game, that information is immediately sent to the server. When information about the next move is returned from the server, it is displayed in the user interface to facilitate a smooth match.

[0275] User experience

[0276] Users can experience professional-level matches anywhere through their devices. For example, if user B starts a chess game, they might choose a standard chess opening. The server activates an AI agent for chess, calculates the next move in response to the user's move, and develops a mid-game strategy. After the match ends, the server evaluates the user's play and provides feedback on their strengths and areas for improvement. This allows user B to improve their tactics for future games.

[0277] A specific example of a prompt message would be, "When predicting your next move, refer to data from past professional players and choose the most effective strategy in the middle game." The overall structure of this system allows users to improve their skills while gaining near-professional match experience.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The server begins collecting game data from professional players. It specifies available internet and cloud storage data sources as input and retrieves the data. Data processing software is used to structure the collected data and convert it into a format suitable for training a generative AI model. The output is a trainable dataset.

[0281] Step 2:

[0282] The server trains a generative AI model. It uses a formatted dataset as input and leverages machine learning libraries (e.g., TensorFlow or PyTorch) to train the model. Here, a multi-layer neural network is commonly used to learn the strategic patterns of professional players from the data. The output is a trained AI model capable of mimicking the strategies of professional players.

[0283] Step 3:

[0284] The server launches a specific AI agent based on the user's selection. As input, there is the type of game selected by the user and the setting information. Based on this information, the corresponding AI agent program is loaded and executed. The output is the initialized state of the AI agent corresponding to the game.

[0285] Step 4:

[0286] The user's terminal receives a notification from the server and displays the state of being ready for the battle. As input, it receives the notification data from the server and displays it on the user interface. Here, it gives a signal to the user to start the game. The output is a screen display indicating that the battle preparation is complete.

[0287] Step 5:

[0288] The user inputs a move in the game on the terminal. The terminal sends the input data from the user to the server. As input, it receives information about the user's move and converts the data into a packet for transferring it to the server. The output is the move data sent to the server.

[0289] Step 6:

[0290] The server receives the move data from the user and calculates the next move using the generative AI model. As input, it receives data about the user's move and the current game situation and performs calculations based on the AI model. The output is the decision information regarding the next move.

[0291] Step 7:

[0292] The server sends the calculated information about the next move to the user's terminal. As input, it uses the move data calculated by the AI model and converts it into a form that the user can understand and sends it. The output is the information about the next move received by the terminal.

[0293] Step 8:

[0294] The user's device displays the information about the next move it has received on the screen. It receives move information from the server as input and renders it to reflect on the game screen. The output is the current game display that the user can visually confirm.

[0295] Step 9:

[0296] After the game ends, the server analyzes the game data and generates feedback for the user. It takes the user's and AI agent's game history as input and performs analysis using an evaluation algorithm. The output is feedback information highlighting the user's strengths and areas for improvement.

[0297] Step 10:

[0298] The user's device receives feedback from the server and displays it to the user. It receives feedback data from the server as input and displays it on the device. The output is a screen display of evaluation information useful to the user.

[0299] (Application Example 1)

[0300] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0301] In modern society, as local communities become increasingly ties, there is a growing need to increase opportunities for interaction among residents and enhance a sense of community. However, traditional methods are limited in their ability to plan events that initiate interaction and in engaging participants, making it difficult to efficiently promote community interaction. In particular, providing opportunities for interaction that can be enjoyed by a wide range of generations, from young people to the elderly, is a crucial issue that contributes to the sustainable development of communities.

[0302] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0303] In this invention, the server includes means for collecting the player's game data and training a generative AI model that learns strategies using this data, means for providing a system that enables participation in a community tournament to promote communication in regional events, and means for activating an AI agent corresponding to the game selected by the user and preparing for a battle. As a result, it becomes possible to promote communication among residents and enhance the sense of unity in the local community through regional events that can be participated in by a wide range of generations.

[0304] The "player's game data" is a record of games played by advanced players with experience and knowledge of the competition, and it is the basic material for the AI to learn strategies based on this data.

[0305] The "generative AI model" is an algorithm that uses machine learning techniques to imitate and learn the skills and strategies of players and provides users with a high-level battle experience.

[0306] A "regional event" is various participatory activities aimed at promoting communication among residents and enhancing the sense of unity within a specific region.

[0307] An "AI agent" is a software component that automatically calculates strategies in the game selected by the user and conducts battles with the user.

[0308] A "community tournament" is an event of competitions and games participated in by local residents, and it is a venue for activating communication among residents.

[0309] To implement this invention, it is necessary to build a system centered on the interaction between the server, the terminal, and the user. The server plays a role in collecting and analyzing the player's game data in order to train a generative AI model that forms the basis of game battles. By using a machine learning framework such as TensorFlow for this training, an AI model that imitates professional-level strategies is formed.

[0310] The server provides a means to activate an AI agent corresponding to the game selected by participants when planning local events. The server receives game moves from users, and based on these, the AI ​​agent calculates the next move in real time and sends it to the user's terminal. This communication and processing uses internet-based real-time communication technology with FastAPI.

[0311] The device will have an application developed with Flutter, which supports multiple platforms, installed, allowing users to register for community tournaments. After each game, the application will receive and display feedback from the server. This helps users improve their skills and facilitates knowledge sharing within the community.

[0312] Through this, users can participate in local community tournaments held as smart city events and learn professional strategies by playing against AI. For example, a chess tournament could be held at a local social event, and participants could enjoy playing against an AI agent. An example of a prompt to the generated AI model would be an instruction such as, "Generate a standard chess opening and a mid-game strategy based on it." This helps users to gain opportunities for further skill improvement.

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The server collects match data from professional players. Its input is match records obtained from internet databases and online game platforms. This data is then analyzed and processed to extract player behavior history and strategies. The output is a training dataset for a generative AI model.

[0316] Step 2:

[0317] The server trains the generated AI model. It uses the training dataset generated in step 1 as input. Based on this dataset, it performs data computations to train the AI ​​model using machine learning frameworks such as TensorFlow. The output is an AI model capable of mimicking the strategies of professional players.

[0318] Step 3:

[0319] Users apply to participate in community tournaments via their devices. Input involves using the interface of an application installed on the device to select a game and enter user information. Output is that the application is recorded on the server, and a corresponding AI agent is prepared.

[0320] Step 4:

[0321] The server activates an AI agent corresponding to the game selected by the user. It receives the user's game selection information as input. The AI ​​agent loads the necessary data to execute a strategy using a generated AI model and prepares for the match. The output is the activation of a playable AI agent.

[0322] Step 5:

[0323] The user plays the game on their device and inputs their moves. The user's moves during the game are transmitted from the device as input. This information is sent to a server, where the AI ​​agent performs real-time calculations to determine the next move. The AI ​​agent's move is then displayed on the user's device as output.

[0324] Step 6:

[0325] The server generates and provides feedback to the user after the game ends. As input, it analyzes the user's hand movements and action history during the game. Based on this, it processes the data to identify the user's strengths and areas for improvement. As output, the feedback information is displayed on the user's device, and advice for the next game is provided.

[0326] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0327] A specific embodiment of this invention requires the construction of an AI agent system that combines an emotion engine. The details are shown below.

[0328] Server-side processing

[0329] The server collects game data from professional players and trains a generative AI model that can mimic professional tactics. Furthermore, the server is equipped with an emotion engine that analyzes emotions in real time from camera images and audio data based on the user's input and actions during gameplay. The output of this emotion engine is reflected in the AI ​​agent's responses and feedback.

[0330] Terminal-side processing

[0331] The user's device runs the game and sends user input to the server. Furthermore, the device provides the user's voice and facial expressions to the emotion engine, transferring this information to the server. The device uses this data to recognize the user's emotional state, thereby personalizing the game experience.

[0332] User experience

[0333] When a user starts a game using their device, an AI agent takes over as an opponent. For example, suppose user C selects a shogi (Japanese chess) game and enters the opening round. The server analyzes user C's emotions in real time, reading their facial expressions and voice. If user C shows signs of confusion, the server can use its emotion engine to slightly adjust the AI's moves to make them easier for user C to understand, or even offer advice in a conversational format.

[0334] After a game ends, the server provides the user with emotion-based feedback based on the emotion and gameplay data collected during the match. For example, it analyzes which situations tend to cause the user stress and provides advice to help improve future strategies. In this way, by combining an AI agent and an emotion engine, this system can provide users with a more interactive and customized learning environment.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The server collects game data from professional players and trains an AI model. The data is cleaned and transformed so that the model can learn professional-level strategies. Once the training is complete, the model is ready to operate as an AI agent.

[0338] Step 2:

[0339] The server sets up an emotion engine and configures it to analyze the user's emotions in real time. This engine has the function of determining the emotional state by analyzing the user's voice and facial expression data.

[0340] Step 3:

[0341] The user operates the device to access the system and select the type of game. They also grant access to the camera and microphone to reflect their emotional state.

[0342] Step 4:

[0343] The device sends the user's selection to the server, which then activates the corresponding AI agent. The game's initial setup is completed, and the user is notified that they are ready to play.

[0344] Step 5:

[0345] The user starts the game through their device and selects and inputs hand movements during gameplay. The device sends this input to the server and also transfers voice and facial expression data to the emotion engine.

[0346] Step 6:

[0347] The server uses the user's input to have the AI ​​agent calculate the optimal next move. Additionally, an emotion engine analyzes the user's emotional state and reflects the results in the AI ​​agent. The AI ​​agent then responds according to the emotional state, for example, by providing gentle advice to reduce stress.

[0348] Step 7:

[0349] The device displays the AI ​​agent's calculation results and suggestions to the user. The user reviews the AI ​​agent's actions and continues playing the game.

[0350] Step 8:

[0351] After the game ends, the server generates feedback on the user's performance based on match data and emotional data. The analysis results, including emotional fluctuations and stress points, are sent to the user's device.

[0352] Step 9:

[0353] The device provides feedback to the user. Based on the information provided, the user analyzes their play style and revises their strategy for the next match.

[0354] (Example 2)

[0355] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0356] Conventional AI-based competitive gaming systems suffer from a lack of dynamic responses that take into account the user's emotional state, resulting in a limited user experience. Furthermore, insufficient feedback tailored to the user's skill level and proficiency level hinders skill improvement.

[0357] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0358] In this invention, the server includes means for collecting match records obtained from professional athletes and using those records to train an artificial intelligence model for learning tactics; means for analyzing the user's emotions and adjusting the AI ​​program's response based on emotion recognition; and means for saving the user's operation records multiple times and evaluating technical improvements. This enables interactive feedback that responds to the user's emotional state and effectively supports the user's skill improvement.

[0359] A "professional athlete" refers to an individual or group that possesses advanced skills in a particular sport and has been recognized for achieving a certain level of success within that sport.

[0360] "Match record" refers to data that records each step, action, and result in a match between players in a competitive game.

[0361] An "artificial intelligence model" is a software structure that autonomously makes decisions and predictions by learning from data, and often includes machine learning algorithms.

[0362] "Competition" refers to matches or contests between players conducted according to rules, and includes a wide variety of genres and activities that involve unusual behavior.

[0363] "Users" refer to individuals or groups who use this system to participate in competitions or gain experiences.

[0364] "Information" refers to knowledge, data, or advice generated or provided by a system, and the content conveyed to the user.

[0365] "Emotion recognition" refers to a technology that detects and identifies a user's emotional state by analyzing their digital data.

[0366] "Attributes" refer to the individual characteristics and traits of users, and include elements that may affect the system's operation and feedback.

[0367] This invention provides an artificial intelligence agent system that utilizes emotion recognition technology. The specific implementation method is described below.

[0368] Server-side processing:

[0369] The server collects a large amount of match records provided by professional players and uses this data to train a generative AI model using a machine learning framework. Specifically, it utilizes frameworks such as TensorFlow and PyTorch to train the model to find the optimal moves in various situations within a match. The server also processes image and audio data sent by users in real time and analyzes the user's emotional state through an emotion recognition API. This analysis process typically uses Microsoft Azure's Face API or Google Cloud's Speech-to-Text.

[0370] Terminal-side processing:

[0371] The terminal functions as a platform where users participate in the competition via an interface, instantly transmitting user actions and inputs to the server. The terminal is also equipped with a camera and microphone, which collect the user's facial expressions and voice. This allows the terminal to acquire user emotion data and transmit it to the server in real time. Typically, high-performance personal computers or smart devices are used as the terminals.

[0372] User experience:

[0373] When a user starts a game using their device, an artificial intelligence agent is assigned as their opponent. For example, if the user chooses chess, the AI ​​agent will make moves based on professional tactics in the opening stages. If the user shows signs of confusion, the server performs emotion analysis, allowing the AI ​​agent to adjust its reaction and provide advice.

[0374] Examples of specific cases and prompt statements:

[0375] For example, the system can analyze where users tend to feel stressed during the process of improving their skills through the game, and then advise them to pay attention to different tactics next time. An example of a prompt message might be, "Please explain how a system can utilize professional match records to provide feedback that takes user emotions into account."

[0376] Thus, the present invention makes it possible to construct a system that provides dynamic feedback corresponding to the user's emotional state and supports an individualized learning experience.

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] The server collects match records from professional players into a database. The input data includes the moves and results for each phase of the game. This data is then fed into a machine learning framework to train a generative AI model. The output is an AI model that has learned to identify the optimal moves within a game. Specifically, the dataset is preprocessed, converted into a format suitable for the model, and then the training process is executed.

[0380] Step 2:

[0381] When a user starts a game, the device uses its camera and microphone to capture the user's facial expressions and voice data. This data becomes input and is sent to the server for emotion recognition API analysis. The server inputs information obtained from facial feature points and voice tone into the emotion engine and performs analysis. The output is the user's current emotional state. Specifically, data collection begins when the user clicks the mouse to start the game.

[0382] Step 3:

[0383] The server adjusts the AI ​​agent's actions in real time based on emotional data and game progress information sent from the terminal. Input data includes the user's emotional state and the current game situation. Based on this, a generative AI model is used to calculate the next action, generating the adjusted AI agent's behavior as output. Specifically, if the user is confused, the AI ​​can choose a gentler move or offer advice.

[0384] Step 4:

[0385] At the end of a game, the server analyzes the acquired emotional and gameplay data to generate feedback that helps improve the user's skills. Input data includes the player's action log and emotional state during the match. The server aggregates this data and generates feedback that includes where the user struggled and areas for improvement. Specifically, after the analysis, advice for the next game is displayed on the user's screen.

[0386] (Application Example 2)

[0387] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0388] Many modern AI game systems provide a uniform competitive experience without considering the user's emotional changes, resulting in a poor user experience and making it difficult to provide learning support and skill improvement tailored to individual users. In this situation, there is a need to provide a personalized experience that takes into account the emotional state of each user, thereby realizing a more effective learning environment.

[0389] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0390] This invention includes a server that collects game data from professional players and uses this data to train a generative AI model that learns strategies; a server that recognizes the user's emotional state and personalizes the game experience; and a server that provides emotion-based learning support after the game ends. This not only promotes the user's skill improvement but also provides a more user-friendly and effective learning experience.

[0391] "Professional player match data" refers to record data about matches and games played by highly skilled, professional players in a particular sport or game.

[0392] A "generative AI model" is an artificial intelligence system that uses a large dataset to learn and generate responses with high accuracy to specific tasks or strategies.

[0393] An "AI agent" is a program equipped with artificial intelligence that automatically determines and executes actions in response to specific environments and user input.

[0394] "User emotional state" refers to the state in which a user exhibits psychological and emotional responses at a particular moment, which can be detected from facial expressions, tone of voice, and other factors.

[0395] "Feedback" refers to evaluations, advice, or guidelines for learning improvement that a system provides based on the user's actions and results.

[0396] Personalization refers to optimizing content to provide information and experiences tailored to the individual characteristics and needs of each user.

[0397] "Learning support" refers to support and guidance provided to facilitate the acquisition of specific content or skills.

[0398] To implement this invention, it is necessary to build a system in which a server and a terminal work together. The server collects game data from professional players and uses this data to train a generative AI model. This generative AI model calculates strategies and next moves in the game selected by the user. The server is also equipped with emotion recognition capabilities and analyzes image and audio data transmitted from the user's terminal in real time. Emotion recognition APIs such as the Google Cloud Vision API can be used for emotion recognition.

[0399] On the device, the user runs the game using the device and sends input data and data acquired from the camera and microphone to the server. The feedback provided by the server reflects the user's emotional state and personalizes the user's gaming experience.

[0400] A concrete example of this system is a scenario where a user wears smart glasses and interacts with an AI robot designed to assist with studying. The robot can present math problems, read the user's facial expressions, and provide hints while adjusting the difficulty level. In this scenario, the use of a generative AI model ensures that appropriate advice and problems tailored to the user are provided in real time.

[0401] An example of a prompt message is, "The user appears confused. Please advise on the most effective way to explain the math problem to the user." In this way, it is possible to provide an interactive support environment tailored to each individual user.

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] The user starts the device and begins the game. The device uses its camera and microphone to capture the user's facial expressions and voice, and sends this data to the server as input. On the server side, the received data is used to analyze the user's emotional state in real time.

[0405] Step 2:

[0406] The server uses an emotion recognition API to analyze the user's emotions and inputs the results into a generative AI model. The generative AI model calculates the optimal next move based on the analysis results and professional player game data. This analysis result is then reflected in the user's strategy within the game.

[0407] Step 3:

[0408] When users decide to continue or retry a game, they receive strategic and emotionally-based advice from the server. The server provides this advice to the user as voice using a speech synthesis API, allowing users to receive real-time feedback on their next actions.

[0409] Step 4:

[0410] After a game ends, the server records play data and emotional data to measure the user's skill improvement. Based on this, it generates appropriate feedback for the next game and provides it to the user via email or in-app notification. This data allows for adjustments to the long-term learning plan.

[0411] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0412] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0413] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0417] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0418] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0419] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0420] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0421] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0422] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0423] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0424] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0425] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0426] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0427] In order to implement this invention, it is necessary to construct a competitive game system using an AI agent through the interaction of a server, a terminal, and a user.

[0428] Server-side processing

[0429] The server first collects game data from professional players via the internet and datasets, and uses this data to train a generative AI model. Because this model has the ability to mimic the strategies of professional players, it can provide users with a realistic game experience. The server receives game selections from users and activates the corresponding AI agent. During a game, the server receives the user's moves, and the AI ​​agent calculates the next move based on those moves and sends it to the user's terminal. This process is performed in real time, resulting in smooth gameplay.

[0430] Terminal-side processing

[0431] The user's device receives a notification from the server and confirms that it is ready for a match. When the user enters a move in the game, that information is sent to the server. The next move from the AI ​​agent is displayed on the device, allowing the user to experience a realistic match against a professional-level player. After the game ends, feedback provided by the server is displayed on the device, allowing the user to evaluate their own performance.

[0432] User experience

[0433] Users can play against an AI agent anytime, anywhere, from a device that runs smoothly. For example, suppose user B starts a chess game and chooses a standard opening as their first move. The server-trained AI agent responds to this and develops a strategy in the middle game. After the game ends, the server provides feedback on user B's strengths and areas for improvement in that game, allowing user B to plan how to improve their tactics for their next game.

[0434] Thus, this system has a specific operational model that provides professional-level competitive opportunities through AI agents and supports the improvement of users' skills.

[0435] The following describes the processing flow.

[0436] Step 1:

[0437] The server collects professional players' game data from the internet and existing datasets. It then cleans the collected data and converts it into a format suitable for training AI models.

[0438] Step 2:

[0439] The server uses the collected data to train a generative AI model. Through this training, the model learns the strategies of professional players and acquires the ability to predict appropriate moves.

[0440] Step 3:

[0441] Users access the system using their devices and select the game they wish to play. They can also set the opponent's strength and the scenario.

[0442] Step 4:

[0443] The server activates the corresponding AI agent based on the user's selection. It performs the initial game setup and notifies the user's device that the match is ready.

[0444] Step 5:

[0445] The user inputs their next move via their device and sends it to the server. The server receives this information.

[0446] Step 6:

[0447] The server uses the user's input to have an AI agent calculate the optimal next move. The calculation result is then sent to the user's terminal and displayed.

[0448] Step 7:

[0449] The user looks at the moves suggested by the AI ​​agent, considers their next move, and inputs it. This process is repeated until the end of the game.

[0450] Step 8:

[0451] After the game ends, the server analyzes the data collected during the match and generates feedback on the user's gameplay.

[0452] Step 9:

[0453] The server generates feedback and sends it to the user's device. Based on this feedback, the user reviews their play style and strategy and prepares for the next match.

[0454] (Example 1)

[0455] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0456] The challenge lies in providing users with a realistic and effective competitive experience using professional players' match data, and in appropriately generating evaluation information to support users' skill improvement. In particular, it is necessary to go beyond simply imitating matches and understand the characteristics of each user, providing feedback based on those characteristics. Furthermore, it is important to continuously do this, aiming to improve users' skills while reflecting the latest strategies and techniques in real time.

[0457] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0458] In this invention, the server includes means for acquiring professional player match data using an information processing device and creating a generative AI model that learns strategies using said data; means for executing an AI agent corresponding to a game selected by the user and building game preparations; and means for analyzing the moves of the game entered by the user and having the AI ​​agent calculate the next move. This makes it possible to provide the user with individualized and effective evaluation information while mimicking professional-level strategies in real time.

[0459] An "information processing device" is a device for efficiently acquiring, processing, and analyzing data, and includes computers, servers, or similar technological systems.

[0460] "Professional player match data" refers to a dataset that shows the match results and strategies of skilled or expert players in competitive chess.

[0461] A "generative AI model" is an algorithm or system that uses machine learning techniques to mimic performance based on specific data.

[0462] An "AI agent" is an artificial intelligence program designed to operate automatically and determine appropriate strategies and actions in a specific sport.

[0463] "Means of preparing for competition" refers to the methods and processes for setting up the necessary configurations and environment before a competition begins.

[0464] "Game moves" refers to the specific sequence or content of actions or movements chosen by a player during a game.

[0465] "Evaluation information" refers to feedback data regarding areas for improvement and strengths, provided based on the user's competition results and performance.

[0466] This invention aims to provide users with a realistic competitive experience by utilizing match data from professional players, thereby supporting skill improvement. Specific embodiments of this system are described below.

[0467] Server Role

[0468] The server first collects match data from professional players via the internet and cloud storage services. This process utilizes information processing equipment to efficiently acquire and analyze the data. After data collection, the server trains a generative AI model. This training uses machine learning libraries (e.g., TensorFlow and PyTorch), and Python's pandas and NumPy are used for data processing. The generative AI model is trained to mimic the strategies of professional players and provide users with a highly accurate match experience.

[0469] Once a game is selected, the server runs an AI agent corresponding to that game. Here, independent AI agents are used depending on the type of game, each executing an appropriate strategy based on a generated AI model.

[0470] Terminal role

[0471] The user's device receives notifications from the server and confirms that it is ready for the match. When the user selects a specific move during the game, that information is immediately sent to the server. When information about the next move is returned from the server, it is displayed in the user interface to facilitate a smooth match.

[0472] User experience

[0473] Users can experience professional-level matches anywhere through their devices. For example, if user B starts a chess game, they might choose a standard chess opening. The server activates an AI agent for chess, calculates the next move in response to the user's move, and develops a mid-game strategy. After the match ends, the server evaluates the user's play and provides feedback on their strengths and areas for improvement. This allows user B to improve their tactics for future games.

[0474] A specific example of a prompt message would be, "When predicting your next move, refer to data from past professional players and choose the most effective strategy in the middle game." The overall structure of this system allows users to improve their skills while gaining near-professional match experience.

[0475] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0476] Step 1:

[0477] The server begins collecting game data from professional players. It specifies available internet and cloud storage data sources as input and retrieves the data. Data processing software is used to structure the collected data and convert it into a format suitable for training a generative AI model. The output is a trainable dataset.

[0478] Step 2:

[0479] The server trains a generative AI model. It uses a formatted dataset as input and leverages machine learning libraries (e.g., TensorFlow or PyTorch) to train the model. Here, a multi-layer neural network is commonly used to learn the strategic patterns of professional players from the data. The output is a trained AI model capable of mimicking the strategies of professional players.

[0480] Step 3:

[0481] The server launches a specific AI agent based on the user's selection. The input includes the type of game selected by the user and its settings. Based on this information, the server loads and executes the corresponding AI agent program. The output is the initialized state of the AI ​​agent corresponding to the game.

[0482] Step 4:

[0483] The user's device receives notifications from the server and displays the readiness status for the match. It receives notification data from the server as input and displays it on the user interface. Here, it signals the user to start the game. The output is a screen display indicating that the match is ready.

[0484] Step 5:

[0485] The user inputs their moves into the game via a terminal. The terminal sends the input data from the user to the server. It receives information about the user's moves as input and converts that data into packets for transmission to the server. The output is the move data sent to the server.

[0486] Step 6:

[0487] The server receives move data from the user and calculates the next move using a generated AI model. It receives data about the user's moves and the current game situation as input and performs calculations based on the AI ​​model. The output is decision information regarding the next move.

[0488] Step 7:

[0489] The server sends the calculated next move information to the user's terminal. It uses move data calculated by the AI ​​model as input, converts it into a format the user can understand, and then sends it. The output is the next move information received by the terminal.

[0490] Step 8:

[0491] The user's device displays the information about the next move it has received on the screen. It receives move information from the server as input and renders it to reflect on the game screen. The output is the current game display that the user can visually confirm.

[0492] Step 9:

[0493] After the game ends, the server analyzes the game data and generates feedback for the user. It takes the user's and AI agent's game history as input and performs analysis using an evaluation algorithm. The output is feedback information highlighting the user's strengths and areas for improvement.

[0494] Step 10:

[0495] The user's device receives feedback from the server and displays it to the user. It receives feedback data from the server as input and displays it on the device. The output is a screen display of evaluation information useful to the user.

[0496] (Application Example 1)

[0497] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0498] In modern society, as local communities become increasingly ties, there is a growing need to increase opportunities for interaction among residents and enhance a sense of community. However, traditional methods are limited in their ability to plan events that initiate interaction and in engaging participants, making it difficult to efficiently promote community interaction. In particular, providing opportunities for interaction that can be enjoyed by a wide range of generations, from young people to the elderly, is a crucial issue that contributes to the sustainable development of communities.

[0499] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0500] This invention includes a server that collects match data from professional players and trains a generative AI model that learns strategies using the data; a system that allows participation in community tournaments to promote interaction at local events; and a system that activates an AI agent corresponding to a game selected by the user and prepares it for battle. This makes it possible to promote interaction among residents and enhance a sense of community unity through local events that can be participated in by a wide range of generations.

[0501] "Professional player match data" refers to records of matches played by advanced players with competitive experience and knowledge, and this data serves as foundational material for AI to learn strategies.

[0502] A "generative AI model" is an algorithm that uses machine learning techniques to imitate and learn the skills and strategies of professional players, providing users with an advanced competitive experience.

[0503] "Community events" are various participatory activities aimed at promoting interaction among residents and enhancing a sense of unity within a specific area.

[0504] An "AI agent" is a software component that automatically calculates strategies in a game selected by the user and plays against the user in that game.

[0505] A "community tournament" is an event involving competitions and games that local residents participate in, serving as a place to revitalize interaction among residents.

[0506] To implement this invention, it is necessary to build a system centered around the interaction between a server, a terminal, and a user. The server is responsible for collecting and analyzing professional player match data to train a generative AI model that forms the basis of game matches. This training utilizes machine learning frameworks such as TensorFlow to create an AI model that mimics professional-level strategies.

[0507] The server provides a means to activate an AI agent corresponding to the game selected by participants when planning local events. The server receives game moves from users, and based on these, the AI ​​agent calculates the next move in real time and sends it to the user's terminal. This communication and processing uses internet-based real-time communication technology with FastAPI.

[0508] The device will have an application developed with Flutter, which supports multiple platforms, installed, allowing users to register for community tournaments. After each game, the application will receive and display feedback from the server. This helps users improve their skills and facilitates knowledge sharing within the community.

[0509] Through this, users can participate in local community tournaments held as smart city events and learn professional strategies by playing against AI. For example, a chess tournament could be held at a local social event, and participants could enjoy playing against an AI agent. An example of a prompt to the generated AI model would be an instruction such as, "Generate a standard chess opening and a mid-game strategy based on it." This helps users to gain opportunities for further skill improvement.

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The server collects match data from professional players. Its input is match records obtained from internet databases and online game platforms. This data is then analyzed and processed to extract player behavior history and strategies. The output is a training dataset for a generative AI model.

[0513] Step 2:

[0514] The server trains the generated AI model. It uses the training dataset generated in step 1 as input. Based on this dataset, it performs data computations to train the AI ​​model using machine learning frameworks such as TensorFlow. The output is an AI model capable of mimicking the strategies of professional players.

[0515] Step 3:

[0516] Users apply to participate in community tournaments via their devices. Input involves using the interface of an application installed on the device to select a game and enter user information. Output is that the application is recorded on the server, and a corresponding AI agent is prepared.

[0517] Step 4:

[0518] The server activates an AI agent corresponding to the game selected by the user. It receives the user's game selection information as input. The AI ​​agent loads the necessary data to execute a strategy using a generated AI model and prepares for the match. The output is the activation of a playable AI agent.

[0519] Step 5:

[0520] The user plays the game on their device and inputs their moves. The user's moves during the game are transmitted from the device as input. This information is sent to a server, where the AI ​​agent performs real-time calculations to determine the next move. The AI ​​agent's moves are then displayed on the user's device as output.

[0521] Step 6:

[0522] The server generates and provides feedback to the user after the game ends. As input, it analyzes the user's hand movements and action history during the game. Based on this, it processes the data to identify the user's strengths and areas for improvement. As output, the feedback information is displayed on the user's device, and advice for the next game is provided.

[0523] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0524] A specific embodiment of this invention requires the construction of an AI agent system that combines an emotion engine. The details are shown below.

[0525] Server-side processing

[0526] The server collects game data from professional players and trains a generative AI model that can mimic professional tactics. Furthermore, the server is equipped with an emotion engine that analyzes emotions in real time from camera images and audio data based on the user's input and actions during gameplay. The output of this emotion engine is reflected in the AI ​​agent's responses and feedback.

[0527] Terminal-side processing

[0528] The user's device runs the game and sends user input to the server. Furthermore, the device provides the user's voice and facial expressions to the emotion engine, transferring this information to the server. The device uses this data to recognize the user's emotional state, thereby personalizing the game experience.

[0529] User experience

[0530] When a user starts a game using their device, an AI agent takes over as an opponent. For example, suppose user C selects a shogi (Japanese chess) game and enters the opening round. The server analyzes user C's emotions in real time, reading their facial expressions and voice. If user C shows signs of confusion, the server can use its emotion engine to slightly adjust the AI's moves to make them easier for user C to understand, or even offer advice in a conversational format.

[0531] After a game ends, the server provides the user with emotion-based feedback based on the emotion and gameplay data collected during the match. For example, it analyzes which situations tend to cause the user stress and provides advice to help improve future strategies. In this way, by combining an AI agent and an emotion engine, this system can provide users with a more interactive and customized learning environment.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The server collects game data from professional players and trains an AI model. The data is cleaned and transformed so that the model can learn professional-level strategies. Once the training is complete, the model is ready to operate as an AI agent.

[0535] Step 2:

[0536] The server sets up an emotion engine and configures it to analyze the user's emotions in real time. This engine has the function of determining the emotional state by analyzing the user's voice and facial expression data.

[0537] Step 3:

[0538] The user operates the device to access the system and select the type of game. They also grant access to the camera and microphone to reflect their emotional state.

[0539] Step 4:

[0540] The device sends the user's selection to the server, which then activates the corresponding AI agent. The game's initial setup is completed, and the user is notified that they are ready to play.

[0541] Step 5:

[0542] The user starts the game through their device and selects and inputs hand movements during gameplay. The device sends this input to the server and also transfers voice and facial expression data to the emotion engine.

[0543] Step 6:

[0544] The server uses the user's input to have the AI ​​agent calculate the optimal next move. Additionally, an emotion engine analyzes the user's emotional state and reflects the results in the AI ​​agent. The AI ​​agent then responds according to the emotional state, for example, by providing gentle advice to reduce stress.

[0545] Step 7:

[0546] The device displays the AI ​​agent's calculation results and suggestions to the user. The user reviews the AI ​​agent's actions and continues playing the game.

[0547] Step 8:

[0548] After the game ends, the server generates feedback on the user's performance based on match data and emotional data. The analysis results, including emotional fluctuations and stress points, are sent to the user's device.

[0549] Step 9:

[0550] The device provides feedback to the user. Based on the information provided, the user analyzes their play style and revises their strategy for the next match.

[0551] (Example 2)

[0552] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0553] Conventional AI-based competitive gaming systems suffer from a lack of dynamic responses that take into account the user's emotional state, resulting in a limited user experience. Furthermore, insufficient feedback tailored to the user's skill level and proficiency level hinders skill improvement.

[0554] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0555] In this invention, the server includes means for collecting match records obtained from professional athletes and using those records to train an artificial intelligence model for learning tactics; means for analyzing the user's emotions and adjusting the AI ​​program's response based on emotion recognition; and means for saving the user's operation records multiple times and evaluating technical improvements. This enables interactive feedback that responds to the user's emotional state and effectively supports the user's skill improvement.

[0556] A "professional athlete" refers to an individual or group that possesses advanced skills in a particular sport and has been recognized for achieving a certain level of success within that sport.

[0557] "Match record" refers to data that records each step, action, and result in a match between players in a competitive game.

[0558] An "artificial intelligence model" is a software structure that autonomously makes decisions and predictions by learning from data, and often includes machine learning algorithms.

[0559] "Competition" refers to matches or contests between players conducted according to rules, and includes a wide variety of genres and activities that involve unusual behavior.

[0560] "Users" refer to individuals or groups who use this system to participate in competitions or gain experiences.

[0561] "Information" refers to knowledge, data, or advice generated or provided by a system, and the content conveyed to the user.

[0562] "Emotion recognition" refers to a technology that detects and identifies a user's emotional state by analyzing their digital data.

[0563] "Attributes" refer to the individual characteristics and traits of users, and include elements that may affect the system's operation and feedback.

[0564] This invention provides an artificial intelligence agent system that utilizes emotion recognition technology. The specific implementation method is described below.

[0565] Server-side processing:

[0566] The server collects a large amount of match records provided by professional players and uses this data to train a generative AI model using a machine learning framework. Specifically, it utilizes frameworks such as TensorFlow and PyTorch to train the model to find the optimal moves in various situations within a match. The server also processes image and audio data sent by users in real time and analyzes the user's emotional state through an emotion recognition API. This analysis process typically uses Microsoft Azure's Face API or Google Cloud's Speech-to-Text.

[0567] Terminal-side processing:

[0568] The terminal functions as a platform where users participate in the competition via an interface, instantly transmitting user actions and inputs to the server. The terminal is also equipped with a camera and microphone, which collect the user's facial expressions and voice. This allows the terminal to acquire user emotion data and transmit it to the server in real time. Typically, high-performance personal computers or smart devices are used as the terminals.

[0569] User experience:

[0570] When a user starts a game using their device, an artificial intelligence agent is assigned as their opponent. For example, if the user chooses chess, the AI ​​agent will make moves based on professional tactics in the opening stages. If the user shows signs of confusion, the server performs emotion analysis, allowing the AI ​​agent to adjust its reaction and provide advice.

[0571] Examples of specific cases and prompt statements:

[0572] For example, the system can analyze where users tend to feel stressed during the process of improving their skills through the game, and then advise them to pay attention to different tactics next time. An example of a prompt message might be, "Please explain how a system can utilize professional match records to provide feedback that takes user emotions into account."

[0573] Thus, the present invention makes it possible to construct a system that provides dynamic feedback corresponding to the user's emotional state and supports an individualized learning experience.

[0574] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0575] Step 1:

[0576] The server collects match records from professional players into a database. The input data includes the moves and results for each phase of the game. This data is then fed into a machine learning framework to train a generative AI model. The output is an AI model that has learned to identify the optimal moves within a game. Specifically, the dataset is preprocessed, converted into a format suitable for the model, and then the training process is executed.

[0577] Step 2:

[0578] When a user starts a game, the device uses its camera and microphone to capture the user's facial expressions and voice data. This data becomes input and is sent to the server for emotion recognition API analysis. The server inputs information obtained from facial feature points and voice tone into the emotion engine and performs analysis. The output is the user's current emotional state. Specifically, data collection begins when the user clicks the mouse to start the game.

[0579] Step 3:

[0580] The server adjusts the AI ​​agent's actions in real time based on emotional data and game progress information sent from the terminal. Input data includes the user's emotional state and the current game situation. Based on this, a generative AI model is used to calculate the next action, generating the adjusted AI agent's behavior as output. Specifically, if the user is confused, the AI ​​can choose a gentler move or offer advice.

[0581] Step 4:

[0582] At the end of a game, the server analyzes the acquired emotional and gameplay data to generate feedback that helps improve the user's skills. Input data includes the player's action log and emotional state during the match. The server aggregates this data and generates feedback that includes where the user struggled and areas for improvement. Specifically, after the analysis, advice for the next game is displayed on the user's screen.

[0583] (Application Example 2)

[0584] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0585] Many modern AI game systems provide a uniform competitive experience without considering the user's emotional changes, resulting in a poor user experience and making it difficult to provide learning support and skill improvement tailored to individual users. In this situation, there is a need to provide a personalized experience that takes into account the emotional state of each user, thereby realizing a more effective learning environment.

[0586] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0587] This invention includes a server that collects game data from professional players and uses this data to train a generative AI model that learns strategies; a server that recognizes the user's emotional state and personalizes the game experience; and a server that provides emotion-based learning support after the game ends. This not only promotes the user's skill improvement but also provides a more user-friendly and effective learning experience.

[0588] "Professional player match data" refers to record data about matches and games played by highly skilled, professional players in a particular sport or game.

[0589] A "generative AI model" is an artificial intelligence system that uses a large dataset to learn and generate responses with high accuracy to specific tasks or strategies.

[0590] An "AI agent" is a program equipped with artificial intelligence that automatically determines and executes actions in response to specific environments and user input.

[0591] "User emotional state" refers to the state in which a user exhibits psychological and emotional responses at a particular moment, which can be detected from facial expressions, tone of voice, and other factors.

[0592] "Feedback" refers to evaluations, advice, or guidelines for learning improvement that a system provides based on the user's actions and results.

[0593] Personalization refers to optimizing content to provide information and experiences tailored to the individual characteristics and needs of each user.

[0594] "Learning support" refers to support and guidance provided to facilitate the acquisition of specific content or skills.

[0595] To implement this invention, it is necessary to build a system in which a server and a terminal work together. The server collects game data from professional players and uses this data to train a generative AI model. This generative AI model calculates strategies and next moves in the game selected by the user. The server is also equipped with emotion recognition capabilities and analyzes image and audio data transmitted from the user's terminal in real time. Emotion recognition APIs such as the Google Cloud Vision API can be used for emotion recognition.

[0596] On the device, the user runs the game using the device and sends input data and data acquired from the camera and microphone to the server. The feedback provided by the server reflects the user's emotional state and personalizes the user's gaming experience.

[0597] A concrete example of this system is a scenario where a user wears smart glasses and interacts with an AI robot designed to assist with studying. The robot can present math problems, read the user's facial expressions, and provide hints while adjusting the difficulty level. In this scenario, the use of a generative AI model ensures that appropriate advice and problems tailored to the user are provided in real time.

[0598] An example of a prompt message is, "The user appears confused. Please advise on the most effective way to explain the math problem to the user." In this way, it is possible to provide an interactive support environment tailored to each individual user.

[0599] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0600] Step 1:

[0601] The user starts the device and begins the game. The device uses its camera and microphone to capture the user's facial expressions and voice, and sends this data to the server as input. On the server side, the received data is used to analyze the user's emotional state in real time.

[0602] Step 2:

[0603] The server uses an emotion recognition API to analyze the user's emotions and inputs the results into a generative AI model. The generative AI model calculates the optimal next move based on the analysis results and professional player game data. This analysis result is then reflected in the user's strategy within the game.

[0604] Step 3:

[0605] When users decide to continue or retry a game, they receive strategic and emotionally-based advice from the server. The server provides this advice to the user as voice using a speech synthesis API, allowing users to receive real-time feedback on their next actions.

[0606] Step 4:

[0607] After a game ends, the server records play data and emotional data to measure the user's skill improvement. Based on this, it generates appropriate feedback for the next game and provides it to the user via email or in-app notification. This data allows for adjustments to the long-term learning plan.

[0608] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0609] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0610] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0611] [Fourth Embodiment]

[0612] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0613] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0614] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0615] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0616] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0617] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0618] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0619] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0620] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0621] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0622] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0623] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0624] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0625] In order to implement this invention, it is necessary to construct a competitive game system using an AI agent through the interaction of a server, a terminal, and a user.

[0626] Server-side processing

[0627] The server first collects game data from professional players via the internet and datasets, and uses this data to train a generative AI model. Because this model has the ability to mimic the strategies of professional players, it can provide users with a realistic game experience. The server receives game selections from users and activates the corresponding AI agent. During a game, the server receives the user's moves, and the AI ​​agent calculates the next move based on those moves and sends it to the user's terminal. This process is performed in real time, resulting in smooth gameplay.

[0628] Terminal-side processing

[0629] The user's device receives a notification from the server and confirms that it is ready for a match. When the user enters a move in the game, that information is sent to the server. The next move from the AI ​​agent is displayed on the device, allowing the user to experience a realistic match against a professional-level player. After the game ends, feedback provided by the server is displayed on the device, allowing the user to evaluate their own performance.

[0630] User experience

[0631] Users can play against an AI agent anytime, anywhere, from a device that runs smoothly. For example, suppose user B starts a chess game and chooses a standard opening as their first move. The server-trained AI agent responds to this and develops a strategy in the middle game. After the game ends, the server provides feedback on user B's strengths and areas for improvement in that game, allowing user B to plan how to improve their tactics for their next game.

[0632] Thus, this system has a specific operational model that provides professional-level competitive opportunities through AI agents and supports the improvement of users' skills.

[0633] The following describes the processing flow.

[0634] Step 1:

[0635] The server collects professional players' game data from the internet and existing datasets. It then cleans the collected data and converts it into a format suitable for training AI models.

[0636] Step 2:

[0637] The server uses the collected data to train a generative AI model. Through this training, the model learns the strategies of professional players and acquires the ability to predict appropriate moves.

[0638] Step 3:

[0639] Users access the system using their devices and select the game they wish to play. They can also set the opponent's strength and the scenario.

[0640] Step 4:

[0641] The server activates the corresponding AI agent based on the user's selection. It performs the initial game setup and notifies the user's device that the match is ready.

[0642] Step 5:

[0643] The user inputs their next move via their device and sends it to the server. The server receives this information.

[0644] Step 6:

[0645] The server uses the user's input to have an AI agent calculate the optimal next move. The calculation result is then sent to the user's terminal and displayed.

[0646] Step 7:

[0647] The user looks at the moves suggested by the AI ​​agent, considers their next move, and inputs it. This process is repeated until the end of the game.

[0648] Step 8:

[0649] After the game ends, the server analyzes the data collected during the match and generates feedback on the user's gameplay.

[0650] Step 9:

[0651] The server generates feedback and sends it to the user's device. Based on this feedback, the user reviews their play style and strategy and prepares for the next match.

[0652] (Example 1)

[0653] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0654] The challenge lies in providing users with a realistic and effective competitive experience using professional players' match data, and in appropriately generating evaluation information to support users' skill improvement. In particular, it is necessary to go beyond simply imitating matches and understand the characteristics of each user, providing feedback based on those characteristics. Furthermore, it is important to continuously do this, aiming to improve users' skills while reflecting the latest strategies and techniques in real time.

[0655] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0656] In this invention, the server includes means for acquiring professional player match data using an information processing device and creating a generative AI model that learns strategies using said data; means for executing an AI agent corresponding to a game selected by the user and building game preparations; and means for analyzing the moves of the game entered by the user and having the AI ​​agent calculate the next move. This makes it possible to provide the user with individualized and effective evaluation information while mimicking professional-level strategies in real time.

[0657] An "information processing device" is a device for efficiently acquiring, processing, and analyzing data, and includes computers, servers, or similar technological systems.

[0658] "Professional player match data" refers to a dataset that shows the match results and strategies of skilled or expert players in competitive chess.

[0659] A "generative AI model" is an algorithm or system that uses machine learning techniques to mimic performance based on specific data.

[0660] An "AI agent" is an artificial intelligence program designed to operate automatically and determine appropriate strategies and actions in a specific sport.

[0661] "Means of preparing for competition" refers to the methods and processes for setting up the necessary configurations and environment before a competition begins.

[0662] "Game moves" refers to the specific sequence or content of actions or movements chosen by a player during a game.

[0663] "Evaluation information" refers to feedback data regarding areas for improvement and strengths, provided based on the user's competition results and performance.

[0664] This invention aims to provide users with a realistic competitive experience by utilizing match data from professional players, thereby supporting skill improvement. Specific embodiments of this system are described below.

[0665] Server Role

[0666] The server first collects match data from professional players via the internet and cloud storage services. This process utilizes information processing equipment to efficiently acquire and analyze the data. After data collection, the server trains a generative AI model. This training uses machine learning libraries (e.g., TensorFlow and PyTorch), and Python's pandas and NumPy are used for data processing. The generative AI model is trained to mimic the strategies of professional players and provide users with a highly accurate match experience.

[0667] Once a game is selected, the server runs an AI agent corresponding to that game. Here, independent AI agents are used depending on the type of game, each executing an appropriate strategy based on a generated AI model.

[0668] Terminal role

[0669] The user's device receives notifications from the server and confirms that it is ready for the match. When the user selects a specific move during the game, that information is immediately sent to the server. When information about the next move is returned from the server, it is displayed in the user interface to facilitate a smooth match.

[0670] User experience

[0671] Users can experience professional-level matches anywhere through their devices. For example, if user B starts a chess game, they might choose a standard chess opening. The server activates an AI agent for chess, calculates the next move in response to the user's move, and develops a mid-game strategy. After the match ends, the server evaluates the user's play and provides feedback on their strengths and areas for improvement. This allows user B to improve their tactics for future games.

[0672] A specific example of a prompt message would be, "When predicting your next move, refer to data from past professional players and choose the most effective strategy in the middle game." The overall structure of this system allows users to improve their skills while gaining near-professional match experience.

[0673] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0674] Step 1:

[0675] The server begins collecting game data from professional players. It specifies available internet and cloud storage data sources as input and retrieves the data. Data processing software is used to structure the collected data and convert it into a format suitable for training a generative AI model. The output is a trainable dataset.

[0676] Step 2:

[0677] The server trains a generative AI model. It uses a formatted dataset as input and leverages machine learning libraries (e.g., TensorFlow or PyTorch) to train the model. Here, a multi-layer neural network is commonly used to learn the strategic patterns of professional players from the data. The output is a trained AI model capable of mimicking the strategies of professional players.

[0678] Step 3:

[0679] The server launches a specific AI agent based on the user's selection. The input includes the type of game selected by the user and its settings. Based on this information, the server loads and executes the corresponding AI agent program. The output is the initialized state of the AI ​​agent corresponding to the game.

[0680] Step 4:

[0681] The user's device receives notifications from the server and displays the readiness status for the match. It receives notification data from the server as input and displays it on the user interface. Here, it signals the user to start the game. The output is a screen display indicating that the match is ready.

[0682] Step 5:

[0683] The user inputs their moves into the game via a terminal. The terminal sends the input data from the user to the server. It receives information about the user's moves as input and converts that data into packets for transmission to the server. The output is the move data sent to the server.

[0684] Step 6:

[0685] The server receives move data from the user and calculates the next move using a generated AI model. It receives data about the user's moves and the current game situation as input and performs calculations based on the AI ​​model. The output is decision information regarding the next move.

[0686] Step 7:

[0687] The server sends the calculated next move information to the user's terminal. It uses move data calculated by the AI ​​model as input, converts it into a format the user can understand, and then sends it. The output is the next move information received by the terminal.

[0688] Step 8:

[0689] The user's device displays the information about the next move it has received on the screen. It receives move information from the server as input and renders it to reflect on the game screen. The output is the current game display that the user can visually confirm.

[0690] Step 9:

[0691] After the game ends, the server analyzes the game data and generates feedback for the user. It takes the user's and AI agent's game history as input and performs analysis using an evaluation algorithm. The output is feedback information highlighting the user's strengths and areas for improvement.

[0692] Step 10:

[0693] The user's device receives feedback from the server and displays it to the user. It receives feedback data from the server as input and displays it on the device. The output is a screen display of evaluation information useful to the user.

[0694] (Application Example 1)

[0695] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0696] In modern society, as local communities become increasingly ties, there is a growing need to increase opportunities for interaction among residents and enhance a sense of community. However, traditional methods are limited in their ability to plan events that initiate interaction and in engaging participants, making it difficult to efficiently promote community interaction. In particular, providing opportunities for interaction that can be enjoyed by a wide range of generations, from young people to the elderly, is a crucial issue that contributes to the sustainable development of communities.

[0697] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0698] This invention includes a server that collects match data from professional players and trains a generative AI model that learns strategies using the data; a system that allows participation in community tournaments to promote interaction at local events; and a system that activates an AI agent corresponding to a game selected by the user and prepares it for battle. This makes it possible to promote interaction among residents and enhance a sense of community unity through local events that can be participated in by a wide range of generations.

[0699] "Professional player match data" refers to records of matches played by advanced players with competitive experience and knowledge, and this data serves as foundational material for AI to learn strategies.

[0700] A "generative AI model" is an algorithm that uses machine learning techniques to imitate and learn the skills and strategies of professional players, providing users with an advanced competitive experience.

[0701] "Community events" are various participatory activities aimed at promoting interaction among residents and enhancing a sense of unity within a specific area.

[0702] An "AI agent" is a software component that automatically calculates strategies in a game selected by the user and plays against the user in that game.

[0703] A "community tournament" is an event involving competitions and games that local residents participate in, serving as a place to revitalize interaction among residents.

[0704] To implement this invention, it is necessary to build a system centered around the interaction between a server, a terminal, and a user. The server is responsible for collecting and analyzing professional player match data to train a generative AI model that forms the basis of game matches. This training utilizes machine learning frameworks such as TensorFlow to create an AI model that mimics professional-level strategies.

[0705] The server provides a means to activate an AI agent corresponding to the game selected by participants when planning local events. The server receives game moves from users, and based on these, the AI ​​agent calculates the next move in real time and sends it to the user's terminal. This communication and processing uses internet-based real-time communication technology with FastAPI.

[0706] The device will have an application developed with Flutter, which supports multiple platforms, installed, allowing users to register for community tournaments. After each game, the application will receive and display feedback from the server. This helps users improve their skills and facilitates knowledge sharing within the community.

[0707] Through this, users can participate in local community tournaments held as smart city events and learn professional strategies by playing against AI. For example, a chess tournament could be held at a local social event, and participants could enjoy playing against an AI agent. An example of a prompt to the generated AI model would be an instruction such as, "Generate a standard chess opening and a mid-game strategy based on it." This helps users to gain opportunities for further skill improvement.

[0708] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0709] Step 1:

[0710] The server collects match data from professional players. Its input is match records obtained from internet databases and online game platforms. This data is then analyzed and processed to extract player behavior history and strategies. The output is a training dataset for a generative AI model.

[0711] Step 2:

[0712] The server trains the generated AI model. It uses the training dataset generated in step 1 as input. Based on this dataset, it performs data computations to train the AI ​​model using machine learning frameworks such as TensorFlow. The output is an AI model capable of mimicking the strategies of professional players.

[0713] Step 3:

[0714] Users apply to participate in community tournaments via their devices. Input involves using the interface of an application installed on the device to select a game and enter user information. Output is that the application is recorded on the server, and a corresponding AI agent is prepared.

[0715] Step 4:

[0716] The server activates an AI agent corresponding to the game selected by the user. It receives the user's game selection information as input. The AI ​​agent loads the necessary data to execute a strategy using a generated AI model and prepares for the match. The output is the activation of a playable AI agent.

[0717] Step 5:

[0718] The user plays the game on their device and inputs their moves. The user's moves during the game are transmitted from the device as input. This information is sent to a server, where the AI ​​agent performs real-time calculations to determine the next move. The AI ​​agent's moves are then displayed on the user's device as output.

[0719] Step 6:

[0720] The server generates and provides feedback to the user after the game ends. As input, it analyzes the user's hand movements and action history during the game. Based on this, it processes the data to identify the user's strengths and areas for improvement. As output, the feedback information is displayed on the user's device, and advice for the next game is provided.

[0721] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0722] A specific embodiment of this invention requires the construction of an AI agent system that combines an emotion engine. The details are shown below.

[0723] Server-side processing

[0724] The server collects game data from professional players and trains a generative AI model that can mimic professional tactics. Furthermore, the server is equipped with an emotion engine that analyzes emotions in real time from camera images and audio data based on the user's input and actions during gameplay. The output of this emotion engine is reflected in the AI ​​agent's responses and feedback.

[0725] Terminal-side processing

[0726] The user's device runs the game and sends user input to the server. Furthermore, the device provides the user's voice and facial expressions to the emotion engine, transferring this information to the server. The device uses this data to recognize the user's emotional state, thereby personalizing the game experience.

[0727] User experience

[0728] When a user starts a game using their device, an AI agent takes over as an opponent. For example, suppose user C selects a shogi (Japanese chess) game and enters the opening round. The server analyzes user C's emotions in real time, reading their facial expressions and voice. If user C shows signs of confusion, the server can use its emotion engine to slightly adjust the AI's moves to make them easier for user C to understand, or even offer advice in a conversational format.

[0729] After a game ends, the server provides the user with emotion-based feedback based on the emotion and gameplay data collected during the match. For example, it analyzes which situations tend to cause the user stress and provides advice to help improve future strategies. In this way, by combining an AI agent and an emotion engine, this system can provide users with a more interactive and customized learning environment.

[0730] The following describes the processing flow.

[0731] Step 1:

[0732] The server collects game data from professional players and trains an AI model. The data is cleaned and transformed so that the model can learn professional-level strategies. Once the training is complete, the model is ready to operate as an AI agent.

[0733] Step 2:

[0734] The server sets up an emotion engine and configures it to analyze the user's emotions in real time. This engine has the function of determining the emotional state by analyzing the user's voice and facial expression data.

[0735] Step 3:

[0736] The user operates the device to access the system and select the type of game. They also grant access to the camera and microphone to reflect their emotional state.

[0737] Step 4:

[0738] The device sends the user's selection to the server, which then activates the corresponding AI agent. The game's initial setup is completed, and the user is notified that they are ready to play.

[0739] Step 5:

[0740] The user starts the game through their device and selects and inputs hand movements during gameplay. The device sends this input to the server and also transfers voice and facial expression data to the emotion engine.

[0741] Step 6:

[0742] The server uses the user's input to have the AI ​​agent calculate the optimal next move. Additionally, an emotion engine analyzes the user's emotional state and reflects the results in the AI ​​agent. The AI ​​agent then responds according to the emotional state, for example, by providing gentle advice to reduce stress.

[0743] Step 7:

[0744] The device displays the AI ​​agent's calculation results and suggestions to the user. The user reviews the AI ​​agent's actions and continues playing the game.

[0745] Step 8:

[0746] After the game ends, the server generates feedback on the user's performance based on match data and emotional data. The analysis results, including emotional fluctuations and stress points, are sent to the user's device.

[0747] Step 9:

[0748] The device provides feedback to the user. Based on the information provided, the user analyzes their play style and revises their strategy for the next match.

[0749] (Example 2)

[0750] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0751] Conventional AI-based competitive gaming systems suffer from a lack of dynamic responses that take into account the user's emotional state, resulting in a limited user experience. Furthermore, insufficient feedback tailored to the user's skill level and proficiency level hinders skill improvement.

[0752] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0753] In this invention, the server includes means for collecting match records obtained from professional athletes and using those records to train an artificial intelligence model for learning tactics; means for analyzing the user's emotions and adjusting the AI ​​program's response based on emotion recognition; and means for saving the user's operation records multiple times and evaluating technical improvements. This enables interactive feedback that responds to the user's emotional state and effectively supports the user's skill improvement.

[0754] A "professional athlete" refers to an individual or group that possesses advanced skills in a particular sport and has been recognized for achieving a certain level of success within that sport.

[0755] "Match record" refers to data that records each step, action, and result in a match between players in a competitive game.

[0756] An "artificial intelligence model" is a software structure that autonomously makes decisions and predictions by learning from data, and often includes machine learning algorithms.

[0757] "Competition" refers to matches or contests between players conducted according to rules, and includes a wide variety of genres and activities that involve unusual behavior.

[0758] "Users" refer to individuals or groups who use this system to participate in competitions or gain experiences.

[0759] "Information" refers to knowledge, data, or advice generated or provided by a system, and the content conveyed to the user.

[0760] "Emotion recognition" refers to a technology that detects and identifies a user's emotional state by analyzing their digital data.

[0761] "Attributes" refer to the individual characteristics and traits of users, and include elements that may affect the system's operation and feedback.

[0762] This invention provides an artificial intelligence agent system that utilizes emotion recognition technology. The specific implementation method is described below.

[0763] Server-side processing:

[0764] The server collects a large amount of match records provided by professional players and uses this data to train a generative AI model using a machine learning framework. Specifically, it utilizes frameworks such as TensorFlow and PyTorch to train the model to find the optimal moves in various situations within a match. The server also processes image and audio data sent by users in real time and analyzes the user's emotional state through an emotion recognition API. This analysis process typically uses Microsoft Azure's Face API or Google Cloud's Speech-to-Text.

[0765] Terminal-side processing:

[0766] The terminal functions as a platform where users participate in the competition via an interface, instantly transmitting user actions and inputs to the server. The terminal is also equipped with a camera and microphone, which collect the user's facial expressions and voice. This allows the terminal to acquire user emotion data and transmit it to the server in real time. Typically, high-performance personal computers or smart devices are used as the terminals.

[0767] User experience:

[0768] When a user starts a game using their device, an artificial intelligence agent is assigned as their opponent. For example, if the user chooses chess, the AI ​​agent will make moves based on professional tactics in the opening stages. If the user shows signs of confusion, the server performs emotion analysis, allowing the AI ​​agent to adjust its reaction and provide advice.

[0769] Examples of specific cases and prompt statements:

[0770] For example, the system can analyze where users tend to feel stressed during the process of improving their skills through the game, and then advise them to pay attention to different tactics next time. An example of a prompt message might be, "Please explain how a system can utilize professional match records to provide feedback that takes user emotions into account."

[0771] Thus, the present invention makes it possible to construct a system that provides dynamic feedback corresponding to the user's emotional state and supports an individualized learning experience.

[0772] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0773] Step 1:

[0774] The server collects match records from professional players into a database. The input data includes the moves and results for each phase of the game. This data is then fed into a machine learning framework to train a generative AI model. The output is an AI model that has learned to identify the optimal moves within a game. Specifically, the dataset is preprocessed, converted into a format suitable for the model, and then the training process is executed.

[0775] Step 2:

[0776] When a user starts a game, the device uses its camera and microphone to capture the user's facial expressions and voice data. This data becomes input and is sent to the server for emotion recognition API analysis. The server inputs information obtained from facial feature points and voice tone into the emotion engine and performs analysis. The output is the user's current emotional state. Specifically, data collection begins when the user clicks the mouse to start the game.

[0777] Step 3:

[0778] The server adjusts the AI ​​agent's actions in real time based on emotional data and game progress information sent from the terminal. Input data includes the user's emotional state and the current game situation. Based on this, a generative AI model is used to calculate the next action, generating the adjusted AI agent's behavior as output. Specifically, if the user is confused, the AI ​​can choose a gentler move or offer advice.

[0779] Step 4:

[0780] At the end of a game, the server analyzes the acquired emotional and gameplay data to generate feedback that helps improve the user's skills. Input data includes the player's action log and emotional state during the match. The server aggregates this data and generates feedback that includes where the user struggled and areas for improvement. Specifically, after the analysis, advice for the next game is displayed on the user's screen.

[0781] (Application Example 2)

[0782] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0783] Many modern AI game systems provide a uniform competitive experience without considering the user's emotional changes, resulting in a poor user experience and making it difficult to provide learning support and skill improvement tailored to individual users. In this situation, there is a need to provide a personalized experience that takes into account the emotional state of each user, thereby realizing a more effective learning environment.

[0784] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0785] This invention includes a server that collects game data from professional players and uses this data to train a generative AI model that learns strategies; a server that recognizes the user's emotional state and personalizes the game experience; and a server that provides emotion-based learning support after the game ends. This not only promotes the user's skill improvement but also provides a more user-friendly and effective learning experience.

[0786] "Professional player match data" refers to record data about matches and games played by highly skilled, professional players in a particular sport or game.

[0787] A "generative AI model" is an artificial intelligence system that uses a large dataset to learn and generate responses with high accuracy to specific tasks or strategies.

[0788] An "AI agent" is a program equipped with artificial intelligence that automatically determines and executes actions in response to specific environments and user input.

[0789] "User emotional state" refers to the state in which a user exhibits psychological and emotional responses at a particular moment, which can be detected from facial expressions, tone of voice, and other factors.

[0790] "Feedback" refers to evaluations, advice, or guidelines for learning improvement that a system provides based on the user's actions and results.

[0791] Personalization refers to optimizing content to provide information and experiences tailored to the individual characteristics and needs of each user.

[0792] "Learning support" refers to support and guidance provided to facilitate the acquisition of specific content or skills.

[0793] To implement this invention, it is necessary to build a system in which a server and a terminal work together. The server collects game data from professional players and uses this data to train a generative AI model. This generative AI model calculates strategies and next moves in the game selected by the user. The server is also equipped with emotion recognition capabilities and analyzes image and audio data transmitted from the user's terminal in real time. Emotion recognition APIs such as the Google Cloud Vision API can be used for emotion recognition.

[0794] On the device, the user runs the game using the device and sends input data and data acquired from the camera and microphone to the server. The feedback provided by the server reflects the user's emotional state and personalizes the user's gaming experience.

[0795] A concrete example of this system is a scenario where a user wears smart glasses and interacts with an AI robot designed to assist with studying. The robot can present math problems, read the user's facial expressions, and provide hints while adjusting the difficulty level. In this scenario, the use of a generative AI model ensures that appropriate advice and problems tailored to the user are provided in real time.

[0796] An example of a prompt message is, "The user appears confused. Please advise on the most effective way to explain the math problem to the user." In this way, it is possible to provide an interactive support environment tailored to each individual user.

[0797] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0798] Step 1:

[0799] The user starts the device and begins the game. The device uses its camera and microphone to capture the user's facial expressions and voice, and sends this data to the server as input. On the server side, the received data is used to analyze the user's emotional state in real time.

[0800] Step 2:

[0801] The server uses an emotion recognition API to analyze the user's emotions and inputs the results into a generative AI model. The generative AI model calculates the optimal next move based on the analysis results and professional player game data. This analysis result is then reflected in the user's strategy within the game.

[0802] Step 3:

[0803] When users decide to continue or retry a game, they receive strategic and emotionally-based advice from the server. The server provides this advice to the user as voice using a speech synthesis API, allowing users to receive real-time feedback on their next actions.

[0804] Step 4:

[0805] After a game ends, the server records play data and emotional data to measure the user's skill improvement. Based on this, it generates appropriate feedback for the next game and provides it to the user via email or in-app notification. This data allows for adjustments to the long-term learning plan.

[0806] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0807] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0808] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0809] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0810] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0811] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0812] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0813] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0814] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0815] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0816] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0817] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0818] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0819] 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.

[0820] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0821] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0822] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0823] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0824] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0825] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0826] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] A means for collecting match data from professional players and training a generative AI model that learns strategies using said data,

[0830] A means to activate an AI agent corresponding to the game selected by the user and prepare for battle,

[0831] A means for an AI agent to analyze the moves entered by the user in a game and calculate the next move,

[0832] A means of generating and providing feedback to users after the game ends,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, comprising means for recording a user's play data multiple times and measuring their skill improvement.

[0836] (Claim 3)

[0837] The system according to claim 1, comprising means for analyzing user characteristics and providing more appropriate feedback for the next match.

[0838] "Example 1"

[0839] (Claim 1)

[0840] A means for acquiring match data of professional players using an information processing device and creating a generative AI model that learns strategies using said data,

[0841] A means of running an AI agent corresponding to the competition selected by the user and building up preparations for the competition,

[0842] A method for analyzing the moves entered by the user in a game and having an AI agent calculate the next move,

[0843] A means of forming and providing evaluation information to users after the competition has ended,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, comprising means for recording user operation data multiple times and evaluating technical improvements.

[0847] (Claim 3)

[0848] The system according to claim 1, comprising means for analyzing user characteristics and providing more appropriate evaluation information for the next competition.

[0849] "Application Example 1"

[0850] (Claim 1)

[0851] A means for collecting match data from professional players and training a generative AI model that learns strategies using said data,

[0852] To promote interaction at local events, a means of providing a system that allows participation in community conventions,

[0853] A means to activate an AI agent corresponding to the game selected by the user and prepare for battle,

[0854] A means for an AI agent to analyze the moves entered by the user in a game and calculate the next move,

[0855] A means of generating and providing feedback to users after the game ends,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, comprising means for recording user play data multiple times and measuring the degree of interaction at local events.

[0859] (Claim 3)

[0860] The system according to claim 1, which includes means for analyzing user characteristics and providing a more appropriate community interaction experience at the next local event.

[0861] "Example 2 of combining an emotion engine"

[0862] (Claim 1)

[0863] A means for collecting match records obtained from professional athletes and using those records to train an artificial intelligence model for acquiring tactics,

[0864] A means of launching an artificial intelligence program corresponding to the sport selected by the user and preparing for the competition,

[0865] A means by which an artificial intelligence program analyzes the game sequence entered by the user and calculates the next move,

[0866] A means of generating and providing information to users after the competition has ended,

[0867] A means for analyzing the user's emotions and adjusting the response of an artificial intelligence program based on emotion recognition,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, comprising means for saving user operation records multiple times and evaluating technical improvements.

[0871] (Claim 3)

[0872] The system according to claim 1, comprising means for analyzing user attributes and providing more appropriate information for the next competition.

[0873] "Application example 2 when combining with an emotional engine"

[0874] (Claim 1)

[0875] A means for collecting match data from professional players and training a generative AI model that learns strategies using said data,

[0876] A means to activate an AI agent corresponding to the game selected by the user and prepare for battle,

[0877] A means for an AI agent to analyze the moves entered by the user in a game and calculate the next move,

[0878] A means of recognizing the user's emotional state using a camera and voice input device and personalizing the game experience,

[0879] A means of generating and providing feedback to users after the game ends, as well as providing emotion-based learning support,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, comprising means for recording user play data multiple times, measuring skill improvement, and analyzing performance changes based on emotional data.

[0883] (Claim 3)

[0884] The system according to claim 1, comprising means for analyzing user characteristics and providing more appropriate feedback in subsequent matches and learning, thereby improving emotional responses. [Explanation of symbols]

[0885] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting match data from professional players and training a generative AI model that learns strategies using said data, To promote interaction at local events, a means of providing a system that allows participation in community conventions, A means to activate an AI agent corresponding to the game selected by the user and prepare for battle, A means for an AI agent to analyze the moves entered by the user in a game and calculate the next move, A means of generating and providing feedback to users after the game ends, A system that includes this.

2. The system according to claim 1, comprising means for recording user play data multiple times and measuring the degree of interaction at local events.

3. The system according to claim 1, which includes means for analyzing user characteristics and providing a more appropriate community interaction experience at the next local event.

Images