System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving information of a hand pointed by a user; means for analyzing the received information to calculate a next best move and a phase evaluation; means for generating an advice in a human-understandable form based on a calculation result; and means for providing the advice to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, the use of artificial intelligence (AI) has progressed in board games such as shogi and go. AI has already come to be recognized as a powerful opponent, surpassing humans in many situations. However, the best moves and numerical position evaluations presented by AI are difficult for many users to intuitively understand. This prevents users from fully utilizing the AI's advice and prevents them from receiving effective feedback to improve their playing skills. Furthermore, there is no system currently available that provides appropriate advice based on a user's past move patterns and habits. Therefore, the present invention aims to solve these problems by providing a system that provides intuitive advice and supports long-term player development. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. A system is provided that includes means for receiving information on moves played by a user, means for analyzing the received information to calculate the next best move and a situation evaluation, means for generating advice in a form that is easy for humans to understand based on the calculation results, and means for providing the advice to the user. Furthermore, the advice generation means includes means for analyzing the user's past game data to detect the user's move patterns and habits, making it possible to provide advice tailored to the user's characteristics. Furthermore, the advice generation means includes means for generating long-term advice based on the detected user's patterns and habits, providing a system that more effectively supports the user's improvement of their shogi skill.

[0006] A "user" is someone who uses the system to play shogi or go games.

[0007] "Move information" refers to data on the specific moves made by the user during a game of shogi or go.

[0008] "Means for receiving" refers to a function or device for receiving information on the user's hand in real time.

[0009] "Means of analysis" refers to functions and algorithms that calculate the next best move and situation assessment based on received move information.

[0010] The "best move" is the move that is considered to be the most advantageous in a shogi or go situation.

[0011] "Situation evaluation" is a numerical indication of how favorable or unfavorable the current situation is.

[0012] "Means for generating" refers to the functions and algorithms for creating advice based on the calculation results.

[0013] The "means for providing" refers to a function or device for displaying or transmitting the generated advice to the user.

[0014] "Past game data" refers to records of games played by the user in the past and data on moves made.

[0015] "Patterns and habits" refer to behaviors and tendencies that a user repeatedly exhibits during a game.

[0016] "Long-term advice" refers to advice that is implemented over time with the aim of improving a user's chess ability. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] This invention provides a system that provides useful advice in real time when a user plays shogi or go, and also analyzes the user's characteristics and habits based on past game data to provide long-term advice. This system is mainly composed of three elements: a server, a terminal, and the user.

[0039] System configuration

[0040] 1. Server:

[0041] The server is equipped with a shogi AI and a generative AI.

[0042] The server receives the user's move information, analyzes it, and calculates the best move.

[0043] The server also uses generative AI to generate advice based on the analysis results from the shogi AI.

[0044] The server also analyzes the user's past game data and generates long-term advice.

[0045] 2. Terminal:

[0046] A terminal is a device (for example, a PC or smartphone) on which a user plays a game.

[0047] The terminal collects information about the user's moves and sends it to the server.

[0048] It also displays the advice and analysis results received from the server to the user.

[0049] 3. User:

[0050] A user is someone who uses the system through games and receives advice.

[0051] Users play games through their devices and improve their skills based on feedback from the system.

[0052] Program processing

[0053] 1. Start of game:

[0054] The game begins when the user clicks the game start button on the terminal.

[0055] The terminal sends a request to start a game to the server.

[0056] The server initializes the game and sends the initial position.

[0057] 2. Receiving and analyzing moves:

[0058] When the user makes the next move, the information about that move is recorded on the terminal.

[0059] The device transmits this information to the server in real time.

[0060] The server updates the situation based on the received moves and uses shogi AI to calculate the next best move and situation evaluation.

[0061] For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin."

[0062] 3. Generating Advice:

[0063] The server receives the analysis results from the shogi AI and uses generative AI to generate advice about the next move.

[0064] Advice is provided in a concrete and easy-to-understand format. For example, the generated advice might be, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop."

[0065] 4. Providing advice:

[0066] The server transmits the generated advice to the user's terminal.

[0067] The terminal displays the advice to the user, who can refer to it to decide on the next move.

[0068] 5. Analysis of past game data:

[0069] The server collects and analyzes the user's past game data.

[0070] Based on this data, the generative AI can detect patterns and habits of the user's moves. For example, if the user tends to exchange pieces early,

[0071] 6. Generating long-term advice:

[0072] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[0073] For example, advice such as "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages" may be generated.

[0074] 7. Providing long-term advice:

[0075] The server transmits the generated long-term advice to the terminal.

[0076] The terminal displays long-term advice to the user.

[0077] The above is a specific embodiment of the present invention, which allows users to receive useful advice in real time during a shogi or go game, and further allows them to improve their playing ability through long-term advice tailored to their own characteristics.

[0078] The processing flow will be explained below.

[0079] Step 1:

[0080] The user clicks the start button on the terminal, which starts the game.

[0081] Step 2:

[0082] The terminal sends the user's request to start a game to the server.

[0083] Step 3:

[0084] The server receives the game start request, initializes the game, and sends the initial position to the terminal.

[0085] Step 4:

[0086] The user looks at the situation and makes the next move.

[0087] Step 5:

[0088] The terminal records the user's moves and sends this information to the server.

[0089] Step 6:

[0090] The server updates the current position based on the moves it receives.

[0091] Step 7:

[0092] The server sends the latest position to the shogi AI, which calculates the next best move and position evaluation.

[0093] Step 8:

[0094] The server receives the best move and situation evaluation returned by the shogi AI.

[0095] Step 9:

[0096] The server passes the analysis results to the generative AI, which generates advice in a form that is easy for the user to understand.

[0097] Step 10:

[0098] The server sends the advice generated by the generative AI to the terminal.

[0099] Step 11:

[0100] The terminal displays the advice on the user's screen.

[0101] Step 12:

[0102] The user makes the next move based on the displayed advice, which returns to step 4.

[0103] Step 13:

[0104] The server periodically collects and stores the user's past game data.

[0105] Step 14:

[0106] The server uses generative AI to analyze the user's past game data and detect their characteristics and habits.

[0107] Step 15:

[0108] The server uses generative AI to generate long-term advice based on detected user patterns and habits.

[0109] Step 16:

[0110] The server generates long-term advice and sends it to the device.

[0111] Step 17:

[0112] The device displays long-term advice on the user's screen.

[0113] Through these steps, the system can provide useful advice in real time and support long-term improvement of chess skills based on the user's characteristics.

[0114] Example 1

[0115] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0116] In games of shogi and go, users are unable to receive appropriate advice in real time, and there is a lack of specific feedback to improve their long-term playing ability. Furthermore, there is a need for a system that effectively uses past game data to analyze users' characteristics and habits and provide advice based on that analysis.

[0117] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0118] In this invention, the server includes means for receiving information on moves played by the user, means for analyzing the received information to calculate the best next move and a situation evaluation, and means for generating advice in a form that is easy for humans to understand based on the calculation results. This makes it possible to provide appropriate advice in real time during the user's game, and to generate long-term advice by analyzing the user's past game data.

[0119] A "user" is someone who uses the system to play shogi or go games and receive advice.

[0120] A "terminal" is a device used by a user to play a game, including a PC or smartphone.

[0121] The "server" is a computer system that implements the shogi AI and generation AI, and is responsible for receiving and analyzing information on the user's moves, and generating and providing advice.

[0122] "Shogi AI" is an artificial intelligence technology that analyzes shogi situations and calculates the best move and situation evaluation.

[0123] "Generative AI" is an artificial intelligence technology that generates easy-to-understand advice for users based on the analysis results from a shogi AI.

[0124] "Past game data" is historical information about games played by the user in the past, and includes data such as moves made and progress of the game situation.

[0125] A "prompt sentence" is a sentence entered to instruct the generation AI to generate advice, and includes specific situation assessments and information on the best move.

[0126] "Advice" is specific and easy-to-understand information that instructs the user on the next move in a game of shogi or go.

[0127] "Long-term advice" is advice on tactics and strategies provided to improve a user's playing ability, based on the results of an analysis of the user's past game data.

[0128] "Real-time" means that advice is provided immediately while the user is playing a game.

[0129] This invention provides a system that provides useful advice in real time when a user plays shogi or go, and also analyzes the user's characteristics and habits based on past game data to provide long-term advice. This system is composed of three elements: a server, a terminal, and the user.

[0130] server

[0131] The server is equipped with a shogi AI and a generative AI (for example, OpenAI's GPT-3 (registered trademark) is a common generative AI model). The server receives information about the user's moves, analyzes it, and calculates the best next move. The server also generates advice using the generative AI based on the analysis results from the shogi AI. Furthermore, the server analyzes the user's past game data and creates long-term advice.

[0132] Specifically, the server is a cloud server (e.g., an AWS (registered trademark) EC2 instance) equipped with a high-performance CPU and GPU, and the database is a database system (e.g., PostgreSQL) for storing and managing users' game history.

[0133] Terminal

[0134] The terminal is the device on which the user plays the game. Specifically, it includes a PC or smartphone. The terminal collects information about the moves made by the user and sends it to the server. It also displays advice and analysis results received from the server to the user.

[0135] A dedicated application for playing games is installed on the device, and the application has the function of monitoring the user's operations in real time and sending that information to the server.

[0136] User

[0137] Users are those who use the system to play games and receive advice. Users play games through their devices and can improve their skills based on feedback from the system.

[0138] Specific examples

[0139] Providing advice during a game

[0140] When the user makes the next move on their device, the information about that move is recorded on the device and sent to the server. The server analyzes the received information and uses shogi AI to calculate the best next move and the position evaluation. For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin." Based on this information, the server uses generative AI to generate advice about the next move.

[0141] Examples of prompts:

[0142] Please generate advice for the user about the next move. The current position is evaluated as +1.2, and the best move is 2-7 Gin. Please explain in a concrete and easy-to-understand way.

[0143] The generated advice might be something like, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop." The server sends this advice to the terminal, which then displays it to the user.

[0144] Generating long-term advice

[0145] Based on the user's past game data, the server uses generative AI to analyze the user's move patterns and habits. For example, if the user tends to exchange pieces early, the server can generate long-term advice.

[0146] Examples of prompts:

[0147] After analyzing the user's past game data, you have noticed a tendency to exchange pieces early on. Please generate long-term advice to improve this tendency. Please explain it by including specific tactics and strategies.

[0148] The generated long-term advice might be, for example, "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages." The server sends this advice to the terminal, which then displays it to the user.

[0149] As a result, users can receive useful advice in real time during a game, and can also improve their Go skills through long-term advice based on their own characteristics and habits.

[0150] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0151] Step 1: Start the game

[0152] Input: The user clicks the start game button on the terminal.

[0153] Operation: The shogi game application on the device starts operation and catches the user's click event. This event triggers the creation of a request data packet to start the game and sends an HTTP POST request to a specific API endpoint on the server.

[0154] Output: An HTTP request containing a game start request is sent to the server. The server receives this and performs the initial game setup. Specifically, it creates a new game session, generates the initial shogi position data, and sends it to the terminal in JSON format. The terminal receives this data and displays the initial position on the screen.

[0155] Step 2: Receiving and analyzing the move

[0156] Input: User makes next move.

[0157] Action: The user moves a piece using the mouse or touch on the device. The device application monitors this action in real time and collects detailed information such as the coordinate data of the move and the type of piece. This information is packaged into a JSON packet and sent to the server as an HTTP POST request.

[0158] Output: The server updates the position based on the received move information. Specifically, it uses a shogi AI (e.g., Bonanza) to calculate the position evaluation and the best move. For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin." The result is output in JSON format.

[0159] Step 3: Generate Advice

[0160] Input: Situation evaluation and best move information from shogi AI.

[0161] Operation: The server converts the received best move data into a prompt sentence and sends it to the generative AI model (e.g., GPT-3). An example of a prompt sentence is, "Please generate advice for the user about the next move. The current position evaluation is '+1.2', and the best move is '2-7 Gin'. Please explain it in a specific and easy-to-understand way."

[0162] Output: Receives advice from the generative AI model and generates specific and easy-to-understand advice, such as "As your next move, it's a good idea to move your silver to 27. This will limit the freedom of your opponent's bishop." This advice is output in JSON format and sent to the device.

[0163] Step 4: Providing advice

[0164] Input: Advice sentence from a generative AI model.

[0165] How it works: The server creates a JSON packet containing advice and sends it to the device as an HTTP response. The device receives it and displays the advice to the user in a GUI. The advice text is displayed on the device screen as a popup or a dedicated widget.

[0166] Output: Advice is displayed on the user's terminal, which the user can use to decide their next move.

[0167] Step 5: Analyze past game data

[0168] Input: User's game history data.

[0169] How it works: The server queries a database for a user's past games and collects data. This data is then fed into analytical algorithms that use generative AI models (e.g., K-means clustering and decision trees) to detect patterns and move habits. For example, information such as "a user tends to exchange pieces early" can be extracted.

[0170] Output: Pattern and habit information based on the analysis results is generated and output in JSON format.

[0171] Step 6: Generate long-term advice

[0172] Input: Information about the user's playing patterns and habits.

[0173] How it works: The server generates a prompt and inputs this information into the generative AI model. An example of a prompt is, "After analyzing the user's past game data, we have found that they tend to exchange pieces early on. Please generate long-term advice to improve this tendency. Please explain it, including specific tactics and strategies."

[0174] Output: A long-term advice statement from the generative AI model is generated. For example, advice such as "Try a strategy that emphasizes defense and avoids piece exchanges in the early stages" is generated and sent to the device in JSON format.

[0175] Step 7: Providing long-term advice

[0176] Input: Long-term advice statements from a generative AI model.

[0177] How it works: The server creates a JSON packet containing the advice and sends it as an HTTP response to the device. The device receives it and displays the long-term advice to the user in a GUI.

[0178] Output: Long-term advice is displayed on the user's device, allowing the user to improve their long-term strategy.

[0179] The above processing steps enable the system to provide real-time and long-term advice.

[0180] (Application example 1)

[0181] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0182] In modern games (such as shogi and go) and factory work sites, there is a demand for systems that provide real-time advice and long-term improvement suggestions to help users and work robots act efficiently and effectively. Conventional systems have had difficulty providing advice that takes into account the individual characteristics and habits of users and the work patterns of robots. To address this issue, the present invention aims to provide a system that analyzes the behavioral data of users and work robots, provides individually optimized advice in real time, and aims to improve long-term efficiency.

[0183] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0184] In this invention, the server includes means for receiving information on moves played by a user, means for analyzing the received information to calculate the best next move and a situation evaluation, means for generating advice in a form that is easy for humans to understand based on the calculation results, means for providing the advice to the user, means for receiving and analyzing robot operation data, means for generating optimal operation procedures based on the analysis results, and means for analyzing past operation data to generate advice for improving long-term operation efficiency. This enables real-time optimization of moves played by users during games and improvement of the efficiency of robot operations in factories.

[0185] A "user" is an entity that uses the system to play games or perform work in a factory.

[0186] A "server" is a computing device that receives and analyzes data from users and robots.

[0187] A "terminal" is a device on which a user plays a game or a robot performs a task.

[0188] "Data analysis" is the process of calculating the optimal next steps or work procedures based on the information received.

[0189] The "best move" is the move in a game that is judged to be the most advantageous at that time.

[0190] "Situation evaluation" is a means of expressing the current situation of a game using numbers or evaluations.

[0191] "Advice" is system-generated instructions or suggestions about next steps or work procedures.

[0192] "Analysis results" are information obtained after the server performs data analysis.

[0193] "Task data" is data related to the task performed by the robot.

[0194] A "pattern" is a characteristic behavioral pattern that a user or robot exhibits through a series of actions.

[0195] A "habit" is a certain behavioral tendency that a user or a robot exhibits in a particular situation.

[0196] "Long-term advice" is improvement proposals that are effective over the long term and are based on past data.

[0197] "Optimized advice" is instructions generated based on a series of data analyses to maximize efficiency and effectiveness.

[0198] This system provides useful advice in real time when users play games (such as shogi or go) or manage robot operations in factories, and makes long-term improvement suggestions based on past behavioral data. This system is mainly composed of three elements: a server, a terminal, and a user or robot.

[0199] System configuration

[0200] 1. Server:

[0201] The server is equipped with AI that analyzes games (such as shogi AI), AI that manages robot work (robot AI), and generative AI.

[0202] The server receives the user's moves and the robot's work data, and calculates the optimal next move, work sequence, and situation evaluation.

[0203] The server also uses generative AI based on the analysis results to generate advice in a format that is easy for humans to understand.

[0204] The server analyzes past game data and work data, and creates long-term advice based on the characteristics and habits of the user and robot.

[0205] The servers use high-performance data center servers (e.g., Google (registered trademark) Cloud, AWS EC2) and AI / ML frameworks (e.g., TENSORFLOW (registered trademark), PyTorch).

[0206] 2. Terminal:

[0207] The terminals are devices on which users play games (e.g., PCs or smartphones) and devices on which robots perform tasks (e.g., transport robots or arm robots).

[0208] The terminal records the user's movements and the robot's actions in real time and transmits the data to the server.

[0209] In addition, the advice and analysis results received from the server are displayed to the user, and are used as reference when the user or robot decides the next move or performs a task.

[0210] The device will also be equipped with sensors (e.g., LiDAR sensor, camera).

[0211] 3. User (Operator):

[0212] Users are players who play games against each other and operators who supervise and manage factory robots.

[0213] Users play games and perform tasks through their terminals, and act based on feedback and advice from the system.

[0214] Program processing (explained in natural language)

[0215] The server receives data on each move made by the user and the robot's work, and calculates the optimal next move and work procedure based on this information. It then uses generative AI to generate advice based on the calculation results in a format that is easy for humans to understand. This advice is sent to the user's device and provided to them in real time.

[0216] The server also uses past game and task data to detect the characteristics and habits of the user and robot, and creates advice for long-term efficiency improvements. This advice is also sent to the user's device, and the user can refer to it when planning their next game or task.

[0217] The hardware uses high-performance data center servers and sensors (e.g., LiDAR sensors and cameras), and the software uses AI / ML frameworks (e.g., TensorFlow, PyTorch). The generative AI model generates advice based on specific game or task scenarios.

[0218] Examples and prompts:

[0219] For example, imagine a robot that transports packages on a conveyor belt in a factory. The robot records the transport time for each package and sends it to a server. Based on past data, the AI ​​on the server analyzes that increasing the speed of the conveyor belt by 15% will reduce the transport time by 20%, and provides that advice to the robot.

[0220] Example prompt sentence:

[0221] "Next, increase the conveyor belt speed by 15% to reduce transport time by 20%. Try this."

[0222] In this way, users and robots can play games or perform tasks while receiving advice that is optimized in real time and over the long term.

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] The user presses the game start button on the terminal to start the game or work.

[0226] Input: Click the Start button

[0227] Output: Request to start a game or work

[0228] A request to start a game or task is sent from the terminal to the server. This causes the system to enter its initial configuration, and the initial state of the game or the initial conditions of the task are sent from the server to the terminal or robot.

[0229] Step 2:

[0230] The user indicates the next move, or the robot begins work.

[0231] Input: User's move information or robot's task data

[0232] Output: Move information or work data sent to the server

[0233] The terminal records the user's gestures and the robot's work data in real time and sends it to the server, which updates the situation based on the received information and records the progress of the robot's work.

[0234] Step 3:

[0235] The server analyzes the received data and calculates the next best move and optimal work procedure.

[0236] Input: Move information or work data

[0237] Output: Calculation results of the best move or optimal work procedure

[0238] The AI ​​(Shogi AI or robot AI) on the server analyzes the received data and calculates the optimal next move, work procedure, and situation evaluation. The results of this calculation include a situation evaluation of "+1.2" or a best move such as "2-7 Gin".

[0239] Step 4:

[0240] The server uses generative AI to generate advice based on the analysis results.

[0241] Input: Calculation results of the best move or optimal work procedure

[0242] Output: Advice translated into an easy-to-understand format

[0243] The server uses generative AI to convert the calculation results into concrete, easy-to-understand advice, such as, "The next move is to move the silver to 27. This will limit the freedom of the opponent's bishop."

[0244] Step 5:

[0245] The server transmits the generated advice to the terminal or robot and provides it to the user or robot.

[0246] Input: Generated advice

[0247] Output: Send advice to user device or robot

[0248] The server sends the generated advice to the user's terminal or robot, which receives the advice and displays or executes it to indicate the next move or progress the task.

[0249] Step 6:

[0250] The server analyzes past data from users and robots and generates long-term advice.

[0251] Input: Past game data or work data

[0252] Output: Long-term advice based on feature detection and habit analysis

[0253] The server collects and analyzes past data from users and robots. Generative AI uses this data to detect specific patterns and habits and create long-term advice based on them. For example, the generated advice might be, "Try a strategy that emphasizes defense and avoids piece exchanges in the early stages."

[0254] Step 7:

[0255] Long-term advice is sent to the user's device or robot for display and execution.

[0256] Input: Generated long-term advice

[0257] Output: Send advice to user device or robot

[0258] The server sends the generated long-term advice to the terminal or robot, which displays or executes it. The user can refer to this advice when playing or working on the next game.

[0259] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0260] This invention relates to a system that provides useful advice in real time when a user plays shogi or go, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[0261] System configuration

[0262] 1. Server:

[0263] The server is equipped with a shogi AI and a generative AI.

[0264] The server receives the user's move information, analyzes it, and calculates the best move.

[0265] The server also uses generative AI to generate advice based on the analysis results from the shogi AI.

[0266] The server also analyzes the user's past game data and generates long-term advice.

[0267] 2. Terminal:

[0268] A terminal is a device (for example, a PC or smartphone) on which a user plays a game.

[0269] The terminal collects information about the user's moves and sends it to the server.

[0270] It also displays the advice and analysis results received from the server to the user.

[0271] 3. User:

[0272] A user is someone who uses the system through games and receives advice.

[0273] Users play games through their devices and improve their skills based on feedback from the system.

[0274] 4. Emotion Engine:

[0275] The emotion engine is a device and program that recognizes the user's emotional state from their voice, facial expression, input actions, and so on.

[0276] The emotion engine collects and analyzes the user's emotion data and sends it to the server.

[0277] Program processing

[0278] 1. Start of game:

[0279] The game begins when the user clicks the game start button on the terminal.

[0280] The terminal sends a request to start a game to the server.

[0281] The server initializes the game and sends the initial position.

[0282] 2. Receiving and analyzing moves:

[0283] When the user looks at the situation and makes the next move, the information about that move is recorded on the terminal.

[0284] The device transmits this information to the server in real time.

[0285] The server updates the game situation based on the received moves and uses shogi AI to calculate the next best move and game situation evaluation.

[0286] 3. Collecting Emotional Data:

[0287] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc.

[0288] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[0289] The emotion engine transmits the recognized emotional state to the server.

[0290] 4. Generating Advice:

[0291] The server uses generative AI to generate advice about the next move based on the analysis results from the shogi AI and the emotional data received from the emotion engine.

[0292] For example, if the user is feeling impatient or anxious, the content and manner of expression of the advice can be changed.

[0293] Advice is provided in a concrete and easy-to-understand format. For example, the generated advice might be, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop."

[0294] 5. Providing advice:

[0295] The server transmits the generated advice to the user's terminal.

[0296] The terminal displays the advice on the user's screen.

[0297] 6. Analysis of past game data:

[0298] The server periodically collects and stores the user's past game data.

[0299] Based on this data, the generative AI detects the user's move patterns and habits.

[0300] 7. Generating long-term advice:

[0301] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[0302] For example, advice such as "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages" may be generated.

[0303] 8. Providing long-term advice:

[0304] The server sends the generated long-term advice to the terminal.

[0305] The device displays long-term advice on the user's screen.

[0306] The above is a specific embodiment of the present invention, which allows users to receive useful advice in real time during a shogi or go game, and also receive feedback based on their emotional state. Furthermore, by analyzing past game data and emotional data, more appropriate and long-term advice can be provided, helping users improve their shogi skills.

[0307] The processing flow will be explained below.

[0308] Step 1:

[0309] The user clicks the start button on the terminal, which starts the game.

[0310] Step 2:

[0311] The terminal sends the user's request to start a game to the server.

[0312] Step 3:

[0313] The server receives the game start request, initializes the game, and sends the initial position to the terminal.

[0314] Step 4:

[0315] The user looks at the situation and makes the next move.

[0316] Step 5:

[0317] The terminal records the user's moves and sends this information to the server.

[0318] Step 6:

[0319] The server updates the current position based on the moves it receives.

[0320] Step 7:

[0321] The server sends the latest position to the shogi AI, which calculates the next best move and position evaluation.

[0322] Step 8:

[0323] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc.

[0324] Step 9:

[0325] The emotion engine analyzes the emotion data and recognizes the user's emotional state, for example, detecting emotions such as "impatience" or "anxiety."

[0326] Step 10:

[0327] The emotional state recognized by the emotion engine is sent to the server.

[0328] Step 11:

[0329] The server uses generative AI to generate advice about the next move based on the analysis results from the shogi AI and the emotional state received from the emotion engine. For example, if the user is feeling impatient, the server will create advice that takes this into account.

[0330] Step 12:

[0331] The server sends the generated advice to the terminal.

[0332] Step 13:

[0333] The device will display advice on the user's screen, such as "Take your time and move your silver to 27 next. This will limit the freedom of your opponent's bishop."

[0334] Step 14:

[0335] The user makes the next move based on the displayed advice, which returns to step 4.

[0336] Step 15:

[0337] The server periodically collects and stores the user's past game data.

[0338] Step 16:

[0339] The server uses generative AI to analyze the user's past game data and detect their characteristics and habits. For example, it detects that they have a habit of exchanging pieces early in the opening game.

[0340] Step 17:

[0341] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[0342] Step 18:

[0343] The server generates long-term advice and sends it to the device.

[0344] Step 19:

[0345] The device will then display long-term advice to the user, such as "Refrain from exchanging pieces early on and try a more defensive strategy."

[0346] These steps enable the system to provide useful advice in real time, provide feedback based on the user's emotional state, and analyze past game data to provide appropriate long-term advice.

[0347] Example 2

[0348] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0349] Conventional shogi and go game systems have struggled to provide users with useful advice in real time. Furthermore, there was no system that recognized the user's emotional state and provided appropriate feedback accordingly. This led to problems such as poor judgment, impatience, and anxiety during the game, leading to a decline in the quality of play. Furthermore, there was a lack of a way to effectively utilize past game data to support long-term improvement in playing ability.

[0350] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0351] In this invention, the server includes: means for receiving information on moves played by the user; means for analyzing the received information to calculate the next best move and a situation evaluation; means for generating advice in a form that is easy for humans to understand based on the calculation results and the user's emotional state; means for providing the advice and emotional feedback to the user; means for collecting emotional data from the user's voice, facial expressions, and input actions; means for analyzing the collected emotional data to recognize the user's emotional state; means for providing the recognized emotional state to the advice generating means; means for analyzing the user's past game data to detect the user's move patterns and habits; and means for generating long-term advice based on the detected user patterns and habits. This allows the user to receive useful advice in real time during a game and obtain appropriate feedback according to their emotional state. Furthermore, long-term advice based on past game data helps the user improve their chess skill.

[0352] A "user" is someone who plays a game and receives advice and feedback from the system.

[0353] "Terminal" refers to the device used by a user to play a game, including, for example, a PC or smartphone.

[0354] The "server" is the central hardware of the system, and performs functions such as data analysis, advice generation, and sentiment analysis.

[0355] "Shogi AI" is an artificial intelligence that calculates the next best move and situation evaluation in a shogi game.

[0356] "Generative AI" is artificial intelligence that generates advice to provide to users based on analysis results and emotional data.

[0357] An "emotion engine" is a device and program that collects emotional data from the user's voice, facial expressions, input actions, etc., and analyzes it to recognize the user's emotional state.

[0358] "Emotional data" is information collected from the user's voice, facial expressions, input actions, etc., and is used to determine the user's emotional state.

[0359] "Situation evaluation" is an evaluation value calculated by shogi AI for the current situation, and is used to determine the next best move.

[0360] "Advice" is information generated by the server based on the calculation results and emotional state and provided to the user, allowing the user to obtain useful information about their next move.

[0361] "Game data" refers to a record of games played by the user, including detailed information about each move.

[0362] "Long-term advice" is advice generated based on the user's past game data, move patterns, and habits, and is intended to improve the user's chess ability.

[0363] This invention relates to a system that provides useful advice in real time when a user plays shogi or go, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[0364] System configuration

[0365] 1. Server:

[0366] The server is equipped with a shogi AI and a generative AI, which analyzes moves, evaluates the situation, and generates advice. Specifically, AlphaZero is used for the shogi AI, and GPT-4 (registered trademark) is used for the generative AI.

[0367] The server receives information about the user's moves, analyzes them, calculates the best next move, and then uses generative AI to generate advice based on the analysis results.

[0368] The server also utilizes the emotion data received from the emotion engine to generate feedback according to when the user is feeling anxious or impatient.

[0369] The system analyzes the user's past game data and provides long-term advice, which helps improve the user's chess skills. Specifically, the system uses MySQL (registered trademark) as a database to manage game data.

[0370] 2. Terminal:

[0371] A terminal is a device on which a user plays a game, and examples include a PC or a smartphone.

[0372] The device collects information about the user's moves and sends it to the server, using HTTPS as the communication protocol to ensure data security.

[0373] The system displays advice and analysis results received from the server to the user, and can also display the user's emotional state during the game.

[0374] 3. User:

[0375] The user plays the game through a terminal and receives advice and feedback provided by the server.

[0376] Users can improve their own chess skills based on this advice.

[0377] 4. Emotion Engine:

[0378] The emotion engine is a device and program that collects and analyzes emotion data from the user's voice, facial expressions, input actions, etc. Specifically, it uses libraries such as OpenCV and Dlib.

[0379] The emotion engine analyzes the collected emotion data and recognizes the user's emotional state.

[0380] The recognized emotion data is sent to the server and used to generate advice.

[0381] Specific operation of the system

[0382] When a user starts a game of Shogi or Go using a device, the system starts by clicking the start game button. The device sends a request to start the game to the server, which performs initialization and returns the initial position. When the user makes their next move, the device sends the information about that move to the server in real time, and the server analyzes the move and calculates the best move and a position evaluation.

[0383] At the same time, the emotion engine collects the user's emotional data and analyzes it in real time to recognize the user's emotional state. This emotional data is also sent to the server, which uses the generative AI to generate advice based on this data. For example, if the user is feeling impatient, the generative AI can be given a prompt such as, "Give me gentle advice on how to play the next move in a situation where the user is feeling impatient," and this is used to generate advice.

[0384] Advice is provided to the user via the device, and specific advice such as "As your next move, it would be better to move the silver to 2-7" is displayed on the screen. This allows users to receive useful advice in real time and improve their play based on feedback during the game. The server also accumulates and analyzes past game data to generate long-term advice. This advice is also provided to the user via the device, allowing users to continuously improve their chess skills.

[0385] The above is a specific operation of the system according to the embodiment of the present invention.

[0386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0387] Step 1: Start the game

[0388] When the user clicks the game start button on the terminal, the game begins.

[0389] Input: User's operation to start a game

[0390] The terminal sends a game start request to the server, which includes initial setting information such as the game ID, user ID, and game type.

[0391] Output: Sending a start request

[0392] The server receives the request and performs the initial setup of the game (generating a game ID, registering player information, and setting the initial position).

[0393] Output: Initial position and initial setting information

[0394] The server sends the completed initial setting information and the initial phase to the terminal.

[0395] Input: Initialization information and initial phase from the server

[0396] The terminal displays the received initial position to the user, and the game officially begins.

[0397] Output: Initial position

[0398] Step 2: Receiving and analyzing the move

[0399] When the user looks at the situation and makes the next move, the information about that move is recorded on the terminal.

[0400] Input: User's move information (such as move coordinates)

[0401] The terminal transmits move information to the server in real time.

[0402] Output: Sending move information

[0403] The server updates the position using the received move information.

[0404] Input: Move information

[0405] The server analyzes the new position using a shogi AI (e.g., AlphaZero) and calculates the next best move and position evaluation.

[0406] Output: Calculated best move and position evaluation

[0407] The server temporarily stores the calculation results and uses them for subsequent processing.

[0408] Output: Stored calculation results

[0409] Step 3: Collecting emotion data

[0410] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc. When using a webcam or microphone, it analyzes the user's facial expressions and tone of voice.

[0411] Input: User's voice, facial expressions, and input actions

[0412] The emotion engine analyzes this data in real time to identify the user's emotional state.

[0413] Output: User's emotional state data

[0414] The emotion engine transmits the recognized emotional state to the server.

[0415] Input: Recognized emotion data

[0416] The server uses this input for the next processing step.

[0417] Output: Sending emotion data

[0418] Step 4: Generating Advice

[0419] The server uses a generative AI (e.g., GPT-4) to generate advice about the next move based on the analysis results from the shogi AI and the emotional data received from the emotion engine.

[0420] Input: Shogi AI analysis results, emotional data

[0421] The server inputs the prompt sentence into the generative AI and generates advice. For example, it inputs a prompt sentence such as, "If the user is in a hurry, please give them gentle advice on how to play the next move. For example, 'Don't rush, take your time to think about your next move.'"

[0422] Output: Generated advice

[0423] The server stores the generated advice and uses it in subsequent steps.

[0424] Output: Stored advice

[0425] Step 5: Providing advice

[0426] The server transmits the generated advice to the user's terminal.

[0427] Input: Generated advice

[0428] The device will then display the received advice on the user's screen. For example, the screen will say, "It would be a good idea to move your silver to 2-7 as your next move."

[0429] Output: Display advice

[0430] Step 6: Analyze past game data

[0431] The server periodically collects and stores the user's past game data, including game dates and times, game types, game results, and detailed information about each move.

[0432] Input: Past game data

[0433] The server analyzes this data and uses generative AI to detect the user's move patterns and habits.

[0434] Output: Data on move patterns and habits

[0435] Step 7: Generate long-term advice

[0436] The server generates long-term advice based on the user's move patterns and habits to help improve their playing ability.

[0437] Input: Data on move patterns and habits

[0438] The server uses generative AI to generate detailed advice on specific strategies and points to note, such as "Try a defensive strategy and avoid exchanging pieces in the early stages."

[0439] Output: Generated long-term advice

[0440] Step 8: Providing long-term advice

[0441] The server sends the generated long-term advice to the terminal.

[0442] Input: Generated long-term advice

[0443] The device will then display long-term advice to the user on their screen, such as "In your next game, I recommend you refrain from exchanging pieces early on and instead focus on defense."

[0444] Output: Displaying long-term advice

[0445] The above is a detailed description of the specific processing flow of this system and the operations performed at each step.

[0446] (Application example 2)

[0447] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0448] Existing shogi and go game systems struggle to provide appropriate advice in real time. Furthermore, they lack systems that can adapt feedback based on the user's emotional state, making it difficult to reduce user stress and fatigue. Furthermore, the lack of real-time advice and emotion recognition is also a challenge for factory robots and other automated systems.

[0449] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving information on moves played by the user; means for analyzing the received information and calculating the next best move and a situation evaluation; means for generating advice in a form that is easy for humans to understand based on the calculation results; means for providing the advice to the user; means for recognizing the emotional state of the operator and generating feedback according to that emotional state; and means for collecting work data and providing long-term improvement advice. This allows the user to receive useful advice in real time and receive feedback according to their emotional state. Furthermore, the ability to analyze past work data and game data and provide long-term improvement advice is expected to improve the user's technical skills and work efficiency.

[0450] "Information about the user's hand gestures" is a record of the specific operations and actions performed by the operator.

[0451] The "receiving means" is a hardware and software mechanism for acquiring the information about the user's hand gesture and transmitting it to other components in the system.

[0452] "Means of analysis" refers to the use of specific algorithms or models to calculate the next best move or situation assessment based on the information received.

[0453] "Best next move and situation evaluation" means the next move that is most suitable for the current situation in a game of shogi or go, and an evaluation of that situation.

[0454] The "means for generating advice" is a mechanism for creating specific advice in a form that is easy for humans to understand, based on the analysis results.

[0455] The "means for providing advice" refers to the hardware and software mechanisms for presenting the generated advice to the user.

[0456] "Emotional state of the operator" refers to the psychological state of the operator while working, and includes information such as stress and fatigue.

[0457] "Means for recognizing emotional states" is a general term for technologies and devices for detecting and analyzing an operator's emotional state from their voice, facial expressions, actions, etc.

[0458] A "feedback generation mechanism" is a mechanism that generates appropriate responses or advice based on the perceived emotional state.

[0459] "Work data" is a record of specific operations performed by operators or systems in the past and their results.

[0460] The "means of providing long-term improvement advice" is a system that uses collected work data to create and provide specific advice to improve operator skills and work efficiency over the long term.

[0461] This invention relates to a system that provides useful advice in real time when a user is performing a task, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[0462] System configuration

[0463] 1. Server:

[0464] The server is equipped with a shogi AI and a generative AI.

[0465] The server receives the user's operation information, analyzes it, and calculates the optimal work procedure.

[0466] The server also uses generative AI based on the analysis results to generate easy-to-understand advice.

[0467] The server also analyzes the user's emotional state and provides feedback based thereon.

[0468] 2. Terminal:

[0469] A terminal is a device (e.g., a PC or tablet) on which a user performs work.

[0470] The terminal collects various pieces of user operation information and transmits it to the server.

[0471] It also displays the advice and analysis results received from the server to the user.

[0472] 3. User:

[0473] A user is an operator who performs work using the system.

[0474] Users can receive real-time advice through their devices, improving work efficiency.

[0475] 4. Emotion Engine:

[0476] The emotion engine is a device and program that recognizes the user's emotional state from facial expressions, voice, actions, and the like.

[0477] The emotion engine collects and analyzes emotion data and sends it to the server.

[0478] Program processing (server, terminal, emotion engine)

[0479] 1. Data collection: While the user is working, the device collects operational information in real time and sends it to the server. The emotion engine also recognizes the user's facial expressions, voice, and movements, analyzes their emotional state, and sends the data to the server.

[0480] 2. Data analysis: Based on the received operation information, the server uses an analytical algorithm to evaluate the current work situation and calculate the optimal work procedure. It also analyzes emotional data to determine whether the user is feeling stressed or tired.

[0481] 3. Advice generation: The server uses generative AI based on the analysis results to generate easy-to-understand work advice. For example, specific advice such as, "As a next step, it is a good idea to connect part A to part B. This will improve assembly efficiency."

[0482] 4. Providing feedback: The server also generates appropriate feedback based on the emotion data, such as "You seem to be feeling tired. Please take a 5-minute break."

[0483] 5. Displaying Advice: The generated advice and feedback is sent to the terminal and displayed on the user's screen.

[0484] Specific examples

[0485] In a specific work scenario, the server advises a user who is assembling one part into another on the appropriate work procedure. Also, if the emotion engine detects the user's fatigue, the server will recommend taking a break.

[0486] Prompt Sentence Examples

[0487] Based on the emotion and task data above, provide advice on the best work procedures for the current task, and include suggestions for breaks if the operator is tired.

[0488] By implementing the present invention in this manner, it is possible to provide useful advice in real time and appropriate feedback according to the user's emotional state, thereby improving the user's work efficiency and safety.

[0489] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0490] Step 1:

[0491] Data collection

[0492] The device collects operational information about the work the user performs in real time. Specifically, it uses sensors and logging functions to obtain data on the procedures and actions the user takes on the device. This data is stored in the device's internal database and then sent to the server. The input is the user's operational information, and the output is the operational data sent to the server.

[0493] Step 2:

[0494] Emotional Data Collection

[0495] The emotion engine collects the user's facial expressions, voice, and movements in real time. The emotion engine is equipped with a camera, microphone, and sensors that collect data to recognize the user's emotional state. This data is sent to a server for analysis. The input is the user's facial expressions, voice, and movement data, and the output is the emotion data sent to the server.

[0496] Step 3:

[0497] Data analysis

[0498] The server uses an analysis algorithm to evaluate the current work situation and emotional state based on the received operation information and emotional data. A specific example of analysis is identifying the current work progress and problems from the user's operation data, and calculating the user's stress level and fatigue level from the emotional data. The input is operation information and emotional data, and the output is an analysis result: an evaluation of the work situation and an evaluation of the emotional state.

[0499] Step 4:

[0500] Advice Generation

[0501] The server uses generative AI based on the analysis results to generate work advice that is easy for the user to understand. For example, if work progress is delayed, it generates specific instructions such as "Connect part A to part B." If it determines that the user is tired, it generates feedback such as "Take a five-minute break." The input is the work situation assessment and emotional state assessment, and the output is the generated advice and feedback.

[0502] Step 5:

[0503] Providing advice

[0504] The server sends the generated advice and feedback to the terminal, which then displays it on the user's screen. For example, the terminal might display a message saying, "As a next step, connect component A to component B." The input is the generated advice and feedback, and the output is the instructions or suggestions displayed on the user's screen.

[0505] Step 6:

[0506] Work data accumulation

[0507] The server accumulates user operation information and emotion data collected daily and maintains a database of this data, allowing for long-term pattern and trend analysis. The input is the accumulated operation information and emotion data, and the output is an updated database.

[0508] Step 7:

[0509] Generate long-term improvement advice

[0510] The server analyzes the accumulated task and emotion data and generates long-term advice to improve the user's task performance. For example, specific advice such as "Based on past data, there is a more efficient procedure for assembling parts" may be generated. The input is data from the long-term database, and the output is long-term improvement advice.

[0511] The above is the specific flow of operations at each processing step. This series of processes allows users to receive useful advice and emotional feedback in real time, improving work efficiency and safety.

[0512] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0513] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0514] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0515] [Second embodiment]

[0516] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0517] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0518] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0519] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0520] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0521] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0522] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0523] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0524] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0525] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0526] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0527] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0528] This invention provides a system that provides useful advice in real time when a user plays shogi or go, and also analyzes the user's characteristics and habits based on past game data to provide long-term advice. This system is mainly composed of three elements: a server, a terminal, and the user.

[0529] System configuration

[0530] 1. Server:

[0531] The server is equipped with a shogi AI and a generative AI.

[0532] The server receives the user's move information, analyzes it, and calculates the best move.

[0533] The server also uses generative AI to generate advice based on the analysis results from the shogi AI.

[0534] The server also analyzes the user's past game data and generates long-term advice.

[0535] 2. Terminal:

[0536] A terminal is a device (for example, a PC or smartphone) on which a user plays a game.

[0537] The terminal collects information about the user's moves and sends it to the server.

[0538] It also displays the advice and analysis results received from the server to the user.

[0539] 3. User:

[0540] A user is someone who uses the system through games and receives advice.

[0541] Users play games through their devices and improve their skills based on feedback from the system.

[0542] Program processing

[0543] 1. Start of game:

[0544] The game begins when the user clicks the game start button on the terminal.

[0545] The terminal sends a request to start a game to the server.

[0546] The server initializes the game and sends the initial position.

[0547] 2. Receiving and analyzing moves:

[0548] When the user makes the next move, the information about that move is recorded on the terminal.

[0549] The device transmits this information to the server in real time.

[0550] The server updates the situation based on the received moves and uses shogi AI to calculate the next best move and situation evaluation.

[0551] For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin."

[0552] 3. Generating Advice:

[0553] The server receives the analysis results from the shogi AI and uses generative AI to generate advice about the next move.

[0554] Advice is provided in a concrete and easy-to-understand format. For example, the generated advice might be, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop."

[0555] 4. Providing advice:

[0556] The server transmits the generated advice to the user's terminal.

[0557] The terminal displays the advice to the user, who can refer to it to decide on the next move.

[0558] 5. Analysis of past game data:

[0559] The server collects and analyzes the user's past game data.

[0560] Based on this data, the generative AI can detect patterns and habits of the user's moves. For example, if the user tends to exchange pieces early,

[0561] 6. Generating long-term advice:

[0562] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[0563] For example, advice such as "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages" may be generated.

[0564] 7. Providing long-term advice:

[0565] The server transmits the generated long-term advice to the terminal.

[0566] The terminal displays long-term advice to the user.

[0567] The above is a specific embodiment of the present invention, which allows users to receive useful advice in real time during a shogi or go game, and further allows them to improve their playing ability through long-term advice tailored to their own characteristics.

[0568] The processing flow will be explained below.

[0569] Step 1:

[0570] The user clicks the start button on the terminal, which starts the game.

[0571] Step 2:

[0572] The terminal sends the user's request to start a game to the server.

[0573] Step 3:

[0574] The server receives the game start request, initializes the game, and sends the initial position to the terminal.

[0575] Step 4:

[0576] The user looks at the situation and makes the next move.

[0577] Step 5:

[0578] The terminal records the user's moves and sends this information to the server.

[0579] Step 6:

[0580] The server updates the current position based on the moves it receives.

[0581] Step 7:

[0582] The server sends the latest position to the shogi AI, which calculates the next best move and position evaluation.

[0583] Step 8:

[0584] The server receives the best move and situation evaluation returned by the shogi AI.

[0585] Step 9:

[0586] The server passes the analysis results to the generative AI, which generates advice in a form that is easy for the user to understand.

[0587] Step 10:

[0588] The server sends the advice generated by the generative AI to the terminal.

[0589] Step 11:

[0590] The terminal displays the advice on the user's screen.

[0591] Step 12:

[0592] The user makes the next move based on the displayed advice, which returns to step 4.

[0593] Step 13:

[0594] The server periodically collects and stores the user's past game data.

[0595] Step 14:

[0596] The server uses generative AI to analyze the user's past game data and detect their characteristics and habits.

[0597] Step 15:

[0598] The server uses generative AI to generate long-term advice based on detected user patterns and habits.

[0599] Step 16:

[0600] The server generates long-term advice and sends it to the device.

[0601] Step 17:

[0602] The device displays long-term advice on the user's screen.

[0603] Through these steps, the system can provide useful advice in real time and support long-term improvement of chess skills based on the user's characteristics.

[0604] Example 1

[0605] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0606] In games of shogi and go, users are unable to receive appropriate advice in real time, and there is a lack of specific feedback to improve their long-term playing ability. Furthermore, there is a need for a system that effectively uses past game data to analyze users' characteristics and habits and provide advice based on that analysis.

[0607] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0608] In this invention, the server includes means for receiving information on moves played by the user, means for analyzing the received information to calculate the best next move and a situation evaluation, and means for generating advice in a form that is easy for humans to understand based on the calculation results. This makes it possible to provide appropriate advice in real time during the user's game, and to generate long-term advice by analyzing the user's past game data.

[0609] A "user" is someone who uses the system to play shogi or go games and receive advice.

[0610] A "terminal" is a device used by a user to play a game, including a PC or smartphone.

[0611] The "server" is a computer system that implements the shogi AI and generation AI, and is responsible for receiving and analyzing information on the user's moves, and generating and providing advice.

[0612] "Shogi AI" is an artificial intelligence technology that analyzes shogi situations and calculates the best move and situation evaluation.

[0613] "Generative AI" is an artificial intelligence technology that generates easy-to-understand advice for users based on the analysis results from a shogi AI.

[0614] "Past game data" is historical information about games played by the user in the past, and includes data such as moves made and progress of the game situation.

[0615] A "prompt sentence" is a sentence entered to instruct the generation AI to generate advice, and includes specific situation assessments and information on the best move.

[0616] "Advice" is specific and easy-to-understand information that instructs the user on the next move in a game of shogi or go.

[0617] "Long-term advice" is advice on tactics and strategies provided to improve a user's playing ability, based on the results of an analysis of the user's past game data.

[0618] "Real-time" means that advice is provided immediately while the user is playing a game.

[0619] This invention provides a system that provides useful advice in real time when a user plays shogi or go, and also analyzes the user's characteristics and habits based on past game data to provide long-term advice. This system is composed of three elements: a server, a terminal, and the user.

[0620] server

[0621] The server is equipped with a shogi AI and a generative AI (for example, OpenAI's GPT-3, a common generative AI model). The server receives information about the user's moves, analyzes them, and calculates the best next move. The server also generates advice using the generative AI based on the analysis results from the shogi AI. Furthermore, the server analyzes the user's past game data and creates long-term advice.

[0622] Specifically, the server is a cloud server (e.g., an AWS EC2 instance) equipped with a high-performance CPU and GPU, and the database is a database system (e.g., PostgreSQL) for storing and managing users' game history.

[0623] Terminal

[0624] The terminal is the device on which the user plays the game. Specifically, it includes a PC or smartphone. The terminal collects information about the moves made by the user and sends it to the server. It also displays advice and analysis results received from the server to the user.

[0625] A dedicated application for playing games is installed on the device, and the application has the function of monitoring the user's operations in real time and sending that information to the server.

[0626] User

[0627] Users are those who use the system to play games and receive advice. Users play games through their devices and can improve their skills based on feedback from the system.

[0628] Specific examples

[0629] Providing advice during a game

[0630] When the user makes the next move on their device, the information about that move is recorded on the device and sent to the server. The server analyzes the received information and uses shogi AI to calculate the best next move and the position evaluation. For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin." Based on this information, the server uses generative AI to generate advice about the next move.

[0631] Examples of prompts:

[0632] Please generate advice for the user about the next move. The current position is evaluated as +1.2, and the best move is 2-7 Gin. Please explain in a concrete and easy-to-understand way.

[0633] The generated advice might be something like, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop." The server sends this advice to the terminal, which then displays it to the user.

[0634] Generating long-term advice

[0635] Based on the user's past game data, the server uses generative AI to analyze the user's move patterns and habits. For example, if the user tends to exchange pieces early, the server can generate long-term advice.

[0636] Examples of prompts:

[0637] After analyzing the user's past game data, you have noticed a tendency to exchange pieces early on. Please generate long-term advice to improve this tendency. Please explain it by including specific tactics and strategies.

[0638] The generated long-term advice might be, for example, "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages." The server sends this advice to the terminal, which then displays it to the user.

[0639] As a result, users can receive useful advice in real time during a game, and can also improve their Go skills through long-term advice based on their own characteristics and habits.

[0640] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0641] Step 1: Start the game

[0642] Input: The user clicks the start game button on the terminal.

[0643] Operation: The shogi game application on the device starts operation and catches the user's click event. This event triggers the creation of a request data packet to start the game and sends an HTTP POST request to a specific API endpoint on the server.

[0644] Output: An HTTP request containing a game start request is sent to the server. The server receives this and performs the initial game setup. Specifically, it creates a new game session, generates the initial shogi position data, and sends it to the terminal in JSON format. The terminal receives this data and displays the initial position on the screen.

[0645] Step 2: Receiving and analyzing the move

[0646] Input: User makes next move.

[0647] Action: The user moves a piece using the mouse or touch on the device. The device application monitors this action in real time and collects detailed information such as the coordinate data of the move and the type of piece. This information is packaged into a JSON packet and sent to the server as an HTTP POST request.

[0648] Output: The server updates the position based on the received move information. Specifically, it uses a shogi AI (e.g., Bonanza) to calculate the position evaluation and the best move. For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin." The result is output in JSON format.

[0649] Step 3: Generate Advice

[0650] Input: Situation evaluation and best move information from shogi AI.

[0651] Operation: The server converts the received best move data into a prompt sentence and sends it to the generative AI model (e.g., GPT-3). An example of a prompt sentence is, "Please generate advice for the user about the next move. The current position evaluation is '+1.2', and the best move is '2-7 Gin'. Please explain it in a specific and easy-to-understand way."

[0652] Output: Receives advice from the generative AI model and generates specific and easy-to-understand advice, such as "As your next move, it's a good idea to move your silver to 27. This will limit the freedom of your opponent's bishop." This advice is output in JSON format and sent to the device.

[0653] Step 4: Providing advice

[0654] Input: Advice sentence from a generative AI model.

[0655] How it works: The server creates a JSON packet containing advice and sends it to the device as an HTTP response. The device receives it and displays the advice to the user in a GUI. The advice text is displayed on the device screen as a popup or a dedicated widget.

[0656] Output: Advice is displayed on the user's terminal, which the user can use to decide their next move.

[0657] Step 5: Analyze past game data

[0658] Input: User's game history data.

[0659] How it works: The server queries a database for a user's past games and collects data. This data is then fed into analytical algorithms that use generative AI models (e.g., K-means clustering and decision trees) to detect patterns and move habits. For example, information such as "a user tends to exchange pieces early" can be extracted.

[0660] Output: Pattern and habit information based on the analysis results is generated and output in JSON format.

[0661] Step 6: Generate long-term advice

[0662] Input: Information about the user's playing patterns and habits.

[0663] How it works: The server generates a prompt and inputs this information into the generative AI model. An example of a prompt is, "After analyzing the user's past game data, we have found that they tend to exchange pieces early on. Please generate long-term advice to improve this tendency. Please explain it, including specific tactics and strategies."

[0664] Output: A long-term advice statement from the generative AI model is generated. For example, advice such as "Try a strategy that emphasizes defense and avoids piece exchanges in the early stages" is generated and sent to the device in JSON format.

[0665] Step 7: Providing long-term advice

[0666] Input: Long-term advice statements from a generative AI model.

[0667] How it works: The server creates a JSON packet containing the advice and sends it as an HTTP response to the device. The device receives it and displays the long-term advice to the user in a GUI.

[0668] Output: Long-term advice is displayed on the user's device, allowing the user to improve their long-term strategy.

[0669] The above processing steps enable the system to provide real-time and long-term advice.

[0670] (Application example 1)

[0671] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0672] In modern games (such as shogi and go) and factory work sites, there is a demand for systems that provide real-time advice and long-term improvement suggestions to help users and work robots act efficiently and effectively. Conventional systems have had difficulty providing advice that takes into account the individual characteristics and habits of users and the work patterns of robots. To address this issue, the present invention aims to provide a system that analyzes the behavioral data of users and work robots, provides individually optimized advice in real time, and aims to improve long-term efficiency.

[0673] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0674] In this invention, the server includes means for receiving information on moves played by a user, means for analyzing the received information to calculate the best next move and a situation evaluation, means for generating advice in a form that is easy for humans to understand based on the calculation results, means for providing the advice to the user, means for receiving and analyzing robot operation data, means for generating optimal operation procedures based on the analysis results, and means for analyzing past operation data to generate advice for improving long-term operation efficiency. This enables real-time optimization of moves played by users during games and improvement of the efficiency of robot operations in factories.

[0675] A "user" is an entity that uses the system to play games or perform work in a factory.

[0676] A "server" is a computing device that receives and analyzes data from users and robots.

[0677] A "terminal" is a device on which a user plays a game or a robot performs a task.

[0678] "Data analysis" is the process of calculating the optimal next steps or work procedures based on the information received.

[0679] The "best move" is the move in a game that is judged to be the most advantageous at that time.

[0680] "Situation evaluation" is a means of expressing the current situation of a game using numbers or evaluations.

[0681] "Advice" is system-generated instructions or suggestions about next steps or work procedures.

[0682] "Analysis results" are information obtained after the server performs data analysis.

[0683] "Task data" is data related to the task performed by the robot.

[0684] A "pattern" is a characteristic behavioral pattern that a user or robot exhibits through a series of actions.

[0685] A "habit" is a certain behavioral tendency that a user or a robot exhibits in a particular situation.

[0686] "Long-term advice" is improvement proposals that are effective over the long term and are based on past data.

[0687] "Optimized advice" is instructions generated based on a series of data analyses to maximize efficiency and effectiveness.

[0688] This system provides useful advice in real time when users play games (such as shogi or go) or manage robot operations in factories, and makes long-term improvement suggestions based on past behavioral data. This system is mainly composed of three elements: a server, a terminal, and a user or robot.

[0689] System configuration

[0690] 1. Server:

[0691] The server is equipped with AI that analyzes games (such as shogi AI), AI that manages robot work (robot AI), and generative AI.

[0692] The server receives the user's moves and the robot's work data, and calculates the optimal next move, work sequence, and situation evaluation.

[0693] The server also uses generative AI based on the analysis results to generate advice in a format that is easy for humans to understand.

[0694] The server analyzes past game data and work data, and creates long-term advice based on the characteristics and habits of the user and robot.

[0695] The servers use high-performance data center servers (e.g., Google Cloud, AWS EC2) and AI / ML frameworks (e.g., TensorFlow, PyTorch).

[0696] 2. Terminal:

[0697] The terminals are devices on which users play games (e.g., PCs or smartphones) and devices on which robots perform tasks (e.g., transport robots or arm robots).

[0698] The terminal records the user's movements and the robot's actions in real time and transmits the data to the server.

[0699] In addition, the advice and analysis results received from the server are displayed to the user, and are used as reference when the user or robot decides the next move or performs a task.

[0700] The device will also be equipped with sensors (e.g., LiDAR sensor, camera).

[0701] 3. User (Operator):

[0702] Users are players who play games against each other and operators who supervise and manage factory robots.

[0703] Users play games and perform tasks through their terminals, and act based on feedback and advice from the system.

[0704] Program processing (explained in natural language)

[0705] The server receives data on each move made by the user and the robot's work, and calculates the optimal next move and work procedure based on this information. It then uses generative AI to generate advice based on the calculation results in a format that is easy for humans to understand. This advice is sent to the user's device and provided to them in real time.

[0706] The server also uses past game and task data to detect the characteristics and habits of the user and robot, and creates advice for long-term efficiency improvements. This advice is also sent to the user's device, and the user can refer to it when planning their next game or task.

[0707] The hardware uses high-performance data center servers and sensors (e.g., LiDAR sensors and cameras), and the software uses AI / ML frameworks (e.g., TensorFlow, PyTorch). The generative AI model generates advice based on specific game or task scenarios.

[0708] Examples and prompts:

[0709] For example, imagine a robot that transports packages on a conveyor belt in a factory. The robot records the transport time for each package and sends it to a server. Based on past data, the AI ​​on the server analyzes that increasing the speed of the conveyor belt by 15% will reduce the transport time by 20%, and provides that advice to the robot.

[0710] Example prompt sentence:

[0711] "Next, increase the conveyor belt speed by 15% to reduce transport time by 20%. Try this."

[0712] In this way, users and robots can play games or perform tasks while receiving advice that is optimized in real time and over the long term.

[0713] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0714] Step 1:

[0715] The user presses the game start button on the terminal to start the game or work.

[0716] Input: Click the Start button

[0717] Output: Request to start a game or work

[0718] A request to start a game or task is sent from the terminal to the server. This causes the system to enter its initial configuration, and the initial state of the game or the initial conditions of the task are sent from the server to the terminal or robot.

[0719] Step 2:

[0720] The user indicates the next move, or the robot begins work.

[0721] Input: User's move information or robot's task data

[0722] Output: Move information or work data sent to the server

[0723] The terminal records the user's gestures and the robot's work data in real time and sends it to the server, which updates the situation based on the received information and records the progress of the robot's work.

[0724] Step 3:

[0725] The server analyzes the received data and calculates the next best move and optimal work procedure.

[0726] Input: Move information or work data

[0727] Output: Calculation results of the best move or optimal work procedure

[0728] The AI ​​(Shogi AI or robot AI) on the server analyzes the received data and calculates the optimal next move, work procedure, and situation evaluation. The results of this calculation include a situation evaluation of "+1.2" or a best move such as "2-7 Gin".

[0729] Step 4:

[0730] The server uses generative AI to generate advice based on the analysis results.

[0731] Input: Calculation results of the best move or optimal work procedure

[0732] Output: Advice translated into an easy-to-understand format

[0733] The server uses generative AI to convert the calculation results into concrete, easy-to-understand advice, such as, "The next move is to move the silver to 27. This will limit the freedom of the opponent's bishop."

[0734] Step 5:

[0735] The server transmits the generated advice to the terminal or robot and provides it to the user or robot.

[0736] Input: Generated advice

[0737] Output: Send advice to user device or robot

[0738] The server sends the generated advice to the user's terminal or robot, which receives the advice and displays or executes it to indicate the next move or progress the task.

[0739] Step 6:

[0740] The server analyzes past data from users and robots and generates long-term advice.

[0741] Input: Past game data or work data

[0742] Output: Long-term advice based on feature detection and habit analysis

[0743] The server collects and analyzes past data from users and robots. Generative AI uses this data to detect specific patterns and habits and create long-term advice based on them. For example, the generated advice might be, "Try a strategy that emphasizes defense and avoids piece exchanges in the early stages."

[0744] Step 7:

[0745] Long-term advice is sent to the user's device or robot for display and execution.

[0746] Input: Generated long-term advice

[0747] Output: Send advice to user device or robot

[0748] The server sends the generated long-term advice to the terminal or robot, which displays or executes it. The user can refer to this advice when playing or working on the next game.

[0749] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0750] This invention relates to a system that provides useful advice in real time when a user plays shogi or go, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[0751] System configuration

[0752] 1. Server:

[0753] The server is equipped with a shogi AI and a generative AI.

[0754] The server receives the user's move information, analyzes it, and calculates the best move.

[0755] The server also uses generative AI to generate advice based on the analysis results from the shogi AI.

[0756] The server also analyzes the user's past game data and generates long-term advice.

[0757] 2. Terminal:

[0758] A terminal is a device (for example, a PC or smartphone) on which a user plays a game.

[0759] The terminal collects information about the user's moves and sends it to the server.

[0760] It also displays the advice and analysis results received from the server to the user.

[0761] 3. User:

[0762] A user is someone who uses the system through games and receives advice.

[0763] Users play games through their devices and improve their skills based on feedback from the system.

[0764] 4. Emotion Engine:

[0765] The emotion engine is a device and program that recognizes the user's emotional state from their voice, facial expression, input actions, and so on.

[0766] The emotion engine collects and analyzes the user's emotion data and sends it to the server.

[0767] Program processing

[0768] 1. Start of game:

[0769] The game begins when the user clicks the game start button on the terminal.

[0770] The terminal sends a request to start a game to the server.

[0771] The server initializes the game and sends the initial position.

[0772] 2. Receiving and analyzing moves:

[0773] When the user looks at the situation and makes the next move, the information about that move is recorded on the terminal.

[0774] The device transmits this information to the server in real time.

[0775] The server updates the game situation based on the received moves and uses shogi AI to calculate the next best move and game situation evaluation.

[0776] 3. Collecting Emotional Data:

[0777] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc.

[0778] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[0779] The emotion engine transmits the recognized emotional state to the server.

[0780] 4. Generating Advice:

[0781] The server uses generative AI to generate advice about the next move based on the analysis results from the shogi AI and the emotional data received from the emotion engine.

[0782] For example, if the user is feeling impatient or anxious, the content and manner of expression of the advice can be changed.

[0783] Advice is provided in a concrete and easy-to-understand format. For example, the generated advice might be, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop."

[0784] 5. Providing advice:

[0785] The server transmits the generated advice to the user's terminal.

[0786] The terminal displays the advice on the user's screen.

[0787] 6. Analysis of past game data:

[0788] The server periodically collects and stores the user's past game data.

[0789] Based on this data, the generative AI detects the user's move patterns and habits.

[0790] 7. Generating long-term advice:

[0791] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[0792] For example, advice such as "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages" may be generated.

[0793] 8. Providing long-term advice:

[0794] The server sends the generated long-term advice to the terminal.

[0795] The device displays long-term advice on the user's screen.

[0796] The above is a specific embodiment of the present invention, which allows users to receive useful advice in real time during a shogi or go game, and also receive feedback based on their emotional state. Furthermore, by analyzing past game data and emotional data, more appropriate and long-term advice can be provided, helping users improve their shogi skills.

[0797] The processing flow will be explained below.

[0798] Step 1:

[0799] The user clicks the start button on the terminal, which starts the game.

[0800] Step 2:

[0801] The terminal sends the user's request to start a game to the server.

[0802] Step 3:

[0803] The server receives the game start request, initializes the game, and sends the initial position to the terminal.

[0804] Step 4:

[0805] The user looks at the situation and makes the next move.

[0806] Step 5:

[0807] The terminal records the user's moves and sends this information to the server.

[0808] Step 6:

[0809] The server updates the current position based on the moves it receives.

[0810] Step 7:

[0811] The server sends the latest position to the shogi AI, which calculates the next best move and position evaluation.

[0812] Step 8:

[0813] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc.

[0814] Step 9:

[0815] The emotion engine analyzes the emotion data and recognizes the user's emotional state, for example, detecting emotions such as "impatience" or "anxiety."

[0816] Step 10:

[0817] The emotional state recognized by the emotion engine is sent to the server.

[0818] Step 11:

[0819] The server uses generative AI to generate advice about the next move based on the analysis results from the shogi AI and the emotional state received from the emotion engine. For example, if the user is feeling impatient, the server will create advice that takes this into account.

[0820] Step 12:

[0821] The server sends the generated advice to the terminal.

[0822] Step 13:

[0823] The device will display advice on the user's screen, such as "Take your time and move your silver to 27 next. This will limit the freedom of your opponent's bishop."

[0824] Step 14:

[0825] The user makes the next move based on the displayed advice, which returns to step 4.

[0826] Step 15:

[0827] The server periodically collects and stores the user's past game data.

[0828] Step 16:

[0829] The server uses generative AI to analyze the user's past game data and detect their characteristics and habits. For example, it detects that they have a habit of exchanging pieces early in the opening game.

[0830] Step 17:

[0831] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[0832] Step 18:

[0833] The server generates long-term advice and sends it to the device.

[0834] Step 19:

[0835] The device will then display long-term advice to the user, such as "Refrain from exchanging pieces early on and try a more defensive strategy."

[0836] These steps enable the system to provide useful advice in real time, provide feedback based on the user's emotional state, and analyze past game data to provide appropriate long-term advice.

[0837] Example 2

[0838] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0839] Conventional shogi and go game systems have struggled to provide users with useful advice in real time. Furthermore, there was no system that recognized the user's emotional state and provided appropriate feedback accordingly. This led to problems such as poor judgment, impatience, and anxiety during the game, leading to a decline in the quality of play. Furthermore, there was a lack of a way to effectively utilize past game data to support long-term improvement in playing ability.

[0840] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0841] In this invention, the server includes: means for receiving information on moves played by the user; means for analyzing the received information to calculate the next best move and a situation evaluation; means for generating advice in a form that is easy for humans to understand based on the calculation results and the user's emotional state; means for providing the advice and emotional feedback to the user; means for collecting emotional data from the user's voice, facial expressions, and input actions; means for analyzing the collected emotional data to recognize the user's emotional state; means for providing the recognized emotional state to the advice generating means; means for analyzing the user's past game data to detect the user's move patterns and habits; and means for generating long-term advice based on the detected user patterns and habits. This allows the user to receive useful advice in real time during a game and obtain appropriate feedback according to their emotional state. Furthermore, long-term advice based on past game data helps the user improve their chess skill.

[0842] A "user" is someone who plays a game and receives advice and feedback from the system.

[0843] "Terminal" refers to the device used by a user to play a game, including, for example, a PC or smartphone.

[0844] The "server" is the central hardware of the system, and performs functions such as data analysis, advice generation, and sentiment analysis.

[0845] "Shogi AI" is an artificial intelligence that calculates the next best move and situation evaluation in a shogi game.

[0846] "Generative AI" is artificial intelligence that generates advice to provide to users based on analysis results and emotional data.

[0847] An "emotion engine" is a device and program that collects emotional data from the user's voice, facial expressions, input actions, etc., and analyzes it to recognize the user's emotional state.

[0848] "Emotional data" is information collected from the user's voice, facial expressions, input actions, etc., and is used to determine the user's emotional state.

[0849] "Situation evaluation" is an evaluation value calculated by shogi AI for the current situation, and is used to determine the next best move.

[0850] "Advice" is information generated by the server based on the calculation results and emotional state and provided to the user, allowing the user to obtain useful information about their next move.

[0851] "Game data" refers to a record of games played by the user, including detailed information about each move.

[0852] "Long-term advice" is advice generated based on the user's past game data, move patterns, and habits, and is intended to improve the user's chess ability.

[0853] This invention relates to a system that provides useful advice in real time when a user plays shogi or go, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[0854] System configuration

[0855] 1. Server:

[0856] The server is equipped with a shogi AI and a generative AI, which analyzes moves, evaluates the situation, and generates advice. Specifically, AlphaZero is used for the shogi AI, and GPT-4 is used for the generative AI.

[0857] The server receives information about the user's moves, analyzes them, calculates the best next move, and then uses generative AI to generate advice based on the analysis results.

[0858] The server also utilizes the emotion data received from the emotion engine to generate feedback according to when the user is feeling anxious or impatient.

[0859] The system analyzes the user's past game data and provides long-term advice, which helps improve the user's chess skills. Specifically, the system uses MySQL as a database to manage game data.

[0860] 2. Terminal:

[0861] A terminal is a device on which a user plays a game, and examples include a PC or a smartphone.

[0862] The device collects information about the user's moves and sends it to the server, using HTTPS as the communication protocol to ensure data security.

[0863] The system displays advice and analysis results received from the server to the user, and can also display the user's emotional state during the game.

[0864] 3. User:

[0865] The user plays the game through a terminal and receives advice and feedback provided by the server.

[0866] Users can improve their own chess skills based on this advice.

[0867] 4. Emotion Engine:

[0868] The emotion engine is a device and program that collects and analyzes emotion data from the user's voice, facial expressions, input actions, etc. Specifically, it uses libraries such as OpenCV and Dlib.

[0869] The emotion engine analyzes the collected emotion data and recognizes the user's emotional state.

[0870] The recognized emotion data is sent to the server and used to generate advice.

[0871] Specific operation of the system

[0872] When a user starts a game of Shogi or Go using a device, the system starts by clicking the start game button. The device sends a request to start the game to the server, which performs initialization and returns the initial position. When the user makes their next move, the device sends the information about that move to the server in real time, and the server analyzes the move and calculates the best move and a position evaluation.

[0873] At the same time, the emotion engine collects the user's emotional data and analyzes it in real time to recognize the user's emotional state. This emotional data is also sent to the server, which uses the generative AI to generate advice based on this data. For example, if the user is feeling impatient, the generative AI can be given a prompt such as, "Give me gentle advice on how to play the next move in a situation where the user is feeling impatient," and this is used to generate advice.

[0874] Advice is provided to the user via the device, and specific advice such as "As your next move, it would be better to move the silver to 2-7" is displayed on the screen. This allows users to receive useful advice in real time and improve their play based on feedback during the game. The server also accumulates and analyzes past game data to generate long-term advice. This advice is also provided to the user via the device, allowing users to continuously improve their chess skills.

[0875] The above is a specific operation of the system according to the embodiment of the present invention.

[0876] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0877] Step 1: Start the game

[0878] When the user clicks the game start button on the terminal, the game begins.

[0879] Input: User's operation to start a game

[0880] The terminal sends a game start request to the server, which includes initial setting information such as the game ID, user ID, and game type.

[0881] Output: Sending a start request

[0882] The server receives the request and performs the initial setup of the game (generating a game ID, registering player information, and setting the initial position).

[0883] Output: Initial position and initial setting information

[0884] The server sends the completed initial setting information and the initial phase to the terminal.

[0885] Input: Initialization information and initial phase from the server

[0886] The terminal displays the received initial position to the user, and the game officially begins.

[0887] Output: Initial position

[0888] Step 2: Receiving and analyzing the move

[0889] When the user looks at the situation and makes the next move, the information about that move is recorded on the terminal.

[0890] Input: User's move information (such as move coordinates)

[0891] The terminal transmits move information to the server in real time.

[0892] Output: Sending move information

[0893] The server updates the position using the received move information.

[0894] Input: Move information

[0895] The server analyzes the new position using a shogi AI (e.g., AlphaZero) and calculates the next best move and position evaluation.

[0896] Output: Calculated best move and position evaluation

[0897] The server temporarily stores the calculation results and uses them for subsequent processing.

[0898] Output: Stored calculation results

[0899] Step 3: Collecting emotion data

[0900] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc. When using a webcam or microphone, it analyzes the user's facial expressions and tone of voice.

[0901] Input: User's voice, facial expressions, and input actions

[0902] The emotion engine analyzes this data in real time to identify the user's emotional state.

[0903] Output: User's emotional state data

[0904] The emotion engine transmits the recognized emotional state to the server.

[0905] Input: Recognized emotion data

[0906] The server uses this input for the next processing step.

[0907] Output: Sending emotion data

[0908] Step 4: Generating Advice

[0909] The server uses a generative AI (e.g., GPT-4) to generate advice about the next move based on the analysis results from the shogi AI and the emotional data received from the emotion engine.

[0910] Input: Shogi AI analysis results, emotional data

[0911] The server inputs the prompt sentence into the generative AI and generates advice. For example, it inputs a prompt sentence such as, "If the user is in a hurry, please give them gentle advice on how to play the next move. For example, 'Don't rush, take your time to think about your next move.'"

[0912] Output: Generated advice

[0913] The server stores the generated advice and uses it in subsequent steps.

[0914] Output: Stored advice

[0915] Step 5: Providing advice

[0916] The server transmits the generated advice to the user's terminal.

[0917] Input: Generated advice

[0918] The device will then display the received advice on the user's screen. For example, the screen will say, "It would be a good idea to move your silver to 2-7 as your next move."

[0919] Output: Display advice

[0920] Step 6: Analyze past game data

[0921] The server periodically collects and stores the user's past game data, including game dates and times, game types, game results, and detailed information about each move.

[0922] Input: Past game data

[0923] The server analyzes this data and uses generative AI to detect the user's move patterns and habits.

[0924] Output: Data on move patterns and habits

[0925] Step 7: Generate long-term advice

[0926] The server generates long-term advice based on the user's move patterns and habits to help improve their playing ability.

[0927] Input: Data on move patterns and habits

[0928] The server uses generative AI to generate detailed advice on specific strategies and points to note, such as "Try a defensive strategy and avoid exchanging pieces in the early stages."

[0929] Output: Generated long-term advice

[0930] Step 8: Providing long-term advice

[0931] The server sends the generated long-term advice to the terminal.

[0932] Input: Generated long-term advice

[0933] The device will then display long-term advice to the user on their screen, such as "In your next game, I recommend you refrain from exchanging pieces early on and instead focus on defense."

[0934] Output: Displaying long-term advice

[0935] The above is a detailed description of the specific processing flow of this system and the operations performed at each step.

[0936] (Application example 2)

[0937] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0938] Existing shogi and go game systems struggle to provide appropriate advice in real time. Furthermore, they lack systems that can adapt feedback based on the user's emotional state, making it difficult to reduce user stress and fatigue. Furthermore, the lack of real-time advice and emotion recognition is also a challenge for factory robots and other automated systems.

[0939] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving information on moves played by the user; means for analyzing the received information and calculating the next best move and a situation evaluation; means for generating advice in a form that is easy for humans to understand based on the calculation results; means for providing the advice to the user; means for recognizing the emotional state of the operator and generating feedback according to that emotional state; and means for collecting work data and providing long-term improvement advice. This allows the user to receive useful advice in real time and receive feedback according to their emotional state. Furthermore, the ability to analyze past work data and game data and provide long-term improvement advice is expected to improve the user's technical skills and work efficiency.

[0940] "Information about the user's hand gestures" is a record of the specific operations and actions performed by the operator.

[0941] The "receiving means" is a hardware and software mechanism for acquiring the information about the user's hand gesture and transmitting it to other components in the system.

[0942] "Means of analysis" refers to the use of specific algorithms or models to calculate the next best move or situation assessment based on the information received.

[0943] "Best next move and situation evaluation" means the next move that is most suitable for the current situation in a game of shogi or go, and an evaluation of that situation.

[0944] The "means for generating advice" is a mechanism for creating specific advice in a form that is easy for humans to understand, based on the analysis results.

[0945] The "means for providing advice" refers to the hardware and software mechanisms for presenting the generated advice to the user.

[0946] "Emotional state of the operator" refers to the psychological state of the operator while working, and includes information such as stress and fatigue.

[0947] "Means for recognizing emotional states" is a general term for technologies and devices for detecting and analyzing an operator's emotional state from their voice, facial expressions, actions, etc.

[0948] A "feedback generation mechanism" is a mechanism that generates appropriate responses or advice based on the perceived emotional state.

[0949] "Work data" is a record of specific operations performed by operators or systems in the past and their results.

[0950] The "means of providing long-term improvement advice" is a system that uses collected work data to create and provide specific advice to improve operator skills and work efficiency over the long term.

[0951] This invention relates to a system that provides useful advice in real time when a user is performing a task, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[0952] System configuration

[0953] 1. Server:

[0954] The server is equipped with a shogi AI and a generative AI.

[0955] The server receives the user's operation information, analyzes it, and calculates the optimal work procedure.

[0956] The server also uses generative AI based on the analysis results to generate easy-to-understand advice.

[0957] The server also analyzes the user's emotional state and provides feedback based thereon.

[0958] 2. Terminal:

[0959] A terminal is a device (e.g., a PC or tablet) on which a user performs work.

[0960] The terminal collects various pieces of user operation information and transmits it to the server.

[0961] It also displays the advice and analysis results received from the server to the user.

[0962] 3. User:

[0963] A user is an operator who performs work using the system.

[0964] Users can receive real-time advice through their devices, improving work efficiency.

[0965] 4. Emotion Engine:

[0966] The emotion engine is a device and program that recognizes the user's emotional state from facial expressions, voice, actions, and the like.

[0967] The emotion engine collects and analyzes emotion data and sends it to the server.

[0968] Program processing (server, terminal, emotion engine)

[0969] 1. Data collection: While the user is working, the device collects operational information in real time and sends it to the server. The emotion engine also recognizes the user's facial expressions, voice, and movements, analyzes their emotional state, and sends the data to the server.

[0970] 2. Data analysis: Based on the received operation information, the server uses an analytical algorithm to evaluate the current work situation and calculate the optimal work procedure. It also analyzes emotional data to determine whether the user is feeling stressed or tired.

[0971] 3. Advice generation: The server uses generative AI based on the analysis results to generate easy-to-understand work advice. For example, specific advice such as, "As a next step, it is a good idea to connect part A to part B. This will improve assembly efficiency."

[0972] 4. Providing feedback: The server also generates appropriate feedback based on the emotion data, such as "You seem to be feeling tired. Please take a 5-minute break."

[0973] 5. Displaying Advice: The generated advice and feedback is sent to the terminal and displayed on the user's screen.

[0974] Specific examples

[0975] In a specific work scenario, the server advises a user who is assembling one part into another on the appropriate work procedure. Also, if the emotion engine detects the user's fatigue, the server will recommend taking a break.

[0976] Prompt Sentence Examples

[0977] Based on the emotion and task data above, provide advice on the best work procedures for the current task, and include suggestions for breaks if the operator is tired.

[0978] By implementing the present invention in this manner, it is possible to provide useful advice in real time and appropriate feedback according to the user's emotional state, thereby improving the user's work efficiency and safety.

[0979] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0980] Step 1:

[0981] Data collection

[0982] The device collects operational information about the work the user performs in real time. Specifically, it uses sensors and logging functions to obtain data on the procedures and actions the user takes on the device. This data is stored in the device's internal database and then sent to the server. The input is the user's operational information, and the output is the operational data sent to the server.

[0983] Step 2:

[0984] Emotional Data Collection

[0985] The emotion engine collects the user's facial expressions, voice, and movements in real time. The emotion engine is equipped with a camera, microphone, and sensors that collect data to recognize the user's emotional state. This data is sent to a server for analysis. The input is the user's facial expressions, voice, and movement data, and the output is the emotion data sent to the server.

[0986] Step 3:

[0987] Data analysis

[0988] The server uses an analysis algorithm to evaluate the current work situation and emotional state based on the received operation information and emotional data. A specific example of analysis is identifying the current work progress and problems from the user's operation data, and calculating the user's stress level and fatigue level from the emotional data. The input is operation information and emotional data, and the output is an analysis result: an evaluation of the work situation and an evaluation of the emotional state.

[0989] Step 4:

[0990] Advice Generation

[0991] The server uses generative AI based on the analysis results to generate work advice that is easy for the user to understand. For example, if work progress is delayed, it generates specific instructions such as "Connect part A to part B." If it determines that the user is tired, it generates feedback such as "Take a five-minute break." The input is the work situation assessment and emotional state assessment, and the output is the generated advice and feedback.

[0992] Step 5:

[0993] Providing advice

[0994] The server sends the generated advice and feedback to the terminal, which then displays it on the user's screen. For example, the terminal might display a message saying, "As a next step, connect component A to component B." The input is the generated advice and feedback, and the output is the instructions or suggestions displayed on the user's screen.

[0995] Step 6:

[0996] Work data accumulation

[0997] The server accumulates user operation information and emotion data collected daily and maintains a database of this data, allowing for long-term pattern and trend analysis. The input is the accumulated operation information and emotion data, and the output is an updated database.

[0998] Step 7:

[0999] Generate long-term improvement advice

[1000] The server analyzes the accumulated task and emotion data and generates long-term advice to improve the user's task performance. For example, specific advice such as "Based on past data, there is a more efficient procedure for assembling parts" may be generated. The input is data from the long-term database, and the output is long-term improvement advice.

[1001] The above is the specific flow of operations at each processing step. This series of processes allows users to receive useful advice and emotional feedback in real time, improving work efficiency and safety.

[1002] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1003] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1004] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1005] [Third embodiment]

[1006] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1007] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1008] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1009] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1010] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1011] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1012] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1013] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1014] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1015] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1016] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1017] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1018] This invention provides a system that provides useful advice in real time when a user plays shogi or go, and also analyzes the user's characteristics and habits based on past game data to provide long-term advice. This system is mainly composed of three elements: a server, a terminal, and the user.

[1019] System configuration

[1020] 1. Server:

[1021] The server is equipped with a shogi AI and a generative AI.

[1022] The server receives the user's move information, analyzes it, and calculates the best move.

[1023] The server also uses generative AI to generate advice based on the analysis results from the shogi AI.

[1024] The server also analyzes the user's past game data and generates long-term advice.

[1025] 2. Terminal:

[1026] A terminal is a device (for example, a PC or smartphone) on which a user plays a game.

[1027] The terminal collects information about the user's moves and sends it to the server.

[1028] It also displays the advice and analysis results received from the server to the user.

[1029] 3. User:

[1030] A user is someone who uses the system through games and receives advice.

[1031] Users play games through their devices and improve their skills based on feedback from the system.

[1032] Program processing

[1033] 1. Start of game:

[1034] The game begins when the user clicks the game start button on the terminal.

[1035] The terminal sends a request to start a game to the server.

[1036] The server initializes the game and sends the initial position.

[1037] 2. Receiving and analyzing moves:

[1038] When the user makes the next move, the information about that move is recorded on the terminal.

[1039] The device transmits this information to the server in real time.

[1040] The server updates the situation based on the received moves and uses shogi AI to calculate the next best move and situation evaluation.

[1041] For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin."

[1042] 3. Generating Advice:

[1043] The server receives the analysis results from the shogi AI and uses generative AI to generate advice about the next move.

[1044] Advice is provided in a concrete and easy-to-understand format. For example, the generated advice might be, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop."

[1045] 4. Providing advice:

[1046] The server transmits the generated advice to the user's terminal.

[1047] The terminal displays the advice to the user, who can refer to it to decide on the next move.

[1048] 5. Analysis of past game data:

[1049] The server collects and analyzes the user's past game data.

[1050] Based on this data, the generative AI can detect patterns and habits of the user's moves. For example, if the user tends to exchange pieces early,

[1051] 6. Generating long-term advice:

[1052] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[1053] For example, advice such as "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages" may be generated.

[1054] 7. Providing long-term advice:

[1055] The server transmits the generated long-term advice to the terminal.

[1056] The terminal displays long-term advice to the user.

[1057] The above is a specific embodiment of the present invention, which allows users to receive useful advice in real time during a shogi or go game, and further allows them to improve their playing ability through long-term advice tailored to their own characteristics.

[1058] The processing flow will be explained below.

[1059] Step 1:

[1060] The user clicks the start button on the terminal, which starts the game.

[1061] Step 2:

[1062] The terminal sends the user's request to start a game to the server.

[1063] Step 3:

[1064] The server receives the game start request, initializes the game, and sends the initial position to the terminal.

[1065] Step 4:

[1066] The user looks at the situation and makes the next move.

[1067] Step 5:

[1068] The terminal records the user's moves and sends this information to the server.

[1069] Step 6:

[1070] The server updates the current position based on the moves it receives.

[1071] Step 7:

[1072] The server sends the latest position to the shogi AI, which calculates the next best move and position evaluation.

[1073] Step 8:

[1074] The server receives the best move and situation evaluation returned by the shogi AI.

[1075] Step 9:

[1076] The server passes the analysis results to the generative AI, which generates advice in a form that is easy for the user to understand.

[1077] Step 10:

[1078] The server sends the advice generated by the generative AI to the terminal.

[1079] Step 11:

[1080] The terminal displays the advice on the user's screen.

[1081] Step 12:

[1082] The user makes the next move based on the displayed advice, which returns to step 4.

[1083] Step 13:

[1084] The server periodically collects and stores the user's past game data.

[1085] Step 14:

[1086] The server uses generative AI to analyze the user's past game data and detect their characteristics and habits.

[1087] Step 15:

[1088] The server uses generative AI to generate long-term advice based on detected user patterns and habits.

[1089] Step 16:

[1090] The server generates long-term advice and sends it to the device.

[1091] Step 17:

[1092] The device displays long-term advice on the user's screen.

[1093] Through these steps, the system can provide useful advice in real time and support long-term improvement of chess skills based on the user's characteristics.

[1094] Example 1

[1095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1096] In games of shogi and go, users are unable to receive appropriate advice in real time, and there is a lack of specific feedback to improve their long-term playing ability. Furthermore, there is a need for a system that effectively uses past game data to analyze users' characteristics and habits and provide advice based on that analysis.

[1097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1098] In this invention, the server includes means for receiving information on moves played by the user, means for analyzing the received information to calculate the best next move and a situation evaluation, and means for generating advice in a form that is easy for humans to understand based on the calculation results. This makes it possible to provide appropriate advice in real time during the user's game, and to generate long-term advice by analyzing the user's past game data.

[1099] A "user" is someone who uses the system to play shogi or go games and receive advice.

[1100] A "terminal" is a device used by a user to play a game, including a PC or smartphone.

[1101] The "server" is a computer system that implements the shogi AI and generation AI, and is responsible for receiving and analyzing information on the user's moves, and generating and providing advice.

[1102] "Shogi AI" is an artificial intelligence technology that analyzes shogi situations and calculates the best move and situation evaluation.

[1103] "Generative AI" is an artificial intelligence technology that generates easy-to-understand advice for users based on the analysis results from a shogi AI.

[1104] "Past game data" is historical information about games played by the user in the past, and includes data such as moves made and progress of the game situation.

[1105] A "prompt sentence" is a sentence entered to instruct the generation AI to generate advice, and includes specific situation assessments and information on the best move.

[1106] "Advice" is specific and easy-to-understand information that instructs the user on the next move in a game of shogi or go.

[1107] "Long-term advice" is advice on tactics and strategies provided to improve a user's playing ability, based on the results of an analysis of the user's past game data.

[1108] "Real-time" means that advice is provided immediately while the user is playing a game.

[1109] This invention provides a system that provides useful advice in real time when a user plays shogi or go, and also analyzes the user's characteristics and habits based on past game data to provide long-term advice. This system is composed of three elements: a server, a terminal, and the user.

[1110] server

[1111] The server is equipped with a shogi AI and a generative AI (for example, OpenAI's GPT-3, a common generative AI model). The server receives information about the user's moves, analyzes them, and calculates the best next move. The server also generates advice using the generative AI based on the analysis results from the shogi AI. Furthermore, the server analyzes the user's past game data and creates long-term advice.

[1112] Specifically, the server is a cloud server (e.g., an AWS EC2 instance) equipped with a high-performance CPU and GPU, and the database is a database system (e.g., PostgreSQL) for storing and managing users' game history.

[1113] Terminal

[1114] The terminal is the device on which the user plays the game. Specifically, it includes a PC or smartphone. The terminal collects information about the moves made by the user and sends it to the server. It also displays advice and analysis results received from the server to the user.

[1115] A dedicated application for playing games is installed on the device, and the application has the function of monitoring the user's operations in real time and sending that information to the server.

[1116] User

[1117] Users are those who use the system to play games and receive advice. Users play games through their devices and can improve their skills based on feedback from the system.

[1118] Specific examples

[1119] Providing advice during a game

[1120] When the user makes the next move on their device, the information about that move is recorded on the device and sent to the server. The server analyzes the received information and uses shogi AI to calculate the best next move and the position evaluation. For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin." Based on this information, the server uses generative AI to generate advice about the next move.

[1121] Examples of prompts:

[1122] Please generate advice for the user about the next move. The current position is evaluated as +1.2, and the best move is 2-7 Gin. Please explain in a concrete and easy-to-understand way.

[1123] The generated advice might be something like, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop." The server sends this advice to the terminal, which then displays it to the user.

[1124] Generating long-term advice

[1125] Based on the user's past game data, the server uses generative AI to analyze the user's move patterns and habits. For example, if the user tends to exchange pieces early, the server can generate long-term advice.

[1126] Examples of prompts:

[1127] After analyzing the user's past game data, you have noticed a tendency to exchange pieces early on. Please generate long-term advice to improve this tendency. Please explain it by including specific tactics and strategies.

[1128] The generated long-term advice might be, for example, "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages." The server sends this advice to the terminal, which then displays it to the user.

[1129] As a result, users can receive useful advice in real time during a game, and can also improve their Go skills through long-term advice based on their own characteristics and habits.

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

[1131] Step 1: Start the game

[1132] Input: The user clicks the start game button on the terminal.

[1133] Operation: The shogi game application on the device starts operation and catches the user's click event. This event triggers the creation of a request data packet to start the game and sends an HTTP POST request to a specific API endpoint on the server.

[1134] Output: An HTTP request containing a game start request is sent to the server. The server receives this and performs the initial game setup. Specifically, it creates a new game session, generates the initial shogi position data, and sends it to the terminal in JSON format. The terminal receives this data and displays the initial position on the screen.

[1135] Step 2: Receiving and analyzing the move

[1136] Input: User makes next move.

[1137] Action: The user moves a piece using the mouse or touch on the device. The device application monitors this action in real time and collects detailed information such as the coordinate data of the move and the type of piece. This information is packaged into a JSON packet and sent to the server as an HTTP POST request.

[1138] Output: The server updates the position based on the received move information. Specifically, it uses a shogi AI (e.g., Bonanza) to calculate the position evaluation and the best move. For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin." The result is output in JSON format.

[1139] Step 3: Generate Advice

[1140] Input: Situation evaluation and best move information from shogi AI.

[1141] Operation: The server converts the received best move data into a prompt sentence and sends it to the generative AI model (e.g., GPT-3). An example of a prompt sentence is, "Please generate advice for the user about the next move. The current position evaluation is '+1.2', and the best move is '2-7 Gin'. Please explain it in a specific and easy-to-understand way."

[1142] Output: Receives advice from the generative AI model and generates specific and easy-to-understand advice, such as "As your next move, it's a good idea to move your silver to 27. This will limit the freedom of your opponent's bishop." This advice is output in JSON format and sent to the device.

[1143] Step 4: Providing advice

[1144] Input: Advice sentence from a generative AI model.

[1145] How it works: The server creates a JSON packet containing advice and sends it to the device as an HTTP response. The device receives it and displays the advice to the user in a GUI. The advice text is displayed on the device screen as a popup or a dedicated widget.

[1146] Output: Advice is displayed on the user's terminal, which the user can use to decide their next move.

[1147] Step 5: Analyze past game data

[1148] Input: User's game history data.

[1149] How it works: The server queries a database for a user's past games and collects data. This data is then fed into analytical algorithms that use generative AI models (e.g., K-means clustering and decision trees) to detect patterns and move habits. For example, information such as "a user tends to exchange pieces early" can be extracted.

[1150] Output: Pattern and habit information based on the analysis results is generated and output in JSON format.

[1151] Step 6: Generate long-term advice

[1152] Input: Information about the user's playing patterns and habits.

[1153] How it works: The server generates a prompt and inputs this information into the generative AI model. An example of a prompt is, "After analyzing the user's past game data, we have found that they tend to exchange pieces early on. Please generate long-term advice to improve this tendency. Please explain it, including specific tactics and strategies."

[1154] Output: A long-term advice statement from the generative AI model is generated. For example, advice such as "Try a strategy that emphasizes defense and avoids piece exchanges in the early stages" is generated and sent to the device in JSON format.

[1155] Step 7: Providing long-term advice

[1156] Input: Long-term advice statements from a generative AI model.

[1157] How it works: The server creates a JSON packet containing the advice and sends it as an HTTP response to the device. The device receives it and displays the long-term advice to the user in a GUI.

[1158] Output: Long-term advice is displayed on the user's device, allowing the user to improve their long-term strategy.

[1159] The above processing steps enable the system to provide real-time and long-term advice.

[1160] (Application example 1)

[1161] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1162] In modern games (such as shogi and go) and factory work sites, there is a demand for systems that provide real-time advice and long-term improvement suggestions to help users and work robots act efficiently and effectively. Conventional systems have had difficulty providing advice that takes into account the individual characteristics and habits of users and the work patterns of robots. To address this issue, the present invention aims to provide a system that analyzes the behavioral data of users and work robots, provides individually optimized advice in real time, and aims to improve long-term efficiency.

[1163] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1164] In this invention, the server includes means for receiving information on moves played by a user, means for analyzing the received information to calculate the best next move and a situation evaluation, means for generating advice in a form that is easy for humans to understand based on the calculation results, means for providing the advice to the user, means for receiving and analyzing robot operation data, means for generating optimal operation procedures based on the analysis results, and means for analyzing past operation data to generate advice for improving long-term operation efficiency. This enables real-time optimization of moves played by users during games and improvement of the efficiency of robot operations in factories.

[1165] A "user" is an entity that uses the system to play games or perform work in a factory.

[1166] A "server" is a computing device that receives and analyzes data from users and robots.

[1167] A "terminal" is a device on which a user plays a game or a robot performs a task.

[1168] "Data analysis" is the process of calculating the optimal next steps or work procedures based on the information received.

[1169] The "best move" is the move in a game that is judged to be the most advantageous at that time.

[1170] "Situation evaluation" is a means of expressing the current situation of a game using numbers or evaluations.

[1171] "Advice" is system-generated instructions or suggestions about next steps or work procedures.

[1172] "Analysis results" are information obtained after the server performs data analysis.

[1173] "Task data" is data related to the task performed by the robot.

[1174] A "pattern" is a characteristic behavioral pattern that a user or robot exhibits through a series of actions.

[1175] A "habit" is a certain behavioral tendency that a user or a robot exhibits in a particular situation.

[1176] "Long-term advice" is improvement proposals that are effective over the long term and are based on past data.

[1177] "Optimized advice" is instructions generated based on a series of data analyses to maximize efficiency and effectiveness.

[1178] This system provides useful advice in real time when users play games (such as shogi or go) or manage robot operations in factories, and makes long-term improvement suggestions based on past behavioral data. This system is mainly composed of three elements: a server, a terminal, and a user or robot.

[1179] System configuration

[1180] 1. Server:

[1181] The server is equipped with AI that analyzes games (such as shogi AI), AI that manages robot work (robot AI), and generative AI.

[1182] The server receives the user's moves and the robot's work data, and calculates the optimal next move, work sequence, and situation evaluation.

[1183] The server also uses generative AI based on the analysis results to generate advice in a format that is easy for humans to understand.

[1184] The server analyzes past game data and work data, and creates long-term advice based on the characteristics and habits of the user and robot.

[1185] The servers use high-performance data center servers (e.g., Google Cloud, AWS EC2) and AI / ML frameworks (e.g., TensorFlow, PyTorch).

[1186] 2. Terminal:

[1187] The terminals are devices on which users play games (e.g., PCs or smartphones) and devices on which robots perform tasks (e.g., transport robots or arm robots).

[1188] The terminal records the user's movements and the robot's actions in real time and transmits the data to the server.

[1189] In addition, the advice and analysis results received from the server are displayed to the user, and are used as reference when the user or robot decides the next move or performs a task.

[1190] The device will also be equipped with sensors (e.g., LiDAR sensor, camera).

[1191] 3. User (Operator):

[1192] Users are players who play games against each other and operators who supervise and manage factory robots.

[1193] Users play games and perform tasks through their terminals, and act based on feedback and advice from the system.

[1194] Program processing (explained in natural language)

[1195] The server receives data on each move made by the user and the robot's work, and calculates the optimal next move and work procedure based on this information. It then uses generative AI to generate advice based on the calculation results in a format that is easy for humans to understand. This advice is sent to the user's device and provided to them in real time.

[1196] The server also uses past game and task data to detect the characteristics and habits of the user and robot, and creates advice for long-term efficiency improvements. This advice is also sent to the user's device, and the user can refer to it when planning their next game or task.

[1197] The hardware uses high-performance data center servers and sensors (e.g., LiDAR sensors and cameras), and the software uses AI / ML frameworks (e.g., TensorFlow, PyTorch). The generative AI model generates advice based on specific game or task scenarios.

[1198] Examples and prompts:

[1199] For example, imagine a robot that transports packages on a conveyor belt in a factory. The robot records the transport time for each package and sends it to a server. Based on past data, the AI ​​on the server analyzes that increasing the speed of the conveyor belt by 15% will reduce the transport time by 20%, and provides that advice to the robot.

[1200] Example prompt sentence:

[1201] "Next, increase the conveyor belt speed by 15% to reduce transport time by 20%. Try this."

[1202] In this way, users and robots can play games or perform tasks while receiving advice that is optimized in real time and over the long term.

[1203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1204] Step 1:

[1205] The user presses the game start button on the terminal to start the game or work.

[1206] Input: Click the Start button

[1207] Output: Request to start a game or work

[1208] A request to start a game or task is sent from the terminal to the server. This causes the system to enter its initial configuration, and the initial state of the game or the initial conditions of the task are sent from the server to the terminal or robot.

[1209] Step 2:

[1210] The user indicates the next move, or the robot begins work.

[1211] Input: User's move information or robot's task data

[1212] Output: Move information or work data sent to the server

[1213] The terminal records the user's gestures and the robot's work data in real time and sends it to the server, which updates the situation based on the received information and records the progress of the robot's work.

[1214] Step 3:

[1215] The server analyzes the received data and calculates the next best move and optimal work procedure.

[1216] Input: Move information or work data

[1217] Output: Calculation results of the best move or optimal work procedure

[1218] The AI ​​(Shogi AI or robot AI) on the server analyzes the received data and calculates the optimal next move, work procedure, and situation evaluation. The results of this calculation include a situation evaluation of "+1.2" or a best move such as "2-7 Gin".

[1219] Step 4:

[1220] The server uses generative AI to generate advice based on the analysis results.

[1221] Input: Calculation results of the best move or optimal work procedure

[1222] Output: Advice translated into an easy-to-understand format

[1223] The server uses generative AI to convert the calculation results into concrete, easy-to-understand advice, such as, "The next move is to move the silver to 27. This will limit the freedom of the opponent's bishop."

[1224] Step 5:

[1225] The server transmits the generated advice to the terminal or robot and provides it to the user or robot.

[1226] Input: Generated advice

[1227] Output: Send advice to user device or robot

[1228] The server sends the generated advice to the user's terminal or robot, which receives the advice and displays or executes it to indicate the next move or progress the task.

[1229] Step 6:

[1230] The server analyzes past data from users and robots and generates long-term advice.

[1231] Input: Past game data or work data

[1232] Output: Long-term advice based on feature detection and habit analysis

[1233] The server collects and analyzes past data from users and robots. Generative AI uses this data to detect specific patterns and habits and create long-term advice based on them. For example, the generated advice might be, "Try a strategy that emphasizes defense and avoids piece exchanges in the early stages."

[1234] Step 7:

[1235] Long-term advice is sent to the user's device or robot for display and execution.

[1236] Input: Generated long-term advice

[1237] Output: Send advice to user device or robot

[1238] The server sends the generated long-term advice to the terminal or robot, which displays or executes it. The user can refer to this advice when playing or working on the next game.

[1239] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1240] This invention relates to a system that provides useful advice in real time when a user plays shogi or go, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[1241] System configuration

[1242] 1. Server:

[1243] The server is equipped with a shogi AI and a generative AI.

[1244] The server receives the user's move information, analyzes it, and calculates the best move.

[1245] The server also uses generative AI to generate advice based on the analysis results from the shogi AI.

[1246] The server also analyzes the user's past game data and generates long-term advice.

[1247] 2. Terminal:

[1248] A terminal is a device (for example, a PC or smartphone) on which a user plays a game.

[1249] The terminal collects information about the user's moves and sends it to the server.

[1250] It also displays the advice and analysis results received from the server to the user.

[1251] 3. User:

[1252] A user is someone who uses the system through games and receives advice.

[1253] Users play games through their devices and improve their skills based on feedback from the system.

[1254] 4. Emotion Engine:

[1255] The emotion engine is a device and program that recognizes the user's emotional state from their voice, facial expression, input actions, and so on.

[1256] The emotion engine collects and analyzes the user's emotion data and sends it to the server.

[1257] Program processing

[1258] 1. Start of game:

[1259] The game begins when the user clicks the game start button on the terminal.

[1260] The terminal sends a request to start a game to the server.

[1261] The server initializes the game and sends the initial position.

[1262] 2. Receiving and analyzing moves:

[1263] When the user looks at the situation and makes the next move, the information about that move is recorded on the terminal.

[1264] The device transmits this information to the server in real time.

[1265] The server updates the game situation based on the received moves and uses shogi AI to calculate the next best move and game situation evaluation.

[1266] 3. Collecting Emotional Data:

[1267] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc.

[1268] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[1269] The emotion engine transmits the recognized emotional state to the server.

[1270] 4. Generating Advice:

[1271] The server uses generative AI to generate advice about the next move based on the analysis results from the shogi AI and the emotional data received from the emotion engine.

[1272] For example, if the user is feeling impatient or anxious, the content and manner of expression of the advice can be changed.

[1273] Advice is provided in a concrete and easy-to-understand format. For example, the generated advice might be, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop."

[1274] 5. Providing advice:

[1275] The server transmits the generated advice to the user's terminal.

[1276] The terminal displays the advice on the user's screen.

[1277] 6. Analysis of past game data:

[1278] The server periodically collects and stores the user's past game data.

[1279] Based on this data, the generative AI detects the user's move patterns and habits.

[1280] 7. Generating long-term advice:

[1281] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[1282] For example, advice such as "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages" may be generated.

[1283] 8. Providing long-term advice:

[1284] The server sends the generated long-term advice to the terminal.

[1285] The device displays long-term advice on the user's screen.

[1286] The above is a specific embodiment of the present invention, which allows users to receive useful advice in real time during a shogi or go game, and also receive feedback based on their emotional state. Furthermore, by analyzing past game data and emotional data, more appropriate and long-term advice can be provided, helping users improve their shogi skills.

[1287] The processing flow will be explained below.

[1288] Step 1:

[1289] The user clicks the start button on the terminal, which starts the game.

[1290] Step 2:

[1291] The terminal sends the user's request to start a game to the server.

[1292] Step 3:

[1293] The server receives the game start request, initializes the game, and sends the initial position to the terminal.

[1294] Step 4:

[1295] The user looks at the situation and makes the next move.

[1296] Step 5:

[1297] The terminal records the user's moves and sends this information to the server.

[1298] Step 6:

[1299] The server updates the current position based on the moves it receives.

[1300] Step 7:

[1301] The server sends the latest position to the shogi AI, which calculates the next best move and position evaluation.

[1302] Step 8:

[1303] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc.

[1304] Step 9:

[1305] The emotion engine analyzes the emotion data and recognizes the user's emotional state, for example, detecting emotions such as "impatience" or "anxiety."

[1306] Step 10:

[1307] The emotional state recognized by the emotion engine is sent to the server.

[1308] Step 11:

[1309] The server uses generative AI to generate advice about the next move based on the analysis results from the shogi AI and the emotional state received from the emotion engine. For example, if the user is feeling impatient, the server will create advice that takes this into account.

[1310] Step 12:

[1311] The server sends the generated advice to the terminal.

[1312] Step 13:

[1313] The device will display advice on the user's screen, such as "Take your time and move your silver to 27 next. This will limit the freedom of your opponent's bishop."

[1314] Step 14:

[1315] The user makes the next move based on the displayed advice, which returns to step 4.

[1316] Step 15:

[1317] The server periodically collects and stores the user's past game data.

[1318] Step 16:

[1319] The server uses generative AI to analyze the user's past game data and detect their characteristics and habits. For example, it detects that they have a habit of exchanging pieces early in the opening game.

[1320] Step 17:

[1321] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[1322] Step 18:

[1323] The server generates long-term advice and sends it to the device.

[1324] Step 19:

[1325] The device will then display long-term advice to the user, such as "Refrain from exchanging pieces early on and try a more defensive strategy."

[1326] These steps enable the system to provide useful advice in real time, provide feedback based on the user's emotional state, and analyze past game data to provide appropriate long-term advice.

[1327] Example 2

[1328] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1329] Conventional shogi and go game systems have struggled to provide users with useful advice in real time. Furthermore, there was no system that recognized the user's emotional state and provided appropriate feedback accordingly. This led to problems such as poor judgment, impatience, and anxiety during the game, leading to a decline in the quality of play. Furthermore, there was a lack of a way to effectively utilize past game data to support long-term improvement in playing ability.

[1330] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1331] In this invention, the server includes: means for receiving information on moves played by the user; means for analyzing the received information to calculate the next best move and a situation evaluation; means for generating advice in a form that is easy for humans to understand based on the calculation results and the user's emotional state; means for providing the advice and emotional feedback to the user; means for collecting emotional data from the user's voice, facial expressions, and input actions; means for analyzing the collected emotional data to recognize the user's emotional state; means for providing the recognized emotional state to the advice generating means; means for analyzing the user's past game data to detect the user's move patterns and habits; and means for generating long-term advice based on the detected user patterns and habits. This allows the user to receive useful advice in real time during a game and obtain appropriate feedback according to their emotional state. Furthermore, long-term advice based on past game data helps the user improve their chess skill.

[1332] A "user" is someone who plays a game and receives advice and feedback from the system.

[1333] "Terminal" refers to the device used by a user to play a game, including, for example, a PC or smartphone.

[1334] The "server" is the central hardware of the system, and performs functions such as data analysis, advice generation, and sentiment analysis.

[1335] "Shogi AI" is an artificial intelligence that calculates the next best move and situation evaluation in a shogi game.

[1336] "Generative AI" is artificial intelligence that generates advice to provide to users based on analysis results and emotional data.

[1337] An "emotion engine" is a device and program that collects emotional data from the user's voice, facial expressions, input actions, etc., and analyzes it to recognize the user's emotional state.

[1338] "Emotional data" is information collected from the user's voice, facial expressions, input actions, etc., and is used to determine the user's emotional state.

[1339] "Situation evaluation" is an evaluation value calculated by shogi AI for the current situation, and is used to determine the next best move.

[1340] "Advice" is information generated by the server based on the calculation results and emotional state and provided to the user, allowing the user to obtain useful information about their next move.

[1341] "Game data" refers to a record of games played by the user, including detailed information about each move.

[1342] "Long-term advice" is advice generated based on the user's past game data, move patterns, and habits, and is intended to improve the user's chess ability.

[1343] This invention relates to a system that provides useful advice in real time when a user plays shogi or go, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[1344] System configuration

[1345] 1. Server:

[1346] The server is equipped with a shogi AI and a generative AI, which analyzes moves, evaluates the situation, and generates advice. Specifically, AlphaZero is used for the shogi AI, and GPT-4 is used for the generative AI.

[1347] The server receives information about the user's moves, analyzes them, calculates the best next move, and then uses generative AI to generate advice based on the analysis results.

[1348] The server also utilizes the emotion data received from the emotion engine to generate feedback according to when the user is feeling anxious or impatient.

[1349] The system analyzes the user's past game data and provides long-term advice, which helps improve the user's chess skills. Specifically, the system uses MySQL as a database to manage game data.

[1350] 2. Terminal:

[1351] A terminal is a device on which a user plays a game, and examples include a PC or a smartphone.

[1352] The device collects information about the user's moves and sends it to the server, using HTTPS as the communication protocol to ensure data security.

[1353] The system displays advice and analysis results received from the server to the user, and can also display the user's emotional state during the game.

[1354] 3. User:

[1355] The user plays the game through a terminal and receives advice and feedback provided by the server.

[1356] Users can improve their own chess skills based on this advice.

[1357] 4. Emotion Engine:

[1358] The emotion engine is a device and program that collects and analyzes emotion data from the user's voice, facial expressions, input actions, etc. Specifically, it uses libraries such as OpenCV and Dlib.

[1359] The emotion engine analyzes the collected emotion data and recognizes the user's emotional state.

[1360] The recognized emotion data is sent to the server and used to generate advice.

[1361] Specific operation of the system

[1362] When a user starts a game of Shogi or Go using a device, the system starts by clicking the start game button. The device sends a request to start the game to the server, which performs initialization and returns the initial position. When the user makes their next move, the device sends the information about that move to the server in real time, and the server analyzes the move and calculates the best move and a position evaluation.

[1363] At the same time, the emotion engine collects the user's emotional data and analyzes it in real time to recognize the user's emotional state. This emotional data is also sent to the server, which uses the generative AI to generate advice based on this data. For example, if the user is feeling impatient, the generative AI can be given a prompt such as, "Give me gentle advice on how to play the next move in a situation where the user is feeling impatient," and this is used to generate advice.

[1364] Advice is provided to the user via the device, and specific advice such as "As your next move, it would be better to move the silver to 2-7" is displayed on the screen. This allows users to receive useful advice in real time and improve their play based on feedback during the game. The server also accumulates and analyzes past game data to generate long-term advice. This advice is also provided to the user via the device, allowing users to continuously improve their chess skills.

[1365] The above is a specific operation of the system according to the embodiment of the present invention.

[1366] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1367] Step 1: Start the game

[1368] When the user clicks the game start button on the terminal, the game begins.

[1369] Input: User's operation to start a game

[1370] The terminal sends a game start request to the server, which includes initial setting information such as the game ID, user ID, and game type.

[1371] Output: Sending a start request

[1372] The server receives the request and performs the initial setup of the game (generating a game ID, registering player information, and setting the initial position).

[1373] Output: Initial position and initial setting information

[1374] The server sends the completed initial setting information and the initial phase to the terminal.

[1375] Input: Initialization information and initial phase from the server

[1376] The terminal displays the received initial position to the user, and the game officially begins.

[1377] Output: Initial position

[1378] Step 2: Receiving and analyzing the move

[1379] When the user looks at the situation and makes the next move, the information about that move is recorded on the terminal.

[1380] Input: User's move information (such as move coordinates)

[1381] The terminal transmits move information to the server in real time.

[1382] Output: Sending move information

[1383] The server updates the position using the received move information.

[1384] Input: Move information

[1385] The server analyzes the new position using a shogi AI (e.g., AlphaZero) and calculates the next best move and position evaluation.

[1386] Output: Calculated best move and position evaluation

[1387] The server temporarily stores the calculation results and uses them for subsequent processing.

[1388] Output: Stored calculation results

[1389] Step 3: Collecting emotion data

[1390] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc. When using a webcam or microphone, it analyzes the user's facial expressions and tone of voice.

[1391] Input: User's voice, facial expressions, and input actions

[1392] The emotion engine analyzes this data in real time to identify the user's emotional state.

[1393] Output: User's emotional state data

[1394] The emotion engine transmits the recognized emotional state to the server.

[1395] Input: Recognized emotion data

[1396] The server uses this input for the next processing step.

[1397] Output: Sending emotion data

[1398] Step 4: Generating Advice

[1399] The server uses a generative AI (e.g., GPT-4) to generate advice about the next move based on the analysis results from the shogi AI and the emotional data received from the emotion engine.

[1400] Input: Shogi AI analysis results, emotional data

[1401] The server inputs the prompt sentence into the generative AI and generates advice. For example, it inputs a prompt sentence such as, "If the user is in a hurry, please give them gentle advice on how to play the next move. For example, 'Don't rush, take your time to think about your next move.'"

[1402] Output: Generated advice

[1403] The server stores the generated advice and uses it in subsequent steps.

[1404] Output: Stored advice

[1405] Step 5: Providing advice

[1406] The server transmits the generated advice to the user's terminal.

[1407] Input: Generated advice

[1408] The device will then display the received advice on the user's screen. For example, the screen will say, "It would be a good idea to move your silver to 2-7 as your next move."

[1409] Output: Display advice

[1410] Step 6: Analyze past game data

[1411] The server periodically collects and stores the user's past game data, including game dates and times, game types, game results, and detailed information about each move.

[1412] Input: Past game data

[1413] The server analyzes this data and uses generative AI to detect the user's move patterns and habits.

[1414] Output: Data on move patterns and habits

[1415] Step 7: Generate long-term advice

[1416] The server generates long-term advice based on the user's move patterns and habits to help improve their playing ability.

[1417] Input: Data on move patterns and habits

[1418] The server uses generative AI to generate detailed advice on specific strategies and points to note, such as "Try a defensive strategy and avoid exchanging pieces in the early stages."

[1419] Output: Generated long-term advice

[1420] Step 8: Providing long-term advice

[1421] The server sends the generated long-term advice to the terminal.

[1422] Input: Generated long-term advice

[1423] The device will then display long-term advice to the user on their screen, such as "In your next game, I recommend you refrain from exchanging pieces early on and instead focus on defense."

[1424] Output: Displaying long-term advice

[1425] The above is a detailed description of the specific processing flow of this system and the operations performed at each step.

[1426] (Application example 2)

[1427] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1428] Existing shogi and go game systems struggle to provide appropriate advice in real time. Furthermore, they lack systems that can adapt feedback based on the user's emotional state, making it difficult to reduce user stress and fatigue. Furthermore, the lack of real-time advice and emotion recognition is also a challenge for factory robots and other automated systems.

[1429] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving information on moves played by the user; means for analyzing the received information and calculating the next best move and a situation evaluation; means for generating advice in a form that is easy for humans to understand based on the calculation results; means for providing the advice to the user; means for recognizing the emotional state of the operator and generating feedback according to that emotional state; and means for collecting work data and providing long-term improvement advice. This allows the user to receive useful advice in real time and receive feedback according to their emotional state. Furthermore, the ability to analyze past work data and game data and provide long-term improvement advice is expected to improve the user's technical skills and work efficiency.

[1430] "Information about the user's hand gestures" is a record of the specific operations and actions performed by the operator.

[1431] The "receiving means" is a hardware and software mechanism for acquiring the information about the user's hand gesture and transmitting it to other components in the system.

[1432] "Means of analysis" refers to the use of specific algorithms or models to calculate the next best move or situation assessment based on the information received.

[1433] "Best next move and situation evaluation" means the next move that is most suitable for the current situation in a game of shogi or go, and an evaluation of that situation.

[1434] The "means for generating advice" is a mechanism for creating specific advice in a form that is easy for humans to understand, based on the analysis results.

[1435] The "means for providing advice" refers to the hardware and software mechanisms for presenting the generated advice to the user.

[1436] "Emotional state of the operator" refers to the psychological state of the operator while working, and includes information such as stress and fatigue.

[1437] "Means for recognizing emotional states" is a general term for technologies and devices for detecting and analyzing an operator's emotional state from their voice, facial expressions, actions, etc.

[1438] A "feedback generation mechanism" is a mechanism that generates appropriate responses or advice based on the perceived emotional state.

[1439] "Work data" is a record of specific operations performed by operators or systems in the past and their results.

[1440] The "means of providing long-term improvement advice" is a system that uses collected work data to create and provide specific advice to improve operator skills and work efficiency over the long term.

[1441] This invention relates to a system that provides useful advice in real time when a user is performing a task, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[1442] System configuration

[1443] 1. Server:

[1444] The server is equipped with a shogi AI and a generative AI.

[1445] The server receives the user's operation information, analyzes it, and calculates the optimal work procedure.

[1446] The server also uses generative AI based on the analysis results to generate easy-to-understand advice.

[1447] The server also analyzes the user's emotional state and provides feedback based thereon.

[1448] 2. Terminal:

[1449] A terminal is a device (e.g., a PC or tablet) on which a user performs work.

[1450] The terminal collects various pieces of user operation information and transmits it to the server.

[1451] It also displays the advice and analysis results received from the server to the user.

[1452] 3. User:

[1453] A user is an operator who performs work using the system.

[1454] Users can receive real-time advice through their devices, improving work efficiency.

[1455] 4. Emotion Engine:

[1456] The emotion engine is a device and program that recognizes the user's emotional state from facial expressions, voice, actions, and the like.

[1457] The emotion engine collects and analyzes emotion data and sends it to the server.

[1458] Program processing (server, terminal, emotion engine)

[1459] 1. Data collection: While the user is working, the device collects operational information in real time and sends it to the server. The emotion engine also recognizes the user's facial expressions, voice, and movements, analyzes their emotional state, and sends the data to the server.

[1460] 2. Data analysis: Based on the received operation information, the server uses an analytical algorithm to evaluate the current work situation and calculate the optimal work procedure. It also analyzes emotional data to determine whether the user is feeling stressed or tired.

[1461] 3. Advice generation: The server uses generative AI based on the analysis results to generate easy-to-understand work advice. For example, specific advice such as, "As a next step, it is a good idea to connect part A to part B. This will improve assembly efficiency."

[1462] 4. Providing feedback: The server also generates appropriate feedback based on the emotion data, such as "You seem to be feeling tired. Please take a 5-minute break."

[1463] 5. Displaying Advice: The generated advice and feedback is sent to the terminal and displayed on the user's screen.

[1464] Specific examples

[1465] In a specific work scenario, the server advises a user who is assembling one part into another on the appropriate work procedure. Also, if the emotion engine detects the user's fatigue, the server will recommend taking a break.

[1466] Prompt Sentence Examples

[1467] Based on the emotion and task data above, provide advice on the best work procedures for the current task, and include suggestions for breaks if the operator is tired.

[1468] By implementing the present invention in this manner, it is possible to provide useful advice in real time and appropriate feedback according to the user's emotional state, thereby improving the user's work efficiency and safety.

[1469] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1470] Step 1:

[1471] Data collection

[1472] The device collects operational information about the work the user performs in real time. Specifically, it uses sensors and logging functions to obtain data on the procedures and actions the user takes on the device. This data is stored in the device's internal database and then sent to the server. The input is the user's operational information, and the output is the operational data sent to the server.

[1473] Step 2:

[1474] Emotional Data Collection

[1475] The emotion engine collects the user's facial expressions, voice, and movements in real time. The emotion engine is equipped with a camera, microphone, and sensors that collect data to recognize the user's emotional state. This data is sent to a server for analysis. The input is the user's facial expressions, voice, and movement data, and the output is the emotion data sent to the server.

[1476] Step 3:

[1477] Data analysis

[1478] The server uses an analysis algorithm to evaluate the current work situation and emotional state based on the received operation information and emotional data. A specific example of analysis is identifying the current work progress and problems from the user's operation data, and calculating the user's stress level and fatigue level from the emotional data. The input is operation information and emotional data, and the output is an analysis result: an evaluation of the work situation and an evaluation of the emotional state.

[1479] Step 4:

[1480] Advice Generation

[1481] The server uses generative AI based on the analysis results to generate work advice that is easy for the user to understand. For example, if work progress is delayed, it generates specific instructions such as "Connect part A to part B." If it determines that the user is tired, it generates feedback such as "Take a five-minute break." The input is the work situation assessment and emotional state assessment, and the output is the generated advice and feedback.

[1482] Step 5:

[1483] Providing advice

[1484] The server sends the generated advice and feedback to the terminal, which then displays it on the user's screen. For example, the terminal might display a message saying, "As a next step, connect component A to component B." The input is the generated advice and feedback, and the output is the instructions or suggestions displayed on the user's screen.

[1485] Step 6:

[1486] Work data accumulation

[1487] The server accumulates user operation information and emotion data collected daily and maintains a database of this data, allowing for long-term pattern and trend analysis. The input is the accumulated operation information and emotion data, and the output is an updated database.

[1488] Step 7:

[1489] Generate long-term improvement advice

[1490] The server analyzes the accumulated task and emotion data and generates long-term advice to improve the user's task performance. For example, specific advice such as "Based on past data, there is a more efficient procedure for assembling parts" may be generated. The input is data from the long-term database, and the output is long-term improvement advice.

[1491] The above is the specific flow of operations at each processing step. This series of processes allows users to receive useful advice and emotional feedback in real time, improving work efficiency and safety.

[1492] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1493] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1494] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1495] [Fourth embodiment]

[1496] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1497] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1498] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1499] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1500] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1501] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1502] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1503] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1504] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1505] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1506] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1507] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1508] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1509] This invention provides a system that provides useful advice in real time when a user plays shogi or go, and also analyzes the user's characteristics and habits based on past game data to provide long-term advice. This system is mainly composed of three elements: a server, a terminal, and the user.

[1510] System configuration

[1511] 1. Server:

[1512] The server is equipped with a shogi AI and a generative AI.

[1513] The server receives the user's move information, analyzes it, and calculates the best move.

[1514] The server also uses generative AI to generate advice based on the analysis results from the shogi AI.

[1515] The server also analyzes the user's past game data and generates long-term advice.

[1516] 2. Terminal:

[1517] A terminal is a device (for example, a PC or smartphone) on which a user plays a game.

[1518] The terminal collects information about the user's moves and sends it to the server.

[1519] It also displays the advice and analysis results received from the server to the user.

[1520] 3. User:

[1521] A user is someone who uses the system through games and receives advice.

[1522] Users play games through their devices and improve their skills based on feedback from the system.

[1523] Program processing

[1524] 1. Start of game:

[1525] The game begins when the user clicks the game start button on the terminal.

[1526] The terminal sends a request to start a game to the server.

[1527] The server initializes the game and sends the initial position.

[1528] 2. Receiving and analyzing moves:

[1529] When the user makes the next move, the information about that move is recorded on the terminal.

[1530] The device transmits this information to the server in real time.

[1531] The server updates the situation based on the received moves and uses shogi AI to calculate the next best move and situation evaluation.

[1532] For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin."

[1533] 3. Generating Advice:

[1534] The server receives the analysis results from the shogi AI and uses generative AI to generate advice about the next move.

[1535] Advice is provided in a concrete and easy-to-understand format. For example, the generated advice might be, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop."

[1536] 4. Providing advice:

[1537] The server transmits the generated advice to the user's terminal.

[1538] The terminal displays the advice to the user, who can refer to it to decide on the next move.

[1539] 5. Analysis of past game data:

[1540] The server collects and analyzes the user's past game data.

[1541] Based on this data, the generative AI can detect patterns and habits of the user's moves. For example, if the user tends to exchange pieces early,

[1542] 6. Generating long-term advice:

[1543] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[1544] For example, advice such as "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages" may be generated.

[1545] 7. Providing long-term advice:

[1546] The server transmits the generated long-term advice to the terminal.

[1547] The terminal displays long-term advice to the user.

[1548] The above is a specific embodiment of the present invention, which allows users to receive useful advice in real time during a shogi or go game, and further allows them to improve their playing ability through long-term advice tailored to their own characteristics.

[1549] The processing flow will be explained below.

[1550] Step 1:

[1551] The user clicks the start button on the terminal, which starts the game.

[1552] Step 2:

[1553] The terminal sends the user's request to start a game to the server.

[1554] Step 3:

[1555] The server receives the game start request, initializes the game, and sends the initial position to the terminal.

[1556] Step 4:

[1557] The user looks at the situation and makes the next move.

[1558] Step 5:

[1559] The terminal records the user's moves and sends this information to the server.

[1560] Step 6:

[1561] The server updates the current position based on the moves it receives.

[1562] Step 7:

[1563] The server sends the latest position to the shogi AI, which calculates the next best move and position evaluation.

[1564] Step 8:

[1565] The server receives the best move and situation evaluation returned by the shogi AI.

[1566] Step 9:

[1567] The server passes the analysis results to the generative AI, which generates advice in a form that is easy for the user to understand.

[1568] Step 10:

[1569] The server sends the advice generated by the generative AI to the terminal.

[1570] Step 11:

[1571] The terminal displays the advice on the user's screen.

[1572] Step 12:

[1573] The user makes the next move based on the displayed advice, which returns to step 4.

[1574] Step 13:

[1575] The server periodically collects and stores the user's past game data.

[1576] Step 14:

[1577] The server uses generative AI to analyze the user's past game data and detect their characteristics and habits.

[1578] Step 15:

[1579] The server uses generative AI to generate long-term advice based on detected user patterns and habits.

[1580] Step 16:

[1581] The server generates long-term advice and sends it to the device.

[1582] Step 17:

[1583] The device displays long-term advice on the user's screen.

[1584] Through these steps, the system can provide useful advice in real time and support long-term improvement of chess skills based on the user's characteristics.

[1585] Example 1

[1586] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1587] In games of shogi and go, users are unable to receive appropriate advice in real time, and there is a lack of specific feedback to improve their long-term playing ability. Furthermore, there is a need for a system that effectively uses past game data to analyze users' characteristics and habits and provide advice based on that analysis.

[1588] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1589] In this invention, the server includes means for receiving information on moves played by the user, means for analyzing the received information to calculate the best next move and a situation evaluation, and means for generating advice in a form that is easy for humans to understand based on the calculation results. This makes it possible to provide appropriate advice in real time during the user's game, and to generate long-term advice by analyzing the user's past game data.

[1590] A "user" is someone who uses the system to play shogi or go games and receive advice.

[1591] A "terminal" is a device used by a user to play a game, including a PC or smartphone.

[1592] The "server" is a computer system that implements the shogi AI and generation AI, and is responsible for receiving and analyzing information on the user's moves, and generating and providing advice.

[1593] "Shogi AI" is an artificial intelligence technology that analyzes shogi situations and calculates the best move and situation evaluation.

[1594] "Generative AI" is an artificial intelligence technology that generates easy-to-understand advice for users based on the analysis results from a shogi AI.

[1595] "Past game data" is historical information about games played by the user in the past, and includes data such as moves made and progress of the game situation.

[1596] A "prompt sentence" is a sentence entered to instruct the generation AI to generate advice, and includes specific situation assessments and information on the best move.

[1597] "Advice" is specific and easy-to-understand information that instructs the user on the next move in a game of shogi or go.

[1598] "Long-term advice" is advice on tactics and strategies provided to improve a user's playing ability, based on the results of an analysis of the user's past game data.

[1599] "Real-time" means that advice is provided immediately while the user is playing a game.

[1600] This invention provides a system that provides useful advice in real time when a user plays shogi or go, and also analyzes the user's characteristics and habits based on past game data to provide long-term advice. This system is composed of three elements: a server, a terminal, and the user.

[1601] server

[1602] The server is equipped with a shogi AI and a generative AI (for example, OpenAI's GPT-3, a common generative AI model). The server receives information about the user's moves, analyzes them, and calculates the best next move. The server also generates advice using the generative AI based on the analysis results from the shogi AI. Furthermore, the server analyzes the user's past game data and creates long-term advice.

[1603] Specifically, the server is a cloud server (e.g., an AWS EC2 instance) equipped with a high-performance CPU and GPU, and the database is a database system (e.g., PostgreSQL) for storing and managing users' game history.

[1604] Terminal

[1605] The terminal is the device on which the user plays the game. Specifically, it includes a PC or smartphone. The terminal collects information about the moves made by the user and sends it to the server. It also displays advice and analysis results received from the server to the user.

[1606] A dedicated application for playing games is installed on the device, and the application has the function of monitoring the user's operations in real time and sending that information to the server.

[1607] User

[1608] Users are those who use the system to play games and receive advice. Users play games through their devices and can improve their skills based on feedback from the system.

[1609] Specific examples

[1610] Providing advice during a game

[1611] When the user makes the next move on their device, the information about that move is recorded on the device and sent to the server. The server analyzes the received information and uses shogi AI to calculate the best next move and the position evaluation. For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin." Based on this information, the server uses generative AI to generate advice about the next move.

[1612] Examples of prompts:

[1613] Please generate advice for the user about the next move. The current position is evaluated as +1.2, and the best move is 2-7 Gin. Please explain in a concrete and easy-to-understand way.

[1614] The generated advice might be something like, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop." The server sends this advice to the terminal, which then displays it to the user.

[1615] Generating long-term advice

[1616] Based on the user's past game data, the server uses generative AI to analyze the user's move patterns and habits. For example, if the user tends to exchange pieces early, the server can generate long-term advice.

[1617] Examples of prompts:

[1618] After analyzing the user's past game data, you have noticed a tendency to exchange pieces early on. Please generate long-term advice to improve this tendency. Please explain it by including specific tactics and strategies.

[1619] The generated long-term advice might be, for example, "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages." The server sends this advice to the terminal, which then displays it to the user.

[1620] As a result, users can receive useful advice in real time during a game, and can also improve their Go skills through long-term advice based on their own characteristics and habits.

[1621] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1622] Step 1: Start the game

[1623] Input: The user clicks the start game button on the terminal.

[1624] Operation: The shogi game application on the device starts operation and catches the user's click event. This event triggers the creation of a request data packet to start the game and sends an HTTP POST request to a specific API endpoint on the server.

[1625] Output: An HTTP request containing a game start request is sent to the server. The server receives this and performs the initial game setup. Specifically, it creates a new game session, generates the initial shogi position data, and sends it to the terminal in JSON format. The terminal receives this data and displays the initial position on the screen.

[1626] Step 2: Receiving and analyzing the move

[1627] Input: User makes next move.

[1628] Action: The user moves a piece using the mouse or touch on the device. The device application monitors this action in real time and collects detailed information such as the coordinate data of the move and the type of piece. This information is packaged into a JSON packet and sent to the server as an HTTP POST request.

[1629] Output: The server updates the position based on the received move information. Specifically, it uses a shogi AI (e.g., Bonanza) to calculate the position evaluation and the best move. For example, suppose the position evaluation is "+1.2" and the best move is "2-7 Gin." The result is output in JSON format.

[1630] Step 3: Generate Advice

[1631] Input: Situation evaluation and best move information from shogi AI.

[1632] Operation: The server converts the received best move data into a prompt sentence and sends it to the generative AI model (e.g., GPT-3). An example of a prompt sentence is, "Please generate advice for the user about the next move. The current position evaluation is '+1.2', and the best move is '2-7 Gin'. Please explain it in a specific and easy-to-understand way."

[1633] Output: Receives advice from the generative AI model and generates specific and easy-to-understand advice, such as "As your next move, it's a good idea to move your silver to 27. This will limit the freedom of your opponent's bishop." This advice is output in JSON format and sent to the device.

[1634] Step 4: Providing advice

[1635] Input: Advice sentence from a generative AI model.

[1636] How it works: The server creates a JSON packet containing advice and sends it to the device as an HTTP response. The device receives it and displays the advice to the user in a GUI. The advice text is displayed on the device screen as a popup or a dedicated widget.

[1637] Output: Advice is displayed on the user's terminal, which the user can use to decide their next move.

[1638] Step 5: Analyze past game data

[1639] Input: User's game history data.

[1640] How it works: The server queries a database for a user's past games and collects data. This data is then fed into analytical algorithms that use generative AI models (e.g., K-means clustering and decision trees) to detect patterns and move habits. For example, information such as "a user tends to exchange pieces early" can be extracted.

[1641] Output: Pattern and habit information based on the analysis results is generated and output in JSON format.

[1642] Step 6: Generate long-term advice

[1643] Input: Information about the user's playing patterns and habits.

[1644] How it works: The server generates a prompt and inputs this information into the generative AI model. An example of a prompt is, "After analyzing the user's past game data, we have found that they tend to exchange pieces early on. Please generate long-term advice to improve this tendency. Please explain it, including specific tactics and strategies."

[1645] Output: A long-term advice statement from the generative AI model is generated. For example, advice such as "Try a strategy that emphasizes defense and avoids piece exchanges in the early stages" is generated and sent to the device in JSON format.

[1646] Step 7: Providing long-term advice

[1647] Input: Long-term advice statements from a generative AI model.

[1648] How it works: The server creates a JSON packet containing the advice and sends it as an HTTP response to the device. The device receives it and displays the long-term advice to the user in a GUI.

[1649] Output: Long-term advice is displayed on the user's device, allowing the user to improve their long-term strategy.

[1650] The above processing steps enable the system to provide real-time and long-term advice.

[1651] (Application example 1)

[1652] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1653] In modern games (such as shogi and go) and factory work sites, there is a demand for systems that provide real-time advice and long-term improvement suggestions to help users and work robots act efficiently and effectively. Conventional systems have had difficulty providing advice that takes into account the individual characteristics and habits of users and the work patterns of robots. To address this issue, the present invention aims to provide a system that analyzes the behavioral data of users and work robots, provides individually optimized advice in real time, and aims to improve long-term efficiency.

[1654] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1655] In this invention, the server includes means for receiving information on moves played by a user, means for analyzing the received information to calculate the best next move and a situation evaluation, means for generating advice in a form that is easy for humans to understand based on the calculation results, means for providing the advice to the user, means for receiving and analyzing robot operation data, means for generating optimal operation procedures based on the analysis results, and means for analyzing past operation data to generate advice for improving long-term operation efficiency. This enables real-time optimization of moves played by users during games and improvement of the efficiency of robot operations in factories.

[1656] A "user" is an entity that uses the system to play games or perform work in a factory.

[1657] A "server" is a computing device that receives and analyzes data from users and robots.

[1658] A "terminal" is a device on which a user plays a game or a robot performs a task.

[1659] "Data analysis" is the process of calculating the optimal next steps or work procedures based on the information received.

[1660] The "best move" is the move in a game that is judged to be the most advantageous at that time.

[1661] "Situation evaluation" is a means of expressing the current situation of a game using numbers or evaluations.

[1662] "Advice" is system-generated instructions or suggestions about next steps or work procedures.

[1663] "Analysis results" are information obtained after the server performs data analysis.

[1664] "Task data" is data related to the task performed by the robot.

[1665] A "pattern" is a characteristic behavioral pattern that a user or robot exhibits through a series of actions.

[1666] A "habit" is a certain behavioral tendency that a user or a robot exhibits in a particular situation.

[1667] "Long-term advice" is improvement proposals that are effective over the long term and are based on past data.

[1668] "Optimized advice" is instructions generated based on a series of data analyses to maximize efficiency and effectiveness.

[1669] This system provides useful advice in real time when users play games (such as shogi or go) or manage robot operations in factories, and makes long-term improvement suggestions based on past behavioral data. This system is mainly composed of three elements: a server, a terminal, and a user or robot.

[1670] System configuration

[1671] 1. Server:

[1672] The server is equipped with AI that analyzes games (such as shogi AI), AI that manages robot work (robot AI), and generative AI.

[1673] The server receives the user's moves and the robot's work data, and calculates the optimal next move, work sequence, and situation evaluation.

[1674] The server also uses generative AI based on the analysis results to generate advice in a format that is easy for humans to understand.

[1675] The server analyzes past game data and work data, and creates long-term advice based on the characteristics and habits of the user and robot.

[1676] The servers use high-performance data center servers (e.g., Google Cloud, AWS EC2) and AI / ML frameworks (e.g., TensorFlow, PyTorch).

[1677] 2. Terminal:

[1678] The terminals are devices on which users play games (e.g., PCs or smartphones) and devices on which robots perform tasks (e.g., transport robots or arm robots).

[1679] The terminal records the user's movements and the robot's actions in real time and transmits the data to the server.

[1680] In addition, the advice and analysis results received from the server are displayed to the user, and are used as reference when the user or robot decides the next move or performs a task.

[1681] The device will also be equipped with sensors (e.g., LiDAR sensor, camera).

[1682] 3. User (Operator):

[1683] Users are players who play games against each other and operators who supervise and manage factory robots.

[1684] Users play games and perform tasks through their terminals, and act based on feedback and advice from the system.

[1685] Program processing (explained in natural language)

[1686] The server receives data on each move made by the user and the robot's work, and calculates the optimal next move and work procedure based on this information. It then uses generative AI to generate advice based on the calculation results in a format that is easy for humans to understand. This advice is sent to the user's device and provided to them in real time.

[1687] The server also uses past game and task data to detect the characteristics and habits of the user and robot, and creates advice for long-term efficiency improvements. This advice is also sent to the user's device, and the user can refer to it when planning their next game or task.

[1688] The hardware uses high-performance data center servers and sensors (e.g., LiDAR sensors and cameras), and the software uses AI / ML frameworks (e.g., TensorFlow, PyTorch). The generative AI model generates advice based on specific game or task scenarios.

[1689] Examples and prompts:

[1690] For example, imagine a robot that transports packages on a conveyor belt in a factory. The robot records the transport time for each package and sends it to a server. Based on past data, the AI ​​on the server analyzes that increasing the speed of the conveyor belt by 15% will reduce the transport time by 20%, and provides that advice to the robot.

[1691] Example prompt sentence:

[1692] "Next, increase the conveyor belt speed by 15% to reduce transport time by 20%. Try this."

[1693] In this way, users and robots can play games or perform tasks while receiving advice that is optimized in real time and over the long term.

[1694] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1695] Step 1:

[1696] The user presses the game start button on the terminal to start the game or work.

[1697] Input: Click the Start button

[1698] Output: Request to start a game or work

[1699] A request to start a game or task is sent from the terminal to the server. This causes the system to enter its initial configuration, and the initial state of the game or the initial conditions of the task are sent from the server to the terminal or robot.

[1700] Step 2:

[1701] The user indicates the next move, or the robot begins work.

[1702] Input: User's move information or robot's task data

[1703] Output: Move information or work data sent to the server

[1704] The terminal records the user's gestures and the robot's work data in real time and sends it to the server, which updates the situation based on the received information and records the progress of the robot's work.

[1705] Step 3:

[1706] The server analyzes the received data and calculates the next best move and optimal work procedure.

[1707] Input: Move information or work data

[1708] Output: Calculation results of the best move or optimal work procedure

[1709] The AI ​​(Shogi AI or robot AI) on the server analyzes the received data and calculates the optimal next move, work procedure, and situation evaluation. The results of this calculation include a situation evaluation of "+1.2" or a best move such as "2-7 Gin".

[1710] Step 4:

[1711] The server uses generative AI to generate advice based on the analysis results.

[1712] Input: Calculation results of the best move or optimal work procedure

[1713] Output: Advice translated into an easy-to-understand format

[1714] The server uses generative AI to convert the calculation results into concrete, easy-to-understand advice, such as, "The next move is to move the silver to 27. This will limit the freedom of the opponent's bishop."

[1715] Step 5:

[1716] The server transmits the generated advice to the terminal or robot and provides it to the user or robot.

[1717] Input: Generated advice

[1718] Output: Send advice to user device or robot

[1719] The server sends the generated advice to the user's terminal or robot, which receives the advice and displays or executes it to indicate the next move or progress the task.

[1720] Step 6:

[1721] The server analyzes past data from users and robots and generates long-term advice.

[1722] Input: Past game data or work data

[1723] Output: Long-term advice based on feature detection and habit analysis

[1724] The server collects and analyzes past data from users and robots. Generative AI uses this data to detect specific patterns and habits and create long-term advice based on them. For example, the generated advice might be, "Try a strategy that emphasizes defense and avoids piece exchanges in the early stages."

[1725] Step 7:

[1726] Long-term advice is sent to the user's device or robot for display and execution.

[1727] Input: Generated long-term advice

[1728] Output: Send advice to user device or robot

[1729] The server sends the generated long-term advice to the terminal or robot, which displays or executes it. The user can refer to this advice when playing or working on the next game.

[1730] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1731] This invention relates to a system that provides useful advice in real time when a user plays shogi or go, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[1732] System configuration

[1733] 1. Server:

[1734] The server is equipped with a shogi AI and a generative AI.

[1735] The server receives the user's move information, analyzes it, and calculates the best move.

[1736] The server also uses generative AI to generate advice based on the analysis results from the shogi AI.

[1737] The server also analyzes the user's past game data and generates long-term advice.

[1738] 2. Terminal:

[1739] A terminal is a device (for example, a PC or smartphone) on which a user plays a game.

[1740] The terminal collects information about the user's moves and sends it to the server.

[1741] It also displays the advice and analysis results received from the server to the user.

[1742] 3. User:

[1743] A user is someone who uses the system through games and receives advice.

[1744] Users play games through their devices and improve their skills based on feedback from the system.

[1745] 4. Emotion Engine:

[1746] The emotion engine is a device and program that recognizes the user's emotional state from their voice, facial expression, input actions, and so on.

[1747] The emotion engine collects and analyzes the user's emotion data and sends it to the server.

[1748] Program processing

[1749] 1. Start of game:

[1750] The game begins when the user clicks the game start button on the terminal.

[1751] The terminal sends a request to start a game to the server.

[1752] The server initializes the game and sends the initial position.

[1753] 2. Receiving and analyzing moves:

[1754] When the user looks at the situation and makes the next move, the information about that move is recorded on the terminal.

[1755] The device transmits this information to the server in real time.

[1756] The server updates the game situation based on the received moves and uses shogi AI to calculate the next best move and game situation evaluation.

[1757] 3. Collecting Emotional Data:

[1758] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc.

[1759] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[1760] The emotion engine transmits the recognized emotional state to the server.

[1761] 4. Generating Advice:

[1762] The server uses generative AI to generate advice about the next move based on the analysis results from the shogi AI and the emotional data received from the emotion engine.

[1763] For example, if the user is feeling impatient or anxious, the content and manner of expression of the advice can be changed.

[1764] Advice is provided in a concrete and easy-to-understand format. For example, the generated advice might be, "As your next move, it's better to move your silver to 27. This will limit the freedom of your opponent's bishop."

[1765] 5. Providing advice:

[1766] The server transmits the generated advice to the user's terminal.

[1767] The terminal displays the advice on the user's screen.

[1768] 6. Analysis of past game data:

[1769] The server periodically collects and stores the user's past game data.

[1770] Based on this data, the generative AI detects the user's move patterns and habits.

[1771] 7. Generating long-term advice:

[1772] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[1773] For example, advice such as "Try a strategy that emphasizes defense and refrain from exchanging pieces in the early stages" may be generated.

[1774] 8. Providing long-term advice:

[1775] The server sends the generated long-term advice to the terminal.

[1776] The device displays long-term advice on the user's screen.

[1777] The above is a specific embodiment of the present invention, which allows users to receive useful advice in real time during a shogi or go game, and also receive feedback based on their emotional state. Furthermore, by analyzing past game data and emotional data, more appropriate and long-term advice can be provided, helping users improve their shogi skills.

[1778] The processing flow will be explained below.

[1779] Step 1:

[1780] The user clicks the start button on the terminal, which starts the game.

[1781] Step 2:

[1782] The terminal sends the user's request to start a game to the server.

[1783] Step 3:

[1784] The server receives the game start request, initializes the game, and sends the initial position to the terminal.

[1785] Step 4:

[1786] The user looks at the situation and makes the next move.

[1787] Step 5:

[1788] The terminal records the user's moves and sends this information to the server.

[1789] Step 6:

[1790] The server updates the current position based on the moves it receives.

[1791] Step 7:

[1792] The server sends the latest position to the shogi AI, which calculates the next best move and position evaluation.

[1793] Step 8:

[1794] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc.

[1795] Step 9:

[1796] The emotion engine analyzes the emotion data and recognizes the user's emotional state, for example, detecting emotions such as "impatience" or "anxiety."

[1797] Step 10:

[1798] The emotional state recognized by the emotion engine is sent to the server.

[1799] Step 11:

[1800] The server uses generative AI to generate advice about the next move based on the analysis results from the shogi AI and the emotional state received from the emotion engine. For example, if the user is feeling impatient, the server will create advice that takes this into account.

[1801] Step 12:

[1802] The server sends the generated advice to the terminal.

[1803] Step 13:

[1804] The device will display advice on the user's screen, such as "Take your time and move your silver to 27 next. This will limit the freedom of your opponent's bishop."

[1805] Step 14:

[1806] The user makes the next move based on the displayed advice, which returns to step 4.

[1807] Step 15:

[1808] The server periodically collects and stores the user's past game data.

[1809] Step 16:

[1810] The server uses generative AI to analyze the user's past game data and detect their characteristics and habits. For example, it detects that they have a habit of exchanging pieces early in the opening game.

[1811] Step 17:

[1812] Based on the patterns and habits detected, the server generates long-term advice to help users improve their playing skills.

[1813] Step 18:

[1814] The server generates long-term advice and sends it to the device.

[1815] Step 19:

[1816] The device will then display long-term advice to the user, such as "Refrain from exchanging pieces early on and try a more defensive strategy."

[1817] These steps enable the system to provide useful advice in real time, provide feedback based on the user's emotional state, and analyze past game data to provide appropriate long-term advice.

[1818] Example 2

[1819] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1820] Conventional shogi and go game systems have struggled to provide users with useful advice in real time. Furthermore, there was no system that recognized the user's emotional state and provided appropriate feedback accordingly. This led to problems such as poor judgment, impatience, and anxiety during the game, leading to a decline in the quality of play. Furthermore, there was a lack of a way to effectively utilize past game data to support long-term improvement in playing ability.

[1821] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1822] In this invention, the server includes: means for receiving information on moves played by the user; means for analyzing the received information to calculate the next best move and a situation evaluation; means for generating advice in a form that is easy for humans to understand based on the calculation results and the user's emotional state; means for providing the advice and emotional feedback to the user; means for collecting emotional data from the user's voice, facial expressions, and input actions; means for analyzing the collected emotional data to recognize the user's emotional state; means for providing the recognized emotional state to the advice generating means; means for analyzing the user's past game data to detect the user's move patterns and habits; and means for generating long-term advice based on the detected user patterns and habits. This allows the user to receive useful advice in real time during a game and obtain appropriate feedback according to their emotional state. Furthermore, long-term advice based on past game data helps the user improve their chess skill.

[1823] A "user" is someone who plays a game and receives advice and feedback from the system.

[1824] "Terminal" refers to the device used by a user to play a game, including, for example, a PC or smartphone.

[1825] The "server" is the central hardware of the system, and performs functions such as data analysis, advice generation, and sentiment analysis.

[1826] "Shogi AI" is an artificial intelligence that calculates the next best move and situation evaluation in a shogi game.

[1827] "Generative AI" is artificial intelligence that generates advice to provide to users based on analysis results and emotional data.

[1828] An "emotion engine" is a device and program that collects emotional data from the user's voice, facial expressions, input actions, etc., and analyzes it to recognize the user's emotional state.

[1829] "Emotional data" is information collected from the user's voice, facial expressions, input actions, etc., and is used to determine the user's emotional state.

[1830] "Situation evaluation" is an evaluation value calculated by shogi AI for the current situation, and is used to determine the next best move.

[1831] "Advice" is information generated by the server based on the calculation results and emotional state and provided to the user, allowing the user to obtain useful information about their next move.

[1832] "Game data" refers to a record of games played by the user, including detailed information about each move.

[1833] "Long-term advice" is advice generated based on the user's past game data, move patterns, and habits, and is intended to improve the user's chess ability.

[1834] This invention relates to a system that provides useful advice in real time when a user plays shogi or go, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[1835] System configuration

[1836] 1. Server:

[1837] The server is equipped with a shogi AI and a generative AI, which analyzes moves, evaluates the situation, and generates advice. Specifically, AlphaZero is used for the shogi AI, and GPT-4 is used for the generative AI.

[1838] The server receives information about the user's moves, analyzes them, calculates the best next move, and then uses generative AI to generate advice based on the analysis results.

[1839] The server also utilizes the emotion data received from the emotion engine to generate feedback according to when the user is feeling anxious or impatient.

[1840] The system analyzes the user's past game data and provides long-term advice, which helps improve the user's chess skills. Specifically, the system uses MySQL as a database to manage game data.

[1841] 2. Terminal:

[1842] A terminal is a device on which a user plays a game, and examples include a PC or a smartphone.

[1843] The device collects information about the user's moves and sends it to the server, using HTTPS as the communication protocol to ensure data security.

[1844] The system displays advice and analysis results received from the server to the user, and can also display the user's emotional state during the game.

[1845] 3. User:

[1846] The user plays the game through a terminal and receives advice and feedback provided by the server.

[1847] Users can improve their own chess skills based on this advice.

[1848] 4. Emotion Engine:

[1849] The emotion engine is a device and program that collects and analyzes emotion data from the user's voice, facial expressions, input actions, etc. Specifically, it uses libraries such as OpenCV and Dlib.

[1850] The emotion engine analyzes the collected emotion data and recognizes the user's emotional state.

[1851] The recognized emotion data is sent to the server and used to generate advice.

[1852] Specific operation of the system

[1853] When a user starts a game of Shogi or Go using a device, the system starts by clicking the start game button. The device sends a request to start the game to the server, which performs initialization and returns the initial position. When the user makes their next move, the device sends the information about that move to the server in real time, and the server analyzes the move and calculates the best move and a position evaluation.

[1854] At the same time, the emotion engine collects the user's emotional data and analyzes it in real time to recognize the user's emotional state. This emotional data is also sent to the server, which uses the generative AI to generate advice based on this data. For example, if the user is feeling impatient, the generative AI can be given a prompt such as, "Give me gentle advice on how to play the next move in a situation where the user is feeling impatient," and this is used to generate advice.

[1855] Advice is provided to the user via the device, and specific advice such as "As your next move, it would be better to move the silver to 2-7" is displayed on the screen. This allows users to receive useful advice in real time and improve their play based on feedback during the game. The server also accumulates and analyzes past game data to generate long-term advice. This advice is also provided to the user via the device, allowing users to continuously improve their chess skills.

[1856] The above is a specific operation of the system according to the embodiment of the present invention.

[1857] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1858] Step 1: Start the game

[1859] When the user clicks the game start button on the terminal, the game begins.

[1860] Input: User's operation to start a game

[1861] The terminal sends a game start request to the server, which includes initial setting information such as the game ID, user ID, and game type.

[1862] Output: Sending a start request

[1863] The server receives the request and performs the initial setup of the game (generating a game ID, registering player information, and setting the initial position).

[1864] Output: Initial position and initial setting information

[1865] The server sends the completed initial setting information and the initial phase to the terminal.

[1866] Input: Initialization information and initial phase from the server

[1867] The terminal displays the received initial position to the user, and the game officially begins.

[1868] Output: Initial position

[1869] Step 2: Receiving and analyzing the move

[1870] When the user looks at the situation and makes the next move, the information about that move is recorded on the terminal.

[1871] Input: User's move information (such as move coordinates)

[1872] The terminal transmits move information to the server in real time.

[1873] Output: Sending move information

[1874] The server updates the position using the received move information.

[1875] Input: Move information

[1876] The server analyzes the new position using a shogi AI (e.g., AlphaZero) and calculates the next best move and position evaluation.

[1877] Output: Calculated best move and position evaluation

[1878] The server temporarily stores the calculation results and uses them for subsequent processing.

[1879] Output: Stored calculation results

[1880] Step 3: Collecting emotion data

[1881] The emotion engine collects emotional data from the user's voice, facial expressions, input actions, etc. When using a webcam or microphone, it analyzes the user's facial expressions and tone of voice.

[1882] Input: User's voice, facial expressions, and input actions

[1883] The emotion engine analyzes this data in real time to identify the user's emotional state.

[1884] Output: User's emotional state data

[1885] The emotion engine transmits the recognized emotional state to the server.

[1886] Input: Recognized emotion data

[1887] The server uses this input for the next processing step.

[1888] Output: Sending emotion data

[1889] Step 4: Generating Advice

[1890] The server uses a generative AI (e.g., GPT-4) to generate advice about the next move based on the analysis results from the shogi AI and the emotional data received from the emotion engine.

[1891] Input: Shogi AI analysis results, emotional data

[1892] The server inputs the prompt sentence into the generative AI and generates advice. For example, it inputs a prompt sentence such as, "If the user is in a hurry, please give them gentle advice on how to play the next move. For example, 'Don't rush, take your time to think about your next move.'"

[1893] Output: Generated advice

[1894] The server stores the generated advice and uses it in subsequent steps.

[1895] Output: Stored advice

[1896] Step 5: Providing advice

[1897] The server transmits the generated advice to the user's terminal.

[1898] Input: Generated advice

[1899] The device will then display the received advice on the user's screen. For example, the screen will say, "It would be a good idea to move your silver to 2-7 as your next move."

[1900] Output: Display advice

[1901] Step 6: Analyze past game data

[1902] The server periodically collects and stores the user's past game data, including game dates and times, game types, game results, and detailed information about each move.

[1903] Input: Past game data

[1904] The server analyzes this data and uses generative AI to detect the user's move patterns and habits.

[1905] Output: Data on move patterns and habits

[1906] Step 7: Generate long-term advice

[1907] The server generates long-term advice based on the user's move patterns and habits to help improve their playing ability.

[1908] Input: Data on move patterns and habits

[1909] The server uses generative AI to generate detailed advice on specific strategies and points to note, such as "Try a defensive strategy and avoid exchanging pieces in the early stages."

[1910] Output: Generated long-term advice

[1911] Step 8: Providing long-term advice

[1912] The server sends the generated long-term advice to the terminal.

[1913] Input: Generated long-term advice

[1914] The device will then display long-term advice to the user on their screen, such as "In your next game, I recommend you refrain from exchanging pieces early on and instead focus on defense."

[1915] Output: Displaying long-term advice

[1916] The above is a detailed description of the specific processing flow of this system and the operations performed at each step.

[1917] (Application example 2)

[1918] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1919] Existing shogi and go game systems struggle to provide appropriate advice in real time. Furthermore, they lack systems that can adapt feedback based on the user's emotional state, making it difficult to reduce user stress and fatigue. Furthermore, the lack of real-time advice and emotion recognition is also a challenge for factory robots and other automated systems.

[1920] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving information on moves played by the user; means for analyzing the received information and calculating the next best move and a situation evaluation; means for generating advice in a form that is easy for humans to understand based on the calculation results; means for providing the advice to the user; means for recognizing the emotional state of the operator and generating feedback according to that emotional state; and means for collecting work data and providing long-term improvement advice. This allows the user to receive useful advice in real time and receive feedback according to their emotional state. Furthermore, the ability to analyze past work data and game data and provide long-term improvement advice is expected to improve the user's technical skills and work efficiency.

[1921] "Information about the user's hand gestures" is a record of the specific operations and actions performed by the operator.

[1922] The "receiving means" is a hardware and software mechanism for acquiring the information about the user's hand gesture and transmitting it to other components in the system.

[1923] "Means of analysis" refers to the use of specific algorithms or models to calculate the next best move or situation assessment based on the information received.

[1924] "Best next move and situation evaluation" means the next move that is most suitable for the current situation in a game of shogi or go, and an evaluation of that situation.

[1925] The "means for generating advice" is a mechanism for creating specific advice in a form that is easy for humans to understand, based on the analysis results.

[1926] The "means for providing advice" refers to the hardware and software mechanisms for presenting the generated advice to the user.

[1927] "Emotional state of the operator" refers to the psychological state of the operator while working, and includes information such as stress and fatigue.

[1928] "Means for recognizing emotional states" is a general term for technologies and devices for detecting and analyzing an operator's emotional state from their voice, facial expressions, actions, etc.

[1929] A "feedback generation mechanism" is a mechanism that generates appropriate responses or advice based on the perceived emotional state.

[1930] "Work data" is a record of specific operations performed by operators or systems in the past and their results.

[1931] The "means of providing long-term improvement advice" is a system that uses collected work data to create and provide specific advice to improve operator skills and work efficiency over the long term.

[1932] This invention relates to a system that provides useful advice in real time when a user is performing a task, and also recognizes the user's emotional state and provides appropriate feedback. This system is mainly composed of four elements: a server, a terminal, a user, and an emotion engine.

[1933] System configuration

[1934] 1. Server:

[1935] The server is equipped with a shogi AI and a generative AI.

[1936] The server receives the user's operation information, analyzes it, and calculates the optimal work procedure.

[1937] The server also uses generative AI based on the analysis results to generate easy-to-understand advice.

[1938] The server also analyzes the user's emotional state and provides feedback based thereon.

[1939] 2. Terminal:

[1940] A terminal is a device (e.g., a PC or tablet) on which a user performs work.

[1941] The terminal collects various pieces of user operation information and transmits it to the server.

[1942] It also displays the advice and analysis results received from the server to the user.

[1943] 3. User:

[1944] A user is an operator who performs work using the system.

[1945] Users can receive real-time advice through their devices, improving work efficiency.

[1946] 4. Emotion Engine:

[1947] The emotion engine is a device and program that recognizes the user's emotional state from facial expressions, voice, actions, and the like.

[1948] The emotion engine collects and analyzes emotion data and sends it to the server.

[1949] Program processing (server, terminal, emotion engine)

[1950] 1. Data collection: While the user is working, the device collects operational information in real time and sends it to the server. The emotion engine also recognizes the user's facial expressions, voice, and movements, analyzes their emotional state, and sends the data to the server.

[1951] 2. Data analysis: Based on the received operation information, the server uses an analytical algorithm to evaluate the current work situation and calculate the optimal work procedure. It also analyzes emotional data to determine whether the user is feeling stressed or tired.

[1952] 3. Advice generation: The server uses generative AI based on the analysis results to generate easy-to-understand work advice. For example, specific advice such as, "As a next step, it is a good idea to connect part A to part B. This will improve assembly efficiency."

[1953] 4. Providing feedback: The server also generates appropriate feedback based on the emotion data, such as "You seem to be feeling tired. Please take a 5-minute break."

[1954] 5. Displaying Advice: The generated advice and feedback is sent to the terminal and displayed on the user's screen.

[1955] Specific examples

[1956] In a specific work scenario, the server advises a user who is assembling one part into another on the appropriate work procedure. Also, if the emotion engine detects the user's fatigue, the server will recommend taking a break.

[1957] Prompt Sentence Examples

[1958] Based on the emotion and task data above, provide advice on the best work procedures for the current task, and include suggestions for breaks if the operator is tired.

[1959] By implementing the present invention in this manner, it is possible to provide useful advice in real time and appropriate feedback according to the user's emotional state, thereby improving the user's work efficiency and safety.

[1960] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1961] Step 1:

[1962] Data collection

[1963] The device collects operational information about the work the user performs in real time. Specifically, it uses sensors and logging functions to obtain data on the procedures and actions the user takes on the device. This data is stored in the device's internal database and then sent to the server. The input is the user's operational information, and the output is the operational data sent to the server.

[1964] Step 2:

[1965] Emotional Data Collection

[1966] The emotion engine collects the user's facial expressions, voice, and movements in real time. The emotion engine is equipped with a camera, microphone, and sensors that collect data to recognize the user's emotional state. This data is sent to a server for analysis. The input is the user's facial expressions, voice, and movement data, and the output is the emotion data sent to the server.

[1967] Step 3:

[1968] Data analysis

[1969] The server uses an analysis algorithm to evaluate the current work situation and emotional state based on the received operation information and emotional data. A specific example of analysis is identifying the current work progress and problems from the user's operation data, and calculating the user's stress level and fatigue level from the emotional data. The input is operation information and emotional data, and the output is an analysis result: an evaluation of the work situation and an evaluation of the emotional state.

[1970] Step 4:

[1971] Advice Generation

[1972] The server uses generative AI based on the analysis results to generate work advice that is easy for the user to understand. For example, if work progress is delayed, it generates specific instructions such as "Connect part A to part B." If it determines that the user is tired, it generates feedback such as "Take a five-minute break." The input is the work situation assessment and emotional state assessment, and the output is the generated advice and feedback.

[1973] Step 5:

[1974] Providing advice

[1975] The server sends the generated advice and feedback to the terminal, which then displays it on the user's screen. For example, the terminal might display a message saying, "As a next step, connect component A to component B." The input is the generated advice and feedback, and the output is the instructions or suggestions displayed on the user's screen.

[1976] Step 6:

[1977] Work data accumulation

[1978] The server accumulates user operation information and emotion data collected daily and maintains a database of this data, allowing for long-term pattern and trend analysis. The input is the accumulated operation information and emotion data, and the output is an updated database.

[1979] Step 7:

[1980] Generate long-term improvement advice

[1981] The server analyzes the accumulated task and emotion data and generates long-term advice to improve the user's task performance. For example, specific advice such as "Based on past data, there is a more efficient procedure for assembling parts" may be generated. The input is data from the long-term database, and the output is long-term improvement advice.

[1982] The above is the specific flow of operations at each processing step. This series of processes allows users to receive useful advice and emotional feedback in real time, improving work efficiency and safety.

[1983] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1984] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1985] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1986] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1987] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1988] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1989] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1990] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1991] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1992] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1993] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1994] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1995] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1996] 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.

[1997] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1998] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1999] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2000] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2001] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2002] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2003] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2004] The following is further disclosed regarding the above embodiment.

[2005] (Claim 1)

[2006] means for receiving information about a user's hand;

[2007] means for analyzing the received information to calculate the next best move and a position evaluation;

[2008] A means for generating advice based on the calculation results in a form that is easy for humans to understand;

[2009] A system including means for providing said advice to a user.

[2010] (Claim 2)

[2011] 2. The system according to claim 1, wherein the advice generating means includes means for analyzing data of past games played by the user to detect patterns and habits of the user's moves.

[2012] (Claim 3)

[2013] 2. The system of claim 1, wherein the advice generating means includes means for generating long-term advice based on detected user patterns and habits.

[2014] "Example 1"

[2015] (Claim 1)

[2016] means for receiving information about a user's hand;

[2017] means for analyzing the received information to calculate the next best move and a position evaluation;

[2018] A means for generating advice based on the calculation results in a form that is easy for humans to understand;

[2019] means for providing said advice to a user;

[2020] A means for analyzing the user's past game data;

[2021] A means of generating long-term advice based on the analysis results;

[2022] means for providing the generated advice to a user;

[2023] A system including:

[2024] (Claim 2)

[2025] 2. The system according to claim 1, wherein the advice generating means includes means for generating advice by inputting the user's past data as a prompt sentence using a generative AI model.

[2026] (Claim 3)

[2027] 2. The system according to claim 1, wherein the advice providing means includes means for providing advice in real time during a game.

[2028] "Application Example 1"

[2029] (Claim 1)

[2030] means for receiving information about a user's hand;

[2031] means for analyzing the received information to calculate the next best move and a position evaluation;

[2032] A means for generating advice based on the calculation results in a form that is easy for humans to understand;

[2033] means for providing said advice to a user;

[2034] means for receiving and analyzing robot work data;

[2035] A means for generating optimal work procedures based on the analysis results;

[2036] A system including a means for analyzing past work data and generating advice for improving long-term work efficiency.

[2037] (Claim 2)

[2038] 2. The system according to claim 1, wherein the advice generating means includes means for analyzing the user's past game data to detect the user's move patterns and habits, and means for detecting the robot's work patterns and habits.

[2039] (Claim 3)

[2040] 2. The system of claim 1, wherein the advice generating means includes means for generating long-term advice based on detected user patterns and habits and robot patterns and habits.

[2041] "Example 2: Combining Emotion Engines"

[2042] (Claim 1)

[2043] means for receiving information about a user's hand;

[2044] means for analyzing the received information to calculate the next best move and a position evaluation;

[2045] a means for generating advice in a form that is easy for humans to understand based on the calculation results and the user's emotional state;

[2046] means for providing said advice and emotional feedback to a user;

[2047] A system including:

[2048] (Claim 2)

[2049] 2. The system according to claim 1, wherein the advice generating means includes means for analyzing data of past games played by the user to detect patterns and habits of the user's moves.

[2050] (Claim 3)

[2051] 2. The system of claim 1, wherein the advice generating means includes means for generating long-term advice based on detected user patterns and habits.

[2052] (Claim 4)

[2053] means for collecting emotion data from a user's voice, facial expression, and input actions;

[2054] means for analyzing the collected emotion data to recognize the user's emotional state;

[2055] 3. The system of claim 1, further comprising means for providing the recognized emotional state to the advice generating means.

[2056] "Application example 2 when combining emotion engines"

[2057] (Claim 1)

[2058] means for receiving information about a user's hand;

[2059] means for analyzing the received information to calculate the next best move and a position evaluation;

[2060] A means for generating advice based on the calculation results in a form that is easy for humans to understand;

[2061] means for providing said advice to a user;

[2062] means for recognizing an emotional state of an operator and means for generating feedback in response to the emotional state;

[2063] A system that includes a means of collecting operational data and providing long-term improvement advice.

[2064] (Claim 2)

[2065] 2. The system according to claim 1, wherein the advice generating means includes means for analyzing data of past games played by the user to detect patterns and habits of the user's moves.

[2066] (Claim 3)

[2067] 2. The system of claim 1, wherein the advice generating means includes means for generating long-term advice based on detected patterns, habits, and emotional states of the user. [Explanation of symbols]

[2068] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving information about a user's hand; means for analyzing the received information to calculate the next best move and a position evaluation; A means for generating advice based on the calculation results in a form that is easy for humans to understand; A system including means for providing said advice to a user.

2. 2. The system according to claim 1, wherein the advice generating means includes means for analyzing data on past games played by the user to detect patterns and habits of the user's moves.

3. 2. The system of claim 1, wherein the advice generating means includes means for generating long-term advice based on detected user patterns and habits.

Images