System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving play data from a user; means for storing the received play data in a database; AI means for generating a signature play pattern based on the stored play data; means for storing the generated signature play pattern in the database; and means for delivering the signature play pattern to a terminal.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 team sports, it is extremely important for players to not only improve their individual skills, but also to strengthen their coordination with other positions. However, traditional methods are limited to when the entire team is present, making it difficult for individuals to check the coordination of sign plays. Opportunities to discover new sign plays are also limited. This makes it difficult to practice plays efficiently, limiting the scope for skill improvement. [Means for solving the problem]

[0005] This invention is a system equipped with AI means that receives and stores play data from users and generates sign play patterns based on that data. The generated sign play patterns are stored in a database and distributed to devices. In addition, sign play patterns are displayed on smart glasses, allowing users to practice independently. Furthermore, feedback from users is received and stored, and sign play patterns are modified and generated based on that feedback, leading to the discovery of new play patterns and strengthening collaboration. With these means, users can efficiently check and practice sign plays individually, and are expected to further improve their skills.

[0006] "User" refers to any individual or entity that uses the System.

[0007] "Play data" refers to data including information such as the user's position and skills in sports.

[0008] "Database" means a system for storing and managing received and generated data.

[0009] A "sign play pattern" refers to a specific coordinated action or tactical play pattern in team sports.

[0010] "AI means" refers to artificial intelligence algorithms and systems that generate new sign play patterns based on play data.

[0011] "Terminal" refers to a device such as smart glasses used by a user.

[0012] "Smart glasses" refers to a wearable device that can visually display sign play patterns.

[0013] "Feedback" refers to the evaluation or comments provided by a user after practicing a sign play pattern.

[0014] "Modification and generation" refers to adjusting existing sign play patterns or creating new patterns. [Brief explanation of the drawings]

[0015] [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 illustrating 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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention is a system for improving individual and team coordination skills in team sports. This system mainly consists of a server, a device worn by the user (smart glasses), and a generation AI.

[0037] User:

[0038] First, a user inputs their playing data (e.g., position, skill set, etc.) through the system interface. This data is input using a device such as a smartphone or tablet and sent to the server.

[0039] server:

[0040] The server stores the play data received from users in a database. The stored data is organized for each individual user. The server then issues instructions to the generation AI based on the stored play data to generate new sign play patterns.

[0041] The generation AI receives the user's play data and uses a specific algorithm to generate optimal sign play patterns. This AI is designed to evolve based on past data and feedback, providing highly accurate patterns tailored to the user's needs. The generated sign play patterns are sent back to the server and stored in a database.

[0042] Device:

[0043] The device, specifically the smart glasses, accesses the server to acquire the generated sign play patterns, which are then displayed to the user in real time, allowing the user to practice sign plays privately by following the displayed instructions.

[0044] Feedback function:

[0045] After the user practices based on the sign play patterns, they provide feedback on their performance to the system, including specific evaluations and comments. This feedback data is also sent to the server and stored in the database.

[0046] The server analyzes this feedback data and provides it to the generation AI, which then adjusts and updates the sign play patterns based on the feedback, generating more effective patterns. This cyclical process allows users to continually improve their skills and contributes to the discovery of new teamwork.

[0047] Examples:

[0048] For example, let's say the user is in a forward position. The user inputs skill data such as dribbling and speed and sends it to the server. The server receives this data and instructs the generation AI to generate new sign play patterns. The generation AI generates patterns such as effective movements in front of the goal and how to receive a pass, and sends them back to the server.

[0049] The user wearing the smart glasses checks the generated patterns and follows the instructions to practice the movements. The results of the practice are then input into the system as feedback to help improve the sign play patterns.

[0050] In this way, by using this system, users can not only improve their individual skills, but also strengthen their collaborative skills as part of a team.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] Users use devices such as smartphones and tablets to input their playing data (position, skill set, etc.).

[0054] Step 2:

[0055] The user transmits the input play data to the server.

[0056] Step 3:

[0057] The server stores the play data received from the user in a database.

[0058] Step 4:

[0059] The server instructs the generation AI to generate new sign play patterns based on the saved play data.

[0060] Step 5:

[0061] The generation AI generates optimal sign play patterns based on the play data received from the server.

[0062] Step 6:

[0063] The generated sign play pattern is sent back from the generation AI to the server, which stores it in a database.

[0064] Step 7:

[0065] The user starts up the device (smart glasses) and requests acquisition of a signature play pattern.

[0066] Step 8:

[0067] The server distributes the saved signature patterns to the device (smart glasses).

[0068] Step 9:

[0069] The device (smart glasses) visually displays the sign play pattern to the user.

[0070] Step 10:

[0071] Users practice sign plays by following the instructions displayed on the smart glasses.

[0072] Step 11:

[0073] After practicing, the user provides feedback on their performance to the system.

[0074] Step 12:

[0075] The server receives the feedback from the user and stores it in a database.

[0076] Step 13:

[0077] The server provides the stored feedback data to the generation AI.

[0078] Step 14:

[0079] The generative AI adjusts and updates sign play patterns based on feedback, generating more effective patterns.

[0080] Example 1

[0081] 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."

[0082] In traditional team sports, improving individual and team coordination skills has relied primarily on individual experience and coaching, making efficient training difficult. It has also been difficult to provide individualized training methods that take into account each player's characteristics and skills, and there has been a lack of adaptive training programs based on feedback. Furthermore, it has been impossible to provide real-time training instructions.

[0083] 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.

[0084] In this invention, the server includes means for receiving play data from users, means for saving the received play data in a database, a generation AI model means for generating new sign play patterns based on the saved play data, means for saving the generated sign play patterns in a database, means for distributing the sign play patterns to the terminal, means for receiving feedback from users and saving it in a database, and a generation AI model means for adjusting and updating the sign play patterns based on the feedback. This makes it possible to generate optimal sign play patterns based on the characteristics of each player and provide instructions in real time. Furthermore, by continuously improving the sign play patterns based on the feedback, it is possible to efficiently improve skills and strengthen team cooperation.

[0085] "Means for receiving play data from a user" refers to a device or software that allows the server to receive information such as the position and skill set entered by the user.

[0086] "Means for storing received play data in a database" refers to a device or software that has the function of storing information received from users in a database for systematic management by the server.

[0087] "Generative AI model means" refers to an artificial intelligence system that generates new sign play patterns using a specific algorithm based on given data.

[0088] "Means for delivering sign play patterns to a terminal" refers to a device or software with network communication capabilities for transmitting the generated sign play patterns to a terminal, specifically to smart glasses, etc.

[0089] "Means for receiving feedback from users" refers to a device or software that allows the server to receive evaluations and comments entered by users after practicing.

[0090] "Means for storing feedback in a database" refers to a device or software that has the function of storing received feedback in a database for systematic management.

[0091] "Generative AI model means for adjusting and updating sign play patterns" refers to an artificial intelligence system that adaptively changes existing sign play patterns based on received feedback and updates them to more effective patterns.

[0092] "Smart glasses" refers to a wearable device that users can wear to obtain visual information in real time.

[0093] "Database" refers to a data management system for storing, managing, and searching user play data and feedback data.

[0094] This invention is a system for improving individual and team coordination skills in team sports. The system mainly consists of a server, a device worn by the user (smart glasses), and a generative AI model.

[0095] User

[0096] First, a user accesses the system interface using a device such as a smartphone or tablet. The user inputs their playing data (e.g., position, skill set, etc.). This data might be, for example, "I'm a forward and I'm good at dribbling." The input data is then sent to the server.

[0097] server

[0098] The server receives play data sent by users. The received data is stored in a database and organized by user. The server then instructs the generative AI model to generate new sign play patterns based on the stored play data. The generative AI model uses a specific algorithm to generate optimal sign play patterns. This AI is designed to evolve based on past data and feedback.

[0099] The generated sign play patterns are sent back to the server and stored in the database. For example, the instructions to the generative AI model might include a prompt like this: "User's position: forward. Skill set: dribbling, speed. Based on this, please generate the optimal sign play pattern."

[0100] Terminal

[0101] The device, specifically the smart glasses, periodically accesses the server to obtain the latest sign play patterns. These patterns are displayed to the user in real time. The user can then follow the instructions displayed on the smart glasses to practice sign plays individually. For example, the smart glasses may display instructions such as "break through the right side and shoot in front of the goal."

[0102] Feedback function

[0103] After the user practices using the sign play pattern, they provide feedback on their performance to the system. The feedback includes specific evaluations and comments, such as, "This dribbling pattern was performed smoothly." This feedback data is also sent to the server and stored in a database. The server analyzes the feedback data and provides the results to the generative AI model. The generative AI model adjusts and updates the sign play pattern based on the feedback, generating a more effective pattern. This cyclical process allows users to continuously improve their skills and also contributes to the discovery of new teamwork plays.

[0104] Specific examples

[0105] For example, let's say the user is in a forward position. The user inputs skill data such as "dribbling and speed" and sends it to the server. The server receives this data and instructs the generative AI model to generate new sign play patterns. The generative AI model generates patterns such as "effective movements in front of the goal" and "how to receive a pass" and sends them back to the server.

[0106] Wearing the smart glasses, the user checks the generated pattern and practices the movement by following the instruction, "Dribble to the right, then cut back to the left." The results of the practice are then input into the system as feedback, such as "Today's sign play was 70 points. The accuracy of the shot was low," which is used to improve the sign play pattern. In this way, by using this system, users can not only improve their individual skills, but also strengthen their teamwork skills as part of a team.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1:

[0109] Input: Users access the system interface using a smartphone or tablet.

[0110] Process: User inputs their position and skill set (e.g. forward, dribbling, speed).

[0111] Output: The input data is sent to the server.

[0112] Specific operations: The user enters information such as "forward," "dribble," and "speed" into the form displayed on the smartphone screen and presses the submit button.

[0113] Step 2:

[0114] Input: The server receives play data sent by the user.

[0115] Processing: The received play data is stored in a database. The stored data is organized by user.

[0116] Output: Play data is saved in the database.

[0117] Specific operation: To store data from different users separately, the server assigns each user a unique ID and stores the data associated with it.

[0118] Step 3:

[0119] Input: The server instructs the generation AI model to generate new sign play patterns based on saved play data.

[0120] Processing: The instructions include a prompt statement that includes the user's position and skill set, and is passed to the generative AI model (e.g., "Generate the optimal sign play pattern based on forward, dribbling, and speed").

[0121] Output: Instructions to generate new sign play patterns are sent to the generative AI model.

[0122] Specific operation: The server generates a prompt sentence and provides it to the generative AI model.

[0123] Step 4:

[0124] Input: The generative AI model receives a prompt.

[0125] Processing: Generates sign-play patterns using an internal algorithm. The generative AI model takes into account past data and feedback to generate detailed sign-play patterns, such as "break through on the right side and shoot."

[0126] Output: The generated signature pattern is sent back to the server.

[0127] Specific operation: The generative AI model generates new sign play patterns based on the prompt sentence and sends the results to the server.

[0128] Step 5:

[0129] Input: The generated signature pattern arrives at the server.

[0130] Processing: The server stores the generated signature play pattern in a database.

[0131] Output: Sign play patterns are stored in a database.

[0132] Specific operation: The server checks the returned data, organizes it for each user, and stores it.

[0133] Step 6:

[0134] Input: The device (smart glasses) periodically accesses the server.

[0135] Processing: Get the latest sign play pattern.

[0136] Output: The acquired signature pattern is displayed on the smart glasses.

[0137] Specific operation: The smart glasses download the latest patterns from the server and display instructions to the user in real time, such as "break through the right side and shoot in front of the goal."

[0138] Step 7:

[0139] Input: The user practices by following the sign play patterns displayed on the smart glasses.

[0140] Processing: Performing an action according to instructions.

[0141] Output: User practice results.

[0142] Specific actions: The user follows the displayed instructions to perform the actions on the field and actually practice the play.

[0143] Step 8:

[0144] Input: After practicing, the user provides feedback to the system.

[0145] Processing: Feedback includes specific evaluations and comments (e.g., "That dribble pattern was smooth").

[0146] Output: The feedback data is sent to the server.

[0147] Specific operation: The user inputs feedback from their smartphone and sends it to the server.

[0148] Step 9:

[0149] Input: The server receives feedback from the user.

[0150] Processing: The received feedback is stored in a database and analyzed.

[0151] Output: Feedback data is stored in a database.

[0152] Specific operation: The server analyzes the feedback data and accumulates ratings for each user.

[0153] Step 10:

[0154] Input: The server provides the analysis results to the generative AI model.

[0155] Processing: Adjust and update sign play patterns based on feedback.

[0156] Output: The adjusted and updated signature pattern is generated.

[0157] Specific operation: The generative AI model generates new patterns based on the feedback and provides them to the server.

[0158] Through this series of steps, the system can provide optimal sign play patterns based on the user's characteristics and feedback, helping them improve their skills and strengthen teamwork.

[0159] (Application example 1)

[0160] 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."

[0161] Traditional training methods for improving staff collaboration skills in brick-and-mortar stores often require manual feedback and time-consuming training, making them inefficient. It's also difficult to provide optimal training methods tailored to individual staff members' skill levels and roles, making it challenging to improve teamwork. Furthermore, there's no system for reflecting training results in real time, making continuous skill improvement difficult.

[0162] 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.

[0163] In this invention, the server includes means for receiving play data from users, means for saving the received play data in a database, AI means for generating movement patterns based on the saved play data, means for saving the generated movement patterns in the database, and means for delivering the movement patterns to terminals. This makes it possible to generate optimal movement patterns based on the skill sets and feedback of individual staff members and provide them to staff members in real time.

[0164] "Play data" is information about a user's role and skill set that the user inputs into the system.

[0165] The "database" is a system for storing and managing received play data, generated movement patterns, and feedback data.

[0166] "Movement patterns" are optimal work procedures and movement instructions generated by AI means based on the user's role and skills.

[0167] "AI means" refers to a system that uses artificial intelligence technology to generate optimal movement patterns based on received play data and feedback data.

[0168] A "terminal" is a device that can display movement patterns or smart glasses worn by the user.

[0169] "Feedback" is information about performance and areas for improvement that a user provides to the system after performing a task based on their behavioral patterns.

[0170] The "distribution means" is a system for transferring the generated motion patterns from the server to the user's terminal.

[0171] server

[0172] The server receives play data entered by the user using a smartphone or tablet. The play data is information about the user's role and skill set, and the server stores this data in a database. The stored play data is analyzed by AI means to generate optimal movement patterns. A generative AI model (e.g., OpenAI (registered trademark) GPT-4 (registered trademark)) is used. The movement patterns generated in this process are again stored in the database.

[0173] Terminal

[0174] The devices are primarily smart glasses, which access a server to acquire the generated movement patterns. The smart glasses then display the acquired movement patterns to the user in real time, allowing the user to visually check them as they work. This display function allows each staff member to practice the optimal movements for their role.

[0175] User

[0176] The user performs their work by following the movement patterns delivered from the server, checking their movements in real time through smart glasses. After completing the work, the user enters feedback into the system. Feedback is information about performance and areas for improvement provided by the user after performing a task based on the movement patterns. This feedback data is also sent to the server and stored in a database. The server analyzes this feedback data and provides it to the generation AI. The generation AI adjusts and updates the movement patterns based on the feedback, generating more effective patterns. This cyclical process allows the user to continuously improve their skills.

[0177] Specific examples

[0178] For example, let's say a staff member needs to learn how to display a new product. The staff member wears smart glasses and works while viewing the optimal display pattern generated by the AI ​​in real time. The staff member then inputs the results of their work into the system as feedback. Based on this feedback, the AI ​​can refine the pattern for the next time.

[0179] Prompt Sentence Examples

[0180] Below is an example of a prompt to send to the generated AI.

[0181] text

[0182] Please generate movement patterns for staff to optimally display new products. The following information is available as staff skill data.

[0183] Role: Product display

[0184] Skills: Basic product placement and inventory management

[0185] Additional Information: Display space in stores is limited.

[0186] The generated patterns should include how to position products, proper flow of traffic, and when to use necessary tools.

[0187] In this way, the system of the present invention provides an effective training method for improving staff collaboration skills in brick-and-mortar stores and increasing work efficiency.

[0188] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0189] Step 1:

[0190] The server receives "play data" entered by the user using a smartphone or tablet. The play data includes information about the user's role and skill set. The entered play data is saved in a database by the server. This allows the user's skill set to be accumulated in the database.

[0191] Step 2:

[0192] The server generates "movement patterns" by sending prompts to the generative AI based on the play data stored in the database. The generative AI model (e.g., OpenAI GPT-4) creates optimal movement patterns based on past data and predefined algorithms. These movement patterns are specific work procedures that correspond to the user's role and skills. The generated movement patterns are then stored back in the database by the server.

[0193] Step 3:

[0194] The device, specifically the smart glasses, accesses the server to acquire the generated movement patterns. The smart glasses display the movement patterns to the user in real time, allowing the user to visually confirm the patterns as they work. This allows the user to perform the operations efficiently by following the instructions.

[0195] Step 4:

[0196] The user performs a task according to the action pattern and inputs the results into the system as feedback. The feedback includes information about task performance and areas for improvement. The feedback data is sent to the server and stored in a database. This allows the user's actual work results to be recorded in the system.

[0197] Step 5:

[0198] The server analyzes the feedback data and sends prompts to the AI ​​generator based on this data. The AI ​​generator takes the feedback into account and adjusts and updates the next movement pattern to generate a more effective and accurate movement pattern, thereby achieving continuous skill improvement.

[0199] 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.

[0200] This invention is a system for improving the coordination skills of individuals and teams in team sports, and in particular, by combining an emotion engine, it generates and adjusts play patterns taking into account the user's emotional state. This system mainly consists of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[0201] User:

[0202] Users input their playing data (position, skill set, etc.) using a device such as a smartphone or tablet. This data is sent to the server via the device. By wearing the smart glasses, the user can practice based on the displayed sign play patterns.

[0203] server:

[0204] The server stores the play data received from the user in a database and provides it to the generation AI. The generation AI generates sign play patterns based on this data and sends the generated patterns back to the server. The server then stores the generated sign play patterns in a database and distributes them to devices as needed.

[0205] Emotion Engine:

[0206] The emotion engine recognizes the user's emotional state in real time by analyzing facial expressions, voice data, etc. The emotion data recognized by the emotion engine is sent to the server and stored in a database.

[0207] Generation AI:

[0208] The AI ​​combines play data and emotional data to generate signature play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will ease that tension, and if the user is concentrating, it will provide a more difficult pattern. The generated patterns are then sent back to the server.

[0209] Device:

[0210] When a user activates the smart glasses, a request is made to acquire sign play patterns from the server. The server then transmits the generated patterns to the device, and the smart glasses visually display them to the user. The emotion engine continues to monitor the user's emotional state during this process, adaptively changing the content of the sign play patterns as needed.

[0211] Feedback function:

[0212] After the user practices the sign play patterns, they provide feedback to the system about their performance and emotional state, including specific ratings and comments, which are also sent to the server and stored in the database.

[0213] The server analyzes this feedback and emotional data and provides it to the generation AI. The generation AI then adjusts and updates the sign play patterns based on the feedback and emotional data, generating more effective patterns. This cyclical process not only allows users to improve their individual skills, but also enables them to play at a more advanced level that takes into account their emotional state and teamwork skills.

[0214] Examples:

[0215] For example, let's say the user is in a forward position. The user inputs skill data such as dribbling and speed and sends it to the server. The server receives and stores this data, and instructs the generation AI to generate new sign play patterns. The generation AI also takes into account the user's current emotional state and generates patterns such as effective movements in front of the goal and how to receive a pass.

[0216] Wearing the smart glasses, the user views the generated patterns and practices the movements according to the displayed instructions. The emotion engine monitors the user's emotional state during practice and adjusts the instructions as needed. After practice, the user provides feedback on their performance and emotional state to the system, which further refines and updates the sign play patterns.

[0217] In this way, by using this system, users can efficiently check and practice sign plays while taking their emotional state into consideration, which is expected to lead to greater skill improvement.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] Users use devices such as smartphones and tablets to input their playing data (position, skill set, etc.).

[0221] Step 2:

[0222] The user transmits the input play data to the server.

[0223] Step 3:

[0224] The server stores the play data received from the user in a database.

[0225] Step 4:

[0226] The server instructs the generation AI to generate new sign play patterns based on the saved play data.

[0227] Step 5:

[0228] The generation AI generates optimal sign play patterns based on the play data received from the server.

[0229] Step 6:

[0230] The generated sign play pattern is sent back from the generation AI to the server, which stores it in a database.

[0231] Step 7:

[0232] The user starts up the device (smart glasses) and requests acquisition of a signature play pattern.

[0233] Step 8:

[0234] The server distributes the saved signature patterns to the device (smart glasses).

[0235] Step 9:

[0236] The device (smart glasses) visually displays the sign play pattern to the user.

[0237] Step 10:

[0238] The emotion engine analyzes the user's facial expressions and voice data in real time to recognize their emotional state, and the recognized emotional data is sent to the server.

[0239] Step 11:

[0240] The server stores the emotion data received from the emotion engine in a database.

[0241] Step 12:

[0242] The AI ​​optimizes sign play patterns based on the user's play data and emotional data. For example, if the user is nervous, it will provide a relaxing pattern, and if the user is concentrating, it will provide a more difficult pattern.

[0243] Step 13:

[0244] Users practice sign plays by following the instructions displayed on the smart glasses.

[0245] Step 14:

[0246] After practicing, the user provides feedback to the system about their performance and emotional state.

[0247] Step 15:

[0248] The server receives the feedback from the user and stores it in a database.

[0249] Step 16:

[0250] The server provides the stored feedback data and emotional data to the generation AI, instructing it to adjust and improve its sign play patterns.

[0251] Step 17:

[0252] Generative AI adjusts and updates sign-play patterns based on feedback and emotional data to generate more effective patterns.

[0253] Step 18:

[0254] The server re-distributes the updated sign play pattern to the device (smart glasses), allowing the user to practice again.

[0255] Example 2

[0256] 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."

[0257] Conventional training systems for team sports provide playing patterns without considering the user's emotional state, resulting in performance differences depending on the individual's physical condition and psychological state. Furthermore, they are unable to provide real-time feedback and reflect emotional data, making it difficult to effectively support the improvement of teamwork and individual skills. This reduces the efficiency of practice and prevents sufficient support for user growth.

[0258] 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.

[0259] In this invention, the server includes a means for receiving play data from users, a means for storing the received play data in a database, and an AI means for generating sign play patterns based on the play data and emotional data received in real time. This allows for the generation of play patterns that take the user's emotional state into account, providing practice tailored to each individual's condition. Furthermore, by modifying and generating sign play patterns based on feedback and emotional data, it is possible to effectively support the user's growth.

[0260] The "means for receiving play data from the user" is a communication interface for transmitting information about practice such as sports positions and skill sets entered by the user to the server.

[0261] The "means for storing received play data in a database" is a mechanism by which the server records play data sent from users in a storage device.

[0262] The "AI means for generating sign play patterns based on play data and emotional data received in real time" is an artificial intelligence engine that analyzes the user's practice data and emotional data and generates appropriate play patterns based on the results.

[0263] The "means for saving the generated sign play patterns and emotion data in a database" is a system for recording the generated sign play patterns and emotion data recognized by the emotion engine in a storage device.

[0264] The "means for providing the generation AI using play data and emotional data" is a communication interface that allows the server to transmit the stored play data and emotional data to the generation AI for analysis and pattern generation.

[0265] The "means for delivering the sign play pattern to the terminal" is a communication mechanism that allows the server to transmit the generated sign play pattern to the user's smart glasses or other display terminal.

[0266] "Displaying sign play patterns on smart glasses" refers to a function that displays the sign play patterns received by smart glasses from the server in a form that can be visually confirmed by the user.

[0267] The "means for receiving feedback from the user" is a communication interface for transmitting feedback information such as evaluations and emotions input by the user after practice to the server.

[0268] "AI means for storing received feedback in a database and modifying and generating sign play patterns based on the feedback and emotional data" refers to an artificial intelligence engine that records feedback data and emotional data in a storage device and generates more effective sign play patterns based on that data.

[0269] The "system" refers to a comprehensive mechanism that includes a server, user terminals (such as smart glasses), generative AI, emotion engine, and communication means for sending and receiving data between them.

[0270] This invention is a system for improving individual and team coordination skills in team sports, and in particular generates and adjusts play patterns taking into account the user's emotional state. This system is primarily composed of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[0271] server

[0272] The server stores the play data (position, skill set, etc.) received from the user in a database and provides it to the generation AI. The hardware used is server equipment with high-performance processing capabilities (brand names are not specified, but this includes commonly used cloud service servers).

[0273] The server issues instructions to the generation AI based on the play data, stores the generated sign play patterns in a database, and distributes them to devices as needed.

[0274] Terminal

[0275] Users use a smartphone or tablet to input their own play data, which is then sent to a server via the device. By wearing smart glasses, they can visually confirm the sign play patterns and practice based on them. For example, a user can use a smartphone app to input their position as "forward" and their skill set as "dribbling, speed," and then send the data. This data is then saved on the server.

[0276] Emotion Engine

[0277] The emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state in real time. Specifically, it is expected to use a facial recognition camera and voice analysis software. The emotion engine operates while the user is using the smart glasses, and transmits their emotional state during practice to the server in real time.

[0278] Generation AI

[0279] The generation AI combines play data and emotional data to generate sign play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will ease that tension, and conversely, if the user is concentrating, it will provide a more difficult pattern. The generated patterns are then sent back to the server. The AI ​​model used utilizes a common deep learning algorithm.

[0280] Specific examples

[0281] For example, consider the case where a user inputs "data on dribbling and speed for a forward position" and sends it to the server. The server receives and stores the play data, and then instructs the generation AI to generate a new sign play pattern based on that data.

[0282] The generative AI generates "patterns for effective movements in front of the goal and how to receive a pass," taking into account the user's current emotional state. As the user wears the smart glasses and practices movements based on the displayed sign play patterns, the emotion engine monitors the user's emotional state and adaptively changes the instructions as necessary.

[0283] Prompt Sentence Examples

[0284] Here are some example prompts to input to the AI ​​generator:

[0285] "The user's position is forward, and their skill set is focused on dribbling and speed. Their current emotional state is tense. Please generate a pattern of how they will receive a pass in front of the goal, taking this state into account."

[0286] "The user is a midfielder with good defensive skills. He is in a focused state. Please generate an appropriate passing pattern for this situation."

[0287] In this way, by using this system, users can efficiently understand practice patterns while taking into account their emotional state and achieve advanced play.

[0288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0289] Step 1:

[0290] The user uses a smartphone or tablet to input their playing data. Specifically, the user inputs their position (e.g., forward) and skill set (e.g., dribbling, speed) through the application and presses the send button. This action sends the input data from the device to the server.

[0291] Input: Position and Skillset Data

[0292] Output: Play data sent to the server

[0293] Step 2:

[0294] The server stores the play data received from the user in a database. Specifically, the database management system converts the received data into an appropriate format and inserts it into the corresponding table in the database. Through this process, the user's play data is recorded in a form that can be stored for a long period of time.

[0295] Input: User's play data

[0296] Output: Play data stored in the database

[0297] Step 3:

[0298] The server provides the saved play data to the AI ​​generator. Specifically, the server acquires the play data and creates a prompt statement requesting the AI ​​generator to generate a new sign play pattern. The prompt statement includes the user's play data and their emotional state.

[0299] Input: Play data retrieved from the database

[0300] Output: The prompt sent to the generation AI

[0301] Step 4:

[0302] The generation AI generates sign play patterns based on play data and emotional data. Specifically, the generation AI analyzes the input data and generates play patterns that take the user's emotional state into account. For example, if the user is nervous, a pattern to relieve tension will be generated.

[0303] Input: Prompt sentence containing play data and emotion data

[0304] Output: Generated sign play pattern

[0305] Step 5:

[0306] The server stores the generated signature play patterns in a database. Specifically, the generated patterns are received by the server and stored in a corresponding table in the database. This allows the user's signature play patterns to be recorded in a form that can be referenced later.

[0307] Input: Sign play pattern returned from the generation AI

[0308] Output: Sign play patterns stored in the database

[0309] Step 6:

[0310] The user starts up the smart glasses and requests the acquisition of a sign play pattern. Specifically, the user opens the smart glasses application and sends a request to the server to acquire the sign play pattern. This request includes the user ID and session information.

[0311] Input: A get request containing the user ID and session information

[0312] Output: Request data sent to the server

[0313] Step 7:

[0314] The server distributes the generated sign play patterns to the device. Specifically, the server retrieves the corresponding sign play patterns from the database and sends them to the user's smart glasses. This process allows the user to obtain the necessary practice data in real time.

[0315] Input: Retrieval request, signature pattern in database

[0316] Output: Sign play pattern delivered to the terminal

[0317] Step 8:

[0318] The emotion engine recognizes and records the user's emotional state. Specifically, the camera and microphone built into the smart glasses capture the user's facial expressions and voice and send them to the emotion engine. The emotion engine analyzes this and sends the emotional data to the server.

[0319] Input: User's facial expression data, voice data

[0320] Output: Emotion data sent to the server

[0321] Step 9:

[0322] The user practices based on sign play patterns. Specifically, they practice movements and techniques by following instructions displayed on the smart glasses. The user's emotional state is continuously monitored by the emotion engine, and feedback is received from the server as needed.

[0323] Input: Sign play pattern displayed on smart glasses

[0324] Output: The exercise performed

[0325] Step 10:

[0326] Users provide feedback on their performance and emotional state to the system. Specifically, after practice, they use a smartphone or tablet to input their evaluations and comments about the effectiveness of the practice and their own emotional state, and send them to the server.

[0327] Input: Feedback information entered by the user

[0328] Output: Feedback data sent to the server

[0329] Step 11:

[0330] The server provides feedback to the generation AI to generate new patterns. Specifically, the server analyzes the saved feedback data and provides it to the generation AI, instructing it to generate new sign play patterns. The generation AI then uses this data to generate more effective play patterns.

[0331] Input: Feedback data, existing emotion data

[0332] Output: The new sign play pattern generated

[0333] By repeating the above steps, the optimal practice is provided according to the user's playing style and emotional state.

[0334] (Application example 2)

[0335] 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."

[0336] In conventional team sports practice, it is difficult to provide appropriate feedback and guidance to improve individual and team coordination skills. Furthermore, there is no system that provides optimal training methods based on the user's emotional state, making it difficult to maximize the user's motivation and concentration. Furthermore, in virtual stores, it is necessary to provide an optimal experience while taking into account the emotional states of both store staff and customers, but current systems have difficulty achieving this.

[0337] 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 play data from the user, means for saving the received play data in a database, AI means for generating sign play patterns based on the saved play data and the user's emotional data, means for saving the generated sign play patterns in a database, means for distributing the sign play patterns to the terminal, means for monitoring the emotional data of the user and others in real time, and means for adaptively adjusting the sign play patterns based on the monitored emotional data. This makes it possible to provide appropriate and effective feedback and guidance taking into account the user's emotional state. Furthermore, in virtual stores, customer satisfaction can be improved by proposing and adjusting optimal customer service methods in real time based on the emotional states of store staff and customers.

[0338] "Users" refers to people who use the system to provide play data and emotional data.

[0339] "Play data" refers to data such as sports positions and skill sets entered by the user.

[0340] "Database" refers to a digital storage system for storing play data, emotional data, and generated sign play patterns.

[0341] "Emotion data" refers to information about the emotional state obtained by analyzing facial expressions and voice data of the user and other people.

[0342] A "signature play pattern" refers to a pattern that is generated based on the user's play data and emotion data and that instructs a specific play or movement.

[0343] "AI means" refers to technology that uses artificial intelligence to analyze data and generate and modify sign play patterns.

[0344] "Terminal" refers to a device such as smart glasses worn by a user, which is used to display sign play patterns.

[0345] "Monitoring means" refers to technology that observes and collects emotional data of users and others in real time.

[0346] "Adaptive adjustment means" refers to technology that changes sign-play patterns in real time based on monitored emotional data.

[0347] "Feedback" refers to ratings and comments about performance and emotional state provided by users and others after using the system.

[0348] This invention is a system for improving the cooperative skills of individuals and teams, and in particular, by combining an emotion engine, it generates and adjusts play patterns taking into account the user's emotional state. This system mainly consists of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[0349] User operations

[0350] Users use devices such as smartphones or tablets to input their playing data (position, skill set, etc.). This data is sent to a server via the terminal. By wearing the smart glasses, players can practice based on the displayed sign play patterns. An emotion engine is built into the smart glasses and recognizes the user's emotional state by analyzing their facial expressions and voice data in real time.

[0351] Server Processing

[0352] The server stores the play data received from the user in a database and provides it to the generation AI. The generation AI generates sign play patterns based on this data and sends the generated patterns back to the server. The server then stores the generated sign play patterns in a database and distributes them to devices as needed.

[0353] Emotion Engine Functions

[0354] The emotion engine analyzes the user's facial expressions, voice data, and other data to recognize their emotional state in real time. The recognized emotional data is sent to a server and stored in a database. The generation AI combines play data and emotional data to generate sign play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will relieve that tension, and if the user is concentrating, it will provide a more difficult pattern.

[0355] The role of smart glasses

[0356] When a user activates the smart glasses, a request is made to acquire sign play patterns from the server. The server then transmits the generated patterns to the device, and the smart glasses visually display them to the user. The emotion engine continues to monitor the user's emotional state during this process, adaptively changing the content of the sign play patterns as needed.

[0357] Feedback function

[0358] After a user practices a sign play pattern, they provide feedback to the system about their performance and emotional state. The feedback includes specific evaluations and comments, and is sent to the server and stored in a database. The server analyzes this feedback data and emotional data and provides it to the generation AI. The generation AI adjusts and updates the sign play pattern based on the feedback and emotional data, generating a more effective pattern.

[0359] Specific examples

[0360] For example, if the user is a sales clerk serving customers at a virtual store, the sales clerk can send their play data along with their own emotional data to the system. Based on this, the generation AI will suggest ways to serve customers that will help them relax. At the same time, the system will also recognize customer emotional data in real time and suggest ways to serve customers that will help them relax. Below are some example prompts for the generation AI.

[0361] "If a sales associate is smiling at a customer but appears nervous, generate a service suggestion to help the customer relax. Or, if a customer appears angry, recommend instructions to the sales associate to deal with the situation calmly."

[0362] In this way, by using this system, it is possible to efficiently confirm and execute sign plays and customer service methods while taking into account the user's emotional state, which is expected to lead to greater skill development and improved customer satisfaction.

[0363] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0364] Step 1:

[0365] Users use their smartphones or tablets to input their playing data (position, skill set, etc.). The playing data includes information such as the user's practice status and technical skills. This data is sent to the server via the device. The input data is accurately stored in a database and processed into a form that can be used for subsequent processing.

[0366] Step 2:

[0367] The server stores the play data received from the user in a database. Specifically, the server analyzes the received data, divides it into fields, and stores the data in a database table.

[0368] Step 3:

[0369] The server provides the saved play data to the generation AI. The generation AI then runs an algorithm based on this data to generate the user's play patterns. Based on the input data, it generates sign play patterns using various parameters and sends the results back to the server. Here, the generation AI model generates play patterns while also taking emotional data into account.

[0370] Step 4:

[0371] The emotion engine is built into the smart glasses and analyzes the user's facial expressions and voice data in real time. Data analysis is performed to recognize the user's emotional state, and the results are sent to the server. At the same time, the results are saved in a database as play data.

[0372] Step 5:

[0373] The server stores the emotion data sent by the emotion engine and the sign play patterns generated by the generation AI in a database, so that the next time the user retrieves a sign play pattern, they will receive a pattern based on the latest state.

[0374] Step 6:

[0375] When a user starts up their smart glasses, they request the latest sign play patterns from the server. The server searches for the latest patterns stored in the database and delivers them to the device. The smart glasses then visually display the received sign play patterns to the user.

[0376] Step 7:

[0377] The smart glasses continuously monitor the user's emotional state and adjust the sign play patterns as needed. Emotional data is updated in real time and sent to the server. Based on this new data, the regenerative AI adaptively adjusts the play patterns.

[0378] Step 8:

[0379] After the user practices the sign-play pattern, they provide feedback to the system regarding their performance and emotional state. Specifically, the user inputs the feedback through the smart glasses, and the data is sent to the server.

[0380] Step 9:

[0381] The server stores the received feedback in a database. After storing it, it analyzes the feedback data and emotion data and provides the results to the generation AI. Based on this, the generation AI adjusts and updates the sign play pattern to generate a more effective pattern. The results are then returned to the server.

[0382] Step 10:

[0383] The server stores the updated patterns in a database and distributes them to the terminal, allowing the user to always use the latest and most optimal sign play patterns for practice or service provision.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] [Second embodiment]

[0388] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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).

[0394] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0399] 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."

[0400] This invention is a system for improving individual and team coordination skills in team sports. This system mainly consists of a server, a device worn by the user (smart glasses), and a generation AI.

[0401] User:

[0402] First, a user inputs their playing data (e.g., position, skill set, etc.) through the system interface. This data is input using a device such as a smartphone or tablet and sent to the server.

[0403] server:

[0404] The server stores the play data received from users in a database. The stored data is organized for each individual user. The server then issues instructions to the generation AI based on the stored play data to generate new sign play patterns.

[0405] The generation AI receives the user's play data and uses a specific algorithm to generate optimal sign play patterns. This AI is designed to evolve based on past data and feedback, providing highly accurate patterns tailored to the user's needs. The generated sign play patterns are sent back to the server and stored in a database.

[0406] Device:

[0407] The device, specifically the smart glasses, accesses the server to acquire the generated sign play patterns, which are then displayed to the user in real time, allowing the user to practice sign plays privately by following the displayed instructions.

[0408] Feedback function:

[0409] After the user practices based on the sign play patterns, they provide feedback on their performance to the system, including specific evaluations and comments. This feedback data is also sent to the server and stored in the database.

[0410] The server analyzes this feedback data and provides it to the generation AI, which then adjusts and updates the sign play patterns based on the feedback, generating more effective patterns. This cyclical process allows users to continually improve their skills and contributes to the discovery of new teamwork.

[0411] Examples:

[0412] For example, let's say the user is in a forward position. The user inputs skill data such as dribbling and speed and sends it to the server. The server receives this data and instructs the generation AI to generate new sign play patterns. The generation AI generates patterns such as effective movements in front of the goal and how to receive a pass, and sends them back to the server.

[0413] The user wearing the smart glasses checks the generated patterns and follows the instructions to practice the movements. The results of the practice are then input into the system as feedback to help improve the sign play patterns.

[0414] In this way, by using this system, users can not only improve their individual skills, but also strengthen their collaborative skills as part of a team.

[0415] The processing flow will be explained below.

[0416] Step 1:

[0417] Users use devices such as smartphones and tablets to input their playing data (position, skill set, etc.).

[0418] Step 2:

[0419] The user transmits the input play data to the server.

[0420] Step 3:

[0421] The server stores the play data received from the user in a database.

[0422] Step 4:

[0423] The server instructs the generation AI to generate new sign play patterns based on the saved play data.

[0424] Step 5:

[0425] The generation AI generates optimal sign play patterns based on the play data received from the server.

[0426] Step 6:

[0427] The generated sign play pattern is sent back from the generation AI to the server, which stores it in a database.

[0428] Step 7:

[0429] The user starts up the device (smart glasses) and requests acquisition of a signature play pattern.

[0430] Step 8:

[0431] The server distributes the saved signature patterns to the device (smart glasses).

[0432] Step 9:

[0433] The device (smart glasses) visually displays the sign play pattern to the user.

[0434] Step 10:

[0435] Users practice sign plays by following the instructions displayed on the smart glasses.

[0436] Step 11:

[0437] After practicing, the user provides feedback on their performance to the system.

[0438] Step 12:

[0439] The server receives the feedback from the user and stores it in a database.

[0440] Step 13:

[0441] The server provides the stored feedback data to the generation AI.

[0442] Step 14:

[0443] The generative AI adjusts and updates sign play patterns based on feedback, generating more effective patterns.

[0444] Example 1

[0445] 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."

[0446] In traditional team sports, improving individual and team coordination skills has relied primarily on individual experience and coaching, making efficient training difficult. It has also been difficult to provide individualized training methods that take into account each player's characteristics and skills, and there has been a lack of adaptive training programs based on feedback. Furthermore, it has been impossible to provide real-time training instructions.

[0447] 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.

[0448] In this invention, the server includes means for receiving play data from users, means for saving the received play data in a database, a generation AI model means for generating new sign play patterns based on the saved play data, means for saving the generated sign play patterns in a database, means for distributing the sign play patterns to the terminal, means for receiving feedback from users and saving it in a database, and a generation AI model means for adjusting and updating the sign play patterns based on the feedback. This makes it possible to generate optimal sign play patterns based on the characteristics of each player and provide instructions in real time. Furthermore, by continuously improving the sign play patterns based on the feedback, it is possible to efficiently improve skills and strengthen team cooperation.

[0449] "Means for receiving play data from a user" refers to a device or software that allows the server to receive information such as the position and skill set entered by the user.

[0450] "Means for storing received play data in a database" refers to a device or software that has the function of storing information received from users in a database for systematic management by the server.

[0451] "Generative AI model means" refers to an artificial intelligence system that generates new sign play patterns using a specific algorithm based on given data.

[0452] "Means for delivering sign play patterns to a terminal" refers to a device or software with network communication capabilities for transmitting the generated sign play patterns to a terminal, specifically to smart glasses, etc.

[0453] "Means for receiving feedback from users" refers to a device or software that allows the server to receive evaluations and comments entered by users after practicing.

[0454] "Means for storing feedback in a database" refers to a device or software that has the function of storing received feedback in a database for systematic management.

[0455] "Generative AI model means for adjusting and updating sign play patterns" refers to an artificial intelligence system that adaptively changes existing sign play patterns based on received feedback and updates them to more effective patterns.

[0456] "Smart glasses" refers to a wearable device that users can wear to obtain visual information in real time.

[0457] "Database" refers to a data management system for storing, managing, and searching user play data and feedback data.

[0458] This invention is a system for improving individual and team coordination skills in team sports. The system mainly consists of a server, a device worn by the user (smart glasses), and a generative AI model.

[0459] User

[0460] First, a user accesses the system interface using a device such as a smartphone or tablet. The user inputs their playing data (e.g., position, skill set, etc.). This data might be, for example, "I'm a forward and I'm good at dribbling." The input data is then sent to the server.

[0461] server

[0462] The server receives play data sent by users. The received data is stored in a database and organized by user. The server then instructs the generative AI model to generate new sign play patterns based on the stored play data. The generative AI model uses a specific algorithm to generate optimal sign play patterns. This AI is designed to evolve based on past data and feedback.

[0463] The generated sign play patterns are sent back to the server and stored in the database. For example, the instructions to the generative AI model might include a prompt like this: "User's position: forward. Skill set: dribbling, speed. Based on this, please generate the optimal sign play pattern."

[0464] Terminal

[0465] The device, specifically the smart glasses, periodically accesses the server to obtain the latest sign play patterns. These patterns are displayed to the user in real time. The user can then follow the instructions displayed on the smart glasses to practice sign plays individually. For example, the smart glasses may display instructions such as "break through the right side and shoot in front of the goal."

[0466] Feedback function

[0467] After the user practices using the sign play pattern, they provide feedback on their performance to the system. The feedback includes specific evaluations and comments, such as, "This dribbling pattern was performed smoothly." This feedback data is also sent to the server and stored in a database. The server analyzes the feedback data and provides the results to the generative AI model. The generative AI model adjusts and updates the sign play pattern based on the feedback, generating a more effective pattern. This cyclical process allows users to continuously improve their skills and also contributes to the discovery of new teamwork plays.

[0468] Specific examples

[0469] For example, let's say the user is in a forward position. The user inputs skill data such as "dribbling and speed" and sends it to the server. The server receives this data and instructs the generative AI model to generate new sign play patterns. The generative AI model generates patterns such as "effective movements in front of the goal" and "how to receive a pass" and sends them back to the server.

[0470] Wearing the smart glasses, the user checks the generated pattern and practices the movement by following the instruction, "Dribble to the right, then cut back to the left." The results of the practice are then input into the system as feedback, such as "Today's sign play was 70 points. The accuracy of the shot was low," which is used to improve the sign play pattern. In this way, by using this system, users can not only improve their individual skills, but also strengthen their teamwork skills as part of a team.

[0471] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0472] Step 1:

[0473] Input: Users access the system interface using a smartphone or tablet.

[0474] Process: User inputs their position and skill set (e.g. forward, dribbling, speed).

[0475] Output: The input data is sent to the server.

[0476] Specific operations: The user enters information such as "forward," "dribble," and "speed" into the form displayed on the smartphone screen and presses the submit button.

[0477] Step 2:

[0478] Input: The server receives play data sent by the user.

[0479] Processing: The received play data is stored in a database. The stored data is organized by user.

[0480] Output: Play data is saved in the database.

[0481] Specific operation: To store data from different users separately, the server assigns each user a unique ID and stores the data associated with it.

[0482] Step 3:

[0483] Input: The server instructs the generation AI model to generate new sign play patterns based on saved play data.

[0484] Processing: The instructions include a prompt statement that includes the user's position and skill set, and is passed to the generative AI model (e.g., "Generate the optimal sign play pattern based on forward, dribbling, and speed").

[0485] Output: Instructions to generate new sign play patterns are sent to the generative AI model.

[0486] Specific operation: The server generates a prompt sentence and provides it to the generative AI model.

[0487] Step 4:

[0488] Input: The generative AI model receives a prompt.

[0489] Processing: Generates sign-play patterns using an internal algorithm. The generative AI model takes into account past data and feedback to generate detailed sign-play patterns, such as "break through on the right side and shoot."

[0490] Output: The generated signature pattern is sent back to the server.

[0491] Specific operation: The generative AI model generates new sign play patterns based on the prompt sentence and sends the results to the server.

[0492] Step 5:

[0493] Input: The generated signature pattern arrives at the server.

[0494] Processing: The server stores the generated signature play pattern in a database.

[0495] Output: Sign play patterns are stored in a database.

[0496] Specific operation: The server checks the returned data, organizes it for each user, and stores it.

[0497] Step 6:

[0498] Input: The device (smart glasses) periodically accesses the server.

[0499] Processing: Get the latest sign play pattern.

[0500] Output: The acquired signature pattern is displayed on the smart glasses.

[0501] Specific operation: The smart glasses download the latest patterns from the server and display instructions to the user in real time, such as "break through the right side and shoot in front of the goal."

[0502] Step 7:

[0503] Input: The user practices by following the sign play patterns displayed on the smart glasses.

[0504] Processing: Performing an action according to instructions.

[0505] Output: User practice results.

[0506] Specific actions: The user follows the displayed instructions to perform the actions on the field and actually practice the play.

[0507] Step 8:

[0508] Input: After practicing, the user provides feedback to the system.

[0509] Processing: Feedback includes specific evaluations and comments (e.g., "That dribble pattern was smooth").

[0510] Output: The feedback data is sent to the server.

[0511] Specific operation: The user inputs feedback from their smartphone and sends it to the server.

[0512] Step 9:

[0513] Input: The server receives feedback from the user.

[0514] Processing: The received feedback is stored in a database and analyzed.

[0515] Output: Feedback data is stored in a database.

[0516] Specific operation: The server analyzes the feedback data and accumulates ratings for each user.

[0517] Step 10:

[0518] Input: The server provides the analysis results to the generative AI model.

[0519] Processing: Adjust and update sign play patterns based on feedback.

[0520] Output: The adjusted and updated signature pattern is generated.

[0521] Specific operation: The generative AI model generates new patterns based on the feedback and provides them to the server.

[0522] Through this series of steps, the system can provide optimal sign play patterns based on the user's characteristics and feedback, helping them improve their skills and strengthen teamwork.

[0523] (Application example 1)

[0524] 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."

[0525] Traditional training methods for improving staff collaboration skills in brick-and-mortar stores often require manual feedback and time-consuming training, making them inefficient. It's also difficult to provide optimal training methods tailored to individual staff members' skill levels and roles, making it challenging to improve teamwork. Furthermore, there's no system for reflecting training results in real time, making continuous skill improvement difficult.

[0526] 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.

[0527] In this invention, the server includes means for receiving play data from users, means for saving the received play data in a database, AI means for generating movement patterns based on the saved play data, means for saving the generated movement patterns in the database, and means for delivering the movement patterns to terminals. This makes it possible to generate optimal movement patterns based on the skill sets and feedback of individual staff members and provide them to staff members in real time.

[0528] "Play data" is information about a user's role and skill set that the user inputs into the system.

[0529] The "database" is a system for storing and managing received play data, generated movement patterns, and feedback data.

[0530] "Movement patterns" are optimal work procedures and movement instructions generated by AI means based on the user's role and skills.

[0531] "AI means" refers to a system that uses artificial intelligence technology to generate optimal movement patterns based on received play data and feedback data.

[0532] A "terminal" is a device that can display movement patterns or smart glasses worn by the user.

[0533] "Feedback" is information about performance and areas for improvement that a user provides to the system after performing a task based on their behavioral patterns.

[0534] The "distribution means" is a system for transferring the generated motion patterns from the server to the user's terminal.

[0535] server

[0536] The server receives play data entered by the user using a smartphone or tablet. The play data is information about the user's role and skill set, and the server stores this data in a database. The stored play data is analyzed by AI means to generate optimal movement patterns. A generative AI model (e.g., OpenAI GPT-4) is used. The movement patterns generated in this process are again stored in the database.

[0537] Terminal

[0538] The devices are primarily smart glasses, which access a server to acquire the generated movement patterns. The smart glasses then display the acquired movement patterns to the user in real time, allowing the user to visually check them as they work. This display function allows each staff member to practice the optimal movements for their role.

[0539] User

[0540] The user performs their work by following the movement patterns delivered from the server, checking their movements in real time through smart glasses. After completing the work, the user enters feedback into the system. Feedback is information about performance and areas for improvement provided by the user after performing a task based on the movement patterns. This feedback data is also sent to the server and stored in a database. The server analyzes this feedback data and provides it to the generation AI. The generation AI adjusts and updates the movement patterns based on the feedback, generating more effective patterns. This cyclical process allows the user to continuously improve their skills.

[0541] Specific examples

[0542] For example, let's say a staff member needs to learn how to display a new product. The staff member wears smart glasses and works while viewing the optimal display pattern generated by the AI ​​in real time. The staff member then inputs the results of their work into the system as feedback. Based on this feedback, the AI ​​can refine the pattern for the next time.

[0543] Prompt Sentence Examples

[0544] Below is an example of a prompt to send to the generated AI.

[0545] text

[0546] Please generate movement patterns for staff to optimally display new products. The following information is available as staff skill data.

[0547] Role: Product display

[0548] Skills: Basic product placement and inventory management

[0549] Additional Information: Display space in stores is limited.

[0550] The generated patterns should include how to position products, proper flow of traffic, and when to use necessary tools.

[0551] In this way, the system of the present invention provides an effective training method for improving staff collaboration skills in brick-and-mortar stores and increasing work efficiency.

[0552] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0553] Step 1:

[0554] The server receives "play data" entered by the user using a smartphone or tablet. The play data includes information about the user's role and skill set. The entered play data is saved in a database by the server. This allows the user's skill set to be accumulated in the database.

[0555] Step 2:

[0556] The server generates "movement patterns" by sending prompts to the generative AI based on the play data stored in the database. The generative AI model (e.g., OpenAI GPT-4) creates optimal movement patterns based on past data and predefined algorithms. These movement patterns are specific work procedures that correspond to the user's role and skills. The generated movement patterns are then stored back in the database by the server.

[0557] Step 3:

[0558] The device, specifically the smart glasses, accesses the server to acquire the generated movement patterns. The smart glasses display the movement patterns to the user in real time, allowing the user to visually confirm the patterns as they work. This allows the user to perform the operations efficiently by following the instructions.

[0559] Step 4:

[0560] The user performs a task according to the action pattern and inputs the results into the system as feedback. The feedback includes information about task performance and areas for improvement. The feedback data is sent to the server and stored in a database. This allows the user's actual work results to be recorded in the system.

[0561] Step 5:

[0562] The server analyzes the feedback data and sends prompts to the AI ​​generator based on this data. The AI ​​generator takes the feedback into account and adjusts and updates the next movement pattern to generate a more effective and accurate movement pattern, thereby achieving continuous skill improvement.

[0563] 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.

[0564] This invention is a system for improving the coordination skills of individuals and teams in team sports, and in particular, by combining an emotion engine, it generates and adjusts play patterns taking into account the user's emotional state. This system mainly consists of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[0565] User:

[0566] Users input their playing data (position, skill set, etc.) using a device such as a smartphone or tablet. This data is sent to the server via the device. By wearing the smart glasses, the user can practice based on the displayed sign play patterns.

[0567] server:

[0568] The server stores the play data received from the user in a database and provides it to the generation AI. The generation AI generates sign play patterns based on this data and sends the generated patterns back to the server. The server then stores the generated sign play patterns in a database and distributes them to devices as needed.

[0569] Emotion Engine:

[0570] The emotion engine recognizes the user's emotional state in real time by analyzing facial expressions, voice data, etc. The emotion data recognized by the emotion engine is sent to the server and stored in a database.

[0571] Generation AI:

[0572] The AI ​​combines play data and emotional data to generate signature play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will ease that tension, and if the user is concentrating, it will provide a more difficult pattern. The generated patterns are then sent back to the server.

[0573] Device:

[0574] When a user activates the smart glasses, a request is made to acquire sign play patterns from the server. The server then transmits the generated patterns to the device, and the smart glasses visually display them to the user. The emotion engine continues to monitor the user's emotional state during this process, adaptively changing the content of the sign play patterns as needed.

[0575] Feedback function:

[0576] After the user practices the sign play patterns, they provide feedback to the system about their performance and emotional state, including specific ratings and comments, which are also sent to the server and stored in the database.

[0577] The server analyzes this feedback and emotional data and provides it to the generation AI. The generation AI then adjusts and updates the sign play patterns based on the feedback and emotional data, generating more effective patterns. This cyclical process not only allows users to improve their individual skills, but also enables them to play at a more advanced level that takes into account their emotional state and teamwork skills.

[0578] Examples:

[0579] For example, let's say the user is in a forward position. The user inputs skill data such as dribbling and speed and sends it to the server. The server receives and stores this data, and instructs the generation AI to generate new sign play patterns. The generation AI also takes into account the user's current emotional state and generates patterns such as effective movements in front of the goal and how to receive a pass.

[0580] Wearing the smart glasses, the user views the generated patterns and practices the movements according to the displayed instructions. The emotion engine monitors the user's emotional state during practice and adjusts the instructions as needed. After practice, the user provides feedback on their performance and emotional state to the system, which further refines and updates the sign play patterns.

[0581] In this way, by using this system, users can efficiently check and practice sign plays while taking their emotional state into consideration, which is expected to lead to greater skill improvement.

[0582] The processing flow will be explained below.

[0583] Step 1:

[0584] Users use devices such as smartphones and tablets to input their playing data (position, skill set, etc.).

[0585] Step 2:

[0586] The user transmits the input play data to the server.

[0587] Step 3:

[0588] The server stores the play data received from the user in a database.

[0589] Step 4:

[0590] The server instructs the generation AI to generate new sign play patterns based on the saved play data.

[0591] Step 5:

[0592] The generation AI generates optimal sign play patterns based on the play data received from the server.

[0593] Step 6:

[0594] The generated sign play pattern is sent back from the generation AI to the server, which stores it in a database.

[0595] Step 7:

[0596] The user starts up the device (smart glasses) and requests acquisition of a signature play pattern.

[0597] Step 8:

[0598] The server distributes the saved signature patterns to the device (smart glasses).

[0599] Step 9:

[0600] The device (smart glasses) visually displays the sign play pattern to the user.

[0601] Step 10:

[0602] The emotion engine analyzes the user's facial expressions and voice data in real time to recognize their emotional state, and the recognized emotional data is sent to the server.

[0603] Step 11:

[0604] The server stores the emotion data received from the emotion engine in a database.

[0605] Step 12:

[0606] The AI ​​optimizes sign play patterns based on the user's play data and emotional data. For example, if the user is nervous, it will provide a relaxing pattern, and if the user is concentrating, it will provide a more difficult pattern.

[0607] Step 13:

[0608] Users practice sign plays by following the instructions displayed on the smart glasses.

[0609] Step 14:

[0610] After practicing, the user provides feedback to the system about their performance and emotional state.

[0611] Step 15:

[0612] The server receives the feedback from the user and stores it in a database.

[0613] Step 16:

[0614] The server provides the stored feedback data and emotional data to the generation AI, instructing it to adjust and improve its sign play patterns.

[0615] Step 17:

[0616] Generative AI adjusts and updates sign-play patterns based on feedback and emotional data to generate more effective patterns.

[0617] Step 18:

[0618] The server re-distributes the updated sign play pattern to the device (smart glasses), allowing the user to practice again.

[0619] Example 2

[0620] 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."

[0621] Conventional training systems for team sports provide playing patterns without considering the user's emotional state, resulting in performance differences depending on the individual's physical condition and psychological state. Furthermore, they are unable to provide real-time feedback and reflect emotional data, making it difficult to effectively support the improvement of teamwork and individual skills. This reduces the efficiency of practice and prevents sufficient support for user growth.

[0622] 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.

[0623] In this invention, the server includes a means for receiving play data from users, a means for storing the received play data in a database, and an AI means for generating sign play patterns based on the play data and emotional data received in real time. This allows for the generation of play patterns that take the user's emotional state into account, providing practice tailored to each individual's condition. Furthermore, by modifying and generating sign play patterns based on feedback and emotional data, it is possible to effectively support the user's growth.

[0624] The "means for receiving play data from the user" is a communication interface for transmitting information about practice such as sports positions and skill sets entered by the user to the server.

[0625] The "means for storing received play data in a database" is a mechanism by which the server records play data sent from users in a storage device.

[0626] The "AI means for generating sign play patterns based on play data and emotional data received in real time" is an artificial intelligence engine that analyzes the user's practice data and emotional data and generates appropriate play patterns based on the results.

[0627] The "means for saving the generated sign play patterns and emotion data in a database" is a system for recording the generated sign play patterns and emotion data recognized by the emotion engine in a storage device.

[0628] The "means for providing the generation AI using play data and emotional data" is a communication interface that allows the server to transmit the stored play data and emotional data to the generation AI for analysis and pattern generation.

[0629] The "means for delivering the sign play pattern to the terminal" is a communication mechanism that allows the server to transmit the generated sign play pattern to the user's smart glasses or other display terminal.

[0630] "Displaying sign play patterns on smart glasses" refers to a function that displays the sign play patterns received by smart glasses from the server in a form that can be visually confirmed by the user.

[0631] The "means for receiving feedback from the user" is a communication interface for transmitting feedback information such as evaluations and emotions input by the user after practice to the server.

[0632] "AI means for storing received feedback in a database and modifying and generating sign play patterns based on the feedback and emotional data" refers to an artificial intelligence engine that records feedback data and emotional data in a storage device and generates more effective sign play patterns based on that data.

[0633] The "system" refers to a comprehensive mechanism that includes a server, user terminals (such as smart glasses), generative AI, emotion engine, and communication means for sending and receiving data between them.

[0634] This invention is a system for improving individual and team coordination skills in team sports, and in particular generates and adjusts play patterns taking into account the user's emotional state. This system is primarily composed of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[0635] server

[0636] The server stores the play data (position, skill set, etc.) received from the user in a database and provides it to the generation AI. The hardware used is server equipment with high-performance processing capabilities (brand names are not specified, but this includes commonly used cloud service servers).

[0637] The server issues instructions to the generation AI based on the play data, stores the generated sign play patterns in a database, and distributes them to devices as needed.

[0638] Terminal

[0639] Users use a smartphone or tablet to input their own play data, which is then sent to a server via the device. By wearing smart glasses, they can visually confirm the sign play patterns and practice based on them. For example, a user can use a smartphone app to input their position as "forward" and their skill set as "dribbling, speed," and then send the data. This data is then saved on the server.

[0640] Emotion Engine

[0641] The emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state in real time. Specifically, it is expected to use a facial recognition camera and voice analysis software. The emotion engine operates while the user is using the smart glasses, and transmits their emotional state during practice to the server in real time.

[0642] Generation AI

[0643] The generation AI combines play data and emotional data to generate sign play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will ease that tension, and conversely, if the user is concentrating, it will provide a more difficult pattern. The generated patterns are then sent back to the server. The AI ​​model used utilizes a common deep learning algorithm.

[0644] Specific examples

[0645] For example, consider the case where a user inputs "data on dribbling and speed for a forward position" and sends it to the server. The server receives and stores the play data, and then instructs the generation AI to generate a new sign play pattern based on that data.

[0646] The generative AI generates "patterns for effective movements in front of the goal and how to receive a pass," taking into account the user's current emotional state. As the user wears the smart glasses and practices movements based on the displayed sign play patterns, the emotion engine monitors the user's emotional state and adaptively changes the instructions as necessary.

[0647] Prompt Sentence Examples

[0648] Here are some example prompts to input to the AI ​​generator:

[0649] "The user's position is forward, and their skill set is focused on dribbling and speed. Their current emotional state is tense. Please generate a pattern of how they will receive a pass in front of the goal, taking this state into account."

[0650] "The user is a midfielder with good defensive skills. He is in a focused state. Please generate an appropriate passing pattern for this situation."

[0651] In this way, by using this system, users can efficiently understand practice patterns while taking into account their emotional state and achieve advanced play.

[0652] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0653] Step 1:

[0654] The user uses a smartphone or tablet to input their playing data. Specifically, the user inputs their position (e.g., forward) and skill set (e.g., dribbling, speed) through the application and presses the send button. This action sends the input data from the device to the server.

[0655] Input: Position and Skillset Data

[0656] Output: Play data sent to the server

[0657] Step 2:

[0658] The server stores the play data received from the user in a database. Specifically, the database management system converts the received data into an appropriate format and inserts it into the corresponding table in the database. Through this process, the user's play data is recorded in a form that can be stored for a long period of time.

[0659] Input: User's play data

[0660] Output: Play data stored in the database

[0661] Step 3:

[0662] The server provides the saved play data to the AI ​​generator. Specifically, the server acquires the play data and creates a prompt statement requesting the AI ​​generator to generate a new sign play pattern. The prompt statement includes the user's play data and their emotional state.

[0663] Input: Play data retrieved from the database

[0664] Output: The prompt sent to the generation AI

[0665] Step 4:

[0666] The generation AI generates sign play patterns based on play data and emotional data. Specifically, the generation AI analyzes the input data and generates play patterns that take the user's emotional state into account. For example, if the user is nervous, a pattern to relieve tension will be generated.

[0667] Input: Prompt sentence containing play data and emotion data

[0668] Output: Generated sign play pattern

[0669] Step 5:

[0670] The server stores the generated signature play patterns in a database. Specifically, the generated patterns are received by the server and stored in a corresponding table in the database. This allows the user's signature play patterns to be recorded in a form that can be referenced later.

[0671] Input: Sign play pattern returned from the generation AI

[0672] Output: Sign play patterns stored in the database

[0673] Step 6:

[0674] The user starts up the smart glasses and requests the acquisition of a sign play pattern. Specifically, the user opens the smart glasses application and sends a request to the server to acquire the sign play pattern. This request includes the user ID and session information.

[0675] Input: A get request containing the user ID and session information

[0676] Output: Request data sent to the server

[0677] Step 7:

[0678] The server distributes the generated sign play patterns to the device. Specifically, the server retrieves the corresponding sign play patterns from the database and sends them to the user's smart glasses. This process allows the user to obtain the necessary practice data in real time.

[0679] Input: Retrieval request, signature pattern in database

[0680] Output: Sign play pattern delivered to the terminal

[0681] Step 8:

[0682] The emotion engine recognizes and records the user's emotional state. Specifically, the camera and microphone built into the smart glasses capture the user's facial expressions and voice and send them to the emotion engine. The emotion engine analyzes this and sends the emotional data to the server.

[0683] Input: User's facial expression data, voice data

[0684] Output: Emotion data sent to the server

[0685] Step 9:

[0686] The user practices based on sign play patterns. Specifically, they practice movements and techniques by following instructions displayed on the smart glasses. The user's emotional state is continuously monitored by the emotion engine, and feedback is received from the server as needed.

[0687] Input: Sign play pattern displayed on smart glasses

[0688] Output: The exercise performed

[0689] Step 10:

[0690] Users provide feedback on their performance and emotional state to the system. Specifically, after practice, they use a smartphone or tablet to input their evaluations and comments about the effectiveness of the practice and their own emotional state, and send them to the server.

[0691] Input: Feedback information entered by the user

[0692] Output: Feedback data sent to the server

[0693] Step 11:

[0694] The server provides feedback to the generation AI to generate new patterns. Specifically, the server analyzes the saved feedback data and provides it to the generation AI, instructing it to generate new sign play patterns. The generation AI then uses this data to generate more effective play patterns.

[0695] Input: Feedback data, existing emotion data

[0696] Output: The new sign play pattern generated

[0697] By repeating the above steps, the optimal practice is provided according to the user's playing style and emotional state.

[0698] (Application example 2)

[0699] 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."

[0700] In conventional team sports practice, it is difficult to provide appropriate feedback and guidance to improve individual and team coordination skills. Furthermore, there is no system that provides optimal training methods based on the user's emotional state, making it difficult to maximize the user's motivation and concentration. Furthermore, in virtual stores, it is necessary to provide an optimal experience while taking into account the emotional states of both store staff and customers, but current systems have difficulty achieving this.

[0701] 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 play data from the user, means for saving the received play data in a database, AI means for generating sign play patterns based on the saved play data and the user's emotional data, means for saving the generated sign play patterns in a database, means for distributing the sign play patterns to the terminal, means for monitoring the emotional data of the user and others in real time, and means for adaptively adjusting the sign play patterns based on the monitored emotional data. This makes it possible to provide appropriate and effective feedback and guidance taking into account the user's emotional state. Furthermore, in virtual stores, customer satisfaction can be improved by proposing and adjusting optimal customer service methods in real time based on the emotional states of store staff and customers.

[0702] "Users" refers to people who use the system to provide play data and emotional data.

[0703] "Play data" refers to data such as sports positions and skill sets entered by the user.

[0704] "Database" refers to a digital storage system for storing play data, emotional data, and generated sign play patterns.

[0705] "Emotion data" refers to information about the emotional state obtained by analyzing facial expressions and voice data of the user and other people.

[0706] A "signature play pattern" refers to a pattern that is generated based on the user's play data and emotion data and that instructs a specific play or movement.

[0707] "AI means" refers to technology that uses artificial intelligence to analyze data and generate and modify sign play patterns.

[0708] "Terminal" refers to a device such as smart glasses worn by a user, which is used to display sign play patterns.

[0709] "Monitoring means" refers to technology that observes and collects emotional data of users and others in real time.

[0710] "Adaptive adjustment means" refers to technology that changes sign-play patterns in real time based on monitored emotional data.

[0711] "Feedback" refers to ratings and comments about performance and emotional state provided by users and others after using the system.

[0712] This invention is a system for improving the cooperative skills of individuals and teams, and in particular, by combining an emotion engine, it generates and adjusts play patterns taking into account the user's emotional state. This system mainly consists of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[0713] User operations

[0714] Users use devices such as smartphones or tablets to input their playing data (position, skill set, etc.). This data is sent to a server via the terminal. By wearing the smart glasses, players can practice based on the displayed sign play patterns. An emotion engine is built into the smart glasses and recognizes the user's emotional state by analyzing their facial expressions and voice data in real time.

[0715] Server Processing

[0716] The server stores the play data received from the user in a database and provides it to the generation AI. The generation AI generates sign play patterns based on this data and sends the generated patterns back to the server. The server then stores the generated sign play patterns in a database and distributes them to devices as needed.

[0717] Emotion Engine Functions

[0718] The emotion engine analyzes the user's facial expressions, voice data, and other data to recognize their emotional state in real time. The recognized emotional data is sent to a server and stored in a database. The generation AI combines play data and emotional data to generate sign play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will relieve that tension, and if the user is concentrating, it will provide a more difficult pattern.

[0719] The role of smart glasses

[0720] When a user activates the smart glasses, a request is made to acquire sign play patterns from the server. The server then transmits the generated patterns to the device, and the smart glasses visually display them to the user. The emotion engine continues to monitor the user's emotional state during this process, adaptively changing the content of the sign play patterns as needed.

[0721] Feedback function

[0722] After a user practices a sign play pattern, they provide feedback to the system about their performance and emotional state. The feedback includes specific evaluations and comments, and is sent to the server and stored in a database. The server analyzes this feedback data and emotional data and provides it to the generation AI. The generation AI adjusts and updates the sign play pattern based on the feedback and emotional data, generating a more effective pattern.

[0723] Specific examples

[0724] For example, if the user is a sales clerk serving customers at a virtual store, the sales clerk can send their play data along with their own emotional data to the system. Based on this, the generation AI will suggest ways to serve customers that will help them relax. At the same time, the system will also recognize customer emotional data in real time and suggest ways to serve customers that will help them relax. Below are some example prompts for the generation AI.

[0725] "If a sales associate is smiling at a customer but appears nervous, generate a service suggestion to help the customer relax. Or, if a customer appears angry, recommend instructions to the sales associate to deal with the situation calmly."

[0726] In this way, by using this system, it is possible to efficiently confirm and execute sign plays and customer service methods while taking into account the user's emotional state, which is expected to lead to greater skill development and improved customer satisfaction.

[0727] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0728] Step 1:

[0729] Users use their smartphones or tablets to input their playing data (position, skill set, etc.). The playing data includes information such as the user's practice status and technical skills. This data is sent to the server via the device. The input data is accurately stored in a database and processed into a form that can be used for subsequent processing.

[0730] Step 2:

[0731] The server stores the play data received from the user in a database. Specifically, the server analyzes the received data, divides it into fields, and stores the data in a database table.

[0732] Step 3:

[0733] The server provides the saved play data to the generation AI. The generation AI then runs an algorithm based on this data to generate the user's play patterns. Based on the input data, it generates sign play patterns using various parameters and sends the results back to the server. Here, the generation AI model generates play patterns while also taking emotional data into account.

[0734] Step 4:

[0735] The emotion engine is built into the smart glasses and analyzes the user's facial expressions and voice data in real time. Data analysis is performed to recognize the user's emotional state, and the results are sent to the server. At the same time, the results are saved in a database as play data.

[0736] Step 5:

[0737] The server stores the emotion data sent by the emotion engine and the sign play patterns generated by the generation AI in a database, so that the next time the user retrieves a sign play pattern, they will receive a pattern based on the latest state.

[0738] Step 6:

[0739] When a user starts up their smart glasses, they request the latest sign play patterns from the server. The server searches for the latest patterns stored in the database and delivers them to the device. The smart glasses then visually display the received sign play patterns to the user.

[0740] Step 7:

[0741] The smart glasses continuously monitor the user's emotional state and adjust the sign play patterns as needed. Emotional data is updated in real time and sent to the server. Based on this new data, the regenerative AI adaptively adjusts the play patterns.

[0742] Step 8:

[0743] After the user practices the sign-play pattern, they provide feedback to the system regarding their performance and emotional state. Specifically, the user inputs the feedback through the smart glasses, and the data is sent to the server.

[0744] Step 9:

[0745] The server stores the received feedback in a database. After storing it, it analyzes the feedback data and emotion data and provides the results to the generation AI. Based on this, the generation AI adjusts and updates the sign play pattern to generate a more effective pattern. The results are then returned to the server.

[0746] Step 10:

[0747] The server stores the updated patterns in a database and distributes them to the terminal, allowing the user to always use the latest and most optimal sign play patterns for practice or service provision.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] [Third embodiment]

[0752] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0753] 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.

[0754] 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).

[0755] 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.

[0756] 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.

[0757] 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).

[0758] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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."

[0764] This invention is a system for improving individual and team coordination skills in team sports. This system mainly consists of a server, a device worn by the user (smart glasses), and a generation AI.

[0765] User:

[0766] First, a user inputs their playing data (e.g., position, skill set, etc.) through the system interface. This data is input using a device such as a smartphone or tablet and sent to the server.

[0767] server:

[0768] The server stores the play data received from users in a database. The stored data is organized for each individual user. The server then issues instructions to the generation AI based on the stored play data to generate new sign play patterns.

[0769] The generation AI receives the user's play data and uses a specific algorithm to generate optimal sign play patterns. This AI is designed to evolve based on past data and feedback, providing highly accurate patterns tailored to the user's needs. The generated sign play patterns are sent back to the server and stored in a database.

[0770] Device:

[0771] The device, specifically the smart glasses, accesses the server to acquire the generated sign play patterns, which are then displayed to the user in real time, allowing the user to practice sign plays privately by following the displayed instructions.

[0772] Feedback function:

[0773] After the user practices based on the sign play patterns, they provide feedback on their performance to the system, including specific evaluations and comments. This feedback data is also sent to the server and stored in the database.

[0774] The server analyzes this feedback data and provides it to the generation AI, which then adjusts and updates the sign play patterns based on the feedback, generating more effective patterns. This cyclical process allows users to continually improve their skills and contributes to the discovery of new teamwork.

[0775] Examples:

[0776] For example, let's say the user is in a forward position. The user inputs skill data such as dribbling and speed and sends it to the server. The server receives this data and instructs the generation AI to generate new sign play patterns. The generation AI generates patterns such as effective movements in front of the goal and how to receive a pass, and sends them back to the server.

[0777] The user wearing the smart glasses checks the generated patterns and follows the instructions to practice the movements. The results of the practice are then input into the system as feedback to help improve the sign play patterns.

[0778] In this way, by using this system, users can not only improve their individual skills, but also strengthen their collaborative skills as part of a team.

[0779] The processing flow will be explained below.

[0780] Step 1:

[0781] Users use devices such as smartphones and tablets to input their playing data (position, skill set, etc.).

[0782] Step 2:

[0783] The user transmits the input play data to the server.

[0784] Step 3:

[0785] The server stores the play data received from the user in a database.

[0786] Step 4:

[0787] The server instructs the generation AI to generate new sign play patterns based on the saved play data.

[0788] Step 5:

[0789] The generation AI generates optimal sign play patterns based on the play data received from the server.

[0790] Step 6:

[0791] The generated sign play pattern is sent back from the generation AI to the server, which stores it in a database.

[0792] Step 7:

[0793] The user starts up the device (smart glasses) and requests acquisition of a signature play pattern.

[0794] Step 8:

[0795] The server distributes the saved signature patterns to the device (smart glasses).

[0796] Step 9:

[0797] The device (smart glasses) visually displays the sign play pattern to the user.

[0798] Step 10:

[0799] Users practice sign plays by following the instructions displayed on the smart glasses.

[0800] Step 11:

[0801] After practicing, the user provides feedback on their performance to the system.

[0802] Step 12:

[0803] The server receives the feedback from the user and stores it in a database.

[0804] Step 13:

[0805] The server provides the stored feedback data to the generation AI.

[0806] Step 14:

[0807] The generative AI adjusts and updates sign play patterns based on feedback, generating more effective patterns.

[0808] Example 1

[0809] 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."

[0810] In traditional team sports, improving individual and team coordination skills has relied primarily on individual experience and coaching, making efficient training difficult. It has also been difficult to provide individualized training methods that take into account each player's characteristics and skills, and there has been a lack of adaptive training programs based on feedback. Furthermore, it has been impossible to provide real-time training instructions.

[0811] 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.

[0812] In this invention, the server includes means for receiving play data from users, means for saving the received play data in a database, a generation AI model means for generating new sign play patterns based on the saved play data, means for saving the generated sign play patterns in a database, means for distributing the sign play patterns to the terminal, means for receiving feedback from users and saving it in a database, and a generation AI model means for adjusting and updating the sign play patterns based on the feedback. This makes it possible to generate optimal sign play patterns based on the characteristics of each player and provide instructions in real time. Furthermore, by continuously improving the sign play patterns based on the feedback, it is possible to efficiently improve skills and strengthen team cooperation.

[0813] "Means for receiving play data from a user" refers to a device or software that allows the server to receive information such as the position and skill set entered by the user.

[0814] "Means for storing received play data in a database" refers to a device or software that has the function of storing information received from users in a database for systematic management by the server.

[0815] "Generative AI model means" refers to an artificial intelligence system that generates new sign play patterns using a specific algorithm based on given data.

[0816] "Means for delivering sign play patterns to a terminal" refers to a device or software with network communication capabilities for transmitting the generated sign play patterns to a terminal, specifically to smart glasses, etc.

[0817] "Means for receiving feedback from users" refers to a device or software that allows the server to receive evaluations and comments entered by users after practicing.

[0818] "Means for storing feedback in a database" refers to a device or software that has the function of storing received feedback in a database for systematic management.

[0819] "Generative AI model means for adjusting and updating sign play patterns" refers to an artificial intelligence system that adaptively changes existing sign play patterns based on received feedback and updates them to more effective patterns.

[0820] "Smart glasses" refers to a wearable device that users can wear to obtain visual information in real time.

[0821] "Database" refers to a data management system for storing, managing, and searching user play data and feedback data.

[0822] This invention is a system for improving individual and team coordination skills in team sports. The system mainly consists of a server, a device worn by the user (smart glasses), and a generative AI model.

[0823] User

[0824] First, a user accesses the system interface using a device such as a smartphone or tablet. The user inputs their playing data (e.g., position, skill set, etc.). This data might be, for example, "I'm a forward and I'm good at dribbling." The input data is then sent to the server.

[0825] server

[0826] The server receives play data sent by users. The received data is stored in a database and organized by user. The server then instructs the generative AI model to generate new sign play patterns based on the stored play data. The generative AI model uses a specific algorithm to generate optimal sign play patterns. This AI is designed to evolve based on past data and feedback.

[0827] The generated sign play patterns are sent back to the server and stored in the database. For example, the instructions to the generative AI model might include a prompt like this: "User's position: forward. Skill set: dribbling, speed. Based on this, please generate the optimal sign play pattern."

[0828] Terminal

[0829] The device, specifically the smart glasses, periodically accesses the server to obtain the latest sign play patterns. These patterns are displayed to the user in real time. The user can then follow the instructions displayed on the smart glasses to practice sign plays individually. For example, the smart glasses may display instructions such as "break through the right side and shoot in front of the goal."

[0830] Feedback function

[0831] After the user practices using the sign play pattern, they provide feedback on their performance to the system. The feedback includes specific evaluations and comments, such as, "This dribbling pattern was performed smoothly." This feedback data is also sent to the server and stored in a database. The server analyzes the feedback data and provides the results to the generative AI model. The generative AI model adjusts and updates the sign play pattern based on the feedback, generating a more effective pattern. This cyclical process allows users to continuously improve their skills and also contributes to the discovery of new teamwork plays.

[0832] Specific examples

[0833] For example, let's say the user is in a forward position. The user inputs skill data such as "dribbling and speed" and sends it to the server. The server receives this data and instructs the generative AI model to generate new sign play patterns. The generative AI model generates patterns such as "effective movements in front of the goal" and "how to receive a pass" and sends them back to the server.

[0834] Wearing the smart glasses, the user checks the generated pattern and practices the movement by following the instruction, "Dribble to the right, then cut back to the left." The results of the practice are then input into the system as feedback, such as "Today's sign play was 70 points. The accuracy of the shot was low," which is used to improve the sign play pattern. In this way, by using this system, users can not only improve their individual skills, but also strengthen their teamwork skills as part of a team.

[0835] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0836] Step 1:

[0837] Input: Users access the system interface using a smartphone or tablet.

[0838] Process: User inputs their position and skill set (e.g. forward, dribbling, speed).

[0839] Output: The input data is sent to the server.

[0840] Specific operations: The user enters information such as "forward," "dribble," and "speed" into the form displayed on the smartphone screen and presses the submit button.

[0841] Step 2:

[0842] Input: The server receives play data sent by the user.

[0843] Processing: The received play data is stored in a database. The stored data is organized by user.

[0844] Output: Play data is saved in the database.

[0845] Specific operation: To store data from different users separately, the server assigns each user a unique ID and stores the data associated with it.

[0846] Step 3:

[0847] Input: The server instructs the generation AI model to generate new sign play patterns based on saved play data.

[0848] Processing: The instructions include a prompt statement that includes the user's position and skill set, and is passed to the generative AI model (e.g., "Generate the optimal sign play pattern based on forward, dribbling, and speed").

[0849] Output: Instructions to generate new sign play patterns are sent to the generative AI model.

[0850] Specific operation: The server generates a prompt sentence and provides it to the generative AI model.

[0851] Step 4:

[0852] Input: The generative AI model receives a prompt.

[0853] Processing: Generates sign-play patterns using an internal algorithm. The generative AI model takes into account past data and feedback to generate detailed sign-play patterns, such as "break through on the right side and shoot."

[0854] Output: The generated signature pattern is sent back to the server.

[0855] Specific operation: The generative AI model generates new sign play patterns based on the prompt sentence and sends the results to the server.

[0856] Step 5:

[0857] Input: The generated signature pattern arrives at the server.

[0858] Processing: The server stores the generated signature play pattern in a database.

[0859] Output: Sign play patterns are stored in a database.

[0860] Specific operation: The server checks the returned data, organizes it for each user, and stores it.

[0861] Step 6:

[0862] Input: The device (smart glasses) periodically accesses the server.

[0863] Processing: Get the latest sign play pattern.

[0864] Output: The acquired signature pattern is displayed on the smart glasses.

[0865] Specific operation: The smart glasses download the latest patterns from the server and display instructions to the user in real time, such as "break through the right side and shoot in front of the goal."

[0866] Step 7:

[0867] Input: The user practices by following the sign play patterns displayed on the smart glasses.

[0868] Processing: Performing an action according to instructions.

[0869] Output: User practice results.

[0870] Specific actions: The user follows the displayed instructions to perform the actions on the field and actually practice the play.

[0871] Step 8:

[0872] Input: After practicing, the user provides feedback to the system.

[0873] Processing: Feedback includes specific evaluations and comments (e.g., "That dribble pattern was smooth").

[0874] Output: The feedback data is sent to the server.

[0875] Specific operation: The user inputs feedback from their smartphone and sends it to the server.

[0876] Step 9:

[0877] Input: The server receives feedback from the user.

[0878] Processing: The received feedback is stored in a database and analyzed.

[0879] Output: Feedback data is stored in a database.

[0880] Specific operation: The server analyzes the feedback data and accumulates ratings for each user.

[0881] Step 10:

[0882] Input: The server provides the analysis results to the generative AI model.

[0883] Processing: Adjust and update sign play patterns based on feedback.

[0884] Output: The adjusted and updated signature pattern is generated.

[0885] Specific operation: The generative AI model generates new patterns based on the feedback and provides them to the server.

[0886] Through this series of steps, the system can provide optimal sign play patterns based on the user's characteristics and feedback, helping them improve their skills and strengthen teamwork.

[0887] (Application example 1)

[0888] 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."

[0889] Traditional training methods for improving staff collaboration skills in brick-and-mortar stores often require manual feedback and time-consuming training, making them inefficient. It's also difficult to provide optimal training methods tailored to individual staff members' skill levels and roles, making it challenging to improve teamwork. Furthermore, there's no system for reflecting training results in real time, making continuous skill improvement difficult.

[0890] 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.

[0891] In this invention, the server includes means for receiving play data from users, means for saving the received play data in a database, AI means for generating movement patterns based on the saved play data, means for saving the generated movement patterns in the database, and means for delivering the movement patterns to terminals. This makes it possible to generate optimal movement patterns based on the skill sets and feedback of individual staff members and provide them to staff members in real time.

[0892] "Play data" is information about a user's role and skill set that the user inputs into the system.

[0893] The "database" is a system for storing and managing received play data, generated movement patterns, and feedback data.

[0894] "Movement patterns" are optimal work procedures and movement instructions generated by AI means based on the user's role and skills.

[0895] "AI means" refers to a system that uses artificial intelligence technology to generate optimal movement patterns based on received play data and feedback data.

[0896] A "terminal" is a device that can display movement patterns or smart glasses worn by the user.

[0897] "Feedback" is information about performance and areas for improvement that a user provides to the system after performing a task based on their behavioral patterns.

[0898] The "distribution means" is a system for transferring the generated motion patterns from the server to the user's terminal.

[0899] server

[0900] The server receives play data entered by the user using a smartphone or tablet. The play data is information about the user's role and skill set, and the server stores this data in a database. The stored play data is analyzed by AI means to generate optimal movement patterns. A generative AI model (e.g., OpenAI GPT-4) is used. The movement patterns generated in this process are again stored in the database.

[0901] Terminal

[0902] The devices are primarily smart glasses, which access a server to acquire the generated movement patterns. The smart glasses then display the acquired movement patterns to the user in real time, allowing the user to visually check them as they work. This display function allows each staff member to practice the optimal movements for their role.

[0903] User

[0904] The user performs their work by following the movement patterns delivered from the server, checking their movements in real time through smart glasses. After completing the work, the user enters feedback into the system. Feedback is information about performance and areas for improvement provided by the user after performing a task based on the movement patterns. This feedback data is also sent to the server and stored in a database. The server analyzes this feedback data and provides it to the generation AI. The generation AI adjusts and updates the movement patterns based on the feedback, generating more effective patterns. This cyclical process allows the user to continuously improve their skills.

[0905] Specific examples

[0906] For example, let's say a staff member needs to learn how to display a new product. The staff member wears smart glasses and works while viewing the optimal display pattern generated by the AI ​​in real time. The staff member then inputs the results of their work into the system as feedback. Based on this feedback, the AI ​​can refine the pattern for the next time.

[0907] Prompt Sentence Examples

[0908] Below is an example of a prompt to send to the generated AI.

[0909] text

[0910] Please generate movement patterns for staff to optimally display new products. The following information is available as staff skill data.

[0911] Role: Product display

[0912] Skills: Basic product placement and inventory management

[0913] Additional Information: Display space in stores is limited.

[0914] The generated patterns should include how to position products, proper flow of traffic, and when to use necessary tools.

[0915] In this way, the system of the present invention provides an effective training method for improving staff collaboration skills in brick-and-mortar stores and increasing work efficiency.

[0916] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0917] Step 1:

[0918] The server receives "play data" entered by the user using a smartphone or tablet. The play data includes information about the user's role and skill set. The entered play data is saved in a database by the server. This allows the user's skill set to be accumulated in the database.

[0919] Step 2:

[0920] The server generates "movement patterns" by sending prompts to the generative AI based on the play data stored in the database. The generative AI model (e.g., OpenAI GPT-4) creates optimal movement patterns based on past data and predefined algorithms. These movement patterns are specific work procedures that correspond to the user's role and skills. The generated movement patterns are then stored back in the database by the server.

[0921] Step 3:

[0922] The device, specifically the smart glasses, accesses the server to acquire the generated movement patterns. The smart glasses display the movement patterns to the user in real time, allowing the user to visually confirm the patterns as they work. This allows the user to perform the operations efficiently by following the instructions.

[0923] Step 4:

[0924] The user performs a task according to the action pattern and inputs the results into the system as feedback. The feedback includes information about task performance and areas for improvement. The feedback data is sent to the server and stored in a database. This allows the user's actual work results to be recorded in the system.

[0925] Step 5:

[0926] The server analyzes the feedback data and sends prompts to the AI ​​generator based on this data. The AI ​​generator takes the feedback into account and adjusts and updates the next movement pattern to generate a more effective and accurate movement pattern, thereby achieving continuous skill improvement.

[0927] 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.

[0928] This invention is a system for improving the coordination skills of individuals and teams in team sports, and in particular, by combining an emotion engine, it generates and adjusts play patterns taking into account the user's emotional state. This system mainly consists of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[0929] User:

[0930] Users input their playing data (position, skill set, etc.) using a device such as a smartphone or tablet. This data is sent to the server via the device. By wearing the smart glasses, the user can practice based on the displayed sign play patterns.

[0931] server:

[0932] The server stores the play data received from the user in a database and provides it to the generation AI. The generation AI generates sign play patterns based on this data and sends the generated patterns back to the server. The server then stores the generated sign play patterns in a database and distributes them to devices as needed.

[0933] Emotion Engine:

[0934] The emotion engine recognizes the user's emotional state in real time by analyzing facial expressions, voice data, etc. The emotion data recognized by the emotion engine is sent to the server and stored in a database.

[0935] Generation AI:

[0936] The AI ​​combines play data and emotional data to generate signature play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will ease that tension, and if the user is concentrating, it will provide a more difficult pattern. The generated patterns are then sent back to the server.

[0937] Device:

[0938] When a user activates the smart glasses, a request is made to acquire sign play patterns from the server. The server then transmits the generated patterns to the device, and the smart glasses visually display them to the user. The emotion engine continues to monitor the user's emotional state during this process, adaptively changing the content of the sign play patterns as needed.

[0939] Feedback function:

[0940] After the user practices the sign play patterns, they provide feedback to the system about their performance and emotional state, including specific ratings and comments, which are also sent to the server and stored in the database.

[0941] The server analyzes this feedback and emotional data and provides it to the generation AI. The generation AI then adjusts and updates the sign play patterns based on the feedback and emotional data, generating more effective patterns. This cyclical process not only allows users to improve their individual skills, but also enables them to play at a more advanced level that takes into account their emotional state and teamwork skills.

[0942] Examples:

[0943] For example, let's say the user is in a forward position. The user inputs skill data such as dribbling and speed and sends it to the server. The server receives and stores this data, and instructs the generation AI to generate new sign play patterns. The generation AI also takes into account the user's current emotional state and generates patterns such as effective movements in front of the goal and how to receive a pass.

[0944] Wearing the smart glasses, the user views the generated patterns and practices the movements according to the displayed instructions. The emotion engine monitors the user's emotional state during practice and adjusts the instructions as needed. After practice, the user provides feedback on their performance and emotional state to the system, which further refines and updates the sign play patterns.

[0945] In this way, by using this system, users can efficiently check and practice sign plays while taking their emotional state into consideration, which is expected to lead to greater skill improvement.

[0946] The processing flow will be explained below.

[0947] Step 1:

[0948] Users use devices such as smartphones and tablets to input their playing data (position, skill set, etc.).

[0949] Step 2:

[0950] The user transmits the input play data to the server.

[0951] Step 3:

[0952] The server stores the play data received from the user in a database.

[0953] Step 4:

[0954] The server instructs the generation AI to generate new sign play patterns based on the saved play data.

[0955] Step 5:

[0956] The generation AI generates optimal sign play patterns based on the play data received from the server.

[0957] Step 6:

[0958] The generated sign play pattern is sent back from the generation AI to the server, which stores it in a database.

[0959] Step 7:

[0960] The user starts up the device (smart glasses) and requests acquisition of a signature play pattern.

[0961] Step 8:

[0962] The server distributes the saved signature patterns to the device (smart glasses).

[0963] Step 9:

[0964] The device (smart glasses) visually displays the sign play pattern to the user.

[0965] Step 10:

[0966] The emotion engine analyzes the user's facial expressions and voice data in real time to recognize their emotional state, and the recognized emotional data is sent to the server.

[0967] Step 11:

[0968] The server stores the emotion data received from the emotion engine in a database.

[0969] Step 12:

[0970] The AI ​​optimizes sign play patterns based on the user's play data and emotional data. For example, if the user is nervous, it will provide a relaxing pattern, and if the user is concentrating, it will provide a more difficult pattern.

[0971] Step 13:

[0972] Users practice sign plays by following the instructions displayed on the smart glasses.

[0973] Step 14:

[0974] After practicing, the user provides feedback to the system about their performance and emotional state.

[0975] Step 15:

[0976] The server receives the feedback from the user and stores it in a database.

[0977] Step 16:

[0978] The server provides the stored feedback data and emotional data to the generation AI, instructing it to adjust and improve its sign play patterns.

[0979] Step 17:

[0980] Generative AI adjusts and updates sign-play patterns based on feedback and emotional data to generate more effective patterns.

[0981] Step 18:

[0982] The server re-distributes the updated sign play pattern to the device (smart glasses), allowing the user to practice again.

[0983] Example 2

[0984] 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."

[0985] Conventional training systems for team sports provide playing patterns without considering the user's emotional state, resulting in performance differences depending on the individual's physical condition and psychological state. Furthermore, they are unable to provide real-time feedback and reflect emotional data, making it difficult to effectively support the improvement of teamwork and individual skills. This reduces the efficiency of practice and prevents sufficient support for user growth.

[0986] 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.

[0987] In this invention, the server includes a means for receiving play data from users, a means for storing the received play data in a database, and an AI means for generating sign play patterns based on the play data and emotional data received in real time. This allows for the generation of play patterns that take the user's emotional state into account, providing practice tailored to each individual's condition. Furthermore, by modifying and generating sign play patterns based on feedback and emotional data, it is possible to effectively support the user's growth.

[0988] The "means for receiving play data from the user" is a communication interface for transmitting information about practice such as sports positions and skill sets entered by the user to the server.

[0989] The "means for storing received play data in a database" is a mechanism by which the server records play data sent from users in a storage device.

[0990] The "AI means for generating sign play patterns based on play data and emotional data received in real time" is an artificial intelligence engine that analyzes the user's practice data and emotional data and generates appropriate play patterns based on the results.

[0991] The "means for saving the generated sign play patterns and emotion data in a database" is a system for recording the generated sign play patterns and emotion data recognized by the emotion engine in a storage device.

[0992] The "means for providing the generation AI using play data and emotional data" is a communication interface that allows the server to transmit the stored play data and emotional data to the generation AI for analysis and pattern generation.

[0993] The "means for delivering the sign play pattern to the terminal" is a communication mechanism that allows the server to transmit the generated sign play pattern to the user's smart glasses or other display terminal.

[0994] "Displaying sign play patterns on smart glasses" refers to a function that displays the sign play patterns received by smart glasses from the server in a form that can be visually confirmed by the user.

[0995] The "means for receiving feedback from the user" is a communication interface for transmitting feedback information such as evaluations and emotions input by the user after practice to the server.

[0996] "AI means for storing received feedback in a database and modifying and generating sign play patterns based on the feedback and emotional data" refers to an artificial intelligence engine that records feedback data and emotional data in a storage device and generates more effective sign play patterns based on that data.

[0997] The "system" refers to a comprehensive mechanism that includes a server, user terminals (such as smart glasses), generative AI, emotion engine, and communication means for sending and receiving data between them.

[0998] This invention is a system for improving individual and team coordination skills in team sports, and in particular generates and adjusts play patterns taking into account the user's emotional state. This system is primarily composed of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[0999] server

[1000] The server stores the play data (position, skill set, etc.) received from the user in a database and provides it to the generation AI. The hardware used is server equipment with high-performance processing capabilities (brand names are not specified, but this includes commonly used cloud service servers).

[1001] The server issues instructions to the generation AI based on the play data, stores the generated sign play patterns in a database, and distributes them to devices as needed.

[1002] Terminal

[1003] Users use a smartphone or tablet to input their own play data, which is then sent to a server via the device. By wearing smart glasses, they can visually confirm the sign play patterns and practice based on them. For example, a user can use a smartphone app to input their position as "forward" and their skill set as "dribbling, speed," and then send the data. This data is then saved on the server.

[1004] Emotion Engine

[1005] The emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state in real time. Specifically, it is expected to use a facial recognition camera and voice analysis software. The emotion engine operates while the user is using the smart glasses, and transmits their emotional state during practice to the server in real time.

[1006] Generation AI

[1007] The generation AI combines play data and emotional data to generate sign play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will ease that tension, and conversely, if the user is concentrating, it will provide a more difficult pattern. The generated patterns are then sent back to the server. The AI ​​model used utilizes a common deep learning algorithm.

[1008] Specific examples

[1009] For example, consider the case where a user inputs "data on dribbling and speed for a forward position" and sends it to the server. The server receives and stores the play data, and then instructs the generation AI to generate a new sign play pattern based on that data.

[1010] The generative AI generates "patterns for effective movements in front of the goal and how to receive a pass," taking into account the user's current emotional state. As the user wears the smart glasses and practices movements based on the displayed sign play patterns, the emotion engine monitors the user's emotional state and adaptively changes the instructions as necessary.

[1011] Prompt Sentence Examples

[1012] Here are some example prompts to input to the AI ​​generator:

[1013] "The user's position is forward, and their skill set is focused on dribbling and speed. Their current emotional state is tense. Please generate a pattern of how they will receive a pass in front of the goal, taking this state into account."

[1014] "The user is a midfielder with good defensive skills. He is in a focused state. Please generate an appropriate passing pattern for this situation."

[1015] In this way, by using this system, users can efficiently understand practice patterns while taking into account their emotional state and achieve advanced play.

[1016] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1017] Step 1:

[1018] The user uses a smartphone or tablet to input their playing data. Specifically, the user inputs their position (e.g., forward) and skill set (e.g., dribbling, speed) through the application and presses the send button. This action sends the input data from the device to the server.

[1019] Input: Position and Skillset Data

[1020] Output: Play data sent to the server

[1021] Step 2:

[1022] The server stores the play data received from the user in a database. Specifically, the database management system converts the received data into an appropriate format and inserts it into the corresponding table in the database. Through this process, the user's play data is recorded in a form that can be stored for a long period of time.

[1023] Input: User's play data

[1024] Output: Play data stored in the database

[1025] Step 3:

[1026] The server provides the saved play data to the AI ​​generator. Specifically, the server acquires the play data and creates a prompt statement requesting the AI ​​generator to generate a new sign play pattern. The prompt statement includes the user's play data and their emotional state.

[1027] Input: Play data retrieved from the database

[1028] Output: The prompt sent to the generation AI

[1029] Step 4:

[1030] The generation AI generates sign play patterns based on play data and emotional data. Specifically, the generation AI analyzes the input data and generates play patterns that take the user's emotional state into account. For example, if the user is nervous, a pattern to relieve tension will be generated.

[1031] Input: Prompt sentence containing play data and emotion data

[1032] Output: Generated sign play pattern

[1033] Step 5:

[1034] The server stores the generated signature play patterns in a database. Specifically, the generated patterns are received by the server and stored in a corresponding table in the database. This allows the user's signature play patterns to be recorded in a form that can be referenced later.

[1035] Input: Sign play pattern returned from the generation AI

[1036] Output: Sign play patterns stored in the database

[1037] Step 6:

[1038] The user starts up the smart glasses and requests the acquisition of a sign play pattern. Specifically, the user opens the smart glasses application and sends a request to the server to acquire the sign play pattern. This request includes the user ID and session information.

[1039] Input: A get request containing the user ID and session information

[1040] Output: Request data sent to the server

[1041] Step 7:

[1042] The server distributes the generated sign play patterns to the device. Specifically, the server retrieves the corresponding sign play patterns from the database and sends them to the user's smart glasses. This process allows the user to obtain the necessary practice data in real time.

[1043] Input: Retrieval request, signature pattern in database

[1044] Output: Sign play pattern delivered to the terminal

[1045] Step 8:

[1046] The emotion engine recognizes and records the user's emotional state. Specifically, the camera and microphone built into the smart glasses capture the user's facial expressions and voice and send them to the emotion engine. The emotion engine analyzes this and sends the emotional data to the server.

[1047] Input: User's facial expression data, voice data

[1048] Output: Emotion data sent to the server

[1049] Step 9:

[1050] The user practices based on sign play patterns. Specifically, they practice movements and techniques by following instructions displayed on the smart glasses. The user's emotional state is continuously monitored by the emotion engine, and feedback is received from the server as needed.

[1051] Input: Sign play pattern displayed on smart glasses

[1052] Output: The exercise performed

[1053] Step 10:

[1054] Users provide feedback on their performance and emotional state to the system. Specifically, after practice, they use a smartphone or tablet to input their evaluations and comments about the effectiveness of the practice and their own emotional state, and send them to the server.

[1055] Input: Feedback information entered by the user

[1056] Output: Feedback data sent to the server

[1057] Step 11:

[1058] The server provides feedback to the generation AI to generate new patterns. Specifically, the server analyzes the saved feedback data and provides it to the generation AI, instructing it to generate new sign play patterns. The generation AI then uses this data to generate more effective play patterns.

[1059] Input: Feedback data, existing emotion data

[1060] Output: The new sign play pattern generated

[1061] By repeating the above steps, the optimal practice is provided according to the user's playing style and emotional state.

[1062] (Application example 2)

[1063] 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."

[1064] In conventional team sports practice, it is difficult to provide appropriate feedback and guidance to improve individual and team coordination skills. Furthermore, there is no system that provides optimal training methods based on the user's emotional state, making it difficult to maximize the user's motivation and concentration. Furthermore, in virtual stores, it is necessary to provide an optimal experience while taking into account the emotional states of both store staff and customers, but current systems have difficulty achieving this.

[1065] 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 play data from the user, means for saving the received play data in a database, AI means for generating sign play patterns based on the saved play data and the user's emotional data, means for saving the generated sign play patterns in a database, means for distributing the sign play patterns to the terminal, means for monitoring the emotional data of the user and others in real time, and means for adaptively adjusting the sign play patterns based on the monitored emotional data. This makes it possible to provide appropriate and effective feedback and guidance taking into account the user's emotional state. Furthermore, in virtual stores, customer satisfaction can be improved by proposing and adjusting optimal customer service methods in real time based on the emotional states of store staff and customers.

[1066] "Users" refers to people who use the system to provide play data and emotional data.

[1067] "Play data" refers to data such as sports positions and skill sets entered by the user.

[1068] "Database" refers to a digital storage system for storing play data, emotional data, and generated sign play patterns.

[1069] "Emotion data" refers to information about the emotional state obtained by analyzing facial expressions and voice data of the user and other people.

[1070] A "signature play pattern" refers to a pattern that is generated based on the user's play data and emotion data and that instructs a specific play or movement.

[1071] "AI means" refers to technology that uses artificial intelligence to analyze data and generate and modify sign play patterns.

[1072] "Terminal" refers to a device such as smart glasses worn by a user, which is used to display sign play patterns.

[1073] "Monitoring means" refers to technology that observes and collects emotional data of users and others in real time.

[1074] "Adaptive adjustment means" refers to technology that changes sign-play patterns in real time based on monitored emotional data.

[1075] "Feedback" refers to ratings and comments about performance and emotional state provided by users and others after using the system.

[1076] This invention is a system for improving the cooperative skills of individuals and teams, and in particular, by combining an emotion engine, it generates and adjusts play patterns taking into account the user's emotional state. This system mainly consists of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[1077] User operations

[1078] Users use devices such as smartphones or tablets to input their playing data (position, skill set, etc.). This data is sent to a server via the terminal. By wearing the smart glasses, players can practice based on the displayed sign play patterns. An emotion engine is built into the smart glasses and recognizes the user's emotional state by analyzing their facial expressions and voice data in real time.

[1079] Server Processing

[1080] The server stores the play data received from the user in a database and provides it to the generation AI. The generation AI generates sign play patterns based on this data and sends the generated patterns back to the server. The server then stores the generated sign play patterns in a database and distributes them to devices as needed.

[1081] Emotion Engine Functions

[1082] The emotion engine analyzes the user's facial expressions, voice data, and other data to recognize their emotional state in real time. The recognized emotional data is sent to a server and stored in a database. The generation AI combines play data and emotional data to generate sign play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will relieve that tension, and if the user is concentrating, it will provide a more difficult pattern.

[1083] The role of smart glasses

[1084] When a user activates the smart glasses, a request is made to acquire sign play patterns from the server. The server then transmits the generated patterns to the device, and the smart glasses visually display them to the user. The emotion engine continues to monitor the user's emotional state during this process, adaptively changing the content of the sign play patterns as needed.

[1085] Feedback function

[1086] After a user practices a sign play pattern, they provide feedback to the system about their performance and emotional state. The feedback includes specific evaluations and comments, and is sent to the server and stored in a database. The server analyzes this feedback data and emotional data and provides it to the generation AI. The generation AI adjusts and updates the sign play pattern based on the feedback and emotional data, generating a more effective pattern.

[1087] Specific examples

[1088] For example, if the user is a sales clerk serving customers at a virtual store, the sales clerk can send their play data along with their own emotional data to the system. Based on this, the generation AI will suggest ways to serve customers that will help them relax. At the same time, the system will also recognize customer emotional data in real time and suggest ways to serve customers that will help them relax. Below are some example prompts for the generation AI.

[1089] "If a sales associate is smiling at a customer but appears nervous, generate a service suggestion to help the customer relax. Or, if a customer appears angry, recommend instructions to the sales associate to deal with the situation calmly."

[1090] In this way, by using this system, it is possible to efficiently confirm and execute sign plays and customer service methods while taking into account the user's emotional state, which is expected to lead to greater skill development and improved customer satisfaction.

[1091] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1092] Step 1:

[1093] Users use their smartphones or tablets to input their playing data (position, skill set, etc.). The playing data includes information such as the user's practice status and technical skills. This data is sent to the server via the device. The input data is accurately stored in a database and processed into a form that can be used for subsequent processing.

[1094] Step 2:

[1095] The server stores the play data received from the user in a database. Specifically, the server analyzes the received data, divides it into fields, and stores the data in a database table.

[1096] Step 3:

[1097] The server provides the saved play data to the generation AI. The generation AI then runs an algorithm based on this data to generate the user's play patterns. Based on the input data, it generates sign play patterns using various parameters and sends the results back to the server. Here, the generation AI model generates play patterns while also taking emotional data into account.

[1098] Step 4:

[1099] The emotion engine is built into the smart glasses and analyzes the user's facial expressions and voice data in real time. Data analysis is performed to recognize the user's emotional state, and the results are sent to the server. At the same time, the results are saved in a database as play data.

[1100] Step 5:

[1101] The server stores the emotion data sent by the emotion engine and the sign play patterns generated by the generation AI in a database, so that the next time the user retrieves a sign play pattern, they will receive a pattern based on the latest state.

[1102] Step 6:

[1103] When a user starts up their smart glasses, they request the latest sign play patterns from the server. The server searches for the latest patterns stored in the database and delivers them to the device. The smart glasses then visually display the received sign play patterns to the user.

[1104] Step 7:

[1105] The smart glasses continuously monitor the user's emotional state and adjust the sign play patterns as needed. Emotional data is updated in real time and sent to the server. Based on this new data, the regenerative AI adaptively adjusts the play patterns.

[1106] Step 8:

[1107] After the user practices the sign-play pattern, they provide feedback to the system regarding their performance and emotional state. Specifically, the user inputs the feedback through the smart glasses, and the data is sent to the server.

[1108] Step 9:

[1109] The server stores the received feedback in a database. After storing it, it analyzes the feedback data and emotion data and provides the results to the generation AI. Based on this, the generation AI adjusts and updates the sign play pattern to generate a more effective pattern. The results are then returned to the server.

[1110] Step 10:

[1111] The server stores the updated patterns in a database and distributes them to the terminal, allowing the user to always use the latest and most optimal sign play patterns for practice or service provision.

[1112] 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.

[1113] 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.

[1114] 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.

[1115] [Fourth embodiment]

[1116] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1117] 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.

[1118] 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).

[1119] 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.

[1120] 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.

[1121] 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).

[1122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1123] 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.

[1124] 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.

[1125] 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.

[1126] 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.

[1127] 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.

[1128] 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."

[1129] This invention is a system for improving individual and team coordination skills in team sports. This system mainly consists of a server, a device worn by the user (smart glasses), and a generation AI.

[1130] User:

[1131] First, a user inputs their playing data (e.g., position, skill set, etc.) through the system interface. This data is input using a device such as a smartphone or tablet and sent to the server.

[1132] server:

[1133] The server stores the play data received from users in a database. The stored data is organized for each individual user. The server then issues instructions to the generation AI based on the stored play data to generate new sign play patterns.

[1134] The generation AI receives the user's play data and uses a specific algorithm to generate optimal sign play patterns. This AI is designed to evolve based on past data and feedback, providing highly accurate patterns tailored to the user's needs. The generated sign play patterns are sent back to the server and stored in a database.

[1135] Device:

[1136] The device, specifically the smart glasses, accesses the server to acquire the generated sign play patterns, which are then displayed to the user in real time, allowing the user to practice sign plays privately by following the displayed instructions.

[1137] Feedback function:

[1138] After the user practices based on the sign play patterns, they provide feedback on their performance to the system, including specific evaluations and comments. This feedback data is also sent to the server and stored in the database.

[1139] The server analyzes this feedback data and provides it to the generation AI, which then adjusts and updates the sign play patterns based on the feedback, generating more effective patterns. This cyclical process allows users to continually improve their skills and contributes to the discovery of new teamwork.

[1140] Examples:

[1141] For example, let's say the user is in a forward position. The user inputs skill data such as dribbling and speed and sends it to the server. The server receives this data and instructs the generation AI to generate new sign play patterns. The generation AI generates patterns such as effective movements in front of the goal and how to receive a pass, and sends them back to the server.

[1142] The user wearing the smart glasses checks the generated patterns and follows the instructions to practice the movements. The results of the practice are then input into the system as feedback to help improve the sign play patterns.

[1143] In this way, by using this system, users can not only improve their individual skills, but also strengthen their collaborative skills as part of a team.

[1144] The processing flow will be explained below.

[1145] Step 1:

[1146] Users use devices such as smartphones and tablets to input their playing data (position, skill set, etc.).

[1147] Step 2:

[1148] The user transmits the input play data to the server.

[1149] Step 3:

[1150] The server stores the play data received from the user in a database.

[1151] Step 4:

[1152] The server instructs the generation AI to generate new sign play patterns based on the saved play data.

[1153] Step 5:

[1154] The generation AI generates optimal sign play patterns based on the play data received from the server.

[1155] Step 6:

[1156] The generated sign play pattern is sent back from the generation AI to the server, which stores it in a database.

[1157] Step 7:

[1158] The user starts up the device (smart glasses) and requests acquisition of a signature play pattern.

[1159] Step 8:

[1160] The server distributes the saved signature patterns to the device (smart glasses).

[1161] Step 9:

[1162] The device (smart glasses) visually displays the sign play pattern to the user.

[1163] Step 10:

[1164] Users practice sign plays by following the instructions displayed on the smart glasses.

[1165] Step 11:

[1166] After practicing, the user provides feedback on their performance to the system.

[1167] Step 12:

[1168] The server receives the feedback from the user and stores it in a database.

[1169] Step 13:

[1170] The server provides the stored feedback data to the generation AI.

[1171] Step 14:

[1172] The generative AI adjusts and updates sign play patterns based on feedback, generating more effective patterns.

[1173] Example 1

[1174] 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."

[1175] In traditional team sports, improving individual and team coordination skills has relied primarily on individual experience and coaching, making efficient training difficult. It has also been difficult to provide individualized training methods that take into account each player's characteristics and skills, and there has been a lack of adaptive training programs based on feedback. Furthermore, it has been impossible to provide real-time training instructions.

[1176] 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.

[1177] In this invention, the server includes means for receiving play data from users, means for saving the received play data in a database, a generation AI model means for generating new sign play patterns based on the saved play data, means for saving the generated sign play patterns in a database, means for distributing the sign play patterns to the terminal, means for receiving feedback from users and saving it in a database, and a generation AI model means for adjusting and updating the sign play patterns based on the feedback. This makes it possible to generate optimal sign play patterns based on the characteristics of each player and provide instructions in real time. Furthermore, by continuously improving the sign play patterns based on the feedback, it is possible to efficiently improve skills and strengthen team cooperation.

[1178] "Means for receiving play data from a user" refers to a device or software that allows the server to receive information such as the position and skill set entered by the user.

[1179] "Means for storing received play data in a database" refers to a device or software that has the function of storing information received from users in a database for systematic management by the server.

[1180] "Generative AI model means" refers to an artificial intelligence system that generates new sign play patterns using a specific algorithm based on given data.

[1181] "Means for delivering sign play patterns to a terminal" refers to a device or software with network communication capabilities for transmitting the generated sign play patterns to a terminal, specifically to smart glasses, etc.

[1182] "Means for receiving feedback from users" refers to a device or software that allows the server to receive evaluations and comments entered by users after practicing.

[1183] "Means for storing feedback in a database" refers to a device or software that has the function of storing received feedback in a database for systematic management.

[1184] "Generative AI model means for adjusting and updating sign play patterns" refers to an artificial intelligence system that adaptively changes existing sign play patterns based on received feedback and updates them to more effective patterns.

[1185] "Smart glasses" refers to a wearable device that users can wear to obtain visual information in real time.

[1186] "Database" refers to a data management system for storing, managing, and searching user play data and feedback data.

[1187] This invention is a system for improving individual and team coordination skills in team sports. The system mainly consists of a server, a device worn by the user (smart glasses), and a generative AI model.

[1188] User

[1189] First, a user accesses the system interface using a device such as a smartphone or tablet. The user inputs their playing data (e.g., position, skill set, etc.). This data might be, for example, "I'm a forward and I'm good at dribbling." The input data is then sent to the server.

[1190] server

[1191] The server receives play data sent by users. The received data is stored in a database and organized by user. The server then instructs the generative AI model to generate new sign play patterns based on the stored play data. The generative AI model uses a specific algorithm to generate optimal sign play patterns. This AI is designed to evolve based on past data and feedback.

[1192] The generated sign play patterns are sent back to the server and stored in the database. For example, the instructions to the generative AI model might include a prompt like this: "User's position: forward. Skill set: dribbling, speed. Based on this, please generate the optimal sign play pattern."

[1193] Terminal

[1194] The device, specifically the smart glasses, periodically accesses the server to obtain the latest sign play patterns. These patterns are displayed to the user in real time. The user can then follow the instructions displayed on the smart glasses to practice sign plays individually. For example, the smart glasses may display instructions such as "break through the right side and shoot in front of the goal."

[1195] Feedback function

[1196] After the user practices using the sign play pattern, they provide feedback on their performance to the system. The feedback includes specific evaluations and comments, such as, "This dribbling pattern was performed smoothly." This feedback data is also sent to the server and stored in a database. The server analyzes the feedback data and provides the results to the generative AI model. The generative AI model adjusts and updates the sign play pattern based on the feedback, generating a more effective pattern. This cyclical process allows users to continuously improve their skills and also contributes to the discovery of new teamwork plays.

[1197] Specific examples

[1198] For example, let's say the user is in a forward position. The user inputs skill data such as "dribbling and speed" and sends it to the server. The server receives this data and instructs the generative AI model to generate new sign play patterns. The generative AI model generates patterns such as "effective movements in front of the goal" and "how to receive a pass" and sends them back to the server.

[1199] Wearing the smart glasses, the user checks the generated pattern and practices the movement by following the instruction, "Dribble to the right, then cut back to the left." The results of the practice are then input into the system as feedback, such as "Today's sign play was 70 points. The accuracy of the shot was low," which is used to improve the sign play pattern. In this way, by using this system, users can not only improve their individual skills, but also strengthen their teamwork skills as part of a team.

[1200] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1201] Step 1:

[1202] Input: Users access the system interface using a smartphone or tablet.

[1203] Process: User inputs their position and skill set (e.g. forward, dribbling, speed).

[1204] Output: The input data is sent to the server.

[1205] Specific operations: The user enters information such as "forward," "dribble," and "speed" into the form displayed on the smartphone screen and presses the submit button.

[1206] Step 2:

[1207] Input: The server receives play data sent by the user.

[1208] Processing: The received play data is stored in a database. The stored data is organized by user.

[1209] Output: Play data is saved in the database.

[1210] Specific operation: To store data from different users separately, the server assigns each user a unique ID and stores the data associated with it.

[1211] Step 3:

[1212] Input: The server instructs the generation AI model to generate new sign play patterns based on saved play data.

[1213] Processing: The instructions include a prompt statement that includes the user's position and skill set, and is passed to the generative AI model (e.g., "Generate the optimal sign play pattern based on forward, dribbling, and speed").

[1214] Output: Instructions to generate new sign play patterns are sent to the generative AI model.

[1215] Specific operation: The server generates a prompt sentence and provides it to the generative AI model.

[1216] Step 4:

[1217] Input: The generative AI model receives a prompt.

[1218] Processing: Generates sign-play patterns using an internal algorithm. The generative AI model takes into account past data and feedback to generate detailed sign-play patterns, such as "break through on the right side and shoot."

[1219] Output: The generated signature pattern is sent back to the server.

[1220] Specific operation: The generative AI model generates new sign play patterns based on the prompt sentence and sends the results to the server.

[1221] Step 5:

[1222] Input: The generated signature pattern arrives at the server.

[1223] Processing: The server stores the generated signature play pattern in a database.

[1224] Output: Sign play patterns are stored in a database.

[1225] Specific operation: The server checks the returned data, organizes it for each user, and stores it.

[1226] Step 6:

[1227] Input: The device (smart glasses) periodically accesses the server.

[1228] Processing: Get the latest sign play pattern.

[1229] Output: The acquired signature pattern is displayed on the smart glasses.

[1230] Specific operation: The smart glasses download the latest patterns from the server and display instructions to the user in real time, such as "break through the right side and shoot in front of the goal."

[1231] Step 7:

[1232] Input: The user practices by following the sign play patterns displayed on the smart glasses.

[1233] Processing: Performing an action according to instructions.

[1234] Output: User practice results.

[1235] Specific actions: The user follows the displayed instructions to perform the actions on the field and actually practice the play.

[1236] Step 8:

[1237] Input: After practicing, the user provides feedback to the system.

[1238] Processing: Feedback includes specific evaluations and comments (e.g., "That dribble pattern was smooth").

[1239] Output: The feedback data is sent to the server.

[1240] Specific operation: The user inputs feedback from their smartphone and sends it to the server.

[1241] Step 9:

[1242] Input: The server receives feedback from the user.

[1243] Processing: The received feedback is stored in a database and analyzed.

[1244] Output: Feedback data is stored in a database.

[1245] Specific operation: The server analyzes the feedback data and accumulates ratings for each user.

[1246] Step 10:

[1247] Input: The server provides the analysis results to the generative AI model.

[1248] Processing: Adjust and update sign play patterns based on feedback.

[1249] Output: The adjusted and updated signature pattern is generated.

[1250] Specific operation: The generative AI model generates new patterns based on the feedback and provides them to the server.

[1251] Through this series of steps, the system can provide optimal sign play patterns based on the user's characteristics and feedback, helping them improve their skills and strengthen teamwork.

[1252] (Application example 1)

[1253] 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."

[1254] Traditional training methods for improving staff collaboration skills in brick-and-mortar stores often require manual feedback and time-consuming training, making them inefficient. It's also difficult to provide optimal training methods tailored to individual staff members' skill levels and roles, making it challenging to improve teamwork. Furthermore, there's no system for reflecting training results in real time, making continuous skill improvement difficult.

[1255] 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.

[1256] In this invention, the server includes means for receiving play data from users, means for saving the received play data in a database, AI means for generating movement patterns based on the saved play data, means for saving the generated movement patterns in the database, and means for delivering the movement patterns to terminals. This makes it possible to generate optimal movement patterns based on the skill sets and feedback of individual staff members and provide them to staff members in real time.

[1257] "Play data" is information about a user's role and skill set that the user inputs into the system.

[1258] The "database" is a system for storing and managing received play data, generated movement patterns, and feedback data.

[1259] "Movement patterns" are optimal work procedures and movement instructions generated by AI means based on the user's role and skills.

[1260] "AI means" refers to a system that uses artificial intelligence technology to generate optimal movement patterns based on received play data and feedback data.

[1261] A "terminal" is a device that can display movement patterns or smart glasses worn by the user.

[1262] "Feedback" is information about performance and areas for improvement that a user provides to the system after performing a task based on their behavioral patterns.

[1263] The "distribution means" is a system for transferring the generated motion patterns from the server to the user's terminal.

[1264] server

[1265] The server receives play data entered by the user using a smartphone or tablet. The play data is information about the user's role and skill set, and the server stores this data in a database. The stored play data is analyzed by AI means to generate optimal movement patterns. A generative AI model (e.g., OpenAI GPT-4) is used. The movement patterns generated in this process are again stored in the database.

[1266] Terminal

[1267] The devices are primarily smart glasses, which access a server to acquire the generated movement patterns. The smart glasses then display the acquired movement patterns to the user in real time, allowing the user to visually check them as they work. This display function allows each staff member to practice the optimal movements for their role.

[1268] User

[1269] The user performs their work by following the movement patterns delivered from the server, checking their movements in real time through smart glasses. After completing the work, the user enters feedback into the system. Feedback is information about performance and areas for improvement provided by the user after performing a task based on the movement patterns. This feedback data is also sent to the server and stored in a database. The server analyzes this feedback data and provides it to the generation AI. The generation AI adjusts and updates the movement patterns based on the feedback, generating more effective patterns. This cyclical process allows the user to continuously improve their skills.

[1270] Specific examples

[1271] For example, let's say a staff member needs to learn how to display a new product. The staff member wears smart glasses and works while viewing the optimal display pattern generated by the AI ​​in real time. The staff member then inputs the results of their work into the system as feedback. Based on this feedback, the AI ​​can refine the pattern for the next time.

[1272] Prompt Sentence Examples

[1273] Below is an example of a prompt to send to the generated AI.

[1274] text

[1275] Please generate movement patterns for staff to optimally display new products. The following information is available as staff skill data.

[1276] Role: Product display

[1277] Skills: Basic product placement and inventory management

[1278] Additional Information: Display space in stores is limited.

[1279] The generated patterns should include how to position products, proper flow of traffic, and when to use necessary tools.

[1280] In this way, the system of the present invention provides an effective training method for improving staff collaboration skills in brick-and-mortar stores and increasing work efficiency.

[1281] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1282] Step 1:

[1283] The server receives "play data" entered by the user using a smartphone or tablet. The play data includes information about the user's role and skill set. The entered play data is saved in a database by the server. This allows the user's skill set to be accumulated in the database.

[1284] Step 2:

[1285] The server generates "movement patterns" by sending prompts to the generative AI based on the play data stored in the database. The generative AI model (e.g., OpenAI GPT-4) creates optimal movement patterns based on past data and predefined algorithms. These movement patterns are specific work procedures that correspond to the user's role and skills. The generated movement patterns are then stored back in the database by the server.

[1286] Step 3:

[1287] The device, specifically the smart glasses, accesses the server to acquire the generated movement patterns. The smart glasses display the movement patterns to the user in real time, allowing the user to visually confirm the patterns as they work. This allows the user to perform the operations efficiently by following the instructions.

[1288] Step 4:

[1289] The user performs a task according to the action pattern and inputs the results into the system as feedback. The feedback includes information about task performance and areas for improvement. The feedback data is sent to the server and stored in a database. This allows the user's actual work results to be recorded in the system.

[1290] Step 5:

[1291] The server analyzes the feedback data and sends prompts to the AI ​​generator based on this data. The AI ​​generator takes the feedback into account and adjusts and updates the next movement pattern to generate a more effective and accurate movement pattern, thereby achieving continuous skill improvement.

[1292] 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.

[1293] This invention is a system for improving the coordination skills of individuals and teams in team sports, and in particular, by combining an emotion engine, it generates and adjusts play patterns taking into account the user's emotional state. This system mainly consists of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[1294] User:

[1295] Users input their playing data (position, skill set, etc.) using a device such as a smartphone or tablet. This data is sent to the server via the device. By wearing the smart glasses, the user can practice based on the displayed sign play patterns.

[1296] server:

[1297] The server stores the play data received from the user in a database and provides it to the generation AI. The generation AI generates sign play patterns based on this data and sends the generated patterns back to the server. The server then stores the generated sign play patterns in a database and distributes them to devices as needed.

[1298] Emotion Engine:

[1299] The emotion engine recognizes the user's emotional state in real time by analyzing facial expressions, voice data, etc. The emotion data recognized by the emotion engine is sent to the server and stored in a database.

[1300] Generation AI:

[1301] The AI ​​combines play data and emotional data to generate signature play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will ease that tension, and if the user is concentrating, it will provide a more difficult pattern. The generated patterns are then sent back to the server.

[1302] Device:

[1303] When a user activates the smart glasses, a request is made to acquire sign play patterns from the server. The server then transmits the generated patterns to the device, and the smart glasses visually display them to the user. The emotion engine continues to monitor the user's emotional state during this process, adaptively changing the content of the sign play patterns as needed.

[1304] Feedback function:

[1305] After the user practices the sign play patterns, they provide feedback to the system about their performance and emotional state, including specific ratings and comments, which are also sent to the server and stored in the database.

[1306] The server analyzes this feedback and emotional data and provides it to the generation AI. The generation AI then adjusts and updates the sign play patterns based on the feedback and emotional data, generating more effective patterns. This cyclical process not only allows users to improve their individual skills, but also enables them to play at a more advanced level that takes into account their emotional state and teamwork skills.

[1307] Examples:

[1308] For example, let's say the user is in a forward position. The user inputs skill data such as dribbling and speed and sends it to the server. The server receives and stores this data, and instructs the generation AI to generate new sign play patterns. The generation AI also takes into account the user's current emotional state and generates patterns such as effective movements in front of the goal and how to receive a pass.

[1309] Wearing the smart glasses, the user views the generated patterns and practices the movements according to the displayed instructions. The emotion engine monitors the user's emotional state during practice and adjusts the instructions as needed. After practice, the user provides feedback on their performance and emotional state to the system, which further refines and updates the sign play patterns.

[1310] In this way, by using this system, users can efficiently check and practice sign plays while taking their emotional state into consideration, which is expected to lead to greater skill improvement.

[1311] The processing flow will be explained below.

[1312] Step 1:

[1313] Users use devices such as smartphones and tablets to input their playing data (position, skill set, etc.).

[1314] Step 2:

[1315] The user transmits the input play data to the server.

[1316] Step 3:

[1317] The server stores the play data received from the user in a database.

[1318] Step 4:

[1319] The server instructs the generation AI to generate new sign play patterns based on the saved play data.

[1320] Step 5:

[1321] The generation AI generates optimal sign play patterns based on the play data received from the server.

[1322] Step 6:

[1323] The generated sign play pattern is sent back from the generation AI to the server, which stores it in a database.

[1324] Step 7:

[1325] The user starts up the device (smart glasses) and requests acquisition of a signature play pattern.

[1326] Step 8:

[1327] The server distributes the saved signature patterns to the device (smart glasses).

[1328] Step 9:

[1329] The device (smart glasses) visually displays the sign play pattern to the user.

[1330] Step 10:

[1331] The emotion engine analyzes the user's facial expressions and voice data in real time to recognize their emotional state, and the recognized emotional data is sent to the server.

[1332] Step 11:

[1333] The server stores the emotion data received from the emotion engine in a database.

[1334] Step 12:

[1335] The AI ​​optimizes sign play patterns based on the user's play data and emotional data. For example, if the user is nervous, it will provide a relaxing pattern, and if the user is concentrating, it will provide a more difficult pattern.

[1336] Step 13:

[1337] Users practice sign plays by following the instructions displayed on the smart glasses.

[1338] Step 14:

[1339] After practicing, the user provides feedback to the system about their performance and emotional state.

[1340] Step 15:

[1341] The server receives the feedback from the user and stores it in a database.

[1342] Step 16:

[1343] The server provides the stored feedback data and emotional data to the generation AI, instructing it to adjust and improve its sign play patterns.

[1344] Step 17:

[1345] Generative AI adjusts and updates sign-play patterns based on feedback and emotional data to generate more effective patterns.

[1346] Step 18:

[1347] The server re-distributes the updated sign play pattern to the device (smart glasses), allowing the user to practice again.

[1348] Example 2

[1349] 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."

[1350] Conventional training systems for team sports provide playing patterns without considering the user's emotional state, resulting in performance differences depending on the individual's physical condition and psychological state. Furthermore, they are unable to provide real-time feedback and reflect emotional data, making it difficult to effectively support the improvement of teamwork and individual skills. This reduces the efficiency of practice and prevents sufficient support for user growth.

[1351] 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.

[1352] In this invention, the server includes a means for receiving play data from users, a means for storing the received play data in a database, and an AI means for generating sign play patterns based on the play data and emotional data received in real time. This allows for the generation of play patterns that take the user's emotional state into account, providing practice tailored to each individual's condition. Furthermore, by modifying and generating sign play patterns based on feedback and emotional data, it is possible to effectively support the user's growth.

[1353] The "means for receiving play data from the user" is a communication interface for transmitting information about practice such as sports positions and skill sets entered by the user to the server.

[1354] The "means for storing received play data in a database" is a mechanism by which the server records play data sent from users in a storage device.

[1355] The "AI means for generating sign play patterns based on play data and emotional data received in real time" is an artificial intelligence engine that analyzes the user's practice data and emotional data and generates appropriate play patterns based on the results.

[1356] The "means for saving the generated sign play patterns and emotion data in a database" is a system for recording the generated sign play patterns and emotion data recognized by the emotion engine in a storage device.

[1357] The "means for providing the generation AI using play data and emotional data" is a communication interface that allows the server to transmit the stored play data and emotional data to the generation AI for analysis and pattern generation.

[1358] The "means for delivering the sign play pattern to the terminal" is a communication mechanism that allows the server to transmit the generated sign play pattern to the user's smart glasses or other display terminal.

[1359] "Displaying sign play patterns on smart glasses" refers to a function that displays the sign play patterns received by smart glasses from the server in a form that can be visually confirmed by the user.

[1360] The "means for receiving feedback from the user" is a communication interface for transmitting feedback information such as evaluations and emotions input by the user after practice to the server.

[1361] "AI means for storing received feedback in a database and modifying and generating sign play patterns based on the feedback and emotional data" refers to an artificial intelligence engine that records feedback data and emotional data in a storage device and generates more effective sign play patterns based on that data.

[1362] The "system" refers to a comprehensive mechanism that includes a server, user terminals (such as smart glasses), generative AI, emotion engine, and communication means for sending and receiving data between them.

[1363] This invention is a system for improving individual and team coordination skills in team sports, and in particular generates and adjusts play patterns taking into account the user's emotional state. This system is primarily composed of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[1364] server

[1365] The server stores the play data (position, skill set, etc.) received from the user in a database and provides it to the generation AI. The hardware used is server equipment with high-performance processing capabilities (brand names are not specified, but this includes commonly used cloud service servers).

[1366] The server issues instructions to the generation AI based on the play data, stores the generated sign play patterns in a database, and distributes them to devices as needed.

[1367] Terminal

[1368] Users use a smartphone or tablet to input their own play data, which is then sent to a server via the device. By wearing smart glasses, they can visually confirm the sign play patterns and practice based on them. For example, a user can use a smartphone app to input their position as "forward" and their skill set as "dribbling, speed," and then send the data. This data is then saved on the server.

[1369] Emotion Engine

[1370] The emotion engine analyzes the user's facial expressions and voice data to recognize their emotional state in real time. Specifically, it is expected to use a facial recognition camera and voice analysis software. The emotion engine operates while the user is using the smart glasses, and transmits their emotional state during practice to the server in real time.

[1371] Generation AI

[1372] The generation AI combines play data and emotional data to generate sign play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will ease that tension, and conversely, if the user is concentrating, it will provide a more difficult pattern. The generated patterns are then sent back to the server. The AI ​​model used utilizes a common deep learning algorithm.

[1373] Specific examples

[1374] For example, consider the case where a user inputs "data on dribbling and speed for a forward position" and sends it to the server. The server receives and stores the play data, and then instructs the generation AI to generate a new sign play pattern based on that data.

[1375] The generative AI generates "patterns for effective movements in front of the goal and how to receive a pass," taking into account the user's current emotional state. As the user wears the smart glasses and practices movements based on the displayed sign play patterns, the emotion engine monitors the user's emotional state and adaptively changes the instructions as necessary.

[1376] Prompt Sentence Examples

[1377] Here are some example prompts to input to the AI ​​generator:

[1378] "The user's position is forward, and their skill set is focused on dribbling and speed. Their current emotional state is tense. Please generate a pattern of how they will receive a pass in front of the goal, taking this state into account."

[1379] "The user is a midfielder with good defensive skills. He is in a focused state. Please generate an appropriate passing pattern for this situation."

[1380] In this way, by using this system, users can efficiently understand practice patterns while taking into account their emotional state and achieve advanced play.

[1381] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1382] Step 1:

[1383] The user uses a smartphone or tablet to input their playing data. Specifically, the user inputs their position (e.g., forward) and skill set (e.g., dribbling, speed) through the application and presses the send button. This action sends the input data from the device to the server.

[1384] Input: Position and Skillset Data

[1385] Output: Play data sent to the server

[1386] Step 2:

[1387] The server stores the play data received from the user in a database. Specifically, the database management system converts the received data into an appropriate format and inserts it into the corresponding table in the database. Through this process, the user's play data is recorded in a form that can be stored for a long period of time.

[1388] Input: User's play data

[1389] Output: Play data stored in the database

[1390] Step 3:

[1391] The server provides the saved play data to the AI ​​generator. Specifically, the server acquires the play data and creates a prompt statement requesting the AI ​​generator to generate a new sign play pattern. The prompt statement includes the user's play data and their emotional state.

[1392] Input: Play data retrieved from the database

[1393] Output: The prompt sent to the generation AI

[1394] Step 4:

[1395] The generation AI generates sign play patterns based on play data and emotional data. Specifically, the generation AI analyzes the input data and generates play patterns that take the user's emotional state into account. For example, if the user is nervous, a pattern to relieve tension will be generated.

[1396] Input: Prompt sentence containing play data and emotion data

[1397] Output: Generated sign play pattern

[1398] Step 5:

[1399] The server stores the generated signature play patterns in a database. Specifically, the generated patterns are received by the server and stored in a corresponding table in the database. This allows the user's signature play patterns to be recorded in a form that can be referenced later.

[1400] Input: Sign play pattern returned from the generation AI

[1401] Output: Sign play patterns stored in the database

[1402] Step 6:

[1403] The user starts up the smart glasses and requests the acquisition of a sign play pattern. Specifically, the user opens the smart glasses application and sends a request to the server to acquire the sign play pattern. This request includes the user ID and session information.

[1404] Input: A get request containing the user ID and session information

[1405] Output: Request data sent to the server

[1406] Step 7:

[1407] The server distributes the generated sign play patterns to the device. Specifically, the server retrieves the corresponding sign play patterns from the database and sends them to the user's smart glasses. This process allows the user to obtain the necessary practice data in real time.

[1408] Input: Retrieval request, signature pattern in database

[1409] Output: Sign play pattern delivered to the terminal

[1410] Step 8:

[1411] The emotion engine recognizes and records the user's emotional state. Specifically, the camera and microphone built into the smart glasses capture the user's facial expressions and voice and send them to the emotion engine. The emotion engine analyzes this and sends the emotional data to the server.

[1412] Input: User's facial expression data, voice data

[1413] Output: Emotion data sent to the server

[1414] Step 9:

[1415] The user practices based on sign play patterns. Specifically, they practice movements and techniques by following instructions displayed on the smart glasses. The user's emotional state is continuously monitored by the emotion engine, and feedback is received from the server as needed.

[1416] Input: Sign play pattern displayed on smart glasses

[1417] Output: The exercise performed

[1418] Step 10:

[1419] Users provide feedback on their performance and emotional state to the system. Specifically, after practice, they use a smartphone or tablet to input their evaluations and comments about the effectiveness of the practice and their own emotional state, and send them to the server.

[1420] Input: Feedback information entered by the user

[1421] Output: Feedback data sent to the server

[1422] Step 11:

[1423] The server provides feedback to the generation AI to generate new patterns. Specifically, the server analyzes the saved feedback data and provides it to the generation AI, instructing it to generate new sign play patterns. The generation AI then uses this data to generate more effective play patterns.

[1424] Input: Feedback data, existing emotion data

[1425] Output: The new sign play pattern generated

[1426] By repeating the above steps, the optimal practice is provided according to the user's playing style and emotional state.

[1427] (Application example 2)

[1428] 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."

[1429] In conventional team sports practice, it is difficult to provide appropriate feedback and guidance to improve individual and team coordination skills. Furthermore, there is no system that provides optimal training methods based on the user's emotional state, making it difficult to maximize the user's motivation and concentration. Furthermore, in virtual stores, it is necessary to provide an optimal experience while taking into account the emotional states of both store staff and customers, but current systems have difficulty achieving this.

[1430] 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 play data from the user, means for saving the received play data in a database, AI means for generating sign play patterns based on the saved play data and the user's emotional data, means for saving the generated sign play patterns in a database, means for distributing the sign play patterns to the terminal, means for monitoring the emotional data of the user and others in real time, and means for adaptively adjusting the sign play patterns based on the monitored emotional data. This makes it possible to provide appropriate and effective feedback and guidance taking into account the user's emotional state. Furthermore, in virtual stores, customer satisfaction can be improved by proposing and adjusting optimal customer service methods in real time based on the emotional states of store staff and customers.

[1431] "Users" refers to people who use the system to provide play data and emotional data.

[1432] "Play data" refers to data such as sports positions and skill sets entered by the user.

[1433] "Database" refers to a digital storage system for storing play data, emotional data, and generated sign play patterns.

[1434] "Emotion data" refers to information about the emotional state obtained by analyzing facial expressions and voice data of the user and other people.

[1435] A "signature play pattern" refers to a pattern that is generated based on the user's play data and emotion data and that instructs a specific play or movement.

[1436] "AI means" refers to technology that uses artificial intelligence to analyze data and generate and modify sign play patterns.

[1437] "Terminal" refers to a device such as smart glasses worn by a user, which is used to display sign play patterns.

[1438] "Monitoring means" refers to technology that observes and collects emotional data of users and others in real time.

[1439] "Adaptive adjustment means" refers to technology that changes sign-play patterns in real time based on monitored emotional data.

[1440] "Feedback" refers to ratings and comments about performance and emotional state provided by users and others after using the system.

[1441] This invention is a system for improving the cooperative skills of individuals and teams, and in particular, by combining an emotion engine, it generates and adjusts play patterns taking into account the user's emotional state. This system mainly consists of a server, a device worn by the user (smart glasses), a generation AI, and an emotion engine.

[1442] User operations

[1443] Users use devices such as smartphones or tablets to input their playing data (position, skill set, etc.). This data is sent to a server via the terminal. By wearing the smart glasses, players can practice based on the displayed sign play patterns. An emotion engine is built into the smart glasses and recognizes the user's emotional state by analyzing their facial expressions and voice data in real time.

[1444] Server Processing

[1445] The server stores the play data received from the user in a database and provides it to the generation AI. The generation AI generates sign play patterns based on this data and sends the generated patterns back to the server. The server then stores the generated sign play patterns in a database and distributes them to devices as needed.

[1446] Emotion Engine Functions

[1447] The emotion engine analyzes the user's facial expressions, voice data, and other data to recognize their emotional state in real time. The recognized emotional data is sent to a server and stored in a database. The generation AI combines play data and emotional data to generate sign play patterns that adapt to the user's current emotional state. For example, if the user is nervous, it will provide a pattern that will relieve that tension, and if the user is concentrating, it will provide a more difficult pattern.

[1448] The role of smart glasses

[1449] When a user activates the smart glasses, a request is made to acquire sign play patterns from the server. The server then transmits the generated patterns to the device, and the smart glasses visually display them to the user. The emotion engine continues to monitor the user's emotional state during this process, adaptively changing the content of the sign play patterns as needed.

[1450] Feedback function

[1451] After a user practices a sign play pattern, they provide feedback to the system about their performance and emotional state. The feedback includes specific evaluations and comments, and is sent to the server and stored in a database. The server analyzes this feedback data and emotional data and provides it to the generation AI. The generation AI adjusts and updates the sign play pattern based on the feedback and emotional data, generating a more effective pattern.

[1452] Specific examples

[1453] For example, if the user is a sales clerk serving customers at a virtual store, the sales clerk can send their play data along with their own emotional data to the system. Based on this, the generation AI will suggest ways to serve customers that will help them relax. At the same time, the system will also recognize customer emotional data in real time and suggest ways to serve customers that will help them relax. Below are some example prompts for the generation AI.

[1454] "If a sales associate is smiling at a customer but appears nervous, generate a service suggestion to help the customer relax. Or, if a customer appears angry, recommend instructions to the sales associate to deal with the situation calmly."

[1455] In this way, by using this system, it is possible to efficiently confirm and execute sign plays and customer service methods while taking into account the user's emotional state, which is expected to lead to greater skill development and improved customer satisfaction.

[1456] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1457] Step 1:

[1458] Users use their smartphones or tablets to input their playing data (position, skill set, etc.). The playing data includes information such as the user's practice status and technical skills. This data is sent to the server via the device. The input data is accurately stored in a database and processed into a form that can be used for subsequent processing.

[1459] Step 2:

[1460] The server stores the play data received from the user in a database. Specifically, the server analyzes the received data, divides it into fields, and stores the data in a database table.

[1461] Step 3:

[1462] The server provides the saved play data to the generation AI. The generation AI then runs an algorithm based on this data to generate the user's play patterns. Based on the input data, it generates sign play patterns using various parameters and sends the results back to the server. Here, the generation AI model generates play patterns while also taking emotional data into account.

[1463] Step 4:

[1464] The emotion engine is built into the smart glasses and analyzes the user's facial expressions and voice data in real time. Data analysis is performed to recognize the user's emotional state, and the results are sent to the server. At the same time, the results are saved in a database as play data.

[1465] Step 5:

[1466] The server stores the emotion data sent by the emotion engine and the sign play patterns generated by the generation AI in a database, so that the next time the user retrieves a sign play pattern, they will receive a pattern based on the latest state.

[1467] Step 6:

[1468] When a user starts up their smart glasses, they request the latest sign play patterns from the server. The server searches for the latest patterns stored in the database and delivers them to the device. The smart glasses then visually display the received sign play patterns to the user.

[1469] Step 7:

[1470] The smart glasses continuously monitor the user's emotional state and adjust the sign play patterns as needed. Emotional data is updated in real time and sent to the server. Based on this new data, the regenerative AI adaptively adjusts the play patterns.

[1471] Step 8:

[1472] After the user practices the sign-play pattern, they provide feedback to the system regarding their performance and emotional state. Specifically, the user inputs the feedback through the smart glasses, and the data is sent to the server.

[1473] Step 9:

[1474] The server stores the received feedback in a database. After storing it, it analyzes the feedback data and emotion data and provides the results to the generation AI. Based on this, the generation AI adjusts and updates the sign play pattern to generate a more effective pattern. The results are then returned to the server.

[1475] Step 10:

[1476] The server stores the updated patterns in a database and distributes them to the terminal, allowing the user to always use the latest and most optimal sign play patterns for practice or service provision.

[1477] 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] 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.

[1483] 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).

[1484] 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.

[1485] 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."

[1486] 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.

[1487] 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).

[1488] 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.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] The following is further disclosed regarding the above embodiment.

[1499] (Claim 1)

[1500] means for receiving play data from a user;

[1501] A means for storing the received play data in a database;

[1502] An AI means for generating sign play patterns based on stored play data;

[1503] A means for storing the generated sign play pattern in a database;

[1504] A means for delivering a signature play pattern to the terminal;

[1505] A system including:

[1506] (Claim 2)

[1507] The system of claim 1, wherein the smart glasses display a sign play pattern.

[1508] (Claim 3)

[1509] means for receiving feedback from a user;

[1510] 2. The system of claim 1, further comprising AI means for storing the received feedback in a database and modifying and generating sign play patterns based on the feedback.

[1511] "Example 1"

[1512] (Claim 1)

[1513] means for receiving play data from a user;

[1514] A means for storing the received play data in a database;

[1515] A generation AI model means for generating new sign play patterns based on the stored play data;

[1516] A means for storing the generated sign play pattern in a database;

[1517] A means for delivering a signature play pattern to the terminal;

[1518] a means for receiving feedback from users and storing it in a database;

[1519] A generative AI model means for adjusting and updating sign play patterns based on feedback;

[1520] A system including:

[1521] (Claim 2)

[1522] 10. The system of claim 1, comprising smart glasses that display a sign play pattern.

[1523] (Claim 3)

[1524] 2. The system of claim 1, further comprising a generative AI model means for modifying and generating sign play patterns based on feedback.

[1525] "Application Example 1"

[1526] (Claim 1)

[1527] means for receiving play data from a user;

[1528] A means for storing the received play data in a database;

[1529] An AI means for generating movement patterns based on stored play data;

[1530] means for storing the generated motion patterns in a database;

[1531] means for delivering an operation pattern to a terminal;

[1532] A system including:

[1533] (Claim 2)

[1534] 10. The system of claim 1, wherein the smart glasses display the motion pattern.

[1535] (Claim 3)

[1536] means for receiving feedback from a user;

[1537] 2. The system of claim 1, further comprising AI means for storing the received feedback in a database and modifying or generating movement patterns based on the feedback.

[1538] "Example 2: Combining Emotion Engines"

[1539] (Claim 1)

[1540] means for receiving play data from a user;

[1541] A means for storing the received play data in a database;

[1542] An AI means for generating sign play patterns based on play data and emotion data received in real time;

[1543] A means for storing the generated sign play patterns and emotion data in a database;

[1544] A means for providing the play data and emotion data to the generating AI;

[1545] A means for delivering a signature play pattern to the terminal;

[1546] A system including:

[1547] (Claim 2)

[1548] The system of claim 1, wherein the smart glasses display a sign play pattern.

[1549] (Claim 3)

[1550] means for receiving feedback from a user;

[1551] 2. The system of claim 1, further comprising AI means for storing received feedback in a database and modifying and generating sign play patterns based on the feedback and emotional data.

[1552] "Application example 2 when combining emotion engines"

[1553] (Claim 1)

[1554] means for receiving play data from a user;

[1555] A means for storing the received play data in a database;

[1556] an AI means for generating sign play patterns based on the saved play data and the user's emotional data;

[1557] A means for storing the generated sign play pattern in a database;

[1558] A means for delivering a signature play pattern to the terminal;

[1559] means for monitoring the user's and others' emotional data in real time;

[1560] means for adaptively adjusting the sign play pattern based on the monitored emotion data;

[1561] A system including:

[1562] (Claim 2)

[1563] The system of claim 1, wherein a sign play pattern is displayed on the smart glasses and the execution content is adjusted based on the displayed sign play pattern.

[1564] (Claim 3)

[1565] means for receiving feedback from users and others;

[1566] 2. The system of claim 1, further comprising AI means for storing received feedback in a database and modifying and generating sign play patterns based on the feedback and emotional data. [Explanation of symbols]

[1567] 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 play data from a user; A means for storing the received play data in a database; An AI means for generating sign play patterns based on stored play data; A means for storing the generated sign play pattern in a database; A means for delivering a signature play pattern to the terminal; A system including:

2. The system of claim 1, wherein the smart glasses display a sign play pattern.

3. means for receiving feedback from a user; 2. The system according to claim 1, further comprising AI means for storing the received feedback in a database and modifying and generating sign play patterns based on the feedback.

Images