System

Abstract

To provide a system.SOLUTION: A system includes: learning means for inputting a specific prompt sentence into a generative AI model to use a machine learning model and learn tactics in a past game, data on players who participated in the game, and past opponents; means for using the generative AI model to present tactics and formations of teams participating in the game on the basis of the learned data; means for generating a visual simulation video on the basis of the presented tactics and formations and presenting the generated simulation video to a user; means for recognizing a feeling of the user presented with the simulation video; and means for adjusting the machine learning model on the basis of a result of the recognition.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Soccer team coaches are required to understand the latest tactics, player performance data, and opponent tactical data, and to use this information to come up with optimal tactics and formations. However, this information is huge and constantly updated, making it difficult for humans to understand it all and come up with appropriate tactics. [Means for solving the problem]

[0005] The system disclosed herein includes a learning means for utilizing a machine learning model to learn tactics in past matches, data on players participating in the matches, and past opponents by inputting a specific prompt sentence into a generative AI model; a means for using the generative AI model to present tactics and formations of teams participating in the match based on the learned data; a means for generating a visual simulation video based on the presented tactics and formations and presenting the generated simulation video to a user; a means for recognizing the emotions of a user who is presented with the simulation video; and a means for adjusting the machine learning model based on the results of the recognition. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. [Figure 19] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system according to the embodiment 2 of the second embodiment in the case where an emotion engine is combined. [Figure 20] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when combined with an emotion engine. [Figure 21] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the embodiment 3 of the form example 3 in the case where an emotion engine is combined. [Figure 22] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The system of the present invention acquires cutting-edge tactics, player data, and opponent data through a database, API, etc., and performs learning using a machine learning algorithm. Specifically, past match data, player performance data, opponent tactical data, etc. are input, and patterns and trends are extracted from this data.

[0029] "Example 2"

[0030] As a means of presenting the optimal tactics and formations for a team based on learned data, the optimal tactics and formations are calculated using a model generated by a machine learning algorithm and presented to the user. Specifically, the optimal tactics and formations are calculated based on the match conditions and team situation specified by the user and presented to the user. "Example 3"

[0031] As a means of generating and presenting an image video of the goal based on the presented tactics and formation, a video visually expressing the presented tactics and formation is generated using 3D modeling software, animation software, etc., and this is presented to the user. Specifically, based on the presented tactics and formation, the movements of the players and the ball are simulated, and this is generated and presented as a video.

[0032] "Example 4"

[0033] As a means of presenting training methods to realize the proposed tactics and formations, the system calculates what kind of training each player needs to do to realize the proposed tactics and formations based on the learned data and the generated model, and presents this to the user. Specifically, the system calculates the skills and abilities required by each player based on the performance data and past match data of each player, and presents training methods based on this.

[0034] The process flow of each embodiment will be described below.

[0035] "Example 1"

[0036] Step 1: Obtain cutting-edge tactics, player data, and opponent data through databases, APIs, etc.

[0037] Step 2: The acquired data is fed into a machine learning algorithm to learn from it, using data from past matches, player performance data, opponent tactical data, etc. to extract patterns and trends.

[0038] "Example 2"

[0039] Step 1: Calculate optimal tactics and formations using a model generated by a machine learning algorithm.

[0040] Step 2: Present the calculated tactics and formation to the user. At this time, the system presents the optimal tactics and formation based on the match conditions and team situation specified by the user.

[0041] "Example 3"

[0042] Step 1: Using 3D modeling software, animation software, etc., create a video that visually represents the proposed tactics and formations.

[0043] Step 2: The generated video is presented to the user. At this time, the movements of the players and the ball are simulated based on the presented tactics and formation, and this is presented as a video.

[0044] "Example 4"

[0045] Step 1: Based on the learned data and the generated model, calculate what kind of practice each player needs to do to achieve the proposed tactics and formation.

[0046] Step 2: Present the calculated training method to the user. At this time, the skills and abilities required by each player are calculated based on the performance data of each player and past match data, and the training method is presented based on this.

[0047] Example 1

[0048] Next, a description will be given of Example 1 of the embodiment 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".

[0049] In conventional tactical analysis systems, data acquisition, pre-processing, machine learning model training and evaluation were performed separately, and the system lacked efficiency as an integrated system. In addition, the system did not adequately present optimal tactics and formations, or even training methods to achieve them. This limited the improvement of team performance.

[0050] 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. In this invention, the server includes a means for acquiring past match data, player performance data, and opponent tactical data through a database or API, a means for preprocessing the acquired data, a means for learning a machine learning model using the preprocessed data, a means for evaluating the performance of the learned model, a means for deploying the evaluated model, a means for presenting optimal tactics and formations for the team based on the learned data, and a means for generating and presenting an image video up to the goal based on the presented tactics and formations. This makes it possible to consistently perform the processes from data acquisition to model learning, evaluation, deployment, and presentation of tactics, thereby efficiently improving team performance.

[0051] A "database" is a system for systematically storing data and efficiently searching and managing it.

[0052] "API" stands for Application Programming Interface, an interface for exchanging data and functions between different software programs.

[0053] "Past match data" is data that includes information about matches that have previously been played.

[0054] "Player performance data" refers to data relating to a player's movements during a match, their performance, physical strength, etc.

[0055] "Opponent's tactical data" refers to data regarding the opponent's tactics and formation.

[0056] "Preprocessing" is the process of converting data into a format suitable for learning from a machine learning model.

[0057] A "machine learning model" is an algorithm for learning patterns and trends from data and making predictions and classifications. The server may include a learning means for using the machine learning model to learn tactics in past matches, data on players who participated in the matches, and past opponents by inputting a specific prompt sentence into the generative AI model.

[0058] "Evaluation" is the process of measuring the performance of a trained machine learning model and confirming its validity.

[0059] "Deployment" refers to the process of placing a machine learning model that has completed training and evaluation in an actual production environment and making it available for use.

[0060] "Tactics" refers to a team's strategy and playing style in a match.

[0061] A "formation" is a diagram that shows the positions and roles of players during a match.

[0062] An "image video" is a visual simulation video generated based on presented tactics and formations.

[0063] The present invention is a system in which a server acquires past match data, player performance data, and opponent tactical data through a database or API, preprocesses the data, and presents optimal tactics and formations through a series of processes of learning, evaluating, and deploying a machine learning model. The server may include a means for presenting tactics and formations of teams participating in the match based on the learned data using a generative AI model.

[0064] The server first obtains the necessary data using a database or API. A typical relational database management system (RDBMS) is used as the database, and a RESTful API is used as the API. For example, a sports data API can be used to obtain past match data.

[0065] The server then preprocesses the data, including imputing missing values, normalizing the data, encoding categorical data, etc., using the Python Pandas and Scikit-learn libraries.

[0066] The server uses the preprocessed data to train the machine learning model. Machine learning algorithms such as random forest and support vector machine (SVM) are used. Libraries such as Scikit-learn and TENSORFLOW (registered trademark) are used for this purpose.

[0067] To evaluate the performance of the trained model, the server uses methods such as cross-validation and confusion matrix, and calculates evaluation indices such as precision, recall, and F1 score of the model.

[0068] Once the evaluation is complete, the model is deployed by the server using a web framework such as Flask or Django. The deployed model receives new data as input in real time and makes predictions.

[0069] As a concrete example, the server retrieves past match data from a sports data API, preprocesses the data using Pandas, trains a random forest model using Scikit-learn, evaluates the model using cross-validation, and deploys the model using Flask.

[0070] An example prompt is, "Use past match data, player performance data, and opponent tactical data to build a machine learning model to predict the outcome of the next match."

[0071] This system makes it possible to consistently collect data, train models, evaluate them, deploy them, and present tactics, thereby efficiently improving team performance.

[0072] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0073] Step 1: Get the data

[0074] The server retrieves past match data, player performance data, and opponent tactical data through a database or API. Inputs include API endpoint URLs and database queries. Specifically, the server sends API requests and receives data in JSON format. The output is the retrieved raw data.

[0075] Step 2: Preprocessing the data

[0076] The server preprocesses the acquired data. The input includes the raw data acquired in step 1. Specifically, the server creates a data frame using the Pandas library, imputes missing values, normalizes the data, and encodes categorical data. The output is the clean data after preprocessing.

[0077] Step 3: Train the machine learning model

[0078] The server trains a machine learning model using the preprocessed data. The input includes the preprocessed data from step 2. Specifically, the server builds a random forest model using the Scikit-learn library and trains the model with the data. The output is a trained machine learning model.

[0079] Step 4: Evaluate the model

[0080] The server evaluates the performance of the trained model. The inputs include the model trained in step 3 and the preprocessed data. Specifically, the server performs cross-validation and calculates evaluation metrics such as precision, recall, and F1 score. The output is the evaluation result.

[0081] Step 5: Deploy the model

[0082] The server deploys the model once evaluation is complete. The input includes the model evaluated in step 4. Specifically, the server builds a web service using the Flask framework to expose the model as an endpoint. The output is a web service running the deployed model.

[0083] Step 6: Present tactics and formations

[0084] The server then presents the best tactics and formations for the team based on the learned data. The inputs include the model deployed in step 5 and new match data. Specifically, the server inputs the new data into the model and predicts the best tactics and formations. The output is the presented tactics and formations.

[0085] Step 7: Generate and present image videos

[0086] The server generates and presents an image video of the goal based on the presented tactics and formation. The input includes the tactics and formation presented in step 6. In concrete terms, the server uses an image generation algorithm to visually simulate the tactics and formation. The output is the generated image video.

[0087] (Application example 1)

[0088] Next, a description will be given of Application Example 1 of Form 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."

[0089] Conventional sports tactics analysis systems and factory robot operation optimization systems function independently, making comprehensive data analysis and optimization difficult. In addition, there was no system that simultaneously optimized sports tactics and factory robot operations, making efficient data utilization impossible. As a result, tactical optimization of sports teams and improvement of production efficiency in factories were not fully achieved.

[0090] 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.

[0091] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for learning the operation data of robots in a factory and extracting optimal movement patterns, a means for presenting an efficient arrangement of the robots based on the extracted movement patterns, and a means for realizing optimization of the manufacturing line based on the presented arrangement. This makes it possible to simultaneously optimize sports tactics and the operation of robots in a factory.

[0092] "Tactics" refers to the plans and methods a team or player uses to achieve victory in a sport or competition.

[0093] "Player data" refers to information regarding a player's performance, abilities, past match results, etc.

[0094] "Opponent data" refers to information regarding the opponent's tactics, player performance, past match results, etc.

[0095] A "learning means" refers to a method or device that takes data and uses machine learning algorithms to extract patterns and trends.

[0096] "Presentation means" refers to a method or device that displays optimal tactics, formations, and movement patterns based on learned data.

[0097] An "image video" is a visual simulation that is generated based on presented tactics and formations.

[0098] A "factory robot" is an automated machine used in a factory.

[0099] "Operational data" refers to information regarding the robot's operating history and performance.

[0100] A "motion pattern" is a series of movements or steps that a robot follows to perform a specific task.

[0101] "Efficient layout" refers to the location and layout method in which robots and mechanical devices are placed most effectively.

[0102] A "production line" is a series of machines or equipment arranged to efficiently produce products.

[0103] "Optimization" refers to adjusting a system or process to be most effective in achieving a particular purpose.

[0104] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server plays a central role in collecting, learning, and analyzing data. The terminal is a device through which the user interfaces with the system, and the user is responsible for operating the system and checking the results.

[0105] Server Roles

[0106] The server processes and calculates data using the following hardware and software:

[0107] Hardware: Powerful processor, ample memory and storage

[0108] Software: Python, Pandas, Scikit-learn, Joblib

[0109] The server first collects past match data, player performance data, opponent tactical data, factory robot operation data, and production line data through databases and APIs. It then uses machine learning algorithms to learn from this data and extract patterns and trends. Specifically, it analyzes the data using a random forest regression model to derive optimal tactics and movement patterns.

[0110] Terminal Roles

[0111] A terminal is a device through which a user interfaces with the system. It can be a smartphone, tablet, or PC. The terminal receives the analysis results sent from the server and visually presents them to the user. For example, it shows the optimal tactics and formations of a sports team, or the efficient placement of robots in a factory.

[0112] User Roles

[0113] The user operates a terminal to access the system and input the necessary data. The user also checks the analysis results sent from the server and optimizes tactics and placement based on the results. The user follows the training methods and production line optimization procedures presented by the system.

[0114] Examples

[0115] For example, when a robot operating in a factory assembles a product, it can learn optimal movement patterns based on past data and perform efficient movements, improving the efficiency of the production line and enabling cost reduction.

[0116] Examples of prompt statements

[0117] Build a system that uses operational data from robots in factories to learn optimal operating patterns and achieve efficient operation. Past operational data, robot performance data, and production line data are input, and learning is performed using a random forest regression model.

[0118] In this way, by having the server, terminals, and users work together to operate the system, it becomes possible to simultaneously optimize sports tactics and the operation of robots in a factory.

[0119] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0120] Step 1:

[0121] The server collects past match data, player performance data, opponent tactical data, robot operation data in the factory, and production line data through databases and APIs. This data is stored on the server in CSV files or JSON format. The input is data obtained from various databases and APIs, and the output is raw data stored on the server.

[0122] Step 2:

[0123] The server preprocesses the collected data, specifically by imputing missing values, normalizing data, encoding categorical data, etc. The input is the raw data collected in step 1, and the output is the preprocessed data.

[0124] Step 3:

[0125] The server uses the preprocessed data to train a machine learning model, specifically a random forest regression model, to learn patterns and trends in the data. The input is the preprocessed data, and the output is the trained machine learning model.

[0126] Step 4:

[0127] The server uses the trained machine learning model to make predictions on new data, such as predicting the optimal movement pattern for a robot in a factory or the optimal tactics for a sports team. The input is the new data, and the output is the predicted result.

[0128] Step 5:

[0129] The server transmits the prediction result to the terminal. The terminal visually presents the received prediction result to the user. Specifically, the terminal displays a dashboard, a graph, a simulation video, or the like. The input is the prediction result transmitted from the server, and the output is visual information presented to the user. The server may include a means for generating a visual simulation video based on the presented tactics and formations, and presenting the generated simulation video to the user.

[0130] Step 6:

[0131] The user operates the terminal to check the prediction results and optimize tactics and placement as necessary. Specifically, the user follows the practice methods and production line optimization procedures presented by the system. The input is the prediction results displayed on the terminal, and the output is the user's actions.

[0132] In this way, by having the server, terminals, and users work together to operate the system, it becomes possible to simultaneously optimize sports tactics and the operation of robots in a factory.

[0133] Example 2

[0134] Next, a second embodiment of the second embodiment will be described. 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."

[0135] Conventional methods for determining tactics and formations make it difficult to quickly and accurately calculate optimal tactics according to match conditions and team situations. In addition, there was a lack of means to understand how the presented tactics and formations specifically worked, making it difficult to apply them in actual matches.

[0136] 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.

[0137] In this invention, the server includes a means for a user to input match conditions and team situations, a means for transmitting the input data to the server, a means for the server to analyze the data received and input it to the generative AI model, a means for calculating optimal tactics and formations using the generative AI model, and a means for presenting the calculation results to the user. This makes it possible to quickly and accurately calculate optimal tactics and formations according to match conditions and team situations and present them to the user.

[0138] "User" refers to an individual or group that uses the system to input match conditions and team status.

[0139] "Match conditions" refers to information that indicates the environment and circumstances regarding the upcoming match, and includes the weather, the characteristics of the opposing team, and the like.

[0140] "Team status" refers to information indicating the current state of the team, the condition of the players, tactical preferences, and the like.

[0141] A "terminal" is a device through which a user inputs match conditions and team status and communicates with the server.

[0142] The "Server" is a computer system that receives and analyzes data sent by users and uses a generative AI model to calculate optimal tactics and formations.

[0143] A "generative AI model" is a model generated by a machine learning algorithm and is used to calculate optimal tactics and formations based on training data.

[0144] "Tactics" refers to the specific playing style and strategy adopted by a team in a match.

[0145] "Formation" refers to the specific positions in which a team's players are positioned during a match.

[0146] The "calculation results" are information on optimal tactics and formations calculated using a generative AI model.

[0147] "Presenting" is the act of showing the results of a calculation to a user visually or in some other way.

[0148] The present invention is a system that allows a user to input match conditions and team situations, calculates optimal tactics and formations based on the input, and presents the results to the user. A specific embodiment of this system will be described below.

[0149] First, a user uses a terminal to input the match conditions and team status. The terminal can be a device such as a smartphone, tablet, or PC, and input is performed through a dedicated application or web interface. For example, a user may input information such as: "The next match will be played on rainy days, and the opposing team has a high offensive power. Our team has a strong defensive power, but an average offensive power."

[0150] The terminal converts the input data into a data format such as JSON and sends it to the server using an HTTP request. The server analyzes the received data and performs necessary preprocessing, such as converting text data into numerical data. The preprocessed data is then input into the generative AI model.

[0151] The server uses machine learning libraries such as Python's Scikit-learn and TensorFlow to run generative AI models. The generative AI models calculate optimal tactics and formations based on the training data. For example, they can get results such as "The optimal tactic is to strengthen the defense with a 4-4-2 formation while aiming for counter attacks."

[0152] The calculated results are sent from the server to the device. The device analyzes the received results and displays them to the user. For example, it could display on the screen, "The optimal tactic for the next match is to use a 4-4-2 formation, strengthen the defense, and aim for counter attacks."

[0153] This system allows users to quickly and accurately obtain optimal tactics and formations according to match conditions and team situations, and also provides a means to understand how the presented tactics and formations work specifically, making it easier to apply them in actual matches.

[0154] As a concrete example, a user inputs the following prompt into a generative AI model:

[0155] "The next game will be played in rainy weather, and the opposing team has a strong attacking ability. Our team has a strong defense, but an average attacking ability. Please tell me the best tactics and formations for these conditions."

[0156] Based on this prompt, the server uses the generated model to calculate the optimal tactics and formations and presents them to the user. For example, it might present a result such as, "The optimal tactics are a 4-4-2 formation that strengthens the defense while aiming for counter attacks."

[0157] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0158] Step 1:

[0159] The user inputs the match conditions and team status.

[0160] The user inputs the conditions of the next match (e.g., weather, characteristics of the opposing team) and the situation of his / her own team (e.g., players' condition, tactical preferences) through the terminal interface. For example, the user inputs information such as "The next match will be in rain, and the opposing team has a strong offensive power." The input data is in text format.

[0161] Step 2:

[0162] The terminal transmits the input data to the server.

[0163] The terminal converts the data entered by the user into a data format such as JSON format and sends it to the server using an HTTP POST request. For example, it sends the data {"weather": "rain", "opponent_strength": "high_attack"}. The input is text data, and the output is JSON format data.

[0164] Step 3:

[0165] The server analyzes the data it receives and inputs it into a generative AI model.

[0166] The server parses the received JSON data and performs the necessary preprocessing. For example, convert text data into numerical data, such as {"weather": 1, "opponent_strength": 2}. The preprocessed data is input to the generative AI model. The input is JSON format data, and the output is preprocessed numerical data.

[0167] Step 4:

[0168] The server uses generative AI models to calculate optimal tactics and formations.

[0169] The server uses machine learning libraries such as Python's Scikit-learn and TensorFlow to run generative AI models. The model calculates optimal tactics and formations based on the input data. For example, it may obtain a result such as "The optimal tactic is to strengthen the defense with a 4-4-2 formation while aiming for counter attacks." The input is preprocessed numerical data, and the output is tactical and formation information.

[0170] Step 5:

[0171] The server transmits the calculation result to the terminal.

[0172] The server converts the calculated results into a data format such as JSON and sends it to the terminal using an HTTP response. For example, it sends the data {"formation": "4-4-2", "strategy": "defensive_counter"}. The input is tactical and formation information, and the output is JSON format data.

[0173] Step 6:

[0174] The terminal displays the results to the user.

[0175] The terminal analyzes the received results and displays them to the user. For example, it might display on the screen, "The best tactic for the next match is to use a 4-4-2 formation, strengthen the defense, and aim for counter attacks." The input is JSON format data, and the output is a visual display.

[0176] (Application example 2)

[0177] Next, a description will be given of Application Example 2 of Form 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."

[0178] Conventional tactical and formation suggestion systems are limited to suggesting optimal tactics and formations for sports teams, and do not address the optimization of robot placement and operation tactics in factories. For this reason, there is a demand for a system that proposes optimal robot placement and operation tactics to maximize factory production efficiency.

[0179] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0180] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for proposing optimal placement and operation tactics of robots in a factory, a means for calculating optimal placement and operation tactics of robots based on the status and work contents of the factory production line, and a means for presenting this to a factory manager. This makes it possible to optimize not only the tactics and formations of sports teams, but also the placement and operation tactics of robots in a factory.

[0181] "Cutting-edge tactics" are tactics that are formulated based on the latest data analysis techniques and strategic theories.

[0182] "Player data" refers to information relating to a player's performance, physical strength, technique, tactical understanding, etc.

[0183] "Opponent data" refers to information relating to the opponent's tactics, player characteristics, past match results, etc.

[0184] "Learning means" refers to the process of using machine learning algorithms to analyze data and generate models.

[0185] "Means for presenting optimal tactics and formations" refers to a method for presenting to a user the most effective tactics and formations for a team based on learned data.

[0186] "A means for generating and presenting an image video leading up to the goal" refers to a method for simulating movements during a match based on presented tactics and formations, and presenting the results to the user in video format.

[0187] The "means for proposing optimal placement and operation tactics for robots in a factory" is a method for making proposals for optimizing the placement and operation of robots based on the status of the factory's production line and the work content.

[0188] "A means for calculating optimal robot placement and operation tactics based on the status of the factory's production line and the work content" refers to a method for analyzing various data within the factory and calculating optimal robot placement and operation tactics.

[0189] "Means of presenting to the factory manager" refers to a method of presenting the calculated optimal robot placement and operation tactics to the factory manager in an easy-to-understand manner.

[0190] The system for implementing the present invention operates in cooperation with a server, a terminal, and a user. A specific embodiment of the system will be described below.

[0191] server

[0192] The server has the means to learn cutting-edge tactics, player data, and opponent data. For this, it uses Python and machine learning libraries such as scikit-learn. The server has the means to present optimal tactics and formations for teams based on the learned data. It also has the means to generate and present image videos leading up to the goal based on the presented tactics and formations. For this, it uses video generation libraries and simulation software.

[0193] The server also has the means to propose optimal placement and operation tactics for robots in the factory. It has the means to calculate optimal placement and operation tactics for robots based on the status of the factory's production line and the work content. To do this, it uses data analysis tools to analyze various sensor data and work logs in the factory. The calculated results are presented to the factory manager.

[0194] Terminal

[0195] The terminal provides an interface for users to access the server. Smartphones, tablets, PCs, etc. are used as terminals. The terminal displays the tactics and formations presented by the server, as well as the placement and operation tactics of the robots. For this purpose, a web browser or a dedicated application is used.

[0196] User

[0197] The user accesses the server through a terminal and inputs the necessary data. For example, the match conditions of a sports team or the status data of a factory production line. The user checks the optimal tactics and formations, as well as the robot placement and operation tactics presented by the server, and performs actual operations based on them.

[0198] Examples

[0199] For example, to optimize the placement of robots in a factory, the following data is input:

[0200] "In order to optimize the placement of robots in the factory, input the current status data of the production line. For example, input data such as the operating rate, work content, work time, and error rate of each robot."

[0201] Following these prompts, the user inputs the necessary data, which the server analyzes to calculate the optimal placement and operation tactics. The results are displayed on the terminal, and the user can check them and apply them to actual operations.

[0202] The above is a specific embodiment for carrying out the present invention.

[0203] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0204] Step 1:

[0205] A user accesses a server using a terminal.

[0206] Input: Credentials for the user to access the server through the terminal.

[0207] Output: The server verifies the user's identity and grants access.

[0208] Specific operation: The user opens a browser or a dedicated application on the device and enters authentication information into the login screen. The server verifies the authentication information and allows the user access.

[0209] Step 2:

[0210] The user inputs the necessary data through the terminal.

[0211] Input: Data on the match conditions of a sports team or the status of a factory production line.

[0212] Output: The input data that is sent to the server.

[0213] Specific operation: The user enters the match conditions (e.g., weather, opponent information) and factory status data (e.g., each robot's operating rate, work content, work time, error rate) into the input form on the terminal, and presses the send button. The server receives this data.

[0214] Step 3:

[0215] The server analyzes the received data and uses machine learning models to calculate optimal tactics, formations, robot placement and operation tactics.

[0216] Input: Match conditions and factory status data sent by the user.

[0217] Output: Optimal tactics and formations, as well as robot placement and movement tactics.

[0218] Specific operation: The server pre-processes the received data and inputs it into the machine learning model. The model analyzes the data and calculates the optimal tactics, formations, and robot placement and operation tactics.

[0219] Step 4:

[0220] The server transmits the calculated result to the terminal.

[0221] Input: Optimal tactics and formations, as well as robot placement and movement tactics.

[0222] Output: The result data sent to the terminal.

[0223] Specific operation: The server formats the calculated result and sends it to the terminal, which receives it and displays it to the user.

[0224] Step 5:

[0225] The user checks the results via the terminal and reflects them in actual operations.

[0226] Input: Optimal tactics and formations sent from the server, as well as robot placement and movement tactics.

[0227] Output: Actual operation based on user confirmed results.

[0228] Specific operation: Users check the results displayed on their devices and adjust their sports team's tactics or the placement of robots in a factory based on the results.

[0229] Example 3

[0230] Next, a third embodiment of the third embodiment will be described. 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."

[0231] Conventional tactical and formation suggestion systems lacked a means to visually confirm the effectiveness of tactics and formations, and it was difficult to provide specific practice methods to realize the proposed tactics. This made it difficult for users to understand the effects of tactics, and they were unable to find effective practice methods.

[0232] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0233] In this invention, the server includes a means for learning tactics, player data, and opponent data, a means for presenting optimal tactics and formations to a team based on the learned data, a means for generating an image video of the goal based on the presented tactics and formations, a means for presenting the generated image video to a user, a means for calculating a practice method for realizing the presented tactics and formations, and a means for presenting the calculated practice method to a user. This allows a user to visually confirm the effects of the tactics and formations, and further allows the user to know specific practice methods.

[0234] "Tactics" are the specific methods or strategies that plan and direct how a team will play in a match.

[0235] "Player data" refers to information regarding an individual player's performance, skills, physical strength, past match results, etc.

[0236] "Opponent data" refers to information relating to the opposing team's tactics, player characteristics, past match results, etc.

[0237] "Means of learning" refers to methods and techniques for analyzing tactics, player data, and opponent data to derive optimal tactics and formations.

[0238] "Means of presentation" refers to methods or techniques for displaying optimal tactics and formations to the user based on learned data.

[0239] An "image video" is a video that visually depicts the movements of players and the ball, generated based on presented tactics and formations.

[0240] "Means of generation" refers to methods and techniques for creating image videos based on tactics and formations.

[0241] The "means for presenting to the user" refers to a method or technique for displaying the generated image moving image to the user.

[0242] "Means for calculating training methods" refers to methods or techniques for calculating and deriving the training methods necessary to realize the presented tactics and formations.

[0243] The "means for presenting a practice method" refers to a method or technique for displaying the calculated practice method to the user.

[0244] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0245] This invention is a system that generates an image video of the path to the goal based on tactics and formations and presents it to the user. It also includes a function to suggest practice methods for achieving the presented tactics and formations.

[0246] Hardware and Software Used

[0247] Hardware: High-performance server (e.g. GPU-equipped server)

[0248] Software: 3D modeling software (e.g. Blender), animation software (e.g. Autodesk Maya), generative AI models (e.g. GPT-4®)

[0249] Specific operation of the system

[0250] 1. Enter tactics and formations

[0251] Users use terminals to input tactics and formations into the system.

[0252] Example: A user enters "I want to strengthen attacks from the sides with a 4-4-2 formation" into an input form on a terminal and clicks the submit button.

[0253] 2. Simulating the data

[0254] The server analyzes the tactical and formation data received from the user.

[0255] The server uses 3D modelling software (e.g. Blender) to model the player positions and movements.

[0256] The server uses animation software (e.g. Autodesk Maya) to simulate player movements and ball movement.

[0257] Example: The server sets the initial positions of the players in Blender, and calculates the player movements and ball trajectory in Maya.

[0258] 3. Video Generation

[0259] The server generates a visually-presented video based on the simulation results.

[0260] The server uses rendering software to convert the simulation results into a video file.

[0261] Example: A server starts a rendering process, generating a one minute video of images.

[0262] 4. Presenting the video

[0263] The video generated by the server is sent to the user's terminal.

[0264] The terminal displays the received video to the user.

[0265] Example: A server sends a video file to a terminal using the HTTP protocol, and the terminal plays it on a video player.

[0266] 5. Practice suggestions

[0267] Based on the data learned by the server and the generative AI model, it calculates what kind of practice each player needs to do to achieve the tactics and formations.

[0268] The server analyzes each player's performance data and past match data.

[0269] Example: A server retrieves player performance data from a database and uses a generative AI model (e.g. GPT-4) to calculate the required skills and abilities.

[0270] 6. Presentation of practice methods

[0271] The server presents the calculated practice method to the user.

[0272] The practice method received by the terminal is displayed to the user.

[0273] Example: The server sends text data on how to practice to the terminal, and the terminal displays it.

[0274] Examples of prompt statements

[0275] "I want to strengthen my attacks from the sides in a 4-4-2 formation. Please simulate the movement of the players and the ball and generate a video showing how the ball will move to the goal."

[0276] "Please tell me what kind of practice each player should do to implement the tactics you have presented."

[0277] This system enables the user to visually confirm the effects of tactics and formations, and furthermore, to learn specific training methods. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0278] Step 1:

[0279] Tactical and formation input

[0280] Users use terminals to input tactics and formations into the system.

[0281] Input: The user enters "I want to strengthen attacks from the sides with a 4-4-2 formation" into the input form on the terminal and clicks the submit button.

[0282] Output: Tactical and formation data is sent to the server.

[0283] Specific operation: The user enters tactics and formations into the input form on the terminal and clicks the send button, which sends the data to the server.

[0284] Step 2:

[0285] Simulating Data

[0286] The server analyzes the tactical and formation data received from the user.

[0287] Input: Tactical and formation data.

[0288] Output: Initial setup data for the simulation.

[0289] How it works: The server analyzes tactical and formation data, models player positions and movements using 3D modeling software (e.g. Blender), then simulates player and ball movements using animation software (e.g. Autodesk Maya).

[0290] Step 3:

[0291] Video Generation

[0292] The server generates a visually-presented video based on the simulation results.

[0293] Input: Simulation result data.

[0294] Output: Image video file.

[0295] What happens: The server uses rendering software to convert the simulation results into a video file. The server starts the rendering process, producing a one-minute video of the images.

[0296] Step 4:

[0297] Video presentation

[0298] The video generated by the server is sent to the user's terminal.

[0299] Input: Image video file.

[0300] Output: The video displayed on the user's device.

[0301] Specific operation: The server sends a video file to the terminal using the HTTP protocol, and the terminal plays it on the video player.

[0302] Step 5:

[0303] Practice suggestions

[0304] Based on the data learned by the server and the generative AI model, it calculates what kind of practice each player needs to do to achieve the tactics and formations.

[0305] Input: Performance data and past match data for each player.

[0306] Output: Practice suggestions data.

[0307] How it works: The server retrieves player performance data from the database and uses a generative AI model (e.g. GPT-4) to calculate the required skills and abilities.

[0308] Step 6:

[0309] Presentation of practice methods

[0310] The server presents the calculated practice method to the user.

[0311] Input: Practice suggestion data.

[0312] Output: The exercise displayed on the user's device.

[0313] Specific operation: The server sends text data on how to practice to the terminal, and the terminal displays it.

[0314] (Application example 3)

[0315] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0316] Conventional tactical and formation presentation systems lacked the means to visually understand the movements of players and the ball, and the presentation of effective practice methods was limited. In addition, there was also a lack of means to visually understand efficient movement patterns in optimizing the movements of robots and work flows in factories. This made it difficult to understand tactics, improve the efficiency of practice, and improve production efficiency in factories.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0318] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for simulating the movements and work flows of robots in the factory and generating and presenting optimal movement patterns as videos, and a means for calculating what movements and work each robot should perform to efficiently produce and presenting specific movement procedures. This makes it possible to understand tactics, improve the efficiency of practice, and increase production efficiency in the factory.

[0319] "Cutting-edge tactics" are tactics developed based on the latest technology and data analysis.

[0320] "Player Data" refers to information relating to a player's performance or abilities.

[0321] "Opponent Data" refers to information regarding the opponent's tactics and performance.

[0322] "Learning tools" refers to the methods and techniques used to analyze data and find patterns and trends.

[0323] "Means for presenting tactics and formations" refers to a method for showing the user optimal tactics and formations based on the analyzed data.

[0324] "Means of generating and presenting image videos" refers to a method of running simulations based on tactics and formations and showing the results to users as videos.

[0325] "Means of simulating robot movements and work flows within a factory" refers to a method of virtually reproducing the movements of robots and work procedures within a factory.

[0326] "Means of generating and presenting optimal movement patterns as videos" refers to a method of showing efficient movement patterns to users in video format based on simulation results.

[0327] "Means for presenting specific operating procedures" refers to a method for showing the user detailed procedures for the robot to perform a task efficiently.

[0328] "Past Match Data" refers to information relating to the results and tactics of previously played matches.

[0329] "Player Performance Data" refers to information regarding a player's performance in past matches and training sessions.

[0330] "Opponent tactical data" refers to information regarding tactics and formations used by an opponent in the past.

[0331] "Factory work flow data" refers to information about work procedures and processes within a factory.

[0332] "Robot operation data" refers to information related to the robot's movements and work.

[0333] The system for implementing this invention is composed of three main elements: a server, a terminal, and a user. The server learns cutting-edge tactics, player data, and opponent data, and presents the optimal tactics and formations for a team based on the learned data. It also generates and presents an image video of the path to the goal based on the presented tactics and formations. It also simulates the movements and work flows of robots in a factory, and generates and presents optimal movement patterns as videos. It calculates what movements and tasks each robot should perform to ensure efficient production, and presents specific operating procedures.

[0334] The server uses software such as Python, NumPy, Matplotlib, and FFmpeg to perform data analysis and simulation. Specifically, Python is used for data preprocessing and analysis, NumPy is used for numerical calculations, Matplotlib is used to visualize the simulation results, and FFmpeg is used to generate videos.

[0335] The terminal is a device that allows the user to view and operate the information provided by the server. Terminals include PCs, smartphones, tablets, etc. Through the terminal, the user can view tactics and formations, view image videos, and check the robot's operation procedures.

[0336] As a concrete example, the system simulates a scene in which multiple robots work together to assemble a product in a factory, and generates a video of the optimal movement pattern. It provides detailed operation procedures for each robot, and shows specific actions to achieve efficient production. This system allows users to understand tactics, improve the efficiency of practice, and increase production efficiency in the factory.

[0337] Using the generative AI model, the system can generate appropriate simulation results by inputting a prompt sentence such as the following:

[0338] Example prompt:

[0339] "Please simulate a scene in which multiple robots work together to assemble products in a factory, and generate a video of the optimal motion pattern. Please provide detailed operating procedures for each robot, and indicate specific actions to achieve efficient production."

[0340] In this way, the form for carrying out the invention can be concretely shown.

[0341] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0342] Step 1:

[0343] The server collects cutting edge tactics and player and opponent data.

[0344] Input: Tactical data, player data, opponent data

[0345] Data processing: Data preprocessing (missing value completion, normalization, etc.)

[0346] Output: Preprocessed dataset

[0347] Step 2:

[0348] The server learns from the collected data and generates optimal tactics and formations for the team.

[0349] Input: Preprocessed dataset

[0350] Data Computing: Training models using machine learning algorithms

[0351] Output: Optimal tactics and formations

[0352] Step 3:

[0353] The server simulates the movements of the players and the ball based on the generated tactics and formations.

[0354] Input: Optimal tactics and formations

[0355] Data calculation: Generation of motion patterns using simulation algorithms

[0356] Output: Simulation data

[0357] Step 4:

[0358] The server generates an image video based on the simulation data and transmits it to the terminal.

[0359] Input: Simulation data

[0360] Data processing: Video generation (using Matplotlib and FFmpeg)

[0361] Output: Image video file

[0362] Step 5:

[0363] The terminal presents the image video transmitted from the server to the user.

[0364] Input: Image video file

[0365] Specific operation: Play a video using a video player

[0366] Output: A video display that users can visually understand

[0367] Step 6:

[0368] The server simulates the robot's movement and work flow within the factory and generates optimal movement patterns.

[0369] Input: Workflow data within the factory, robot operation data

[0370] Data calculation: Generation of motion patterns using simulation algorithms

[0371] Output: Optimal operating pattern

[0372] Step 7:

[0373] The server generates a video based on the optimal movement pattern and transmits it to the terminal.

[0374] Input: Optimal movement pattern

[0375] Data processing: Video generation (using Matplotlib and FFmpeg)

[0376] Output: Motion pattern video file

[0377] Step 8:

[0378] The terminal presents the motion pattern video transmitted from the server to the user.

[0379] Input: Motion pattern video file

[0380] Specific operation: Play a video using a video player

[0381] Output: A video display that users can visually understand

[0382] Step 9:

[0383] Based on the videos presented, users can understand tactics, improve the efficiency of their practice, and increase production efficiency in their factories.

[0384] Input: Video display

[0385] Specific movements: Watch videos to understand tactics and movement patterns

[0386] Output: Improved tactical understanding, efficient practice, and production efficiency

[0387] Furthermore, an emotion engine for estimating the emotion of the user may be combined. That is, the identification processing unit 290 estimates the emotion of the user using the emotion identification model 59, and performs a calculation using the emotion of the user.

[0388] A specific process may be performed.

[0389] "Example 1"

[0390] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes the user's emotions and presents optimal tactics and formations based on those emotions. Specifically, if the user feels nervous about a match, the emotion engine feeds that information back to the system, and the system uses that information to present tactics and formations that will help the user relax.

[0391] "Example 2"

[0392] In addition, the emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. For example, if a user shows a joyful expression after winning a game, the emotion engine feeds that information back to the system, and the system uses that information to present similar tactics and formations again.

[0393] "Example 3"

[0394] Furthermore, it is possible to adjust the presentation of tactics and formations, and the presentation of practice methods, based on the output of the emotion engine. For example, if the user feels dissatisfied with a particular tactic, the emotion engine will feed that information back to the system, and the system will use that information to present a new tactic that satisfies the user.

[0395] The process flow of each embodiment will be described below.

[0396] "Example 1"

[0397] Step 1: The emotion engine collects the user's emotion data (facial expressions, voice, text input, etc.).

[0398] Step 2: The emotion engine recognizes and analyzes the user's emotions based on the collected data.

[0399] Step 3: The system receives the output from the emotion engine and the AI ​​calculates the optimal tactics and formations based on those emotions.

[0400] Step 4: Present the calculated tactics and formations to the user.

[0401] "Example 2"

[0402] Step 1: The emotion engine collects the user's emotion data (facial expressions, voice, text input, etc.).

[0403] Step 2: The emotion engine recognizes and analyzes the user's emotions based on the collected data.

[0404] Step 3: The system receives the output from the emotion engine and, based on the emotion, either presents similar tactics and formations again or the AI ​​calculates new tactics and formations.

[0405] Step 4: Present the calculated tactics and formations to the user.

[0406] "Example 3"

[0407] Step 1: The emotion engine collects the user's emotion data (facial expressions, voice, text input, etc.).

[0408] Step 2: The emotion engine recognizes and analyzes the user's emotions based on the collected data.

[0409] Step 3: The system receives the output from the emotion engine and the AI ​​calculates new tactics to satisfy the user based on those emotions.

[0410] Step 4: Present the calculated tactics and formations to the user.

[0411] Example 1

[0412] Next, a description will be given of Example 1 of the embodiment 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".

[0413] Conventional tactics and formation suggestion systems only suggest tactics based on past data, and have the problem of not being able to make suggestions that take into account the user's emotional state. In addition, there is a lack of means to determine whether the proposed tactics and formations are optimal for the user. This makes it difficult for users to select appropriate tactics when they are nervous or in a particular emotional state.

[0414] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0415] In this invention, the server includes a means for acquiring past match data, player performance data, and opponent tactical data through a database or API, a means for preprocessing the acquired data and learning using a machine learning algorithm, a means for acquiring user emotion data and generating optimal tactics and formations based on the emotions, and a means for presenting the generated tactics and formations to the user, thereby making it possible to propose optimal tactics and formations taking into account the user's emotional state.

[0416] A "database" is a system that systematically organizes and stores information so that it can be searched and used as needed.

[0417] "API" stands for Application Program Interface, an interface for exchanging data and functions between different software programs.

[0418] "Past Match Data" is information about matches that have previously taken place, including details such as scores, player movements, and tactics.

[0419] "Player performance data" refers to data regarding a player's movements during a match, their results, physical strength, techniques, etc.

[0420] "Opponent's tactical data" refers to data regarding tactics and formations used by the opponent in the past.

[0421] "Preprocessing" is the process of cleaning and transforming data before inputting it into a machine learning model, and includes tasks such as filling in missing values ​​and normalizing the data.

[0422] A "machine learning algorithm" is a mathematical technique for learning patterns and trends from data and making predictions or classifications.

[0423] "Emotion data" is data that indicates the user's emotional state, and includes information obtained from facial expressions, voice, and the like.

[0424] "Tactics and formation" is a plan that shows the player's positioning, movements, and strategy during a match.

[0425] "Presentation" is the act of displaying and providing information to a user.

[0426] The present invention relates to a system in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system will be described below.

[0427] Get the data

[0428] The server obtains past match data, player performance data, and opponent tactical data through a database and API. A relational database such as MySQL (registered trademark) is used as the database, and a RESTful API is used as the API. This allows the latest data to be collected efficiently.

[0429] Data Preprocessing

[0430] The server preprocesses the acquired data by using Python's Pandas library to impute missing values, normalize the data, and encode categorical data, making the data suitable for machine learning algorithms.

[0431] Training a machine learning model

[0432] The server uses the pre-processed data to train machine learning models. Using libraries such as TensorFlow and PyTorch, it builds neural network models to extract patterns and trends from past match data, which can then predict optimal tactics and formations for future matches.

[0433] Acquiring emotion data

[0434] The device acquires the user's emotional data. Specifically, it uses a camera to capture the user's facial expressions and uses the OpenCV library to perform facial expression analysis. It also uses the Google Cloud Speech-to-Text API to analyze voice data. This allows the device to accurately grasp the user's emotional state.

[0435] Tactics and formation generation

[0436] The server uses the emotion data and the trained model to generate optimal tactics and formations. For example, if the user is nervous, it will suggest defensive tactics. This allows the server to provide optimal tactics according to the user's emotional state.

[0437] Presentation of tactics and formations

[0438] The terminal presents the generated tactics and formations to the user. Specifically, it displays on the screen, "Let's adopt a defensive formation to relax." This allows the user to understand the proposed tactics and put them into practice.

[0439] Examples of concrete examples and prompts

[0440] For example, if a user feels nervous before a match, the device captures the user's facial expression through the camera and analyzes it with the emotion engine. The analysis results are sent to the server, which generates a tactic that helps the user relax based on past data and emotion data. The device displays to the user, "To relax, let's adopt a defensive formation."

[0441] An example of a prompt is as follows:

[0442] "Please suggest the best tactics for the next match using past match data, player performance data, and opponent tactical data. Also, if the user is nervous, please suggest tactics that will help them relax."

[0443] In this way, a system is realized in which the server, terminals, and users work together to provide optimal tactics and formations.

[0444] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0445] Step 1: Get the data

[0446] The server retrieves past match data, player performance data, and opponent tactical data through databases and APIs. The inputs are SQL queries and API requests, and the output is the retrieved dataset. Specifically, the server connects to a MySQL database and executes SQL queries to retrieve data. It also uses RESTful APIs to retrieve the latest data from external data sources.

[0447] Step 2: Preprocessing the data

[0448] The server preprocesses the acquired data. The input is the dataset acquired in step 1, and the output is the preprocessed dataset. Specifically, the server uses Python's Pandas library to impute missing values ​​in the data, normalize the data, and encode categorical data, making the data suitable for machine learning algorithms.

[0449] Step 3: Train the machine learning model

[0450] The server trains a machine learning model using the preprocessed data. The input is the preprocessed dataset from step 2, and the output is the trained machine learning model. Specifically, the server uses libraries such as TensorFlow and PyTorch to build a neural network model to extract patterns and trends from past match data, which can then predict optimal tactics and formations for future matches.

[0451] Step 4: Obtaining emotion data

[0452] The device acquires the user's emotional data. The inputs are the user's facial expressions and voice, and the output is the analyzed emotional data. Specifically, the device uses a camera to capture the user's facial expressions and performs facial expression analysis using the OpenCV library. It also uses the Google Cloud Speech-to-Text API to analyze the voice data. This allows the device to accurately grasp the user's emotional state.

[0453] Step 5: Generate tactics and formations

[0454] The server uses the emotion data and the trained model to generate optimal tactics and formations. The inputs are the trained model from step 3 and the emotion data acquired from step 4, and the output is the generated tactics and formations. In concrete terms, the server analyzes the emotion data and generates optimal tactics according to the user's emotional state, such as proposing defensive tactics if the user is nervous.

[0455] Step 6: Present tactics and formations

[0456] The terminal presents the generated tactics and formations to the user. The inputs are the tactics and formations generated in step 5, and the output is the information presented to the user. As a specific operation, the terminal displays on the screen, "Let's adopt a defensive formation to relax." This allows the user to understand the proposed tactics and put them into practice.

[0457] (Application example 1)

[0458] Next, a description will be given of Application Example 1 of Form 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."

[0459] Conventional factory robot systems can collect production data and machine performance data, but it is difficult to comprehensively analyze this data and present optimal production tactics and work formations. In addition, because tactical proposals do not take into account the emotions of workers, it is not possible to reduce worker stress. This has led to a demand for both improving production efficiency and reducing worker stress at the same time.

[0460] 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. In this invention, the server includes a means for learning the most advanced tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for collecting production data in the factory, machine performance data, and worker emotion data, a means for analyzing the collected data and presenting optimal production tactics and work formations, and a means for recognizing the emotions of workers and proposing optimal tactics based on the emotions. This makes it possible to improve production efficiency and reduce worker stress.

[0461] "Cutting-edge tactics" are tactics that are developed using the latest technology and data analysis methods.

[0462] "Player Data" refers to information relating to a player's performance or abilities.

[0463] "Opponent Data" refers to information regarding the opponent's tactics and performance.

[0464] "Means for learning" refers to a method or device for collecting data and analyzing and learning from it using machine learning algorithms.

[0465] "Means for presenting" refers to a method or device for presenting optimal tactics and formations to a user based on the analysis results.

[0466] "Means for generating and presenting an image video" refers to a method or device for creating a simulation video to the goal based on the presented tactics and formation, and displaying it to the user.

[0467] "Factory production data" refers to information relating to production activities within a factory.

[0468] "Machine performance data" refers to information regarding the operating status and performance of machines in a factory.

[0469] "Worker emotion data" refers to information relating to the emotional state of a worker.

[0470] "Means of collection" refers to methods and devices for obtaining various data in real time.

[0471] "Analyzing means" refers to methods or devices used to analyze collected data and extract patterns and trends.

[0472] "Work formation" refers to a plan regarding worker placement and work procedures.

[0473] "Means for recognizing emotions" refers to a method or apparatus for detecting and analyzing the emotional state of a worker.

[0474] "Means for suggesting tactics" refers to a method or device for suggesting optimal tactics or work formations to a user based on analysis results and emotion data.

[0475] A system for carrying out the present invention has the following configuration. The server includes a means for learning cutting-edge tactics, player data, and opponent data, a means for presenting optimal tactics and formations to a team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for collecting production data in a factory, machine performance data, and worker emotion data, a means for analyzing the collected data and presenting optimal production tactics and work formations, and a means for recognizing the emotions of workers and proposing optimal tactics based on the emotions. The server may include a means for recognizing the emotions of a user to whom the simulation video is presented.

[0476] Hardware and Software Used

[0477] Hardware: Factory robots, emotion recognition cameras, sensors

[0478] Software: Python, TensorFlow, OpenCV, emotion recognition API (e.g. Affectiva)

[0479] Data acquisition and processing

[0480] 1. Data collection: The server uses sensors and cameras in the factory to collect production data, machine performance data, and worker emotion data in real time.

[0481] 2. Data preprocessing: The server cleanses the collected data and converts it into a format suitable for machine learning algorithms.

[0482] 3. Machine Learning: The server uses TensorFlow to learn patterns and trends from past data.

[0483] 4. Emotion recognition: The server uses OpenCV and emotion recognition API to recognize emotions from the worker's face in real time.

[0484] 5. Tactical proposal: The server proposes optimal production tactics and work formations based on the learned model and emotion data.

[0485] Examples

[0486] For example, if a production line in a factory is delayed, the system operates as follows:

[0487] 1. Data collection: The server uses sensors to collect information on the machine’s operating status in real time, and cameras to capture the facial expressions of workers.

[0488] 2. Data Preprocessing: The server cleanses the collected data and removes outliers.

[0489] 3. Machine learning: The server learns a model to identify the causes of delays based on past production data.

[0490] 4. Emotion recognition: If a worker is feeling stressed, the server uses an emotion recognition API to feed that information back to the system.

[0491] 5. Tactical Suggestion: The server identifies the cause of delays and suggests work formations that allow workers to relax.

[0492] Example prompts for generative AI models

[0493] Design a system that collects production data, machine performance data, and worker emotion data in a factory, and proposes optimal production tactics and work formations. Include a function that uses an emotion engine to recognize the emotions of workers and propose tactics to reduce stress.

[0494] In this way, applications installed on factory robots can use data to optimize production efficiency and reduce worker stress.

[0495] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0496] Step 1: Data collection

[0497] The server uses sensors and cameras in the factory to collect production data, machine performance data, and worker emotion data in real time. Specifically, it obtains machine operation status and production line progress data from the sensors, and captures worker facial expression data from the cameras. The input is data from the sensors and cameras, and the output is the collected production data, performance data, and emotion data.

[0498] Step 2: Data Preprocessing

[0499] The server cleanses the collected data and converts it into a format suitable for machine learning algorithms. Specifically, it removes outliers, fills in missing values, and standardizes the data. The input is the collected production data, performance data, and sentiment data, and the output is the cleansed data.

[0500] Step 3: Machine learning

[0501] The server uses TensorFlow to learn patterns and trends from past data. Specifically, it trains models based on past production data to identify causes of delays and improve production efficiency. The input is the cleansed data, and the output is the learned model.

[0502] Step 4: Emotion Recognition

[0503] The server uses OpenCV and emotion recognition API to recognize emotions from the worker's face in real time. Specifically, it analyzes facial expression data acquired from the camera and identifies the worker's emotional state. The input is facial expression data from the camera, and the output is the recognized emotion data.

[0504] Step 5: Tactical proposal

[0505] The server proposes optimal production tactics and work formations based on the trained model and emotion data. Specifically, it identifies the cause of delays and generates work formations that allow workers to relax. The inputs are the trained model and recognized emotion data, and the output is the proposed production tactics and work formations.

[0506] Step 6: Image video generation and presentation

[0507] The server creates a simulation video of the run to the goal based on the proposed tactics and formation, and displays it to the user. Specifically, the server uses simulation software to generate a video based on the generated tactics and formation, and transmits it to the user's terminal. The input is the proposed tactics and formation, and the output is the generated simulation video.

[0508] Example 2

[0509] Next, a second embodiment of the second embodiment will be described. 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."

[0510] Conventional tactical and formation presentation systems do not fully consider the game conditions and team situations, and lack the functionality to provide feedback on the user's emotions, making it difficult to provide optimal tactics and formations. In addition, because the model is not adjusted based on the user's emotions, it is not possible to increase user satisfaction.

[0511] 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.

[0512] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations for a team based on the learned data, a means for generating and presenting an image video up to the goal based on the presented tactics and formations, a means for a user to input game conditions and team situations, a means for preprocessing the input data, a means for calculating optimal tactics and formations using a machine learning model, a means for presenting the calculation results to the user, a means for recognizing the user's emotions, and a means for adjusting the model based on the recognition results. This makes it possible to present optimal tactics and formations taking into account game conditions and team situations, and further increases user satisfaction by feeding back the user's emotions.

[0513] "State-of-the-art tactical, player and opponent data" refers to tactical information, player performance data and opponent tactical data collected using the latest technology and methods.

[0514] "Means of learning" refers to the process of using machine learning algorithms to analyze data and generate models.

[0515] "Means for presenting optimal tactics and formations to a team" refers to a process of presenting to a user tactics and formations that are most suitable for specific match conditions and team situations based on learned data.

[0516] "Means for generating and presenting an image video leading up to the goal" refers to the process of simulating plays during a match based on presented tactics and formations, and presenting the results to the user in video format.

[0517] "Means for users to input match conditions and team status" refers to an interface that enables users to input the conditions for the next match and the current status of the team into the system.

[0518] The "means for preprocessing input data" refers to a process of analyzing data entered by a user and performing preprocessing such as filling in missing values ​​and normalizing the data.

[0519] "Means for calculating optimal tactics and formations using a machine learning model" refers to the process of inputting preprocessed data into a machine learning model and calculating optimal tactics and formations.

[0520] "Means of presenting the calculation results to the user" refers to the process of displaying to the user the tactics and formations calculated by the machine learning model.

[0521] "Means for recognizing user emotions" refers to the process of analyzing and recognizing emotions from a user's facial expressions, voice, text input, etc.

[0522] The "means for adjusting the model based on the recognition result" refers to a process of receiving the user's emotion recognition result as feedback and adjusting the machine learning model. The server may include a means for adjusting the machine learning model based on the result of the recognition by the means for recognizing the emotion of the user presented with the simulation video.

[0523] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0524] This invention is a system in which the user inputs the match conditions and team situation, and the server calculates the optimal tactics and formation based on that and presents it to the user. Furthermore, it has the function of recognizing the user's emotions and adjusting the model based on that feedback.

[0525] Hardware and Software Used

[0526] The server processes the data using machine learning libraries such as Python and TensorFlow. The terminal provides an interface for users to input data and has a display to show the results. The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice.

[0527] Program Processing

[0528] The server first receives the match conditions and team status input by the user. This includes the weather, the strength of the opposing team, and the condition of the players. The server then preprocesses this data, filling in missing values ​​and normalizing the data. The preprocessed data is then input into a machine learning model to calculate optimal tactics and formations.

[0529] The calculation results are presented to the user via the device. For example, specific advice such as "Use a 4-4-2 formation in the next game" is displayed. After the user confirms the results, the emotion engine analyzes the user's facial expressions and voice to recognize emotions. For example, if the user shows a happy expression, that information is fed back to the server. The server uses this feedback to adjust the machine learning model and prioritize presenting similar tactics and formations the next time.

[0530] Examples and prompts

[0531] As a concrete example, consider a case where a user inputs the conditions for the next match. For example, the following prompt is input to a generative AI model:

[0532] Our next match will be in rainy weather, and our opponent is one of the best in the league. Our team has been winning a lot recently, but one of our main players has a slight injury. What are the best tactics and formations to use?

[0533] The server receives this prompt and uses the generated model to calculate the optimal tactics and formation. For example, it might present the user with a result such as, "In a match on rainy days, it is best to emphasize defense and use a 4-4-2 formation." If the user shows a happy expression after the match, the emotion engine feeds that information back to the server, and the server uses that information to adjust the model so that it will present the same tactics and formation the next time.

[0534] In this way, a system is realized that provides optimal tactics and formations based on the user's input data and emotional feedback.

[0535] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0536] Step 1:

[0537] The user inputs the match conditions and team status.

[0538] Through the device interface, the user inputs the conditions of the next match and the team's situation, such as the weather, the strength of the opposing team, the condition of the players, etc. The input data is stored on the device in a standard format such as JSON.

[0539] Step 2:

[0540] The terminal transmits the input data to the server.

[0541] The terminal transmits the data entered by the user to the server, using a secure communications protocol, where the data is received and prepared for analysis.

[0542] Step 3:

[0543] The server preprocesses the data received.

[0544] The server preprocesses the received data. Specifically, it complements missing values ​​and normalizes the data. For example, if a player's condition is not entered, it complements the estimated value from past data. The preprocessed data is converted into a format for input into the machine learning model.

[0545] Step 4:

[0546] The server uses machine learning models to calculate optimal tactics and formations.

[0547] The server inputs the preprocessed data into a machine learning model to calculate optimal tactics and formations. For example, it runs a model using Python's TensorFlow library and determines that a 4-4-2 formation is optimal. The calculation results are saved in JSON format.

[0548] Step 5:

[0549] The server transmits the calculation result to the terminal.

[0550] The server sends the calculation results to the terminal, which receives them in JSON format and converts them into a format for display to the user.

[0551] Step 6:

[0552] The terminal displays the results to the user.

[0553] The terminal displays the received results to the user. For example, it displays on the screen, "Please use a 4-4-2 formation in the next game." The user decides on the tactics for the next game based on this information.

[0554] Step 7:

[0555] The emotion engine recognizes the user's emotions.

[0556] The emotion engine recognizes the facial expressions and voices of the user after viewing the results. For example, if the user shows a happy expression, that information is captured. Emotion data is analyzed in real time.

[0557] Step 8:

[0558] The emotion engine feeds back the recognition results to the server.

[0559] The emotion engine feeds back the recognized emotion data to the server. For example, it sends information that "the user showed a happy expression." The feedback data is stored on the server side and used for analysis.

[0560] Step 9:

[0561] The server adjusts the model based on the feedback.

[0562] The server adjusts the machine learning model based on the feedback. For example, it updates the model so that the tactics and formations that the user showed a happy expression will be presented preferentially next time. The adjustments to the model are reflected in the calculation of the next tactics and formations.

[0563] (Application example 2)

[0564] Next, a description will be given of Application Example 2 of Form 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."

[0565] In conventional factory operations, it was difficult to efficiently calculate tactics for optimizing machine operation and placement. In addition, the system could not continue learning based on feedback that took into account the emotions of the operator, which led to issues with insufficient efficiency in operations. This could result in a decline in the productivity and efficiency of the entire factory.

[0566] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0567] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for calculating tactics and placements for optimizing the operation of machines in the factory, and a means for recognizing the user's emotions and allowing the system to continue learning based on the feedback. This makes it possible to efficiently optimize operations in the factory and for the system to continue learning based on feedback that takes the user's emotions into account.

[0568] "Cutting-edge tactics" are tactics derived based on the latest technology and data analysis.

[0569] "Player Data" means information relating to a player's performance or abilities.

[0570] "Opponent Data" means information regarding the opponent's tactics and performance.

[0571] A "learning tool" refers to the methods and techniques used to analyze data and train models.

[0572] "Presentation medium" refers to the method or technique used to display information to the user.

[0573] An "image video to the goal" is a simulation video that is generated based on the presented tactics and formation.

[0574] "Tactics and layouts for optimizing the operation of machines in a factory" refers to strategies and layouts for achieving efficient operation of machines and equipment in a factory.

[0575] "Means of recognizing user emotions" refers to methods and technologies for analyzing emotions from a user's facial expressions, voice, text input, etc.

[0576] "Means for the system to continue learning based on feedback" refers to methods and techniques that allow the system to continually improve using feedback information from users.

[0577] A system for carrying out this invention has the following configuration: The server includes a means for learning cutting-edge tactics, player data, and opponent data, a means for presenting optimal tactics and formations to a team based on the learned data, a means for generating and presenting an image video leading up to the goal based on the presented tactics and formations, a means for calculating tactics and placements for optimizing the operation of machines in a factory, and a means for recognizing the emotions of the user and allowing the system to continue learning based on the feedback.

[0578] Hardware and Software Used

[0579] Hardware

[0580] Camera: Used to capture the user's facial expressions.

[0581] Microphone: Used to capture the user's voice.

[0582] Computer: Used to process data and run models.

[0583] software

[0584] Python: Used to implement the program.

[0585] scikit-learn: Used to train and predict machine learning models.

[0586] emotion_recognition: Used as an emotion engine library.

[0587] Data processing and calculation

[0588] The server first reads the factory status data and inputs it into the machine learning model. The model predicts the optimal tactics and outputs the results. Next, it recognizes the user's emotions and inputs that information into the system as feedback. The system continues to learn based on the feedback and improves the accuracy of the next prediction.

[0589] Examples

[0590] For example, it can calculate the optimal placement and operation patterns for robots in a factory to operate efficiently. The emotion engine recognizes whether the user is satisfied, and if the user is satisfied, it presents the tactic again.

[0591] Examples of prompt statements

[0592] Please enter the current status of your factory. For example, the operation status of robots, the status of the production line, etc.

[0593] Provide a video feed to recognize user emotions.

[0594] It calculates the optimal tactic and presents it to the user.

[0595] In this way, factory operations can be efficiently optimized and the system can continuously learn based on user feedback, taking into account user emotions.

[0596] The flow of the identification process in the application example 2 will be described with reference to FIG.

[0597] Step 1:

[0598] The server reads the factory status data. Specifically, it collects data such as the operation status of robots and the status of the production line, and inputs this data into the machine learning model. The input data includes past operation data and current status data. This allows the model to grasp the current state of the factory.

[0599] Step 2:

[0600] The server calculates optimal tactics and deployment based on the learned data. Specifically, it uses a machine learning model (e.g., RandomForestClassifier) ​​to predict tactics and deployment to optimize the operation of machines in the factory. The input data is the factory status data collected in step 1, and the output is a proposal for optimal tactics and deployment.

[0601] Step 3:

[0602] The server captures the user's facial expressions and voice using a camera and microphone to recognize the user's emotions. Specifically, it uses the emotion_recognition library to analyze the user's emotions. The input data is the user's video feed and audio data, and the output is the user's emotional state.

[0603] Step 4:

[0604] The server inputs the user's emotions into the system as feedback. Specifically, the system continues to learn based on the recognized emotion data. This improves the accuracy of the next prediction. The input data is the user's emotion data obtained in step 3, and the output is the updated machine learning model.

[0605] Step 5:

[0606] The server presents the optimal tactics and placements to the user. Specifically, it displays the generated tactics and placements to the user. The input data are the optimal tactics and placements calculated in step 2, and the output is the information presented to the user.

[0607] Step 6:

[0608] The user checks the presented tactics and placements and provides feedback if necessary. Specifically, the emotion engine recognizes whether the user is satisfied, and if the user is satisfied, the tactic is presented again. The input data is the user's feedback, and the output is the system's learning data.

[0609] Example 3

[0610] Next, a third embodiment of the third embodiment will be described. 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."

[0611] In conventional tactical and formation presentation systems, if a user is dissatisfied with the presented tactics, there is a lack of a means to reflect that feedback. In addition, there is a problem that the presentation of specific practice methods for realizing tactics and formations is insufficient, making it difficult for users to effectively execute tactics.

[0612] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0613] In this invention, the server includes a means for learning the most advanced tactics, player data, and opponent data, a means for presenting the optimal tactics and formations for a team based on the learned data, a means for generating and presenting an image video of the goal based on the presented tactics and formations, a means for analyzing the user's emotions and providing feedback, and a means for generating and presenting new tactics based on the feedback information. This makes it possible to present new tactics that reflect the user's feedback, and also present specific practice methods for realizing the tactics and formations. The server may include a means for presenting practice methods for realizing the tactics and formations.

[0614] "Cutting-edge tactics" refers to strategies designed based on the latest data analysis and tactical theory.

[0615] "Player data" refers to data including information about an individual player's performance, skills, physical fitness, past match results, etc.

[0616] "Opponent data" refers to data that includes information such as the opponent's tactics, player characteristics, past match results, etc.

[0617] "Means of learning" refers to methods that use machine learning and data analysis techniques to analyze tactics and player data and derive optimal tactics.

[0618] "Presentation means" refers to the method of displaying the analysis results and generated tactics and formations to the user in visual or textual form.

[0619] "Image video leading up to the goal" refers to a video that simulates and visually depicts the movements of players and the ball based on presented tactics and formations.

[0620] "Means for analyzing emotions" refers to techniques or algorithms for analyzing a user's emotions, including, for example, methods for determining emotions through user feedback or facial expression recognition.

[0621] "Means of providing feedback" refers to the method by which the system generates new tactics and formations based on the analyzed user's emotional information.

[0622] "Means for generating new tactics" refers to a method for redesigning and presenting optimal tactics and formations taking into account user feedback information.

[0623] "Means for presenting a practice method" refers to a method for presenting to a user specific training menus and practice points necessary to realize tactics and formations.

[0624] This invention is a system that generates an image video of the path to the goal based on the tactics and formations presented by the user, and also presents a practice method for achieving those tactics and formations.It also includes a function to analyze the user's emotions and generate new tactics based on the feedback.

[0625] System Configuration

[0626] Hardware and Software

[0627] Servers play a central role in data learning, analysis, simulation, video generation, emotion analysis, and feedback processing, and therefore require servers equipped with high-performance processors and large-capacity memory.

[0628] Blender is used as the 3D modeling software, which allows for realistic simulation of player and ball movements.

[0629] Unity is used as animation software, which allows for the generation of image videos based on the simulation results.

[0630] A machine learning model is used as a sentiment analysis engine to analyze user emotions and provide feedback.

[0631] Program Processing

[0632] Data learning and analysis

[0633] The server learns cutting-edge tactics, player data, and opponent data, including past match data, player performance data, opponent tactical data, etc. Based on this data, it analyzes the best tactics and formations for each team.

[0634] Presentation of tactics and formations

[0635] The server presents the optimal tactics and formations to the user based on the learned data. The presented tactics and formations are displayed on the user's device.

[0636] Image video generation

[0637] The server uses Blender to simulate the movements of the players and the ball. It then uses Unity to generate an image video based on the simulation results. The generated video is sent to the user's device, where the user can watch it.

[0638] Presentation of practice methods

[0639] Based on the learned data and generative AI models, the server calculates what kind of practice each player needs to achieve the tactics and formations. Specifically, it calculates the necessary skills and abilities based on each player's performance data and past match data, and suggests training methods.

[0640] Sentiment Analysis and Feedback

[0641] The emotion analysis engine analyzes the user's emotions. For example, if the user is dissatisfied with a particular tactic, the user feeds that information back to the system. The server generates a new tactic based on the feedback information and presents it to the user.

[0642] Examples of concrete examples and prompts

[0643] Examples

[0644] A user inputs into the system, "I want to see some attacking tactics in a 4-4-2 formation."

[0645] The server receives the input data and uses Blender to simulate the movement of the players and the ball. For example, it calculates the movement of player A dribbling from the right side and player B receiving the pass in the center.

[0646] The server uses Unity to generate image videos based on the simulation results. For example, it realistically reproduces the dribbling of player A and the passing movements of player B.

[0647] The video generated by the server is transmitted to the user's terminal, and the user watches the video.

[0648] Based on each player's past match data, the server suggests dribbling practice for Player A and passing practice for Player B.

[0649] Users can check the practice methods and incorporate them into their actual training.

[0650] The emotion engine analyzes the user's dissatisfaction and provides feedback to the server.

[0651] The server generates new tactics based on the feedback and presents them to the user.

[0652] Examples of prompt statements

[0653] "Please generate a video showing offensive tactics using a 4-4-2 formation."

[0654] "Please tell me how each player can practice to implement the 4-4-2 formation."

[0655] "I'm not happy with this tactic. Please suggest a new one."

[0656] The above is an embodiment of the invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0657] Step 1:

[0658] The user inputs tactics and formations.

[0659] The user inputs the desired tactics and formations through the system interface, for example, "I want to see attacking tactics in a 4-4-2 formation." The input data is then sent to the server.

[0660] Step 2:

[0661] The server receives and parses the input data.

[0662] The server receives tactical and formation data sent by the user. It analyzes the received data and extracts information necessary for the simulation. Specifically, it analyzes the type of tactics and the placement of the formation. The input is the user's tactical and formation data, and the output is the analyzed simulation information.

[0663] Step 3:

[0664] The server performs the simulation using 3D modeling software.

[0665] The server uses Blender to simulate the movements of players and the ball. For example, it calculates the movements of player A dribbling from the right side and player B receiving the pass in the center. The input is the analyzed simulation information, and the output is the simulation result.

[0666] Step 4:

[0667] The server uses animation software to generate moving images.

[0668] The server uses Unity to generate image videos based on the simulation results. For example, it realistically reproduces the dribbling of player A and the passing movements of player B. The input is the simulation results, and the output is the generated image video.

[0669] Step 5:

[0670] The video generated by the server is sent to the user's terminal.

[0671] The server transmits the generated image video to the user's terminal. The transmission uses data transfer technology via the Internet. The input is the generated image video, and the output is the video transmitted to the user's terminal.

[0672] Step 6:

[0673] A user watches a video.

[0674] The user watches the image video received on the device. Through the video, the user can confirm the specific movements of the tactics and formations. The input is the video sent to the user's device, and the output is the user's viewing behavior.

[0675] Step 7:

[0676] The server calculates the practice method and presents it to the user.

[0677] Based on the learned data and generative AI models, the server calculates what kind of practice each player needs to achieve the tactics and formations. Specifically, based on each player's performance data and past match data, it calculates the necessary skills and abilities and suggests training methods. The input is each player's performance data and past match data, and the output is the calculated training method.

[0678] Step 8:

[0679] The user checks the practice method.

[0680] The user confirms the practice method presented on the terminal. The practice method includes a specific training menu and practice points. The input is the calculated practice method, and the output is the user's confirmation action.

[0681] Step 9:

[0682] The emotion engine analyzes the user's emotions and provides feedback.

[0683] The emotion engine analyzes the user's emotions. For example, if a user is dissatisfied with a particular tactic, it feeds that information back to the system. The input is the user's emotion data, and the output is the feedback information.

[0684] Step 10:

[0685] The server generates new tactics based on the feedback and presents them to the user.

[0686] The server generates new tactics based on the feedback information from the emotion engine. The generated tactics are sent to the user's device and presented to the user. The input is the feedback information, and the output is the newly generated tactics.

[0687] (Application example 3)

[0688] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0689] Conventional systems only provide tactics and formations, and do not provide specific instructions on actual movements or practice methods. In addition, there was not enough adjustment based on simulations or feedback regarding the optimization of robot movements and work within the factory. This made it difficult to create an efficient work environment.

[0690] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0691] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations for a team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for generating and presenting a simulation video of the robot's movements and work in the factory, a means for presenting the optimal work method based on the performance data and past work data of each robot, and a means for analyzing the feedback of the workers with an emotion engine and adjusting the work method and the robot's movements. This makes it possible to present specific movements of tactics and formations, and present and adjust efficient work methods for robots in the factory.

[0692] "Cutting-edge tactics" refers to strategies and formations that are developed using the latest technology and data analysis.

[0693] "Player data" refers to information such as an individual player's performance, skills, and past match results.

[0694] "Opponent data" refers to information such as the opponent's tactics, player characteristics, and past match results.

[0695] "Learning means" refer to the methods and techniques for collecting data, analyzing it, and building models.

[0696] "Presentation medium" refers to the methods or techniques used to present information to the user visually or audibly.

[0697] An "image video leading up to the goal" is a video that is generated based on tactics and formations and visually depicts the movements leading up to the goal.

[0698] A "simulation video of robot movements and work in a factory" is a video that virtually reproduces the movements and work of a robot in a factory.

[0699] "Performance data" refers to data concerning the performance of a robot or athlete, such as their movements, work efficiency, and accuracy.

[0700] "Past work data" refers to data regarding the content and results of work performed in the past.

[0701] An "emotion engine" is a technology that analyzes user emotions and feedback and adjusts system behavior based on that.

[0702] A "system" is a device or program with a set of functions that is composed of multiple means or technologies.

[0703] The system for implementing this invention is composed of three main elements: a server, a terminal, and a user. The specific roles and processing contents of each element are explained below.

[0704] server

[0705] The server learns the latest tactics, player data, and opponent data, and based on this, presents the optimal tactics and formations for each team. Specifically, the server uses the following software and hardware:

[0706] Software: Python, NumPy, Matplotlib, scikit-learn

[0707] Hardware: A server with a powerful processor and large memory capacity

[0708] The server collects data, analyzes it, and builds a model. For example, it generates optimal tactics and formations using past match data and player performance data. It also generates an image video of the path to the goal based on the generated tactics and formations, and presents it to the user.

[0709] In addition, it generates simulation videos of robots' movements and work in the factory, and suggests optimal work methods based on each robot's performance data and past work data. It also analyzes feedback from workers using an emotion engine to adjust work methods and robot movements.

[0710] Terminal

[0711] A terminal is a device that allows a user to receive and display information provided by a server. Specifically, this includes smartphones, tablets, and personal computers. A terminal uses the following software and hardware:

[0712] Software: Web browser, dedicated application

[0713] Hardware: Smartphones, tablets, computers

[0714] The terminals display images of tactics and formations sent from the server, robot simulation videos, optimal work methods, etc. Based on this information, users can understand and practice tactics and work methods.

[0715] User

[0716] The user uses the server and the terminal to implement tactics and work methods based on the information provided. The user performs the following specific operations:

[0717] Watch and understand videos that provide examples of tactics and formations.

[0718] Participants watch simulation videos of robot movements and operations within a factory to learn optimal work methods.

[0719] The worker's feedback is sent to the server, and the work method is adjusted based on the results analyzed by the emotion engine.

[0720] Examples

[0721] For example, if a user wants to optimize the movement of a robot in a factory, he can send a prompt to the server like this:

[0722] "Simulate the robot's movements in a factory and suggest the best way to perform tasks. Then adjust your tactics based on worker feedback."

[0723] The server receives the prompt text, generates a simulation video of the robot's movements and work, and presents the optimal way to work.The user can then practice the work based on this and send feedback to the server, resulting in a more efficient work environment.

[0724] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0725] Step 1:

[0726] The server collects state-of-the-art tactical and player data and opponent data, including past match data, player performance data, opponent tactical data, etc. These data are input and stored in a database.

[0727] Step 2:

[0728] The server analyzes the collected data and uses a generative AI model to generate optimal tactics and formations. Specifically, it uses Python and scikit-learn to learn the data and build a model. The input is the collected data, and the output is the optimal tactics and formations.

[0729] Step 3:

[0730] The server generates an image video of the path to the goal based on the generated tactics and formation. This is done using 3D modeling software and animation software. The input is the generated tactics and formation, and the output is an image video.

[0731] Step 4:

[0732] The server generates simulation videos of the robot's movements and work in the factory, using the robot's performance data and past work data. The input is the robot data, and the output is the simulation video.

[0733] Step 5:

[0734] The server presents the optimal work method based on the performance data and past work data of each robot. Specifically, it analyzes the data using KMeans clustering and calculates the optimal work method. The input is the robot data, and the output is the optimal work method.

[0735] Step 6:

[0736] The terminal displays tactics and formation image videos sent from the server, robot simulation videos, optimal work methods, etc. The input is data from the server, and the output is visual information presented to the user.

[0737] Step 7:

[0738] The user puts tactics and work methods into practice based on the information provided through the terminal. Specifically, the user watches visualization videos of tactics and formations, and watches simulation videos of robot movements and work in a factory. The input is information from the terminal, and the output is the user's understanding and practice.

[0739] Step 8:

[0740] Users send worker feedback to the server through their terminals. The server analyzes the feedback using an emotion engine and adjusts tactics and work methods. The input is the user feedback, and the output is the adjusted tactics and work methods.

[0741] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0742] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0743] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0744] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0745] [Second embodiment]

[0746] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0747] 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.

[0748] 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 wide area network (WAN) and / or a local area network (LAN).

[0749] 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.

[0750] 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 the voice according to instructions from the processor 46.

[0751] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0752] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0753] The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0754] Fig. 4 shows an example of 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0759] "Example 1"

[0760] The system of the present invention acquires cutting-edge tactics, player data, and opponent data through a database, API, etc., and performs learning using a machine learning algorithm. Specifically, past match data, player performance data, opponent tactical data, etc. are input, and patterns and trends are extracted from this data.

[0761] "Example 2"

[0762] As a means of presenting the optimal tactics and formations for a team based on learned data, the optimal tactics and formations are calculated using a model generated by a machine learning algorithm and presented to the user. Specifically, the optimal tactics and formations are calculated based on the match conditions and team situation specified by the user and presented to the user. "Example 3"

[0763] As a means of generating and presenting an image video of the goal based on the presented tactics and formation, a video visually expressing the presented tactics and formation is generated using 3D modeling software, animation software, etc., and this is presented to the user. Specifically, based on the presented tactics and formation, the movements of the players and the ball are simulated, and this is generated and presented as a video.

[0764] "Example 4"

[0765] As a means of presenting training methods to realize the proposed tactics and formations, the system calculates what kind of training each player needs to do to realize the proposed tactics and formations based on the learned data and the generated model, and presents this to the user. Specifically, the system calculates the skills and abilities required by each player based on the performance data and past match data of each player, and presents training methods based on this.

[0766] The process flow of each embodiment will be described below.

[0767] "Example 1"

[0768] Step 1: Obtain cutting-edge tactics, player data, and opponent data through databases, APIs, etc.

[0769] Step 2: The acquired data is fed into a machine learning algorithm to learn from it, using data from past matches, player performance data, opponent tactical data, etc. to extract patterns and trends.

[0770] "Example 2"

[0771] Step 1: Calculate optimal tactics and formations using a model generated by a machine learning algorithm.

[0772] Step 2: Present the calculated tactics and formation to the user. At this time, the system presents the optimal tactics and formation based on the match conditions and team situation specified by the user.

[0773] "Example 3"

[0774] Step 1: Using 3D modeling software, animation software, etc., create a video that visually represents the proposed tactics and formations.

[0775] Step 2: The generated video is presented to the user. At this time, the movements of the players and the ball are simulated based on the presented tactics and formation, and this is presented as a video.

[0776] "Example 4"

[0777] Step 1: Based on the learned data and the generated model, calculate what kind of practice each player needs to do to achieve the proposed tactics and formation.

[0778] Step 2: Present the calculated training method to the user. At this time, the skills and abilities required by each player are calculated based on the performance data of each player and past match data, and the training method is presented based on this.

[0779] Example 1

[0780] Next, a description will be given of Example 1 of Form 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".

[0781] In conventional tactical analysis systems, data acquisition, pre-processing, machine learning model training and evaluation were performed separately, and the system lacked efficiency as an integrated system. In addition, the system did not adequately present optimal tactics and formations, or even training methods to achieve them. This limited the improvement of team performance.

[0782] 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. In this invention, the server includes a means for acquiring past match data, player performance data, and opponent tactical data through a database or API, a means for preprocessing the acquired data, a means for learning a machine learning model using the preprocessed data, a means for evaluating the performance of the learned model, a means for deploying the evaluated model, a means for presenting optimal tactics and formations for the team based on the learned data, and a means for generating and presenting an image video up to the goal based on the presented tactics and formations. This makes it possible to consistently perform the processes from data acquisition to model learning, evaluation, deployment, and presentation of tactics, thereby efficiently improving team performance.

[0783] A "database" is a system for systematically storing data and efficiently searching and managing it.

[0784] "API" stands for Application Programming Interface, an interface for exchanging data and functions between different software programs.

[0785] "Past match data" is data that includes information about matches that have previously been played.

[0786] "Player performance data" refers to data relating to a player's movements during a match, their performance, physical strength, etc.

[0787] "Opponent's tactical data" refers to data regarding the opponent's tactics and formation.

[0788] "Preprocessing" is the process of converting data into a format suitable for learning from a machine learning model.

[0789] A "machine learning model" is an algorithm that learns patterns and trends from data and makes predictions and classifications.

[0790] "Evaluation" is the process of measuring the performance of a trained machine learning model and confirming its validity.

[0791] "Deployment" refers to the process of placing a machine learning model that has completed training and evaluation in an actual production environment and making it available for use.

[0792] "Tactics" refers to a team's strategy and playing style in a match.

[0793] A "formation" is a diagram that shows the positions and roles of players during a match.

[0794] An "image video" is a visual simulation video generated based on presented tactics and formations.

[0795] This invention is a system in which a server obtains past match data, player performance data, and opponent tactical data via a database or API, preprocesses this data, and presents optimal tactics and formations through a series of processes in which the server trains, evaluates, and deploys a machine learning model.

[0796] The server first obtains the necessary data using a database or API. A typical relational database management system (RDBMS) is used as the database, and a RESTful API is used as the API. For example, a sports data API can be used to obtain past match data.

[0797] The server then preprocesses the data, including imputing missing values, normalizing the data, encoding categorical data, etc., using the Python Pandas and Scikit-learn libraries.

[0798] The server uses the preprocessed data to train the machine learning model. Machine learning algorithms such as random forest and support vector machine (SVM) are used. Libraries such as Scikit-learn and TensorFlow are used for this purpose.

[0799] To evaluate the performance of the trained model, the server uses methods such as cross-validation and confusion matrix, and calculates evaluation indices such as precision, recall, and F1 score of the model.

[0800] Once the evaluation is complete, the model is deployed by the server using a web framework such as Flask or Django. The deployed model receives new data as input in real time and makes predictions.

[0801] As a concrete example, the server retrieves past match data from a sports data API, preprocesses the data using Pandas, trains a random forest model using Scikit-learn, evaluates the model using cross-validation, and deploys the model using Flask.

[0802] An example prompt is, "Use past match data, player performance data, and opponent tactical data to build a machine learning model to predict the outcome of the next match."

[0803] This system makes it possible to consistently collect data, train models, evaluate them, deploy them, and present tactics, thereby efficiently improving team performance.

[0804] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0805] Step 1: Get the data

[0806] The server retrieves past match data, player performance data, and opponent tactical data through a database or API. Inputs include API endpoint URLs and database queries. Specifically, the server sends API requests and receives data in JSON format. The output is the retrieved raw data.

[0807] Step 2: Preprocessing the data

[0808] The server preprocesses the acquired data. The input includes the raw data acquired in step 1. Specifically, the server creates a data frame using the Pandas library, imputes missing values, normalizes the data, and encodes categorical data. The output is the clean data after preprocessing.

[0809] Step 3: Train the machine learning model

[0810] The server trains a machine learning model using the preprocessed data. The input includes the preprocessed data from step 2. Specifically, the server builds a random forest model using the Scikit-learn library and trains the model with the data. The output is a trained machine learning model.

[0811] Step 4: Evaluate the model

[0812] The server evaluates the performance of the trained model. The inputs include the model trained in step 3 and the preprocessed data. Specifically, the server performs cross-validation and calculates evaluation metrics such as precision, recall, and F1 score. The output is the evaluation result.

[0813] Step 5: Deploy the model

[0814] The server deploys the model once evaluation is complete. The input includes the model evaluated in step 4. Specifically, the server builds a web service using the Flask framework to expose the model as an endpoint. The output is a web service running the deployed model.

[0815] Step 6: Present tactics and formations

[0816] The server then presents the best tactics and formations for the team based on the learned data. The inputs include the model deployed in step 5 and new match data. Specifically, the server inputs the new data into the model and predicts the best tactics and formations. The output is the presented tactics and formations.

[0817] Step 7: Generate and present image videos

[0818] The server generates and presents an image video of the goal based on the presented tactics and formation. The input includes the tactics and formation presented in step 6. In concrete terms, the server uses an image generation algorithm to visually simulate the tactics and formation. The output is the generated image video.

[0819] (Application example 1)

[0820] Next, a description will be given of Application Example 1 of Form 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".

[0821] Conventional sports tactics analysis systems and factory robot operation optimization systems function independently, making comprehensive data analysis and optimization difficult. In addition, there was no system that simultaneously optimized sports tactics and factory robot operations, making efficient data utilization impossible. As a result, tactical optimization of sports teams and improvement of production efficiency in factories were not fully achieved.

[0822] 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.

[0823] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for learning the operation data of robots in a factory and extracting optimal movement patterns, a means for presenting an efficient arrangement of the robots based on the extracted movement patterns, and a means for realizing optimization of the manufacturing line based on the presented arrangement. This makes it possible to simultaneously optimize sports tactics and the operation of robots in a factory.

[0824] "Tactics" refers to the plans and methods a team or player uses to achieve victory in a sport or competition.

[0825] "Player data" refers to information regarding a player's performance, abilities, past match results, etc.

[0826] "Opponent data" refers to information regarding the opponent's tactics, player performance, past match results, etc.

[0827] A "learning means" refers to a method or device that takes data and uses machine learning algorithms to extract patterns and trends.

[0828] "Presentation means" refers to a method or device that displays optimal tactics, formations, and movement patterns based on learned data.

[0829] An "image video" is a visual simulation that is generated based on presented tactics and formations.

[0830] A "factory robot" is an automated machine used in a factory.

[0831] "Operational data" refers to information regarding the robot's operating history and performance.

[0832] A "motion pattern" is a series of movements or steps that a robot follows to perform a specific task.

[0833] "Efficient layout" refers to the location and layout method in which robots and mechanical devices are placed most effectively.

[0834] A "production line" is a series of machines or equipment arranged to efficiently produce products.

[0835] "Optimization" refers to adjusting a system or process to be most effective in achieving a particular purpose.

[0836] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server plays a central role in collecting, learning, and analyzing data. The terminal is a device through which the user interfaces with the system, and the user is responsible for operating the system and checking the results.

[0837] Server Roles

[0838] The server processes and calculates data using the following hardware and software:

[0839] Hardware: Powerful processor, ample memory and storage

[0840] Software: Python, Pandas, Scikit-learn, Joblib

[0841] The server first collects past match data, player performance data, opponent tactical data, factory robot operation data, and production line data through databases and APIs. It then uses machine learning algorithms to learn from this data and extract patterns and trends. Specifically, it analyzes the data using a random forest regression model to derive optimal tactics and movement patterns.

[0842] Terminal Roles

[0843] A terminal is a device through which a user interfaces with the system. It can be a smartphone, tablet, or PC. The terminal receives the analysis results sent from the server and visually presents them to the user. For example, it shows the optimal tactics and formations of a sports team, or the efficient placement of robots in a factory.

[0844] User Roles

[0845] The user operates a terminal to access the system and input the necessary data. The user also checks the analysis results sent from the server and optimizes tactics and placement based on the results. The user follows the training methods and production line optimization procedures presented by the system.

[0846] Examples

[0847] For example, when a robot operating in a factory assembles a product, it can learn optimal movement patterns based on past data and perform efficient movements, improving the efficiency of the production line and enabling cost reduction.

[0848] Examples of prompt statements

[0849] Build a system that uses operational data from robots in factories to learn optimal operating patterns and achieve efficient operation. Past operational data, robot performance data, and production line data are input, and learning is performed using a random forest regression model.

[0850] In this way, by having the server, terminals, and users work together to operate the system, it becomes possible to simultaneously optimize sports tactics and the operation of robots in a factory.

[0851] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0852] Step 1:

[0853] The server collects past match data, player performance data, opponent tactical data, robot operation data in the factory, and production line data through databases and APIs. This data is stored on the server in CSV files or JSON format. The input is data obtained from various databases and APIs, and the output is raw data stored on the server.

[0854] Step 2:

[0855] The server preprocesses the collected data, specifically by imputing missing values, normalizing data, encoding categorical data, etc. The input is the raw data collected in step 1, and the output is the preprocessed data.

[0856] Step 3:

[0857] The server uses the preprocessed data to train a machine learning model, specifically a random forest regression model, to learn patterns and trends in the data. The input is the preprocessed data, and the output is the trained machine learning model.

[0858] Step 4:

[0859] The server uses the trained machine learning model to make predictions on new data, such as predicting the optimal movement pattern for a robot in a factory or the optimal tactics for a sports team. The input is the new data, and the output is the predicted result.

[0860] Step 5:

[0861] The server transmits the prediction results to the terminal. The terminal visually presents the received prediction results to the user. Specifically, it displays dashboards, graphs, simulation videos, etc. The input is the prediction results transmitted from the server, and the output is the visual information presented to the user.

[0862] Step 6:

[0863] The user operates the terminal to check the prediction results and optimize tactics and placement as necessary. Specifically, the user follows the practice methods and production line optimization procedures presented by the system. The input is the prediction results displayed on the terminal, and the output is the user's actions.

[0864] In this way, by having the server, terminals, and users work together to operate the system, it becomes possible to simultaneously optimize sports tactics and the operation of robots in a factory.

[0865] Example 2

[0866] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0867] Conventional methods for determining tactics and formations make it difficult to quickly and accurately calculate optimal tactics according to match conditions and team situations. In addition, there was a lack of means to understand how the presented tactics and formations specifically worked, making it difficult to apply them in actual matches.

[0868] 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.

[0869] In this invention, the server includes a means for a user to input match conditions and team situations, a means for transmitting the input data to the server, a means for the server to analyze the data received and input it to the generative AI model, a means for calculating optimal tactics and formations using the generative AI model, and a means for presenting the calculation results to the user. This makes it possible to quickly and accurately calculate optimal tactics and formations according to match conditions and team situations and present them to the user.

[0870] "User" refers to an individual or group that uses the system to input match conditions and team status.

[0871] "Match conditions" refers to information that indicates the environment and circumstances regarding the upcoming match, and includes the weather, the characteristics of the opposing team, and the like.

[0872] "Team status" refers to information indicating the current state of the team, the condition of the players, tactical preferences, and the like.

[0873] A "terminal" is a device through which a user inputs match conditions and team status and communicates with the server.

[0874] The "Server" is a computer system that receives and analyzes data sent by users and uses a generative AI model to calculate optimal tactics and formations.

[0875] A "generative AI model" is a model generated by a machine learning algorithm and is used to calculate optimal tactics and formations based on training data.

[0876] "Tactics" refers to the specific playing style and strategy adopted by a team in a match.

[0877] "Formation" refers to the specific positions in which a team's players are positioned during a match.

[0878] The "calculation results" are information on optimal tactics and formations calculated using a generative AI model.

[0879] "Presenting" is the act of showing the results of a calculation to a user visually or in some other way.

[0880] The present invention is a system that allows a user to input match conditions and team situations, calculates optimal tactics and formations based on the input, and presents the results to the user. A specific embodiment of this system will be described below.

[0881] First, a user uses a terminal to input the match conditions and team status. The terminal can be a device such as a smartphone, tablet, or PC, and input is performed through a dedicated application or web interface. For example, a user may input information such as: "The next match will be played on rainy days, and the opposing team has a high offensive power. Our team has a strong defensive power, but an average offensive power."

[0882] The terminal converts the input data into a data format such as JSON and sends it to the server using an HTTP request. The server analyzes the received data and performs necessary preprocessing, such as converting text data into numerical data. The preprocessed data is then input into the generative AI model.

[0883] The server uses machine learning libraries such as Python's Scikit-learn and TensorFlow to run generative AI models. The generative AI models calculate optimal tactics and formations based on the training data. For example, they can get results such as "The optimal tactic is to strengthen the defense with a 4-4-2 formation while aiming for counter attacks."

[0884] The calculated results are sent from the server to the device. The device analyzes the received results and displays them to the user. For example, it could display on the screen, "The optimal tactic for the next match is to use a 4-4-2 formation, strengthen the defense, and aim for counter attacks."

[0885] This system allows users to quickly and accurately obtain optimal tactics and formations according to match conditions and team situations, and also provides a means to understand how the presented tactics and formations work specifically, making it easier to apply them in actual matches.

[0886] As a concrete example, a user inputs the following prompt into a generative AI model:

[0887] "The next game will be played in rainy weather, and the opposing team has a strong attacking ability. Our team has a strong defense, but an average attacking ability. Please tell me the best tactics and formations for these conditions."

[0888] Based on this prompt, the server uses the generated model to calculate the optimal tactics and formations and presents them to the user. For example, it might present a result such as, "The optimal tactics are a 4-4-2 formation that strengthens the defense while aiming for counter attacks."

[0889] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0890] Step 1:

[0891] The user inputs the match conditions and team status.

[0892] The user inputs the conditions of the next match (e.g., weather, characteristics of the opposing team) and the situation of his / her own team (e.g., players' condition, tactical preferences) through the terminal interface. For example, the user inputs information such as "The next match will be in rain, and the opposing team has a strong offensive power." The input data is in text format.

[0893] Step 2:

[0894] The terminal transmits the input data to the server.

[0895] The terminal converts the data entered by the user into a data format such as JSON format and sends it to the server using an HTTP POST request. For example, it sends the data {"weather": "rain", "opponent_strength": "high_attack"}. The input is text data, and the output is JSON format data.

[0896] Step 3:

[0897] The server analyzes the data it receives and inputs it into a generative AI model.

[0898] The server parses the received JSON data and performs the necessary preprocessing. For example, convert text data into numerical data, such as {"weather": 1, "opponent_strength": 2}. The preprocessed data is input to the generative AI model. The input is JSON format data, and the output is preprocessed numerical data.

[0899] Step 4:

[0900] The server uses generative AI models to calculate optimal tactics and formations.

[0901] The server uses machine learning libraries such as Python's Scikit-learn and TensorFlow to run generative AI models. The model calculates optimal tactics and formations based on the input data. For example, it may obtain a result such as "The optimal tactic is to strengthen the defense with a 4-4-2 formation while aiming for counter attacks." The input is preprocessed numerical data, and the output is tactical and formation information.

[0902] Step 5:

[0903] The server transmits the calculation result to the terminal.

[0904] The server converts the calculated results into a data format such as JSON and sends it to the terminal using an HTTP response. For example, it sends the data {"formation": "4-4-2", "strategy": "defensive_counter"}. The input is tactical and formation information, and the output is JSON format data.

[0905] Step 6:

[0906] The terminal displays the results to the user.

[0907] The terminal analyzes the received results and displays them to the user. For example, it might display on the screen, "The best tactic for the next match is to use a 4-4-2 formation, strengthen the defense, and aim for counter attacks." The input is JSON format data, and the output is a visual display.

[0908] (Application example 2)

[0909] Next, a description will be given of Application Example 2 of Form 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".

[0910] Conventional tactical and formation suggestion systems are limited to suggesting optimal tactics and formations for sports teams, and do not address the optimization of robot placement and operation tactics in factories. For this reason, there is a demand for a system that proposes optimal robot placement and operation tactics to maximize factory production efficiency.

[0911] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0912] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for proposing optimal placement and operation tactics of robots in a factory, a means for calculating optimal placement and operation tactics of robots based on the status and work contents of the factory production line, and a means for presenting this to a factory manager. This makes it possible to optimize not only the tactics and formations of sports teams, but also the placement and operation tactics of robots in a factory.

[0913] "Cutting-edge tactics" are tactics that are formulated based on the latest data analysis techniques and strategic theories.

[0914] "Player data" refers to information relating to a player's performance, physical strength, technique, tactical understanding, etc.

[0915] "Opponent data" refers to information relating to the opponent's tactics, player characteristics, past match results, etc.

[0916] "Learning means" refers to the process of using machine learning algorithms to analyze data and generate models.

[0917] "Means for presenting optimal tactics and formations" refers to a method for presenting to a user the most effective tactics and formations for a team based on learned data.

[0918] "A means for generating and presenting an image video leading up to the goal" refers to a method for simulating movements during a match based on presented tactics and formations, and presenting the results to the user in video format.

[0919] The "means for proposing optimal placement and operation tactics for robots in a factory" is a method for making proposals for optimizing the placement and operation of robots based on the status of the factory's production line and the work content.

[0920] "A means for calculating optimal robot placement and operation tactics based on the status of the factory's production line and the work content" refers to a method for analyzing various data within the factory and calculating optimal robot placement and operation tactics.

[0921] "Means of presenting to the factory manager" refers to a method of presenting the calculated optimal robot placement and operation tactics to the factory manager in an easy-to-understand manner.

[0922] The system for implementing the present invention operates in cooperation with a server, a terminal, and a user. A specific embodiment of the system will be described below.

[0923] server

[0924] The server has the means to learn cutting-edge tactics, player data, and opponent data. For this, it uses Python and machine learning libraries such as scikit-learn. The server has the means to present optimal tactics and formations for teams based on the learned data. It also has the means to generate and present image videos leading up to the goal based on the presented tactics and formations. For this, it uses video generation libraries and simulation software.

[0925] The server also has the means to propose optimal placement and operation tactics for robots in the factory. It has the means to calculate optimal placement and operation tactics for robots based on the status of the factory's production line and the work content. To do this, it uses data analysis tools to analyze various sensor data and work logs in the factory. The calculated results are presented to the factory manager.

[0926] Terminal

[0927] The terminal provides an interface for users to access the server. Smartphones, tablets, PCs, etc. are used as terminals. The terminal displays the tactics and formations presented by the server, as well as the placement and operation tactics of the robots. For this purpose, a web browser or a dedicated application is used.

[0928] User

[0929] The user accesses the server through a terminal and inputs the necessary data. For example, the match conditions of a sports team or the status data of a factory production line. The user checks the optimal tactics and formations, as well as the robot placement and operation tactics presented by the server, and performs actual operations based on them.

[0930] Examples

[0931] For example, to optimize the placement of robots in a factory, the following data is input:

[0932] "In order to optimize the placement of robots in the factory, input the current status data of the production line. For example, input data such as the operating rate, work content, work time, and error rate of each robot."

[0933] Following these prompts, the user inputs the necessary data, which the server analyzes to calculate the optimal placement and operation tactics. The results are displayed on the terminal, and the user can check them and apply them to actual operations.

[0934] The above is a specific embodiment for carrying out the present invention.

[0935] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0936] Step 1:

[0937] A user accesses a server using a terminal.

[0938] Input: Credentials for the user to access the server through the terminal.

[0939] Output: The server verifies the user's identity and grants access.

[0940] Specific operation: The user opens a browser or a dedicated application on the device and enters authentication information into the login screen. The server verifies the authentication information and allows the user access.

[0941] Step 2:

[0942] The user inputs the necessary data through the terminal.

[0943] Input: Data on the match conditions of a sports team or the status of a factory production line.

[0944] Output: The input data that is sent to the server.

[0945] Specific operation: The user enters the match conditions (e.g., weather, opponent information) and factory status data (e.g., each robot's operating rate, work content, work time, error rate) into the input form on the terminal, and presses the send button. The server receives this data.

[0946] Step 3:

[0947] The server analyzes the received data and uses machine learning models to calculate optimal tactics, formations, robot placement and operation tactics.

[0948] Input: Match conditions and factory status data sent by the user.

[0949] Output: Optimal tactics and formations, as well as robot placement and movement tactics.

[0950] Specific operation: The server pre-processes the received data and inputs it into the machine learning model. The model analyzes the data and calculates the optimal tactics, formations, and robot placement and operation tactics.

[0951] Step 4:

[0952] The server transmits the calculated result to the terminal.

[0953] Input: Optimal tactics and formations, as well as robot placement and movement tactics.

[0954] Output: The result data sent to the terminal.

[0955] Specific operation: The server formats the calculated result and sends it to the terminal, which receives it and displays it to the user.

[0956] Step 5:

[0957] The user checks the results via the terminal and reflects them in actual operations.

[0958] Input: Optimal tactics and formations sent from the server, as well as robot placement and movement tactics.

[0959] Output: Actual operation based on user confirmed results.

[0960] Specific operation: Users check the results displayed on their devices and adjust their sports team's tactics or the placement of robots in a factory based on the results.

[0961] Example 3

[0962] Next, a third embodiment of the third embodiment will be described. 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".

[0963] Conventional tactical and formation suggestion systems lacked a means to visually confirm the effectiveness of tactics and formations, and it was difficult to provide specific practice methods to realize the proposed tactics. This made it difficult for users to understand the effects of tactics, and they were unable to find effective practice methods.

[0964] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0965] In this invention, the server includes a means for learning tactics, player data, and opponent data, a means for presenting optimal tactics and formations to a team based on the learned data, a means for generating an image video of the goal based on the presented tactics and formations, a means for presenting the generated image video to a user, a means for calculating a practice method for realizing the presented tactics and formations, and a means for presenting the calculated practice method to a user. This allows a user to visually confirm the effects of the tactics and formations, and further allows the user to know specific practice methods.

[0966] "Tactics" are the specific methods or strategies that plan and direct how a team will play in a match.

[0967] "Player data" refers to information regarding an individual player's performance, skills, physical strength, past match results, etc.

[0968] "Opponent data" refers to information relating to the opposing team's tactics, player characteristics, past match results, etc.

[0969] "Means of learning" refers to methods and techniques for analyzing tactics, player data, and opponent data to derive optimal tactics and formations.

[0970] "Means of presentation" refers to methods or techniques for displaying optimal tactics and formations to the user based on learned data.

[0971] An "image video" is a video that visually depicts the movements of players and the ball, generated based on presented tactics and formations.

[0972] "Means of generation" refers to methods and techniques for creating image videos based on tactics and formations.

[0973] The "means for presenting to the user" refers to a method or technique for displaying the generated image moving image to the user.

[0974] "Means for calculating training methods" refers to methods or techniques for calculating and deriving the training methods necessary to realize the presented tactics and formations.

[0975] The "means for presenting a practice method" refers to a method or technique for displaying the calculated practice method to the user.

[0976] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0977] This invention is a system that generates an image video of the path to the goal based on tactics and formations and presents it to the user. It also includes a function to suggest practice methods for achieving the presented tactics and formations.

[0978] Hardware and Software Used

[0979] Hardware: High-performance server (e.g. GPU-equipped server)

[0980] Software: 3D modeling software (e.g. Blender), animation software (e.g. Autodesk Maya), generative AI models (e.g. GPT-4)

[0981] Specific operation of the system

[0982] 1. Enter tactics and formations

[0983] Users use terminals to input tactics and formations into the system.

[0984] Example: A user enters "I want to strengthen attacks from the sides with a 4-4-2 formation" into an input form on a terminal and clicks the submit button.

[0985] 2. Simulating the data

[0986] The server analyzes the tactical and formation data received from the user.

[0987] The server uses 3D modelling software (e.g. Blender) to model the player positions and movements.

[0988] The server uses animation software (e.g. Autodesk Maya) to simulate player movements and ball movement.

[0989] Example: The server sets the initial positions of the players in Blender, and calculates the player movements and ball trajectory in Maya.

[0990] 3. Video Generation

[0991] The server generates a visually-presented video based on the simulation results.

[0992] The server uses rendering software to convert the simulation results into a video file.

[0993] Example: A server starts a rendering process, generating a one minute video of images.

[0994] 4. Presenting the video

[0995] The video generated by the server is sent to the user's terminal.

[0996] The terminal displays the received video to the user.

[0997] Example: A server sends a video file to a terminal using the HTTP protocol, and the terminal plays it on a video player.

[0998] 5. Practice suggestions

[0999] Based on the data learned by the server and the generative AI model, it calculates what kind of practice each player needs to do to achieve the tactics and formations.

[1000] The server analyzes each player's performance data and past match data.

[1001] Example: A server retrieves player performance data from a database and uses a generative AI model (e.g. GPT-4) to calculate the required skills and abilities.

[1002] 6. Presentation of practice methods

[1003] The server presents the calculated practice method to the user.

[1004] The practice method received by the terminal is displayed to the user.

[1005] Example: The server sends text data on how to practice to the terminal, and the terminal displays it.

[1006] Examples of prompt statements

[1007] "I want to strengthen my attacks from the sides in a 4-4-2 formation. Please simulate the movement of the players and the ball and generate a video showing how the ball will move to the goal."

[1008] "Please tell me what kind of practice each player should do to implement the tactics you have presented."

[1009] This system enables the user to visually confirm the effects of tactics and formations, and furthermore, to learn specific training methods. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1010] Step 1:

[1011] Tactical and formation input

[1012] Users use terminals to input tactics and formations into the system.

[1013] Input: The user enters "I want to strengthen attacks from the sides with a 4-4-2 formation" into the input form on the terminal and clicks the submit button.

[1014] Output: Tactical and formation data is sent to the server.

[1015] Specific operation: The user enters tactics and formations into the input form on the terminal and clicks the send button, which sends the data to the server.

[1016] Step 2:

[1017] Simulating Data

[1018] The server analyzes the tactical and formation data received from the user.

[1019] Input: Tactical and formation data.

[1020] Output: Initial setup data for the simulation.

[1021] How it works: The server analyzes tactical and formation data, models player positions and movements using 3D modeling software (e.g. Blender), then simulates player and ball movements using animation software (e.g. Autodesk Maya).

[1022] Step 3:

[1023] Video Generation

[1024] The server generates a visually-presented video based on the simulation results.

[1025] Input: Simulation result data.

[1026] Output: Image video file.

[1027] What happens: The server uses rendering software to convert the simulation results into a video file. The server starts the rendering process, producing a one-minute video of the images.

[1028] Step 4:

[1029] Video presentation

[1030] The video generated by the server is sent to the user's terminal.

[1031] Input: Image video file.

[1032] Output: The video displayed on the user's device.

[1033] Specific operation: The server sends a video file to the terminal using the HTTP protocol, and the terminal plays it on the video player.

[1034] Step 5:

[1035] Practice suggestions

[1036] Based on the data learned by the server and the generative AI model, it calculates what kind of practice each player needs to do to achieve the tactics and formations.

[1037] Input: Performance data and past match data for each player.

[1038] Output: Practice suggestions data.

[1039] How it works: The server retrieves player performance data from the database and uses a generative AI model (e.g. GPT-4) to calculate the required skills and abilities.

[1040] Step 6:

[1041] Presentation of practice methods

[1042] The server presents the calculated practice method to the user.

[1043] Input: Practice suggestion data.

[1044] Output: The exercise displayed on the user's device.

[1045] Specific operation: The server sends text data on how to practice to the terminal, and the terminal displays it.

[1046] (Application example 3)

[1047] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1048] Conventional tactical and formation presentation systems lacked the means to visually understand the movements of players and the ball, and the presentation of effective practice methods was limited. In addition, there was also a lack of means to visually understand efficient movement patterns in optimizing the movements of robots and work flows in factories. This made it difficult to understand tactics, improve the efficiency of practice, and improve production efficiency in factories.

[1049] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1050] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for simulating the movements and work flows of robots in the factory and generating and presenting optimal movement patterns as videos, and a means for calculating what movements and work each robot should perform to efficiently produce and presenting specific movement procedures. This makes it possible to understand tactics, improve the efficiency of practice, and increase production efficiency in the factory.

[1051] "Cutting-edge tactics" are tactics developed based on the latest technology and data analysis.

[1052] "Player Data" refers to information relating to a player's performance or abilities.

[1053] "Opponent Data" refers to information regarding the opponent's tactics and performance.

[1054] "Learning tools" refers to the methods and techniques used to analyze data and find patterns and trends.

[1055] "Means for presenting tactics and formations" refers to a method for showing the user optimal tactics and formations based on the analyzed data.

[1056] "Means of generating and presenting image videos" refers to a method of running simulations based on tactics and formations and showing the results to users as videos.

[1057] "Means of simulating robot movements and work flows within a factory" refers to a method of virtually reproducing the movements of robots and work procedures within a factory.

[1058] "Means of generating and presenting optimal movement patterns as videos" refers to a method of showing efficient movement patterns to users in video format based on simulation results.

[1059] "Means for presenting specific operating procedures" refers to a method for showing the user detailed procedures for the robot to perform a task efficiently.

[1060] "Past Match Data" refers to information relating to the results and tactics of previously played matches.

[1061] "Player Performance Data" refers to information regarding a player's performance in past matches and training sessions.

[1062] "Opponent tactical data" refers to information regarding tactics and formations used by an opponent in the past.

[1063] "Factory work flow data" refers to information about work procedures and processes within a factory.

[1064] "Robot operation data" refers to information related to the robot's movements and work.

[1065] The system for implementing this invention is composed of three main elements: a server, a terminal, and a user. The server learns cutting-edge tactics, player data, and opponent data, and presents the optimal tactics and formations for a team based on the learned data. It also generates and presents an image video of the path to the goal based on the presented tactics and formations. It also simulates the movements and work flows of robots in a factory, and generates and presents optimal movement patterns as videos. It calculates what movements and tasks each robot should perform to ensure efficient production, and presents specific operating procedures.

[1066] The server uses software such as Python, NumPy, Matplotlib, and FFmpeg to perform data analysis and simulation. Specifically, Python is used for data preprocessing and analysis, NumPy is used for numerical calculations, Matplotlib is used to visualize the simulation results, and FFmpeg is used to generate videos.

[1067] The terminal is a device that allows the user to view and operate the information provided by the server. Terminals include PCs, smartphones, tablets, etc. Through the terminal, the user can view tactics and formations, view image videos, and check the robot's operation procedures.

[1068] As a concrete example, the system simulates a scene in which multiple robots work together to assemble a product in a factory, and generates a video of the optimal movement pattern. It provides detailed operation procedures for each robot, and shows specific actions to achieve efficient production. This system allows users to understand tactics, improve the efficiency of practice, and increase production efficiency in the factory.

[1069] Using the generative AI model, the system can generate appropriate simulation results by inputting a prompt sentence such as the following:

[1070] Example prompt:

[1071] "Please simulate a scene in which multiple robots work together to assemble products in a factory, and generate a video of the optimal motion pattern. Please provide detailed operating procedures for each robot, and indicate specific actions to achieve efficient production."

[1072] In this way, the form for carrying out the invention can be concretely shown.

[1073] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1074] Step 1:

[1075] The server collects cutting edge tactics and player and opponent data.

[1076] Input: Tactical data, player data, opponent data

[1077] Data processing: Data preprocessing (missing value completion, normalization, etc.)

[1078] Output: Preprocessed dataset

[1079] Step 2:

[1080] The server learns from the collected data and generates optimal tactics and formations for the team.

[1081] Input: Preprocessed dataset

[1082] Data Computing: Training models using machine learning algorithms

[1083] Output: Optimal tactics and formations

[1084] Step 3:

[1085] The server simulates the movements of players and the ball based on the generated tactics and formations.

[1086] Input: Optimal tactics and formations

[1087] Data calculation: Generation of motion patterns using simulation algorithms

[1088] Output: Simulation data

[1089] Step 4:

[1090] The server generates an image video based on the simulation data and transmits it to the terminal.

[1091] Input: Simulation data

[1092] Data processing: Video generation (using Matplotlib and FFmpeg)

[1093] Output: Image video file

[1094] Step 5:

[1095] The terminal presents the image video transmitted from the server to the user.

[1096] Input: Image video file

[1097] Specific operation: Play a video using a video player

[1098] Output: A video display that users can visually understand

[1099] Step 6:

[1100] The server simulates the robot's movement and work flow within the factory and generates optimal movement patterns.

[1101] Input: Workflow data within the factory, robot operation data

[1102] Data calculation: Generation of motion patterns using simulation algorithms

[1103] Output: Optimal operating pattern

[1104] Step 7:

[1105] The server generates a video based on the optimal movement pattern and transmits it to the terminal.

[1106] Input: Optimal movement pattern

[1107] Data processing: Video generation (using Matplotlib and FFmpeg)

[1108] Output: Motion pattern video file

[1109] Step 8:

[1110] The terminal presents the motion pattern video transmitted from the server to the user.

[1111] Input: Motion pattern video file

[1112] Specific operation: Play a video using a video player

[1113] Output: A video display that users can visually understand

[1114] Step 9:

[1115] Based on the videos presented, users can understand tactics, improve the efficiency of their practice, and increase production efficiency in their factories.

[1116] Input: Video display

[1117] Specific movements: Watch videos to understand tactics and movement patterns

[1118] Output: Improved tactical understanding, efficient practice, and production efficiency

[1119] In addition, 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.

[1120] "Example 1"

[1121] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes the user's emotions and presents optimal tactics and formations based on those emotions. Specifically, if the user feels nervous about a match, the emotion engine feeds that information back to the system, and the system uses that information to present tactics and formations that will help the user relax.

[1122] "Example 2"

[1123] In addition, the emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc. For example, if a user shows a joyful expression after winning a game, the emotion engine feeds that information back to the system, and the system uses that information to present similar tactics and formations again.

[1124] "Example 3"

[1125] Furthermore, it is possible to adjust the presentation of tactics and formations, as well as the presentation of training methods, based on the output of the emotion engine.

[1126] For example, if a user feels dissatisfied with a particular tactic, the emotion engine can feed that information back into the system, which can then use that information to suggest a new tactic that will satisfy the user.

[1127] The process flow of each embodiment will be described below.

[1128] "Example 1"

[1129] Step 1: The emotion engine collects the user's emotion data (facial expressions, voice, text input, etc.).

[1130] Step 2: The emotion engine recognizes and analyzes the user's emotions based on the collected data.

[1131] Step 3: The system receives the output from the emotion engine and the AI ​​calculates the optimal tactics and formations based on those emotions.

[1132] Step 4: Present the calculated tactics and formations to the user.

[1133] "Example 2"

[1134] Step 1: The emotion engine collects the user's emotion data (facial expressions, voice, text input, etc.).

[1135] Step 2: The emotion engine recognizes and analyzes the user's emotions based on the collected data.

[1136] Step 3: The system receives the output from the emotion engine and, based on the emotion, either presents similar tactics and formations again or the AI ​​calculates new tactics and formations.

[1137] Step 4: Present the calculated tactics and formations to the user.

[1138] "Example 3"

[1139] Step 1: The emotion engine collects the user's emotion data (facial expressions, voice, text input, etc.).

[1140] Step 2: The emotion engine recognizes and analyzes the user's emotions based on the collected data.

[1141] Step 3: The system receives the output from the emotion engine and the AI ​​calculates new tactics to satisfy the user based on those emotions.

[1142] Step 4: Present the calculated tactics and formations to the user.

[1143] Example 1

[1144] Next, a description will be given of Example 1 of Form 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".

[1145] Conventional tactics and formation suggestion systems only suggest tactics based on past data, and have the problem of not being able to make suggestions that take into account the user's emotional state. In addition, there is a lack of means to determine whether the proposed tactics and formations are optimal for the user. This makes it difficult for users to select appropriate tactics when they are nervous or in a particular emotional state.

[1146] 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.

[1147] In this invention, the server includes a means for acquiring past match data, player performance data, and opponent tactical data through a database or API, a means for preprocessing the acquired data and learning using a machine learning algorithm, a means for acquiring user emotion data and generating optimal tactics and formations based on the emotions, and a means for presenting the generated tactics and formations to the user, thereby making it possible to propose optimal tactics and formations taking into account the user's emotional state.

[1148] A "database" is a system that systematically organizes and stores information so that it can be searched and used as needed.

[1149] "API" stands for Application Program Interface, an interface for exchanging data and functions between different software programs.

[1150] "Past Match Data" is information about matches that have previously taken place, including details such as scores, player movements, and tactics.

[1151] "Player performance data" refers to data regarding a player's movements during a match, their results, physical strength, techniques, etc.

[1152] "Opponent's tactical data" refers to data regarding tactics and formations used by the opponent in the past.

[1153] "Preprocessing" is the process of cleaning and transforming data before inputting it into a machine learning model, and includes tasks such as filling in missing values ​​and normalizing the data.

[1154] A "machine learning algorithm" is a mathematical technique for learning patterns and trends from data and making predictions or classifications.

[1155] "Emotion data" is data that indicates the user's emotional state, and includes information obtained from facial expressions, voice, and the like.

[1156] "Tactics and formation" is a plan that shows the player's positioning, movements, and strategy during a match.

[1157] "Presentation" is the act of displaying and providing information to a user.

[1158] The present invention relates to a system in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system will be described below.

[1159] Get the data

[1160] The server retrieves past match data, player performance data, and opponent tactical data through a database and API. A relational database such as MySQL is used as the database, and a RESTful API is used as the API. This allows the latest data to be collected efficiently.

[1161] Data Preprocessing

[1162] The server preprocesses the acquired data by using Python's Pandas library to impute missing values, normalize the data, and encode categorical data, making the data suitable for machine learning algorithms.

[1163] Training a machine learning model

[1164] The server uses the pre-processed data to train machine learning models. Using libraries such as TensorFlow and PyTorch, it builds neural network models to extract patterns and trends from past match data, which can then predict optimal tactics and formations for future matches.

[1165] Acquiring emotion data

[1166] The device acquires the user's emotional data. Specifically, it uses a camera to capture the user's facial expressions and uses the OpenCV library to perform facial expression analysis. It also uses the Google Cloud Speech-to-Text API to analyze voice data. This allows the device to accurately grasp the user's emotional state.

[1167] Tactics and formation generation

[1168] The server uses the emotion data and the trained model to generate optimal tactics and formations. For example, if the user is nervous, it will suggest defensive tactics. This allows the server to provide optimal tactics according to the user's emotional state.

[1169] Presentation of tactics and formations

[1170] The terminal presents the generated tactics and formations to the user. Specifically, it displays on the screen, "Let's adopt a defensive formation to relax." This allows the user to understand the proposed tactics and put them into practice.

[1171] Examples of concrete examples and prompts

[1172] For example, if a user feels nervous before a match, the device captures the user's facial expression through the camera and analyzes it with the emotion engine. The analysis results are sent to the server, which generates a tactic that helps the user relax based on past data and emotion data. The device displays to the user, "To relax, let's adopt a defensive formation."

[1173] An example of a prompt is as follows:

[1174] "Please suggest the best tactics for the next match using past match data, player performance data, and opponent tactical data. Also, if the user is nervous, please suggest tactics that will help them relax."

[1175] In this way, a system is realized in which the server, terminals, and users work together to provide optimal tactics and formations.

[1176] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1177] Step 1: Get the data

[1178] The server retrieves past match data, player performance data, and opponent tactical data through databases and APIs. The inputs are SQL queries and API requests, and the output is the retrieved dataset. Specifically, the server connects to a MySQL database and executes SQL queries to retrieve data. It also uses RESTful APIs to retrieve the latest data from external data sources.

[1179] Step 2: Preprocessing the data

[1180] The server preprocesses the acquired data. The input is the dataset acquired in step 1, and the output is the preprocessed dataset. Specifically, the server uses Python's Pandas library to impute missing values ​​in the data, normalize the data, and encode categorical data, making the data suitable for machine learning algorithms.

[1181] Step 3: Train the machine learning model

[1182] The server trains a machine learning model using the preprocessed data. The input is the preprocessed dataset from step 2, and the output is the trained machine learning model. Specifically, the server uses libraries such as TensorFlow and PyTorch to build a neural network model to extract patterns and trends from past match data, which can then predict optimal tactics and formations for future matches.

[1183] Step 4: Obtaining emotion data

[1184] The device acquires the user's emotional data. The inputs are the user's facial expressions and voice, and the output is the analyzed emotional data. Specifically, the device uses a camera to capture the user's facial expressions and performs facial expression analysis using the OpenCV library. It also uses the Google Cloud Speech-to-Text API to analyze the voice data. This allows the device to accurately grasp the user's emotional state.

[1185] Step 5: Generate tactics and formations

[1186] The server uses the emotion data and the trained model to generate optimal tactics and formations. The inputs are the trained model from step 3 and the emotion data acquired from step 4, and the output is the generated tactics and formations. In concrete terms, the server analyzes the emotion data and generates optimal tactics according to the user's emotional state, such as proposing defensive tactics if the user is nervous.

[1187] Step 6: Present tactics and formations

[1188] The terminal presents the generated tactics and formations to the user. The inputs are the tactics and formations generated in step 5, and the output is the information presented to the user. As a specific operation, the terminal displays on the screen, "Let's adopt a defensive formation to relax." This allows the user to understand the proposed tactics and put them into practice.

[1189] (Application example 1)

[1190] Next, a description will be given of Application Example 1 of Form 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".

[1191] Conventional factory robot systems can collect production data and machine performance data, but it is difficult to comprehensively analyze this data and present optimal production tactics and work formations. In addition, because tactical proposals do not take into account the emotions of workers, it is not possible to reduce worker stress. This has led to a demand for both improving production efficiency and reducing worker stress at the same time.

[1192] 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. In this invention, the server includes a means for learning the most advanced tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for collecting production data in the factory, machine performance data, and worker emotion data, a means for analyzing the collected data and presenting optimal production tactics and work formations, and a means for recognizing the emotions of workers and proposing optimal tactics based on the emotions. This makes it possible to improve production efficiency and reduce worker stress.

[1193] "Cutting-edge tactics" are tactics that are developed using the latest technology and data analysis methods.

[1194] "Player Data" refers to information relating to a player's performance or abilities.

[1195] "Opponent Data" refers to information regarding the opponent's tactics and performance.

[1196] "Means for learning" refers to a method or device for collecting data and analyzing and learning from it using machine learning algorithms.

[1197] "Means for presenting" refers to a method or device for presenting optimal tactics and formations to a user based on the analysis results.

[1198] "Means for generating and presenting an image video" refers to a method or device for creating a simulation video to the goal based on the presented tactics and formation, and displaying it to the user.

[1199] "Factory production data" refers to information relating to production activities within a factory.

[1200] "Machine performance data" refers to information regarding the operating status and performance of machines in a factory.

[1201] "Worker emotion data" refers to information relating to the emotional state of a worker.

[1202] "Means of collection" refers to methods and devices for obtaining various data in real time.

[1203] "Analyzing means" refers to methods or devices used to analyze collected data and extract patterns and trends.

[1204] "Work formation" refers to a plan regarding worker placement and work procedures.

[1205] "Means for recognizing emotions" refers to a method or apparatus for detecting and analyzing the emotional state of a worker.

[1206] "Means for suggesting tactics" refers to a method or device for suggesting optimal tactics or work formations to a user based on analysis results and emotion data.

[1207] A system for carrying out this invention has the following configuration: The server includes means for learning cutting-edge tactics, player data, and opponent data, means for presenting optimal tactics and formations to a team based on the learned data, means for generating and presenting an image video to the goal based on the presented tactics and formations, means for collecting production data in a factory, machine performance data, and worker emotion data, means for analyzing the collected data and presenting optimal production tactics and work formations, and means for recognizing worker emotions and proposing optimal tactics based on the emotions.

[1208] Hardware and Software Used

[1209] Hardware: Factory robots, emotion recognition cameras, sensors

[1210] Software: Python, TensorFlow, OpenCV, emotion recognition API (e.g. Affectiva)

[1211] Data acquisition and processing

[1212] 1. Data collection: The server uses sensors and cameras in the factory to collect production data, machine performance data, and worker emotion data in real time.

[1213] 2. Data preprocessing: The server cleanses the collected data and converts it into a format suitable for machine learning algorithms.

[1214] 3. Machine Learning: The server uses TensorFlow to learn patterns and trends from past data.

[1215] 4. Emotion recognition: The server uses OpenCV and emotion recognition API to recognize emotions from the worker's face in real time.

[1216] 5. Tactical proposal: The server proposes optimal production tactics and work formations based on the learned model and emotion data.

[1217] Examples

[1218] For example, if a production line in a factory is delayed, the system operates as follows:

[1219] 1. Data collection: The server uses sensors to collect information on the machine’s operating status in real time, and cameras to capture the facial expressions of workers.

[1220] 2. Data Preprocessing: The server cleanses the collected data and removes outliers.

[1221] 3. Machine learning: The server learns a model to identify the causes of delays based on past production data.

[1222] 4. Emotion recognition: If a worker is feeling stressed, the server uses an emotion recognition API to feed that information back to the system.

[1223] 5. Tactical Suggestion: The server identifies the cause of delays and suggests work formations that allow workers to relax.

[1224] Example prompts for generative AI models

[1225] Design a system that collects production data, machine performance data, and worker emotion data in a factory, and proposes optimal production tactics and work formations. Include a function that uses an emotion engine to recognize the emotions of workers and propose tactics to reduce stress.

[1226] In this way, applications installed on factory robots can use data to optimize production efficiency and reduce worker stress.

[1227] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1228] Step 1: Data collection

[1229] The server uses sensors and cameras in the factory to collect production data, machine performance data, and worker emotion data in real time. Specifically, it obtains machine operation status and production line progress data from the sensors, and captures worker facial expression data from the cameras. The input is data from the sensors and cameras, and the output is the collected production data, performance data, and emotion data.

[1230] Step 2: Data Preprocessing

[1231] The server cleanses the collected data and converts it into a format suitable for machine learning algorithms. Specifically, it removes outliers, fills in missing values, and standardizes the data. The input is the collected production data, performance data, and sentiment data, and the output is the cleansed data.

[1232] Step 3: Machine learning

[1233] The server uses TensorFlow to learn patterns and trends from past data. Specifically, it trains models based on past production data to identify causes of delays and improve production efficiency. The input is the cleansed data, and the output is the learned model.

[1234] Step 4: Emotion Recognition

[1235] The server uses OpenCV and emotion recognition API to recognize emotions from the worker's face in real time. Specifically, it analyzes facial expression data acquired from the camera and identifies the worker's emotional state. The input is facial expression data from the camera, and the output is the recognized emotion data.

[1236] Step 5: Tactical proposal

[1237] The server proposes optimal production tactics and work formations based on the trained model and emotion data. Specifically, it identifies the cause of delays and generates work formations that allow workers to relax. The inputs are the trained model and recognized emotion data, and the output is the proposed production tactics and work formations.

[1238] Step 6: Image video generation and presentation

[1239] The server creates a simulation video of the run to the goal based on the proposed tactics and formation, and displays it to the user. Specifically, the server uses simulation software to generate a video based on the generated tactics and formation, and transmits it to the user's terminal. The input is the proposed tactics and formation, and the output is the generated simulation video.

[1240] Example 2

[1241] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1242] Conventional tactical and formation presentation systems do not fully consider the game conditions and team situations, and lack the functionality to provide feedback on the user's emotions, making it difficult to provide optimal tactics and formations. In addition, because the model is not adjusted based on the user's emotions, it is not possible to increase user satisfaction.

[1243] 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.

[1244] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations for a team based on the learned data, a means for generating and presenting an image video up to the goal based on the presented tactics and formations, a means for a user to input game conditions and team situations, a means for preprocessing the input data, a means for calculating optimal tactics and formations using a machine learning model, a means for presenting the calculation results to the user, a means for recognizing the user's emotions, and a means for adjusting the model based on the recognition results. This makes it possible to present optimal tactics and formations taking into account game conditions and team situations, and further increases user satisfaction by feeding back the user's emotions.

[1245] "State-of-the-art tactical, player and opponent data" refers to tactical information, player performance data and opponent tactical data collected using the latest technology and methods.

[1246] "Means of learning" refers to the process of using machine learning algorithms to analyze data and generate models.

[1247] "Means for presenting optimal tactics and formations to a team" refers to a process of presenting to a user tactics and formations that are most suitable for specific match conditions and team situations based on learned data.

[1248] "Means for generating and presenting an image video leading up to the goal" refers to the process of simulating plays during a match based on presented tactics and formations, and presenting the results to the user in video format.

[1249] "Means for users to input match conditions and team status" refers to an interface that enables users to input the conditions for the next match and the current status of the team into the system.

[1250] The "means for preprocessing input data" refers to a process of analyzing data entered by a user and performing preprocessing such as filling in missing values ​​and normalizing the data.

[1251] "Means for calculating optimal tactics and formations using a machine learning model" refers to the process of inputting preprocessed data into a machine learning model and calculating optimal tactics and formations.

[1252] "Means of presenting the calculation results to the user" refers to the process of displaying to the user the tactics and formations calculated by the machine learning model.

[1253] "Means for recognizing user emotions" refers to the process of analyzing and recognizing emotions from a user's facial expressions, voice, text input, etc.

[1254] "Means for adjusting the model based on the recognition results" refers to the process of receiving the user's emotion recognition results as feedback and adjusting the machine learning model.

[1255] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1256] This invention is a system in which the user inputs the match conditions and team situation, and the server calculates the optimal tactics and formation based on that and presents it to the user. Furthermore, it has the function of recognizing the user's emotions and adjusting the model based on that feedback.

[1257] Hardware and Software Used

[1258] The server processes the data using machine learning libraries such as Python and TensorFlow. The terminal provides an interface for users to input data and has a display to show the results. The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice.

[1259] Program Processing

[1260] The server first receives the match conditions and team status input by the user. This includes the weather, the strength of the opposing team, and the condition of the players. The server then preprocesses this data, filling in missing values ​​and normalizing the data. The preprocessed data is then input into a machine learning model to calculate optimal tactics and formations.

[1261] The calculation results are presented to the user via the device. For example, specific advice such as "Use a 4-4-2 formation in the next game" is displayed. After the user confirms the results, the emotion engine analyzes the user's facial expressions and voice to recognize emotions. For example, if the user shows a happy expression, that information is fed back to the server. The server uses this feedback to adjust the machine learning model and prioritize presenting similar tactics and formations the next time.

[1262] Examples and prompts

[1263] As a concrete example, consider a case where a user inputs the conditions for the next match. For example, the following prompt is input to a generative AI model:

[1264] Our next match will be in rainy weather, and our opponent is one of the best in the league. Our team has been winning a lot recently, but one of our main players has a slight injury. What are the best tactics and formations to use?

[1265] The server receives this prompt and uses the generated model to calculate the optimal tactics and formation. For example, it might present the user with a result such as, "In a match on rainy days, it is best to emphasize defense and use a 4-4-2 formation." If the user shows a happy expression after the match, the emotion engine feeds that information back to the server, and the server uses that information to adjust the model so that it will present the same tactics and formation the next time.

[1266] In this way, a system is realized that provides optimal tactics and formations based on the user's input data and emotional feedback.

[1267] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1268] Step 1:

[1269] The user inputs the match conditions and team status.

[1270] Through the device interface, the user inputs the conditions of the next match and the team's situation, such as the weather, the strength of the opposing team, the condition of the players, etc. The input data is stored on the device in a standard format such as JSON.

[1271] Step 2:

[1272] The terminal transmits the input data to the server.

[1273] The terminal transmits the data entered by the user to the server, using a secure communications protocol, where the data is received and prepared for analysis.

[1274] Step 3:

[1275] The server preprocesses the data received.

[1276] The server preprocesses the received data. Specifically, it complements missing values ​​and normalizes the data. For example, if a player's condition is not entered, it complements the estimated value from past data. The preprocessed data is converted into a format for input into the machine learning model.

[1277] Step 4:

[1278] The server uses machine learning models to calculate optimal tactics and formations.

[1279] The server inputs the preprocessed data into a machine learning model to calculate optimal tactics and formations. For example, it runs a model using Python's TensorFlow library and determines that a 4-4-2 formation is optimal. The calculation results are saved in JSON format.

[1280] Step 5:

[1281] The server transmits the calculation result to the terminal.

[1282] The server sends the calculation results to the terminal, which receives them in JSON format and converts them into a format for display to the user.

[1283] Step 6:

[1284] The terminal displays the results to the user.

[1285] The terminal displays the received results to the user. For example, it displays on the screen, "Please use a 4-4-2 formation in the next game." The user decides on the tactics for the next game based on this information.

[1286] Step 7:

[1287] The emotion engine recognizes the user's emotions.

[1288] The emotion engine recognizes the facial expressions and voices of the user after viewing the results. For example, if the user shows a happy expression, that information is captured. Emotion data is analyzed in real time.

[1289] Step 8:

[1290] The emotion engine feeds back the recognition results to the server.

[1291] The emotion engine feeds back the recognized emotion data to the server. For example, it sends information that "the user showed a happy expression." The feedback data is stored on the server side and used for analysis.

[1292] Step 9:

[1293] The server adjusts the model based on the feedback.

[1294] The server adjusts the machine learning model based on the feedback. For example, it updates the model so that the tactics and formations that the user showed a happy expression will be presented preferentially next time. The adjustments to the model are reflected in the calculation of the next tactics and formations.

[1295] (Application example 2)

[1296] Next, a description will be given of Application Example 2 of Form 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".

[1297] In conventional factory operations, it was difficult to efficiently calculate tactics for optimizing machine operation and placement. In addition, the system could not continue learning based on feedback that took into account the emotions of the operator, which led to issues with insufficient efficiency in operations. This could result in a decline in the productivity and efficiency of the entire factory.

[1298] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1299] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for calculating tactics and placements for optimizing the operation of machines in the factory, and a means for recognizing the user's emotions and allowing the system to continue learning based on the feedback. This makes it possible to efficiently optimize operations in the factory and for the system to continue learning based on feedback that takes the user's emotions into account.

[1300] "Cutting-edge tactics" are tactics derived based on the latest technology and data analysis.

[1301] "Player Data" means information relating to a player's performance or abilities.

[1302] "Opponent Data" means information regarding the opponent's tactics and performance.

[1303] A "learning tool" refers to the methods and techniques used to analyze data and train models.

[1304] "Presentation medium" refers to the method or technique used to display information to the user.

[1305] An "image video to the goal" is a simulation video that is generated based on the presented tactics and formation.

[1306] "Tactics and layouts for optimizing the operation of machines in a factory" refers to strategies and layouts for achieving efficient operation of machines and equipment in a factory.

[1307] "Means of recognizing user emotions" refers to methods and technologies for analyzing emotions from a user's facial expressions, voice, text input, etc.

[1308] "Means for the system to continue learning based on feedback" refers to methods and techniques that allow the system to continually improve using feedback information from users.

[1309] A system for carrying out this invention has the following configuration: The server includes a means for learning cutting-edge tactics, player data, and opponent data, a means for presenting optimal tactics and formations to a team based on the learned data, a means for generating and presenting an image video leading up to the goal based on the presented tactics and formations, a means for calculating tactics and placements for optimizing the operation of machines in a factory, and a means for recognizing the emotions of the user and allowing the system to continue learning based on the feedback.

[1310] Hardware and Software Used

[1311] Hardware

[1312] Camera: Used to capture the user's facial expressions.

[1313] Microphone: Used to capture the user's voice.

[1314] Computer: Used to process data and run models.

[1315] software

[1316] Python: Used to implement the program.

[1317] scikit-learn: Used to train and predict machine learning models.

[1318] emotion_recognition: Used as an emotion engine library.

[1319] Data processing and calculation

[1320] The server first reads the factory status data and inputs it into the machine learning model. The model predicts the optimal tactics and outputs the results. Next, it recognizes the user's emotions and inputs that information into the system as feedback. The system continues to learn based on the feedback and improves the accuracy of the next prediction.

[1321] Examples

[1322] For example, it can calculate the optimal placement and operation patterns for robots in a factory to operate efficiently. The emotion engine recognizes whether the user is satisfied, and if the user is satisfied, it presents the tactic again.

[1323] Examples of prompt statements

[1324] Please enter the current status of your factory. For example, the operation status of robots, the status of the production line, etc.

[1325] Provide a video feed to recognize user emotions.

[1326] It calculates the optimal tactic and presents it to the user.

[1327] In this way, factory operations can be efficiently optimized and the system can continuously learn based on user feedback, taking into account user emotions.

[1328] The flow of the identification process in the application example 2 will be described with reference to FIG.

[1329] Step 1:

[1330] The server reads the factory status data. Specifically, it collects data such as the operation status of robots and the status of the production line, and inputs this data into the machine learning model. The input data includes past operation data and current status data. This allows the model to grasp the current state of the factory.

[1331] Step 2:

[1332] The server calculates optimal tactics and deployment based on the learned data. Specifically, it uses a machine learning model (e.g., RandomForestClassifier) ​​to predict tactics and deployment to optimize the operation of machines in the factory. The input data is the factory status data collected in step 1, and the output is a proposal for optimal tactics and deployment.

[1333] Step 3:

[1334] The server captures the user's facial expressions and voice using a camera and microphone to recognize the user's emotions. Specifically, it uses the emotion_recognition library to analyze the user's emotions. The input data is the user's video feed and audio data, and the output is the user's emotional state.

[1335] Step 4:

[1336] The server inputs the user's emotions into the system as feedback. Specifically, the system continues to learn based on the recognized emotion data. This improves the accuracy of the next prediction. The input data is the user's emotion data obtained in step 3, and the output is the updated machine learning model.

[1337] Step 5:

[1338] The server presents the optimal tactics and placements to the user. Specifically, it displays the generated tactics and placements to the user. The input data are the optimal tactics and placements calculated in step 2, and the output is the information presented to the user.

[1339] Step 6:

[1340] The user checks the presented tactics and placements and provides feedback if necessary. Specifically, the emotion engine recognizes whether the user is satisfied, and if the user is satisfied, the tactic is presented again. The input data is the user's feedback, and the output is the system's learning data.

[1341] Example 3

[1342] Next, a third embodiment of the third embodiment will be described. 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".

[1343] In conventional tactical and formation presentation systems, if a user is dissatisfied with the presented tactics, there is a lack of a means to reflect that feedback. In addition, there is a problem that the presentation of specific practice methods for realizing tactics and formations is insufficient, making it difficult for users to effectively execute tactics.

[1344] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1345] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations for a team based on the learned data, a means for generating and presenting an image video of the goal based on the presented tactics and formations, a means for analyzing the user's emotions and providing feedback, and a means for generating and presenting new tactics based on the feedback information. This makes it possible to present new tactics that reflect the user's feedback, and also present specific practice methods for realizing the tactics and formations.

[1346] "Cutting-edge tactics" refers to strategies designed based on the latest data analysis and tactical theory.

[1347] "Player data" refers to data including information about an individual player's performance, skills, physical fitness, past match results, etc.

[1348] "Opponent data" refers to data that includes information such as the opponent's tactics, player characteristics, past match results, etc.

[1349] "Means of learning" refers to methods that use machine learning and data analysis techniques to analyze tactics and player data and derive optimal tactics.

[1350] "Presentation means" refers to the method of displaying the analysis results and generated tactics and formations to the user in visual or textual form.

[1351] "Image video leading up to the goal" refers to a video that simulates and visually depicts the movements of players and the ball based on presented tactics and formations.

[1352] "Means for analyzing emotions" refers to techniques or algorithms for analyzing a user's emotions, including, for example, methods for determining emotions through user feedback or facial expression recognition.

[1353] "Means of providing feedback" refers to the method by which the system generates new tactics and formations based on the analyzed user's emotional information.

[1354] "Means for generating new tactics" refers to a method for redesigning and presenting optimal tactics and formations taking into account user feedback information.

[1355] "Means for presenting a practice method" refers to a method for presenting to a user specific training menus and practice points necessary to realize tactics and formations.

[1356] This invention is a system that generates an image video of the path to the goal based on the tactics and formations presented by the user, and also presents a practice method for achieving those tactics and formations.It also includes a function to analyze the user's emotions and generate new tactics based on the feedback.

[1357] System Configuration

[1358] Hardware and Software

[1359] Servers play a central role in data learning, analysis, simulation, video generation, emotion analysis, and feedback processing, and therefore require servers equipped with high-performance processors and large-capacity memory.

[1360] Blender is used as the 3D modeling software, which allows for realistic simulation of player and ball movements.

[1361] Unity is used as animation software, which allows for the generation of image videos based on the simulation results.

[1362] A machine learning model is used as a sentiment analysis engine to analyze user emotions and provide feedback.

[1363] Program Processing

[1364] Data learning and analysis

[1365] The server learns cutting-edge tactics, player data, and opponent data, including past match data, player performance data, opponent tactical data, etc. Based on this data, it analyzes the best tactics and formations for each team.

[1366] Presentation of tactics and formations

[1367] The server presents the optimal tactics and formations to the user based on the learned data. The presented tactics and formations are displayed on the user's device.

[1368] Image video generation

[1369] The server uses Blender to simulate the movements of the players and the ball. It then uses Unity to generate an image video based on the simulation results. The generated video is sent to the user's device, where the user can watch it.

[1370] Presentation of practice methods

[1371] Based on the learned data and generative AI models, the server calculates what kind of practice each player needs to do to realize the tactics and formations. Specifically, it calculates the necessary skills and abilities based on each player's performance data and past match data, and suggests training methods.

[1372] Sentiment Analysis and Feedback

[1373] The emotion analysis engine analyzes the user's emotions. For example, if the user is dissatisfied with a particular tactic, the user feeds that information back to the system. The server generates new tactics based on the feedback information and presents them to the user.

[1374] Examples of concrete examples and prompts

[1375] Examples

[1376] A user inputs into the system, "I want to see some attacking tactics in a 4-4-2 formation."

[1377] The server receives the input data and uses Blender to simulate the movement of the players and the ball. For example, it calculates the movement of player A dribbling from the right side and player B receiving the pass in the center.

[1378] The server uses Unity to generate image videos based on the simulation results. For example, it realistically reproduces the dribbling movements of player A and the passing movements of player B.

[1379] The video generated by the server is transmitted to the user's terminal, and the user watches the video.

[1380] Based on each player's past match data, the server suggests dribbling practice for Player A and passing practice for Player B.

[1381] Users can check the practice methods and incorporate them into their actual training.

[1382] The emotion engine analyzes the user's dissatisfaction and provides feedback to the server.

[1383] The server generates new tactics based on the feedback and presents them to the user.

[1384] Examples of prompt statements

[1385] "Please generate a video showing offensive tactics using a 4-4-2 formation."

[1386] "Please tell me how each player can practice to implement the 4-4-2 formation."

[1387] "I'm not happy with this tactic. Please suggest a new one."

[1388] The above is an embodiment of the invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1389] Step 1:

[1390] The user inputs tactics and formations.

[1391] The user inputs the desired tactics and formations through the system interface, for example, "I want to see attacking tactics in a 4-4-2 formation." The input data is then sent to the server.

[1392] Step 2:

[1393] The server receives and parses the input data.

[1394] The server receives tactical and formation data sent by the user. It analyzes the received data and extracts information necessary for the simulation. Specifically, it analyzes the type of tactics and the placement of the formation. The input is the user's tactical and formation data, and the output is the analyzed simulation information.

[1395] Step 3:

[1396] The server performs the simulation using 3D modeling software.

[1397] The server uses Blender to simulate the movements of players and the ball. For example, it calculates the movements of player A dribbling from the right side and player B receiving the pass in the center. The input is the analyzed simulation information, and the output is the simulation result.

[1398] Step 4:

[1399] The server uses animation software to generate moving images.

[1400] The server uses Unity to generate image videos based on the simulation results. For example, it realistically reproduces the dribbling of player A and the passing movements of player B. The input is the simulation results, and the output is the generated image video.

[1401] Step 5:

[1402] The video generated by the server is sent to the user's terminal.

[1403] The server transmits the generated image video to the user's terminal. The transmission uses data transfer technology via the Internet. The input is the generated image video, and the output is the video transmitted to the user's terminal.

[1404] Step 6:

[1405] A user watches a video.

[1406] The user watches the image video received on the device. Through the video, the user can confirm the specific movements of the tactics and formations. The input is the video sent to the user's device, and the output is the user's viewing behavior.

[1407] Step 7:

[1408] The server calculates the practice method and presents it to the user.

[1409] Based on the learned data and generative AI models, the server calculates what kind of practice each player needs to achieve the tactics and formations. Specifically, based on each player's performance data and past match data, it calculates the necessary skills and abilities and suggests training methods. The input is each player's performance data and past match data, and the output is the calculated training method.

[1410] Step 8:

[1411] The user checks the practice method.

[1412] The user confirms the practice method presented on the terminal. The practice method includes a specific training menu and practice points. The input is the calculated practice method, and the output is the user's confirmation action.

[1413] Step 9:

[1414] The emotion engine analyzes the user's emotions and provides feedback.

[1415] The emotion engine analyzes the user's emotions. For example, if a user is dissatisfied with a particular tactic, it feeds that information back to the system. The input is the user's emotion data, and the output is the feedback information.

[1416] Step 10:

[1417] The server generates new tactics based on the feedback and presents them to the user.

[1418] The server generates new tactics based on the feedback information from the emotion engine. The generated tactics are sent to the user's device and presented to the user. The input is the feedback information, and the output is the newly generated tactics.

[1419] (Application example 3)

[1420] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1421] Conventional systems only provide tactics and formations, and do not provide specific instructions on actual movements or practice methods. In addition, there was not enough adjustment based on simulations or feedback regarding the optimization of robot movements and work within the factory. This made it difficult to create an efficient work environment.

[1422] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1423] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations for a team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for generating and presenting a simulation video of the robot's movements and work in the factory, a means for presenting the optimal work method based on the performance data and past work data of each robot, and a means for analyzing the feedback of the workers with an emotion engine and adjusting the work method and the robot's movements. This makes it possible to present specific movements of tactics and formations, and present and adjust efficient work methods for robots in the factory.

[1424] "Cutting-edge tactics" refers to strategies and formations that are developed using the latest technology and data analysis.

[1425] "Player data" refers to information such as an individual player's performance, skills, and past match results.

[1426] "Opponent data" refers to information such as the opponent's tactics, player characteristics, and past match results.

[1427] "Learning means" refer to the methods and techniques for collecting data, analyzing it, and building models.

[1428] "Presentation medium" refers to the methods or techniques used to present information to the user visually or audibly.

[1429] An "image video leading up to the goal" is a video that is generated based on tactics and formations and visually depicts the movements leading up to the goal.

[1430] A "simulation video of robot movements and work in a factory" is a video that virtually reproduces the movements and work of a robot in a factory.

[1431] "Performance data" refers to data concerning the performance of a robot or athlete, such as their movements, work efficiency, and accuracy.

[1432] "Past work data" refers to data regarding the content and results of work performed in the past.

[1433] An "emotion engine" is a technology that analyzes user emotions and feedback and adjusts system behavior based on that.

[1434] A "system" is a device or program with a set of functions that is composed of multiple means or technologies.

[1435] The system for implementing this invention is composed of three main elements: a server, a terminal, and a user. The specific roles and processing contents of each element are explained below.

[1436] server

[1437] The server learns the latest tactics, player data, and opponent data, and based on this, presents the optimal tactics and formations for each team. Specifically, the server uses the following software and hardware:

[1438] Software: Python, NumPy, Matplotlib, scikit-learn

[1439] Hardware: A server with a powerful processor and large memory capacity

[1440] The server collects data, analyzes it, and builds a model. For example, it generates optimal tactics and formations using past match data and player performance data. It also generates an image video of the path to the goal based on the generated tactics and formations, and presents it to the user.

[1441] In addition, it generates simulation videos of robots' movements and work in the factory, and suggests optimal work methods based on each robot's performance data and past work data. It also analyzes feedback from workers using an emotion engine to adjust work methods and robot movements.

[1442] Terminal

[1443] A terminal is a device that allows a user to receive and display information provided by a server. Specifically, this includes smartphones, tablets, and personal computers. A terminal uses the following software and hardware:

[1444] Software: Web browser, dedicated application

[1445] Hardware: Smartphones, tablets, computers

[1446] The terminals display images of tactics and formations sent from the server, robot simulation videos, optimal work methods, etc. Based on this information, users can understand and practice tactics and work methods.

[1447] User

[1448] The user uses the server and the terminal to implement tactics and work methods based on the information provided. The user performs the following specific operations:

[1449] Watch and understand videos that provide examples of tactics and formations.

[1450] Participants watch simulation videos of robot movements and operations within a factory to learn optimal work methods.

[1451] The worker's feedback is sent to the server, and the work method is adjusted based on the results analyzed by the emotion engine.

[1452] Examples

[1453] For example, if a user wants to optimize the movement of a robot in a factory, he can send a prompt to the server like this:

[1454] "Simulate the robot's movements in a factory and suggest the best way to perform tasks. Then adjust your tactics based on worker feedback."

[1455] The server receives the prompt text, generates a simulation video of the robot's movements and work, and presents the optimal way to work.The user can then practice the work based on this and send feedback to the server, resulting in a more efficient work environment.

[1456] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1457] Step 1:

[1458] The server collects state-of-the-art tactical and player data and opponent data, including past match data, player performance data, opponent tactical data, etc. These data are input and stored in a database.

[1459] Step 2:

[1460] The server analyzes the collected data and uses a generative AI model to generate optimal tactics and formations. Specifically, it uses Python and scikit-learn to learn the data and build a model. The input is the collected data, and the output is the optimal tactics and formations.

[1461] Step 3:

[1462] The server generates an image video of the path to the goal based on the generated tactics and formation. This is done using 3D modeling software and animation software. The input is the generated tactics and formation, and the output is an image video.

[1463] Step 4:

[1464] The server generates simulation videos of the robot's movements and work in the factory, using the robot's performance data and past work data. The input is the robot data, and the output is the simulation video.

[1465] Step 5:

[1466] The server presents the optimal work method based on the performance data and past work data of each robot. Specifically, it analyzes the data using KMeans clustering and calculates the optimal work method. The input is the robot data, and the output is the optimal work method.

[1467] Step 6:

[1468] The terminal displays tactics and formation image videos sent from the server, robot simulation videos, optimal work methods, etc. The input is data from the server, and the output is visual information presented to the user.

[1469] Step 7:

[1470] The user puts tactics and work methods into practice based on the information provided through the terminal. Specifically, the user watches visualization videos of tactics and formations, and watches simulation videos of robot movements and work in a factory. The input is information from the terminal, and the output is the user's understanding and practice.

[1471] Step 8:

[1472] Users send worker feedback to the server through their terminals. The server analyzes the feedback using an emotion engine and adjusts tactics and work methods. The input is the user feedback, and the output is the adjusted tactics and work methods.

[1473] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[1474] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1475] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1476] 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 smart glasses 214.

[1477] [Third embodiment]

[1478] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1479] 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.

[1480] 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 wide area network (WAN) and / or a local area network (LAN).

[1481] 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.

[1482] 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 the voice according to instructions from the processor 46.

[1483] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1484] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1485] Fig. 6 shows an example of 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.

[1486] 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.

[1487] 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.

[1488] In the headset type terminal 314, the reception and output process is performed by the processor 46. A reception and output program 60 is stored in the storage 50. The processor 46 reads out the reception and output program 60 from the storage 50, and executes the read reception and output program 60 on the RAM 48.

[1489] The reception and output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception and output program 60 executed on the RAM 48.

[1490] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1491] "Example 1"

[1492] The system of the present invention acquires cutting-edge tactics, player data, and opponent data through a database, API, etc., and performs learning using a machine learning algorithm. Specifically, past match data, player performance data, opponent tactical data, etc. are input, and patterns and trends are extracted from this data.

[1493] "Example 2"

[1494] As a means of presenting the optimal tactics and formations for a team based on learned data, the optimal tactics and formations are calculated using a model generated by a machine learning algorithm and presented to the user. Specifically, the optimal tactics and formations are calculated based on the match conditions and team situation specified by the user and presented to the user. "Example 3"

[1495] As a means of generating and presenting an image video of the goal based on the presented tactics and formation, a video visually expressing the presented tactics and formation is generated using 3D modeling software, animation software, etc., and this is presented to the user. Specifically, based on the presented tactics and formation, the movements of the players and the ball are simulated, and this is generated and presented as a video.

[1496] "Example 4"

[1497] As a means of presenting training methods to realize the proposed tactics and formations, the system calculates what kind of training each player needs to do to realize the proposed tactics and formations based on the learned data and the generated model, and presents this to the user. Specifically, the system calculates the skills and abilities required by each player based on the performance data and past match data of each player, and presents training methods based on this.

[1498] The process flow of each embodiment will be described below.

[1499] "Example 1"

[1500] Step 1: Obtain cutting-edge tactics, player data, and opponent data through databases, APIs, etc.

[1501] Step 2: The acquired data is fed into a machine learning algorithm to learn from it, using data from past matches, player performance data, opponent tactical data, etc. to extract patterns and trends.

[1502] "Example 2"

[1503] Step 1: Calculate optimal tactics and formations using a model generated by a machine learning algorithm.

[1504] Step 2: Present the calculated tactics and formation to the user. At this time, the system presents the optimal tactics and formation based on the match conditions and team situation specified by the user.

[1505] "Example 3"

[1506] Step 1: Using 3D modeling software, animation software, etc., create a video that visually represents the proposed tactics and formations.

[1507] Step 2: The generated video is presented to the user. At this time, the movements of the players and the ball are simulated based on the presented tactics and formation, and this is presented as a video.

[1508] "Example 4"

[1509] Step 1: Based on the learned data and the generated model, determine what kind of practice each player should do.

[1510] Calculate whether the proposed tactics and formations can be realized.

[1511] Step 2: Present the calculated training method to the user. At this time, the skills and abilities required by each player are calculated based on the performance data of each player and past match data, and the training method is presented based on this.

[1512] Example 1

[1513] Next, a description will be given of Example 1 of the embodiment 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".

[1514] In conventional tactical analysis systems, data acquisition, pre-processing, machine learning model training and evaluation were performed separately, and the system lacked efficiency as an integrated system. In addition, the system did not adequately present optimal tactics and formations, or even training methods to achieve them. This limited the improvement of team performance.

[1515] 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. In this invention, the server includes a means for acquiring past match data, player performance data, and opponent tactical data through a database or API, a means for preprocessing the acquired data, a means for learning a machine learning model using the preprocessed data, a means for evaluating the performance of the learned model, a means for deploying the evaluated model, a means for presenting optimal tactics and formations for the team based on the learned data, and a means for generating and presenting an image video up to the goal based on the presented tactics and formations. This makes it possible to consistently perform the processes from data acquisition to model learning, evaluation, deployment, and presentation of tactics, thereby efficiently improving team performance.

[1516] A "database" is a system for systematically storing data and efficiently searching and managing it.

[1517] "API" stands for Application Programming Interface, an interface for exchanging data and functions between different software programs.

[1518] "Past match data" is data that includes information about matches that have previously been played.

[1519] "Player performance data" refers to data relating to a player's movements during a match, their performance, physical strength, etc.

[1520] "Opponent's tactical data" refers to data regarding the opponent's tactics and formation.

[1521] "Preprocessing" is the process of converting data into a format suitable for learning from a machine learning model.

[1522] A "machine learning model" is an algorithm that learns patterns and trends from data and makes predictions and classifications.

[1523] "Evaluation" is the process of measuring the performance of a trained machine learning model and confirming its validity.

[1524] "Deployment" refers to the process of placing a machine learning model that has completed training and evaluation in an actual production environment and making it available for use.

[1525] "Tactics" refers to a team's strategy and playing style in a match.

[1526] A "formation" is a diagram that shows the positions and roles of players during a match.

[1527] An "image video" is a visual simulation video generated based on presented tactics and formations.

[1528] This invention is a system in which a server obtains past match data, player performance data, and opponent tactical data via a database or API, preprocesses this data, and presents optimal tactics and formations through a series of processes in which the server trains, evaluates, and deploys a machine learning model.

[1529] The server first obtains the necessary data using a database or API. A typical relational database management system (RDBMS) is used as the database, and a RESTful API is used as the API. For example, a sports data API can be used to obtain past match data.

[1530] The server then preprocesses the data, including imputing missing values, normalizing the data, encoding categorical data, etc., using the Python Pandas and Scikit-learn libraries.

[1531] The server uses the preprocessed data to train the machine learning model. Machine learning algorithms such as random forest and support vector machine (SVM) are used. Libraries such as Scikit-learn and TensorFlow are used for this purpose.

[1532] To evaluate the performance of the trained model, the server uses methods such as cross-validation and confusion matrix, and calculates evaluation indices such as precision, recall, and F1 score of the model.

[1533] Once the evaluation is complete, the model is deployed by the server using a web framework such as Flask or Django. The deployed model receives new data as input in real time and makes predictions.

[1534] As a concrete example, the server retrieves past match data from a sports data API, preprocesses the data using Pandas, trains a random forest model using Scikit-learn, evaluates the model using cross-validation, and deploys the model using Flask.

[1535] An example prompt is, "Use past match data, player performance data, and opponent tactical data to build a machine learning model to predict the outcome of the next match."

[1536] This system makes it possible to consistently collect data, train models, evaluate them, deploy them, and present tactics, thereby efficiently improving team performance.

[1537] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1538] Step 1: Get the data

[1539] The server retrieves past match data, player performance data, and opponent tactical data through a database or API. Inputs include API endpoint URLs and database queries. Specifically, the server sends API requests and receives data in JSON format. The output is the retrieved raw data.

[1540] Step 2: Preprocessing the data

[1541] The server preprocesses the acquired data. The input includes the raw data acquired in step 1. Specifically, the server creates a data frame using the Pandas library, imputes missing values, normalizes the data, and encodes categorical data. The output is the clean data after preprocessing.

[1542] Step 3: Train the machine learning model

[1543] The server trains a machine learning model using the preprocessed data. The input includes the preprocessed data from step 2. Specifically, the server builds a random forest model using the Scikit-learn library and trains the model with the data. The output is a trained machine learning model.

[1544] Step 4: Evaluate the model

[1545] The server evaluates the performance of the trained model. The inputs include the model trained in step 3 and the preprocessed data. Specifically, the server performs cross-validation and calculates evaluation metrics such as precision, recall, and F1 score. The output is the evaluation result.

[1546] Step 5: Deploy the model

[1547] The server deploys the model once evaluation is complete. The input includes the model evaluated in step 4. Specifically, the server builds a web service using the Flask framework to expose the model as an endpoint. The output is a web service running the deployed model.

[1548] Step 6: Present tactics and formations

[1549] The server then presents the best tactics and formations for the team based on the learned data. The inputs include the model deployed in step 5 and new match data. Specifically, the server inputs the new data into the model and predicts the best tactics and formations. The output is the presented tactics and formations.

[1550] Step 7: Generate and present image videos

[1551] The server generates and presents an image video of the goal based on the presented tactics and formation. The input includes the tactics and formation presented in step 6. In concrete terms, the server uses an image generation algorithm to visually simulate the tactics and formation. The output is the generated image video.

[1552] (Application example 1)

[1553] Next, a description will be given of Application Example 1 of Form 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".

[1554] Conventional sports tactics analysis systems and factory robot operation optimization systems function independently, making comprehensive data analysis and optimization difficult. In addition, there was no system that simultaneously optimized sports tactics and factory robot operations, making efficient data utilization impossible. As a result, tactical optimization of sports teams and improvement of production efficiency in factories were not fully achieved.

[1555] 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.

[1556] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for learning the operation data of robots in a factory and extracting optimal movement patterns, a means for presenting an efficient arrangement of the robots based on the extracted movement patterns, and a means for realizing optimization of the manufacturing line based on the presented arrangement. This makes it possible to simultaneously optimize sports tactics and the operation of robots in a factory.

[1557] "Tactics" refers to the plans and methods a team or player uses to achieve victory in a sport or competition.

[1558] "Player data" refers to information regarding a player's performance, abilities, past match results, etc.

[1559] "Opponent data" refers to information regarding the opponent's tactics, player performance, past match results, etc.

[1560] A "learning means" refers to a method or device that takes data and uses machine learning algorithms to extract patterns and trends.

[1561] "Presentation means" refers to a method or device that displays optimal tactics, formations, and movement patterns based on learned data.

[1562] An "image video" is a visual simulation that is generated based on presented tactics and formations.

[1563] A "factory robot" is an automated machine used in a factory.

[1564] "Operational data" refers to information regarding the robot's operating history and performance.

[1565] A "motion pattern" is a series of movements or steps that a robot follows to perform a specific task.

[1566] "Efficient layout" refers to the location and layout method in which robots and mechanical devices are placed most effectively.

[1567] A "production line" is a series of machines or equipment arranged to efficiently produce products.

[1568] "Optimization" refers to adjusting a system or process to be most effective in achieving a particular purpose.

[1569] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server plays a central role in collecting, learning, and analyzing data. The terminal is a device through which the user interfaces with the system, and the user is responsible for operating the system and checking the results.

[1570] Server Roles

[1571] The server processes and calculates data using the following hardware and software:

[1572] Hardware: Powerful processor, ample memory and storage

[1573] Software: Python, Pandas, Scikit-learn, Joblib

[1574] The server first collects past match data, player performance data, opponent tactical data, factory robot operation data, and production line data through databases and APIs. It then uses machine learning algorithms to learn from this data and extract patterns and trends. Specifically, it analyzes the data using a random forest regression model to derive optimal tactics and movement patterns.

[1575] Terminal Roles

[1576] A terminal is a device through which a user interfaces with the system. It can be a smartphone, tablet, or PC. The terminal receives the analysis results sent from the server and visually presents them to the user. For example, it shows the optimal tactics and formations of a sports team, or the efficient placement of robots in a factory.

[1577] User Roles

[1578] The user operates a terminal to access the system and input the necessary data. The user also checks the analysis results sent from the server and optimizes tactics and placement based on the results. The user follows the training methods and production line optimization procedures presented by the system.

[1579] Examples

[1580] For example, when a robot operating in a factory assembles a product, it can learn optimal movement patterns based on past data and perform efficient movements, improving the efficiency of the production line and enabling cost reduction.

[1581] Examples of prompt statements

[1582] Build a system that uses operational data from robots in factories to learn optimal operating patterns and achieve efficient operation. Past operational data, robot performance data, and production line data are input, and learning is performed using a random forest regression model.

[1583] In this way, by having the server, terminals, and users work together to operate the system, it becomes possible to simultaneously optimize sports tactics and the operation of robots in a factory.

[1584] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1585] Step 1:

[1586] The server collects past match data, player performance data, opponent tactical data, robot operation data in the factory, and production line data through databases and APIs. This data is stored on the server in CSV files or JSON format. The input is data obtained from various databases and APIs, and the output is raw data stored on the server.

[1587] Step 2:

[1588] The server preprocesses the collected data, specifically by imputing missing values, normalizing data, encoding categorical data, etc. The input is the raw data collected in step 1, and the output is the preprocessed data.

[1589] Step 3:

[1590] The server uses the preprocessed data to train a machine learning model, specifically a random forest regression model, to learn patterns and trends in the data. The input is the preprocessed data, and the output is the trained machine learning model.

[1591] Step 4:

[1592] The server uses the trained machine learning model to make predictions on new data, such as predicting the optimal movement pattern for a robot in a factory or the optimal tactics for a sports team. The input is the new data, and the output is the predicted result.

[1593] Step 5:

[1594] The server transmits the prediction results to the terminal. The terminal visually presents the received prediction results to the user. Specifically, it displays dashboards, graphs, simulation videos, etc. The input is the prediction results transmitted from the server, and the output is the visual information presented to the user.

[1595] Step 6:

[1596] The user operates the terminal to check the prediction results and optimize tactics and placement as necessary. Specifically, the user follows the practice methods and production line optimization procedures presented by the system. The input is the prediction results displayed on the terminal, and the output is the user's actions.

[1597] In this way, by having the server, terminals, and users work together to operate the system, it becomes possible to simultaneously optimize sports tactics and the operation of robots in a factory.

[1598] Example 2

[1599] Next, a second embodiment of the second form will be described. 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".

[1600] Conventional methods for determining tactics and formations make it difficult to quickly and accurately calculate optimal tactics according to match conditions and team situations. In addition, there was a lack of means to understand how the presented tactics and formations specifically worked, making it difficult to apply them in actual matches.

[1601] 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.

[1602] In this invention, the server includes a means for a user to input match conditions and team situations, a means for transmitting the input data to the server, a means for the server to analyze the data received and input it to the generative AI model, a means for calculating optimal tactics and formations using the generative AI model, and a means for presenting the calculation results to the user. This makes it possible to quickly and accurately calculate optimal tactics and formations according to match conditions and team situations and present them to the user.

[1603] "User" refers to an individual or group that uses the system to input match conditions and team status.

[1604] "Match conditions" refers to information that indicates the environment and circumstances regarding the upcoming match, and includes the weather, the characteristics of the opposing team, and the like.

[1605] "Team status" refers to information indicating the current state of the team, the condition of the players, tactical preferences, and the like.

[1606] A "terminal" is a device through which a user inputs match conditions and team status and communicates with the server.

[1607] The "Server" is a computer system that receives and analyzes data sent by users and uses a generative AI model to calculate optimal tactics and formations.

[1608] A "generative AI model" is a model generated by a machine learning algorithm and is used to calculate optimal tactics and formations based on training data.

[1609] "Tactics" refers to the specific playing style and strategy adopted by a team in a match.

[1610] "Formation" refers to the specific positions in which a team's players are positioned during a match.

[1611] The "calculation results" are information on optimal tactics and formations calculated using a generative AI model.

[1612] "Presenting" is the act of showing the results of a calculation to a user visually or in some other way.

[1613] The present invention is a system that allows a user to input match conditions and team situations, calculates optimal tactics and formations based on the input, and presents the results to the user. A specific embodiment of this system will be described below.

[1614] First, a user uses a terminal to input the match conditions and team status. The terminal can be a device such as a smartphone, tablet, or PC, and input is performed through a dedicated application or web interface. For example, a user may input information such as: "The next match will be played on rainy days, and the opposing team has a high offensive power. Our team has a strong defensive power, but an average offensive power."

[1615] The terminal converts the input data into a data format such as JSON and sends it to the server using an HTTP request. The server analyzes the received data and performs necessary preprocessing, such as converting text data into numerical data. The preprocessed data is then input into the generative AI model.

[1616] The server uses machine learning libraries such as Python's Scikit-learn and TensorFlow to run generative AI models. The generative AI models calculate optimal tactics and formations based on the training data. For example, they can get results such as "The optimal tactic is to strengthen the defense with a 4-4-2 formation while aiming for counter attacks."

[1617] The calculated results are sent from the server to the device. The device analyzes the received results and displays them to the user. For example, it could display on the screen, "The optimal tactic for the next match is to use a 4-4-2 formation, strengthen the defense, and aim for counter attacks."

[1618] This system allows users to quickly and accurately obtain optimal tactics and formations according to match conditions and team situations, and also provides a means to understand how the presented tactics and formations work specifically, making it easier to apply them in actual matches.

[1619] As a concrete example, a user might input the following prompt into a generative AI model:

[1620] "The next game will be played in rainy weather, and the opposing team has a strong attacking ability. Our team has a strong defense, but an average attacking ability. Please tell me the best tactics and formations for these conditions."

[1621] Based on this prompt, the server uses the generated model to calculate the optimal tactics and formations and presents them to the user. For example, it might present a result such as, "The optimal tactics are a 4-4-2 formation that strengthens the defense while aiming for counter attacks."

[1622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1623] Step 1:

[1624] The user inputs the match conditions and team status.

[1625] The user inputs the conditions of the next match (e.g., weather, characteristics of the opposing team) and the situation of his / her own team (e.g., players' condition, tactical preferences) through the terminal interface. For example, the user inputs information such as "The next match will be in rain, and the opposing team has a strong offensive power." The input data is in text format.

[1626] Step 2:

[1627] The terminal transmits the input data to the server.

[1628] The terminal converts the data entered by the user into a data format such as JSON format and sends it to the server using an HTTP POST request. For example, it sends the data {"weather": "rain", "opponent_strength": "high_attack"}. The input is text data, and the output is JSON format data.

[1629] Step 3:

[1630] The server analyzes the data it receives and inputs it into a generative AI model.

[1631] The server parses the received JSON data and performs the necessary preprocessing. For example, convert text data into numerical data, such as {"weather": 1, "opponent_strength": 2}. The preprocessed data is input to the generative AI model. The input is JSON format data, and the output is preprocessed numerical data.

[1632] Step 4:

[1633] The server uses generative AI models to calculate optimal tactics and formations.

[1634] The server uses machine learning libraries such as Python's Scikit-learn and TensorFlow to run generative AI models. The model calculates optimal tactics and formations based on the input data. For example, it may obtain a result such as "The optimal tactic is to strengthen the defense with a 4-4-2 formation while aiming for counter attacks." The input is preprocessed numerical data, and the output is tactical and formation information.

[1635] Step 5:

[1636] The server transmits the calculation result to the terminal.

[1637] The server converts the calculated results into a data format such as JSON and sends it to the terminal using an HTTP response. For example, it sends the data {"formation": "4-4-2", "strategy": "defensive_counter"}. The input is tactical and formation information, and the output is JSON format data.

[1638] Step 6:

[1639] The terminal displays the results to the user.

[1640] The terminal analyzes the received results and displays them to the user. For example, it might display on the screen, "The best tactic for the next match is to use a 4-4-2 formation, strengthen the defense, and aim for counter attacks." The input is JSON format data, and the output is a visual display.

[1641] (Application example 2)

[1642] Next, a description will be given of Application Example 2 of Form 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".

[1643] Conventional tactical and formation suggestion systems are limited to suggesting optimal tactics and formations for sports teams, and do not address the optimization of robot placement and operation tactics in factories. For this reason, there is a demand for a system that proposes optimal robot placement and operation tactics to maximize factory production efficiency.

[1644] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1645] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for proposing optimal placement and operation tactics of robots in a factory, a means for calculating optimal placement and operation tactics of robots based on the status and work contents of the factory production line, and a means for presenting this to a factory manager. This makes it possible to optimize not only the tactics and formations of sports teams, but also the placement and operation tactics of robots in a factory.

[1646] "Cutting-edge tactics" are tactics that are formulated based on the latest data analysis techniques and strategic theories.

[1647] "Player data" refers to information relating to a player's performance, physical strength, technique, tactical understanding, etc.

[1648] "Opponent data" refers to information relating to the opponent's tactics, player characteristics, past match results, etc.

[1649] "Learning means" refers to the process of using machine learning algorithms to analyze data and generate models.

[1650] "Means for presenting optimal tactics and formations" refers to a method for presenting to a user the most effective tactics and formations for a team based on learned data.

[1651] "A means for generating and presenting an image video leading up to the goal" refers to a method for simulating movements during a match based on presented tactics and formations, and presenting the results to the user in video format.

[1652] The "means for proposing optimal placement and operation tactics for robots in a factory" is a method for making proposals for optimizing the placement and operation of robots based on the status of the factory's production line and the work content.

[1653] "A means for calculating optimal robot placement and operation tactics based on the status of the factory's production line and the work content" refers to a method for analyzing various data within the factory and calculating optimal robot placement and operation tactics.

[1654] "Means of presenting to the factory manager" refers to a method of presenting the calculated optimal robot placement and operation tactics to the factory manager in an easy-to-understand manner.

[1655] The system for implementing the present invention operates in cooperation with a server, a terminal, and a user. A specific embodiment of the system will be described below.

[1656] server

[1657] The server has the means to learn cutting-edge tactics, player data, and opponent data. For this, it uses Python and machine learning libraries such as scikit-learn. The server has the means to present optimal tactics and formations for teams based on the learned data. It also has the means to generate and present image videos leading up to the goal based on the presented tactics and formations. For this, it uses video generation libraries and simulation software.

[1658] The server also has the means to propose optimal placement and operation tactics for robots in the factory. It has the means to calculate optimal placement and operation tactics for robots based on the status of the factory's production line and the work content. To do this, it uses data analysis tools to analyze various sensor data and work logs in the factory. The calculated results are presented to the factory manager.

[1659] Terminal

[1660] The terminal provides an interface for users to access the server. Smartphones, tablets, PCs, etc. are used as terminals. The terminal displays the tactics and formations presented by the server, as well as the placement and operation tactics of the robots. For this purpose, a web browser or a dedicated application is used.

[1661] User

[1662] The user accesses the server through a terminal and inputs the necessary data. For example, the match conditions of a sports team or the status data of a factory production line. The user checks the optimal tactics and formations, as well as the robot placement and operation tactics presented by the server, and performs actual operations based on them.

[1663] Examples

[1664] For example, to optimize the placement of robots in a factory, the following data is input:

[1665] "In order to optimize the placement of robots in the factory, input the current status data of the production line. For example, input data such as the operating rate, work content, work time, and error rate of each robot."

[1666] Following these prompts, the user inputs the necessary data, which the server analyzes to calculate the optimal placement and operation tactics. The results are displayed on the terminal, and the user can check them and apply them to actual operations.

[1667] The above is a specific embodiment for carrying out the present invention.

[1668] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1669] Step 1:

[1670] A user accesses a server using a terminal.

[1671] Input: Credentials for the user to access the server through the terminal.

[1672] Output: The server verifies the user's identity and grants access.

[1673] Specific operation: The user opens a browser or a dedicated application on the device and enters authentication information into the login screen. The server verifies the authentication information and allows the user access.

[1674] Step 2:

[1675] The user inputs the necessary data through the terminal.

[1676] Input: Data on the match conditions of a sports team or the status of a factory production line.

[1677] Output: The input data that is sent to the server.

[1678] Specific operation: The user enters the match conditions (e.g., weather, opponent information) and factory status data (e.g., each robot's operating rate, work content, work time, error rate) into the input form on the terminal, and presses the send button. The server receives this data.

[1679] Step 3:

[1680] The server analyzes the received data and uses machine learning models to calculate optimal tactics, formations, robot placement and operation tactics.

[1681] Input: Match conditions and factory status data sent by the user.

[1682] Output: Optimal tactics and formations, as well as robot placement and movement tactics.

[1683] Specific operation: The server pre-processes the received data and inputs it into the machine learning model. The model analyzes the data and calculates the optimal tactics, formations, and robot placement and operation tactics.

[1684] Step 4:

[1685] The server transmits the calculated result to the terminal.

[1686] Input: Optimal tactics and formations, as well as robot placement and movement tactics.

[1687] Output: The result data sent to the terminal.

[1688] Specific operation: The server formats the calculated result and sends it to the terminal, which receives it and displays it to the user.

[1689] Step 5:

[1690] The user checks the results via the terminal and reflects them in actual operations.

[1691] Input: Optimal tactics and formations sent from the server, as well as robot placement and movement tactics.

[1692] Output: Actual operation based on user confirmed results.

[1693] Specific operation: Users check the results displayed on their devices and adjust their sports team's tactics or the placement of robots in a factory based on the results.

[1694] Example 3

[1695] Next, a third embodiment of the third embodiment will be described. 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".

[1696] Conventional tactical and formation suggestion systems lacked a means to visually confirm the effectiveness of tactics and formations, and it was difficult to provide specific practice methods to realize the proposed tactics. This made it difficult for users to understand the effects of tactics, and they were unable to find effective practice methods.

[1697] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1698] In this invention, the server includes a means for learning tactics, player data, and opponent data, a means for presenting optimal tactics and formations to a team based on the learned data, a means for generating an image video of the goal based on the presented tactics and formations, a means for presenting the generated image video to a user, a means for calculating a practice method for realizing the presented tactics and formations, and a means for presenting the calculated practice method to a user. This allows a user to visually confirm the effects of the tactics and formations, and further allows the user to know specific practice methods.

[1699] "Tactics" are the specific methods or strategies that plan and direct how a team will play in a match.

[1700] "Player data" refers to information regarding an individual player's performance, skills, physical strength, past match results, etc.

[1701] "Opponent data" refers to information relating to the opposing team's tactics, player characteristics, past match results, etc.

[1702] "Means of learning" refers to methods and techniques for analyzing tactics, player data, and opponent data to derive optimal tactics and formations.

[1703] "Means of presentation" refers to methods or techniques for displaying optimal tactics and formations to the user based on learned data.

[1704] An "image video" is a video that visually depicts the movements of players and the ball, generated based on presented tactics and formations.

[1705] "Means of generation" refers to methods and techniques for creating image videos based on tactics and formations.

[1706] The "means for presenting to the user" refers to a method or technique for displaying the generated image moving image to the user.

[1707] "Means for calculating training methods" refers to methods or techniques for calculating and deriving the training methods necessary to realize the presented tactics and formations.

[1708] The "means for presenting a practice method" refers to a method or technique for displaying the calculated practice method to the user.

[1709] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1710] This invention is a system that generates an image video of the path to the goal based on tactics and formations and presents it to the user. It also includes a function to suggest practice methods for achieving the presented tactics and formations.

[1711] Hardware and Software Used

[1712] Hardware: High-performance server (e.g. server with GPU)

[1713] Software: 3D modeling software (e.g. Blender), animation software (e.g. Autodesk Maya), generative AI models (e.g. GPT-4)

[1714] Specific operation of the system

[1715] 1. Enter tactics and formations

[1716] Users use terminals to input tactics and formations into the system.

[1717] Example: A user enters "I want to strengthen attacks from the sides with a 4-4-2 formation" into an input form on a terminal and clicks the submit button.

[1718] 2. Simulating the data

[1719] The server analyzes the tactical and formation data received from the user.

[1720] The server uses 3D modelling software (e.g. Blender) to model the player positions and movements.

[1721] The server uses animation software (e.g. Autodesk Maya) to simulate player movements and ball movement.

[1722] Example: The server sets the initial positions of the players in Blender, and calculates the player movements and ball trajectory in Maya.

[1723] 3. Video Generation

[1724] The server generates a visually-presented video based on the simulation results.

[1725] The server uses rendering software to convert the simulation results into a video file.

[1726] Example: A server starts a rendering process, generating a one minute video of images.

[1727] 4. Presenting the video

[1728] The video generated by the server is sent to the user's terminal.

[1729] The terminal displays the received video to the user.

[1730] Example: A server sends a video file to a terminal using the HTTP protocol, and the terminal plays it on a video player.

[1731] 5. Practice suggestions

[1732] Based on the data learned by the server and the generative AI model, it calculates what kind of practice each player needs to do to achieve the tactics and formations.

[1733] The server analyzes each player's performance data and past match data.

[1734] Example: A server retrieves player performance data from a database and uses a generative AI model (e.g. GPT-4) to calculate the required skills and abilities.

[1735] 6. Presentation of practice methods

[1736] The server presents the calculated practice method to the user.

[1737] The practice method received by the terminal is displayed to the user.

[1738] Example: The server sends text data on how to practice to the terminal, and the terminal displays it.

[1739] Examples of prompt statements

[1740] "I want to strengthen my attacks from the sides in a 4-4-2 formation. Please simulate the movement of the players and the ball and generate a video showing how the ball will move to the goal."

[1741] "Please tell me what kind of practice each player should do to implement the tactics you have presented."

[1742] This system enables the user to visually confirm the effects of tactics and formations, and furthermore, to learn specific training methods. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1743] Step 1:

[1744] Tactical and formation input

[1745] Users use terminals to input tactics and formations into the system.

[1746] Input: The user enters "I want to strengthen attacks from the sides with a 4-4-2 formation" into the input form on the terminal and clicks the submit button.

[1747] Output: Tactical and formation data is sent to the server.

[1748] Specific operation: The user enters tactics and formations into the input form on the terminal and clicks the send button, which sends the data to the server.

[1749] Step 2:

[1750] Simulating Data

[1751] The server analyzes the tactical and formation data received from the user.

[1752] Input: Tactical and formation data.

[1753] Output: Initial setup data for the simulation.

[1754] How it works: The server analyzes tactical and formation data, models player positions and movements using 3D modeling software (e.g. Blender), then simulates player and ball movements using animation software (e.g. Autodesk Maya).

[1755] Step 3:

[1756] Video Generation

[1757] The server generates a visually-presented video based on the simulation results.

[1758] Input: Simulation result data.

[1759] Output: Image video file.

[1760] What happens: The server uses rendering software to convert the simulation results into a video file. The server starts the rendering process, producing a one-minute video of the images.

[1761] Step 4:

[1762] Video presentation

[1763] The video generated by the server is sent to the user's terminal.

[1764] Input: Image video file.

[1765] Output: The video displayed on the user's device.

[1766] Specific operation: The server sends a video file to the terminal using the HTTP protocol, and the terminal plays it on the video player.

[1767] Step 5:

[1768] Practice suggestions

[1769] Based on the data learned by the server and the generative AI model, it calculates what kind of practice each player needs to do to achieve the tactics and formations.

[1770] Input: Performance data and past match data for each player.

[1771] Output: Practice suggestions data.

[1772] How it works: The server retrieves player performance data from the database and uses a generative AI model (e.g. GPT-4) to calculate the required skills and abilities.

[1773] Step 6:

[1774] Presentation of practice methods

[1775] The server presents the calculated practice method to the user.

[1776] Input: Practice suggestion data.

[1777] Output: The exercise displayed on the user's device.

[1778] Specific operation: The server sends text data on how to practice to the terminal, and the terminal displays it.

[1779] (Application example 3)

[1780] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1781] Conventional tactical and formation presentation systems lacked the means to visually understand the movements of players and the ball, and the presentation of effective practice methods was limited. In addition, there was also a lack of means to visually understand efficient movement patterns in optimizing the movements of robots and work flows in factories. This made it difficult to understand tactics, improve the efficiency of practice, and improve production efficiency in factories.

[1782] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1783] In this invention, the server includes a means for learning the latest tactics, player data, and opponent data, a means for presenting the optimal tactics and formations to the team based on the learned data, a means for generating and presenting an image video to the goal based on the presented tactics and formations, a means for simulating the movements and work flows of robots in the factory and generating and presenting optimal movement patterns as videos, and a means for calculating what movements and work each robot should perform to efficiently produce and presenting specific movement procedures. This makes it possible to understand tactics, improve the efficiency of practice, and increase production efficiency in the factory.

[1784] "Cutting-edge tactics" are tactics developed based on the latest technology and data analysis.

[1785] "Player Data" refers to information relating to a player's performance or abilities.

[1786] "Opponent Data" refers to information regarding the opponent's tactics and performance.

[1787] "Learning tools" refers to the methods and techniques used to analyze data and find patterns and trends.

[1788] "Means for presenting tactics and formations" refers to a method for showing the user optimal tactics and formations based on the analyzed data.

[1789] "Means of generating and presenting image videos" refers to a method of running simulations based on tactics and formations and showing the results to users as videos.

[1790] "Means of simulating robot movements and work flows within a factory" refers to a method of virtually reproducing the movements of robots and work procedures within a factory.

[1791] "Means of generating and presenting optimal movement patterns as videos" refers to a method of showing efficient movement patterns to users in video format based on simulation results.

[1792] "Means for presenting specific operating procedures" refers to a method for showing the user detailed procedures for the robot to perform a task efficiently.

[1793] "Past Match Data" refers to information relating to the results and tactics of previously played matches.

[1794] "Player Performance Data" refers to information regarding a player's performance in past matches and training sessions.

[1795] "Opponent tactical data" refers to information regarding tactics and formations used by an opponent in the past.

[1796] "Factory work flow data" refers to information about work procedures and processes within a factory.

[1797] "Robot operation data" refers to information related to the robot's movements and work.

[1798] The sy...

Claims

1. A learning means for learning tactics in past matches, data on players who participated in the matches, and past opponents by inputting a specific prompt sentence into the generating AI model and using a machine learning model; A means for presenting tactics and formations of teams participating in the match based on the learned data using a generative AI model; A means for generating a visual simulation video based on the presented tactics and formations, and presenting the generated simulation video to a user; A means for recognizing an emotion of a user to whom the simulation video is presented; A means for adjusting the machine learning model based on the results of the recognition. A system including:

2. The system according to claim 1 , further comprising means for presenting a practice method for realizing the tactics and formations.

3. 2. The system according to claim 1, wherein the learning means learns the performance of the player in addition to tactics in past matches, data of players who participated in the matches, and past opponents.

Images