System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting player performance and score data; means for analyzing the collected data and generating a predictive model; and means for using the generated predictive model to predict new data and suggest strategies.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern sports organizations, efficient and accurate data analysis is essential to improving the performance of players and teams. However, it is difficult to achieve sufficient accuracy and efficiency using current manual data collection and existing analysis tools. Furthermore, many challenges exist regarding how to effectively link collected data to strategy planning and training plans. The present invention aims to solve these challenges and provide a system for achieving highly accurate data-based strategy planning, training, and scouting. [Means for solving the problem]

[0005] The system of the present invention includes a means for collecting data on players' game appearances and points scored, a means for analyzing the collected data and generating a prediction model, and a means for predicting new data and proposing strategies using the generated prediction model. This system enables efficient and accurate data collection and analysis, and proposes strategies based on the results. Furthermore, by including a means for standardizing data as a preprocessing step and a means for saving the collected data in Pandas DataFrame format, further improvements in accuracy and efficiency can be achieved.

[0006] "Athlete" refers to an individual athlete participating in a competition.

[0007] "Match Appearances" refers to the number of matches a player takes part in within a specific period of time.

[0008] "Scoring Data" refers to the record of the points scored by a player during a game.

[0009] "Collection methods" refers to the technologies and methods used to collect and store specific data.

[0010] "Analytical means" refers to the techniques and methods used to process collected data and derive useful information and insights.

[0011] A "predictive model" refers to a mathematical model that predicts future data based on collected data.

[0012] "Strategy suggestion tools" refers to techniques or methods for suggesting specific courses of action or strategies based on the results of a predictive model.

[0013] "Efficiency" refers to achieving maximum results with minimal time and resources.

[0014] "Accurate" refers to data or processing results that are extremely close to actual values ​​or facts.

[0015] "Standardization" refers to the process of aligning the range and scale of data to make it easier to compare.

[0016] A "Pandas DataFrame" refers to a two-dimensional data structure used in the Python programming language that makes it easy to manipulate and analyze labeled data. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] The present invention relates to a system for collecting data on the number of matches played and the number of points scored by players, and for analyzing, predicting, and proposing such data.

[0039] Data collection and storage

[0040] The server instantiates the DataCollector class and calls the collect_data method to collect player data. The collected data includes the number of matches played and points scored by each player. This data is saved in Pandas DataFrame format, making it easy to analyze later.

[0041] Data analysis

[0042] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. This analysis process first uses StandardScaler to standardize data such as game appearances, reducing data variability. It then uses a linear regression model to generate a score prediction model. This prediction model is used to predict future scores based on a player's past performance data.

[0043] Strategic proposal

[0044] The server then instantiates the StrategySuggester class and suggests a strategy using the new data. This new data could be, for example, new players or game appearances based on the upcoming game schedule. The server uses the prediction model to predict the score for the new data and suggests a strategy based on the prediction. If the score is high, the server suggests an "offensive strategy," and if the score is low, the server suggests a "defensive strategy."

[0045] Specific examples

[0046] For example, suppose a user inputs player data for 2023 into the system (15, 10, and 5 game appearances, with 300, 210, and 50 points, respectively). This data is collected by the server and used as the base data for generating a prediction model. Next, if the number of game appearances for a new member is input (e.g., 9 and 7 games), the server accepts this as new data and calculates the predicted points. For example, if the predicted points are 180 for 9 game appearances and 140 for 7 game appearances, the server will suggest a "defense-focused strategy" for each.

[0047] The terminal displays the results of these strategy proposals to the user, who can then use this information to plan specific training and match strategies for their players.

[0048] In this way, the system of the present invention efficiently and accurately collects and analyzes player appearance and score data, generates predictive models, and proposes strategies based on them, thereby significantly improving the performance of sports teams.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of points scored by each player. Specifically, temporary data is generated and saved in the Pandas DataFrame format.

[0052] Step 2:

[0053] The server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. At this stage, as a data preprocessing step, it uses StandardScaler to standardize the appearance data. Then, it uses the standardized data to generate a linear regression model to predict points.

[0054] Step 3:

[0055] The server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on new data, such as the number of games played by a new player. The server inputs this new data into the prediction model and predicts the score.

[0056] Step 4:

[0057] The server proposes a strategy based on the predicted score. Specifically, if the predicted score is high, it proposes an "offense-oriented strategy," and if the predicted score is low, it proposes a "defense-oriented strategy."

[0058] Step 5:

[0059] The terminal displays the strategy proposals provided by the server to the user, who can then use them to plan specific training and match strategies for the players.

[0060] Through this process, the system can efficiently and accurately collect and analyze data, create predictive models, and propose strategies based on them, thereby contributing to improving the performance of sports organizations.

[0061] Example 1

[0062] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0063] This invention relates to a system that collects information on players' game appearances and scores, predicts their future performance based on this information, and proposes effective strategies. Conventional systems require manual data collection and analysis, which is inefficient and has limited accuracy. This makes it difficult to quickly develop effective strategies that can contribute to improving the performance of sports teams.

[0064] 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.

[0065] In this invention, the server includes a means for collecting information on the number of games played and the scores of players, a means for analyzing the collected information and generating a prediction model, and a means for predicting new information using the generated prediction model and proposing a strategy, thereby enabling the rapid and accurate collection and analysis of player performance information, the generation of a prediction model, and the proposing of an effective strategy.

[0066] "Athlete" means an individual or team member who takes part in a competition or sporting event.

[0067] "Appearances" is the number of matches or competitions an athlete takes part in within a specific period of time.

[0068] "Score information" refers to data on the points and scores that a player has earned in a match or competition.

[0069] "Means of collecting information" refers to the technical means by which servers and devices obtain information on the number of competitions and scores through APIs, databases, etc.

[0070] "Means for analyzing information" are technical means for processing collected data and identifying characteristics and trends.

[0071] The "means for generating a predictive model" refers to a means for creating a mathematical model for predicting future performance from past data using a machine learning algorithm.

[0072] "New information" refers to newly added data or circumstances that are not based on existing data.

[0073] "Means for proposing strategies" are technical means for formulating competition and training plans based on the results of the predictive model.

[0074] The "data frame format" is a tabular data structure consisting of rows and columns, and is a format that is particularly used when using the Pandas library.

[0075] "Standardization methods" are technical methods for adjusting data to reduce variability and make the mean zero and the standard deviation one.

[0076] This invention relates to a system that collects information on the number of matches played and the number of points scored by players, analyzes the data, generates a prediction model, and proposes strategies. This system is realized by a server, a terminal, and a user, each playing their own role.

[0077] Data collection and storage

[0078] To collect information on the number of matches played and the number of points scored by each player, the server instantiates a specific class (DataCollector class) and calls a specific method (collector_data method). Specifically, the server obtains the number of matches played and the number of points scored by each player from an API or database, and stores this information in Pandas DataFrame format. Pandas is a powerful Python data manipulation library and is an ideal data storage format.

[0079] Data analysis

[0080] The server then instantiates another class (DataAnalyzer class) and uses a specific method (analyze_data method) to analyze the collected information. This process begins by standardizing the data using StandardScaler. StandardScaler is a tool included in the scikit-learn library that converts the mean to 0 and the standard deviation to 1 to reduce data variability. This makes the data scale uniform, improving the accuracy of the predictive model.

[0081] Model Generation and Prediction

[0082] The server then generates a linear regression model to predict future scores based on a player's past performance data. The linear regression model is also implemented using the scikit-learn library. Based on the trained model, future scores are predicted when new data (such as the number of games played by a new player) is input. This allows sports organizations to develop strategies based on the predicted scores.

[0083] Strategic proposal

[0084] Next, the server instantiates the StrategySuggester class and suggests a strategy using the new data. This new data includes new players and the number of appearances based on the upcoming game schedule. The server uses the generated prediction model to predict the score for the new data and suggests a strategy based on the prediction results. If the score is high, it suggests an "offensive strategy," and if the score is low, it suggests a "defensive strategy."

[0085] Results display

[0086] The terminal displays the results of these strategy proposals to the user. Based on this information, the user can plan specific strategies for player training and matches. The terminal displays the results of the strategy proposals on the screen and provides them to the user by printing them out as needed.

[0087] Specific examples

[0088] For example, suppose a user inputs player data for 2023 into the system (15, 10, and 5 game appearances, with 300, 210, and 50 points, respectively). This data is collected by the server and becomes the base data for generating a prediction model. When the number of game appearances for a new member is input (e.g., 9 and 7 games), the server accepts this as new data and calculates the predicted points. For example, if the predicted points are 180 for 9 game appearances and 140 for 7 game appearances, a "defense-focused strategy" will be suggested for each.

[0089] Example prompt sentence:

[0090] "Based on the following data, please calculate the expected points for the new members based on the number of games they play and propose a strategy:

[0091] 2023 Player Data:

[0092] Matches played: 15, 10, 5

[0093] Points: 300, 210, 50

[0094] Number of matches played by new members:

[0095] 9 matches

[0096] Seven games.”

[0097] In this way, the system of the present invention can significantly improve the performance of sports teams by efficiently and accurately collecting and analyzing information on players' game appearances and points scored, generating predictive models, and proposing strategies based on those models.

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1: Data collection

[0100] The server instantiates the DataCollector class and calls the collect_data method. This method retrieves information about players' appearances and points from an API or database. For example, it retrieves data in JSON format from the API and extracts information about each player. Specifically, it collects information such as Player A's appearance in 15 games and his score of 300. The input is player data retrieved from the API endpoint, and the output is data in Pandas DataFrame format.

[0101] Step 2: Save data

[0102] The server saves the collected data in Pandas DataFrame format. The DataFrame format makes it easy to manipulate and analyze data. Specifically, it converts JSON data into a Pandas DataFrame and saves the number of matches played and points scored by each player in tabular format. The input is the data collected in Step 1, and the output is data in DataFrame format.

[0103] Step 3: Data Preprocessing

[0104] The server instantiates the DataAnalyzer class and preprocesses the data using the analyze_data method. In this process, the data is standardized using StandardScaler. The input is data in DataFrame format, and the output is the standardized data. Specifically, the variance of the number of games played and points scored is reduced, and the mean is converted to 0 and the standard deviation to 1.

[0105] Step 4: Model generation

[0106] The server generates a linear regression model. The input is the preprocessed data from step 3, and the output is a predictive model. Specifically, the scikit-learn library is used to train a predictive model based on past performance data. This model predicts points scored using the number of matches played as input.

[0107] Step 5: Predict

[0108] The server uses new data to make predictions. For example, it takes the number of games played by a new member as input and uses a prediction model to calculate future points. The input is new game play data, and the output is the predicted points. Specifically, it predicts 180 points in 9 games played, and 140 points in 7 games played.

[0109] Step 6: Strategic proposal

[0110] The server instantiates the StrategySuggester class and proposes a strategy based on the prediction results. The input is the score data predicted in step 5, and the output is the proposed strategy. Specifically, if the score is high, an "offensive strategy" is proposed, and if the score is low, a "defensive strategy" is proposed. For example, if the number of games played is 9, a defensive strategy is proposed.

[0111] Step 7: View the results

[0112] The terminal displays the results of the strategy proposal to the user. The input is the strategy proposed in step 6, and the output is the strategy information displayed to the user. Specifically, the server displays the strategy proposed by the server on the competition screen or training plan screen. The user uses this information to plan strategies for actual training or matches.

[0113] (Application example 1)

[0114] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0115] To efficiently improve the performance of robots used in factories, a system is needed that collects robot work data, analyzes it, and proposes optimal work strategies. However, current systems lack the ability to standardize data or generate appropriate predictive models, making it difficult to propose effective strategies.

[0116] 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.

[0117] In this invention, the server includes means for collecting robot task data and efficiency data, means for analyzing the collected data and generating a prediction model, and means for predicting new data using the generated prediction model and proposing a task strategy, thereby making it possible to propose an optimal task strategy for efficiently improving the robot's performance.

[0118] "Robot work data" is information about a series of tasks performed by a robot in a factory, and specifically includes numerical data such as how many times the robot performed each task.

[0119] "Efficiency data" is information that indicates the ratio of the results obtained to the time and resource usage of the work performed by the robot, and specifically includes the productivity and success rate per task.

[0120] The "collection means" is a combination of hardware and software for acquiring work data and efficiency data from each robot, and includes sensors and data collection programs.

[0121] "Means of analysis" refers to algorithms and programs used to analyze collected data, and to standardize data and recognize patterns.

[0122] A "means for generating a predictive model" is a mathematical and computational method for predicting future efficiency or performance based on past data, such as using a linear regression model.

[0123] The "means for proposing a work strategy" refers to a means for showing an optimal work plan based on the generated predictive model, and includes visualization tools and recommendation systems.

[0124] "Standardization means" refers to algorithms and programs that reduce data variability and convert data into a comparable form, such as StandardScaler.

[0125] "Means of saving in Pandas DataFrame format" refers to a method of storing collected data in a DataFrame object of the Pandas library, which facilitates subsequent data processing and analysis.

[0126] The present invention relates to a system that collects and analyzes work data and efficiency data of robots in a factory to propose optimal work strategies. This system provides a means for efficiently improving the performance of robots.

[0127] Data collection and storage

[0128] The server instantiates the DataCollector class and calls the collect_data method to collect robot work data and efficiency data. The collected data is saved in Pandas DataFrame format. Examples of data include the robot ID, number of tasks, and efficiency information. For example, data is collected where the robot ID is 1, the number of tasks is 10, and the efficiency is 90.

[0129] Data analysis

[0130] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. In this analysis process, it first uses StandardScaler to standardize the data. StandardScaler is used to reduce data variability. Then, it uses a linear regression model to generate an efficiency prediction model. This prediction model is used to predict future efficiency based on past work data.

[0131] Work strategy proposal

[0132] The server then instantiates the StrategySuggester class and proposes a work strategy using the new data. This new data could be, for example, the number of tasks performed by a new robot. The server uses the prediction model to predict the efficiency of the new data and proposes a work strategy based on the prediction results. If the efficiency is high, the server proposes a "high-efficiency work strategy," and if the efficiency is low, the server proposes an "improvement suggestion strategy."

[0133] Examples of specific examples and prompts

[0134] For example, suppose a user inputs new robot data (robot ID: 4, number of tasks: 8) into the system. This data is collected by the server and used as the base data for generating a prediction model. The server then receives this as new data and calculates the prediction efficiency. If the prediction efficiency is 70, the server will propose an "improvement proposal strategy." This information is useful for formulating specific work strategies for subsequent tasks.

[0135] An example of a prompt is as follows:

[0136] Predict the efficiency of robots IDs 4 and 5 in a factory when they process 8 and 12 tasks, respectively, and propose an optimal work strategy based on that.

[0137] In this way, the system of the present invention efficiently and accurately analyzes collected work data and efficiency data, generates a predictive model, and proposes an optimal work strategy based on the model, thereby improving the performance of robots in factories and increasing production efficiency.

[0138] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0139] Step 1:

[0140] The server instantiates the DataCollector class and calls the collect_data method. This collects robot work data and efficiency data. Specifically, information on each robot's ID, number of tasks, and efficiency is collected. For example, data such as robot ID 1, number of tasks 10, and efficiency 90 can be obtained. The collected data is saved in Pandas DataFrame format.

[0141] Step 2:

[0142] The server analyzes the collected data using an instance of the DataAnalyzer class. Specifically, it calls the analyze_data method to standardize the data. StandardScaler is used for standardization, and scaling is performed to reduce data variation. The collected data is given as input, and standardized data is obtained as output.

[0143] Step 3:

[0144] The server uses the standardized data to generate a predictive model. Specifically, it uses a linear regression model to build a model for predicting future efficiency based on past data. The analyzed data is divided into X and y, and a model is generated using LinearRegression. The input is the standardized data, and the output is a linear regression model for predicting efficiency.

[0145] Step 4:

[0146] The server uses an instance of the StrategySuggester class to suggest a work strategy for new data. Specifically, it calls the suggest_strategy method of the strategy_suggester instance, inputs the work data of a new robot, and predicts its efficiency. For example, if the new robot ID is 4 and the number of tasks is 8, its efficiency is predicted using the model, and the predicted efficiency is 70. The predicted efficiency is obtained as the output.

[0147] Step 5:

[0148] Based on the provided predicted efficiency, the server proposes an optimal work strategy. If the efficiency is high, it proposes a "high-efficiency work strategy," and if it is low, it proposes an "improvement proposal strategy." For example, if the efficiency is 70, it proposes the "improvement proposal strategy." This proposal information is sent to the terminal, and the user can use it to plan a specific work strategy.

[0149] An example of a prompt is as follows:

[0150] Predict the efficiency of robots IDs 4 and 5 in a factory when they process 8 and 12 tasks, respectively, and propose an optimal work strategy based on that.

[0151] In this way, a system is created to improve the performance of robots in a factory.

[0152] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0153] This invention relates to a system that collects data on the number of matches played and the number of points scored by players, and analyzes, predicts, and proposes strategies by combining this with an emotion engine that recognizes the emotions of the user, thereby making more appropriate strategy proposals.

[0154] Data collection and storage

[0155] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of goals scored by each player. This data is saved in a Pandas DataFrame format, making it easy to analyze later.

[0156] Data analysis

[0157] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. During the analysis process, a StandardScaler is used to standardize the appearance data. A linear regression model is then used to generate a score prediction model. The prediction model is used to predict future scores based on a player's past performance data.

[0158] Strategy suggestions and emotion recognition

[0159] Next, the server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on the new data. Here, an emotion engine is added to recognize user emotions and collect emotion data, for example, when a user expresses dissatisfaction with a proposed strategy.

[0160] The server adjusts the strategy by taking into account the user's emotional data collected using the emotion engine. Specifically, the emotional data is reflected in the prediction model to propose a strategy that will satisfy the user. For example, if the user is dissatisfied with the proposed tactics, the server may adjust the strategy to one that emphasizes more defense.

[0161] Specific examples

[0162] For example, if a user inputs player data into the system (number of games played: 15, 10, 5, with points scored of 300, 210, 50, respectively), this data is collected by the server and used as the base data for generating a prediction model. If a user then inputs the number of games played by a new member (e.g., 9 games, 7 games), the server will accept this as new data and calculate the predicted points.

[0163] The server also uses an emotion engine to collect the user's emotional data (happiness, dissatisfaction, etc.). For example, if the predicted score is 180 and an "attack-focused tactic" is suggested, and the user expresses dissatisfaction with the suggestion, the emotion engine will feed that information back to the server. The server will then readjust the prediction model based on the emotional data and suggest a strategy that suits the user's emotions, such as switching to a "defense-focused tactic."

[0164] The terminal displays the final strategy proposal to the user, who can then use it to plan specific strategies for training players and matches.

[0165] In this way, by combining the emotion engine, it is possible to realize more flexible and effective strategy proposals that are not based solely on data but also take into account the user's emotions, which can greatly contribute to improving the performance of sports organizations.

[0166] The processing flow will be explained below.

[0167] Step 1:

[0168] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of goals scored by each player. This data is saved in a Pandas DataFrame format, making it easy to analyze later.

[0169] Step 2:

[0170] The server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. At this stage, as a data preprocessing step, it uses StandardScaler to standardize the appearance data. Then, it builds a linear regression model using the standardized data to generate a model to predict points.

[0171] Step 3:

[0172] The server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on new data, such as the number of games played by a new member. The server inputs this new data into the prediction model and predicts the score.

[0173] Step 4:

[0174] The server instantiates an emotion engine to collect the user's emotion data. Specifically, the engine recognizes the user's emotion toward the strategy proposal (e.g., joy, dissatisfaction, etc.) and transmits the data to the server.

[0175] Step 5:

[0176] The server readjusts the strategy proposals based on the user's emotional data provided by the emotion engine. For example, if the predicted score is 180 and an "attack-focused strategy" is proposed, and the user expresses dissatisfaction, the server will readjust the prediction model based on that information and propose a "defense-focused strategy" instead.

[0177] Step 6:

[0178] The terminal displays the final strategy proposal to the user, who can then use the proposal to plan specific training and match strategies for the players.

[0179] In this way, by combining the emotion engine, it becomes possible to propose more flexible and effective strategies that are not only based on data but also take into account the emotions of the user, which will greatly contribute to improving the performance of sports organizations.

[0180] Example 2

[0181] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0182] Conventional player performance analysis systems are limited to collecting and analyzing data on the number of matches played and points scored, and have the problem of being unable to propose appropriate strategies that take the user's emotions into account. As a result, users may be dissatisfied with the proposed strategies, and optimal performance improvements may not be achieved.

[0183] 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.

[0184] In this invention, the server includes means for collecting data on the number of matches played and the number of points scored by players, means for analyzing the collected data and generating a prediction model, means for predicting new data using the generated prediction model and proposing a strategy, and means for recognizing the user's emotions and adjusting the strategy based on the emotion data, thereby enabling more appropriate strategy proposals that are based not only on data but also on the user's emotions.

[0185] "Player appearances" refers to the number of times a player has appeared in an official match.

[0186] "Score Data" refers to information regarding the scores scored by a player during a match.

[0187] "Collection means" refers to the technological devices or functions used to capture and store information such as player appearances and goalscoring data.

[0188] "Analyzing means" refers to the technical devices or capabilities used to analyze collected data and extract useful information or patterns.

[0189] "Predictive Model" means a mathematical or statistical model used to forecast future events or outcomes based on data collected in the past.

[0190] "Means for proposing strategies" refers to a technical device or function for proposing methods of competition or training based on the results of a predictive model.

[0191] "Means for recognizing user emotions" refers to a technical device or function for detecting the user's emotional state (happiness, dissatisfaction, etc.) and capturing it as data.

[0192] "Emotion data" refers to data that expresses the user's emotional state as numerical values ​​or categories.

[0193] "Means for adjusting strategy based on emotional data" refers to a technical device or function that takes into account the collected emotional data of users, recalculates the optimal strategy, and adjusts the content of suggestions.

[0194] "Standardization means" refers to a technical device or function that equalizes data variability and makes data on different scales comparable.

[0195] "Tabular" refers to data arranged in a regular pattern of rows and columns.

[0196] "Storage means" refers to technical devices or functions that record and store collected or generated data in a form that can be accessed at a later date.

[0197] This invention relates to a system that collects data on the number of matches played and the number of points scored by players, analyzes and predicts the results, and proposes strategies that take into account the user's emotions. This system is realized through processing between a server, a terminal, and a user.

[0198] The server first instantiates the DataCollector class and uses the collect_data method to collect data on players' appearances and goals. This data is then saved in Pandas DataFrame format using Pandas, a Python data analysis library. This makes it easier to manage the data and perform subsequent analysis.

[0199] The server then instantiates the DataAnalyzer class and analyzes the data using the analyze_data method. Specifically, it uses StandardScaler to standardize the appearance data and then uses a linear regression model to generate a model for predicting points. The model is used to predict future points based on a player's past performance data.

[0200] The server then instantiates the StrategySuggester class and uses the suggest_strategy method to propose a strategy based on the new data. At this stage, an emotion engine is added to recognize the user's emotions. Specifically, if the user expresses dissatisfaction with the proposed strategy, the emotion data is collected. The server then adjusts the strategy based on the emotion data and makes a proposal that satisfies the user.

[0201] For example, suppose a user inputs the following player data into the system: number of matches played: 15, 10, 5, with respective scores of 300, 210, 50. This data is collected by the server and becomes the basis for the prediction model. If a new member later inputs the number of matches played (e.g., 9 matches, 7 matches), the server will accept this as new data and calculate the predicted score. At this time, the emotion engine will collect the user's emotional data (e.g., dissatisfaction), and the server will readjust the strategy based on that data. For example, if an "attack-focused tactic" is proposed but the user expresses dissatisfaction, the server may switch to a "defense-focused tactic" based on the emotional data.

[0202] The terminal displays the final strategy proposal sent from the server to the user, who can then use it to plan specific training and match strategies for the players.

[0203] Examples of prompts include:

[0204] Enter player data:

[0205] Matches played: 15, 10, 5

[0206] Points: 300, 210, 50

[0207] Number of games played by new members: 9, 7

[0208] Emotional data: Dissatisfaction

[0209] Based on this prompt, the server can collect, analyze, and predict data, and adjust strategies based on emotional data, and then suggest the optimal strategy to the user.

[0210] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0211] Processing Step Description

[0212] Step 1:

[0213] The server instantiates the DataCollector class. As input, it receives the number of matches played and the number of points scored by each player. Specifically, it retrieves the data from an API or database and saves it in Pandas DataFrame format. This allows the data to be managed in a unified format. The output is data in Pandas DataFrame format.

[0214] Step 2:

[0215] The server instantiates the DataAnalyzer class. The input is the Pandas DataFrame data collected in step 1. The server uses the analyze_data method to first standardize the appearance data using StandardScaler. It then creates a linear regression model and generates a predictive model based on this model. The output is the predictive model.

[0216] Step 3:

[0217] The server instantiates the StrategySuggester class. The input is the prediction model generated in step 2. The server uses the suggest_strategy method to receive new player data as input, calculate predicted scores, and propose a strategy. Specifically, it inputs normalized game appearance data into the prediction model to predict scores. The output is the predicted strategy suggestion.

[0218] Step 4:

[0219] The user provides feedback on the proposed strategy by clicking a button indicating their level of satisfaction (e.g., happy, dissatisfied) with the proposed strategy. The input is the user's emotional data.

[0220] Step 5:

[0221] The server uses an emotion engine to collect user emotion data. The input is the user emotion data collected in step 4. The server readjusts the strategy based on this data. Specifically, it analyzes the emotion data and modifies the strategy if there is a high level of dissatisfaction. The output is a proposed adjusted strategy.

[0222] Step 6:

[0223] The terminal displays the final strategy proposal to the user. The input is the strategy proposal adjusted in step 5. The terminal presents the proposal to the user in an easy-to-understand format, allowing the user to take concrete action. The output is the strategy proposal displayed on the screen.

[0224] Through these steps, the system can collect and analyze player performance data, generate predictive models, and even suggest strategies that take the user's emotions into account.

[0225] (Application example 2)

[0226] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0227] Autonomous vehicles are required to recognize the driver's emotional state and provide an optimal driving strategy based on that. Such a system would contribute to reducing driver stress and promoting safe driving. However, conventional navigation systems have the problem of being unable to propose driving strategies that take the driver's emotional state into account and can only provide uniform route guidance.

[0228] 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.

[0229] In this invention, the server includes means for collecting data on the number of games played and the scores of players, means for analyzing the collected data and generating a prediction model, means for predicting new data using the generated prediction model and proposing a strategy, means for collecting and analyzing a user's emotions, and means for adjusting and proposing a strategy using the user's emotion data, thereby enabling the proposal of a driving strategy that takes into account the driver's emotional state.

[0230] "Player Appearances" refers to the total number of matches a player participates in during a particular period.

[0231] "Score data" refers to numerical information about the points scored by a player in a match.

[0232] "Collection Means" refers to the technical capabilities and methods used to capture and record player appearance and goal data.

[0233] "Means for analyzing and generating predictive models" refers to the technological capabilities and methods for analyzing collected data and creating mathematical and statistical models based on that data to predict future performance.

[0234] "Means for proposing strategies" refers to the technical capabilities and methods for evaluating new data and recommending optimal plans of action or courses of action based on the generated predictive models.

[0235] "Means for collecting and analyzing user emotions" refers to technical functions and methods for detecting and analyzing the emotional state of a user from their facial expressions and voice.

[0236] "Means for adjusting and proposing strategies using emotional data" refers to technical functions and methods for taking into account the emotional data of a user and selecting and proposing an optimal strategy.

[0237] "Standardization measures" refer to technical features or methods for converting collected data values ​​onto a consistent scale.

[0238] "Means for storing data in a data frame format" refers to the technical features and methods for storing collected data in a tabular format consisting of rows and columns.

[0239] This invention relates to a system that recognizes the driver's emotional state in real time and adjusts and proposes driving strategies based on that. This system is based on the collection and analysis of players' game appearances and score data, and analyzes and reflects the user's emotional data in real time to optimize navigation strategies while actually driving.

[0240] 1. Data Collection

[0241] The server collects the driver's facial expressions and tone of voice via the device's built-in camera and microphone. Specifically, it analyzes the facial expression data captured by the camera and the voice data collected by the microphone using an emotion recognition model. The emotion recognition model uses a model based on deep learning technology (such as TensorFlow or Keras).

[0242] 2. Data analysis

[0243] The server stores the collected emotion data in a data frame format (Pandas DataFrame). The emotion data is standardized (StandardScaler) to ensure consistency and then analyzed using a linear regression model (LinearRegression). This generates a predictive model based on the driver's emotional state.

[0244] 3. Strategy proposal and emotion recognition

[0245] The server uses an emotion prediction model to suggest a driving strategy that matches the driver's emotional state. Specifically, if the driver is stressed, the server suggests the shortest route, and if the driver is relaxed, it suggests a scenic route. This information is displayed on the device (smartphone or head-mounted display) and provided to the driver.

[0246] Specific examples

[0247] For example, if the system determines that the driver is stressed, the device will display "Suggest the shortest route." On the other hand, if the system determines that the driver is relaxed, it will display "Suggest the scenic route." This allows the driver to select the optimal driving route based on their emotional state.

[0248] Example prompts for generative AI models

[0249] "We need an app that suggests routes that help you relax while driving. It should recognize your emotions and suggest the best driving route based on them."

[0250] "Create a navigation system that suggests the shortest route when the driver is stressed, or a scenic route when the driver is relaxed."

[0251] The above is an embodiment of the invention, which makes it possible to propose a driving strategy that takes into account the emotional state of the driver.

[0252] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0253] Step 1:

[0254] The server collects the driver's facial expressions and tone of voice in real time through the camera and microphone built into the device. The input here is the camera video and audio data, and the output is that these data are sent to the server. The camera captures the driver's face, and the microphone picks up the audio.

[0255] Step 2:

[0256] The server inputs the collected facial and voice data into an emotion recognition model to analyze the driver's emotional state. The input here is the captured facial and voice data, and the output is the analysis result (emotional state) by the emotion recognition model. Deep learning libraries such as TensorFlow and Keras are used to evaluate emotions.

[0257] Step 3:

[0258] The server saves the parsed emotion data in Pandas DataFrame format. Here, the input is emotion data and the output is saved in DataFrame format. The Pandas library is used to structure the data to facilitate later analysis.

[0259] Step 4:

[0260] The server normalizes the stored data using StandardScaler. The input here is the emotion data stored in a data frame, and the output is the normalized data. StandardScaler is used to unify the scale of the data.

[0261] Step 5:

[0262] The server trains a linear regression model using the normalized data to generate a predictive model. Here, the input is the normalized data, and the output is a predictive model based on the driver's emotions. LinearRegression is used to build the predictive model.

[0263] Step 6:

[0264] The server uses the generated predictive model to predict the driver's emotional state and proposes a driving strategy based on it. The input here is the current emotional data, and the output is the optimal driving strategy. If the driver is relaxed, it will suggest a scenic route, and if the driver is stressed, it will suggest the shortest route.

[0265] Step 7:

[0266] The device displays the proposed driving strategy to the user, where the input is the driving strategy information sent from the server and the output is the displayed route proposal. The information is provided visually on the device's display or head-mounted display.

[0267] Through these steps, an optimal driving strategy that reflects the driver's emotional state is proposed.

[0268] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0269] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0270] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0271] [Second embodiment]

[0272] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0273] 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.

[0274] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0275] 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.

[0276] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0277] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0278] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0279] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0280] 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.

[0281] 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.

[0282] 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.

[0283] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0284] The present invention relates to a system for collecting data on the number of matches played and the number of points scored by players, and for analyzing, predicting, and proposing such data.

[0285] Data collection and storage

[0286] The server instantiates the DataCollector class and calls the collect_data method to collect player data. The collected data includes the number of matches played and points scored by each player. This data is saved in Pandas DataFrame format, making it easy to analyze later.

[0287] Data analysis

[0288] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. This analysis process first uses StandardScaler to standardize data such as game appearances, reducing data variability. It then uses a linear regression model to generate a score prediction model. This prediction model is used to predict future scores based on a player's past performance data.

[0289] Strategic proposal

[0290] The server then instantiates the StrategySuggester class and suggests a strategy using the new data. This new data could be, for example, new players or game appearances based on the upcoming game schedule. The server uses the prediction model to predict the score for the new data and suggests a strategy based on the prediction. If the score is high, the server suggests an "offensive strategy," and if the score is low, the server suggests a "defensive strategy."

[0291] Specific examples

[0292] For example, suppose a user inputs player data for 2023 into the system (15, 10, and 5 game appearances, with 300, 210, and 50 points, respectively). This data is collected by the server and used as the base data for generating a prediction model. Next, if the number of game appearances for a new member is input (e.g., 9 and 7 games), the server accepts this as new data and calculates the predicted points. For example, if the predicted points are 180 for 9 game appearances and 140 for 7 game appearances, the server will suggest a "defense-focused strategy" for each.

[0293] The terminal displays the results of these strategy proposals to the user, who can then use this information to plan specific training and match strategies for their players.

[0294] In this way, the system of the present invention efficiently and accurately collects and analyzes player appearance and score data, generates predictive models, and proposes strategies based on them, thereby significantly improving the performance of sports teams.

[0295] The processing flow will be explained below.

[0296] Step 1:

[0297] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of points scored by each player. Specifically, temporary data is generated and saved in the Pandas DataFrame format.

[0298] Step 2:

[0299] The server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. At this stage, as a data preprocessing step, it uses StandardScaler to standardize the appearance data. Then, it uses the standardized data to generate a linear regression model to predict points.

[0300] Step 3:

[0301] The server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on new data, such as the number of games played by a new player. The server inputs this new data into the prediction model and predicts the score.

[0302] Step 4:

[0303] The server proposes a strategy based on the predicted score. Specifically, if the predicted score is high, it proposes an "offense-oriented strategy," and if the predicted score is low, it proposes a "defense-oriented strategy."

[0304] Step 5:

[0305] The terminal displays the strategy proposals provided by the server to the user, who can then use them to plan specific training and match strategies for the players.

[0306] Through this process, the system can efficiently and accurately collect and analyze data, create predictive models, and propose strategies based on them, thereby contributing to improving the performance of sports organizations.

[0307] Example 1

[0308] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0309] This invention relates to a system that collects information on players' game appearances and scores, predicts their future performance based on this information, and proposes effective strategies. Conventional systems require manual data collection and analysis, which is inefficient and has limited accuracy. This makes it difficult to quickly develop effective strategies that can contribute to improving the performance of sports teams.

[0310] 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.

[0311] In this invention, the server includes a means for collecting information on the number of games played and the scores of players, a means for analyzing the collected information and generating a prediction model, and a means for predicting new information using the generated prediction model and proposing a strategy, thereby enabling the rapid and accurate collection and analysis of player performance information, the generation of a prediction model, and the proposing of an effective strategy.

[0312] "Athlete" means an individual or team member who takes part in a competition or sporting event.

[0313] "Appearances" is the number of matches or competitions an athlete takes part in within a specific period of time.

[0314] "Score information" refers to data on the points and scores that a player has earned in a match or competition.

[0315] "Means of collecting information" refers to the technical means by which servers and devices obtain information on the number of competitions and scores through APIs, databases, etc.

[0316] "Means for analyzing information" are technical means for processing collected data and identifying characteristics and trends.

[0317] The "means for generating a predictive model" refers to a means for creating a mathematical model for predicting future performance from past data using a machine learning algorithm.

[0318] "New information" refers to newly added data or circumstances that are not based on existing data.

[0319] "Means for proposing strategies" are technical means for formulating competition and training plans based on the results of the predictive model.

[0320] The "data frame format" is a tabular data structure consisting of rows and columns, and is a format that is particularly used when using the Pandas library.

[0321] "Standardization methods" are technical methods for adjusting data to reduce variability and make the mean zero and the standard deviation one.

[0322] This invention relates to a system that collects information on the number of matches played and the number of points scored by players, analyzes the data, generates a prediction model, and proposes strategies. This system is realized by a server, a terminal, and a user, each playing their own role.

[0323] Data collection and storage

[0324] To collect information on the number of matches played and the number of points scored by each player, the server instantiates a specific class (DataCollector class) and calls a specific method (collector_data method). Specifically, the server obtains the number of matches played and the number of points scored by each player from an API or database, and stores this information in Pandas DataFrame format. Pandas is a powerful Python data manipulation library and is an ideal data storage format.

[0325] Data analysis

[0326] The server then instantiates another class (DataAnalyzer class) and uses a specific method (analyze_data method) to analyze the collected information. This process begins by standardizing the data using StandardScaler. StandardScaler is a tool included in the scikit-learn library that converts the mean to 0 and the standard deviation to 1 to reduce data variability. This makes the data scale uniform, improving the accuracy of the predictive model.

[0327] Model Generation and Prediction

[0328] The server then generates a linear regression model to predict future scores based on a player's past performance data. The linear regression model is also implemented using the scikit-learn library. Based on the trained model, future scores are predicted when new data (such as the number of games played by a new player) is input. This allows sports organizations to develop strategies based on the predicted scores.

[0329] Strategic proposal

[0330] Next, the server instantiates the StrategySuggester class and suggests a strategy using the new data. This new data includes new players and the number of appearances based on the upcoming game schedule. The server uses the generated prediction model to predict the score for the new data and suggests a strategy based on the prediction results. If the score is high, it suggests an "offensive strategy," and if the score is low, it suggests a "defensive strategy."

[0331] Results display

[0332] The terminal displays the results of these strategy proposals to the user. Based on this information, the user can plan specific strategies for player training and matches. The terminal displays the results of the strategy proposals on the screen and provides them to the user by printing them out as needed.

[0333] Specific examples

[0334] For example, suppose a user inputs player data for 2023 into the system (15, 10, and 5 game appearances, with 300, 210, and 50 points, respectively). This data is collected by the server and becomes the base data for generating a prediction model. When the number of game appearances for a new member is input (e.g., 9 and 7 games), the server accepts this as new data and calculates the predicted points. For example, if the predicted points are 180 for 9 game appearances and 140 for 7 game appearances, a "defense-focused strategy" will be suggested for each.

[0335] Example prompt sentence:

[0336] "Based on the following data, please calculate the expected points for the new members based on the number of games they play and propose a strategy:

[0337] 2023 Player Data:

[0338] Matches played: 15, 10, 5

[0339] Points: 300, 210, 50

[0340] Number of matches played by new members:

[0341] 9 matches

[0342] Seven games.”

[0343] In this way, the system of the present invention can significantly improve the performance of sports teams by efficiently and accurately collecting and analyzing information on players' game appearances and points scored, generating predictive models, and proposing strategies based on those models.

[0344] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0345] Step 1: Data collection

[0346] The server instantiates the DataCollector class and calls the collect_data method. This method retrieves information about players' appearances and points from an API or database. For example, it retrieves data in JSON format from the API and extracts information about each player. Specifically, it collects information such as Player A's appearance in 15 games and his score of 300. The input is player data retrieved from the API endpoint, and the output is data in Pandas DataFrame format.

[0347] Step 2: Save data

[0348] The server saves the collected data in Pandas DataFrame format. The DataFrame format makes it easy to manipulate and analyze data. Specifically, it converts JSON data into a Pandas DataFrame and saves the number of matches played and points scored by each player in tabular format. The input is the data collected in Step 1, and the output is data in DataFrame format.

[0349] Step 3: Data Preprocessing

[0350] The server instantiates the DataAnalyzer class and preprocesses the data using the analyze_data method. In this process, the data is standardized using StandardScaler. The input is data in DataFrame format, and the output is the standardized data. Specifically, the variance of the number of games played and points scored is reduced, and the mean is converted to 0 and the standard deviation to 1.

[0351] Step 4: Model generation

[0352] The server generates a linear regression model. The input is the preprocessed data from step 3, and the output is a predictive model. Specifically, the scikit-learn library is used to train a predictive model based on past performance data. This model predicts points scored using the number of matches played as input.

[0353] Step 5: Predict

[0354] The server uses new data to make predictions. For example, it takes the number of games played by a new member as input and uses a prediction model to calculate future points. The input is new game play data, and the output is the predicted points. Specifically, it predicts 180 points in 9 games played, and 140 points in 7 games played.

[0355] Step 6: Strategic proposal

[0356] The server instantiates the StrategySuggester class and proposes a strategy based on the prediction results. The input is the score data predicted in step 5, and the output is the proposed strategy. Specifically, if the score is high, an "offensive strategy" is proposed, and if the score is low, a "defensive strategy" is proposed. For example, if the number of games played is 9, a defensive strategy is proposed.

[0357] Step 7: View the results

[0358] The terminal displays the results of the strategy proposal to the user. The input is the strategy proposed in step 6, and the output is the strategy information displayed to the user. Specifically, the server displays the strategy proposed by the server on the competition screen or training plan screen. The user uses this information to plan strategies for actual training or matches.

[0359] (Application example 1)

[0360] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0361] To efficiently improve the performance of robots used in factories, a system is needed that collects robot work data, analyzes it, and proposes optimal work strategies. However, current systems lack the ability to standardize data or generate appropriate predictive models, making it difficult to propose effective strategies.

[0362] 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.

[0363] In this invention, the server includes means for collecting robot task data and efficiency data, means for analyzing the collected data and generating a prediction model, and means for predicting new data using the generated prediction model and proposing a task strategy, thereby making it possible to propose an optimal task strategy for efficiently improving the robot's performance.

[0364] "Robot work data" is information about a series of tasks performed by a robot in a factory, and specifically includes numerical data such as how many times the robot performed each task.

[0365] "Efficiency data" is information that indicates the ratio of the results obtained to the time and resource usage of the work performed by the robot, and specifically includes the productivity and success rate per task.

[0366] The "collection means" is a combination of hardware and software for acquiring work data and efficiency data from each robot, and includes sensors and data collection programs.

[0367] "Means of analysis" refers to algorithms and programs used to analyze collected data, and to standardize data and recognize patterns.

[0368] A "means for generating a predictive model" is a mathematical and computational method for predicting future efficiency or performance based on past data, such as using a linear regression model.

[0369] The "means for proposing a work strategy" refers to a means for showing an optimal work plan based on the generated predictive model, and includes visualization tools and recommendation systems.

[0370] "Standardization means" refers to algorithms and programs that reduce data variability and convert data into a comparable form, such as StandardScaler.

[0371] "Means of saving in Pandas DataFrame format" refers to a method of storing collected data in a DataFrame object of the Pandas library, which facilitates subsequent data processing and analysis.

[0372] The present invention relates to a system that collects and analyzes work data and efficiency data of robots in a factory to propose optimal work strategies. This system provides a means for efficiently improving the performance of robots.

[0373] Data collection and storage

[0374] The server instantiates the DataCollector class and calls the collect_data method to collect robot work data and efficiency data. The collected data is saved in Pandas DataFrame format. Examples of data include the robot ID, number of tasks, and efficiency information. For example, data is collected where the robot ID is 1, the number of tasks is 10, and the efficiency is 90.

[0375] Data analysis

[0376] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. In this analysis process, it first uses StandardScaler to standardize the data. StandardScaler is used to reduce data variability. Then, it uses a linear regression model to generate an efficiency prediction model. This prediction model is used to predict future efficiency based on past work data.

[0377] Work strategy proposal

[0378] The server then instantiates the StrategySuggester class and proposes a work strategy using the new data. This new data could be, for example, the number of tasks performed by a new robot. The server uses the prediction model to predict the efficiency of the new data and proposes a work strategy based on the prediction results. If the efficiency is high, the server proposes a "high-efficiency work strategy," and if the efficiency is low, the server proposes an "improvement suggestion strategy."

[0379] Examples of specific examples and prompts

[0380] For example, suppose a user inputs new robot data (robot ID: 4, number of tasks: 8) into the system. This data is collected by the server and used as the base data for generating a prediction model. The server then receives this as new data and calculates the prediction efficiency. If the prediction efficiency is 70, the server will propose an "improvement proposal strategy." This information is useful for formulating specific work strategies for subsequent tasks.

[0381] An example of a prompt is as follows:

[0382] Predict the efficiency of robots IDs 4 and 5 in a factory when they process 8 and 12 tasks, respectively, and propose an optimal work strategy based on that.

[0383] In this way, the system of the present invention efficiently and accurately analyzes collected work data and efficiency data, generates a predictive model, and proposes an optimal work strategy based on the model, thereby improving the performance of robots in factories and increasing production efficiency.

[0384] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0385] Step 1:

[0386] The server instantiates the DataCollector class and calls the collect_data method. This collects robot work data and efficiency data. Specifically, information on each robot's ID, number of tasks, and efficiency is collected. For example, data such as robot ID 1, number of tasks 10, and efficiency 90 can be obtained. The collected data is saved in Pandas DataFrame format.

[0387] Step 2:

[0388] The server analyzes the collected data using an instance of the DataAnalyzer class. Specifically, it calls the analyze_data method to standardize the data. StandardScaler is used for standardization, and scaling is performed to reduce data variation. The collected data is given as input, and standardized data is obtained as output.

[0389] Step 3:

[0390] The server uses the standardized data to generate a predictive model. Specifically, it uses a linear regression model to build a model for predicting future efficiency based on past data. The analyzed data is divided into X and y, and a model is generated using LinearRegression. The input is the standardized data, and the output is a linear regression model for predicting efficiency.

[0391] Step 4:

[0392] The server uses an instance of the StrategySuggester class to suggest a work strategy for new data. Specifically, it calls the suggest_strategy method of the strategy_suggester instance, inputs the work data of a new robot, and predicts its efficiency. For example, if the new robot ID is 4 and the number of tasks is 8, its efficiency is predicted using the model, and the predicted efficiency is 70. The predicted efficiency is obtained as the output.

[0393] Step 5:

[0394] Based on the provided predicted efficiency, the server proposes an optimal work strategy. If the efficiency is high, it proposes a "high-efficiency work strategy," and if it is low, it proposes an "improvement proposal strategy." For example, if the efficiency is 70, it proposes the "improvement proposal strategy." This proposal information is sent to the terminal, and the user can use it to plan a specific work strategy.

[0395] An example of a prompt is as follows:

[0396] Predict the efficiency of robots IDs 4 and 5 in a factory when they process 8 and 12 tasks, respectively, and propose an optimal work strategy based on that.

[0397] In this way, a system is created to improve the performance of robots in a factory.

[0398] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0399] This invention relates to a system that collects data on the number of matches played and the number of points scored by players, and analyzes, predicts, and proposes strategies by combining this with an emotion engine that recognizes the emotions of the user, thereby making more appropriate strategy proposals.

[0400] Data collection and storage

[0401] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of goals scored by each player. This data is saved in a Pandas DataFrame format, making it easy to analyze later.

[0402] Data analysis

[0403] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. During the analysis process, a StandardScaler is used to standardize the appearance data. A linear regression model is then used to generate a score prediction model. The prediction model is used to predict future scores based on a player's past performance data.

[0404] Strategy suggestions and emotion recognition

[0405] Next, the server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on the new data. Here, an emotion engine is added to recognize user emotions and collect emotion data, for example, when a user expresses dissatisfaction with a proposed strategy.

[0406] The server adjusts the strategy by taking into account the user's emotional data collected using the emotion engine. Specifically, the emotional data is reflected in the prediction model to propose a strategy that will satisfy the user. For example, if the user is dissatisfied with the proposed tactics, the server may adjust the strategy to one that emphasizes more defense.

[0407] Specific examples

[0408] For example, if a user inputs player data into the system (number of games played: 15, 10, 5, with points scored of 300, 210, 50, respectively), this data is collected by the server and used as the base data for generating a prediction model. If a user then inputs the number of games played by a new member (e.g., 9 games, 7 games), the server will accept this as new data and calculate the predicted points.

[0409] The server also uses an emotion engine to collect the user's emotional data (happiness, dissatisfaction, etc.). For example, if the predicted score is 180 and an "attack-focused tactic" is suggested, and the user expresses dissatisfaction with the suggestion, the emotion engine will feed that information back to the server. The server will then readjust the prediction model based on the emotional data and suggest a strategy that suits the user's emotions, such as switching to a "defense-focused tactic."

[0410] The terminal displays the final strategy proposal to the user, who can then use it to plan specific strategies for training players and matches.

[0411] In this way, by combining the emotion engine, it is possible to realize more flexible and effective strategy proposals that are not based solely on data but also take into account the user's emotions, which can greatly contribute to improving the performance of sports organizations.

[0412] The processing flow will be explained below.

[0413] Step 1:

[0414] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of goals scored by each player. This data is saved in a Pandas DataFrame format, making it easy to analyze later.

[0415] Step 2:

[0416] The server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. At this stage, as a data preprocessing step, it uses StandardScaler to standardize the appearance data. Then, it builds a linear regression model using the standardized data to generate a model to predict points.

[0417] Step 3:

[0418] The server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on new data, such as the number of games played by a new member. The server inputs this new data into the prediction model and predicts the score.

[0419] Step 4:

[0420] The server instantiates an emotion engine to collect the user's emotion data. Specifically, the engine recognizes the user's emotion toward the strategy proposal (e.g., joy, dissatisfaction, etc.) and transmits the data to the server.

[0421] Step 5:

[0422] The server readjusts the strategy proposals based on the user's emotional data provided by the emotion engine. For example, if the predicted score is 180 and an "attack-focused strategy" is proposed, and the user expresses dissatisfaction, the server will readjust the prediction model based on that information and propose a "defense-focused strategy" instead.

[0423] Step 6:

[0424] The terminal displays the final strategy proposal to the user, who can then use the proposal to plan specific training and match strategies for the players.

[0425] In this way, by combining the emotion engine, it becomes possible to propose more flexible and effective strategies that are not only based on data but also take into account the emotions of the user, which will greatly contribute to improving the performance of sports organizations.

[0426] Example 2

[0427] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0428] Conventional player performance analysis systems are limited to collecting and analyzing data on the number of matches played and points scored, and have the problem of being unable to propose appropriate strategies that take the user's emotions into account. As a result, users may be dissatisfied with the proposed strategies, and optimal performance improvements may not be achieved.

[0429] 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.

[0430] In this invention, the server includes means for collecting data on the number of matches played and the number of points scored by players, means for analyzing the collected data and generating a prediction model, means for predicting new data using the generated prediction model and proposing a strategy, and means for recognizing the user's emotions and adjusting the strategy based on the emotion data, thereby enabling more appropriate strategy proposals that are based not only on data but also on the user's emotions.

[0431] "Player appearances" refers to the number of times a player has appeared in an official match.

[0432] "Score Data" refers to information regarding the scores scored by a player during a match.

[0433] "Collection means" refers to the technological devices or functions used to capture and store information such as player appearances and goalscoring data.

[0434] "Analyzing means" refers to the technical devices or capabilities used to analyze collected data and extract useful information or patterns.

[0435] "Predictive Model" means a mathematical or statistical model used to forecast future events or outcomes based on data collected in the past.

[0436] "Means for proposing strategies" refers to a technical device or function for proposing methods of competition or training based on the results of a predictive model.

[0437] "Means for recognizing user emotions" refers to a technical device or function for detecting the user's emotional state (happiness, dissatisfaction, etc.) and capturing it as data.

[0438] "Emotion data" refers to data that expresses the user's emotional state as numerical values ​​or categories.

[0439] "Means for adjusting strategy based on emotional data" refers to a technical device or function that takes into account the collected emotional data of users, recalculates the optimal strategy, and adjusts the content of suggestions.

[0440] "Standardization means" refers to a technical device or function that equalizes data variability and makes data on different scales comparable.

[0441] "Tabular" refers to data arranged in a regular pattern of rows and columns.

[0442] "Storage means" refers to technical devices or functions that record and store collected or generated data in a form that can be accessed at a later date.

[0443] This invention relates to a system that collects data on the number of matches played and the number of points scored by players, analyzes and predicts the results, and proposes strategies that take into account the user's emotions. This system is realized through processing between a server, a terminal, and a user.

[0444] The server first instantiates the DataCollector class and uses the collect_data method to collect data on players' appearances and goals. This data is then saved in Pandas DataFrame format using Pandas, a Python data analysis library. This makes it easier to manage the data and perform subsequent analysis.

[0445] The server then instantiates the DataAnalyzer class and analyzes the data using the analyze_data method. Specifically, it uses StandardScaler to standardize the appearance data and then uses a linear regression model to generate a model for predicting points. The model is used to predict future points based on a player's past performance data.

[0446] The server then instantiates the StrategySuggester class and uses the suggest_strategy method to propose a strategy based on the new data. At this stage, an emotion engine is added to recognize the user's emotions. Specifically, if the user expresses dissatisfaction with the proposed strategy, the emotion data is collected. The server then adjusts the strategy based on the emotion data and makes a proposal that satisfies the user.

[0447] For example, suppose a user inputs the following player data into the system: number of matches played: 15, 10, 5, with respective scores of 300, 210, 50. This data is collected by the server and becomes the basis for the prediction model. If a new member later inputs the number of matches played (e.g., 9 matches, 7 matches), the server will accept this as new data and calculate the predicted score. At this time, the emotion engine will collect the user's emotional data (e.g., dissatisfaction), and the server will readjust the strategy based on that data. For example, if an "attack-focused tactic" is proposed but the user expresses dissatisfaction, the server may switch to a "defense-focused tactic" based on the emotional data.

[0448] The terminal displays the final strategy proposal sent from the server to the user, who can then use it to plan specific training and match strategies for the players.

[0449] Examples of prompts include:

[0450] Enter player data:

[0451] Matches played: 15, 10, 5

[0452] Points: 300, 210, 50

[0453] Number of games played by new members: 9, 7

[0454] Emotional data: Dissatisfaction

[0455] Based on this prompt, the server can collect, analyze, and predict data, and adjust strategies based on emotional data, and then suggest the optimal strategy to the user.

[0456] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0457] Processing Step Description

[0458] Step 1:

[0459] The server instantiates the DataCollector class. As input, it receives the number of matches played and the number of points scored by each player. Specifically, it retrieves the data from an API or database and saves it in Pandas DataFrame format. This allows the data to be managed in a unified format. The output is data in Pandas DataFrame format.

[0460] Step 2:

[0461] The server instantiates the DataAnalyzer class. The input is the Pandas DataFrame data collected in step 1. The server uses the analyze_data method to first standardize the appearance data using StandardScaler. It then creates a linear regression model and generates a predictive model based on this model. The output is the predictive model.

[0462] Step 3:

[0463] The server instantiates the StrategySuggester class. The input is the prediction model generated in step 2. The server uses the suggest_strategy method to receive new player data as input, calculate predicted scores, and propose a strategy. Specifically, it inputs normalized game appearance data into the prediction model to predict scores. The output is the predicted strategy suggestion.

[0464] Step 4:

[0465] The user provides feedback on the proposed strategy by clicking a button indicating their level of satisfaction (e.g., happy, dissatisfied) with the proposed strategy. The input is the user's emotional data.

[0466] Step 5:

[0467] The server uses an emotion engine to collect user emotion data. The input is the user emotion data collected in step 4. The server readjusts the strategy based on this data. Specifically, it analyzes the emotion data and modifies the strategy if there is a high level of dissatisfaction. The output is a proposed adjusted strategy.

[0468] Step 6:

[0469] The terminal displays the final strategy proposal to the user. The input is the strategy proposal adjusted in step 5. The terminal presents the proposal to the user in an easy-to-understand format, allowing the user to take concrete action. The output is the strategy proposal displayed on the screen.

[0470] Through these steps, the system can collect and analyze player performance data, generate predictive models, and even suggest strategies that take the user's emotions into account.

[0471] (Application example 2)

[0472] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0473] Autonomous vehicles are required to recognize the driver's emotional state and provide an optimal driving strategy based on that. Such a system would contribute to reducing driver stress and promoting safe driving. However, conventional navigation systems have the problem of being unable to propose driving strategies that take the driver's emotional state into account and can only provide uniform route guidance.

[0474] 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.

[0475] In this invention, the server includes means for collecting data on the number of games played and the scores of players, means for analyzing the collected data and generating a prediction model, means for predicting new data using the generated prediction model and proposing a strategy, means for collecting and analyzing a user's emotions, and means for adjusting and proposing a strategy using the user's emotion data, thereby enabling the proposal of a driving strategy that takes into account the driver's emotional state.

[0476] "Player Appearances" refers to the total number of matches a player participates in during a particular period.

[0477] "Score data" refers to numerical information about the points scored by a player in a match.

[0478] "Collection Means" refers to the technical capabilities and methods used to capture and record player appearance and goal data.

[0479] "Means for analyzing and generating predictive models" refers to the technological capabilities and methods for analyzing collected data and creating mathematical and statistical models based on that data to predict future performance.

[0480] "Means for proposing strategies" refers to the technical capabilities and methods for evaluating new data and recommending optimal plans of action or courses of action based on the generated predictive models.

[0481] "Means for collecting and analyzing user emotions" refers to technical functions and methods for detecting and analyzing the emotional state of a user from their facial expressions and voice.

[0482] "Means for adjusting and proposing strategies using emotional data" refers to technical functions and methods for taking into account the emotional data of a user and selecting and proposing an optimal strategy.

[0483] "Standardization measures" refer to technical features or methods for converting collected data values ​​onto a consistent scale.

[0484] "Means for storing data in a data frame format" refers to the technical features and methods for storing collected data in a tabular format consisting of rows and columns.

[0485] This invention relates to a system that recognizes the driver's emotional state in real time and adjusts and proposes driving strategies based on that. This system is based on the collection and analysis of players' game appearances and score data, and analyzes and reflects the user's emotional data in real time to optimize navigation strategies while actually driving.

[0486] 1. Data Collection

[0487] The server collects the driver's facial expressions and tone of voice via the device's built-in camera and microphone. Specifically, it analyzes the facial expression data captured by the camera and the voice data collected by the microphone using an emotion recognition model. The emotion recognition model uses a model based on deep learning technology (such as TensorFlow or Keras).

[0488] 2. Data analysis

[0489] The server stores the collected emotion data in a data frame format (Pandas DataFrame). The emotion data is standardized (StandardScaler) to ensure consistency and then analyzed using a linear regression model (LinearRegression). This generates a predictive model based on the driver's emotional state.

[0490] 3. Strategy proposal and emotion recognition

[0491] The server uses an emotion prediction model to suggest a driving strategy that matches the driver's emotional state. Specifically, if the driver is stressed, the server suggests the shortest route, and if the driver is relaxed, it suggests a scenic route. This information is displayed on the device (smartphone or head-mounted display) and provided to the driver.

[0492] Specific examples

[0493] For example, if the system determines that the driver is stressed, the device will display "Suggest the shortest route." On the other hand, if the system determines that the driver is relaxed, it will display "Suggest the scenic route." This allows the driver to select the optimal driving route based on their emotional state.

[0494] Example prompts for generative AI models

[0495] "We need an app that suggests routes that help you relax while driving. It should recognize your emotions and suggest the best driving route based on them."

[0496] "Create a navigation system that suggests the shortest route when the driver is stressed, or a scenic route when the driver is relaxed."

[0497] The above is an embodiment of the invention, which makes it possible to propose a driving strategy that takes into account the emotional state of the driver.

[0498] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0499] Step 1:

[0500] The server collects the driver's facial expressions and tone of voice in real time through the camera and microphone built into the device. The input here is the camera video and audio data, and the output is that these data are sent to the server. The camera captures the driver's face, and the microphone picks up the audio.

[0501] Step 2:

[0502] The server inputs the collected facial and voice data into an emotion recognition model to analyze the driver's emotional state. The input here is the captured facial and voice data, and the output is the analysis result (emotional state) by the emotion recognition model. Deep learning libraries such as TensorFlow and Keras are used to evaluate emotions.

[0503] Step 3:

[0504] The server saves the parsed emotion data in Pandas DataFrame format. Here, the input is emotion data and the output is saved in DataFrame format. The Pandas library is used to structure the data to facilitate later analysis.

[0505] Step 4:

[0506] The server normalizes the stored data using StandardScaler. The input here is the emotion data stored in a data frame, and the output is the normalized data. StandardScaler is used to unify the scale of the data.

[0507] Step 5:

[0508] The server trains a linear regression model using the normalized data to generate a predictive model. Here, the input is the normalized data, and the output is a predictive model based on the driver's emotions. LinearRegression is used to build the predictive model.

[0509] Step 6:

[0510] The server uses the generated predictive model to predict the driver's emotional state and proposes a driving strategy based on it. The input here is the current emotional data, and the output is the optimal driving strategy. If the driver is relaxed, it will suggest a scenic route, and if the driver is stressed, it will suggest the shortest route.

[0511] Step 7:

[0512] The device displays the proposed driving strategy to the user, where the input is the driving strategy information sent from the server and the output is the displayed route proposal. The information is provided visually on the device's display or head-mounted display.

[0513] Through these steps, an optimal driving strategy that reflects the driver's emotional state is proposed.

[0514] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0515] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0516] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0517] [Third embodiment]

[0518] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0519] 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.

[0520] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0521] 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.

[0522] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0523] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0524] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0525] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0526] 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.

[0527] 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.

[0528] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0529] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0530] The present invention relates to a system for collecting data on the number of matches played and the number of points scored by players, and for analyzing, predicting, and proposing such data.

[0531] Data collection and storage

[0532] The server instantiates the DataCollector class and calls the collect_data method to collect player data. The collected data includes the number of matches played and points scored by each player. This data is saved in Pandas DataFrame format, making it easy to analyze later.

[0533] Data analysis

[0534] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. This analysis process first uses StandardScaler to standardize data such as game appearances, reducing data variability. It then uses a linear regression model to generate a score prediction model. This prediction model is used to predict future scores based on a player's past performance data.

[0535] Strategic proposal

[0536] The server then instantiates the StrategySuggester class and suggests a strategy using the new data. This new data could be, for example, new players or game appearances based on the upcoming game schedule. The server uses the prediction model to predict the score for the new data and suggests a strategy based on the prediction. If the score is high, the server suggests an "offensive strategy," and if the score is low, the server suggests a "defensive strategy."

[0537] Specific examples

[0538] For example, suppose a user inputs player data for 2023 into the system (15, 10, and 5 game appearances, with 300, 210, and 50 points, respectively). This data is collected by the server and used as the base data for generating a prediction model. Next, if the number of game appearances for a new member is input (e.g., 9 and 7 games), the server accepts this as new data and calculates the predicted points. For example, if the predicted points are 180 for 9 game appearances and 140 for 7 game appearances, the server will suggest a "defense-focused strategy" for each.

[0539] The terminal displays the results of these strategy proposals to the user, who can then use this information to plan specific training and match strategies for their players.

[0540] In this way, the system of the present invention efficiently and accurately collects and analyzes player appearance and score data, generates predictive models, and proposes strategies based on them, thereby significantly improving the performance of sports teams.

[0541] The processing flow will be explained below.

[0542] Step 1:

[0543] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of points scored by each player. Specifically, temporary data is generated and saved in the Pandas DataFrame format.

[0544] Step 2:

[0545] The server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. At this stage, as a data preprocessing step, it uses StandardScaler to standardize the appearance data. Then, it uses the standardized data to generate a linear regression model to predict points.

[0546] Step 3:

[0547] The server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on new data, such as the number of games played by a new player. The server inputs this new data into the prediction model and predicts the score.

[0548] Step 4:

[0549] The server proposes a strategy based on the predicted score. Specifically, if the predicted score is high, it proposes an "offense-oriented strategy," and if the predicted score is low, it proposes a "defense-oriented strategy."

[0550] Step 5:

[0551] The terminal displays the strategy proposals provided by the server to the user, who can then use them to plan specific training and match strategies for the players.

[0552] Through this process, the system can efficiently and accurately collect and analyze data, create predictive models, and propose strategies based on them, thereby contributing to improving the performance of sports organizations.

[0553] Example 1

[0554] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0555] This invention relates to a system that collects information on players' game appearances and scores, predicts their future performance based on this information, and proposes effective strategies. Conventional systems require manual data collection and analysis, which is inefficient and has limited accuracy. This makes it difficult to quickly develop effective strategies that can contribute to improving the performance of sports teams.

[0556] 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.

[0557] In this invention, the server includes a means for collecting information on the number of games played and the scores of players, a means for analyzing the collected information and generating a prediction model, and a means for predicting new information using the generated prediction model and proposing a strategy, thereby enabling the rapid and accurate collection and analysis of player performance information, the generation of a prediction model, and the proposing of an effective strategy.

[0558] "Athlete" means an individual or team member who takes part in a competition or sporting event.

[0559] "Appearances" is the number of matches or competitions an athlete takes part in within a specific period of time.

[0560] "Score information" refers to data on the points and scores that a player has earned in a match or competition.

[0561] "Means of collecting information" refers to the technical means by which servers and devices obtain information on the number of competitions and scores through APIs, databases, etc.

[0562] "Means for analyzing information" are technical means for processing collected data and identifying characteristics and trends.

[0563] The "means for generating a predictive model" refers to a means for creating a mathematical model for predicting future performance from past data using a machine learning algorithm.

[0564] "New information" refers to newly added data or circumstances that are not based on existing data.

[0565] "Means for proposing strategies" are technical means for formulating competition and training plans based on the results of the predictive model.

[0566] The "data frame format" is a tabular data structure consisting of rows and columns, and is a format that is particularly used when using the Pandas library.

[0567] "Standardization methods" are technical methods for adjusting data to reduce variability and make the mean zero and the standard deviation one.

[0568] This invention relates to a system that collects information on the number of matches played and the number of points scored by players, analyzes the data, generates a prediction model, and proposes strategies. This system is realized by a server, a terminal, and a user, each playing their own role.

[0569] Data collection and storage

[0570] To collect information on the number of matches played and the number of points scored by each player, the server instantiates a specific class (DataCollector class) and calls a specific method (collector_data method). Specifically, the server obtains the number of matches played and the number of points scored by each player from an API or database, and stores this information in Pandas DataFrame format. Pandas is a powerful Python data manipulation library and is an ideal data storage format.

[0571] Data analysis

[0572] The server then instantiates another class (DataAnalyzer class) and uses a specific method (analyze_data method) to analyze the collected information. This process begins by standardizing the data using StandardScaler. StandardScaler is a tool included in the scikit-learn library that converts the mean to 0 and the standard deviation to 1 to reduce data variability. This makes the data scale uniform, improving the accuracy of the predictive model.

[0573] Model Generation and Prediction

[0574] The server then generates a linear regression model to predict future scores based on a player's past performance data. The linear regression model is also implemented using the scikit-learn library. Based on the trained model, future scores are predicted when new data (such as the number of games played by a new player) is input. This allows sports organizations to develop strategies based on the predicted scores.

[0575] Strategic proposal

[0576] Next, the server instantiates the StrategySuggester class and suggests a strategy using the new data. This new data includes new players and the number of appearances based on the upcoming game schedule. The server uses the generated prediction model to predict the score for the new data and suggests a strategy based on the prediction results. If the score is high, it suggests an "offensive strategy," and if the score is low, it suggests a "defensive strategy."

[0577] Results display

[0578] The terminal displays the results of these strategy proposals to the user. Based on this information, the user can plan specific strategies for player training and matches. The terminal displays the results of the strategy proposals on the screen and provides them to the user by printing them out as needed.

[0579] Specific examples

[0580] For example, suppose a user inputs player data for 2023 into the system (15, 10, and 5 game appearances, with 300, 210, and 50 points, respectively). This data is collected by the server and becomes the base data for generating a prediction model. When the number of game appearances for a new member is input (e.g., 9 and 7 games), the server accepts this as new data and calculates the predicted points. For example, if the predicted points are 180 for 9 game appearances and 140 for 7 game appearances, a "defense-focused strategy" will be suggested for each.

[0581] Example prompt sentence:

[0582] "Based on the following data, please calculate the expected points for the new members based on the number of games they play and propose a strategy:

[0583] 2023 Player Data:

[0584] Matches played: 15, 10, 5

[0585] Points: 300, 210, 50

[0586] Number of matches played by new members:

[0587] 9 matches

[0588] Seven games.”

[0589] In this way, the system of the present invention can significantly improve the performance of sports teams by efficiently and accurately collecting and analyzing information on players' game appearances and points scored, generating predictive models, and proposing strategies based on those models.

[0590] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0591] Step 1: Data collection

[0592] The server instantiates the DataCollector class and calls the collect_data method. This method retrieves information about players' appearances and points from an API or database. For example, it retrieves data in JSON format from the API and extracts information about each player. Specifically, it collects information such as Player A's appearance in 15 games and his score of 300. The input is player data retrieved from the API endpoint, and the output is data in Pandas DataFrame format.

[0593] Step 2: Save data

[0594] The server saves the collected data in Pandas DataFrame format. The DataFrame format makes it easy to manipulate and analyze data. Specifically, it converts JSON data into a Pandas DataFrame and saves the number of matches played and points scored by each player in tabular format. The input is the data collected in Step 1, and the output is data in DataFrame format.

[0595] Step 3: Data Preprocessing

[0596] The server instantiates the DataAnalyzer class and preprocesses the data using the analyze_data method. In this process, the data is standardized using StandardScaler. The input is data in DataFrame format, and the output is the standardized data. Specifically, the variance of the number of games played and points scored is reduced, and the mean is converted to 0 and the standard deviation to 1.

[0597] Step 4: Model generation

[0598] The server generates a linear regression model. The input is the preprocessed data from step 3, and the output is a predictive model. Specifically, the scikit-learn library is used to train a predictive model based on past performance data. This model predicts points scored using the number of matches played as input.

[0599] Step 5: Predict

[0600] The server uses new data to make predictions. For example, it takes the number of games played by a new member as input and uses a prediction model to calculate future points. The input is new game play data, and the output is the predicted points. Specifically, it predicts 180 points in 9 games played, and 140 points in 7 games played.

[0601] Step 6: Strategic proposal

[0602] The server instantiates the StrategySuggester class and proposes a strategy based on the prediction results. The input is the score data predicted in step 5, and the output is the proposed strategy. Specifically, if the score is high, an "offensive strategy" is proposed, and if the score is low, a "defensive strategy" is proposed. For example, if the number of games played is 9, a defensive strategy is proposed.

[0603] Step 7: View the results

[0604] The terminal displays the results of the strategy proposal to the user. The input is the strategy proposed in step 6, and the output is the strategy information displayed to the user. Specifically, the server displays the strategy proposed by the server on the competition screen or training plan screen. The user uses this information to plan strategies for actual training or matches.

[0605] (Application example 1)

[0606] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0607] To efficiently improve the performance of robots used in factories, a system is needed that collects robot work data, analyzes it, and proposes optimal work strategies. However, current systems lack the ability to standardize data or generate appropriate predictive models, making it difficult to propose effective strategies.

[0608] 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.

[0609] In this invention, the server includes means for collecting robot task data and efficiency data, means for analyzing the collected data and generating a prediction model, and means for predicting new data using the generated prediction model and proposing a task strategy, thereby making it possible to propose an optimal task strategy for efficiently improving the robot's performance.

[0610] "Robot work data" is information about a series of tasks performed by a robot in a factory, and specifically includes numerical data such as how many times the robot performed each task.

[0611] "Efficiency data" is information that indicates the ratio of the results obtained to the time and resource usage of the work performed by the robot, and specifically includes the productivity and success rate per task.

[0612] The "collection means" is a combination of hardware and software for acquiring work data and efficiency data from each robot, and includes sensors and data collection programs.

[0613] "Means of analysis" refers to algorithms and programs used to analyze collected data, and to standardize data and recognize patterns.

[0614] A "means for generating a predictive model" is a mathematical and computational method for predicting future efficiency or performance based on past data, such as using a linear regression model.

[0615] The "means for proposing a work strategy" refers to a means for showing an optimal work plan based on the generated predictive model, and includes visualization tools and recommendation systems.

[0616] "Standardization means" refers to algorithms and programs that reduce data variability and convert data into a comparable form, such as StandardScaler.

[0617] "Means of saving in Pandas DataFrame format" refers to a method of storing collected data in a DataFrame object of the Pandas library, which facilitates subsequent data processing and analysis.

[0618] The present invention relates to a system that collects and analyzes work data and efficiency data of robots in a factory to propose optimal work strategies. This system provides a means for efficiently improving the performance of robots.

[0619] Data collection and storage

[0620] The server instantiates the DataCollector class and calls the collect_data method to collect robot work data and efficiency data. The collected data is saved in Pandas DataFrame format. Examples of data include the robot ID, number of tasks, and efficiency information. For example, data is collected where the robot ID is 1, the number of tasks is 10, and the efficiency is 90.

[0621] Data analysis

[0622] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. In this analysis process, it first uses StandardScaler to standardize the data. StandardScaler is used to reduce data variability. Then, it uses a linear regression model to generate an efficiency prediction model. This prediction model is used to predict future efficiency based on past work data.

[0623] Work strategy proposal

[0624] The server then instantiates the StrategySuggester class and proposes a work strategy using the new data. This new data could be, for example, the number of tasks performed by a new robot. The server uses the prediction model to predict the efficiency of the new data and proposes a work strategy based on the prediction results. If the efficiency is high, the server proposes a "high-efficiency work strategy," and if the efficiency is low, the server proposes an "improvement suggestion strategy."

[0625] Examples of specific examples and prompts

[0626] For example, suppose a user inputs new robot data (robot ID: 4, number of tasks: 8) into the system. This data is collected by the server and used as the base data for generating a prediction model. The server then receives this as new data and calculates the prediction efficiency. If the prediction efficiency is 70, the server will propose an "improvement proposal strategy." This information is useful for formulating specific work strategies for subsequent tasks.

[0627] An example of a prompt is as follows:

[0628] Predict the efficiency of robots IDs 4 and 5 in a factory when they process 8 and 12 tasks, respectively, and propose an optimal work strategy based on that.

[0629] In this way, the system of the present invention efficiently and accurately analyzes collected work data and efficiency data, generates a predictive model, and proposes an optimal work strategy based on the model, thereby improving the performance of robots in factories and increasing production efficiency.

[0630] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0631] Step 1:

[0632] The server instantiates the DataCollector class and calls the collect_data method. This collects robot work data and efficiency data. Specifically, information on each robot's ID, number of tasks, and efficiency is collected. For example, data such as robot ID 1, number of tasks 10, and efficiency 90 can be obtained. The collected data is saved in Pandas DataFrame format.

[0633] Step 2:

[0634] The server analyzes the collected data using an instance of the DataAnalyzer class. Specifically, it calls the analyze_data method to standardize the data. StandardScaler is used for standardization, and scaling is performed to reduce data variation. The collected data is given as input, and standardized data is obtained as output.

[0635] Step 3:

[0636] The server uses the standardized data to generate a predictive model. Specifically, it uses a linear regression model to build a model for predicting future efficiency based on past data. The analyzed data is divided into X and y, and a model is generated using LinearRegression. The input is the standardized data, and the output is a linear regression model for predicting efficiency.

[0637] Step 4:

[0638] The server uses an instance of the StrategySuggester class to suggest a work strategy for new data. Specifically, it calls the suggest_strategy method of the strategy_suggester instance, inputs the work data of a new robot, and predicts its efficiency. For example, if the new robot ID is 4 and the number of tasks is 8, its efficiency is predicted using the model, and the predicted efficiency is 70. The predicted efficiency is obtained as the output.

[0639] Step 5:

[0640] Based on the provided predicted efficiency, the server proposes an optimal work strategy. If the efficiency is high, it proposes a "high-efficiency work strategy," and if it is low, it proposes an "improvement proposal strategy." For example, if the efficiency is 70, it proposes the "improvement proposal strategy." This proposal information is sent to the terminal, and the user can use it to plan a specific work strategy.

[0641] An example of a prompt is as follows:

[0642] Predict the efficiency of robots IDs 4 and 5 in a factory when they process 8 and 12 tasks, respectively, and propose an optimal work strategy based on that.

[0643] In this way, a system is created to improve the performance of robots in a factory.

[0644] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0645] This invention relates to a system that collects data on the number of matches played and the number of points scored by players, and analyzes, predicts, and proposes strategies by combining this with an emotion engine that recognizes the emotions of the user, thereby making more appropriate strategy proposals.

[0646] Data collection and storage

[0647] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of goals scored by each player. This data is saved in a Pandas DataFrame format, making it easy to analyze later.

[0648] Data analysis

[0649] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. During the analysis process, a StandardScaler is used to standardize the appearance data. A linear regression model is then used to generate a score prediction model. The prediction model is used to predict future scores based on a player's past performance data.

[0650] Strategy suggestions and emotion recognition

[0651] Next, the server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on the new data. Here, an emotion engine is added to recognize user emotions and collect emotion data, for example, when a user expresses dissatisfaction with a proposed strategy.

[0652] The server adjusts the strategy by taking into account the user's emotional data collected using the emotion engine. Specifically, the emotional data is reflected in the prediction model to propose a strategy that will satisfy the user. For example, if the user is dissatisfied with the proposed tactics, the server may adjust the strategy to one that emphasizes more defense.

[0653] Specific examples

[0654] For example, if a user inputs player data into the system (number of games played: 15, 10, 5, with points scored of 300, 210, 50, respectively), this data is collected by the server and used as the base data for generating a prediction model. If a user then inputs the number of games played by a new member (e.g., 9 games, 7 games), the server will accept this as new data and calculate the predicted points.

[0655] The server also uses an emotion engine to collect the user's emotional data (happiness, dissatisfaction, etc.). For example, if the predicted score is 180 and an "attack-focused tactic" is suggested, and the user expresses dissatisfaction with the suggestion, the emotion engine will feed that information back to the server. The server will then readjust the prediction model based on the emotional data and suggest a strategy that suits the user's emotions, such as switching to a "defense-focused tactic."

[0656] The terminal displays the final strategy proposal to the user, who can then use it to plan specific strategies for training players and matches.

[0657] In this way, by combining the emotion engine, it is possible to realize more flexible and effective strategy proposals that are not based solely on data but also take into account the user's emotions, which can greatly contribute to improving the performance of sports organizations.

[0658] The processing flow will be explained below.

[0659] Step 1:

[0660] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of goals scored by each player. This data is saved in a Pandas DataFrame format, making it easy to analyze later.

[0661] Step 2:

[0662] The server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. At this stage, as a data preprocessing step, it uses StandardScaler to standardize the appearance data. Then, it builds a linear regression model using the standardized data to generate a model to predict points.

[0663] Step 3:

[0664] The server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on new data, such as the number of games played by a new member. The server inputs this new data into the prediction model and predicts the score.

[0665] Step 4:

[0666] The server instantiates an emotion engine to collect the user's emotion data. Specifically, the engine recognizes the user's emotion toward the strategy proposal (e.g., joy, dissatisfaction, etc.) and transmits the data to the server.

[0667] Step 5:

[0668] The server readjusts the strategy proposals based on the user's emotional data provided by the emotion engine. For example, if the predicted score is 180 and an "attack-focused strategy" is proposed, and the user expresses dissatisfaction, the server will readjust the prediction model based on that information and propose a "defense-focused strategy" instead.

[0669] Step 6:

[0670] The terminal displays the final strategy proposal to the user, who can then use the proposal to plan specific training and match strategies for the players.

[0671] In this way, by combining the emotion engine, it becomes possible to propose more flexible and effective strategies that are not only based on data but also take into account the emotions of the user, which will greatly contribute to improving the performance of sports organizations.

[0672] Example 2

[0673] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0674] Conventional player performance analysis systems are limited to collecting and analyzing data on the number of matches played and points scored, and have the problem of being unable to propose appropriate strategies that take the user's emotions into account. As a result, users may be dissatisfied with the proposed strategies, and optimal performance improvements may not be achieved.

[0675] 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.

[0676] In this invention, the server includes means for collecting data on the number of matches played and the number of points scored by players, means for analyzing the collected data and generating a prediction model, means for predicting new data using the generated prediction model and proposing a strategy, and means for recognizing the user's emotions and adjusting the strategy based on the emotion data, thereby enabling more appropriate strategy proposals that are based not only on data but also on the user's emotions.

[0677] "Player appearances" refers to the number of times a player has appeared in an official match.

[0678] "Score Data" refers to information regarding the scores scored by a player during a match.

[0679] "Collection means" refers to the technological devices or functions used to capture and store information such as player appearances and goalscoring data.

[0680] "Analyzing means" refers to the technical devices or capabilities used to analyze collected data and extract useful information or patterns.

[0681] "Predictive Model" means a mathematical or statistical model used to forecast future events or outcomes based on data collected in the past.

[0682] "Means for proposing strategies" refers to a technical device or function for proposing methods of competition or training based on the results of a predictive model.

[0683] "Means for recognizing user emotions" refers to a technical device or function for detecting the user's emotional state (happiness, dissatisfaction, etc.) and capturing it as data.

[0684] "Emotion data" refers to data that expresses the user's emotional state as numerical values ​​or categories.

[0685] "Means for adjusting strategy based on emotional data" refers to a technical device or function that takes into account the collected emotional data of users, recalculates the optimal strategy, and adjusts the content of suggestions.

[0686] "Standardization means" refers to a technical device or function that equalizes data variability and makes data on different scales comparable.

[0687] "Tabular" refers to data arranged in a regular pattern of rows and columns.

[0688] "Storage means" refers to technical devices or functions that record and store collected or generated data in a form that can be accessed at a later date.

[0689] This invention relates to a system that collects data on the number of matches played and the number of points scored by players, analyzes and predicts the results, and proposes strategies that take into account the user's emotions. This system is realized through processing between a server, a terminal, and a user.

[0690] The server first instantiates the DataCollector class and uses the collect_data method to collect data on players' appearances and goals. This data is then saved in Pandas DataFrame format using Pandas, a Python data analysis library. This makes it easier to manage the data and perform subsequent analysis.

[0691] The server then instantiates the DataAnalyzer class and analyzes the data using the analyze_data method. Specifically, it uses StandardScaler to standardize the appearance data and then uses a linear regression model to generate a model for predicting points. The model is used to predict future points based on a player's past performance data.

[0692] The server then instantiates the StrategySuggester class and uses the suggest_strategy method to propose a strategy based on the new data. At this stage, an emotion engine is added to recognize the user's emotions. Specifically, if the user expresses dissatisfaction with the proposed strategy, the emotion data is collected. The server then adjusts the strategy based on the emotion data and makes a proposal that satisfies the user.

[0693] For example, suppose a user inputs the following player data into the system: number of matches played: 15, 10, 5, with respective scores of 300, 210, 50. This data is collected by the server and becomes the basis for the prediction model. If a new member later inputs the number of matches played (e.g., 9 matches, 7 matches), the server will accept this as new data and calculate the predicted score. At this time, the emotion engine will collect the user's emotional data (e.g., dissatisfaction), and the server will readjust the strategy based on that data. For example, if an "attack-focused tactic" is proposed but the user expresses dissatisfaction, the server may switch to a "defense-focused tactic" based on the emotional data.

[0694] The terminal displays the final strategy proposal sent from the server to the user, who can then use it to plan specific training and match strategies for the players.

[0695] Examples of prompts include:

[0696] Enter player data:

[0697] Matches played: 15, 10, 5

[0698] Points: 300, 210, 50

[0699] Number of games played by new members: 9, 7

[0700] Emotional data: Dissatisfaction

[0701] Based on this prompt, the server can collect, analyze, and predict data, and adjust strategies based on emotional data, and then suggest the optimal strategy to the user.

[0702] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0703] Processing Step Description

[0704] Step 1:

[0705] The server instantiates the DataCollector class. As input, it receives the number of matches played and the number of points scored by each player. Specifically, it retrieves the data from an API or database and saves it in Pandas DataFrame format. This allows the data to be managed in a unified format. The output is data in Pandas DataFrame format.

[0706] Step 2:

[0707] The server instantiates the DataAnalyzer class. The input is the Pandas DataFrame data collected in step 1. The server uses the analyze_data method to first standardize the appearance data using StandardScaler. It then creates a linear regression model and generates a predictive model based on this model. The output is the predictive model.

[0708] Step 3:

[0709] The server instantiates the StrategySuggester class. The input is the prediction model generated in step 2. The server uses the suggest_strategy method to receive new player data as input, calculate predicted scores, and propose a strategy. Specifically, it inputs normalized game appearance data into the prediction model to predict scores. The output is the predicted strategy suggestion.

[0710] Step 4:

[0711] The user provides feedback on the proposed strategy by clicking a button indicating their level of satisfaction (e.g., happy, dissatisfied) with the proposed strategy. The input is the user's emotional data.

[0712] Step 5:

[0713] The server uses an emotion engine to collect user emotion data. The input is the user emotion data collected in step 4. The server readjusts the strategy based on this data. Specifically, it analyzes the emotion data and modifies the strategy if there is a high level of dissatisfaction. The output is a proposed adjusted strategy.

[0714] Step 6:

[0715] The terminal displays the final strategy proposal to the user. The input is the strategy proposal adjusted in step 5. The terminal presents the proposal to the user in an easy-to-understand format, allowing the user to take concrete action. The output is the strategy proposal displayed on the screen.

[0716] Through these steps, the system can collect and analyze player performance data, generate predictive models, and even suggest strategies that take the user's emotions into account.

[0717] (Application example 2)

[0718] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0719] Autonomous vehicles are required to recognize the driver's emotional state and provide an optimal driving strategy based on that. Such a system would contribute to reducing driver stress and promoting safe driving. However, conventional navigation systems have the problem of being unable to propose driving strategies that take the driver's emotional state into account and can only provide uniform route guidance.

[0720] 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.

[0721] In this invention, the server includes means for collecting data on the number of games played and the scores of players, means for analyzing the collected data and generating a prediction model, means for predicting new data using the generated prediction model and proposing a strategy, means for collecting and analyzing a user's emotions, and means for adjusting and proposing a strategy using the user's emotion data, thereby enabling the proposal of a driving strategy that takes into account the driver's emotional state.

[0722] "Player Appearances" refers to the total number of matches a player participates in during a particular period.

[0723] "Score data" refers to numerical information about the points scored by a player in a match.

[0724] "Collection Means" refers to the technical capabilities and methods used to capture and record player appearance and goal data.

[0725] "Means for analyzing and generating predictive models" refers to the technological capabilities and methods for analyzing collected data and creating mathematical and statistical models based on that data to predict future performance.

[0726] "Means for proposing strategies" refers to the technical capabilities and methods for evaluating new data and recommending optimal plans of action or courses of action based on the generated predictive models.

[0727] "Means for collecting and analyzing user emotions" refers to technical functions and methods for detecting and analyzing the emotional state of a user from their facial expressions and voice.

[0728] "Means for adjusting and proposing strategies using emotional data" refers to technical functions and methods for taking into account the emotional data of a user and selecting and proposing an optimal strategy.

[0729] "Standardization measures" refer to technical features or methods for converting collected data values ​​onto a consistent scale.

[0730] "Means for storing data in a data frame format" refers to the technical features and methods for storing collected data in a tabular format consisting of rows and columns.

[0731] This invention relates to a system that recognizes the driver's emotional state in real time and adjusts and proposes driving strategies based on that. This system is based on the collection and analysis of players' game appearances and score data, and analyzes and reflects the user's emotional data in real time to optimize navigation strategies while actually driving.

[0732] 1. Data Collection

[0733] The server collects the driver's facial expressions and tone of voice via the device's built-in camera and microphone. Specifically, it analyzes the facial expression data captured by the camera and the voice data collected by the microphone using an emotion recognition model. The emotion recognition model uses a model based on deep learning technology (such as TensorFlow or Keras).

[0734] 2. Data analysis

[0735] The server stores the collected emotion data in a data frame format (Pandas DataFrame). The emotion data is standardized (StandardScaler) to ensure consistency and then analyzed using a linear regression model (LinearRegression). This generates a predictive model based on the driver's emotional state.

[0736] 3. Strategy proposal and emotion recognition

[0737] The server uses an emotion prediction model to suggest a driving strategy that matches the driver's emotional state. Specifically, if the driver is stressed, the server suggests the shortest route, and if the driver is relaxed, it suggests a scenic route. This information is displayed on the device (smartphone or head-mounted display) and provided to the driver.

[0738] Specific examples

[0739] For example, if the system determines that the driver is stressed, the device will display "Suggest the shortest route." On the other hand, if the system determines that the driver is relaxed, it will display "Suggest the scenic route." This allows the driver to select the optimal driving route based on their emotional state.

[0740] Example prompts for generative AI models

[0741] "We need an app that suggests routes that help you relax while driving. It should recognize your emotions and suggest the best driving route based on them."

[0742] "Create a navigation system that suggests the shortest route when the driver is stressed, or a scenic route when the driver is relaxed."

[0743] The above is an embodiment of the invention, which makes it possible to propose a driving strategy that takes into account the emotional state of the driver.

[0744] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0745] Step 1:

[0746] The server collects the driver's facial expressions and tone of voice in real time through the camera and microphone built into the device. The input here is the camera video and audio data, and the output is that these data are sent to the server. The camera captures the driver's face, and the microphone picks up the audio.

[0747] Step 2:

[0748] The server inputs the collected facial and voice data into an emotion recognition model to analyze the driver's emotional state. The input here is the captured facial and voice data, and the output is the analysis result (emotional state) by the emotion recognition model. Deep learning libraries such as TensorFlow and Keras are used to evaluate emotions.

[0749] Step 3:

[0750] The server saves the parsed emotion data in Pandas DataFrame format. Here, the input is emotion data and the output is saved in DataFrame format. The Pandas library is used to structure the data to facilitate later analysis.

[0751] Step 4:

[0752] The server normalizes the stored data using StandardScaler. The input here is the emotion data stored in a data frame, and the output is the normalized data. StandardScaler is used to unify the scale of the data.

[0753] Step 5:

[0754] The server trains a linear regression model using the normalized data to generate a predictive model. Here, the input is the normalized data, and the output is a predictive model based on the driver's emotions. LinearRegression is used to build the predictive model.

[0755] Step 6:

[0756] The server uses the generated predictive model to predict the driver's emotional state and proposes a driving strategy based on it. The input here is the current emotional data, and the output is the optimal driving strategy. If the driver is relaxed, it will suggest a scenic route, and if the driver is stressed, it will suggest the shortest route.

[0757] Step 7:

[0758] The device displays the proposed driving strategy to the user, where the input is the driving strategy information sent from the server and the output is the displayed route proposal. The information is provided visually on the device's display or head-mounted display.

[0759] Through these steps, an optimal driving strategy that reflects the driver's emotional state is proposed.

[0760] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0761] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0762] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0763] [Fourth embodiment]

[0764] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0765] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0766] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0767] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0768] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0769] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0770] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0771] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0772] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0773] 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.

[0774] 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.

[0775] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0776] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0777] The present invention relates to a system for collecting data on the number of matches played and the number of points scored by players, and for analyzing, predicting, and proposing such data.

[0778] Data collection and storage

[0779] The server instantiates the DataCollector class and calls the collect_data method to collect player data. The collected data includes the number of matches played and points scored by each player. This data is saved in Pandas DataFrame format, making it easy to analyze later.

[0780] Data analysis

[0781] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. This analysis process first uses StandardScaler to standardize data such as game appearances, reducing data variability. It then uses a linear regression model to generate a score prediction model. This prediction model is used to predict future scores based on a player's past performance data.

[0782] Strategic proposal

[0783] The server then instantiates the StrategySuggester class and suggests a strategy using the new data. This new data could be, for example, new players or game appearances based on the upcoming game schedule. The server uses the prediction model to predict the score for the new data and suggests a strategy based on the prediction. If the score is high, the server suggests an "offensive strategy," and if the score is low, the server suggests a "defensive strategy."

[0784] Specific examples

[0785] For example, suppose a user inputs player data for 2023 into the system (15, 10, and 5 game appearances, with 300, 210, and 50 points, respectively). This data is collected by the server and used as the base data for generating a prediction model. Next, if the number of game appearances for a new member is input (e.g., 9 and 7 games), the server accepts this as new data and calculates the predicted points. For example, if the predicted points are 180 for 9 game appearances and 140 for 7 game appearances, the server will suggest a "defense-focused strategy" for each.

[0786] The terminal displays the results of these strategy proposals to the user, who can then use this information to plan specific training and match strategies for their players.

[0787] In this way, the system of the present invention efficiently and accurately collects and analyzes player appearance and score data, generates predictive models, and proposes strategies based on them, thereby significantly improving the performance of sports teams.

[0788] The processing flow will be explained below.

[0789] Step 1:

[0790] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of points scored by each player. Specifically, temporary data is generated and saved in the Pandas DataFrame format.

[0791] Step 2:

[0792] The server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. At this stage, as a data preprocessing step, it uses StandardScaler to standardize the appearance data. Then, it uses the standardized data to generate a linear regression model to predict points.

[0793] Step 3:

[0794] The server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on new data, such as the number of games played by a new player. The server inputs this new data into the prediction model and predicts the score.

[0795] Step 4:

[0796] The server proposes a strategy based on the predicted score. Specifically, if the predicted score is high, it proposes an "offense-oriented strategy," and if the predicted score is low, it proposes a "defense-oriented strategy."

[0797] Step 5:

[0798] The terminal displays the strategy proposals provided by the server to the user, who can then use them to plan specific training and match strategies for the players.

[0799] Through this process, the system can efficiently and accurately collect and analyze data, create predictive models, and propose strategies based on them, thereby contributing to improving the performance of sports organizations.

[0800] Example 1

[0801] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0802] This invention relates to a system that collects information on players' game appearances and scores, predicts their future performance based on this information, and proposes effective strategies. Conventional systems require manual data collection and analysis, which is inefficient and has limited accuracy. This makes it difficult to quickly develop effective strategies that can contribute to improving the performance of sports teams.

[0803] 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.

[0804] In this invention, the server includes a means for collecting information on the number of games played and the scores of players, a means for analyzing the collected information and generating a prediction model, and a means for predicting new information using the generated prediction model and proposing a strategy, thereby enabling the rapid and accurate collection and analysis of player performance information, the generation of a prediction model, and the proposing of an effective strategy.

[0805] "Athlete" means an individual or team member who takes part in a competition or sporting event.

[0806] "Appearances" is the number of matches or competitions an athlete takes part in within a specific period of time.

[0807] "Score information" refers to data on the points and scores that a player has earned in a match or competition.

[0808] "Means of collecting information" refers to the technical means by which servers and devices obtain information on the number of competitions and scores through APIs, databases, etc.

[0809] "Means for analyzing information" are technical means for processing collected data and identifying characteristics and trends.

[0810] The "means for generating a predictive model" refers to a means for creating a mathematical model for predicting future performance from past data using a machine learning algorithm.

[0811] "New information" refers to newly added data or circumstances that are not based on existing data.

[0812] "Means for proposing strategies" are technical means for formulating competition and training plans based on the results of the predictive model.

[0813] The "data frame format" is a tabular data structure consisting of rows and columns, and is a format that is particularly used when using the Pandas library.

[0814] "Standardization methods" are technical methods for adjusting data to reduce variability and make the mean zero and the standard deviation one.

[0815] This invention relates to a system that collects information on the number of matches played and the number of points scored by players, analyzes the data, generates a prediction model, and proposes strategies. This system is realized by a server, a terminal, and a user, each playing their own role.

[0816] Data collection and storage

[0817] To collect information on the number of matches played and the number of points scored by each player, the server instantiates a specific class (DataCollector class) and calls a specific method (collector_data method). Specifically, the server obtains the number of matches played and the number of points scored by each player from an API or database, and stores this information in Pandas DataFrame format. Pandas is a powerful Python data manipulation library and is an ideal data storage format.

[0818] Data analysis

[0819] The server then instantiates another class (DataAnalyzer class) and uses a specific method (analyze_data method) to analyze the collected information. This process begins by standardizing the data using StandardScaler. StandardScaler is a tool included in the scikit-learn library that converts the mean to 0 and the standard deviation to 1 to reduce data variability. This makes the data scale uniform, improving the accuracy of the predictive model.

[0820] Model Generation and Prediction

[0821] The server then generates a linear regression model to predict future scores based on a player's past performance data. The linear regression model is also implemented using the scikit-learn library. Based on the trained model, future scores are predicted when new data (such as the number of games played by a new player) is input. This allows sports organizations to develop strategies based on the predicted scores.

[0822] Strategic proposal

[0823] Next, the server instantiates the StrategySuggester class and suggests a strategy using the new data. This new data includes new players and the number of appearances based on the upcoming game schedule. The server uses the generated prediction model to predict the score for the new data and suggests a strategy based on the prediction results. If the score is high, it suggests an "offensive strategy," and if the score is low, it suggests a "defensive strategy."

[0824] Results display

[0825] The terminal displays the results of these strategy proposals to the user. Based on this information, the user can plan specific strategies for player training and matches. The terminal displays the results of the strategy proposals on the screen and provides them to the user by printing them out as needed.

[0826] Specific examples

[0827] For example, suppose a user inputs player data for 2023 into the system (15, 10, and 5 game appearances, with 300, 210, and 50 points, respectively). This data is collected by the server and becomes the base data for generating a prediction model. When the number of game appearances for a new member is input (e.g., 9 and 7 games), the server accepts this as new data and calculates the predicted points. For example, if the predicted points are 180 for 9 game appearances and 140 for 7 game appearances, a "defense-focused strategy" will be suggested for each.

[0828] Example prompt sentence:

[0829] "Based on the following data, please calculate the expected points for the new members based on the number of games they play and propose a strategy:

[0830] 2023 Player Data:

[0831] Matches played: 15, 10, 5

[0832] Points: 300, 210, 50

[0833] Number of matches played by new members:

[0834] 9 matches

[0835] Seven games.”

[0836] In this way, the system of the present invention can significantly improve the performance of sports teams by efficiently and accurately collecting and analyzing information on players' game appearances and points scored, generating predictive models, and proposing strategies based on those models.

[0837] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0838] Step 1: Data collection

[0839] The server instantiates the DataCollector class and calls the collect_data method. This method retrieves information about players' appearances and points from an API or database. For example, it retrieves data in JSON format from the API and extracts information about each player. Specifically, it collects information such as Player A's appearance in 15 games and his score of 300. The input is player data retrieved from the API endpoint, and the output is data in Pandas DataFrame format.

[0840] Step 2: Save data

[0841] The server saves the collected data in Pandas DataFrame format. The DataFrame format makes it easy to manipulate and analyze data. Specifically, it converts JSON data into a Pandas DataFrame and saves the number of matches played and points scored by each player in tabular format. The input is the data collected in Step 1, and the output is data in DataFrame format.

[0842] Step 3: Data Preprocessing

[0843] The server instantiates the DataAnalyzer class and preprocesses the data using the analyze_data method. In this process, the data is standardized using StandardScaler. The input is data in DataFrame format, and the output is the standardized data. Specifically, the variance of the number of games played and points scored is reduced, and the mean is converted to 0 and the standard deviation to 1.

[0844] Step 4: Model generation

[0845] The server generates a linear regression model. The input is the preprocessed data from step 3, and the output is a predictive model. Specifically, the scikit-learn library is used to train a predictive model based on past performance data. This model predicts points scored using the number of matches played as input.

[0846] Step 5: Predict

[0847] The server uses new data to make predictions. For example, it takes the number of games played by a new member as input and uses a prediction model to calculate future points. The input is new game play data, and the output is the predicted points. Specifically, it predicts 180 points in 9 games played, and 140 points in 7 games played.

[0848] Step 6: Strategic proposal

[0849] The server instantiates the StrategySuggester class and proposes a strategy based on the prediction results. The input is the score data predicted in step 5, and the output is the proposed strategy. Specifically, if the score is high, an "offensive strategy" is proposed, and if the score is low, a "defensive strategy" is proposed. For example, if the number of games played is 9, a defensive strategy is proposed.

[0850] Step 7: View the results

[0851] The terminal displays the results of the strategy proposal to the user. The input is the strategy proposed in step 6, and the output is the strategy information displayed to the user. Specifically, the server displays the strategy proposed by the server on the competition screen or training plan screen. The user uses this information to plan strategies for actual training or matches.

[0852] (Application example 1)

[0853] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0854] To efficiently improve the performance of robots used in factories, a system is needed that collects robot work data, analyzes it, and proposes optimal work strategies. However, current systems lack the ability to standardize data or generate appropriate predictive models, making it difficult to propose effective strategies.

[0855] 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.

[0856] In this invention, the server includes means for collecting robot task data and efficiency data, means for analyzing the collected data and generating a prediction model, and means for predicting new data using the generated prediction model and proposing a task strategy, thereby making it possible to propose an optimal task strategy for efficiently improving the robot's performance.

[0857] "Robot work data" is information about a series of tasks performed by a robot in a factory, and specifically includes numerical data such as how many times the robot performed each task.

[0858] "Efficiency data" is information that indicates the ratio of the results obtained to the time and resource usage of the work performed by the robot, and specifically includes the productivity and success rate per task.

[0859] The "collection means" is a combination of hardware and software for acquiring work data and efficiency data from each robot, and includes sensors and data collection programs.

[0860] "Means of analysis" refers to algorithms and programs used to analyze collected data, and to standardize data and recognize patterns.

[0861] A "means for generating a predictive model" is a mathematical and computational method for predicting future efficiency or performance based on past data, such as using a linear regression model.

[0862] The "means for proposing a work strategy" refers to a means for showing an optimal work plan based on the generated predictive model, and includes visualization tools and recommendation systems.

[0863] "Standardization means" refers to algorithms and programs that reduce data variability and convert data into a comparable form, such as StandardScaler.

[0864] "Means of saving in Pandas DataFrame format" refers to a method of storing collected data in a DataFrame object of the Pandas library, which facilitates subsequent data processing and analysis.

[0865] The present invention relates to a system that collects and analyzes work data and efficiency data of robots in a factory to propose optimal work strategies. This system provides a means for efficiently improving the performance of robots.

[0866] Data collection and storage

[0867] The server instantiates the DataCollector class and calls the collect_data method to collect robot work data and efficiency data. The collected data is saved in Pandas DataFrame format. Examples of data include the robot ID, number of tasks, and efficiency information. For example, data is collected where the robot ID is 1, the number of tasks is 10, and the efficiency is 90.

[0868] Data analysis

[0869] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. In this analysis process, it first uses StandardScaler to standardize the data. StandardScaler is used to reduce data variability. Then, it uses a linear regression model to generate an efficiency prediction model. This prediction model is used to predict future efficiency based on past work data.

[0870] Work strategy proposal

[0871] The server then instantiates the StrategySuggester class and proposes a work strategy using the new data. This new data could be, for example, the number of tasks performed by a new robot. The server uses the prediction model to predict the efficiency of the new data and proposes a work strategy based on the prediction results. If the efficiency is high, the server proposes a "high-efficiency work strategy," and if the efficiency is low, the server proposes an "improvement suggestion strategy."

[0872] Examples of specific examples and prompts

[0873] For example, suppose a user inputs new robot data (robot ID: 4, number of tasks: 8) into the system. This data is collected by the server and used as the base data for generating a prediction model. The server then receives this as new data and calculates the prediction efficiency. If the prediction efficiency is 70, the server will propose an "improvement proposal strategy." This information is useful for formulating specific work strategies for subsequent tasks.

[0874] An example of a prompt is as follows:

[0875] Predict the efficiency of robots IDs 4 and 5 in a factory when they process 8 and 12 tasks, respectively, and propose an optimal work strategy based on that.

[0876] In this way, the system of the present invention efficiently and accurately analyzes collected work data and efficiency data, generates a predictive model, and proposes an optimal work strategy based on the model, thereby improving the performance of robots in factories and increasing production efficiency.

[0877] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0878] Step 1:

[0879] The server instantiates the DataCollector class and calls the collect_data method. This collects robot work data and efficiency data. Specifically, information on each robot's ID, number of tasks, and efficiency is collected. For example, data such as robot ID 1, number of tasks 10, and efficiency 90 can be obtained. The collected data is saved in Pandas DataFrame format.

[0880] Step 2:

[0881] The server analyzes the collected data using an instance of the DataAnalyzer class. Specifically, it calls the analyze_data method to standardize the data. StandardScaler is used for standardization, and scaling is performed to reduce data variation. The collected data is given as input, and standardized data is obtained as output.

[0882] Step 3:

[0883] The server uses the standardized data to generate a predictive model. Specifically, it uses a linear regression model to build a model for predicting future efficiency based on past data. The analyzed data is divided into X and y, and a model is generated using LinearRegression. The input is the standardized data, and the output is a linear regression model for predicting efficiency.

[0884] Step 4:

[0885] The server uses an instance of the StrategySuggester class to suggest a work strategy for new data. Specifically, it calls the suggest_strategy method of the strategy_suggester instance, inputs the work data of a new robot, and predicts its efficiency. For example, if the new robot ID is 4 and the number of tasks is 8, its efficiency is predicted using the model, and the predicted efficiency is 70. The predicted efficiency is obtained as the output.

[0886] Step 5:

[0887] Based on the provided predicted efficiency, the server proposes an optimal work strategy. If the efficiency is high, it proposes a "high-efficiency work strategy," and if it is low, it proposes an "improvement proposal strategy." For example, if the efficiency is 70, it proposes the "improvement proposal strategy." This proposal information is sent to the terminal, and the user can use it to plan a specific work strategy.

[0888] An example of a prompt is as follows:

[0889] Predict the efficiency of robots IDs 4 and 5 in a factory when they process 8 and 12 tasks, respectively, and propose an optimal work strategy based on that.

[0890] In this way, a system is created to improve the performance of robots in a factory.

[0891] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0892] This invention relates to a system that collects data on the number of matches played and the number of points scored by players, and analyzes, predicts, and proposes strategies by combining this with an emotion engine that recognizes the emotions of the user, thereby making more appropriate strategy proposals.

[0893] Data collection and storage

[0894] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of goals scored by each player. This data is saved in a Pandas DataFrame format, making it easy to analyze later.

[0895] Data analysis

[0896] Next, the server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. During the analysis process, a StandardScaler is used to standardize the appearance data. A linear regression model is then used to generate a score prediction model. The prediction model is used to predict future scores based on a player's past performance data.

[0897] Strategy suggestions and emotion recognition

[0898] Next, the server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on the new data. Here, an emotion engine is added to recognize user emotions and collect emotion data, for example, when a user expresses dissatisfaction with a proposed strategy.

[0899] The server adjusts the strategy by taking into account the user's emotional data collected using the emotion engine. Specifically, the emotional data is reflected in the prediction model to propose a strategy that will satisfy the user. For example, if the user is dissatisfied with the proposed tactics, the server may adjust the strategy to one that emphasizes more defense.

[0900] Specific examples

[0901] For example, if a user inputs player data into the system (number of games played: 15, 10, 5, with points scored of 300, 210, 50, respectively), this data is collected by the server and used as the base data for generating a prediction model. If a user then inputs the number of games played by a new member (e.g., 9 games, 7 games), the server will accept this as new data and calculate the predicted points.

[0902] The server also uses an emotion engine to collect the user's emotional data (happiness, dissatisfaction, etc.). For example, if the predicted score is 180 and an "attack-focused tactic" is suggested, and the user expresses dissatisfaction with the suggestion, the emotion engine will feed that information back to the server. The server will then readjust the prediction model based on the emotional data and suggest a strategy that suits the user's emotions, such as switching to a "defense-focused tactic."

[0903] The terminal displays the final strategy proposal to the user, who can then use it to plan specific strategies for training players and matches.

[0904] In this way, by combining the emotion engine, it is possible to realize more flexible and effective strategy proposals that are not based solely on data but also take into account the user's emotions, which can greatly contribute to improving the performance of sports organizations.

[0905] The processing flow will be explained below.

[0906] Step 1:

[0907] The server instantiates the DataCollector class and calls the collect_data method to collect the number of matches played and the number of goals scored by each player. This data is saved in a Pandas DataFrame format, making it easy to analyze later.

[0908] Step 2:

[0909] The server instantiates the DataAnalyzer class and analyzes the collected data using the analyze_data method. At this stage, as a data preprocessing step, it uses StandardScaler to standardize the appearance data. Then, it builds a linear regression model using the standardized data to generate a model to predict points.

[0910] Step 3:

[0911] The server instantiates the StrategySuggester class and uses the suggest_strategy method to suggest a strategy based on new data, such as the number of games played by a new member. The server inputs this new data into the prediction model and predicts the score.

[0912] Step 4:

[0913] The server instantiates an emotion engine to collect the user's emotion data. Specifically, the engine recognizes the user's emotion toward the strategy proposal (e.g., joy, dissatisfaction, etc.) and transmits the data to the server.

[0914] Step 5:

[0915] The server readjusts the strategy proposals based on the user's emotional data provided by the emotion engine. For example, if the predicted score is 180 and an "attack-focused strategy" is proposed, and the user expresses dissatisfaction, the server will readjust the prediction model based on that information and propose a "defense-focused strategy" instead.

[0916] Step 6:

[0917] The terminal displays the final strategy proposal to the user, who can then use the proposal to plan specific training and match strategies for the players.

[0918] In this way, by combining the emotion engine, it becomes possible to propose more flexible and effective strategies that are not only based on data but also take into account the emotions of the user, which will greatly contribute to improving the performance of sports organizations.

[0919] Example 2

[0920] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0921] Conventional player performance analysis systems are limited to collecting and analyzing data on the number of matches played and points scored, and have the problem of being unable to propose appropriate strategies that take the user's emotions into account. As a result, users may be dissatisfied with the proposed strategies, and optimal performance improvements may not be achieved.

[0922] 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.

[0923] In this invention, the server includes means for collecting data on the number of matches played and the number of points scored by players, means for analyzing the collected data and generating a prediction model, means for predicting new data using the generated prediction model and proposing a strategy, and means for recognizing the user's emotions and adjusting the strategy based on the emotion data, thereby enabling more appropriate strategy proposals that are based not only on data but also on the user's emotions.

[0924] "Player appearances" refers to the number of times a player has appeared in an official match.

[0925] "Score Data" refers to information regarding the scores scored by a player during a match.

[0926] "Collection means" refers to the technological devices or functions used to capture and store information such as player appearances and goalscoring data.

[0927] "Analyzing means" refers to the technical devices or capabilities used to analyze collected data and extract useful information or patterns.

[0928] "Predictive Model" means a mathematical or statistical model used to forecast future events or outcomes based on data collected in the past.

[0929] "Means for proposing strategies" refers to a technical device or function for proposing methods of competition or training based on the results of a predictive model.

[0930] "Means for recognizing user emotions" refers to a technical device or function for detecting the user's emotional state (happiness, dissatisfaction, etc.) and capturing it as data.

[0931] "Emotion data" refers to data that expresses the user's emotional state as numerical values ​​or categories.

[0932] "Means for adjusting strategy based on emotional data" refers to a technical device or function that takes into account the collected emotional data of users, recalculates the optimal strategy, and adjusts the content of suggestions.

[0933] "Standardization means" refers to a technical device or function that equalizes data variability and makes data on different scales comparable.

[0934] "Tabular" refers to data arranged in a regular pattern of rows and columns.

[0935] "Storage means" refers to technical devices or functions that record and store collected or generated data in a form that can be accessed at a later date.

[0936] This invention relates to a system that collects data on the number of matches played and the number of points scored by players, analyzes and predicts the results, and proposes strategies that take into account the user's emotions. This system is realized through processing between a server, a terminal, and a user.

[0937] The server first instantiates the DataCollector class and uses the collect_data method to collect data on players' appearances and goals. This data is then saved in Pandas DataFrame format using Pandas, a Python data analysis library. This makes it easier to manage the data and perform subsequent analysis.

[0938] The server then instantiates the DataAnalyzer class and analyzes the data using the analyze_data method. Specifically, it uses StandardScaler to standardize the appearance data and then uses a linear regression model to generate a model for predicting points. The model is used to predict future points based on a player's past performance data.

[0939] The server then instantiates the StrategySuggester class and uses the suggest_strategy method to propose a strategy based on the new data. At this stage, an emotion engine is added to recognize the user's emotions. Specifically, if the user expresses dissatisfaction with the proposed strategy, the emotion data is collected. The server then adjusts the strategy based on the emotion data and makes a proposal that satisfies the user.

[0940] For example, suppose a user inputs the following player data into the system: number of matches played: 15, 10, 5, with respective scores of 300, 210, 50. This data is collected by the server and becomes the basis for the prediction model. If a new member later inputs the number of matches played (e.g., 9 matches, 7 matches), the server will accept this as new data and calculate the predicted score. At this time, the emotion engine will collect the user's emotional data (e.g., dissatisfaction), and the server will readjust the strategy based on that data. For example, if an "attack-focused tactic" is proposed but the user expresses dissatisfaction, the server may switch to a "defense-focused tactic" based on the emotional data.

[0941] The terminal displays the final strategy proposal sent from the server to the user, who can then use it to plan specific training and match strategies for the players.

[0942] Examples of prompts include:

[0943] Enter player data:

[0944] Matches played: 15, 10, 5

[0945] Points: 300, 210, 50

[0946] Number of games played by new members: 9, 7

[0947] Emotional data: Dissatisfaction

[0948] Based on this prompt, the server can collect, analyze, and predict data, and adjust strategies based on emotional data, and then suggest the optimal strategy to the user.

[0949] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0950] Processing Step Description

[0951] Step 1:

[0952] The server instantiates the DataCollector class. As input, it receives the number of matches played and the number of points scored by each player. Specifically, it retrieves the data from an API or database and saves it in Pandas DataFrame format. This allows the data to be managed in a unified format. The output is data in Pandas DataFrame format.

[0953] Step 2:

[0954] The server instantiates the DataAnalyzer class. The input is the Pandas DataFrame data collected in step 1. The server uses the analyze_data method to first standardize the appearance data using StandardScaler. It then creates a linear regression model and generates a predictive model based on this model. The output is the predictive model.

[0955] Step 3:

[0956] The server instantiates the StrategySuggester class. The input is the prediction model generated in step 2. The server uses the suggest_strategy method to receive new player data as input, calculate predicted scores, and propose a strategy. Specifically, it inputs normalized game appearance data into the prediction model to predict scores. The output is the predicted strategy suggestion.

[0957] Step 4:

[0958] The user provides feedback on the proposed strategy by clicking a button indicating their level of satisfaction (e.g., happy, dissatisfied) with the proposed strategy. The input is the user's emotional data.

[0959] Step 5:

[0960] The server uses an emotion engine to collect user emotion data. The input is the user emotion data collected in step 4. The server readjusts the strategy based on this data. Specifically, it analyzes the emotion data and modifies the strategy if there is a high level of dissatisfaction. The output is a proposed adjusted strategy.

[0961] Step 6:

[0962] The terminal displays the final strategy proposal to the user. The input is the strategy proposal adjusted in step 5. The terminal presents the proposal to the user in an easy-to-understand format, allowing the user to take concrete action. The output is the strategy proposal displayed on the screen.

[0963] Through these steps, the system can collect and analyze player performance data, generate predictive models, and even suggest strategies that take the user's emotions into account.

[0964] (Application example 2)

[0965] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0966] Autonomous vehicles are required to recognize the driver's emotional state and provide an optimal driving strategy based on that. Such a system would contribute to reducing driver stress and promoting safe driving. However, conventional navigation systems have the problem of being unable to propose driving strategies that take the driver's emotional state into account and can only provide uniform route guidance.

[0967] 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.

[0968] In this invention, the server includes means for collecting data on the number of games played and the scores of players, means for analyzing the collected data and generating a prediction model, means for predicting new data using the generated prediction model and proposing a strategy, means for collecting and analyzing a user's emotions, and means for adjusting and proposing a strategy using the user's emotion data, thereby enabling the proposal of a driving strategy that takes into account the driver's emotional state.

[0969] "Player Appearances" refers to the total number of matches a player participates in during a particular period.

[0970] "Score data" refers to numerical information about the points scored by a player in a match.

[0971] "Collection Means" refers to the technical capabilities and methods used to capture and record player appearance and goal data.

[0972] "Means for analyzing and generating predictive models" refers to the technological capabilities and methods for analyzing collected data and creating mathematical and statistical models based on that data to predict future performance.

[0973] "Means for proposing strategies" refers to the technical capabilities and methods for evaluating new data and recommending optimal plans of action or courses of action based on the generated predictive models.

[0974] "Means for collecting and analyzing user emotions" refers to technical functions and methods for detecting and analyzing the emotional state of a user from their facial expressions and voice.

[0975] "Means for adjusting and proposing strategies using emotional data" refers to technical functions and methods for taking into account the emotional data of a user and selecting and proposing an optimal strategy.

[0976] "Standardization measures" refer to technical features or methods for converting collected data values ​​onto a consistent scale.

[0977] "Means for storing data in a data frame format" refers to the technical features and methods for storing collected data in a tabular format consisting of rows and columns.

[0978] This invention relates to a system that recognizes the driver's emotional state in real time and adjusts and proposes driving strategies based on that. This system is based on the collection and analysis of players' game appearances and score data, and analyzes and reflects the user's emotional data in real time to optimize navigation strategies while actually driving.

[0979] 1. Data Collection

[0980] The server collects the driver's facial expressions and tone of voice via the device's built-in camera and microphone. Specifically, it analyzes the facial expression data captured by the camera and the voice data collected by the microphone using an emotion recognition model. The emotion recognition model uses a model based on deep learning technology (such as TensorFlow or Keras).

[0981] 2. Data analysis

[0982] The server stores the collected emotion data in a data frame format (Pandas DataFrame). The emotion data is standardized (StandardScaler) to ensure consistency and then analyzed using a linear regression model (LinearRegression). This generates a predictive model based on the driver's emotional state.

[0983] 3. Strategy proposal and emotion recognition

[0984] The server uses an emotion prediction model to suggest a driving strategy that matches the driver's emotional state. Specifically, if the driver is stressed, the server suggests the shortest route, and if the driver is relaxed, it suggests a scenic route. This information is displayed on the device (smartphone or head-mounted display) and provided to the driver.

[0985] Specific examples

[0986] For example, if the system determines that the driver is stressed, the device will display "Suggest the shortest route." On the other hand, if the system determines that the driver is relaxed, it will display "Suggest the scenic route." This allows the driver to select the optimal driving route based on their emotional state.

[0987] Example prompts for generative AI models

[0988] "We need an app that suggests routes that help you relax while driving. It should recognize your emotions and suggest the best driving route based on them."

[0989] "Create a navigation system that suggests the shortest route when the driver is stressed, or a scenic route when the driver is relaxed."

[0990] The above is an embodiment of the invention, which makes it possible to propose a driving strategy that takes into account the emotional state of the driver.

[0991] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0992] Step 1:

[0993] The server collects the driver's facial expressions and tone of voice in real time through the camera and microphone built into the device. The input here is the camera video and audio data, and the output is that these data are sent to the server. The camera captures the driver's face, and the microphone picks up the audio.

[0994] Step 2:

[0995] The server inputs the collected facial and voice data into an emotion recognition model to analyze the driver's emotional state. The input here is the captured facial and voice data, and the output is the analysis result (emotional state) by the emotion recognition model. Deep learning libraries such as TensorFlow and Keras are used to evaluate emotions.

[0996] Step 3:

[0997] The server saves the parsed emotion data in Pandas DataFrame format. Here, the input is emotion data and the output is saved in DataFrame format. The Pandas library is used to structure the data to facilitate later analysis.

[0998] Step 4:

[0999] The server normalizes the stored data using StandardScaler. The input here is the emotion data stored in a data frame, and the output is the normalized data. StandardScaler is used to unify the scale of the data.

[1000] Step 5:

[1001] The server trains a linear regression model using the normalized data to generate a predictive model. Here, the input is the normalized data, and the output is a predictive model based on the driver's emotions. LinearRegression is used to build the predictive model.

[1002] Step 6:

[1003] The server uses the generated predictive model to predict the driver's emotional state and proposes a driving strategy based on it. The input here is the current emotional data, and the output is the optimal driving strategy. If the driver is relaxed, it will suggest a scenic route, and if the driver is stressed, it will suggest the shortest route.

[1004] Step 7:

[1005] The device displays the proposed driving strategy to the user, where the input is the driving strategy information sent from the server and the output is the displayed route proposal. The information is provided visually on the device's display or head-mounted display.

[1006] Through these steps, an optimal driving strategy that reflects the driver's emotional state is proposed.

[1007] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1008] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1009] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1010] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1011] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1012] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1013] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1014] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1015] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1016] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1017] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1018] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1019] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1020] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1021] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1022] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1023] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1024] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1025] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1026] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1027] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1028] The following is further disclosed regarding the above embodiment.

[1029] (Claim 1)

[1030] a means for collecting player appearance and goal data;

[1031] means for analyzing the collected data and generating predictive models;

[1032] A means for predicting new data using the generated predictive model and proposing strategies;

[1033] A system including:

[1034] (Claim 2)

[1035] 10. The system according to claim 1, further comprising means for performing standardization as a preprocessing of the data.

[1036] (Claim 3)

[1037] 10. The system of claim 1, further comprising means for saving the collected data in a Pandas DataFrame format.

[1038] "Example 1"

[1039] (Claim 1)

[1040] a means for collecting player appearance and score information;

[1041] means for analyzing the collected information and generating a predictive model;

[1042] A means for predicting new information and proposing strategies using the generated predictive model;

[1043] A means for storing the collected information in a data frame format;

[1044] A means for proposing a strategy based on unknown information using the generated predictive model;

[1045] A system including:

[1046] (Claim 2)

[1047] 10. The system of claim 1, further comprising means for standardizing the collected information.

[1048] (Claim 3)

[1049] 10. The system of claim 1, further comprising means for storing the collected information in a data frame format.

[1050]

[1051] "Application Example 1"

[1052] (Claim 1)

[1053] means for collecting robot work data and efficiency data;

[1054] means for analyzing the collected data and generating predictive models;

[1055] a means for predicting new data using the generated predictive model and proposing a work strategy;

[1056] A system including:

[1057] (Claim 2)

[1058] The system of claim 1, further comprising means for performing standardization as a preprocessing of the data.

[1059] (Claim 3)

[1060] 10. The system of claim 1, further comprising means for saving the collected data in a Pandas DataFrame format.

[1061] "Example 2: Combining Emotion Engines"

[1062] New Claims

[1063] (Claim 1)

[1064] a means for collecting player appearance and goal data;

[1065] means for analyzing the collected data and generating predictive models;

[1066] A means for predicting new data using the generated predictive model and proposing strategies;

[1067] a means for recognizing user emotions and adjusting strategies based on the emotion data;

[1068] A system including:

[1069] (Claim 2)

[1070] 10. The system according to claim 1, further comprising means for performing standardization as a preprocessing of the data.

[1071] (Claim 3)

[1072] 10. The system of claim 1, further comprising means for storing the collected data in tabular form.

[1073] "Application example 2 when combining emotion engines"

[1074] (Claim 1)

[1075] a means for collecting player appearance and goal data;

[1076] means for analyzing the collected data and generating predictive models;

[1077] A means for predicting new data using the generated predictive model and proposing strategies;

[1078] means for collecting and analyzing user emotions;

[1079] a means for adjusting and suggesting strategies using user emotional data;

[1080] A system including:

[1081] (Claim 2)

[1082] 10. The system according to claim 1, further comprising means for performing standardization as a preprocessing of the data.

[1083] (Claim 3)

[1084] 10. The system of claim 1, further comprising means for storing the collected data in a data frame format. [Explanation of symbols]

[1085] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting player appearance and goal data; means for analyzing the collected data and generating predictive models; A means for predicting new data using the generated predictive model and proposing strategies; A system including:

2. 2. The system according to claim 1, further comprising means for performing standardization as a preprocessing of the data.

3. The system of claim 1 , further comprising means for saving the collected data in a Pandas DataFrame format.

Images